From 4623a614e87e4f2df08c83b5b9f68af394951dc9 Mon Sep 17 00:00:00 2001 From: Koro Chen Date: Tue, 23 Jun 2015 19:01:20 +0800 Subject: [PATCH 001/428] ASoC: mediatek: Fix unbalanced calls to runtime suspend/resume This adds call to runtime suspend in dev remove. It fixs the problem that suspend is not called in the case of CONFIG_PM=n. It also fixs build warning when CONFIG_PM=n. Signed-off-by: Koro Chen Signed-off-by: Mark Brown --- sound/soc/mediatek/mtk-afe-pcm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/soc/mediatek/mtk-afe-pcm.c b/sound/soc/mediatek/mtk-afe-pcm.c index cc228db5fb76..9863da73dfe0 100644 --- a/sound/soc/mediatek/mtk-afe-pcm.c +++ b/sound/soc/mediatek/mtk-afe-pcm.c @@ -1199,6 +1199,8 @@ err_pm_disable: static int mtk_afe_pcm_dev_remove(struct platform_device *pdev) { pm_runtime_disable(&pdev->dev); + if (!pm_runtime_status_suspended(&pdev->dev)) + mtk_afe_runtime_suspend(&pdev->dev); snd_soc_unregister_component(&pdev->dev); snd_soc_unregister_platform(&pdev->dev); return 0; From ffacb48e5a4665d3d7286babb38a5af855a36bc0 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Fri, 26 Jun 2015 10:39:43 +0100 Subject: [PATCH 002/428] ASoC: dapm: Fix deadlock on auto-disable mux controls The commit 02aa78abec6e ("ASoC: DAPM: Add APIs to create individual DAPM controls.") added locking to the snd_soc_dapm_new_control function but did not update the call to snd_soc_dapm_new_control in the auto-disable mux code, this appears to be because the patches were sent at fairly similar times. This patch change the call in the auto-disable mux code to use the new snd_soc_dapm_new_control_unlocked function instead. Signed-off-by: Charles Keepax Signed-off-by: Mark Brown --- sound/soc/soc-dapm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index aa327c92480c..a47a8ce7a5ea 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -389,8 +389,8 @@ static int dapm_kcontrol_data_alloc(struct snd_soc_dapm_widget *widget, data->value = template.on_val; - data->widget = snd_soc_dapm_new_control(widget->dapm, - &template); + data->widget = snd_soc_dapm_new_control_unlocked( + widget->dapm, &template); if (!data->widget) { ret = -ENOMEM; goto err_name; From 30b03d05e07467b8c6ec683ea96b5bffcbcd3931 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Marczykowski-G=C3=B3recki?= Date: Fri, 26 Jun 2015 03:28:24 +0200 Subject: [PATCH 003/428] xen/gntdevt: Fix race condition in gntdev_release() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit While gntdev_release() is called the MMU notifier is still registered and can traverse priv->maps list even if no pages are mapped (which is the case -- gntdev_release() is called after all). But gntdev_release() will clear that list, so make sure that only one of those things happens at the same time. Signed-off-by: Marek Marczykowski-Górecki Cc: Signed-off-by: David Vrabel --- drivers/xen/gntdev.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 67b9163db718..0dbb222daaf1 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -568,12 +568,14 @@ static int gntdev_release(struct inode *inode, struct file *flip) pr_debug("priv %p\n", priv); + mutex_lock(&priv->lock); while (!list_empty(&priv->maps)) { map = list_entry(priv->maps.next, struct grant_map, next); list_del(&map->next); gntdev_put_map(NULL /* already removed */, map); } WARN_ON(!list_empty(&priv->freeable_maps)); + mutex_unlock(&priv->lock); if (use_ptemod) mmu_notifier_unregister(&priv->mn, priv->mm); From 7084ffbff494669b06ceb457150c38887e26d2a3 Mon Sep 17 00:00:00 2001 From: Liam Girdwood Date: Mon, 29 Jun 2015 17:36:43 +0100 Subject: [PATCH 004/428] ASoC: topology: Fix TLV size calculation. TLV size calculation was incorrectly calculated. Fix this according to include/sound/tlv.h Signed-off-by: Liam Girdwood Signed-off-by: Mark Brown --- sound/soc/soc-topology.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index d0960683c409..7a19df313fe8 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -580,27 +580,26 @@ static int soc_tplg_init_kcontrol(struct soc_tplg *tplg, } static int soc_tplg_create_tlv(struct soc_tplg *tplg, - struct snd_kcontrol_new *kc, u32 tlv_size) + struct snd_kcontrol_new *kc, struct snd_soc_tplg_ctl_tlv *tplg_tlv) { - struct snd_soc_tplg_ctl_tlv *tplg_tlv; struct snd_ctl_tlv *tlv; + int size; - if (tlv_size == 0) + if (tplg_tlv->count == 0) return 0; - tplg_tlv = (struct snd_soc_tplg_ctl_tlv *) tplg->pos; - tplg->pos += tlv_size; - - tlv = kzalloc(sizeof(*tlv) + tlv_size, GFP_KERNEL); + size = ((tplg_tlv->count + (sizeof(unsigned int) - 1)) & + ~(sizeof(unsigned int) - 1)); + tlv = kzalloc(sizeof(*tlv) + size, GFP_KERNEL); if (tlv == NULL) return -ENOMEM; dev_dbg(tplg->dev, " created TLV type %d size %d bytes\n", - tplg_tlv->numid, tplg_tlv->size); + tplg_tlv->numid, size); tlv->numid = tplg_tlv->numid; - tlv->length = tplg_tlv->size; - memcpy(tlv->tlv, tplg_tlv + 1, tplg_tlv->size); + tlv->length = size; + memcpy(&tlv->tlv[0], tplg_tlv->data, size); kc->tlv.p = (void *)tlv; return 0; @@ -773,7 +772,7 @@ static int soc_tplg_dmixer_create(struct soc_tplg *tplg, unsigned int count, } /* create any TLV data */ - soc_tplg_create_tlv(tplg, &kc, mc->hdr.tlv_size); + soc_tplg_create_tlv(tplg, &kc, &mc->tlv); /* register control here */ err = soc_tplg_add_kcontrol(tplg, &kc, From 9c3a473220dda073603a24e93d3015322bda950a Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Mon, 29 Jun 2015 17:36:45 +0100 Subject: [PATCH 005/428] ASoC: topology: fix typos in topology header Signed-off-by: Vinod Koul Signed-off-by: Mark Brown --- include/uapi/sound/asoc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h index 12215205ab8d..785c5ca0994b 100644 --- a/include/uapi/sound/asoc.h +++ b/include/uapi/sound/asoc.h @@ -110,7 +110,7 @@ /* * Block Header. - * This header preceeds all object and object arrays below. + * This header precedes all object and object arrays below. */ struct snd_soc_tplg_hdr { __le32 magic; /* magic number */ @@ -222,7 +222,7 @@ struct snd_soc_tplg_stream_config { /* * Manifest. List totals for each payload type. Not used in parsing, but will * be passed to the component driver before any other objects in order for any - * global componnent resource allocations. + * global component resource allocations. * * File block representation for manifest :- * +-----------------------------------+----+ From 93aa6c7bbc4124c8361c26a8b2c5c40afb185619 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 3 Jul 2015 09:28:09 -0400 Subject: [PATCH 006/428] SUNRPC: Don't reencode message if transmission failed with ENOBUFS If we're running out of buffer memory when transmitting data, then we want to just delay for a moment, and then continue transmitting the remainder of the message. Signed-off-by: Trond Myklebust --- net/sunrpc/clnt.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index cbc6af923dd1..23608eb0ded2 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1902,6 +1902,7 @@ call_transmit_status(struct rpc_task *task) switch (task->tk_status) { case -EAGAIN: + case -ENOBUFS: break; default: dprint_status(task); @@ -1928,7 +1929,6 @@ call_transmit_status(struct rpc_task *task) case -ECONNABORTED: case -EADDRINUSE: case -ENOTCONN: - case -ENOBUFS: case -EPIPE: rpc_task_force_reencode(task); } @@ -2057,12 +2057,13 @@ call_status(struct rpc_task *task) case -ECONNABORTED: rpc_force_rebind(clnt); case -EADDRINUSE: - case -ENOBUFS: rpc_delay(task, 3*HZ); case -EPIPE: case -ENOTCONN: task->tk_action = call_bind; break; + case -ENOBUFS: + rpc_delay(task, HZ>>2); case -EAGAIN: task->tk_action = call_transmit; break; From b5872f0c67edf3714dd46f04d73c3644f3addaf9 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 3 Jul 2015 09:32:23 -0400 Subject: [PATCH 007/428] SUNRPC: Don't confuse ENOBUFS with a write_space issue ENOBUFS means that memory allocations are failing due to an actual low memory situation. It should not be confused with being out of socket buffer space. Handle the problem by just punting to the delay in call_status. Reported-by: Neil Brown Signed-off-by: Trond Myklebust --- net/sunrpc/xprtsock.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index ee359fc7af16..44c1927b68c7 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -539,6 +539,7 @@ static int xs_local_send_request(struct rpc_task *task) switch (status) { case -ENOBUFS: + break; case -EAGAIN: status = xs_nospace(task); break; @@ -692,7 +693,6 @@ static int xs_tcp_send_request(struct rpc_task *task) status = -ENOTCONN; /* Should we call xs_close() here? */ break; - case -ENOBUFS: case -EAGAIN: status = xs_nospace(task); break; @@ -703,6 +703,7 @@ static int xs_tcp_send_request(struct rpc_task *task) case -ECONNREFUSED: case -ENOTCONN: case -EADDRINUSE: + case -ENOBUFS: case -EPIPE: clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags); } From 8b895ce652dc73bcf42a0c24acfc0708a06ea7c3 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 5 Jul 2015 15:12:06 -0400 Subject: [PATCH 008/428] NFSv4.1: Handle SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED status bit correctly. If the server tells us that only some state has been revoked, then we need to run the full TEST_STATEID dog and pony show in order to discover which locks and delegations are still OK. Currently we blow away all state, which means that we lose all locks! Signed-off-by: Trond Myklebust --- fs/nfs/nfs4state.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 605840dc89cf..f76916169b5f 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -2191,12 +2191,20 @@ static void nfs41_handle_server_reboot(struct nfs_client *clp) } } -static void nfs41_handle_state_revoked(struct nfs_client *clp) +static void nfs41_handle_all_state_revoked(struct nfs_client *clp) { nfs4_reset_all_state(clp); dprintk("%s: state revoked on server %s\n", __func__, clp->cl_hostname); } +static void nfs41_handle_some_state_revoked(struct nfs_client *clp) +{ + nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_nograce); + nfs4_schedule_state_manager(clp); + + dprintk("%s: state revoked on server %s\n", __func__, clp->cl_hostname); +} + static void nfs41_handle_recallable_state_revoked(struct nfs_client *clp) { /* This will need to handle layouts too */ @@ -2231,10 +2239,11 @@ void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags) if (flags & SEQ4_STATUS_RESTART_RECLAIM_NEEDED) nfs41_handle_server_reboot(clp); - if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED | - SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED | + if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED)) + nfs41_handle_all_state_revoked(clp); + if (flags & (SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED | SEQ4_STATUS_ADMIN_STATE_REVOKED)) - nfs41_handle_state_revoked(clp); + nfs41_handle_some_state_revoked(clp); if (flags & SEQ4_STATUS_LEASE_MOVED) nfs4_schedule_lease_moved_recovery(clp); if (flags & SEQ4_STATUS_RECALLABLE_STATE_REVOKED) From 4099287feb5833c24b5a91e1fe55207cf7559350 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 5 Jul 2015 15:20:53 -0400 Subject: [PATCH 009/428] NFSv4.1: Handle SEQ4_STATUS_RECALLABLE_STATE_REVOKED status bit correctly Try to handle this for now by invalidating all outstanding layouts for this server and then testing all the open+lock+delegation stateids. At some later stage, we may want to optimise by separating out the testing of delegation stateids only, and adding testing of layout stateids. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4state.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index f76916169b5f..469452996154 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -2207,8 +2207,10 @@ static void nfs41_handle_some_state_revoked(struct nfs_client *clp) static void nfs41_handle_recallable_state_revoked(struct nfs_client *clp) { - /* This will need to handle layouts too */ - nfs_expire_all_delegations(clp); + /* FIXME: For now, we destroy all layouts. */ + pnfs_destroy_all_layouts(clp); + /* FIXME: For now, we test all delegations+open state+locks. */ + nfs41_handle_some_state_revoked(clp); dprintk("%s: Recallable state revoked on server %s!\n", __func__, clp->cl_hostname); } From b13529059cf782f9b4e4ac0ca9d524bd922163da Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 5 Jul 2015 15:26:58 -0400 Subject: [PATCH 010/428] NFSv4.1: Handle SEQ4_STATUS_BACKCHANNEL_FAULT correctly RFC5661 states: The server has encountered an unrecoverable fault with the backchannel (e.g., it has lost track of the sequence ID for a slot in the backchannel). The client MUST stop sending more requests on the session's fore channel, wait for all outstanding requests to complete on the fore and back channel, and then destroy the session. Ensure we do so... Signed-off-by: Trond Myklebust --- fs/nfs/nfs4state.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 469452996154..f2e2ad894461 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -2217,9 +2217,9 @@ static void nfs41_handle_recallable_state_revoked(struct nfs_client *clp) static void nfs41_handle_backchannel_fault(struct nfs_client *clp) { - nfs_expire_all_delegations(clp); - if (test_and_set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) == 0) - nfs4_schedule_state_manager(clp); + set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state); + nfs4_schedule_state_manager(clp); + dprintk("%s: server %s declared a backchannel fault\n", __func__, clp->cl_hostname); } From b15c7cdde4991be5058f442c6d08d404d56f662c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 5 Jul 2015 15:01:36 -0400 Subject: [PATCH 011/428] NFSv4.1: nfs41_sequence_done should handle sequence flag errors Instead of just kicking off lease recovery, we should look into the sequence flag errors and handle them. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 6f228b5af819..1607b41a6d84 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -616,8 +616,7 @@ int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res) clp = session->clp; do_renew_lease(clp, res->sr_timestamp); /* Check sequence flags */ - if (res->sr_status_flags != 0) - nfs4_schedule_lease_recovery(clp); + nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags); nfs41_update_target_slotid(slot->table, slot, res); break; case 1: From be824167e33a8b747423c90f72479deb03255d54 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 5 Jul 2015 14:50:46 -0400 Subject: [PATCH 012/428] NFSv4: Leases are renewed in sequence_done when we have sessions Ensure that the calls to renew_lease() in open_done() etc. only apply to session-less versions of NFSv4.x (i.e. NFSv4.0). Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 1607b41a6d84..9f24238032f8 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -467,7 +467,10 @@ static void do_renew_lease(struct nfs_client *clp, unsigned long timestamp) static void renew_lease(const struct nfs_server *server, unsigned long timestamp) { - do_renew_lease(server->nfs_client, timestamp); + struct nfs_client *clp = server->nfs_client; + + if (!nfs4_has_session(clp)) + do_renew_lease(clp, timestamp); } struct nfs4_call_sync_data { @@ -7572,13 +7575,8 @@ static int nfs4_proc_sequence(struct nfs_client *clp, struct rpc_cred *cred) goto out; } ret = rpc_wait_for_completion_task(task); - if (!ret) { - struct nfs4_sequence_res *res = task->tk_msg.rpc_resp; - - if (task->tk_status == 0) - nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags); + if (!ret) ret = task->tk_status; - } rpc_put_task(task); out: dprintk("<-- %s status=%d\n", __func__, ret); From e50b1e06b79e9d51efbff9627b4dd407184ef43f Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Mon, 6 Jul 2015 17:01:24 +0200 Subject: [PATCH 013/428] ASoC: dapm: Lock during userspace access The DAPM lock must be held when accessing the DAPM graph status through sysfs or debugfs, otherwise concurrent changes to the graph can result in undefined behaviour. Signed-off-by: Lars-Peter Clausen Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- sound/soc/soc-dapm.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index a47a8ce7a5ea..1779430013ea 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -1952,6 +1952,7 @@ static ssize_t dapm_widget_power_read_file(struct file *file, size_t count, loff_t *ppos) { struct snd_soc_dapm_widget *w = file->private_data; + struct snd_soc_card *card = w->dapm->card; char *buf; int in, out; ssize_t ret; @@ -1961,6 +1962,8 @@ static ssize_t dapm_widget_power_read_file(struct file *file, if (!buf) return -ENOMEM; + mutex_lock(&card->dapm_mutex); + /* Supply widgets are not handled by is_connected_{input,output}_ep() */ if (w->is_supply) { in = 0; @@ -2007,6 +2010,8 @@ static ssize_t dapm_widget_power_read_file(struct file *file, p->sink->name); } + mutex_unlock(&card->dapm_mutex); + ret = simple_read_from_buffer(user_buf, count, ppos, buf, ret); kfree(buf); @@ -2281,11 +2286,15 @@ static ssize_t dapm_widget_show(struct device *dev, struct snd_soc_pcm_runtime *rtd = dev_get_drvdata(dev); int i, count = 0; + mutex_lock(&rtd->card->dapm_mutex); + for (i = 0; i < rtd->num_codecs; i++) { struct snd_soc_codec *codec = rtd->codec_dais[i]->codec; count += dapm_widget_show_codec(codec, buf + count); } + mutex_unlock(&rtd->card->dapm_mutex); + return count; } From 8bc76c8bf6e5d96985eb05afe1b94699d580eb68 Mon Sep 17 00:00:00 2001 From: "Fang, Yang A" Date: Mon, 6 Jul 2015 14:12:38 -0700 Subject: [PATCH 014/428] ASoC: Intel: fix incorrect widget name We should use "HiFi Playback" and "HiFi Capture".it will fix below err cht-bsw-max98090: ASoC: no sink widget found for AIF1 Playback cht-bsw-max98090: ASoC: Failed to add route ssp2 Tx -> direct -> AIF1 Playback cht-bsw-max98090: ASoC: no source widget found for AIF1 Capture cht-bsw-max98090: ASoC: Failed to add route AIF1 Capture -> direct -> ssp2 Rx Signed-off-by: Fang, Yang A Signed-off-by: Mark Brown --- sound/soc/intel/boards/cht_bsw_max98090_ti.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/intel/boards/cht_bsw_max98090_ti.c b/sound/soc/intel/boards/cht_bsw_max98090_ti.c index d604ee80eda4..70f832114a5a 100644 --- a/sound/soc/intel/boards/cht_bsw_max98090_ti.c +++ b/sound/soc/intel/boards/cht_bsw_max98090_ti.c @@ -69,12 +69,12 @@ static const struct snd_soc_dapm_route cht_audio_map[] = { {"Headphone", NULL, "HPR"}, {"Ext Spk", NULL, "SPKL"}, {"Ext Spk", NULL, "SPKR"}, - {"AIF1 Playback", NULL, "ssp2 Tx"}, + {"HiFi Playback", NULL, "ssp2 Tx"}, {"ssp2 Tx", NULL, "codec_out0"}, {"ssp2 Tx", NULL, "codec_out1"}, {"codec_in0", NULL, "ssp2 Rx" }, {"codec_in1", NULL, "ssp2 Rx" }, - {"ssp2 Rx", NULL, "AIF1 Capture"}, + {"ssp2 Rx", NULL, "HiFi Capture"}, }; static const struct snd_kcontrol_new cht_mc_controls[] = { From 9b353cc8f199e4bc78023e8300306b5a16b48e75 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 29 Jun 2015 13:07:06 +0300 Subject: [PATCH 015/428] target/pr: Fix possible uninitialized variable usage Triggered a compilation warning. Fixes: 2650d71e2 target: move transport ID handling to the core Signed-off-by: Sagi Grimberg Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_pr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index 0fdbe43b7dad..5ab7100de17e 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -1474,7 +1474,7 @@ core_scsi3_decode_spec_i_port( LIST_HEAD(tid_dest_list); struct pr_transport_id_holder *tidh_new, *tidh, *tidh_tmp; unsigned char *buf, *ptr, proto_ident; - const unsigned char *i_str; + const unsigned char *i_str = NULL; char *iport_ptr = NULL, i_buf[PR_REG_ISID_ID_LEN]; sense_reason_t ret; u32 tpdl, tid_len = 0; From 27e6772b0d492375621f496a114617bf9c17c8d2 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 29 Jun 2015 18:32:03 +0300 Subject: [PATCH 016/428] target/spc: Set SPT correctly in Extended INQUIRY Data VPD page LIO supports protection types 1,3 so setting a hard-coded SPT=3 is fine for now. Signed-off-by: Sagi Grimberg Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_spc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c index b0744433315a..5df4d9b097dc 100644 --- a/drivers/target/target_core_spc.c +++ b/drivers/target/target_core_spc.c @@ -458,6 +458,9 @@ spc_emulate_evpd_86(struct se_cmd *cmd, unsigned char *buf) buf[4] = 0x4; } + /* logical unit supports type 1 and type 3 protection */ + buf[4] |= (0x3 << 3); + /* Set HEADSUP, ORDSUP, SIMPSUP */ buf[5] = 0x07; From 3aa3c67b266fd6114c019bbac35de79aca02d520 Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Mon, 6 Jul 2015 15:26:37 -0700 Subject: [PATCH 017/428] target: Add extra TYPE_DISK + protection checks for INQUIRY SPT Cc: Sagi Grimberg Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_spc.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c index 5df4d9b097dc..b5ba1ec3c354 100644 --- a/drivers/target/target_core_spc.c +++ b/drivers/target/target_core_spc.c @@ -454,12 +454,16 @@ spc_emulate_evpd_86(struct se_cmd *cmd, unsigned char *buf) cmd->se_sess->sess_prot_type == TARGET_DIF_TYPE1_PROT) buf[4] = 0x5; else if (dev->dev_attrib.pi_prot_type == TARGET_DIF_TYPE3_PROT || - cmd->se_sess->sess_prot_type == TARGET_DIF_TYPE3_PROT) + cmd->se_sess->sess_prot_type == TARGET_DIF_TYPE3_PROT) buf[4] = 0x4; } /* logical unit supports type 1 and type 3 protection */ - buf[4] |= (0x3 << 3); + if ((dev->transport->get_device_type(dev) == TYPE_DISK) && + (sess->sup_prot_ops & (TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS)) && + (dev->dev_attrib.pi_prot_type || cmd->se_sess->sess_prot_type)) { + buf[4] |= (0x3 << 3); + } /* Set HEADSUP, ORDSUP, SIMPSUP */ buf[5] = 0x07; From 5dacbfc934cab0778852b18dd5d67ecebfcf9a2e Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Sat, 4 Jul 2015 14:05:24 +0300 Subject: [PATCH 018/428] target/rd: Set ramdisk as non rotational device Since a RAM backend device is not really a rotational device, we set it as is_nonrot=1 which will be forwarded in VPD page 0xb1 (block device characteristics) response. Signed-off-by: Sagi Grimberg Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_rd.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c index 4703f403f31c..384cf8894411 100644 --- a/drivers/target/target_core_rd.c +++ b/drivers/target/target_core_rd.c @@ -333,6 +333,7 @@ static int rd_configure_device(struct se_device *dev) dev->dev_attrib.hw_block_size = RD_BLOCKSIZE; dev->dev_attrib.hw_max_sectors = UINT_MAX; dev->dev_attrib.hw_queue_depth = RD_MAX_DEVICE_QUEUE_DEPTH; + dev->dev_attrib.is_nonrot = 1; rd_dev->rd_dev_id = rd_host->rd_host_dev_id_count++; From ae128293d97404f491dc76f1843c7adacfec3441 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 15 Jun 2015 17:25:16 +0900 Subject: [PATCH 019/428] dmaengine: pl330: Fix overflow when reporting residue in memcpy During memcpy operations the residue was always set to an u32 overflowed value. In pl330_tx_status() function number of currently transferred bytes was subtracted from internal "bytes_requested" field. However this "bytes_requested" was not initialized at start to length of memcpy buffer so transferred bytes were subtracted from 0 causing overflow. Signed-off-by: Krzysztof Kozlowski Cc: Fixes: aee4d1fac887 ("dmaengine: pl330: improve pl330_tx_status() function") Signed-off-by: Vinod Koul --- drivers/dma/pl330.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index f513f77b1d85..c535cd059724 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -2623,6 +2623,7 @@ pl330_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dst, desc->rqcfg.brst_len = 1; desc->rqcfg.brst_len = get_burst_len(desc, len); + desc->bytes_requested = len; desc->txd.flags = flags; From 5dd90e5b91e0f5c925b12b132c7cd27538870256 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 15 Jun 2015 23:00:09 +0900 Subject: [PATCH 020/428] dmaengine: pl330: Really fix choppy sound because of wrong residue calculation When pl330 driver was used during sound playback, after some time or after a number of plays the sound became choppy or totally noisy. For example on Odroid XU3 board the first four executions of aplay with small WAVE worked fine, but fifth was unrecognizable with errors: $ aplay /usr/share/sounds/alsa/Front_Right.wava underrun!!! (at least 0.095 ms long) Issue was caused by wrong residue reported by pl330 driver to pcm_dmaengine for its cyclic dma transfers. The pl330_tx_status(), residue reporting function, used a "last" flag in a descriptor to indicate that there is no more data to send. The pl330_tx_submit() iterated over descriptors trying to remove this flag from them and then mark last descriptor as "last". However when iterating it actually removed the flag not from descriptors but always from last of it (and then reset it). Thus effectively once some descriptor was marked as last, then it stayed like this forever causing residue to be reported too low. Signed-off-by: Krzysztof Kozlowski Fixes: aee4d1fac887 ("dmaengine: pl330: improve pl330_tx_status() function") Cc: Reported-by: gabriel@unseen.is Suggested-by: Marek Szyprowski Tested-by: Lars-Peter Clausen Signed-off-by: Vinod Koul --- drivers/dma/pl330.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index c535cd059724..ecab4ea059b4 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -2328,7 +2328,7 @@ static dma_cookie_t pl330_tx_submit(struct dma_async_tx_descriptor *tx) desc->txd.callback = last->txd.callback; desc->txd.callback_param = last->txd.callback_param; } - last->last = false; + desc->last = false; dma_cookie_assign(&desc->txd); From ebac95a9208e6b5f134df8518df1bfd1b3fee354 Mon Sep 17 00:00:00 2001 From: Juergen Borleis Date: Fri, 3 Jul 2015 12:39:36 +0200 Subject: [PATCH 021/428] ASoC: fsl-ssi: Fix bitclock calculation for master mode According to the datasheet 'pm', 'psr' and 'div2' should never be all 0. Since commit 541b03ad6cfe ("ASoC: fsl_ssi: Fix the incorrect limitation of the bit clock rate") this can happen, because for some bitclock rates 'pm' = 0 seems to be a valid choice but does not work due to hardware restrictions. This results into a bad hardware behaviour (slow audio for example). Feature tested on a i.MX25. Signed-off-by: Juergen Borleis Acked-by: Nicolin Chen Signed-off-by: Mark Brown --- sound/soc/fsl/fsl_ssi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c index c7647e066cfd..c0b940e2019f 100644 --- a/sound/soc/fsl/fsl_ssi.c +++ b/sound/soc/fsl/fsl_ssi.c @@ -633,7 +633,7 @@ static int fsl_ssi_set_bclk(struct snd_pcm_substream *substream, sub *= 100000; do_div(sub, freq); - if (sub < savesub) { + if (sub < savesub && !(i == 0 && psr == 0 && div2 == 0)) { baudrate = tmprate; savesub = sub; pm = i; From 56e7366e43ca676dd28f0e91240a579ad41e9b71 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Fri, 19 Jun 2015 23:55:26 +0530 Subject: [PATCH 022/428] ASoC: Intel: use CONFIG_SND_SOC for intel boards The Intel boards directory was under CONFIG_SND_SOC_INTEL_SST so the machines which don't need these were not allowed to be selected/compiled without enabling this symbol The machine should be allowed to selected by ASoC and then they should select rest of symbols required Reported-by: Michele Curti Signed-off-by: Vinod Koul Acked-by: Liam Girdwood Signed-off-by: Mark Brown --- sound/soc/intel/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/intel/Makefile b/sound/soc/intel/Makefile index 3853ec2ddbc7..6de5d5cd3280 100644 --- a/sound/soc/intel/Makefile +++ b/sound/soc/intel/Makefile @@ -7,4 +7,4 @@ obj-$(CONFIG_SND_SOC_INTEL_BAYTRAIL) += baytrail/ obj-$(CONFIG_SND_SST_MFLD_PLATFORM) += atom/ # Machine support -obj-$(CONFIG_SND_SOC_INTEL_SST) += boards/ +obj-$(CONFIG_SND_SOC) += boards/ From 690edcfad0e570a9a2a42d9b98cd04efaf21489d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 8 Jul 2015 20:19:23 +0200 Subject: [PATCH 023/428] NFSv4.2/flexfiles: Fix a typo in the flexfiles layoutstats code Signed-off-by: Trond Myklebust --- fs/nfs/flexfilelayout/flexfilelayout.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index c12951b9551e..b3289d701eea 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1852,7 +1852,7 @@ ff_layout_mirror_prepare_stats(struct nfs42_layoutstat_args *args, struct nfs42_layoutstat_devinfo *devinfo; int i; - for (i = 0; i <= FF_LAYOUT_MIRROR_COUNT(pls); i++) { + for (i = 0; i < FF_LAYOUT_MIRROR_COUNT(pls); i++) { if (*dev_count >= dev_limit) break; mirror = FF_LAYOUT_COMP(pls, i); From e18077b6e5dfe26e9fbbdc1fd1085a1701c24bea Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Wed, 8 Jul 2015 21:59:59 +0200 Subject: [PATCH 024/428] ASoC: dapm: Fix kcontrol widget name memory management The name field of the widget template is only used inside snd_soc_dapm_new_control_unlocked() which allocates a copy for the actual widget. This means we need to free the name allocated for the template in dapm_kcontrol_data_alloc() and not the name of the actual widget in dapm_kcontrol_free(). Otherwise we get a double free on the widget name and a memory leak on the template name. Fixes: 773da9b358bf ("ASoC: dapm: Append "Autodisable" to autodisable widget names") Signed-off-by: Lars-Peter Clausen Signed-off-by: Mark Brown --- sound/soc/soc-dapm.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 1779430013ea..9f270c0308b7 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -358,9 +358,10 @@ static int dapm_kcontrol_data_alloc(struct snd_soc_dapm_widget *widget, data->widget = snd_soc_dapm_new_control_unlocked(widget->dapm, &template); + kfree(name); if (!data->widget) { ret = -ENOMEM; - goto err_name; + goto err_data; } } break; @@ -391,9 +392,10 @@ static int dapm_kcontrol_data_alloc(struct snd_soc_dapm_widget *widget, data->widget = snd_soc_dapm_new_control_unlocked( widget->dapm, &template); + kfree(name); if (!data->widget) { ret = -ENOMEM; - goto err_name; + goto err_data; } snd_soc_dapm_add_path(widget->dapm, data->widget, @@ -408,8 +410,6 @@ static int dapm_kcontrol_data_alloc(struct snd_soc_dapm_widget *widget, return 0; -err_name: - kfree(name); err_data: kfree(data); return ret; @@ -418,8 +418,6 @@ err_data: static void dapm_kcontrol_free(struct snd_kcontrol *kctl) { struct dapm_kcontrol_data *data = snd_kcontrol_chip(kctl); - if (data->widget) - kfree(data->widget->name); kfree(data->wlist); kfree(data); } From 2210438b6aae9668cf89c272fef935b83aedf81d Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Wed, 8 Jul 2015 22:14:48 +0200 Subject: [PATCH 025/428] ASoC: Free card DAPM context on snd_soc_instantiate_card() error path Make sure the to free the card DAPM context if snd_soc_instantiate_card() fails, otherwise the memory allocated for the DAPM widgets is leaked. Signed-off-by: Lars-Peter Clausen Signed-off-by: Mark Brown --- sound/soc/soc-core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 3a4a5c0e3f97..0e1e69c7abd5 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1716,6 +1716,7 @@ card_probe_error: if (card->remove) card->remove(card); + snd_soc_dapm_free(&card->dapm); soc_cleanup_card_debugfs(card); snd_card_free(card->snd_card); From 94319ba10ecabc8f28129566d1f5793e3e7a0a79 Mon Sep 17 00:00:00 2001 From: Koro Chen Date: Thu, 9 Jul 2015 10:51:27 +0800 Subject: [PATCH 026/428] ASoC: mediatek: Use platform_of_node for machine drivers This replaces the platform_name in snd_soc_dai_link by device tree node. Signed-off-by: Koro Chen Signed-off-by: Mark Brown --- .../bindings/sound/mt8173-max98090.txt | 2 ++ .../bindings/sound/mt8173-rt5650-rt5676.txt | 2 ++ sound/soc/mediatek/mt8173-max98090.c | 17 +++++++++++++---- sound/soc/mediatek/mt8173-rt5650-rt5676.c | 19 +++++++++++++++---- 4 files changed, 32 insertions(+), 8 deletions(-) diff --git a/Documentation/devicetree/bindings/sound/mt8173-max98090.txt b/Documentation/devicetree/bindings/sound/mt8173-max98090.txt index 829bd26d17f8..519e97c8f1b8 100644 --- a/Documentation/devicetree/bindings/sound/mt8173-max98090.txt +++ b/Documentation/devicetree/bindings/sound/mt8173-max98090.txt @@ -3,11 +3,13 @@ MT8173 with MAX98090 CODEC Required properties: - compatible : "mediatek,mt8173-max98090" - mediatek,audio-codec: the phandle of the MAX98090 audio codec +- mediatek,platform: the phandle of MT8173 ASoC platform Example: sound { compatible = "mediatek,mt8173-max98090"; mediatek,audio-codec = <&max98090>; + mediatek,platform = <&afe>; }; diff --git a/Documentation/devicetree/bindings/sound/mt8173-rt5650-rt5676.txt b/Documentation/devicetree/bindings/sound/mt8173-rt5650-rt5676.txt index 61e98c976bd4..f205ce9e31dd 100644 --- a/Documentation/devicetree/bindings/sound/mt8173-rt5650-rt5676.txt +++ b/Documentation/devicetree/bindings/sound/mt8173-rt5650-rt5676.txt @@ -3,11 +3,13 @@ MT8173 with RT5650 RT5676 CODECS Required properties: - compatible : "mediatek,mt8173-rt5650-rt5676" - mediatek,audio-codec: the phandles of rt5650 and rt5676 codecs +- mediatek,platform: the phandle of MT8173 ASoC platform Example: sound { compatible = "mediatek,mt8173-rt5650-rt5676"; mediatek,audio-codec = <&rt5650 &rt5676>; + mediatek,platform = <&afe>; }; diff --git a/sound/soc/mediatek/mt8173-max98090.c b/sound/soc/mediatek/mt8173-max98090.c index 4d44b5803e55..2d2536af141f 100644 --- a/sound/soc/mediatek/mt8173-max98090.c +++ b/sound/soc/mediatek/mt8173-max98090.c @@ -103,7 +103,6 @@ static struct snd_soc_dai_link mt8173_max98090_dais[] = { .name = "MAX98090 Playback", .stream_name = "MAX98090 Playback", .cpu_dai_name = "DL1", - .platform_name = "11220000.mt8173-afe-pcm", .codec_name = "snd-soc-dummy", .codec_dai_name = "snd-soc-dummy-dai", .trigger = {SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST}, @@ -114,7 +113,6 @@ static struct snd_soc_dai_link mt8173_max98090_dais[] = { .name = "MAX98090 Capture", .stream_name = "MAX98090 Capture", .cpu_dai_name = "VUL", - .platform_name = "11220000.mt8173-afe-pcm", .codec_name = "snd-soc-dummy", .codec_dai_name = "snd-soc-dummy-dai", .trigger = {SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST}, @@ -125,7 +123,6 @@ static struct snd_soc_dai_link mt8173_max98090_dais[] = { { .name = "Codec", .cpu_dai_name = "I2S", - .platform_name = "11220000.mt8173-afe-pcm", .no_pcm = 1, .codec_dai_name = "HiFi", .init = mt8173_max98090_init, @@ -152,9 +149,21 @@ static struct snd_soc_card mt8173_max98090_card = { static int mt8173_max98090_dev_probe(struct platform_device *pdev) { struct snd_soc_card *card = &mt8173_max98090_card; - struct device_node *codec_node; + struct device_node *codec_node, *platform_node; int ret, i; + platform_node = of_parse_phandle(pdev->dev.of_node, + "mediatek,platform", 0); + if (!platform_node) { + dev_err(&pdev->dev, "Property 'platform' missing or invalid\n"); + return -EINVAL; + } + for (i = 0; i < card->num_links; i++) { + if (mt8173_max98090_dais[i].platform_name) + continue; + mt8173_max98090_dais[i].platform_of_node = platform_node; + } + codec_node = of_parse_phandle(pdev->dev.of_node, "mediatek,audio-codec", 0); if (!codec_node) { diff --git a/sound/soc/mediatek/mt8173-rt5650-rt5676.c b/sound/soc/mediatek/mt8173-rt5650-rt5676.c index 094055323059..6f52eca05e26 100644 --- a/sound/soc/mediatek/mt8173-rt5650-rt5676.c +++ b/sound/soc/mediatek/mt8173-rt5650-rt5676.c @@ -138,7 +138,6 @@ static struct snd_soc_dai_link mt8173_rt5650_rt5676_dais[] = { .name = "rt5650_rt5676 Playback", .stream_name = "rt5650_rt5676 Playback", .cpu_dai_name = "DL1", - .platform_name = "11220000.mt8173-afe-pcm", .codec_name = "snd-soc-dummy", .codec_dai_name = "snd-soc-dummy-dai", .trigger = {SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST}, @@ -149,7 +148,6 @@ static struct snd_soc_dai_link mt8173_rt5650_rt5676_dais[] = { .name = "rt5650_rt5676 Capture", .stream_name = "rt5650_rt5676 Capture", .cpu_dai_name = "VUL", - .platform_name = "11220000.mt8173-afe-pcm", .codec_name = "snd-soc-dummy", .codec_dai_name = "snd-soc-dummy-dai", .trigger = {SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST}, @@ -161,7 +159,6 @@ static struct snd_soc_dai_link mt8173_rt5650_rt5676_dais[] = { { .name = "Codec", .cpu_dai_name = "I2S", - .platform_name = "11220000.mt8173-afe-pcm", .no_pcm = 1, .codecs = mt8173_rt5650_rt5676_codecs, .num_codecs = 2, @@ -209,7 +206,21 @@ static struct snd_soc_card mt8173_rt5650_rt5676_card = { static int mt8173_rt5650_rt5676_dev_probe(struct platform_device *pdev) { struct snd_soc_card *card = &mt8173_rt5650_rt5676_card; - int ret; + struct device_node *platform_node; + int i, ret; + + platform_node = of_parse_phandle(pdev->dev.of_node, + "mediatek,platform", 0); + if (!platform_node) { + dev_err(&pdev->dev, "Property 'platform' missing or invalid\n"); + return -EINVAL; + } + + for (i = 0; i < card->num_links; i++) { + if (mt8173_rt5650_rt5676_dais[i].platform_name) + continue; + mt8173_rt5650_rt5676_dais[i].platform_of_node = platform_node; + } mt8173_rt5650_rt5676_codecs[0].of_node = of_parse_phandle(pdev->dev.of_node, "mediatek,audio-codec", 0); From 95dd8653de658143770cb0e55a58d2aab97c79d2 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 9 Jul 2015 22:56:00 +0200 Subject: [PATCH 027/428] netfilter: ctnetlink: put back references to master ct and expect objects We have to put back the references to the master conntrack and the expectation that we just created, otherwise we'll leak them. Fixes: 0ef71ee1a5b9 ("netfilter: ctnetlink: refactor ctnetlink_create_expect") Reported-by: Tim Wiess Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_netlink.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index d1c23940a86a..6b8b0abbfab4 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2995,11 +2995,6 @@ ctnetlink_create_expect(struct net *net, u16 zone, } err = nf_ct_expect_related_report(exp, portid, report); - if (err < 0) - goto err_exp; - - return 0; -err_exp: nf_ct_expect_put(exp); err_ct: nf_ct_put(ct); From c5d73716e95d510c0655272ce44f318932309cb1 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 9 Jul 2015 17:58:39 +0200 Subject: [PATCH 028/428] pNFS: Layoutreturn must invalidate all existing layout segments. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 9f24238032f8..671498ca36d7 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7964,16 +7964,19 @@ static void nfs4_layoutreturn_release(void *calldata) { struct nfs4_layoutreturn *lrp = calldata; struct pnfs_layout_hdr *lo = lrp->args.layout; + LIST_HEAD(freeme); dprintk("--> %s\n", __func__); spin_lock(&lo->plh_inode->i_lock); if (lrp->res.lrs_present) pnfs_set_layout_stateid(lo, &lrp->res.stateid, true); + pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range); pnfs_clear_layoutreturn_waitbit(lo); clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags); rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq); lo->plh_block_lgets--; spin_unlock(&lo->plh_inode->i_lock); + pnfs_free_lseg_list(&freeme); pnfs_put_layout_hdr(lrp->args.layout); nfs_iput_and_deactive(lrp->inode); kfree(calldata); From df9cecc1a36d70ec09d34e83bad452064754fdc4 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 9 Jul 2015 23:38:11 +0200 Subject: [PATCH 029/428] pNFS: pnfs_roc_drain should return 'true' when sleeping Also clean up the case where we don't find a return-on-close layout segment. Signed-off-by: Trond Myklebust --- fs/nfs/pnfs.c | 24 +++++++++++------------- 1 file changed, 11 insertions(+), 13 deletions(-) diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 0ba9a02c9566..8e9f467e409c 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1146,14 +1146,14 @@ bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task) struct pnfs_layout_segment *lseg; nfs4_stateid stateid; u32 current_seqid; - bool found = false, layoutreturn = false; + bool layoutreturn = false; spin_lock(&ino->i_lock); list_for_each_entry(lseg, &nfsi->layout->plh_segs, pls_list) if (test_bit(NFS_LSEG_ROC, &lseg->pls_flags)) { rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL); - found = true; - goto out; + spin_unlock(&ino->i_lock); + return true; } lo = nfsi->layout; current_seqid = be32_to_cpu(lo->plh_stateid.seqid); @@ -1162,23 +1162,21 @@ bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task) * a barrier, we choose the worst-case barrier. */ *barrier = current_seqid + atomic_read(&lo->plh_outstanding); -out: - if (!found) { - stateid = lo->plh_stateid; - layoutreturn = - test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + stateid = lo->plh_stateid; + layoutreturn = test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags); - if (layoutreturn) { - lo->plh_block_lgets++; - pnfs_get_layout_hdr(lo); - } + if (layoutreturn) { + lo->plh_block_lgets++; + pnfs_get_layout_hdr(lo); } + spin_unlock(&ino->i_lock); if (layoutreturn) { rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL); pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, false); + return true; } - return found; + return false; } /* From 7f27392cd4cbcadeeaff9eedebcaec8fae9aec8e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 9 Jul 2015 18:40:01 +0200 Subject: [PATCH 030/428] pNFS: Fix races between return-on-close and layoutreturn. If one or more of the layout segments reports an error during I/O, then we may have to send a layoutreturn to report the error back to the NFS metadata server. This patch ensures that the return-on-close code can detect the outstanding layoutreturn, and not preempt it. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 2 -- fs/nfs/pnfs.c | 63 ++++++++++++++++++++++++++--------------------- 2 files changed, 35 insertions(+), 30 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 671498ca36d7..c5c9e0d070f8 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7972,8 +7972,6 @@ static void nfs4_layoutreturn_release(void *calldata) pnfs_set_layout_stateid(lo, &lrp->res.stateid, true); pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range); pnfs_clear_layoutreturn_waitbit(lo); - clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags); - rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq); lo->plh_block_lgets--; spin_unlock(&lo->plh_inode->i_lock); pnfs_free_lseg_list(&freeme); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 8e9f467e409c..27e2bcaa88da 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -352,7 +352,7 @@ pnfs_layout_need_return(struct pnfs_layout_hdr *lo, { struct pnfs_layout_segment *s; - if (!test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags)) + if (!test_and_clear_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags)) return false; list_for_each_entry(s, &lo->plh_segs, pls_list) @@ -362,6 +362,18 @@ pnfs_layout_need_return(struct pnfs_layout_hdr *lo, return true; } +static bool +pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo) +{ + if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) + return false; + lo->plh_return_iomode = 0; + lo->plh_block_lgets++; + pnfs_get_layout_hdr(lo); + clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags); + return true; +} + static void pnfs_layoutreturn_before_put_lseg(struct pnfs_layout_segment *lseg, struct pnfs_layout_hdr *lo, struct inode *inode) { @@ -372,17 +384,16 @@ static void pnfs_layoutreturn_before_put_lseg(struct pnfs_layout_segment *lseg, if (pnfs_layout_need_return(lo, lseg)) { nfs4_stateid stateid; enum pnfs_iomode iomode; + bool send; stateid = lo->plh_stateid; iomode = lo->plh_return_iomode; - /* decreased in pnfs_send_layoutreturn() */ - lo->plh_block_lgets++; - lo->plh_return_iomode = 0; + send = pnfs_prepare_layoutreturn(lo); spin_unlock(&inode->i_lock); - pnfs_get_layout_hdr(lo); - - /* Send an async layoutreturn so we dont deadlock */ - pnfs_send_layoutreturn(lo, stateid, iomode, false); + if (send) { + /* Send an async layoutreturn so we dont deadlock */ + pnfs_send_layoutreturn(lo, stateid, iomode, false); + } } else spin_unlock(&inode->i_lock); } @@ -924,6 +935,7 @@ void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo) clear_bit_unlock(NFS_LAYOUT_RETURN, &lo->plh_flags); smp_mb__after_atomic(); wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN); + rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq); } static int @@ -978,6 +990,7 @@ _pnfs_return_layout(struct inode *ino) LIST_HEAD(tmp_list); nfs4_stateid stateid; int status = 0, empty; + bool send; dprintk("NFS: %s for inode %lu\n", __func__, ino->i_ino); @@ -1007,17 +1020,18 @@ _pnfs_return_layout(struct inode *ino) /* Don't send a LAYOUTRETURN if list was initially empty */ if (empty) { spin_unlock(&ino->i_lock); - pnfs_put_layout_hdr(lo); dprintk("NFS: %s no layout segments to return\n", __func__); - goto out; + goto out_put_layout_hdr; } set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags); - lo->plh_block_lgets++; + send = pnfs_prepare_layoutreturn(lo); spin_unlock(&ino->i_lock); pnfs_free_lseg_list(&tmp_list); - - status = pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true); + if (send) + status = pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true); +out_put_layout_hdr: + pnfs_put_layout_hdr(lo); out: dprintk("<-- %s status: %d\n", __func__, status); return status; @@ -1097,13 +1111,9 @@ bool pnfs_roc(struct inode *ino) out_noroc: if (lo) { stateid = lo->plh_stateid; - layoutreturn = - test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, - &lo->plh_flags); - if (layoutreturn) { - lo->plh_block_lgets++; - pnfs_get_layout_hdr(lo); - } + if (test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + &lo->plh_flags)) + layoutreturn = pnfs_prepare_layoutreturn(lo); } spin_unlock(&ino->i_lock); if (layoutreturn) { @@ -1163,16 +1173,14 @@ bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task) */ *barrier = current_seqid + atomic_read(&lo->plh_outstanding); stateid = lo->plh_stateid; - layoutreturn = test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, - &lo->plh_flags); - if (layoutreturn) { - lo->plh_block_lgets++; - pnfs_get_layout_hdr(lo); - } + if (test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + &lo->plh_flags)) + layoutreturn = pnfs_prepare_layoutreturn(lo); + if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) + rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL); spin_unlock(&ino->i_lock); if (layoutreturn) { - rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL); pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, false); return true; } @@ -1693,7 +1701,6 @@ void pnfs_error_mark_layout_for_return(struct inode *inode, spin_lock(&inode->i_lock); /* set failure bit so that pnfs path will be retried later */ pnfs_layout_set_fail_bit(lo, iomode); - set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags); if (lo->plh_return_iomode == 0) lo->plh_return_iomode = range.iomode; else if (lo->plh_return_iomode != range.iomode) From bdc59cf233433ddd2cd671db02bd6b52323ce63d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 9 Jul 2015 23:54:09 +0200 Subject: [PATCH 031/428] pNFS: pnfs_roc_drain() fix a race with open If a process reopens the file before we can send off the CLOSE/DELEGRETURN, then pnfs_roc_drain() may end up waiting for a new set of layout segments that are marked as return-on-close, but haven't yet been returned. Fix this by only waiting for those layout segments that were invalidated in pnfs_roc(). Signed-off-by: Trond Myklebust --- fs/nfs/pnfs.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 27e2bcaa88da..b02e32e2abeb 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1159,12 +1159,15 @@ bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task) bool layoutreturn = false; spin_lock(&ino->i_lock); - list_for_each_entry(lseg, &nfsi->layout->plh_segs, pls_list) - if (test_bit(NFS_LSEG_ROC, &lseg->pls_flags)) { - rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL); - spin_unlock(&ino->i_lock); - return true; - } + list_for_each_entry(lseg, &nfsi->layout->plh_segs, pls_list) { + if (!test_bit(NFS_LSEG_ROC, &lseg->pls_flags)) + continue; + if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags)) + continue; + rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL); + spin_unlock(&ino->i_lock); + return true; + } lo = nfsi->layout; current_seqid = be32_to_cpu(lo->plh_stateid.seqid); From faa4a54f0be15b5d81b574fb5a40db24345d1a6c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 9 Jul 2015 18:24:07 +0200 Subject: [PATCH 032/428] pNFS: Don't throw out valid layout segments It is OK for layout segments to remain hashed even if no-one holds any references to them, provided that the segments are still valid. Signed-off-by: Trond Myklebust --- fs/nfs/pnfs.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index b02e32e2abeb..18aa3b7962eb 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -422,6 +422,10 @@ pnfs_put_lseg(struct pnfs_layout_segment *lseg) pnfs_layoutreturn_before_put_lseg(lseg, lo, inode); if (atomic_dec_and_lock(&lseg->pls_refcount, &inode->i_lock)) { + if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags)) { + spin_unlock(&inode->i_lock); + return; + } pnfs_get_layout_hdr(lo); pnfs_layout_remove_lseg(lo, lseg); spin_unlock(&inode->i_lock); @@ -462,6 +466,8 @@ pnfs_put_lseg_locked(struct pnfs_layout_segment *lseg) test_bit(NFS_LSEG_VALID, &lseg->pls_flags)); if (atomic_dec_and_test(&lseg->pls_refcount)) { struct pnfs_layout_hdr *lo = lseg->pls_layout; + if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags)) + return; pnfs_get_layout_hdr(lo); pnfs_layout_remove_lseg(lo, lseg); pnfs_free_lseg_async(lseg); From a18da49ff3ec849c4584ae3abe2b83ff50705ace Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 9 Jul 2015 22:19:28 +0900 Subject: [PATCH 033/428] ASoC: zx: i2s: Fix devm_ioremap_resource return value check Value returned by devm_ioremap_resource() was checked for non-NULL but devm_ioremap_resource() returns IOMEM_ERR_PTR, not NULL. In case of error this could lead to dereference of ERR_PTR. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Jun Nie Signed-off-by: Mark Brown --- sound/soc/zte/zx296702-i2s.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/zte/zx296702-i2s.c b/sound/soc/zte/zx296702-i2s.c index 98d96e1b17e0..1930c42e1f55 100644 --- a/sound/soc/zte/zx296702-i2s.c +++ b/sound/soc/zte/zx296702-i2s.c @@ -393,9 +393,9 @@ static int zx_i2s_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); zx_i2s->mapbase = res->start; zx_i2s->reg_base = devm_ioremap_resource(&pdev->dev, res); - if (!zx_i2s->reg_base) { + if (IS_ERR(zx_i2s->reg_base)) { dev_err(&pdev->dev, "ioremap failed!\n"); - return -EIO; + return PTR_ERR(zx_i2s->reg_base); } writel_relaxed(0, zx_i2s->reg_base + ZX_I2S_FIFO_CTRL); From 2dfbe9afcda3243dd309826cbbb8ae9e9f602006 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 9 Jul 2015 22:19:29 +0900 Subject: [PATCH 034/428] ASoC: zx: spdif: Fix devm_ioremap_resource return value check Value returned by devm_ioremap_resource() was checked for non-NULL but devm_ioremap_resource() returns IOMEM_ERR_PTR, not NULL. In case of error this could lead to dereference of ERR_PTR. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Jun Nie Signed-off-by: Mark Brown --- sound/soc/zte/zx296702-spdif.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/zte/zx296702-spdif.c b/sound/soc/zte/zx296702-spdif.c index 11a0e46a1156..26265ce4caca 100644 --- a/sound/soc/zte/zx296702-spdif.c +++ b/sound/soc/zte/zx296702-spdif.c @@ -322,9 +322,9 @@ static int zx_spdif_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); zx_spdif->mapbase = res->start; zx_spdif->reg_base = devm_ioremap_resource(&pdev->dev, res); - if (!zx_spdif->reg_base) { + if (IS_ERR(zx_spdif->reg_base)) { dev_err(&pdev->dev, "ioremap failed!\n"); - return -EIO; + return PTR_ERR(zx_spdif->reg_base); } zx_spdif_dev_init(zx_spdif->reg_base); From 484836ec2de24d9a7c6471f022b746d947698725 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Thu, 9 Jul 2015 17:15:01 -0700 Subject: [PATCH 035/428] netfilter: IDLETIMER: fix lockdep warning Dynamically allocated sysfs attributes should be initialized with sysfs_attr_init() otherwise lockdep will be angry with us: [ 45.468653] BUG: key ffffffc030fad4e0 not in .data! [ 45.468655] ------------[ cut here ]------------ [ 45.468666] WARNING: CPU: 0 PID: 1176 at /mnt/host/source/src/third_party/kernel/v3.18/kernel/locking/lockdep.c:2991 lockdep_init_map+0x12c/0x490() [ 45.468672] DEBUG_LOCKS_WARN_ON(1) [ 45.468672] CPU: 0 PID: 1176 Comm: iptables Tainted: G U W 3.18.0 #43 [ 45.468674] Hardware name: XXX [ 45.468675] Call trace: [ 45.468680] [] dump_backtrace+0x0/0x10c [ 45.468683] [] show_stack+0x10/0x1c [ 45.468688] [] dump_stack+0x74/0x94 [ 45.468692] [] warn_slowpath_common+0x84/0xb0 [ 45.468694] [] warn_slowpath_fmt+0x4c/0x58 [ 45.468697] [] lockdep_init_map+0x128/0x490 [ 45.468701] [] __kernfs_create_file+0x80/0xe4 [ 45.468704] [] sysfs_add_file_mode_ns+0x104/0x170 [ 45.468706] [] sysfs_create_file_ns+0x58/0x64 [ 45.468711] [] idletimer_tg_checkentry+0x14c/0x324 [ 45.468714] [] xt_check_target+0x170/0x198 [ 45.468717] [] check_target+0x58/0x6c [ 45.468720] [] translate_table+0x30c/0x424 [ 45.468723] [] do_ipt_set_ctl+0x144/0x1d0 [ 45.468728] [] nf_setsockopt+0x50/0x60 [ 45.468732] [] ip_setsockopt+0x8c/0xb4 [ 45.468735] [] raw_setsockopt+0x10/0x50 [ 45.468739] [] sock_common_setsockopt+0x14/0x20 [ 45.468742] [] SyS_setsockopt+0x88/0xb8 [ 45.468744] ---[ end trace 41d156354d18c039 ]--- Signed-off-by: Dmitry Torokhov Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_IDLETIMER.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index f407ebc13481..29d2c31f406c 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -126,6 +126,7 @@ static int idletimer_tg_create(struct idletimer_tg_info *info) goto out; } + sysfs_attr_init(&info->timer->attr.attr); info->timer->attr.attr.name = kstrdup(info->label, GFP_KERNEL); if (!info->timer->attr.attr.name) { ret = -ENOMEM; From 326bf17ea5d4f8f17b54cbf167b8cb504c606ee9 Mon Sep 17 00:00:00 2001 From: Alex Gartrell Date: Fri, 26 Jun 2015 03:18:45 -0700 Subject: [PATCH 036/428] ipvs: fix ipv6 route unreach panic Previously there was a trivial panic unshare -n /bin/bash <dev and use that for the purpose of the invocation. Signed-off-by: Alex Gartrell Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- net/netfilter/ipvs/ip_vs_xmit.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index bf66a8657a5f..b99d80695b1f 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -505,6 +505,13 @@ err_put: return -1; err_unreach: + /* The ip6_link_failure function requires the dev field to be set + * in order to get the net (further for the sake of fwmark + * reflection). + */ + if (!skb->dev) + skb->dev = skb_dst(skb)->dev; + dst_link_failure(skb); return -1; } From 4754957f04f5f368792a0eb7dab0ae89fb93dcfd Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sat, 27 Jun 2015 14:39:30 +0300 Subject: [PATCH 037/428] ipvs: do not use random local source address for tunnels Michael Vallaly reports about wrong source address used in rare cases for tunneled traffic. Looks like __ip_vs_get_out_rt in 3.10+ is providing uninitialized dest_dst->dst_saddr.ip because ip_vs_dest_dst_alloc uses kmalloc. While we retry after seeing EINVAL from routing for data that does not look like valid local address, it still succeeded when this memory was previously used from other dests and with different local addresses. As result, we can use valid local address that is not suitable for our real server. Fix it by providing 0.0.0.0 every time our cache is refreshed. By this way we will get preferred source address from routing. Reported-by: Michael Vallaly Fixes: 026ace060dfe ("ipvs: optimize dst usage for real server") Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- net/netfilter/ipvs/ip_vs_xmit.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index b99d80695b1f..ec30d68ccc0b 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -130,7 +130,6 @@ static struct rtable *do_output_route4(struct net *net, __be32 daddr, memset(&fl4, 0, sizeof(fl4)); fl4.daddr = daddr; - fl4.saddr = (rt_mode & IP_VS_RT_MODE_CONNECT) ? *saddr : 0; fl4.flowi4_flags = (rt_mode & IP_VS_RT_MODE_KNOWN_NH) ? FLOWI_FLAG_KNOWN_NH : 0; From 05f00505a89acd21f5d0d20f5797dfbc4cf85243 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Mon, 29 Jun 2015 21:51:40 +0300 Subject: [PATCH 038/428] ipvs: fix crash if scheduler is changed I overlooked the svc->sched_data usage from schedulers when the services were converted to RCU in 3.10. Now the rare ipvsadm -E command can change the scheduler but due to the reverse order of ip_vs_bind_scheduler and ip_vs_unbind_scheduler we provide new sched_data to the old scheduler resulting in a crash. To fix it without changing the scheduler methods we have to use synchronize_rcu() only for the editing case. It means all svc->scheduler readers should expect a NULL value. To avoid breakage for the service listing and ipvsadm -R we can use the "none" name to indicate that scheduler is not assigned, a state when we drop new connections. Reported-by: Alexander Vasiliev Fixes: ceec4c381681 ("ipvs: convert services to rcu") Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- net/netfilter/ipvs/ip_vs_core.c | 16 ++++++- net/netfilter/ipvs/ip_vs_ctl.c | 80 ++++++++++++++++++++------------ net/netfilter/ipvs/ip_vs_sched.c | 12 ++--- 3 files changed, 70 insertions(+), 38 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 5d2b806a862e..38fbc194b9cb 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -319,7 +319,13 @@ ip_vs_sched_persist(struct ip_vs_service *svc, * return *ignored=0 i.e. ICMP and NF_DROP */ sched = rcu_dereference(svc->scheduler); - dest = sched->schedule(svc, skb, iph); + if (sched) { + /* read svc->sched_data after svc->scheduler */ + smp_rmb(); + dest = sched->schedule(svc, skb, iph); + } else { + dest = NULL; + } if (!dest) { IP_VS_DBG(1, "p-schedule: no dest found.\n"); kfree(param.pe_data); @@ -467,7 +473,13 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, } sched = rcu_dereference(svc->scheduler); - dest = sched->schedule(svc, skb, iph); + if (sched) { + /* read svc->sched_data after svc->scheduler */ + smp_rmb(); + dest = sched->schedule(svc, skb, iph); + } else { + dest = NULL; + } if (dest == NULL) { IP_VS_DBG(1, "Schedule: no dest found.\n"); return NULL; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 285eae3a1454..24c554201a76 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -842,15 +842,16 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, __ip_vs_dst_cache_reset(dest); spin_unlock_bh(&dest->dst_lock); - sched = rcu_dereference_protected(svc->scheduler, 1); if (add) { ip_vs_start_estimator(svc->net, &dest->stats); list_add_rcu(&dest->n_list, &svc->destinations); svc->num_dests++; - if (sched->add_dest) + sched = rcu_dereference_protected(svc->scheduler, 1); + if (sched && sched->add_dest) sched->add_dest(svc, dest); } else { - if (sched->upd_dest) + sched = rcu_dereference_protected(svc->scheduler, 1); + if (sched && sched->upd_dest) sched->upd_dest(svc, dest); } } @@ -1084,7 +1085,7 @@ static void __ip_vs_unlink_dest(struct ip_vs_service *svc, struct ip_vs_scheduler *sched; sched = rcu_dereference_protected(svc->scheduler, 1); - if (sched->del_dest) + if (sched && sched->del_dest) sched->del_dest(svc, dest); } } @@ -1175,11 +1176,14 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, ip_vs_use_count_inc(); /* Lookup the scheduler by 'u->sched_name' */ - sched = ip_vs_scheduler_get(u->sched_name); - if (sched == NULL) { - pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name); - ret = -ENOENT; - goto out_err; + if (strcmp(u->sched_name, "none")) { + sched = ip_vs_scheduler_get(u->sched_name); + if (!sched) { + pr_info("Scheduler module ip_vs_%s not found\n", + u->sched_name); + ret = -ENOENT; + goto out_err; + } } if (u->pe_name && *u->pe_name) { @@ -1240,10 +1244,12 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, spin_lock_init(&svc->stats.lock); /* Bind the scheduler */ - ret = ip_vs_bind_scheduler(svc, sched); - if (ret) - goto out_err; - sched = NULL; + if (sched) { + ret = ip_vs_bind_scheduler(svc, sched); + if (ret) + goto out_err; + sched = NULL; + } /* Bind the ct retriever */ RCU_INIT_POINTER(svc->pe, pe); @@ -1291,17 +1297,20 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, static int ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u) { - struct ip_vs_scheduler *sched, *old_sched; + struct ip_vs_scheduler *sched = NULL, *old_sched; struct ip_vs_pe *pe = NULL, *old_pe = NULL; int ret = 0; /* * Lookup the scheduler, by 'u->sched_name' */ - sched = ip_vs_scheduler_get(u->sched_name); - if (sched == NULL) { - pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name); - return -ENOENT; + if (strcmp(u->sched_name, "none")) { + sched = ip_vs_scheduler_get(u->sched_name); + if (!sched) { + pr_info("Scheduler module ip_vs_%s not found\n", + u->sched_name); + return -ENOENT; + } } old_sched = sched; @@ -1329,14 +1338,20 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u) old_sched = rcu_dereference_protected(svc->scheduler, 1); if (sched != old_sched) { - /* Bind the new scheduler */ - ret = ip_vs_bind_scheduler(svc, sched); - if (ret) { - old_sched = sched; - goto out; + if (old_sched) { + ip_vs_unbind_scheduler(svc, old_sched); + RCU_INIT_POINTER(svc->scheduler, NULL); + /* Wait all svc->sched_data users */ + synchronize_rcu(); + } + /* Bind the new scheduler */ + if (sched) { + ret = ip_vs_bind_scheduler(svc, sched); + if (ret) { + ip_vs_scheduler_put(sched); + goto out; + } } - /* Unbind the old scheduler on success */ - ip_vs_unbind_scheduler(svc, old_sched); } /* @@ -1982,6 +1997,7 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v) const struct ip_vs_iter *iter = seq->private; const struct ip_vs_dest *dest; struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler); + char *sched_name = sched ? sched->name : "none"; if (iter->table == ip_vs_svc_table) { #ifdef CONFIG_IP_VS_IPV6 @@ -1990,18 +2006,18 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v) ip_vs_proto_name(svc->protocol), &svc->addr.in6, ntohs(svc->port), - sched->name); + sched_name); else #endif seq_printf(seq, "%s %08X:%04X %s %s ", ip_vs_proto_name(svc->protocol), ntohl(svc->addr.ip), ntohs(svc->port), - sched->name, + sched_name, (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":""); } else { seq_printf(seq, "FWM %08X %s %s", - svc->fwmark, sched->name, + svc->fwmark, sched_name, (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":""); } @@ -2427,13 +2443,15 @@ ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src) { struct ip_vs_scheduler *sched; struct ip_vs_kstats kstats; + char *sched_name; sched = rcu_dereference_protected(src->scheduler, 1); + sched_name = sched ? sched->name : "none"; dst->protocol = src->protocol; dst->addr = src->addr.ip; dst->port = src->port; dst->fwmark = src->fwmark; - strlcpy(dst->sched_name, sched->name, sizeof(dst->sched_name)); + strlcpy(dst->sched_name, sched_name, sizeof(dst->sched_name)); dst->flags = src->flags; dst->timeout = src->timeout / HZ; dst->netmask = src->netmask; @@ -2892,6 +2910,7 @@ static int ip_vs_genl_fill_service(struct sk_buff *skb, struct ip_vs_flags flags = { .flags = svc->flags, .mask = ~0 }; struct ip_vs_kstats kstats; + char *sched_name; nl_service = nla_nest_start(skb, IPVS_CMD_ATTR_SERVICE); if (!nl_service) @@ -2910,8 +2929,9 @@ static int ip_vs_genl_fill_service(struct sk_buff *skb, } sched = rcu_dereference_protected(svc->scheduler, 1); + sched_name = sched ? sched->name : "none"; pe = rcu_dereference_protected(svc->pe, 1); - if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, sched->name) || + if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, sched_name) || (pe && nla_put_string(skb, IPVS_SVC_ATTR_PE_NAME, pe->name)) || nla_put(skb, IPVS_SVC_ATTR_FLAGS, sizeof(flags), &flags) || nla_put_u32(skb, IPVS_SVC_ATTR_TIMEOUT, svc->timeout / HZ) || diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c index 199760c71f39..7e8141647943 100644 --- a/net/netfilter/ipvs/ip_vs_sched.c +++ b/net/netfilter/ipvs/ip_vs_sched.c @@ -74,7 +74,7 @@ void ip_vs_unbind_scheduler(struct ip_vs_service *svc, if (sched->done_service) sched->done_service(svc); - /* svc->scheduler can not be set to NULL */ + /* svc->scheduler can be set to NULL only by caller */ } @@ -147,21 +147,21 @@ void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler) void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg) { - struct ip_vs_scheduler *sched; + struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler); + char *sched_name = sched ? sched->name : "none"; - sched = rcu_dereference(svc->scheduler); if (svc->fwmark) { IP_VS_ERR_RL("%s: FWM %u 0x%08X - %s\n", - sched->name, svc->fwmark, svc->fwmark, msg); + sched_name, svc->fwmark, svc->fwmark, msg); #ifdef CONFIG_IP_VS_IPV6 } else if (svc->af == AF_INET6) { IP_VS_ERR_RL("%s: %s [%pI6c]:%d - %s\n", - sched->name, ip_vs_proto_name(svc->protocol), + sched_name, ip_vs_proto_name(svc->protocol), &svc->addr.in6, ntohs(svc->port), msg); #endif } else { IP_VS_ERR_RL("%s: %s %pI4:%d - %s\n", - sched->name, ip_vs_proto_name(svc->protocol), + sched_name, ip_vs_proto_name(svc->protocol), &svc->addr.ip, ntohs(svc->port), msg); } } From 71563f3414e917c62acd8e0fb0edf8ed6af63e4b Mon Sep 17 00:00:00 2001 From: Alex Gartrell Date: Sun, 5 Jul 2015 14:28:26 -0700 Subject: [PATCH 039/428] ipvs: skb_orphan in case of forwarding It is possible that we bind against a local socket in early_demux when we are actually going to want to forward it. In this case, the socket serves no purpose and only serves to confuse things (particularly functions which implicitly expect sk_fullsock to be true, like ip_local_out). Additionally, skb_set_owner_w is totally broken for non full-socks. Signed-off-by: Alex Gartrell Fixes: 41063e9dd119 ("ipv4: Early TCP socket demux.") Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- net/netfilter/ipvs/ip_vs_xmit.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index ec30d68ccc0b..34dc1429ebdb 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -533,6 +533,21 @@ static inline int ip_vs_tunnel_xmit_prepare(struct sk_buff *skb, return ret; } +/* In the event of a remote destination, it's possible that we would have + * matches against an old socket (particularly a TIME-WAIT socket). This + * causes havoc down the line (ip_local_out et. al. expect regular sockets + * and invalid memory accesses will happen) so simply drop the association + * in this case. +*/ +static inline void ip_vs_drop_early_demux_sk(struct sk_buff *skb) +{ + /* If dev is set, the packet came from the LOCAL_IN callback and + * not from a local TCP socket. + */ + if (skb->dev) + skb_orphan(skb); +} + /* return NF_STOLEN (sent) or NF_ACCEPT if local=1 (not sent) */ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb, struct ip_vs_conn *cp, int local) @@ -544,12 +559,21 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb, ip_vs_notrack(skb); else ip_vs_update_conntrack(skb, cp, 1); + + /* Remove the early_demux association unless it's bound for the + * exact same port and address on this host after translation. + */ + if (!local || cp->vport != cp->dport || + !ip_vs_addr_equal(cp->af, &cp->vaddr, &cp->daddr)) + ip_vs_drop_early_demux_sk(skb); + if (!local) { skb_forward_csum(skb); NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb, NULL, skb_dst(skb)->dev, dst_output_sk); } else ret = NF_ACCEPT; + return ret; } @@ -563,6 +587,7 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb, if (likely(!(cp->flags & IP_VS_CONN_F_NFCT))) ip_vs_notrack(skb); if (!local) { + ip_vs_drop_early_demux_sk(skb); skb_forward_csum(skb); NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb, NULL, skb_dst(skb)->dev, dst_output_sk); @@ -851,6 +876,8 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af, struct ipv6hdr *old_ipv6h = NULL; #endif + ip_vs_drop_early_demux_sk(skb); + if (skb_headroom(skb) < max_headroom || skb_cloned(skb)) { new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) From 56184858d1fc95c46723436b455cb7261cd8be6f Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Wed, 8 Jul 2015 08:31:33 +0300 Subject: [PATCH 040/428] ipvs: fix crash with sync protocol v0 and FTP Fix crash in 3.5+ if FTP is used after switching sync_version to 0. Fixes: 749c42b620a9 ("ipvs: reduce sync rate with time thresholds") Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- net/netfilter/ipvs/ip_vs_sync.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index b08ba9538d12..d99ad93eb855 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -612,7 +612,7 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp, pkts = atomic_add_return(1, &cp->in_pkts); else pkts = sysctl_sync_threshold(ipvs); - ip_vs_sync_conn(net, cp->control, pkts); + ip_vs_sync_conn(net, cp, pkts); } } From e3895c0334d0ef46e80f22eaf2a52401ff6d5a67 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 9 Jul 2015 11:15:27 +0300 Subject: [PATCH 041/428] ipvs: call skb_sender_cpu_clear Reset XPS's sender_cpu on forwarding. Signed-off-by: Julian Anastasov Fixes: 2bd82484bb4c ("xps: fix xps for stacked devices") Signed-off-by: Simon Horman --- net/netfilter/ipvs/ip_vs_xmit.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 34dc1429ebdb..258a0b0e82a2 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -529,6 +529,8 @@ static inline int ip_vs_tunnel_xmit_prepare(struct sk_buff *skb, if (ret == NF_ACCEPT) { nf_reset(skb); skb_forward_csum(skb); + if (!skb->sk) + skb_sender_cpu_clear(skb); } return ret; } @@ -569,6 +571,8 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb, if (!local) { skb_forward_csum(skb); + if (!skb->sk) + skb_sender_cpu_clear(skb); NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb, NULL, skb_dst(skb)->dev, dst_output_sk); } else @@ -589,6 +593,8 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb, if (!local) { ip_vs_drop_early_demux_sk(skb); skb_forward_csum(skb); + if (!skb->sk) + skb_sender_cpu_clear(skb); NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb, NULL, skb_dst(skb)->dev, dst_output_sk); } else From 2c57d478018551f2a0983293413f2f198e49ec23 Mon Sep 17 00:00:00 2001 From: Jeeja KP Date: Tue, 14 Jul 2015 13:10:47 +0530 Subject: [PATCH 042/428] ASoC: topology: Fix to add dapm mixer info Mixer control for widgets can't be created if the info is NULL. So assign the correct info for this. Signed-off-by: Jeeja KP Signed-off-by: Subhransu S. Prusty Acked-by: Liam Girdwood Signed-off-by: Mark Brown --- sound/soc/soc-topology.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 7a19df313fe8..59ac211f8fe7 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -144,7 +144,7 @@ static const struct snd_soc_tplg_kcontrol_ops io_ops[] = { {SND_SOC_TPLG_CTL_STROBE, snd_soc_get_strobe, snd_soc_put_strobe, NULL}, {SND_SOC_TPLG_DAPM_CTL_VOLSW, snd_soc_dapm_get_volsw, - snd_soc_dapm_put_volsw, NULL}, + snd_soc_dapm_put_volsw, snd_soc_info_volsw}, {SND_SOC_TPLG_DAPM_CTL_ENUM_DOUBLE, snd_soc_dapm_get_enum_double, snd_soc_dapm_put_enum_double, snd_soc_info_enum_double}, {SND_SOC_TPLG_DAPM_CTL_ENUM_VIRT, snd_soc_dapm_get_enum_double, From c9ddbac9c89110f77cb0fa07e634aaf1194899aa Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Tue, 14 Jul 2015 18:27:46 -0500 Subject: [PATCH 043/428] PCI: Restore PCI_MSIX_FLAGS_BIRMASK definition 09a2c73ddfc7 ("PCI: Remove unused PCI_MSIX_FLAGS_BIRMASK definition") removed PCI_MSIX_FLAGS_BIRMASK from an exported header because it was unused in the kernel. But that breaks user programs that were using it (QEMU in particular). Restore the PCI_MSIX_FLAGS_BIRMASK definition. [bhelgaas: changelog] Signed-off-by: Michael S. Tsirkin Signed-off-by: Bjorn Helgaas CC: stable@vger.kernel.org # v3.13+ --- include/uapi/linux/pci_regs.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index efe3443572ba..413417f3707b 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -319,6 +319,7 @@ #define PCI_MSIX_PBA 8 /* Pending Bit Array offset */ #define PCI_MSIX_PBA_BIR 0x00000007 /* BAR index */ #define PCI_MSIX_PBA_OFFSET 0xfffffff8 /* Offset into specified BAR */ +#define PCI_MSIX_FLAGS_BIRMASK PCI_MSIX_PBA_BIR /* deprecated */ #define PCI_CAP_MSIX_SIZEOF 12 /* size of MSIX registers */ /* MSI-X Table entry format */ From 412efa73dcd3bd03c1838c91e094533a95529039 Mon Sep 17 00:00:00 2001 From: Shilpa Sreeramalu Date: Wed, 15 Jul 2015 07:58:09 -0700 Subject: [PATCH 044/428] ASoC: Intel: Get correct usage_count value to load firmware The usage_count variable was read before it was set to the correct value, due to which the firmware load was failing. Because of this IPC messages sent to the firmware were timing out causing a delay of about 1 second while playing audio from the internal speakers. With this patch the usage_count is read after the function call pm_runtime_get_sync which will increment the usage_count variable and the firmware load is successful and all the IPC messages are processed correctly. Signed-off-by: Shilpa Sreeramalu Signed-off-by: Fang, Yang A Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- sound/soc/intel/atom/sst/sst_drv_interface.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/sound/soc/intel/atom/sst/sst_drv_interface.c b/sound/soc/intel/atom/sst/sst_drv_interface.c index 620da1d1b9e3..0e0e4d9c021f 100644 --- a/sound/soc/intel/atom/sst/sst_drv_interface.c +++ b/sound/soc/intel/atom/sst/sst_drv_interface.c @@ -42,6 +42,11 @@ #define MIN_FRAGMENT_SIZE (50 * 1024) #define MAX_FRAGMENT_SIZE (1024 * 1024) #define SST_GET_BYTES_PER_SAMPLE(pcm_wd_sz) (((pcm_wd_sz + 15) >> 4) << 1) +#ifdef CONFIG_PM +#define GET_USAGE_COUNT(dev) (atomic_read(&dev->power.usage_count)) +#else +#define GET_USAGE_COUNT(dev) 1 +#endif int free_stream_context(struct intel_sst_drv *ctx, unsigned int str_id) { @@ -141,15 +146,9 @@ static int sst_power_control(struct device *dev, bool state) int ret = 0; int usage_count = 0; -#ifdef CONFIG_PM - usage_count = atomic_read(&dev->power.usage_count); -#else - usage_count = 1; -#endif - if (state == true) { ret = pm_runtime_get_sync(dev); - + usage_count = GET_USAGE_COUNT(dev); dev_dbg(ctx->dev, "Enable: pm usage count: %d\n", usage_count); if (ret < 0) { dev_err(ctx->dev, "Runtime get failed with err: %d\n", ret); @@ -164,6 +163,7 @@ static int sst_power_control(struct device *dev, bool state) } } } else { + usage_count = GET_USAGE_COUNT(dev); dev_dbg(ctx->dev, "Disable: pm usage count: %d\n", usage_count); return sst_pm_runtime_put(ctx); } From 91a57731eed05714609855b1d72e6118b6b3ec6f Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Wed, 8 Jul 2015 17:34:43 +0300 Subject: [PATCH 045/428] ARM: DRA7: hwmod: fix gpmc hwmod GPMC smart idle is not really broken but it does not support smart idle with wakeup. Fixes: 556708fe8718 ("ARM: OMAP: DRA7: hwmod: Make gpmc software supervised as the smart idle is broken") Signed-off-by: Roger Quadros Reviewed-by: Paul Walmsley Signed-off-by: Paul Walmsley --- arch/arm/mach-omap2/omap_hwmod_7xx_data.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c index 2606c6608bd8..562247bced49 100644 --- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c @@ -827,8 +827,7 @@ static struct omap_hwmod_class_sysconfig dra7xx_gpmc_sysc = { .syss_offs = 0x0014, .sysc_flags = (SYSC_HAS_AUTOIDLE | SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET | SYSS_HAS_RESET_STATUS), - .idlemodes = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART | - SIDLE_SMART_WKUP), + .idlemodes = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART), .sysc_fields = &omap_hwmod_sysc_type1, }; @@ -844,7 +843,7 @@ static struct omap_hwmod dra7xx_gpmc_hwmod = { .class = &dra7xx_gpmc_hwmod_class, .clkdm_name = "l3main1_clkdm", /* Skip reset for CONFIG_OMAP_GPMC_DEBUG for bootloader timings */ - .flags = HWMOD_SWSUP_SIDLE | DEBUG_OMAP_GPMC_HWMOD_FLAGS, + .flags = DEBUG_OMAP_GPMC_HWMOD_FLAGS, .main_clk = "l3_iclk_div", .prcm = { .omap4 = { From f2a5ded38592e5936a099ea6535ad5d3addcbc9d Mon Sep 17 00:00:00 2001 From: Nicolas Boichat Date: Fri, 17 Jul 2015 10:36:57 +0800 Subject: [PATCH 046/428] ASoC: rt5645: Check if codec is initialized in workqueue handler This fixes kernel panic on boot, if rt5645->codec is NULL when rt5645_jack_detect_work is first called. rt5645_jack_detect_work needs rt5645->codec to be initialized to setup dapm pins. Also, reporting jack events is useless, as the jacks cannot be set before the codec is ready. Since we manually call the interrupt handler in rt5645_set_jack_detect, the initial jack state will be reported correctly, and dapm pins will be setup at that time. Signed-off-by: Nicolas Boichat Signed-off-by: Mark Brown --- sound/soc/codecs/rt5645.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index 9ce311e088fc..e9cc3aae5366 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -2943,6 +2943,9 @@ static int rt5645_irq_detection(struct rt5645_priv *rt5645) { int val, btn_type, gpio_state = 0, report = 0; + if (!rt5645->codec) + return -EINVAL; + switch (rt5645->pdata.jd_mode) { case 0: /* Not using rt5645 JD */ if (rt5645->gpiod_hp_det) { From 653cdc13a340ad1cef29f1bab0d05d0771fa1d57 Mon Sep 17 00:00:00 2001 From: Reinhard Speyerer Date: Tue, 14 Jul 2015 22:55:06 +0200 Subject: [PATCH 047/428] USB: qcserial/option: make AT URCs work for Sierra Wireless MC7305/MC7355 Tests with a Sierra Wireless MC7355 have shown that 1199:9041 devices also require the option_send_setup() code to be used on the USB interface for the AT port to make unsolicited response codes work correctly. Move these devices from the qcserial driver to the option driver like it has been done for the 1199:68c0 devices in commit d80c0d14183516f184a5ac88e11008ee4c7d2a2e ("USB: qcserial/option: make AT URCs work for Sierra Wireless MC73xx"). Signed-off-by: Reinhard Speyerer Cc: stable Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 2 ++ drivers/usb/serial/qcserial.c | 1 - 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 19b85ee98a72..876423b8892c 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1099,6 +1099,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */ { USB_DEVICE_INTERFACE_CLASS(SIERRA_VENDOR_ID, 0x68c0, 0xff), .driver_info = (kernel_ulong_t)&sierra_mc73xx_blacklist }, /* MC73xx */ + { USB_DEVICE_INTERFACE_CLASS(SIERRA_VENDOR_ID, 0x9041, 0xff), + .driver_info = (kernel_ulong_t)&sierra_mc73xx_blacklist }, /* MC7305/MC7355 */ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6003), diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index 9c63897b3a56..552dc9a7f523 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -145,7 +145,6 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x1199, 0x901c)}, /* Sierra Wireless EM7700 */ {DEVICE_SWI(0x1199, 0x901f)}, /* Sierra Wireless EM7355 */ {DEVICE_SWI(0x1199, 0x9040)}, /* Sierra Wireless Modem */ - {DEVICE_SWI(0x1199, 0x9041)}, /* Sierra Wireless MC7305/MC7355 */ {DEVICE_SWI(0x1199, 0x9051)}, /* Netgear AirCard 340U */ {DEVICE_SWI(0x1199, 0x9053)}, /* Sierra Wireless Modem */ {DEVICE_SWI(0x1199, 0x9054)}, /* Sierra Wireless Modem */ From aeec6cdad6cda5fdf26f937c0d15f101539d8185 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 16 Jul 2015 16:56:14 +0530 Subject: [PATCH 048/428] ARC/time: Migrate to new 'set-state' interface Migrate arc driver to the new 'set-state' interface provided by clockevents core, the earlier 'set-mode' interface is marked obsolete now. This also enables us to implement callbacks for new states of clockevent devices, for example: ONESHOT_STOPPED. Cc: Vineet Gupta Signed-off-by: Viresh Kumar Signed-off-by: Vineet Gupta --- arch/arc/kernel/time.c | 40 +++++++++++++++------------------------- 1 file changed, 15 insertions(+), 25 deletions(-) diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c index 3364d2bbc515..4294761a2b3e 100644 --- a/arch/arc/kernel/time.c +++ b/arch/arc/kernel/time.c @@ -203,34 +203,24 @@ static int arc_clkevent_set_next_event(unsigned long delta, return 0; } -static void arc_clkevent_set_mode(enum clock_event_mode mode, - struct clock_event_device *dev) +static int arc_clkevent_set_periodic(struct clock_event_device *dev) { - switch (mode) { - case CLOCK_EVT_MODE_PERIODIC: - /* - * At X Hz, 1 sec = 1000ms -> X cycles; - * 10ms -> X / 100 cycles - */ - arc_timer_event_setup(arc_get_core_freq() / HZ); - break; - case CLOCK_EVT_MODE_ONESHOT: - break; - default: - break; - } - - return; + /* + * At X Hz, 1 sec = 1000ms -> X cycles; + * 10ms -> X / 100 cycles + */ + arc_timer_event_setup(arc_get_core_freq() / HZ); + return 0; } static DEFINE_PER_CPU(struct clock_event_device, arc_clockevent_device) = { - .name = "ARC Timer0", - .features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC, - .mode = CLOCK_EVT_MODE_UNUSED, - .rating = 300, - .irq = TIMER0_IRQ, /* hardwired, no need for resources */ - .set_next_event = arc_clkevent_set_next_event, - .set_mode = arc_clkevent_set_mode, + .name = "ARC Timer0", + .features = CLOCK_EVT_FEAT_ONESHOT | + CLOCK_EVT_FEAT_PERIODIC, + .rating = 300, + .irq = TIMER0_IRQ, /* hardwired, no need for resources */ + .set_next_event = arc_clkevent_set_next_event, + .set_state_periodic = arc_clkevent_set_periodic, }; static irqreturn_t timer_irq_handler(int irq, void *dev_id) @@ -240,7 +230,7 @@ static irqreturn_t timer_irq_handler(int irq, void *dev_id) * irq_set_chip_and_handler() asked for handle_percpu_devid_irq() */ struct clock_event_device *evt = this_cpu_ptr(&arc_clockevent_device); - int irq_reenable = evt->mode == CLOCK_EVT_MODE_PERIODIC; + int irq_reenable = clockevent_state_periodic(evt); /* * Any write to CTRL reg ACks the interrupt, we rewrite the From d05a76ab4d9ece9bd987a8c29e3f384ec9f7b211 Mon Sep 17 00:00:00 2001 From: Alexey Brodkin Date: Thu, 16 Jul 2015 21:45:38 +0300 Subject: [PATCH 049/428] ARCv2: add knob for DIV_REV in Kconfig Being highly configurable core ARC HS among other features might be configured with or without DIV_REM_OPTION (hardware divider). That option when enabled adds following instructions: div, divu, rem, remu. By default ARC HS38 has this option enabled. So we add here possibility to disable usage of hardware divider by compiler. Signed-off-by: Alexey Brodkin Signed-off-by: Vineet Gupta --- arch/arc/Kconfig | 4 ++++ arch/arc/Makefile | 10 +++++++++- 2 files changed, 13 insertions(+), 1 deletion(-) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 91cf4055acab..f7cfa7d574f6 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -379,6 +379,10 @@ config ARC_HAS_LL64 dest operands with 2 possible source operands. default y +config ARC_HAS_DIV_REM + bool "Insn: div, divu, rem, remu" + default y + config ARC_HAS_RTC bool "Local 64-bit r/o cycle counter" default n diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 46d87310220d..8a27a48304a4 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -36,8 +36,16 @@ cflags-$(atleast_gcc44) += -fsection-anchors cflags-$(CONFIG_ARC_HAS_LLSC) += -mlock cflags-$(CONFIG_ARC_HAS_SWAPE) += -mswape +ifdef CONFIG_ISA_ARCV2 + ifndef CONFIG_ARC_HAS_LL64 -cflags-$(CONFIG_ISA_ARCV2) += -mno-ll64 +cflags-y += -mno-ll64 +endif + +ifndef CONFIG_ARC_HAS_DIV_REM +cflags-y += -mno-div-rem +endif + endif cflags-$(CONFIG_ARC_DW2_UNWIND) += -fasynchronous-unwind-tables From 6da3700c98cdc8360f55c5510915efae1d66deea Mon Sep 17 00:00:00 2001 From: Pieter Hollants Date: Mon, 20 Jul 2015 11:56:17 +0200 Subject: [PATCH 050/428] USB: qcserial: Add support for Dell Wireless 5809e 4G Modem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Added the USB IDs 0x413c:0x81b1 for the "Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card", a Dell-branded Sierra Wireless EM7305 LTE card in M.2 form factor, used eg. in Dell's Latitude E7540 Notebook series. "lsusb -v" output for this device: Bus 002 Device 003: ID 413c:81b1 Dell Computer Corp. Device Descriptor: bLength 18 bDescriptorType 1 bcdUSB 2.00 bDeviceClass 0 bDeviceSubClass 0 bDeviceProtocol 0 bMaxPacketSize0 64 idVendor 0x413c Dell Computer Corp. idProduct 0x81b1 bcdDevice 0.06 iManufacturer 1 Sierra Wireless, Incorporated iProduct 2 Dell Wireless 5809e Gobi™ 4G LTE Mobile Broadband Card iSerial 3 bNumConfigurations 2 Configuration Descriptor: bLength 9 bDescriptorType 2 wTotalLength 204 bNumInterfaces 4 bConfigurationValue 1 iConfiguration 0 bmAttributes 0xe0 Self Powered Remote Wakeup MaxPower 500mA Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 0 bAlternateSetting 0 bNumEndpoints 2 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 255 Vendor Specific Subclass bInterfaceProtocol 255 Vendor Specific Protocol iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x81 EP 1 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x01 EP 1 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 2 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 0 bInterfaceProtocol 0 iInterface 0 ** UNRECOGNIZED: 05 24 00 10 01 ** UNRECOGNIZED: 05 24 01 00 00 ** UNRECOGNIZED: 04 24 02 02 ** UNRECOGNIZED: 05 24 06 00 00 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x83 EP 3 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x000c 1x 12 bytes bInterval 9 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x82 EP 2 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x02 EP 2 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 3 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 0 bInterfaceProtocol 0 iInterface 0 ** UNRECOGNIZED: 05 24 00 10 01 ** UNRECOGNIZED: 05 24 01 00 00 ** UNRECOGNIZED: 04 24 02 02 ** UNRECOGNIZED: 05 24 06 00 00 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x85 EP 5 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x000c 1x 12 bytes bInterval 9 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x84 EP 4 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x03 EP 3 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 8 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 255 Vendor Specific Subclass bInterfaceProtocol 255 Vendor Specific Protocol iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x87 EP 7 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x000a 1x 10 bytes bInterval 9 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x86 EP 6 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x04 EP 4 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 ** UNRECOGNIZED: 2c ff 42 49 53 54 00 01 07 f5 40 f6 00 00 00 00 01 f7 c4 09 02 f8 c4 09 03 f9 88 13 04 fa 10 27 05 fb 10 27 06 fc c4 09 07 fd c4 09 Configuration Descriptor: bLength 9 bDescriptorType 2 wTotalLength 95 bNumInterfaces 2 bConfigurationValue 2 iConfiguration 0 bmAttributes 0xe0 Self Powered Remote Wakeup MaxPower 500mA Interface Association: bLength 8 bDescriptorType 11 bFirstInterface 12 bInterfaceCount 2 bFunctionClass 2 Communications bFunctionSubClass 14 bFunctionProtocol 0 iFunction 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 12 bAlternateSetting 0 bNumEndpoints 1 bInterfaceClass 2 Communications bInterfaceSubClass 14 bInterfaceProtocol 0 iInterface 0 CDC Header: bcdCDC 1.10 CDC Union: bMasterInterface 12 bSlaveInterface 13 CDC MBIM: bcdMBIMVersion 1.00 wMaxControlMessage 4096 bNumberFilters 32 bMaxFilterSize 128 wMaxSegmentSize 1500 bmNetworkCapabilities 0x20 8-byte ntb input size CDC MBIM Extended: bcdMBIMExtendedVersion 1.00 bMaxOutstandingCommandMessages 64 wMTU 1500 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x82 EP 2 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 9 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 13 bAlternateSetting 0 bNumEndpoints 0 bInterfaceClass 10 CDC Data bInterfaceSubClass 0 bInterfaceProtocol 2 iInterface 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 13 bAlternateSetting 1 bNumEndpoints 2 bInterfaceClass 10 CDC Data bInterfaceSubClass 0 bInterfaceProtocol 2 iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x81 EP 1 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x01 EP 1 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Device Qualifier (for other device speed): bLength 10 bDescriptorType 6 bcdUSB 2.00 bDeviceClass 0 bDeviceSubClass 0 bDeviceProtocol 0 bMaxPacketSize0 64 bNumConfigurations 2 Device Status: 0x0000 (Bus Powered) Signed-off-by: Pieter Hollants Cc: stable Signed-off-by: Johan Hovold --- drivers/usb/serial/qcserial.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index 552dc9a7f523..d156545728c2 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -157,6 +157,7 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x413c, 0x81a4)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a8)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a9)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */ + {DEVICE_SWI(0x413c, 0x81b1)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */ /* Huawei devices */ {DEVICE_HWI(0x03f0, 0x581d)}, /* HP lt4112 LTE/HSPA+ Gobi 4G Modem (Huawei me906e) */ From 929423fa83e5b75e94101b280738b9a5a376a0e1 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 20 Jul 2015 13:49:39 +0200 Subject: [PATCH 051/428] xen: release lock occasionally during ballooning When dom0 is being ballooned balloon_process() will hold the balloon mutex until it is finished. This will block e.g. creation of new domains as the device backends for the new domain need some autoballooned pages for the ring buffers. Avoid this by releasing the balloon mutex from time to time during ballooning. Adjust the comment above balloon_process() regarding multiple instances of balloon_process(). Instead of open coding it, just use cond_resched(). Signed-off-by: Juergen Gross Signed-off-by: David Vrabel --- drivers/xen/balloon.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index fd933695f232..bf4a23c7c591 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -472,7 +472,7 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) } /* - * We avoid multiple worker processes conflicting via the balloon mutex. + * As this is a work item it is guaranteed to run as a single instance only. * We may of course race updates of the target counts (which are protected * by the balloon lock), or with changes to the Xen hard limit, but we will * recover from these in time. @@ -482,9 +482,10 @@ static void balloon_process(struct work_struct *work) enum bp_state state = BP_DONE; long credit; - mutex_lock(&balloon_mutex); do { + mutex_lock(&balloon_mutex); + credit = current_credit(); if (credit > 0) { @@ -499,17 +500,15 @@ static void balloon_process(struct work_struct *work) state = update_schedule(state); -#ifndef CONFIG_PREEMPT - if (need_resched()) - schedule(); -#endif + mutex_unlock(&balloon_mutex); + + cond_resched(); + } while (credit && state == BP_DONE); /* Schedule more work if there is some still to be done. */ if (state == BP_EAGAIN) schedule_delayed_work(&balloon_worker, balloon_stats.schedule_delay * HZ); - - mutex_unlock(&balloon_mutex); } /* Resets the Xen limit, sets new target, and kicks off processing. */ From 0838aa7fcfcd875caa7bcc5dab0c3fd40444553d Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 13 Jul 2015 15:11:48 +0200 Subject: [PATCH 052/428] netfilter: fix netns dependencies with conntrack templates Quoting Daniel Borkmann: "When adding connection tracking template rules to a netns, f.e. to configure netfilter zones, the kernel will endlessly busy-loop as soon as we try to delete the given netns in case there's at least one template present, which is problematic i.e. if there is such bravery that the priviledged user inside the netns is assumed untrusted. Minimal example: ip netns add foo ip netns exec foo iptables -t raw -A PREROUTING -d 1.2.3.4 -j CT --zone 1 ip netns del foo What happens is that when nf_ct_iterate_cleanup() is being called from nf_conntrack_cleanup_net_list() for a provided netns, we always end up with a net->ct.count > 0 and thus jump back to i_see_dead_people. We don't get a soft-lockup as we still have a schedule() point, but the serving CPU spins on 100% from that point onwards. Since templates are normally allocated with nf_conntrack_alloc(), we also bump net->ct.count. The issue why they are not yet nf_ct_put() is because the per netns .exit() handler from x_tables (which would eventually invoke xt_CT's xt_ct_tg_destroy() that drops reference on info->ct) is called in the dependency chain at a *later* point in time than the per netns .exit() handler for the connection tracker. This is clearly a chicken'n'egg problem: after the connection tracker .exit() handler, we've teared down all the connection tracking infrastructure already, so rightfully, xt_ct_tg_destroy() cannot be invoked at a later point in time during the netns cleanup, as that would lead to a use-after-free. At the same time, we cannot make x_tables depend on the connection tracker module, so that the xt_ct_tg_destroy() would be invoked earlier in the cleanup chain." Daniel confirms this has to do with the order in which modules are loaded or having compiled nf_conntrack as modules while x_tables built-in. So we have no guarantees regarding the order in which netns callbacks are executed. Fix this by allocating the templates through kmalloc() from the respective SYNPROXY and CT targets, so they don't depend on the conntrack kmem cache. Then, release then via nf_ct_tmpl_free() from destroy_conntrack(). This branch is marked as unlikely since conntrack templates are rarely allocated and only from the configuration plane path. Note that templates are not kept in any list to avoid further dependencies with nf_conntrack anymore, thus, the tmpl larval list is removed. Reported-by: Daniel Borkmann Signed-off-by: Pablo Neira Ayuso Tested-by: Daniel Borkmann --- include/net/netfilter/nf_conntrack.h | 2 +- include/net/netns/conntrack.h | 1 - net/netfilter/nf_conntrack_core.c | 67 ++++++++++++++++++---------- net/netfilter/nf_synproxy_core.c | 7 ++- net/netfilter/xt_CT.c | 8 ++-- 5 files changed, 51 insertions(+), 34 deletions(-) diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 095433b8a8b0..37cd3911d5c5 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -291,7 +291,7 @@ extern unsigned int nf_conntrack_max; extern unsigned int nf_conntrack_hash_rnd; void init_nf_conntrack_hash_rnd(void); -void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl); +struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags); #define NF_CT_STAT_INC(net, count) __this_cpu_inc((net)->ct.stat->count) #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count) diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index 29d6a94db54d..723b61c82b3f 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -68,7 +68,6 @@ struct ct_pcpu { spinlock_t lock; struct hlist_nulls_head unconfirmed; struct hlist_nulls_head dying; - struct hlist_nulls_head tmpl; }; struct netns_ct { diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 13fad8668f83..651039ad1681 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -287,6 +287,46 @@ static void nf_ct_del_from_dying_or_unconfirmed_list(struct nf_conn *ct) spin_unlock(&pcpu->lock); } +/* Released via destroy_conntrack() */ +struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags) +{ + struct nf_conn *tmpl; + + tmpl = kzalloc(sizeof(struct nf_conn), GFP_KERNEL); + if (tmpl == NULL) + return NULL; + + tmpl->status = IPS_TEMPLATE; + write_pnet(&tmpl->ct_net, net); + +#ifdef CONFIG_NF_CONNTRACK_ZONES + if (zone) { + struct nf_conntrack_zone *nf_ct_zone; + + nf_ct_zone = nf_ct_ext_add(tmpl, NF_CT_EXT_ZONE, GFP_ATOMIC); + if (!nf_ct_zone) + goto out_free; + nf_ct_zone->id = zone; + } +#endif + atomic_set(&tmpl->ct_general.use, 0); + + return tmpl; +#ifdef CONFIG_NF_CONNTRACK_ZONES +out_free: + kfree(tmpl); + return NULL; +#endif +} +EXPORT_SYMBOL_GPL(nf_ct_tmpl_alloc); + +static void nf_ct_tmpl_free(struct nf_conn *tmpl) +{ + nf_ct_ext_destroy(tmpl); + nf_ct_ext_free(tmpl); + kfree(tmpl); +} + static void destroy_conntrack(struct nf_conntrack *nfct) { @@ -298,6 +338,10 @@ destroy_conntrack(struct nf_conntrack *nfct) NF_CT_ASSERT(atomic_read(&nfct->use) == 0); NF_CT_ASSERT(!timer_pending(&ct->timeout)); + if (unlikely(nf_ct_is_template(ct))) { + nf_ct_tmpl_free(ct); + return; + } rcu_read_lock(); l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); if (l4proto && l4proto->destroy) @@ -540,28 +584,6 @@ out: } EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert); -/* deletion from this larval template list happens via nf_ct_put() */ -void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl) -{ - struct ct_pcpu *pcpu; - - __set_bit(IPS_TEMPLATE_BIT, &tmpl->status); - __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); - nf_conntrack_get(&tmpl->ct_general); - - /* add this conntrack to the (per cpu) tmpl list */ - local_bh_disable(); - tmpl->cpu = smp_processor_id(); - pcpu = per_cpu_ptr(nf_ct_net(tmpl)->ct.pcpu_lists, tmpl->cpu); - - spin_lock(&pcpu->lock); - /* Overload tuple linked list to put us in template list. */ - hlist_nulls_add_head_rcu(&tmpl->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, - &pcpu->tmpl); - spin_unlock_bh(&pcpu->lock); -} -EXPORT_SYMBOL_GPL(nf_conntrack_tmpl_insert); - /* Confirm a connection given skb; places it in hash table */ int __nf_conntrack_confirm(struct sk_buff *skb) @@ -1751,7 +1773,6 @@ int nf_conntrack_init_net(struct net *net) spin_lock_init(&pcpu->lock); INIT_HLIST_NULLS_HEAD(&pcpu->unconfirmed, UNCONFIRMED_NULLS_VAL); INIT_HLIST_NULLS_HEAD(&pcpu->dying, DYING_NULLS_VAL); - INIT_HLIST_NULLS_HEAD(&pcpu->tmpl, TEMPLATE_NULLS_VAL); } net->ct.stat = alloc_percpu(struct ip_conntrack_stat); diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 789feeae6c44..71f1e9fdfa18 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -349,12 +349,10 @@ static void __net_exit synproxy_proc_exit(struct net *net) static int __net_init synproxy_net_init(struct net *net) { struct synproxy_net *snet = synproxy_pernet(net); - struct nf_conntrack_tuple t; struct nf_conn *ct; int err = -ENOMEM; - memset(&t, 0, sizeof(t)); - ct = nf_conntrack_alloc(net, 0, &t, &t, GFP_KERNEL); + ct = nf_ct_tmpl_alloc(net, 0, GFP_KERNEL); if (IS_ERR(ct)) { err = PTR_ERR(ct); goto err1; @@ -365,7 +363,8 @@ static int __net_init synproxy_net_init(struct net *net) if (!nfct_synproxy_ext_add(ct)) goto err2; - nf_conntrack_tmpl_insert(net, ct); + __set_bit(IPS_CONFIRMED_BIT, &ct->status); + nf_conntrack_get(&ct->ct_general); snet->tmpl = ct; snet->stats = alloc_percpu(struct synproxy_stats); diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 75747aecdebe..c6630030c912 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -184,7 +184,6 @@ out: static int xt_ct_tg_check(const struct xt_tgchk_param *par, struct xt_ct_target_info_v1 *info) { - struct nf_conntrack_tuple t; struct nf_conn *ct; int ret = -EOPNOTSUPP; @@ -202,8 +201,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, if (ret < 0) goto err1; - memset(&t, 0, sizeof(t)); - ct = nf_conntrack_alloc(par->net, info->zone, &t, &t, GFP_KERNEL); + ct = nf_ct_tmpl_alloc(par->net, info->zone, GFP_KERNEL); ret = PTR_ERR(ct); if (IS_ERR(ct)) goto err2; @@ -227,8 +225,8 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, if (ret < 0) goto err3; } - - nf_conntrack_tmpl_insert(par->net, ct); + __set_bit(IPS_CONFIRMED_BIT, &ct->status); + nf_conntrack_get(&ct->ct_general); out: info->ct = ct; return 0; From 21481f2cfef9a79d3676916ef9424b1a7794776c Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Mon, 20 Jul 2015 17:19:17 +0300 Subject: [PATCH 053/428] ARCv2: lib: memcpy: Missing PREFETCHW Signed-off-by: Vineet Gupta --- arch/arc/lib/memcpy-archs.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arc/lib/memcpy-archs.S b/arch/arc/lib/memcpy-archs.S index 1b2b3acfed52..0cab0b8a57c5 100644 --- a/arch/arc/lib/memcpy-archs.S +++ b/arch/arc/lib/memcpy-archs.S @@ -206,7 +206,7 @@ unalignedOffby3: ld.ab r6, [r1, 4] prefetch [r1, 28] ;Prefetch the next read location ld.ab r8, [r1,4] - prefetch [r3, 32] ;Prefetch the next write location + prefetchw [r3, 32] ;Prefetch the next write location SHIFT_1 (r7, r6, 8) or r7, r7, r5 From 262137bca7cfbe690f8e904822b68f720998324a Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Mon, 20 Jul 2015 12:05:03 +0300 Subject: [PATCH 054/428] ARCv2: lib: memset: Don't assume 64-bit load/stores There are configurations which may not have LDD/STD Signed-off-by: Claudiu Zissulescu Signed-off-by: Alexey Brodkin Signed-off-by: Vineet Gupta --- arch/arc/lib/memset-archs.S | 43 +++++++++++++++++++++++++++++++------ 1 file changed, 36 insertions(+), 7 deletions(-) diff --git a/arch/arc/lib/memset-archs.S b/arch/arc/lib/memset-archs.S index 92d573c734b5..365b18364815 100644 --- a/arch/arc/lib/memset-archs.S +++ b/arch/arc/lib/memset-archs.S @@ -10,12 +10,6 @@ #undef PREALLOC_NOT_AVAIL -#ifdef PREALLOC_NOT_AVAIL -#define PREWRITE(A,B) prefetchw [(A),(B)] -#else -#define PREWRITE(A,B) prealloc [(A),(B)] -#endif - ENTRY(memset) prefetchw [r0] ; Prefetch the write location mov.f 0, r2 @@ -51,9 +45,15 @@ ENTRY(memset) ;;; Convert len to Dwords, unfold x8 lsr.f lp_count, lp_count, 6 + lpnz @.Lset64bytes ;; LOOP START - PREWRITE(r3, 64) ;Prefetch the next write location +#ifdef PREALLOC_NOT_AVAIL + prefetchw [r3, 64] ;Prefetch the next write location +#else + prealloc [r3, 64] +#endif +#ifdef CONFIG_ARC_HAS_LL64 std.ab r4, [r3, 8] std.ab r4, [r3, 8] std.ab r4, [r3, 8] @@ -62,16 +62,45 @@ ENTRY(memset) std.ab r4, [r3, 8] std.ab r4, [r3, 8] std.ab r4, [r3, 8] +#else + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] +#endif .Lset64bytes: lsr.f lp_count, r2, 5 ;Last remaining max 124 bytes lpnz .Lset32bytes ;; LOOP START prefetchw [r3, 32] ;Prefetch the next write location +#ifdef CONFIG_ARC_HAS_LL64 std.ab r4, [r3, 8] std.ab r4, [r3, 8] std.ab r4, [r3, 8] std.ab r4, [r3, 8] +#else + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] +#endif .Lset32bytes: and.f lp_count, r2, 0x1F ;Last remaining 31 bytes From c2227a39a078473115910512aa0f8d53bd915e60 Mon Sep 17 00:00:00 2001 From: Kinglong Mee Date: Tue, 7 Jul 2015 10:16:37 +0800 Subject: [PATCH 055/428] nfsd: Drop BUG_ON and ignore SECLABEL on absent filesystem On an absent filesystem (one served by another server), we need to be able to handle requests for certain attributest (like fs_locations, so the client can find out which server does have the filesystem), but others we can't. We forgot to take that into account when adding another attribute bitmask work for the SECURITY_LABEL attribute. There an export entry with the "refer" option can result in: [ 88.414272] kernel BUG at fs/nfsd/nfs4xdr.c:2249! [ 88.414828] invalid opcode: 0000 [#1] SMP [ 88.415368] Modules linked in: rpcsec_gss_krb5 nfsv4 dns_resolver nfs fscache nfsd xfs libcrc32c iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi iosf_mbi ppdev btrfs coretemp crct10dif_pclmul crc32_pclmul crc32c_intel xor ghash_clmulni_intel raid6_pq vmw_balloon parport_pc parport i2c_piix4 shpchp vmw_vmci acpi_cpufreq auth_rpcgss nfs_acl lockd grace sunrpc vmwgfx drm_kms_helper ttm drm mptspi mptscsih serio_raw mptbase e1000 scsi_transport_spi ata_generic pata_acpi [last unloaded: nfsd] [ 88.417827] CPU: 0 PID: 2116 Comm: nfsd Not tainted 4.0.7-300.fc22.x86_64 #1 [ 88.418448] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 05/20/2014 [ 88.419093] task: ffff880079146d50 ti: ffff8800785d8000 task.ti: ffff8800785d8000 [ 88.419729] RIP: 0010:[] [] nfsd4_encode_fattr+0x820/0x1f00 [nfsd] [ 88.420376] RSP: 0000:ffff8800785db998 EFLAGS: 00010206 [ 88.421027] RAX: 0000000000000001 RBX: 000000000018091a RCX: ffff88006668b980 [ 88.421676] RDX: 00000000fffef7fc RSI: 0000000000000000 RDI: ffff880078d05000 [ 88.422315] RBP: ffff8800785dbb58 R08: ffff880078d043f8 R09: ffff880078d4a000 [ 88.422968] R10: 0000000000010000 R11: 0000000000000002 R12: 0000000000b0a23a [ 88.423612] R13: ffff880078d05000 R14: ffff880078683100 R15: ffff88006668b980 [ 88.424295] FS: 0000000000000000(0000) GS:ffff88007c600000(0000) knlGS:0000000000000000 [ 88.424944] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 88.425597] CR2: 00007f40bc370f90 CR3: 0000000035af5000 CR4: 00000000001407f0 [ 88.426285] Stack: [ 88.426921] ffff8800785dbaa8 ffffffffa049e4af ffff8800785dba08 ffffffff813298f0 [ 88.427585] ffff880078683300 ffff8800769b0de8 0000089d00000001 0000000087f805e0 [ 88.428228] ffff880000000000 ffff880079434a00 0000000000000000 ffff88006668b980 [ 88.428877] Call Trace: [ 88.429527] [] ? exp_get_by_name+0x7f/0xb0 [nfsd] [ 88.430168] [] ? inode_doinit_with_dentry+0x210/0x6a0 [ 88.430807] [] ? d_lookup+0x2e/0x60 [ 88.431449] [] ? dput+0x33/0x230 [ 88.432097] [] ? mntput+0x24/0x40 [ 88.432719] [] ? path_put+0x22/0x30 [ 88.433340] [] ? nfsd_cross_mnt+0xb7/0x1c0 [nfsd] [ 88.433954] [] nfsd4_encode_dirent+0x1b0/0x3d0 [nfsd] [ 88.434601] [] ? nfsd4_encode_getattr+0x40/0x40 [nfsd] [ 88.435172] [] nfsd_readdir+0x1c1/0x2a0 [nfsd] [ 88.435710] [] ? nfsd_direct_splice_actor+0x20/0x20 [nfsd] [ 88.436447] [] nfsd4_encode_readdir+0x120/0x220 [nfsd] [ 88.437011] [] nfsd4_encode_operation+0x7d/0x190 [nfsd] [ 88.437566] [] nfsd4_proc_compound+0x24d/0x6f0 [nfsd] [ 88.438157] [] nfsd_dispatch+0xc3/0x220 [nfsd] [ 88.438680] [] svc_process_common+0x43b/0x690 [sunrpc] [ 88.439192] [] svc_process+0x103/0x1b0 [sunrpc] [ 88.439694] [] nfsd+0x117/0x190 [nfsd] [ 88.440194] [] ? nfsd_destroy+0x90/0x90 [nfsd] [ 88.440697] [] kthread+0xd8/0xf0 [ 88.441260] [] ? kthread_worker_fn+0x180/0x180 [ 88.441762] [] ret_from_fork+0x58/0x90 [ 88.442322] [] ? kthread_worker_fn+0x180/0x180 [ 88.442879] Code: 0f 84 93 05 00 00 83 f8 ea c7 85 a0 fe ff ff 00 00 27 30 0f 84 ba fe ff ff 85 c0 0f 85 a5 fe ff ff e9 e3 f9 ff ff 0f 1f 44 00 00 <0f> 0b 66 0f 1f 44 00 00 be 04 00 00 00 4c 89 ef 4c 89 8d 68 fe [ 88.444052] RIP [] nfsd4_encode_fattr+0x820/0x1f00 [nfsd] [ 88.444658] RSP [ 88.445232] ---[ end trace 6cb9d0487d94a29f ]--- Signed-off-by: Kinglong Mee Cc: stable@vger.kernel.org Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4xdr.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 54633858733a..75e0563c09d1 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2143,6 +2143,7 @@ nfsd4_encode_aclname(struct xdr_stream *xdr, struct svc_rqst *rqstp, #define WORD0_ABSENT_FS_ATTRS (FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_FSID | \ FATTR4_WORD0_RDATTR_ERROR) #define WORD1_ABSENT_FS_ATTRS FATTR4_WORD1_MOUNTED_ON_FILEID +#define WORD2_ABSENT_FS_ATTRS 0 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL static inline __be32 @@ -2171,7 +2172,7 @@ nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp, { return 0; } #endif -static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *rdattr_err) +static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *bmval2, u32 *rdattr_err) { /* As per referral draft: */ if (*bmval0 & ~WORD0_ABSENT_FS_ATTRS || @@ -2184,6 +2185,7 @@ static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *rdattr_err) } *bmval0 &= WORD0_ABSENT_FS_ATTRS; *bmval1 &= WORD1_ABSENT_FS_ATTRS; + *bmval2 &= WORD2_ABSENT_FS_ATTRS; return 0; } @@ -2246,8 +2248,7 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, BUG_ON(bmval2 & ~nfsd_suppattrs2(minorversion)); if (exp->ex_fslocs.migrated) { - BUG_ON(bmval[2]); - status = fattr_handle_absent_fs(&bmval0, &bmval1, &rdattr_err); + status = fattr_handle_absent_fs(&bmval0, &bmval1, &bmval2, &rdattr_err); if (status) goto out; } @@ -2286,8 +2287,8 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, } #ifdef CONFIG_NFSD_V4_SECURITY_LABEL - if ((bmval[2] & FATTR4_WORD2_SECURITY_LABEL) || - bmval[0] & FATTR4_WORD0_SUPPORTED_ATTRS) { + if ((bmval2 & FATTR4_WORD2_SECURITY_LABEL) || + bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) { err = security_inode_getsecctx(d_inode(dentry), &context, &contextlen); contextsupport = (err == 0); From 1ca4b88e7de23f6f86d2009101fe42d5b9dbf3de Mon Sep 17 00:00:00 2001 From: Kinglong Mee Date: Thu, 9 Jul 2015 17:38:26 +0800 Subject: [PATCH 056/428] nfsd: Fix a file leak on nfsd4_layout_setlease failure If nfsd4_layout_setlease fails, nfsd will not put ls->ls_file. Fix commit c5c707f96f "nfsd: implement pNFS layout recalls". Signed-off-by: Kinglong Mee Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4layouts.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 6904213a4363..ebf90e487c75 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -212,6 +212,7 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate, BUG_ON(!ls->ls_file); if (nfsd4_layout_setlease(ls)) { + fput(ls->ls_file); put_nfs4_file(fp); kmem_cache_free(nfs4_layout_stateid_cache, ls); return NULL; From fee50f3c8427aacabfb603229bf0a9056c3f2638 Mon Sep 17 00:00:00 2001 From: Darren Hart Date: Mon, 20 Jul 2015 15:48:37 -0700 Subject: [PATCH 057/428] selftests/futex: Fix futex_cmp_requeue_pi() error handling An earlier (pre-kernel-integration) refactoring of this code mistakenly replaced the error condition, <, with a >. Use < to detect an error as opposed to a successful requeue or signal race. Reported-by: David Binderman Cc: Shuah Khan Signed-off-by: Darren Hart Signed-off-by: Shuah Khan --- .../futex/functional/futex_requeue_pi_signal_restart.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c b/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c index 7f0c756993af..3d7dc6afc3f8 100644 --- a/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c +++ b/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c @@ -191,7 +191,7 @@ int main(int argc, char *argv[]) if (res > 0) { atomic_set(&requeued, 1); break; - } else if (res > 0) { + } else if (res < 0) { error("FUTEX_CMP_REQUEUE_PI failed\n", errno); ret = RET_ERROR; break; From 1342ff45bd4a43d4ef058aa419399437461f3c88 Mon Sep 17 00:00:00 2001 From: Beata Michalska Date: Mon, 15 Jun 2015 10:12:46 +0200 Subject: [PATCH 058/428] ARM: dts: Update video-phy node with syscon phandle for exynos3250 As a follow-up to recent changes to Exynos mipi video phy driver, introducing support for PMU regmap in commit e4b3d38088df ("phy: exynos-video-mipi: Fix regression by adding support for PMU regmap") add a syscon phandle to video-phy node to bring back to life both MIPI DSI display and MIPI CSIS-2 camera sensor on Exynos3250. Signed-off-by: Beata Michalska Reviewed-by: Javier Martinez Canillas Signed-off-by: Krzysztof Kozlowski Signed-off-by: Kukjin Kim --- arch/arm/boot/dts/exynos3250.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/exynos3250.dtsi b/arch/arm/boot/dts/exynos3250.dtsi index d7201333e3bc..2db99433e17f 100644 --- a/arch/arm/boot/dts/exynos3250.dtsi +++ b/arch/arm/boot/dts/exynos3250.dtsi @@ -138,8 +138,8 @@ mipi_phy: video-phy@10020710 { compatible = "samsung,s5pv210-mipi-video-phy"; - reg = <0x10020710 8>; #phy-cells = <1>; + syscon = <&pmu_system_controller>; }; pd_cam: cam-power-domain@10023C00 { From 300bde79f3d86b1af6fcde7b7b2439ecffccbff4 Mon Sep 17 00:00:00 2001 From: Thomas Abraham Date: Fri, 3 Apr 2015 18:43:47 +0200 Subject: [PATCH 059/428] ARM: dts: add CPU OPP and regulator supply property for exynos4210 For Exynos4210 platforms, add CPU operating points and CPU regulator supply properties for migrating from Exynos specific cpufreq driver to using generic cpufreq driver. Cc: Doug Anderson Cc: Andreas Faerber Cc: Sachin Kamat Cc: Andreas Farber Cc: Javier Martinez Canillas Signed-off-by: Thomas Abraham [b.zolnierkie: removed exynos5250 and exynos5420 support for now] Signed-off-by: Bartlomiej Zolnierkiewicz [k.kozlowski: Rebased, moved cpu nodes to alphabetical position] Signed-off-by: Krzysztof Kozlowski Signed-off-by: Kukjin Kim --- arch/arm/boot/dts/exynos4210-origen.dts | 4 ++++ arch/arm/boot/dts/exynos4210-trats.dts | 4 ++++ arch/arm/boot/dts/exynos4210-universal_c210.dts | 4 ++++ arch/arm/boot/dts/exynos4210.dtsi | 12 ++++++++++++ 4 files changed, 24 insertions(+) diff --git a/arch/arm/boot/dts/exynos4210-origen.dts b/arch/arm/boot/dts/exynos4210-origen.dts index e0abfc3324d1..e050d85cdacd 100644 --- a/arch/arm/boot/dts/exynos4210-origen.dts +++ b/arch/arm/boot/dts/exynos4210-origen.dts @@ -127,6 +127,10 @@ }; }; +&cpu0 { + cpu0-supply = <&buck1_reg>; +}; + &fimd { pinctrl-0 = <&lcd_en &lcd_clk &lcd_data24 &pwm0_out>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/exynos4210-trats.dts b/arch/arm/boot/dts/exynos4210-trats.dts index 98f3ce65cb9a..ba34886f8b65 100644 --- a/arch/arm/boot/dts/exynos4210-trats.dts +++ b/arch/arm/boot/dts/exynos4210-trats.dts @@ -188,6 +188,10 @@ }; }; +&cpu0 { + cpu0-supply = <&varm_breg>; +}; + &dsi_0 { vddcore-supply = <&vusb_reg>; vddio-supply = <&vmipi_reg>; diff --git a/arch/arm/boot/dts/exynos4210-universal_c210.dts b/arch/arm/boot/dts/exynos4210-universal_c210.dts index d4f2b11319dd..775892b2cc6a 100644 --- a/arch/arm/boot/dts/exynos4210-universal_c210.dts +++ b/arch/arm/boot/dts/exynos4210-universal_c210.dts @@ -548,6 +548,10 @@ }; }; +&cpu0 { + cpu0-supply = <&vdd_arm_reg>; +}; + &pinctrl_1 { hdmi_hpd: hdmi-hpd { samsung,pins = "gpx3-7"; diff --git a/arch/arm/boot/dts/exynos4210.dtsi b/arch/arm/boot/dts/exynos4210.dtsi index 10d3c173396e..3e5ba665d200 100644 --- a/arch/arm/boot/dts/exynos4210.dtsi +++ b/arch/arm/boot/dts/exynos4210.dtsi @@ -40,6 +40,18 @@ device_type = "cpu"; compatible = "arm,cortex-a9"; reg = <0x900>; + clocks = <&clock CLK_ARM_CLK>; + clock-names = "cpu"; + clock-latency = <160000>; + + operating-points = < + 1200000 1250000 + 1000000 1150000 + 800000 1075000 + 500000 975000 + 400000 975000 + 200000 950000 + >; cooling-min-level = <4>; cooling-max-level = <2>; #cooling-cells = <2>; /* min followed by max */ From a798c24a69b64f09e2d323ac8155a36373e5d5fd Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Tue, 21 Jul 2015 11:51:35 +0200 Subject: [PATCH 060/428] ASoC: dapm: Don't add prefix to widget stream name Commit fdb6eb0a1287 ("ASoC: dapm: Modify widget stream name according to prefix") fixed the case where a DAPM route between a DAI widget and a DAC/ADC/AIF widget with a matching stream name was not created when the DAPM context was using a prefix. Unfortunately the patch introduced a few issues on its own like leaking the dynamically allocated stream name memory and also not checking whether the allocation succeeded in the first place. It is also incomplete in that it still does not handle the case where stream name of the widget is a substring of the stream name of the DAI, which is explicitly allowed and works fine if no DAPM prefix is used. Revert the commit and take a slightly different approach to solving the issue. Instead of comparing the widget's stream name to the name of the DAI widget compare it to the stream name of the DAI widget. The stream name of the DAI widget is identical to the name of the DAI widget except that it wont have the DAPM prefix added. So this approach behaves identical regardless to whether the DAPM context uses a prefix or not. We don't have to worry about potentially matching with a widget with the same stream name, but from a different DAPM context with a different prefix, since the code already makes sure that both the DAI widget and the matched widget are from the same DAPM context. Fixes: fdb6eb0a1287 ("ASoC: dapm: Modify widget stream name according to prefix") Signed-off-by: Lars-Peter Clausen Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- sound/soc/soc-dapm.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 9f270c0308b7..e0de8072c514 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -3341,16 +3341,10 @@ snd_soc_dapm_new_control_unlocked(struct snd_soc_dapm_context *dapm, } prefix = soc_dapm_prefix(dapm); - if (prefix) { + if (prefix) w->name = kasprintf(GFP_KERNEL, "%s %s", prefix, widget->name); - if (widget->sname) - w->sname = kasprintf(GFP_KERNEL, "%s %s", prefix, - widget->sname); - } else { + else w->name = kasprintf(GFP_KERNEL, "%s", widget->name); - if (widget->sname) - w->sname = kasprintf(GFP_KERNEL, "%s", widget->sname); - } if (w->name == NULL) { kfree(w); return NULL; @@ -3799,7 +3793,7 @@ int snd_soc_dapm_link_dai_widgets(struct snd_soc_card *card) break; } - if (!w->sname || !strstr(w->sname, dai_w->name)) + if (!w->sname || !strstr(w->sname, dai_w->sname)) continue; if (dai_w->id == snd_soc_dapm_dai_in) { From 2f01a33bd26545c16fea7592697f7f15c416402b Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Tue, 21 Jul 2015 09:51:29 +0800 Subject: [PATCH 061/428] usb: chipidea: ehci_init_driver is intended to call one time The ehci_init_driver is used to initialize hcd APIs for each ehci controller driver, it is designed to be called only one time and before driver register is called. The current design will cause ehci_init_driver is called multiple times at probe process, it will cause hc_driver's initialization affect current running hcd. We run out NULL pointer dereference problem when one hcd is started by module_init, and the other is started by otg thread at SMP platform. The reason for this problem is ehci_init_driver will do memory copy for current uniform hc_driver, and this memory copy will do memset (as 0) first, so when the first hcd is running usb_add_hcd, and the second hcd may clear the uniform hc_driver's space (at ehci_init_driver), then the first hcd will meet NULL pointer at the same time. See below two logs: LOG_1: ci_hdrc ci_hdrc.0: EHCI Host Controller ci_hdrc ci_hdrc.0: new USB bus registered, assigned bus number 1 ci_hdrc ci_hdrc.1: doesn't support gadget Unable to handle kernel NULL pointer dereference at virtual address 00000014 pgd = 80004000 [00000014] *pgd=00000000 Internal error: Oops: 805 [#1] PREEMPT SMP ARM Modules linked in: CPU: 0 PID: 108 Comm: kworker/u8:2 Not tainted 3.14.38-222193-g24b2734-dirty #25 Workqueue: ci_otg ci_otg_work task: d839ec00 ti: d8400000 task.ti: d8400000 PC is at ehci_run+0x4c/0x284 LR is at _raw_spin_unlock_irqrestore+0x28/0x54 pc : [<8041f9a0>] lr : [<8070ea84>] psr: 60000113 sp : d8401e30 ip : 00000000 fp : d8004400 r10: 00000001 r9 : 00000001 r8 : 00000000 r7 : 00000000 r6 : d8419940 r5 : 80dd24c0 r4 : d8419800 r3 : 8001d060 r2 : 00000000 r1 : 00000001 r0 : 00000000 Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment kernel Control: 10c53c7d Table: 1000404a DAC: 00000015 Process kworker/u8:2 (pid: 108, stack limit = 0xd8400238) Stack: (0xd8401e30 to 0xd8402000) 1e20: d87523c0 d8401e48 66667562 d8419800 1e40: 00000000 00000000 d8419800 00000000 00000000 00000000 d84198b0 8040fcdc 1e60: 00000000 80dd320c d8477610 d8419c00 d803d010 d8419800 00000000 00000000 1e80: d8004400 00000000 d8400008 80431494 80431374 d803d100 d803d010 d803d1ac 1ea0: 00000000 80432428 804323d4 d803d100 00000001 80435eb8 80e0d0bc d803d100 1ec0: 00000006 80436458 00000000 d803d100 80e92ec8 80436f44 d803d010 d803d100 1ee0: d83fde00 8043292c d8752710 d803d1f4 d803d010 8042ddfc 8042ddb8 d83f3b00 1f00: d803d1f4 80042b60 00000000 00000003 00000001 00000001 80054598 d83f3b00 1f20: d8004400 d83f3b18 d8004414 d8400000 80e3957b 00000089 d8004400 80043814 1f40: d839ec00 00000000 d83fcd80 d83f3b00 800436e4 00000000 00000000 00000000 1f60: 00000000 80048f34 00000000 00000000 00000000 d83f3b00 00000000 00000000 1f80: d8401f80 d8401f80 00000000 00000000 d8401f90 d8401f90 d8401fac d83fcd80 1fa0: 80048e68 00000000 00000000 8000e538 00000000 00000000 00000000 00000000 1fc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 1fe0: 00000000 00000000 00000000 00000000 00000013 00000000 00000000 00000000 [<8041f9a0>] (ehci_run) from [<8040fcdc>] (usb_add_hcd+0x248/0x6e8) [<8040fcdc>] (usb_add_hcd) from [<80431494>] (host_start+0x120/0x2e4) [<80431494>] (host_start) from [<80432428>] (ci_otg_start_host+0x54/0xbc) [<80432428>] (ci_otg_start_host) from [<80435eb8>] (otg_set_protocol+0xa4/0xd0) [<80435eb8>] (otg_set_protocol) from [<80436458>] (otg_set_state+0x574/0xc58) [<80436458>] (otg_set_state) from [<80436f44>] (otg_statemachine+0x408/0x46c) [<80436f44>] (otg_statemachine) from [<8043292c>] (ci_otg_fsm_work+0x3c/0x190) [<8043292c>] (ci_otg_fsm_work) from [<8042ddfc>] (ci_otg_work+0x44/0x1c4) [<8042ddfc>] (ci_otg_work) from [<80042b60>] (process_one_work+0xf4/0x35c) [<80042b60>] (process_one_work) from [<80043814>] (worker_thread+0x130/0x3bc) [<80043814>] (worker_thread) from [<80048f34>] (kthread+0xcc/0xe4) [<80048f34>] (kthread) from [<8000e538>] (ret_from_fork+0x14/0x3c) Code: e5953018 e3530000 0a000000 e12fff33 (e5878014) LOG_2: ci_hdrc ci_hdrc.0: EHCI Host Controller ci_hdrc ci_hdrc.0: new USB bus registered, assigned bus number 1 ci_hdrc ci_hdrc.1: doesn't support gadget Unable to handle kernel NULL pointer dereference at virtual address 00000000 pgd = 80004000 [00000000] *pgd=00000000 In Online 00:00ternal e Offline rror: Oops: 80000005 [#1] PREEMPT SMP ARM Modules linked in: CPU: 0 PID: 108 Comm: kworker/u8:2 Not tainted 3.14.38-02007-g24b2734-dirty #127 Workque Online 00:00ue: ci_o Offline tg ci_otg_work Online 00:00task: d8 Offline 39ec00 ti: d83ea000 task.ti: d83ea000 PC is at 0x0 LR is at usb_add_hcd+0x248/0x6e8 pc : [<00000000>] lr : [<8040f644>] psr: 60000113 sp : d83ebe60 ip : 00000000 fp : d8004400 r10: 00000001 r9 : 00000001 r8 : d85fd4b0 r7 : 00000000 r6 : 00000000 r5 : 00000000 r4 : d85fd400 r3 : 00000000 r2 : d85fd4f4 r1 : 80410178 r0 : d85fd400 Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment kernel Control: 10c53c7d Table: 1000404a DAC: 00000015 Process kworker/u8:2 (pid: 108, stack limit = 0xd83ea238) Stack: (0xd83ebe60 to 0xd83ec000) be60: 00000000 80dd920c d8654e10 d85fd800 d803e010 d85fd400 00000000 00000000 be80: d8004400 00000000 d83ea008 80430e34 80430d14 d803e100 d803e010 d803e1ac bea0: 00000000 80431dc8 80431d74 d803e100 00000001 80435858 80e130bc d803e100 bec0: 00000006 80435df8 00000000 d803e100 80e98ec8 804368e4 d803e010 d803e100 bee0: d86e8100 804322cc d86cf050 d803e1f4 d803e010 8042d79c 8042d758 d83cf900 bf00: d803e1f4 80042b78 00000000 00000003 00000001 00000001 800545e8 d83cf900 bf20: d8004400 d83cf918 d8004414 d83ea000 80e3f57b 00000089 d8004400 8004382c bf40: d839ec00 00000000 d8393780 d83cf900 800436fc 00000000 00000000 00000000 bf60: 00000000 80048f50 80e019f4 00000000 0000264c d83cf900 00000000 00000000 bf80: d83ebf80 d83ebf80 00000000 00000000 d83ebf90 d83ebf90 d83ebfac d8393780 bfa0: 80048e84 00000000 00000000 8000e538 00000000 00000000 00000000 00000000 bfc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 bfe0: 00000000 00000000 00000000 00000000 00000013 00000000 ee66e85d 133ebd03 [<804 Online 00:000f644>] Offline (usb_add_hcd) from [<80430e34>] (host_start+0x120/0x2e4) [<80430e34>] (host_start) from [<80431dc8>] (ci_otg_start_host+0x54/0xbc) [<80431dc8>] (ci_otg_start_host) from [<80435858>] (otg_set_protocol+0xa4/0xd0) [<80435858>] (otg_set_protocol) from [<80435df8>] (otg_set_state+0x574/0xc58) [<80435df8>] (otg_set_state) from [<804368e4>] (otg_statemachine+0x408/0x46c) [<804368e4>] (otg_statemachine) from [<804322cc>] (ci_otg_fsm_work+0x3c/0x190) [<804322cc>] (ci_otg_fsm_work) from [<8042d79c>] (ci_otg_work+0x44/0x1c4) [<8042d79c>] (ci_otg_work) from [<80042b78>] (process_one_work+0xf4/0x35c) [<80042b78>] (process_one_work) from [<8004382c>] (worker_thread+0x130/0x3bc) [<8004382c>] (worker_thread) from [<80048f50>] (kthread+0xcc/0xe4) [<80048f50>] (kthread) from [<8000e538>] (ret_from_fork+0x14/0x3c) Code: bad PC value Cc: Jun Li Cc: Cc: Alan Stern Acked-by: Alan Stern Signed-off-by: Peter Chen --- drivers/usb/chipidea/core.c | 13 ++++++++++++- drivers/usb/chipidea/host.c | 7 +++++-- drivers/usb/chipidea/host.h | 6 ++++++ 3 files changed, 23 insertions(+), 3 deletions(-) diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c index 74fea4fa41b1..3ad48e1c0c57 100644 --- a/drivers/usb/chipidea/core.c +++ b/drivers/usb/chipidea/core.c @@ -1024,7 +1024,18 @@ static struct platform_driver ci_hdrc_driver = { }, }; -module_platform_driver(ci_hdrc_driver); +static int __init ci_hdrc_platform_register(void) +{ + ci_hdrc_host_driver_init(); + return platform_driver_register(&ci_hdrc_driver); +} +module_init(ci_hdrc_platform_register); + +static void __exit ci_hdrc_platform_unregister(void) +{ + platform_driver_unregister(&ci_hdrc_driver); +} +module_exit(ci_hdrc_platform_unregister); MODULE_ALIAS("platform:ci_hdrc"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/usb/chipidea/host.c b/drivers/usb/chipidea/host.c index 6cf87b8b13a8..7161439def19 100644 --- a/drivers/usb/chipidea/host.c +++ b/drivers/usb/chipidea/host.c @@ -249,9 +249,12 @@ int ci_hdrc_host_init(struct ci_hdrc *ci) rdrv->name = "host"; ci->roles[CI_ROLE_HOST] = rdrv; + return 0; +} + +void ci_hdrc_host_driver_init(void) +{ ehci_init_driver(&ci_ehci_hc_driver, &ehci_ci_overrides); orig_bus_suspend = ci_ehci_hc_driver.bus_suspend; ci_ehci_hc_driver.bus_suspend = ci_ehci_bus_suspend; - - return 0; } diff --git a/drivers/usb/chipidea/host.h b/drivers/usb/chipidea/host.h index 5707bf379bfb..0f12f131bdd3 100644 --- a/drivers/usb/chipidea/host.h +++ b/drivers/usb/chipidea/host.h @@ -5,6 +5,7 @@ int ci_hdrc_host_init(struct ci_hdrc *ci); void ci_hdrc_host_destroy(struct ci_hdrc *ci); +void ci_hdrc_host_driver_init(void); #else @@ -18,6 +19,11 @@ static inline void ci_hdrc_host_destroy(struct ci_hdrc *ci) } +static void ci_hdrc_host_driver_init(void) +{ + +} + #endif #endif /* __DRIVERS_USB_CHIPIDEA_HOST_H */ From b101acfabc9377469af3abfb7cb63112da367284 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Wed, 22 Jul 2015 11:27:45 +0800 Subject: [PATCH 062/428] ASoC: sgtl5000: Fix up define for SGTL5000_SMALL_POP Currently, below code actually does not update any bit because SGTL5000_SMALL_POP is 0. snd_soc_update_bits(codec, SGTL5000_CHIP_REF_CTRL, SGTL5000_SMALL_POP, 1); The SGTL5000_SMALL_POP should be BIT(0) rather than 0, fix it. Signed-off-by: Axel Lin Acked-By: Alexander Stein Signed-off-by: Mark Brown --- sound/soc/codecs/sgtl5000.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/codecs/sgtl5000.h b/sound/soc/codecs/sgtl5000.h index bd7a344bf8c5..1c317de26176 100644 --- a/sound/soc/codecs/sgtl5000.h +++ b/sound/soc/codecs/sgtl5000.h @@ -275,7 +275,7 @@ #define SGTL5000_BIAS_CTRL_MASK 0x000e #define SGTL5000_BIAS_CTRL_SHIFT 1 #define SGTL5000_BIAS_CTRL_WIDTH 3 -#define SGTL5000_SMALL_POP 0 +#define SGTL5000_SMALL_POP 1 /* * SGTL5000_CHIP_MIC_CTRL From a6c2a32ac83567f15e9af3dcbc73148ce68b2ced Mon Sep 17 00:00:00 2001 From: Ben Zhang Date: Tue, 21 Jul 2015 14:46:26 -0700 Subject: [PATCH 063/428] ASoC: ssm4567: Keep TDM_BCLKS in ssm4567_set_dai_fmt The regmap_write in ssm4567_set_dai_fmt accidentally clears the TDM_BCLKS field which was set earlier by ssm4567_set_tdm_slot. This patch fixes it by using regmap_update_bits with proper mask. Signed-off-by: Ben Zhang Acked-by: Lars-Peter Clausen Acked-by: Anatol Pomozov Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- sound/soc/codecs/ssm4567.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/sound/soc/codecs/ssm4567.c b/sound/soc/codecs/ssm4567.c index 938d2cb6d78b..84a4f5ad8064 100644 --- a/sound/soc/codecs/ssm4567.c +++ b/sound/soc/codecs/ssm4567.c @@ -315,7 +315,13 @@ static int ssm4567_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt) if (invert_fclk) ctrl1 |= SSM4567_SAI_CTRL_1_FSYNC; - return regmap_write(ssm4567->regmap, SSM4567_REG_SAI_CTRL_1, ctrl1); + return regmap_update_bits(ssm4567->regmap, SSM4567_REG_SAI_CTRL_1, + SSM4567_SAI_CTRL_1_BCLK | + SSM4567_SAI_CTRL_1_FSYNC | + SSM4567_SAI_CTRL_1_LJ | + SSM4567_SAI_CTRL_1_TDM | + SSM4567_SAI_CTRL_1_PDM, + ctrl1); } static int ssm4567_set_power(struct ssm4567 *ssm4567, bool enable) From 4b31814d20cbe5cd4ccf18089751e77a04afe4f2 Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Tue, 21 Jul 2015 21:37:31 -0700 Subject: [PATCH 064/428] netfilter: nf_conntrack: Support expectations in different zones When zones were originally introduced, the expectation functions were all extended to perform lookup using the zone. However, insertion was not modified to check the zone. This means that two expectations which are intended to apply for different connections that have the same tuple but exist in different zones cannot both be tracked. Fixes: 5d0aa2ccd4 (netfilter: nf_conntrack: add support for "conntrack zones") Signed-off-by: Joe Stringer Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_expect.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 7a17070c5dab..b45a4223cb05 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -219,7 +219,8 @@ static inline int expect_clash(const struct nf_conntrack_expect *a, a->mask.src.u3.all[count] & b->mask.src.u3.all[count]; } - return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask); + return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask) && + nf_ct_zone(a->master) == nf_ct_zone(b->master); } static inline int expect_matches(const struct nf_conntrack_expect *a, From 6dd3f13e4239a8c2b1e60687d7321bc0df614f33 Mon Sep 17 00:00:00 2001 From: Michal Marek Date: Thu, 16 Jul 2015 18:23:53 +0200 Subject: [PATCH 065/428] kbuild: Do not pick up ARCH_{CPP,A,C}FLAGS from the environment Initialize the ARCH_* overrides before including the arch Makefile, to avoid picking up the values from the environment. The variables can still be overriden on the make command line, but this won't happen by accident. Signed-off-by: Michal Marek --- Makefile | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/Makefile b/Makefile index 13270c0a9336..dc868bcdaf45 100644 --- a/Makefile +++ b/Makefile @@ -597,6 +597,11 @@ endif # $(dot-config) # Defaults to vmlinux, but the arch makefile usually adds further targets all: vmlinux +# The arch Makefile can set ARCH_{CPP,A,C}FLAGS to override the default +# values of the respective KBUILD_* variables +ARCH_CPPFLAGS := +ARCH_AFLAGS := +ARCH_CFLAGS := include arch/$(SRCARCH)/Makefile KBUILD_CFLAGS += $(call cc-option,-fno-delete-null-pointer-checks,) From 3d1450d54a4fc277fc4598acf2335f74b66b08fc Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Tue, 7 Jul 2015 20:26:07 +0200 Subject: [PATCH 066/428] Makefile: Force gzip and xz on module install Running `make modules_install` ordinarily will overwrite existing modules. This is the desired behavior, and is how pretty much every other `make install` target works. However, if CONFIG_MODULE_COMPRESS is enabled, modules are passed through gzip and xz which then do the file writing. Both gzip and xz will error out if the file already exists, unless -f is passed. This patch adds -f so that the behavior is uniform. Signed-off-by: Jason A. Donenfeld Signed-off-by: Michal Marek --- Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Makefile b/Makefile index dc868bcdaf45..c5234fe6adb3 100644 --- a/Makefile +++ b/Makefile @@ -852,10 +852,10 @@ export mod_strip_cmd mod_compress_cmd = true ifdef CONFIG_MODULE_COMPRESS ifdef CONFIG_MODULE_COMPRESS_GZIP - mod_compress_cmd = gzip -n + mod_compress_cmd = gzip -n -f endif # CONFIG_MODULE_COMPRESS_GZIP ifdef CONFIG_MODULE_COMPRESS_XZ - mod_compress_cmd = xz + mod_compress_cmd = xz -f endif # CONFIG_MODULE_COMPRESS_XZ endif # CONFIG_MODULE_COMPRESS export mod_compress_cmd From 68514471ceceac63c7fa9ad684d882f41be5b2d8 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 22 Jul 2015 16:31:17 -0400 Subject: [PATCH 067/428] SUNRPC: Fix a backchannel deadlock xprt_alloc_bc_request() cannot call xprt_free_bc_request() without deadlocking, since it already holds the xprt->bc_pa_lock. Reported-by: Chuck Lever Fixes: 0d2a970d0ae55 ("SUNRPC: Fix a backchannel race") Signed-off-by: Trond Myklebust --- net/sunrpc/backchannel_rqst.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index 9825ff0f91d6..5a3b50aec397 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -240,8 +240,8 @@ static struct rpc_rqst *xprt_alloc_bc_request(struct rpc_xprt *xprt, __be32 xid) req = xprt_alloc_bc_req(xprt, GFP_ATOMIC); if (!req) goto not_found; - /* Note: this 'free' request adds it to xprt->bc_pa_list */ - xprt_free_bc_request(req); + list_add_tail(&req->rq_bc_pa_list, &xprt->bc_pa_list); + xprt->bc_alloc_count++; } req = list_first_entry(&xprt->bc_pa_list, struct rpc_rqst, rq_bc_pa_list); From 1980bd4d829a87ccd21b949f8a11ff1b426f5b0b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 22 Jul 2015 17:05:32 -0400 Subject: [PATCH 068/428] SUNRPC: xprt_complete_bc_request must also decrement the free slot count Calling xprt_complete_bc_request() effectively causes the slot to be allocated, so it needs to decrement the backchannel free slot count as well. Fixes: 0d2a970d0ae5 ("SUNRPC: Fix a backchannel race") Signed-off-by: Trond Myklebust --- net/sunrpc/backchannel_rqst.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index 5a3b50aec397..6255d141133b 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -336,7 +336,7 @@ void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied) spin_lock(&xprt->bc_pa_lock); list_del(&req->rq_bc_pa_list); - xprt->bc_alloc_count--; + xprt_dec_alloc_count(xprt, 1); spin_unlock(&xprt->bc_pa_lock); req->rq_private_buf.len = copied; From 3c38cbe2ade88240fabb585b408f779ad3b9a31b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 22 Jul 2015 13:46:13 -0400 Subject: [PATCH 069/428] NFSv4: We must set NFS_OPEN_STATE flag in nfs_resync_open_stateid_locked Otherwise, nfs4_select_rw_stateid() will always return the zero stateid instead of the correct open stateid. Fixes: f95549cf24660 ("NFSv4: More CLOSE/OPEN races") Cc: stable@vger.kernel.org # 4.0+ Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index c5c9e0d070f8..9264994ec9d3 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1200,12 +1200,15 @@ static bool nfs_need_update_open_stateid(struct nfs4_state *state, static void nfs_resync_open_stateid_locked(struct nfs4_state *state) { + if (!(state->n_wronly || state->n_rdonly || state->n_rdwr)) + return; if (state->n_wronly) set_bit(NFS_O_WRONLY_STATE, &state->flags); if (state->n_rdonly) set_bit(NFS_O_RDONLY_STATE, &state->flags); if (state->n_rdwr) set_bit(NFS_O_RDWR_STATE, &state->flags); + set_bit(NFS_OPEN_STATE, &state->flags); } static void nfs_clear_open_stateid_locked(struct nfs4_state *state, From 2b83d3de4c18af49800e0b26ae013db4fcf43a4a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 5 Jul 2015 20:06:38 -0400 Subject: [PATCH 070/428] NFSv4/pnfs: Ensure we don't miss a file extension pNFS writes don't return attributes, however that doesn't mean that we should ignore the fact that they may be extending the file. This patch ensures that if a write is seen to extend the file, then we always set an attribute barrier, and update the cached file size. Signed-off-by: Trond Myklebust --- fs/nfs/write.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 359e9ad596c9..0e6a2b8786b4 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1378,24 +1378,27 @@ static void nfs_writeback_check_extend(struct nfs_pgio_header *hdr, { struct nfs_pgio_args *argp = &hdr->args; struct nfs_pgio_res *resp = &hdr->res; + u64 size = argp->offset + resp->count; if (!(fattr->valid & NFS_ATTR_FATTR_SIZE)) + fattr->size = size; + if (nfs_size_to_loff_t(fattr->size) < i_size_read(hdr->inode)) { + fattr->valid &= ~NFS_ATTR_FATTR_SIZE; return; - if (argp->offset + resp->count != fattr->size) - return; - if (nfs_size_to_loff_t(fattr->size) < i_size_read(hdr->inode)) + } + if (size != fattr->size) return; /* Set attribute barrier */ nfs_fattr_set_barrier(fattr); + /* ...and update size */ + fattr->valid |= NFS_ATTR_FATTR_SIZE; } void nfs_writeback_update_inode(struct nfs_pgio_header *hdr) { - struct nfs_fattr *fattr = hdr->res.fattr; + struct nfs_fattr *fattr = &hdr->fattr; struct inode *inode = hdr->inode; - if (fattr == NULL) - return; spin_lock(&inode->i_lock); nfs_writeback_check_extend(hdr, fattr); nfs_post_op_update_inode_force_wcc_locked(inode, fattr); From 85a23cee3f2c928475f31777ead5a71340a12fc3 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 5 Jul 2015 11:02:53 -0400 Subject: [PATCH 071/428] NFS: Don't revalidate the mapping if both size and change attr are up to date If we've ensured that the size and the change attribute are both correct, then there is no point in marking those attributes as needing revalidation again. Only do so if we know the size is incorrect and was not updated. Fixes: f2467b6f64da ("NFS: Clear NFS_INO_REVAL_PAGECACHE when...") Signed-off-by: Trond Myklebust --- fs/nfs/inode.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index b77b328a06d7..d654661defb3 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1244,9 +1244,11 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat if (fattr->valid & NFS_ATTR_FATTR_SIZE) { cur_size = i_size_read(inode); new_isize = nfs_size_to_loff_t(fattr->size); - if (cur_size != new_isize && nfsi->nrequests == 0) + if (cur_size != new_isize) invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE; } + if (nfsi->nrequests != 0) + invalid &= ~NFS_INO_REVAL_PAGECACHE; /* Have any file permissions changed? */ if ((fattr->valid & NFS_ATTR_FATTR_MODE) && (inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) @@ -1684,8 +1686,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) invalid |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_DATA | NFS_INO_INVALID_ACCESS - | NFS_INO_INVALID_ACL - | NFS_INO_REVAL_PAGECACHE; + | NFS_INO_INVALID_ACL; if (S_ISDIR(inode->i_mode)) nfs_force_lookup_revalidate(inode); inode->i_version = fattr->change_attr; @@ -1717,7 +1718,6 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) if ((nfsi->nrequests == 0) || new_isize > cur_isize) { i_size_write(inode, new_isize); invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA; - invalid &= ~NFS_INO_REVAL_PAGECACHE; } dprintk("NFS: isize change on server for file %s/%ld " "(%Ld to %Ld)\n", From 5c675d6420511e035c150e420ab26d0306bbb736 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 5 Jul 2015 16:07:04 -0400 Subject: [PATCH 072/428] NFS: Set NFS_INO_REVAL_PAGECACHE if the change attribute is uninitialised We can't allow caching of data until the change attribute has been initialised correctly. Signed-off-by: Trond Myklebust --- fs/nfs/inode.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index d654661defb3..426e4f8207ef 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -443,7 +443,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st if (fattr->valid & NFS_ATTR_FATTR_CHANGE) inode->i_version = fattr->change_attr; else if (nfs_server_capable(inode, NFS_CAP_CHANGE_ATTR)) - nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR); + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR + | NFS_INO_REVAL_PAGECACHE); if (fattr->valid & NFS_ATTR_FATTR_SIZE) inode->i_size = nfs_size_to_loff_t(fattr->size); else From cd812599796f500b042f5464b6665755eca21137 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 5 Jul 2015 11:12:07 -0400 Subject: [PATCH 073/428] NFS: Remove the "NFS_CAP_CHANGE_ATTR" capability Setting the change attribute has been mandatory for all NFS versions, since commit 3a1556e8662c ("NFSv2/v3: Simulate the change attribute"). We should therefore not have anything be conditional on it being set/unset. Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 2 +- fs/nfs/inode.c | 4 ++-- fs/nfs/nfs4proc.c | 3 --- include/linux/nfs_fs_sb.h | 2 +- 4 files changed, 4 insertions(+), 7 deletions(-) diff --git a/fs/nfs/client.c b/fs/nfs/client.c index ecebb406cc1a..4a90c9bb3135 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -775,7 +775,7 @@ static int nfs_init_server(struct nfs_server *server, server->options = data->options; server->caps |= NFS_CAP_HARDLINKS|NFS_CAP_SYMLINKS|NFS_CAP_FILEID| NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|NFS_CAP_OWNER_GROUP| - NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME|NFS_CAP_CHANGE_ATTR; + NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME; if (data->rsize) server->rsize = nfs_block_size(data->rsize, NULL); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 426e4f8207ef..0adc7d245b3d 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -442,7 +442,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR); if (fattr->valid & NFS_ATTR_FATTR_CHANGE) inode->i_version = fattr->change_attr; - else if (nfs_server_capable(inode, NFS_CAP_CHANGE_ATTR)) + else nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR | NFS_INO_REVAL_PAGECACHE); if (fattr->valid & NFS_ATTR_FATTR_SIZE) @@ -1692,7 +1692,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfs_force_lookup_revalidate(inode); inode->i_version = fattr->change_attr; } - } else if (server->caps & NFS_CAP_CHANGE_ATTR) + } else nfsi->cache_validity |= save_cache_validity; if (fattr->valid & NFS_ATTR_FATTR_MTIME) { diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 9264994ec9d3..c85ffe67b5f3 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -8591,7 +8591,6 @@ static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = { .minor_version = 0, .init_caps = NFS_CAP_READDIRPLUS | NFS_CAP_ATOMIC_OPEN - | NFS_CAP_CHANGE_ATTR | NFS_CAP_POSIX_LOCK, .init_client = nfs40_init_client, .shutdown_client = nfs40_shutdown_client, @@ -8617,7 +8616,6 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = { .minor_version = 1, .init_caps = NFS_CAP_READDIRPLUS | NFS_CAP_ATOMIC_OPEN - | NFS_CAP_CHANGE_ATTR | NFS_CAP_POSIX_LOCK | NFS_CAP_STATEID_NFSV41 | NFS_CAP_ATOMIC_OPEN_V1, @@ -8640,7 +8638,6 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = { .minor_version = 2, .init_caps = NFS_CAP_READDIRPLUS | NFS_CAP_ATOMIC_OPEN - | NFS_CAP_CHANGE_ATTR | NFS_CAP_POSIX_LOCK | NFS_CAP_STATEID_NFSV41 | NFS_CAP_ATOMIC_OPEN_V1 diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index a2ea1491d3df..20bc8e51b161 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -220,7 +220,7 @@ struct nfs_server { #define NFS_CAP_SYMLINKS (1U << 2) #define NFS_CAP_ACLS (1U << 3) #define NFS_CAP_ATOMIC_OPEN (1U << 4) -#define NFS_CAP_CHANGE_ATTR (1U << 5) +/* #define NFS_CAP_CHANGE_ATTR (1U << 5) */ #define NFS_CAP_FILEID (1U << 6) #define NFS_CAP_MODE (1U << 7) #define NFS_CAP_NLINK (1U << 8) From 115c48d7a5351abeadd0c8a3dc87eca3d66a6475 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 5 Jul 2015 12:36:34 -0400 Subject: [PATCH 074/428] NFS: nfs_mark_for_revalidate should always set NFS_INO_REVAL_PAGECACHE I'm not aware of any existing bugs around this, but the expectation is that nfs_mark_for_revalidate() should always force a revalidation of the cached metadata. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index f91b5ade30c9..874b77228fb9 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -292,9 +292,12 @@ static inline void nfs_mark_for_revalidate(struct inode *inode) struct nfs_inode *nfsi = NFS_I(inode); spin_lock(&inode->i_lock); - nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS; + nfsi->cache_validity |= NFS_INO_INVALID_ATTR | + NFS_INO_REVAL_PAGECACHE | + NFS_INO_INVALID_ACCESS | + NFS_INO_INVALID_ACL; if (S_ISDIR(inode->i_mode)) - nfsi->cache_validity |= NFS_INO_REVAL_PAGECACHE|NFS_INO_INVALID_DATA; + nfsi->cache_validity |= NFS_INO_INVALID_DATA; spin_unlock(&inode->i_lock); } From 8a7330130470e173832385861c1aa6e37a4e50d2 Mon Sep 17 00:00:00 2001 From: Zhao Lei Date: Wed, 15 Jul 2015 11:48:14 +0800 Subject: [PATCH 075/428] btrfs: Fix lockdep warning of btrfs_run_delayed_iputs() Liu Bo reported a lockdep warning of delayed_iput_sem in xfstests generic/241: [ 2061.345955] ============================================= [ 2061.346027] [ INFO: possible recursive locking detected ] [ 2061.346027] 4.1.0+ #268 Tainted: G W [ 2061.346027] --------------------------------------------- [ 2061.346027] btrfs-cleaner/3045 is trying to acquire lock: [ 2061.346027] (&fs_info->delayed_iput_sem){++++..}, at: [] btrfs_run_delayed_iputs+0x6b/0x100 [ 2061.346027] but task is already holding lock: [ 2061.346027] (&fs_info->delayed_iput_sem){++++..}, at: [] btrfs_run_delayed_iputs+0x6b/0x100 [ 2061.346027] other info that might help us debug this: [ 2061.346027] Possible unsafe locking scenario: [ 2061.346027] CPU0 [ 2061.346027] ---- [ 2061.346027] lock(&fs_info->delayed_iput_sem); [ 2061.346027] lock(&fs_info->delayed_iput_sem); [ 2061.346027] *** DEADLOCK *** It is rarely happened, about 1/400 in my test env. The reason is recursion of btrfs_run_delayed_iputs(): cleaner_kthread -> btrfs_run_delayed_iputs() *1 -> get delayed_iput_sem lock *2 -> iput() -> ... -> btrfs_commit_transaction() -> btrfs_run_delayed_iputs() *1 -> get delayed_iput_sem lock (dead lock) *2 *1: recursion of btrfs_run_delayed_iputs() *2: warning of lockdep about delayed_iput_sem When fs is in high stress, new iputs may added into fs_info->delayed_iputs list when btrfs_run_delayed_iputs() is running, which cause second btrfs_run_delayed_iputs() run into down_read(&fs_info->delayed_iput_sem) again, and cause above lockdep warning. Actually, it will not cause real problem because both locks are read lock, but to avoid lockdep warning, we can do a fix. Fix: Don't do btrfs_run_delayed_iputs() in btrfs_commit_transaction() for cleaner_kthread thread to break above recursion path. cleaner_kthread is calling btrfs_run_delayed_iputs() explicitly in code, and don't need to call btrfs_run_delayed_iputs() again in btrfs_commit_transaction(), it also give us a bonus to avoid stack overflow. Test: No above lockdep warning after patch in 1200 generic/241 tests. Reported-by: Liu Bo Signed-off-by: Zhao Lei Reviewed-by: Liu Bo Signed-off-by: Chris Mason --- fs/btrfs/transaction.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 51e0f0d0053e..f5021fcb154e 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -2152,7 +2152,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, kmem_cache_free(btrfs_trans_handle_cachep, trans); - if (current != root->fs_info->transaction_kthread) + if (current != root->fs_info->transaction_kthread && + current != root->fs_info->cleaner_kthread) btrfs_run_delayed_iputs(root); return ret; From 95ab1f64908795a2edd6b847eca94a0c63a44be4 Mon Sep 17 00:00:00 2001 From: Zhao Lei Date: Wed, 15 Jul 2015 21:02:09 +0800 Subject: [PATCH 076/428] btrfs: Avoid NULL pointer dereference of free_extent_buffer when read_tree_block() fail When read_tree_block() failed, we can see following dmesg: [ 134.371389] BUG: unable to handle kernel NULL pointer dereference at 0000000000000063 [ 134.372236] IP: [] free_extent_buffer+0x21/0x90 [ 134.372236] PGD 0 [ 134.372236] Oops: 0000 [#1] SMP [ 134.372236] Modules linked in: [ 134.372236] CPU: 0 PID: 2289 Comm: mount Not tainted 4.2.0-rc1_HEAD_c65b99f046843d2455aa231747b5a07a999a9f3d_+ #115 [ 134.372236] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.7.5.1-0-g8936dbb-20141113_115728-nilsson.home.kraxel.org 04/01/2014 [ 134.372236] task: ffff88003b6e1a00 ti: ffff880011e60000 task.ti: ffff880011e60000 [ 134.372236] RIP: 0010:[] [] free_extent_buffer+0x21/0x90 ... [ 134.372236] Call Trace: [ 134.372236] [] free_root_extent_buffers+0x91/0xb0 [ 134.372236] [] free_root_pointers+0x17d/0x190 [ 134.372236] [] open_ctree+0x1ca0/0x25b0 [ 134.372236] [] ? disk_name+0x97/0xb0 [ 134.372236] [] btrfs_mount+0x8fa/0xab0 ... Reason: read_tree_block() changed to return error number on fail, and this value(not NULL) is set to tree_root->node, then subsequent code will run to: free_root_pointers() ->free_root_extent_buffers() ->free_extent_buffer() ->atomic_read((extent_buffer *)(-E_XXX)->refs); and trigger above error. Fix: Set tree_root->node to NULL on fail to make error_handle code happy. Signed-off-by: Zhao Lei Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index e5aad7f535aa..84cbbb2d562e 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2842,6 +2842,7 @@ int open_ctree(struct super_block *sb, !extent_buffer_uptodate(chunk_root->node)) { printk(KERN_ERR "BTRFS: failed to read chunk root on %s\n", sb->s_id); + chunk_root->node = NULL; goto fail_tree_roots; } btrfs_set_root_node(&chunk_root->root_item, chunk_root->node); @@ -2879,7 +2880,7 @@ retry_root_backup: !extent_buffer_uptodate(tree_root->node)) { printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n", sb->s_id); - + tree_root->node = NULL; goto recovery_tree_root; } From 3e303ea60db3f0222c25a13f39a7cca7bf860df0 Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Fri, 17 Jul 2015 23:45:23 +0800 Subject: [PATCH 077/428] btrfs: its btrfs_err() instead of btrfs_error() sorry I indented to use btrfs_err() and I have no idea how btrfs_error() got there. infact I was thinking about these kind of oversights since these two func are too closely named. Signed-off-by: Anand Jain Reviewed-by: Liu Bo Reviewed-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/dev-replace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 862fbc206755..564a7de17d99 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -378,7 +378,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root, ret = btrfs_kobj_add_device(tgt_device->fs_devices, tgt_device); if (ret) - btrfs_error(root->fs_info, ret, "kobj add dev failed"); + btrfs_err(root->fs_info, "kobj add dev failed %d\n", ret); printk_in_rcu(KERN_INFO "BTRFS: dev_replace from %s (devid %llu) to %s started\n", From 00d80e342c0f4f1990ab69f594ee1e2348e51dd9 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 20 Jul 2015 14:56:20 +0100 Subject: [PATCH 078/428] Btrfs: fix quick exhaustion of the system array in the superblock Omar reported that after commit 4fbcdf669454 ("Btrfs: fix -ENOSPC when finishing block group creation"), introduced in 4.2-rc1, the following test was failing due to exhaustion of the system array in the superblock: #!/bin/bash truncate -s 100T big.img mkfs.btrfs big.img mount -o loop big.img /mnt/loop num=5 sz=10T for ((i = 0; i < $num; i++)); do echo fallocate $i $sz fallocate -l $sz /mnt/loop/testfile$i done btrfs filesystem sync /mnt/loop for ((i = 0; i < $num; i++)); do echo rm $i rm /mnt/loop/testfile$i btrfs filesystem sync /mnt/loop done umount /mnt/loop This made btrfs_add_system_chunk() fail with -EFBIG due to excessive allocation of system block groups. This happened because the test creates a large number of data block groups per transaction and when committing the transaction we start the writeout of the block group caches for all the new new (dirty) block groups, which results in pre-allocating space for each block group's free space cache using the same transaction handle. That in turn often leads to creation of more block groups, and all get attached to the new_bgs list of the same transaction handle to the point of getting a list with over 1500 elements, and creation of new block groups leads to the need of reserving space in the chunk block reserve and often creating a new system block group too. So that made us quickly exhaust the chunk block reserve/system space info, because as of the commit mentioned before, we do reserve space for each new block group in the chunk block reserve, unlike before where we would not and would at most allocate one new system block group and therefore would only ensure that there was enough space in the system space info to allocate 1 new block group even if we ended up allocating thousands of new block groups using the same transaction handle. That worked most of the time because the computed required space at check_system_chunk() is very pessimistic (assumes a chunk tree height of BTRFS_MAX_LEVEL/8 and that all nodes/leafs in a path will be COWed and split) and since the updates to the chunk tree all happen at btrfs_create_pending_block_groups it is unlikely that a path needs to be COWed more than once (unless writepages() for the btree inode is called by mm in between) and that compensated for the need of creating any new nodes/leads in the chunk tree. So fix this by ensuring we don't accumulate a too large list of new block groups in a transaction's handles new_bgs list, inserting/updating the chunk tree for all accumulated new block groups and releasing the unused space from the chunk block reserve whenever the list becomes sufficiently large. This is a generic solution even though the problem currently can only happen when starting the writeout of the free space caches for all dirty block groups (btrfs_start_dirty_block_groups()). Reported-by: Omar Sandoval Signed-off-by: Filipe Manana Tested-by: Omar Sandoval Signed-off-by: Chris Mason --- fs/btrfs/extent-tree.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 171312d51799..07204bf601ed 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4227,6 +4227,24 @@ out: space_info->chunk_alloc = 0; spin_unlock(&space_info->lock); mutex_unlock(&fs_info->chunk_mutex); + /* + * When we allocate a new chunk we reserve space in the chunk block + * reserve to make sure we can COW nodes/leafs in the chunk tree or + * add new nodes/leafs to it if we end up needing to do it when + * inserting the chunk item and updating device items as part of the + * second phase of chunk allocation, performed by + * btrfs_finish_chunk_alloc(). So make sure we don't accumulate a + * large number of new block groups to create in our transaction + * handle's new_bgs list to avoid exhausting the chunk block reserve + * in extreme cases - like having a single transaction create many new + * block groups when starting to write out the free space caches of all + * the block groups that were made dirty during the lifetime of the + * transaction. + */ + if (trans->chunk_bytes_reserved >= (2 * 1024 * 1024ull)) { + btrfs_create_pending_block_groups(trans, trans->root); + btrfs_trans_release_chunk_metadata(trans); + } return ret; } From 450ed0db011d200a691591a75fdbcd7cae1a9b4a Mon Sep 17 00:00:00 2001 From: Alexey Brodkin Date: Thu, 16 Jul 2015 21:45:17 +0300 Subject: [PATCH 079/428] ARCv2: allow selection of page size for MMUv4 MMUv4 also supports the configurable page size as MMUv3. Signed-off-by: Alexey Brodkin Signed-off-by: Vineet Gupta --- arch/arc/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index f7cfa7d574f6..a5fccdfbfc8f 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -313,11 +313,11 @@ config ARC_PAGE_SIZE_8K config ARC_PAGE_SIZE_16K bool "16KB" - depends on ARC_MMU_V3 + depends on ARC_MMU_V3 || ARC_MMU_V4 config ARC_PAGE_SIZE_4K bool "4KB" - depends on ARC_MMU_V3 + depends on ARC_MMU_V3 || ARC_MMU_V4 endchoice From 3ba3a73e9f204ce7904cae7d14be399b467c4fef Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Mon, 20 Jul 2015 20:45:51 +1000 Subject: [PATCH 080/428] powerpc/powernv/ioda2: Fix calculation for memory allocated for TCE table The existing code stores the amount of memory allocated for a TCE table. At the moment it uses @offset which is a virtual offset in the TCE table which is only correct for a one level tables and it does not include memory allocated for intermediate levels. When multilevel TCE table is requested, WARN_ON in tce_iommu_create_table() prints a warning. This adds an additional counter to pnv_pci_ioda2_table_do_alloc_pages() to count actually allocated memory. Signed-off-by: Alexey Kardashevskiy Reviewed-by: David Gibson Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/powernv/pci-ioda.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 5738d315248b..85cbc96eff6c 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -2220,7 +2220,7 @@ static void pnv_pci_ioda_setup_opal_tce_kill(struct pnv_phb *phb) static __be64 *pnv_pci_ioda2_table_do_alloc_pages(int nid, unsigned shift, unsigned levels, unsigned long limit, - unsigned long *current_offset) + unsigned long *current_offset, unsigned long *total_allocated) { struct page *tce_mem = NULL; __be64 *addr, *tmp; @@ -2236,6 +2236,7 @@ static __be64 *pnv_pci_ioda2_table_do_alloc_pages(int nid, unsigned shift, } addr = page_address(tce_mem); memset(addr, 0, allocated); + *total_allocated += allocated; --levels; if (!levels) { @@ -2245,7 +2246,7 @@ static __be64 *pnv_pci_ioda2_table_do_alloc_pages(int nid, unsigned shift, for (i = 0; i < entries; ++i) { tmp = pnv_pci_ioda2_table_do_alloc_pages(nid, shift, - levels, limit, current_offset); + levels, limit, current_offset, total_allocated); if (!tmp) break; @@ -2267,7 +2268,7 @@ static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset, struct iommu_table *tbl) { void *addr; - unsigned long offset = 0, level_shift; + unsigned long offset = 0, level_shift, total_allocated = 0; const unsigned window_shift = ilog2(window_size); unsigned entries_shift = window_shift - page_shift; unsigned table_shift = max_t(unsigned, entries_shift + 3, PAGE_SHIFT); @@ -2286,7 +2287,7 @@ static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset, /* Allocate TCE table */ addr = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift, - levels, tce_table_size, &offset); + levels, tce_table_size, &offset, &total_allocated); /* addr==NULL means that the first level allocation failed */ if (!addr) @@ -2308,7 +2309,7 @@ static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset, page_shift); tbl->it_level_size = 1ULL << (level_shift - 3); tbl->it_indirect_levels = levels - 1; - tbl->it_allocated_size = offset; + tbl->it_allocated_size = total_allocated; pr_devel("Created TCE table: ws=%08llx ts=%lx @%08llx\n", window_size, tce_table_size, bus_offset); From 120d200a86273d1840d091959dca65617cd9eff2 Mon Sep 17 00:00:00 2001 From: Luis Henriques Date: Fri, 17 Jul 2015 14:20:31 +0100 Subject: [PATCH 081/428] macintosh/ans-lcd: fix build failure after module_init/exit relocation After commit 0fd972a7d91d ("module: relocate module_init from init.h to module.h") ans-lcd module fails to build with: drivers/macintosh/ans-lcd.c:201:1: warning: data definition has no type or storage class [enabled by default] module_init(anslcd_init); ^ drivers/macintosh/ans-lcd.c:201:1: error: type defaults to 'int' in declaration of 'module_init' [-Werror=implicit-int] drivers/macintosh/ans-lcd.c:201:1: warning: parameter names (without types) in function declaration [enabled by default] drivers/macintosh/ans-lcd.c:202:1: warning: data definition has no type or storage class [enabled by default] module_exit(anslcd_exit); ^ drivers/macintosh/ans-lcd.c:202:1: error: type defaults to 'int' in declaration of 'module_exit' [-Werror=implicit-int] drivers/macintosh/ans-lcd.c:202:1: warning: parameter names (without types) in function declaration [enabled by default] drivers/macintosh/ans-lcd.c:155:1: warning: 'anslcd_init' defined but not used [-Wunused-function] anslcd_init(void) ^ drivers/macintosh/ans-lcd.c:195:1: warning: 'anslcd_exit' defined but not used [-Wunused-function] anslcd_exit(void) ^ This commit fixes it by replacing linux/init.h by linux/module.h. Fixes: 0fd972a7d91d ("module: relocate module_init from init.h to module.h") Signed-off-by: Luis Henriques Acked-by: Paul Gortmaker Signed-off-by: Michael Ellerman --- drivers/macintosh/ans-lcd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/macintosh/ans-lcd.c b/drivers/macintosh/ans-lcd.c index 1a57e88a38f7..cd35079c8c98 100644 --- a/drivers/macintosh/ans-lcd.c +++ b/drivers/macintosh/ans-lcd.c @@ -7,7 +7,7 @@ #include #include #include -#include +#include #include #include From 6f043b50da8e03bdcc5703fd37ea45bc6892432f Mon Sep 17 00:00:00 2001 From: Tadeusz Struk Date: Tue, 21 Jul 2015 22:07:47 -0700 Subject: [PATCH 082/428] crypto: qat - Fix invalid synchronization between register/unregister sym algs The synchronization method used atomic was bogus. Use a proper synchronization with mutex. Cc: stable@vger.kernel.org Signed-off-by: Tadeusz Struk Signed-off-by: Herbert Xu --- drivers/crypto/qat/qat_common/qat_algs.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c index 067402c7c2a9..df427c0e9e7b 100644 --- a/drivers/crypto/qat/qat_common/qat_algs.c +++ b/drivers/crypto/qat/qat_common/qat_algs.c @@ -73,7 +73,8 @@ ICP_QAT_HW_CIPHER_KEY_CONVERT, \ ICP_QAT_HW_CIPHER_DECRYPT) -static atomic_t active_dev; +static DEFINE_MUTEX(algs_lock); +static unsigned int active_devs; struct qat_alg_buf { uint32_t len; @@ -1280,7 +1281,10 @@ static struct crypto_alg qat_algs[] = { { int qat_algs_register(void) { - if (atomic_add_return(1, &active_dev) == 1) { + int ret = 0; + + mutex_lock(&algs_lock); + if (++active_devs == 1) { int i; for (i = 0; i < ARRAY_SIZE(qat_algs); i++) @@ -1289,21 +1293,25 @@ int qat_algs_register(void) CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC : CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC; - return crypto_register_algs(qat_algs, ARRAY_SIZE(qat_algs)); + ret = crypto_register_algs(qat_algs, ARRAY_SIZE(qat_algs)); } - return 0; + mutex_unlock(&algs_lock); + return ret; } int qat_algs_unregister(void) { - if (atomic_sub_return(1, &active_dev) == 0) - return crypto_unregister_algs(qat_algs, ARRAY_SIZE(qat_algs)); - return 0; + int ret = 0; + + mutex_lock(&algs_lock); + if (--active_devs == 0) + ret = crypto_unregister_algs(qat_algs, ARRAY_SIZE(qat_algs)); + mutex_unlock(&algs_lock); + return ret; } int qat_algs_init(void) { - atomic_set(&active_dev, 0); crypto_get_default_rng(); return 0; } From f898c522f0e9ac9f3177d0762b76e2ab2d2cf9c0 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 22 Jul 2015 18:05:35 +0800 Subject: [PATCH 083/428] crypto: ixp4xx - Remove bogus BUG_ON on scattered dst buffer This patch removes a bogus BUG_ON in the ablkcipher path that triggers when the destination buffer is different from the source buffer and is scattered. Cc: stable@vger.kernel.org Signed-off-by: Herbert Xu --- drivers/crypto/ixp4xx_crypto.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c index 7ba495f75370..402631a19a11 100644 --- a/drivers/crypto/ixp4xx_crypto.c +++ b/drivers/crypto/ixp4xx_crypto.c @@ -905,7 +905,6 @@ static int ablk_perform(struct ablkcipher_request *req, int encrypt) crypt->mode |= NPE_OP_NOT_IN_PLACE; /* This was never tested by Intel * for more than one dst buffer, I think. */ - BUG_ON(req->dst->length < nbytes); req_ctx->dst = NULL; if (!chainup_buffers(dev, req->dst, nbytes, &dst_hook, flags, DMA_FROM_DEVICE)) From 9a258afa928b45e6dd2efcac46ccf7eea705d35a Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Thu, 16 Jul 2015 16:16:44 +0300 Subject: [PATCH 084/428] ARM: OMAP2+: hwmod: Fix _wait_target_ready() for hwmods without sysc For hwmods without sysc, _init_mpu_rt_base(oh) won't be called and so _find_mpu_rt_port(oh) will return NULL thus preventing ready state check on those modules after the module is enabled. This can potentially cause a bus access error if the module is accessed before the module is ready. Fix this by unconditionally calling _init_mpu_rt_base() during hwmod _init(). Do ioremap only if we need SYSC access. Eventhough _wait_target_ready() check doesn't really need MPU RT port but just the PRCM registers, we still mandate that the hwmod must have an MPU RT port if ready state check needs to be done. Else it would mean that the module is not accessible by MPU so there is no point in waiting for target to be ready. e.g. this fixes the below DCAN bus access error on AM437x-gp-evm. [ 16.672978] ------------[ cut here ]------------ [ 16.677885] WARNING: CPU: 0 PID: 1580 at drivers/bus/omap_l3_noc.c:147 l3_interrupt_handler+0x234/0x35c() [ 16.687946] 44000000.ocp:L3 Custom Error: MASTER M2 (64-bit) TARGET L4_PER_0 (Read): Data Access in User mode during Functional access [ 16.700654] Modules linked in: xhci_hcd btwilink ti_vpfe dwc3 videobuf2_core ov2659 bluetooth v4l2_common videodev ti_am335x_adc kfifo_buf industrialio c_can_platform videobuf2_dma_contig media snd_soc_tlv320aic3x pixcir_i2c_ts c_can dc [ 16.731144] CPU: 0 PID: 1580 Comm: rpc.statd Not tainted 3.14.26-02561-gf733aa036398 #180 [ 16.739747] Backtrace: [ 16.742336] [] (dump_backtrace) from [] (show_stack+0x18/0x1c) [ 16.750285] r6:00000093 r5:00000009 r4:eab5b8a8 r3:00000000 [ 16.756252] [] (show_stack) from [] (dump_stack+0x20/0x28) [ 16.763870] [] (dump_stack) from [] (warn_slowpath_common+0x6c/0x8c) [ 16.772408] [] (warn_slowpath_common) from [] (warn_slowpath_fmt+0x38/0x40) [ 16.781550] r8:c05d1f90 r7:c0730844 r6:c0730448 r5:80080003 r4:ed0cd210 [ 16.788626] [] (warn_slowpath_fmt) from [] (l3_interrupt_handler+0x234/0x35c) [ 16.797968] r3:ed0cd480 r2:c0730508 [ 16.801747] [] (l3_interrupt_handler) from [] (handle_irq_event_percpu+0x54/0x1bc) [ 16.811533] r10:ed005600 r9:c084855b r8:0000002a r7:00000000 r6:00000000 r5:0000002a [ 16.819780] r4:ed0e6d80 [ 16.822453] [] (handle_irq_event_percpu) from [] (handle_irq_event+0x30/0x40) [ 16.831789] r10:eb2b6938 r9:eb2b6960 r8:bf011420 r7:fa240100 r6:00000000 r5:0000002a [ 16.840052] r4:ed005600 [ 16.842744] [] (handle_irq_event) from [] (handle_fasteoi_irq+0x74/0x128) [ 16.851702] r4:ed005600 r3:00000000 [ 16.855479] [] (handle_fasteoi_irq) from [] (generic_handle_irq+0x28/0x38) [ 16.864523] r4:0000002a r3:c0066164 [ 16.868294] [] (generic_handle_irq) from [] (handle_IRQ+0x38/0x8c) [ 16.876612] r4:c081c640 r3:00000202 [ 16.880380] [] (handle_IRQ) from [] (gic_handle_irq+0x30/0x5c) [ 16.888328] r6:eab5ba38 r5:c0804460 r4:fa24010c r3:00000100 [ 16.894303] [] (gic_handle_irq) from [] (__irq_svc+0x40/0x50) [ 16.902193] Exception stack(0xeab5ba38 to 0xeab5ba80) [ 16.907499] ba20: 00000000 00000006 [ 16.916108] ba40: fa1d0000 fa1d0008 ed3d3000 eab5bab4 ed3d3460 c0842af4 bf011420 eb2b6960 [ 16.924716] ba60: eb2b6938 eab5ba8c eab5ba90 eab5ba80 bf035220 bf07702c 600f0013 ffffffff [ 16.933317] r7:eab5ba6c r6:ffffffff r5:600f0013 r4:bf07702c [ 16.939317] [] (c_can_plat_read_reg_aligned_to_16bit [c_can_platform]) from [] (c_can_get_berr_counter+0x38/0x64 [c_can]) [ 16.952696] [] (c_can_get_berr_counter [c_can]) from [] (can_fill_info+0x124/0x15c [can_dev]) [ 16.963480] r5:ec8c9740 r4:ed3d3000 [ 16.967253] [] (can_fill_info [can_dev]) from [] (rtnl_fill_ifinfo+0x58c/0x8fc) [ 16.976749] r6:ec8c9740 r5:ed3d3000 r4:eb2b6780 [ 16.981613] [] (rtnl_fill_ifinfo) from [] (rtnl_dump_ifinfo+0xf0/0x1dc) [ 16.990401] r10:ec8c9740 r9:00000000 r8:00000000 r7:00000000 r6:ebd4d1b4 r5:ed3d3000 [ 16.998671] r4:00000000 [ 17.001342] [] (rtnl_dump_ifinfo) from [] (netlink_dump+0xa8/0x1e0) [ 17.009772] r10:00000000 r9:00000000 r8:c0503318 r7:ebf3e6c0 r6:ebd4d1b4 r5:ec8c9740 [ 17.018050] r4:ebd4d000 [ 17.020714] [] (netlink_dump) from [] (__netlink_dump_start+0x104/0x154) [ 17.029591] r6:eab5bd34 r5:ec8c9980 r4:ebd4d000 [ 17.034454] [] (__netlink_dump_start) from [] (rtnetlink_rcv_msg+0x110/0x1f4) [ 17.043778] r7:00000000 r6:ec8c9980 r5:00000f40 r4:ebf3e6c0 [ 17.049743] [] (rtnetlink_rcv_msg) from [] (netlink_rcv_skb+0xb4/0xc8) [ 17.058449] r8:eab5bdac r7:ec8c9980 r6:c05054f4 r5:ec8c9980 r4:ebf3e6c0 [ 17.065534] [] (netlink_rcv_skb) from [] (rtnetlink_rcv+0x24/0x2c) [ 17.073854] r6:ebd4d000 r5:00000014 r4:ec8c9980 r3:c0504110 [ 17.079846] [] (rtnetlink_rcv) from [] (netlink_unicast+0x180/0x1ec) [ 17.088363] r4:ed0c6800 r3:c0504110 [ 17.092113] [] (netlink_unicast) from [] (netlink_sendmsg+0x2ac/0x380) [ 17.100813] r10:00000000 r8:00000008 r7:ec8c9980 r6:ebd4d000 r5:eab5be70 r4:eab5bee4 [ 17.109083] [] (netlink_sendmsg) from [] (sock_sendmsg+0x90/0xb0) [ 17.117305] r10:00000000 r9:eab5a000 r8:becdda3c r7:0000000c r6:ea978400 r5:eab5be70 [ 17.125563] r4:c05103c4 [ 17.128225] [] (sock_sendmsg) from [] (SyS_sendto+0xb8/0xdc) [ 17.136001] r6:becdda5c r5:00000014 r4:ecd37040 [ 17.140876] [] (SyS_sendto) from [] (ret_fast_syscall+0x0/0x30) [ 17.148923] r10:00000000 r8:c000e804 r7:00000122 r6:becdda5c r5:0000000c r4:becdda5c [ 17.157169] ---[ end trace 2b71e15b38f58bad ]--- Fixes: 6423d6df1440 ("ARM: OMAP2+: hwmod: check for module address space during init") Signed-off-by: Roger Quadros Signed-off-by: Paul Walmsley Cc: --- arch/arm/mach-omap2/omap_hwmod.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index d78c12e7cb5e..486cc4ded190 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -2373,6 +2373,9 @@ static int of_dev_hwmod_lookup(struct device_node *np, * registers. This address is needed early so the OCP registers that * are part of the device's address space can be ioremapped properly. * + * If SYSC access is not needed, the registers will not be remapped + * and non-availability of MPU access is not treated as an error. + * * Returns 0 on success, -EINVAL if an invalid hwmod is passed, and * -ENXIO on absent or invalid register target address space. */ @@ -2387,6 +2390,11 @@ static int __init _init_mpu_rt_base(struct omap_hwmod *oh, void *data, _save_mpu_port_index(oh); + /* if we don't need sysc access we don't need to ioremap */ + if (!oh->class->sysc) + return 0; + + /* we can't continue without MPU PORT if we need sysc access */ if (oh->_int_flags & _HWMOD_NO_MPU_PORT) return -ENXIO; @@ -2396,8 +2404,10 @@ static int __init _init_mpu_rt_base(struct omap_hwmod *oh, void *data, oh->name); /* Extract the IO space from device tree blob */ - if (!np) + if (!np) { + pr_err("omap_hwmod: %s: no dt node\n", oh->name); return -ENXIO; + } va_start = of_iomap(np, index + oh->mpu_rt_idx); } else { @@ -2456,13 +2466,11 @@ static int __init _init(struct omap_hwmod *oh, void *data) oh->name, np->name); } - if (oh->class->sysc) { - r = _init_mpu_rt_base(oh, NULL, index, np); - if (r < 0) { - WARN(1, "omap_hwmod: %s: doesn't have mpu register target base\n", - oh->name); - return 0; - } + r = _init_mpu_rt_base(oh, NULL, index, np); + if (r < 0) { + WARN(1, "omap_hwmod: %s: doesn't have mpu register target base\n", + oh->name); + return 0; } r = _init_clocks(oh, NULL); From 25ba265390c09b0a2b2f3fd9ba82e37248b7a371 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Mon, 20 Jul 2015 20:31:25 +0300 Subject: [PATCH 085/428] Bluetooth: Fix NULL pointer dereference in smp_conn_security The l2cap_conn->smp pointer may be NULL for various valid reasons where SMP has failed to initialize properly. One such scenario is when crypto support is missing, another when the adapter has been powered on through a legacy method. The smp_conn_security() function should have the appropriate check for this situation to avoid NULL pointer dereferences. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann Cc: stable@vger.kernel.org # 4.0+ --- net/bluetooth/smp.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 3d0f7d2a0616..ad82324f710f 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -2312,6 +2312,10 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) return 1; chan = conn->smp; + if (!chan) { + BT_ERR("SMP security requested but not available"); + return 1; + } if (!hci_dev_test_flag(hcon->hdev, HCI_LE_ENABLED)) return 1; From fd4e1393c414275d28577a2242f4e424cf80a605 Mon Sep 17 00:00:00 2001 From: Nicholas Mc Guire Date: Mon, 6 Jul 2015 18:04:40 +0200 Subject: [PATCH 086/428] tcm_qla2xxx: pass timeout as HZ independent value API compliance scanning with coccinelle flagged: ./drivers/scsi/qla2xxx/tcm_qla2xxx.c:407:2-29: WARNING: timeout is HZ dependent This was introduced in 'commit 75f8c1f693ee ("[SCSI] tcm_qla2xxx: Add >= 24xx series fabric module for target-core")'. wait_for_completion_timeout() expects a timeout in jiffies so the numeric constant makes the effective timeout HZ dependent. Resolved by converting it to CONST * HZ. Signed-off-by: Nicholas Mc Guire Acked-by: Nilesh Javali Signed-off-by: Nicholas Bellinger --- drivers/scsi/qla2xxx/tcm_qla2xxx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index d9a8c6084346..33364b663cc9 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -405,7 +405,7 @@ static int tcm_qla2xxx_write_pending_status(struct se_cmd *se_cmd) se_cmd->t_state == TRANSPORT_COMPLETE_QF_WP) { spin_unlock_irqrestore(&se_cmd->t_state_lock, flags); wait_for_completion_timeout(&se_cmd->t_transport_stop_comp, - 3000); + 3 * HZ); return 0; } spin_unlock_irqrestore(&se_cmd->t_state_lock, flags); From bc1a7d6aff763ea29db6319185327f86b0fe93b6 Mon Sep 17 00:00:00 2001 From: Andy Grover Date: Thu, 9 Jul 2015 09:56:47 -0700 Subject: [PATCH 087/428] target: Indicate success if writing 0 to pi_prot_type See https://bugzilla.redhat.com/show_bug.cgi?id=1240687 Returning 0 from a configfs store function results in infinite retries. Reported-by: Yanko Kaneti Signed-off-by: Andy Grover Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_configfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index 0b0de3647478..cb09e6988b56 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -747,7 +747,7 @@ static ssize_t store_pi_prot_type(struct se_dev_attrib *da, if (!dev->transport->init_prot || !dev->transport->free_prot) { /* 0 is only allowed value for non-supporting backends */ if (flag == 0) - return 0; + return count; pr_err("DIF protection not supported by backend: %s\n", dev->transport->name); From 9105bfc038ca5a506404ce37cd3c0e85f76351e3 Mon Sep 17 00:00:00 2001 From: Andy Grover Date: Thu, 9 Jul 2015 09:56:48 -0700 Subject: [PATCH 088/428] target: Do not return 0 from aptpl and alua configfs store functions Here are some more instances where we are returning 0 from a configfs store function, the unintended result of which is likely infinite retries from userspace. Signed-off-by: Andy Grover Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_configfs.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index cb09e6988b56..7f3cb3a2b783 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -1590,9 +1590,9 @@ static ssize_t target_core_dev_pr_store_attr_res_aptpl_metadata( u8 type = 0; if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) - return 0; + return count; if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS) - return 0; + return count; if (dev->export_count) { pr_debug("Unable to process APTPL metadata while" @@ -1985,7 +1985,7 @@ static ssize_t target_core_store_alua_lu_gp( lu_gp_mem = dev->dev_alua_lu_gp_mem; if (!lu_gp_mem) - return 0; + return count; if (count > LU_GROUP_NAME_BUF) { pr_err("ALUA LU Group Alias too large!\n"); From c20910264c367a5dfbf6c09e8ec2ff0c5c52857a Mon Sep 17 00:00:00 2001 From: David Disseldorp Date: Sun, 12 Jul 2015 18:49:18 +0200 Subject: [PATCH 089/428] target/configfs: handle match_int() errors As a follow up to ce31c1b0dc4038a1dec64585d892adb73d9c45f4 - there are still a few LIO match_int() calls that don't check the return value. Propagate errors rather than using the potentially uninitialised result. Signed-off-by: David Disseldorp Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_configfs.c | 32 ++++++++++++++++++++------- 1 file changed, 24 insertions(+), 8 deletions(-) diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index 7f3cb3a2b783..c2e9fea90b4a 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -1658,22 +1658,32 @@ static ssize_t target_core_dev_pr_store_attr_res_aptpl_metadata( * PR APTPL Metadata for Reservation */ case Opt_res_holder: - match_int(args, &arg); + ret = match_int(args, &arg); + if (ret) + goto out; res_holder = arg; break; case Opt_res_type: - match_int(args, &arg); + ret = match_int(args, &arg); + if (ret) + goto out; type = (u8)arg; break; case Opt_res_scope: - match_int(args, &arg); + ret = match_int(args, &arg); + if (ret) + goto out; break; case Opt_res_all_tg_pt: - match_int(args, &arg); + ret = match_int(args, &arg); + if (ret) + goto out; all_tg_pt = (int)arg; break; case Opt_mapped_lun: - match_int(args, &arg); + ret = match_int(args, &arg); + if (ret) + goto out; mapped_lun = (u64)arg; break; /* @@ -1701,14 +1711,20 @@ static ssize_t target_core_dev_pr_store_attr_res_aptpl_metadata( } break; case Opt_tpgt: - match_int(args, &arg); + ret = match_int(args, &arg); + if (ret) + goto out; tpgt = (u16)arg; break; case Opt_port_rtpi: - match_int(args, &arg); + ret = match_int(args, &arg); + if (ret) + goto out; break; case Opt_target_lun: - match_int(args, &arg); + ret = match_int(args, &arg); + if (ret) + goto out; target_lun = (u64)arg; break; default: From fa8173a3ef0570affde7da352de202190b3786c2 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Thu, 23 Jul 2015 23:22:26 +0800 Subject: [PATCH 090/428] ASoC: pcm1681: Fix setting de-emphasis sampling rate selection The de-emphasis sampling rate selection is controlled by BIT[3:4] of PCM1681_DEEMPH_CONTROL register. Do proper left shift to set it. Signed-off-by: Axel Lin Acked-by: Marek Belisko Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- sound/soc/codecs/pcm1681.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/codecs/pcm1681.c b/sound/soc/codecs/pcm1681.c index 477e13d30971..e7ba557979cb 100644 --- a/sound/soc/codecs/pcm1681.c +++ b/sound/soc/codecs/pcm1681.c @@ -102,7 +102,7 @@ static int pcm1681_set_deemph(struct snd_soc_codec *codec) if (val != -1) { regmap_update_bits(priv->regmap, PCM1681_DEEMPH_CONTROL, - PCM1681_DEEMPH_RATE_MASK, val); + PCM1681_DEEMPH_RATE_MASK, val << 3); enable = 1; } else enable = 0; From 49fa63d8c2f95b636cc31a7164aeac0309dfa3c9 Mon Sep 17 00:00:00 2001 From: Steve Wise Date: Wed, 22 Jul 2015 14:14:17 -0500 Subject: [PATCH 091/428] RDMA/cxgb3: fail get_dma_mr on 64 bit arches T3 HW only supports 32 bit MRs. If the system uses 64 bit memory addresses, then a registered 32 bit MR will wrap and write to the wrong memory when used with addresses > 4GB. To prevent this, simply fail to allocate an MR on 64 bit machines (other means of registering memory are still available and software can still work, we just don't allow this means of memory registration). Signed-off-by: Steve Wise Signed-off-by: Doug Ledford --- drivers/infiniband/hw/cxgb3/iwch_provider.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c index b1b73232f217..bbbe0184e592 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_provider.c +++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c @@ -736,6 +736,10 @@ static struct ib_mr *iwch_get_dma_mr(struct ib_pd *pd, int acc) /* * T3 only supports 32 bits of size. */ + if (sizeof(phys_addr_t) > 4) { + pr_warn_once(MOD "Cannot support dma_mrs on this platform.\n"); + return ERR_PTR(-ENOTSUPP); + } bl.size = 0xffffffff; bl.addr = 0; kva = 0; From efc1eedbf63a194b3b576fc25776f3f1fa55a4d4 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 22 Jul 2015 14:30:03 -0600 Subject: [PATCH 092/428] IB/ipoib: Fix CONFIG_INFINIBAND_IPOIB_CM If the above is turned off then ipoib_cm_dev_init unconditionally returns ENOSYS, and the newly added error handling in 0b3957 prevents ipoib from coming up at all: kernel: mlx4_0: ipoib_transport_dev_init failed kernel: mlx4_0: failed to initialize port 1 (ret = -12) Fixes: 0b39578bcde4 (IB/ipoib: Use dedicated workqueues per interface) Signed-off-by: Jason Gunthorpe Signed-off-by: Doug Ledford --- drivers/infiniband/ulp/ipoib/ipoib_verbs.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c index 9e6ee82a8fd7..851c8219d501 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c @@ -177,7 +177,8 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca) else size += ipoib_recvq_size * ipoib_max_conn_qp; } else - goto out_free_wq; + if (ret != -ENOSYS) + goto out_free_wq; cq_attr.cqe = size; priv->recv_cq = ib_create_cq(priv->ca, ipoib_ib_completion, NULL, From 71ee67306ecbdfc0c94ed93c77ff99d29e961d69 Mon Sep 17 00:00:00 2001 From: Devesh Sharma Date: Fri, 24 Jul 2015 05:03:59 +0530 Subject: [PATCH 093/428] RDMA/ocrdma: update ocrdma license to dual-license Change of license from GPLv2 to dual-license (GPLv2 and BSD 2-Clause) All contributors were contacted off-list and permission to make this change was received. The complete list of contributors are Cc:ed here. Cc: Tejun Heo Cc: Duan Jiong Cc: Roland Dreier Cc: Jes Sorensen Cc: Sasha Levin Cc: Dan Carpenter Cc: Prarit Bhargava Cc: Colin Ian King Cc: Wei Yongjun Cc: Moni Shoua Cc: Rasmus Villemoes Cc: Li RongQing Cc: Devendra Naga Signed-off-by: Devesh Sharma Signed-off-by: Doug Ledford --- drivers/infiniband/hw/ocrdma/ocrdma.h | 53 +++++++++++++-------- drivers/infiniband/hw/ocrdma/ocrdma_abi.h | 53 +++++++++++++-------- drivers/infiniband/hw/ocrdma/ocrdma_ah.c | 53 +++++++++++++-------- drivers/infiniband/hw/ocrdma/ocrdma_ah.h | 53 +++++++++++++-------- drivers/infiniband/hw/ocrdma/ocrdma_hw.c | 53 +++++++++++++-------- drivers/infiniband/hw/ocrdma/ocrdma_hw.h | 53 +++++++++++++-------- drivers/infiniband/hw/ocrdma/ocrdma_main.c | 53 +++++++++++++-------- drivers/infiniband/hw/ocrdma/ocrdma_sli.h | 53 +++++++++++++-------- drivers/infiniband/hw/ocrdma/ocrdma_stats.c | 53 +++++++++++++-------- drivers/infiniband/hw/ocrdma/ocrdma_stats.h | 53 +++++++++++++-------- drivers/infiniband/hw/ocrdma/ocrdma_verbs.c | 53 +++++++++++++-------- drivers/infiniband/hw/ocrdma/ocrdma_verbs.h | 53 +++++++++++++-------- 12 files changed, 408 insertions(+), 228 deletions(-) diff --git a/drivers/infiniband/hw/ocrdma/ocrdma.h b/drivers/infiniband/hw/ocrdma/ocrdma.h index b396344fae16..6a36338593cd 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma.h @@ -1,21 +1,36 @@ -/******************************************************************* - * This file is part of the Emulex RoCE Device Driver for * - * RoCE (RDMA over Converged Ethernet) adapters. * - * Copyright (C) 2008-2012 Emulex. All rights reserved. * - * EMULEX and SLI are trademarks of Emulex. * - * www.emulex.com * - * * - * This program is free software; you can redistribute it and/or * - * modify it under the terms of version 2 of the GNU General * - * Public License as published by the Free Software Foundation. * - * This program is distributed in the hope that it will be useful. * - * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND * - * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY, * - * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE * - * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD * - * TO BE LEGALLY INVALID. See the GNU General Public License for * - * more details, a copy of which can be found in the file COPYING * - * included with this package. * +/* This file is part of the Emulex RoCE Device Driver for + * RoCE (RDMA over Converged Ethernet) adapters. + * Copyright (C) 2012-2015 Emulex. All rights reserved. + * EMULEX and SLI are trademarks of Emulex. + * www.emulex.com + * + * This software is available to you under a choice of one of two licenses. + * You may choose to be licensed under the terms of the GNU General Public + * License (GPL) Version 2, available from the file COPYING in the main + * directory of this source tree, or the BSD license below: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * - Redistributions of source code must retain the above copyright notice, + * this list of conditions and the following disclaimer. + * + * - Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR + * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF + * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. * * Contact Information: * linux-drivers@emulex.com @@ -23,7 +38,7 @@ * Emulex * 3333 Susan Street * Costa Mesa, CA 92626 - *******************************************************************/ + */ #ifndef __OCRDMA_H__ #define __OCRDMA_H__ diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_abi.h b/drivers/infiniband/hw/ocrdma/ocrdma_abi.h index 1554cca5712a..430b1350fe96 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_abi.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma_abi.h @@ -1,21 +1,36 @@ -/******************************************************************* - * This file is part of the Emulex RoCE Device Driver for * - * RoCE (RDMA over Converged Ethernet) adapters. * - * Copyright (C) 2008-2012 Emulex. All rights reserved. * - * EMULEX and SLI are trademarks of Emulex. * - * www.emulex.com * - * * - * This program is free software; you can redistribute it and/or * - * modify it under the terms of version 2 of the GNU General * - * Public License as published by the Free Software Foundation. * - * This program is distributed in the hope that it will be useful. * - * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND * - * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY, * - * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE * - * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD * - * TO BE LEGALLY INVALID. See the GNU General Public License for * - * more details, a copy of which can be found in the file COPYING * - * included with this package. * +/* This file is part of the Emulex RoCE Device Driver for + * RoCE (RDMA over Converged Ethernet) adapters. + * Copyright (C) 2012-2015 Emulex. All rights reserved. + * EMULEX and SLI are trademarks of Emulex. + * www.emulex.com + * + * This software is available to you under a choice of one of two licenses. + * You may choose to be licensed under the terms of the GNU General Public + * License (GPL) Version 2, available from the file COPYING in the main + * directory of this source tree, or the BSD license below: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * - Redistributions of source code must retain the above copyright notice, + * this list of conditions and the following disclaimer. + * + * - Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR + * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF + * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. * * Contact Information: * linux-drivers@emulex.com @@ -23,7 +38,7 @@ * Emulex * 3333 Susan Street * Costa Mesa, CA 92626 - *******************************************************************/ + */ #ifndef __OCRDMA_ABI_H__ #define __OCRDMA_ABI_H__ diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c index 29b27675dd70..44766fee1f4e 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c @@ -1,21 +1,36 @@ -/******************************************************************* - * This file is part of the Emulex RoCE Device Driver for * - * RoCE (RDMA over Converged Ethernet) adapters. * - * Copyright (C) 2008-2012 Emulex. All rights reserved. * - * EMULEX and SLI are trademarks of Emulex. * - * www.emulex.com * - * * - * This program is free software; you can redistribute it and/or * - * modify it under the terms of version 2 of the GNU General * - * Public License as published by the Free Software Foundation. * - * This program is distributed in the hope that it will be useful. * - * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND * - * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY, * - * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE * - * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD * - * TO BE LEGALLY INVALID. See the GNU General Public License for * - * more details, a copy of which can be found in the file COPYING * - * included with this package. * +/* This file is part of the Emulex RoCE Device Driver for + * RoCE (RDMA over Converged Ethernet) adapters. + * Copyright (C) 2012-2015 Emulex. All rights reserved. + * EMULEX and SLI are trademarks of Emulex. + * www.emulex.com + * + * This software is available to you under a choice of one of two licenses. + * You may choose to be licensed under the terms of the GNU General Public + * License (GPL) Version 2, available from the file COPYING in the main + * directory of this source tree, or the BSD license below: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * - Redistributions of source code must retain the above copyright notice, + * this list of conditions and the following disclaimer. + * + * - Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR + * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF + * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. * * Contact Information: * linux-drivers@emulex.com @@ -23,7 +38,7 @@ * Emulex * 3333 Susan Street * Costa Mesa, CA 92626 - *******************************************************************/ + */ #include #include diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.h b/drivers/infiniband/hw/ocrdma/ocrdma_ah.h index cf366fe03cb8..04a30ae67473 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.h @@ -1,21 +1,36 @@ -/******************************************************************* - * This file is part of the Emulex RoCE Device Driver for * - * RoCE (RDMA over Converged Ethernet) adapters. * - * Copyright (C) 2008-2012 Emulex. All rights reserved. * - * EMULEX and SLI are trademarks of Emulex. * - * www.emulex.com * - * * - * This program is free software; you can redistribute it and/or * - * modify it under the terms of version 2 of the GNU General * - * Public License as published by the Free Software Foundation. * - * This program is distributed in the hope that it will be useful. * - * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND * - * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY, * - * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE * - * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD * - * TO BE LEGALLY INVALID. See the GNU General Public License for * - * more details, a copy of which can be found in the file COPYING * - * included with this package. * +/* This file is part of the Emulex RoCE Device Driver for + * RoCE (RDMA over Converged Ethernet) adapters. + * Copyright (C) 2012-2015 Emulex. All rights reserved. + * EMULEX and SLI are trademarks of Emulex. + * www.emulex.com + * + * This software is available to you under a choice of one of two licenses. + * You may choose to be licensed under the terms of the GNU General Public + * License (GPL) Version 2, available from the file COPYING in the main + * directory of this source tree, or the BSD license below: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * - Redistributions of source code must retain the above copyright notice, + * this list of conditions and the following disclaimer. + * + * - Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR + * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF + * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. * * Contact Information: * linux-drivers@emulex.com @@ -23,7 +38,7 @@ * Emulex * 3333 Susan Street * Costa Mesa, CA 92626 - *******************************************************************/ + */ #ifndef __OCRDMA_AH_H__ #define __OCRDMA_AH_H__ diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c index 47615ff33bc6..aab391a15db4 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c @@ -1,21 +1,36 @@ -/******************************************************************* - * This file is part of the Emulex RoCE Device Driver for * - * RoCE (RDMA over Converged Ethernet) CNA Adapters. * - * Copyright (C) 2008-2012 Emulex. All rights reserved. * - * EMULEX and SLI are trademarks of Emulex. * - * www.emulex.com * - * * - * This program is free software; you can redistribute it and/or * - * modify it under the terms of version 2 of the GNU General * - * Public License as published by the Free Software Foundation. * - * This program is distributed in the hope that it will be useful. * - * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND * - * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY, * - * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE * - * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD * - * TO BE LEGALLY INVALID. See the GNU General Public License for * - * more details, a copy of which can be found in the file COPYING * - * included with this package. * +/* This file is part of the Emulex RoCE Device Driver for + * RoCE (RDMA over Converged Ethernet) adapters. + * Copyright (C) 2012-2015 Emulex. All rights reserved. + * EMULEX and SLI are trademarks of Emulex. + * www.emulex.com + * + * This software is available to you under a choice of one of two licenses. + * You may choose to be licensed under the terms of the GNU General Public + * License (GPL) Version 2, available from the file COPYING in the main + * directory of this source tree, or the BSD license below: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * - Redistributions of source code must retain the above copyright notice, + * this list of conditions and the following disclaimer. + * + * - Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR + * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF + * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. * * Contact Information: * linux-drivers@emulex.com @@ -23,7 +38,7 @@ * Emulex * 3333 Susan Street * Costa Mesa, CA 92626 - *******************************************************************/ + */ #include #include diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.h b/drivers/infiniband/hw/ocrdma/ocrdma_hw.h index e905972fceb7..7ed885c1851e 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.h @@ -1,21 +1,36 @@ -/******************************************************************* - * This file is part of the Emulex RoCE Device Driver for * - * RoCE (RDMA over Converged Ethernet) CNA Adapters. * - * Copyright (C) 2008-2012 Emulex. All rights reserved. * - * EMULEX and SLI are trademarks of Emulex. * - * www.emulex.com * - * * - * This program is free software; you can redistribute it and/or * - * modify it under the terms of version 2 of the GNU General * - * Public License as published by the Free Software Foundation. * - * This program is distributed in the hope that it will be useful. * - * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND * - * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY, * - * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE * - * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD * - * TO BE LEGALLY INVALID. See the GNU General Public License for * - * more details, a copy of which can be found in the file COPYING * - * included with this package. * +/* This file is part of the Emulex RoCE Device Driver for + * RoCE (RDMA over Converged Ethernet) adapters. + * Copyright (C) 2012-2015 Emulex. All rights reserved. + * EMULEX and SLI are trademarks of Emulex. + * www.emulex.com + * + * This software is available to you under a choice of one of two licenses. + * You may choose to be licensed under the terms of the GNU General Public + * License (GPL) Version 2, available from the file COPYING in the main + * directory of this source tree, or the BSD license below: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * - Redistributions of source code must retain the above copyright notice, + * this list of conditions and the following disclaimer. + * + * - Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR + * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF + * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. * * Contact Information: * linux-drivers@emulex.com @@ -23,7 +38,7 @@ * Emulex * 3333 Susan Street * Costa Mesa, CA 92626 - *******************************************************************/ + */ #ifndef __OCRDMA_HW_H__ #define __OCRDMA_HW_H__ diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c index d98a707a5eb9..6ded95a66725 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c @@ -1,21 +1,36 @@ -/******************************************************************* - * This file is part of the Emulex RoCE Device Driver for * - * RoCE (RDMA over Converged Ethernet) adapters. * - * Copyright (C) 2008-2012 Emulex. All rights reserved. * - * EMULEX and SLI are trademarks of Emulex. * - * www.emulex.com * - * * - * This program is free software; you can redistribute it and/or * - * modify it under the terms of version 2 of the GNU General * - * Public License as published by the Free Software Foundation. * - * This program is distributed in the hope that it will be useful. * - * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND * - * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY, * - * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE * - * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD * - * TO BE LEGALLY INVALID. See the GNU General Public License for * - * more details, a copy of which can be found in the file COPYING * - * included with this package. * +/* This file is part of the Emulex RoCE Device Driver for + * RoCE (RDMA over Converged Ethernet) adapters. + * Copyright (C) 2012-2015 Emulex. All rights reserved. + * EMULEX and SLI are trademarks of Emulex. + * www.emulex.com + * + * This software is available to you under a choice of one of two licenses. + * You may choose to be licensed under the terms of the GNU General Public + * License (GPL) Version 2, available from the file COPYING in the main + * directory of this source tree, or the BSD license below: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * - Redistributions of source code must retain the above copyright notice, + * this list of conditions and the following disclaimer. + * + * - Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR + * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF + * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. * * Contact Information: * linux-drivers@emulex.com @@ -23,7 +38,7 @@ * Emulex * 3333 Susan Street * Costa Mesa, CA 92626 - *******************************************************************/ + */ #include #include diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h index 02ad0aee99af..80006b24aa11 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h @@ -1,21 +1,36 @@ -/******************************************************************* - * This file is part of the Emulex RoCE Device Driver for * - * RoCE (RDMA over Converged Ethernet) adapters. * - * Copyright (C) 2008-2012 Emulex. All rights reserved. * - * EMULEX and SLI are trademarks of Emulex. * - * www.emulex.com * - * * - * This program is free software; you can redistribute it and/or * - * modify it under the terms of version 2 of the GNU General * - * Public License as published by the Free Software Foundation. * - * This program is distributed in the hope that it will be useful. * - * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND * - * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY, * - * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE * - * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD * - * TO BE LEGALLY INVALID. See the GNU General Public License for * - * more details, a copy of which can be found in the file COPYING * - * included with this package. * +/* This file is part of the Emulex RoCE Device Driver for + * RoCE (RDMA over Converged Ethernet) adapters. + * Copyright (C) 2012-2015 Emulex. All rights reserved. + * EMULEX and SLI are trademarks of Emulex. + * www.emulex.com + * + * This software is available to you under a choice of one of two licenses. + * You may choose to be licensed under the terms of the GNU General Public + * License (GPL) Version 2, available from the file COPYING in the main + * directory of this source tree, or the BSD license below: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * - Redistributions of source code must retain the above copyright notice, + * this list of conditions and the following disclaimer. + * + * - Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR + * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF + * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. * * Contact Information: * linux-drivers@emulex.com @@ -23,7 +38,7 @@ * Emulex * 3333 Susan Street * Costa Mesa, CA 92626 - *******************************************************************/ + */ #ifndef __OCRDMA_SLI_H__ #define __OCRDMA_SLI_H__ diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c index 48d7ef51aa0c..69334e214571 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c @@ -1,21 +1,36 @@ -/******************************************************************* - * This file is part of the Emulex RoCE Device Driver for * - * RoCE (RDMA over Converged Ethernet) adapters. * - * Copyright (C) 2008-2014 Emulex. All rights reserved. * - * EMULEX and SLI are trademarks of Emulex. * - * www.emulex.com * - * * - * This program is free software; you can redistribute it and/or * - * modify it under the terms of version 2 of the GNU General * - * Public License as published by the Free Software Foundation. * - * This program is distributed in the hope that it will be useful. * - * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND * - * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY, * - * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE * - * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD * - * TO BE LEGALLY INVALID. See the GNU General Public License for * - * more details, a copy of which can be found in the file COPYING * - * included with this package. * +/* This file is part of the Emulex RoCE Device Driver for + * RoCE (RDMA over Converged Ethernet) adapters. + * Copyright (C) 2012-2015 Emulex. All rights reserved. + * EMULEX and SLI are trademarks of Emulex. + * www.emulex.com + * + * This software is available to you under a choice of one of two licenses. + * You may choose to be licensed under the terms of the GNU General Public + * License (GPL) Version 2, available from the file COPYING in the main + * directory of this source tree, or the BSD license below: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * - Redistributions of source code must retain the above copyright notice, + * this list of conditions and the following disclaimer. + * + * - Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR + * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF + * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. * * Contact Information: * linux-drivers@emulex.com @@ -23,7 +38,7 @@ * Emulex * 3333 Susan Street * Costa Mesa, CA 92626 - *******************************************************************/ + */ #include #include diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_stats.h b/drivers/infiniband/hw/ocrdma/ocrdma_stats.h index 091edd68a8a3..c9e58d04c7b8 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_stats.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma_stats.h @@ -1,21 +1,36 @@ -/******************************************************************* - * This file is part of the Emulex RoCE Device Driver for * - * RoCE (RDMA over Converged Ethernet) adapters. * - * Copyright (C) 2008-2014 Emulex. All rights reserved. * - * EMULEX and SLI are trademarks of Emulex. * - * www.emulex.com * - * * - * This program is free software; you can redistribute it and/or * - * modify it under the terms of version 2 of the GNU General * - * Public License as published by the Free Software Foundation. * - * This program is distributed in the hope that it will be useful. * - * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND * - * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY, * - * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE * - * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD * - * TO BE LEGALLY INVALID. See the GNU General Public License for * - * more details, a copy of which can be found in the file COPYING * - * included with this package. * +/* This file is part of the Emulex RoCE Device Driver for + * RoCE (RDMA over Converged Ethernet) adapters. + * Copyright (C) 2012-2015 Emulex. All rights reserved. + * EMULEX and SLI are trademarks of Emulex. + * www.emulex.com + * + * This software is available to you under a choice of one of two licenses. + * You may choose to be licensed under the terms of the GNU General Public + * License (GPL) Version 2, available from the file COPYING in the main + * directory of this source tree, or the BSD license below: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * - Redistributions of source code must retain the above copyright notice, + * this list of conditions and the following disclaimer. + * + * - Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR + * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF + * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. * * Contact Information: * linux-drivers@emulex.com @@ -23,7 +38,7 @@ * Emulex * 3333 Susan Street * Costa Mesa, CA 92626 - *******************************************************************/ + */ #ifndef __OCRDMA_STATS_H__ #define __OCRDMA_STATS_H__ diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c index 5bb61eb58f2c..bc84cd462ecf 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c @@ -1,21 +1,36 @@ -/******************************************************************* - * This file is part of the Emulex RoCE Device Driver for * - * RoCE (RDMA over Converged Ethernet) adapters. * - * Copyright (C) 2008-2012 Emulex. All rights reserved. * - * EMULEX and SLI are trademarks of Emulex. * - * www.emulex.com * - * * - * This program is free software; you can redistribute it and/or * - * modify it under the terms of version 2 of the GNU General * - * Public License as published by the Free Software Foundation. * - * This program is distributed in the hope that it will be useful. * - * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND * - * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY, * - * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE * - * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD * - * TO BE LEGALLY INVALID. See the GNU General Public License for * - * more details, a copy of which can be found in the file COPYING * - * included with this package. * +/* This file is part of the Emulex RoCE Device Driver for + * RoCE (RDMA over Converged Ethernet) adapters. + * Copyright (C) 2012-2015 Emulex. All rights reserved. + * EMULEX and SLI are trademarks of Emulex. + * www.emulex.com + * + * This software is available to you under a choice of one of two licenses. + * You may choose to be licensed under the terms of the GNU General Public + * License (GPL) Version 2, available from the file COPYING in the main + * directory of this source tree, or the BSD license below: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * - Redistributions of source code must retain the above copyright notice, + * this list of conditions and the following disclaimer. + * + * - Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR + * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF + * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. * * Contact Information: * linux-drivers@emulex.com @@ -23,7 +38,7 @@ * Emulex * 3333 Susan Street * Costa Mesa, CA 92626 - *******************************************************************/ + */ #include #include diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h index b15c608efa7b..eaccb2d3cb9f 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h @@ -1,21 +1,36 @@ -/******************************************************************* - * This file is part of the Emulex RoCE Device Driver for * - * RoCE (RDMA over Converged Ethernet) adapters. * - * Copyright (C) 2008-2012 Emulex. All rights reserved. * - * EMULEX and SLI are trademarks of Emulex. * - * www.emulex.com * - * * - * This program is free software; you can redistribute it and/or * - * modify it under the terms of version 2 of the GNU General * - * Public License as published by the Free Software Foundation. * - * This program is distributed in the hope that it will be useful. * - * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND * - * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY, * - * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE * - * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD * - * TO BE LEGALLY INVALID. See the GNU General Public License for * - * more details, a copy of which can be found in the file COPYING * - * included with this package. * +/* This file is part of the Emulex RoCE Device Driver for + * RoCE (RDMA over Converged Ethernet) adapters. + * Copyright (C) 2012-2015 Emulex. All rights reserved. + * EMULEX and SLI are trademarks of Emulex. + * www.emulex.com + * + * This software is available to you under a choice of one of two licenses. + * You may choose to be licensed under the terms of the GNU General Public + * License (GPL) Version 2, available from the file COPYING in the main + * directory of this source tree, or the BSD license below: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * - Redistributions of source code must retain the above copyright notice, + * this list of conditions and the following disclaimer. + * + * - Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR + * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF + * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. * * Contact Information: * linux-drivers@emulex.com @@ -23,7 +38,7 @@ * Emulex * 3333 Susan Street * Costa Mesa, CA 92626 - *******************************************************************/ + */ #ifndef __OCRDMA_VERBS_H__ #define __OCRDMA_VERBS_H__ From b8f5595eb96c9fce1c907d13e89581e5061edf2e Mon Sep 17 00:00:00 2001 From: Devesh Sharma Date: Fri, 24 Jul 2015 05:04:00 +0530 Subject: [PATCH 094/428] RDMA/ocrdma: update ocrdma module license string Change module_license from "GPL" to "Dual BSD/GPL" Cc: Tejun Heo Cc: Duan Jiong Cc: Roland Dreier Cc: Jes Sorensen Cc: Sasha Levin Cc: Dan Carpenter Cc: Prarit Bhargava Cc: Colin Ian King Cc: Wei Yongjun Cc: Moni Shoua Cc: Rasmus Villemoes Cc: Li RongQing Cc: Devendra Naga Signed-off-by: Devesh Sharma Signed-off-by: Doug Ledford --- drivers/infiniband/hw/ocrdma/ocrdma_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c index 6ded95a66725..b119a3413a15 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c @@ -61,7 +61,7 @@ MODULE_VERSION(OCRDMA_ROCE_DRV_VERSION); MODULE_DESCRIPTION(OCRDMA_ROCE_DRV_DESC " " OCRDMA_ROCE_DRV_VERSION); MODULE_AUTHOR("Emulex Corporation"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("Dual BSD/GPL"); static LIST_HEAD(ocrdma_dev_list); static DEFINE_SPINLOCK(ocrdma_devlist_lock); From bffc4496886683fac86d31e5d0cf9a22f8044e3d Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Sun, 19 Jul 2015 12:09:16 +0800 Subject: [PATCH 095/428] ASoC: cs4265: Fix setting dai format for Left/Right Justified MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The settings in current code does not match the datasheet, fix it. DAC Control - Address 03h DAC Digital Interface Format (Bits 5:4) DAC_DIF1 DAC_DIF0 Description 0 0 Left Justified, up to 24-bit data (default) 0 1 I²S, up to 24-bit data 1 0 Right-Justified, 16-bit Data 1 1 Right-Justified, 24-bit Data Transmitter Control 2 - Address 12h Transmitter Digital Interface Format (Bits 7:6) Tx_DIF1 Tx_DIF0 Description Format Figure 0 0 Left Justified, up to 24-bit data (default) 0 1 I²S, up to 24-bit data 1 0 Right-Justified, 16-bit Data 1 1 Right-Justified, 24-bit Data Signed-off-by: Axel Lin Signed-off-by: Mark Brown --- sound/soc/codecs/cs4265.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/sound/soc/codecs/cs4265.c b/sound/soc/codecs/cs4265.c index d7ec4756e45b..8e36198474d9 100644 --- a/sound/soc/codecs/cs4265.c +++ b/sound/soc/codecs/cs4265.c @@ -457,14 +457,14 @@ static int cs4265_pcm_hw_params(struct snd_pcm_substream *substream, case SND_SOC_DAIFMT_RIGHT_J: if (params_width(params) == 16) { snd_soc_update_bits(codec, CS4265_DAC_CTL, - CS4265_DAC_CTL_DIF, (1 << 5)); + CS4265_DAC_CTL_DIF, (2 << 4)); snd_soc_update_bits(codec, CS4265_SPDIF_CTL2, - CS4265_SPDIF_CTL2_DIF, (1 << 7)); + CS4265_SPDIF_CTL2_DIF, (2 << 6)); } else { snd_soc_update_bits(codec, CS4265_DAC_CTL, - CS4265_DAC_CTL_DIF, (3 << 5)); + CS4265_DAC_CTL_DIF, (3 << 4)); snd_soc_update_bits(codec, CS4265_SPDIF_CTL2, - CS4265_SPDIF_CTL2_DIF, (1 << 7)); + CS4265_SPDIF_CTL2_DIF, (3 << 6)); } break; case SND_SOC_DAIFMT_LEFT_J: @@ -473,7 +473,7 @@ static int cs4265_pcm_hw_params(struct snd_pcm_substream *substream, snd_soc_update_bits(codec, CS4265_ADC_CTL, CS4265_ADC_DIF, 0); snd_soc_update_bits(codec, CS4265_SPDIF_CTL2, - CS4265_SPDIF_CTL2_DIF, (1 << 6)); + CS4265_SPDIF_CTL2_DIF, 0); break; default: From 4bc94d5dc95d3a2159d821b39277477e69507f67 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Fri, 24 Jul 2015 15:14:04 -0600 Subject: [PATCH 096/428] vfio: Fix lockdep issue When we open a device file descriptor, we currently have the following: vfio_group_get_device_fd() mutex_lock(&group->device_lock); open() ... if (ret) release() If we hit that error case, we call the backend driver release path, which for vfio-pci looks like this: vfio_pci_release() vfio_pci_disable() vfio_pci_try_bus_reset() vfio_pci_get_devs() vfio_device_get_from_dev() vfio_group_get_device() mutex_lock(&group->device_lock); Whoops, we've stumbled back onto group.device_lock and created a deadlock. There's a low likelihood of ever seeing this play out, but obviously it needs to be fixed. To do that we can use a reference to the vfio_device for vfio_group_get_device_fd() rather than holding the lock. There was a loop in this function, theoretically allowing multiple devices with the same name, but in practice we don't expect such a thing to happen and the code is already aborting from the loop with break on any sort of error rather than continuing and only parsing the first match anyway, so the loop was effectively unused already. Signed-off-by: Alex Williamson Fixes: 20f300175a1e ("vfio/pci: Fix racy vfio_device_get_from_dev() call") Reported-by: Joerg Roedel Tested-by: Joerg Roedel --- drivers/vfio/vfio.c | 97 ++++++++++++++++++++++++++------------------- 1 file changed, 57 insertions(+), 40 deletions(-) diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 2fb29dfeffbd..563c510f285c 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -689,6 +689,23 @@ struct vfio_device *vfio_device_get_from_dev(struct device *dev) } EXPORT_SYMBOL_GPL(vfio_device_get_from_dev); +static struct vfio_device *vfio_device_get_from_name(struct vfio_group *group, + char *buf) +{ + struct vfio_device *device; + + mutex_lock(&group->device_lock); + list_for_each_entry(device, &group->device_list, group_next) { + if (!strcmp(dev_name(device->dev), buf)) { + vfio_device_get(device); + break; + } + } + mutex_unlock(&group->device_lock); + + return device; +} + /* * Caller must hold a reference to the vfio_device */ @@ -1198,53 +1215,53 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf) { struct vfio_device *device; struct file *filep; - int ret = -ENODEV; + int ret; if (0 == atomic_read(&group->container_users) || !group->container->iommu_driver || !vfio_group_viable(group)) return -EINVAL; - mutex_lock(&group->device_lock); - list_for_each_entry(device, &group->device_list, group_next) { - if (strcmp(dev_name(device->dev), buf)) - continue; + device = vfio_device_get_from_name(group, buf); + if (!device) + return -ENODEV; - ret = device->ops->open(device->device_data); - if (ret) - break; - /* - * We can't use anon_inode_getfd() because we need to modify - * the f_mode flags directly to allow more than just ioctls - */ - ret = get_unused_fd_flags(O_CLOEXEC); - if (ret < 0) { - device->ops->release(device->device_data); - break; - } - - filep = anon_inode_getfile("[vfio-device]", &vfio_device_fops, - device, O_RDWR); - if (IS_ERR(filep)) { - put_unused_fd(ret); - ret = PTR_ERR(filep); - device->ops->release(device->device_data); - break; - } - - /* - * TODO: add an anon_inode interface to do this. - * Appears to be missing by lack of need rather than - * explicitly prevented. Now there's need. - */ - filep->f_mode |= (FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE); - - vfio_device_get(device); - atomic_inc(&group->container_users); - - fd_install(ret, filep); - break; + ret = device->ops->open(device->device_data); + if (ret) { + vfio_device_put(device); + return ret; } - mutex_unlock(&group->device_lock); + + /* + * We can't use anon_inode_getfd() because we need to modify + * the f_mode flags directly to allow more than just ioctls + */ + ret = get_unused_fd_flags(O_CLOEXEC); + if (ret < 0) { + device->ops->release(device->device_data); + vfio_device_put(device); + return ret; + } + + filep = anon_inode_getfile("[vfio-device]", &vfio_device_fops, + device, O_RDWR); + if (IS_ERR(filep)) { + put_unused_fd(ret); + ret = PTR_ERR(filep); + device->ops->release(device->device_data); + vfio_device_put(device); + return ret; + } + + /* + * TODO: add an anon_inode interface to do this. + * Appears to be missing by lack of need rather than + * explicitly prevented. Now there's need. + */ + filep->f_mode |= (FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE); + + atomic_inc(&group->container_users); + + fd_install(ret, filep); return ret; } From ba9f6f64a0ff6b7ecaed72144c179061f8eca378 Mon Sep 17 00:00:00 2001 From: Saurav Kashyap Date: Wed, 10 Jun 2015 11:05:17 -0400 Subject: [PATCH 097/428] qla2xxx: Fix hardware lock/unlock issue causing kernel panic. [ Upstream commit ef86cb2059a14b4024c7320999ee58e938873032 ] This patch fixes a kernel panic for qla2xxx Target core Module driver introduced by a fix in the qla2xxx initiator code. Commit ef86cb2 ("qla2xxx: Mark port lost when we receive an RSCN for it.") introduced the regression for qla2xxx Target driver. Stack trace will have following signature --- --- [ffff88081faa3cc8] _raw_spin_lock_irqsave at ffffffff815b1f03 [ffff88081faa3cd0] qlt_fc_port_deleted at ffffffffa096ccd0 [qla2xxx] [ffff88081faa3d20] qla2x00_schedule_rport_del at ffffffffa0913831[qla2xxx] [ffff88081faa3d50] qla2x00_mark_device_lost at ffffffffa09159c5[qla2xxx] [ffff88081faa3db0] qla2x00_async_event at ffffffffa0938d59 [qla2xxx] [ffff88081faa3e30] qla24xx_msix_default at ffffffffa093a326 [qla2xxx] [ffff88081faa3e90] handle_irq_event_percpu at ffffffff810a7b8d [ffff88081faa3ee0] handle_irq_event at ffffffff810a7d32 [ffff88081faa3f10] handle_edge_irq at ffffffff810ab6b9 [ffff88081faa3f30] handle_irq at ffffffff8100619c [ffff88081faa3f70] do_IRQ at ffffffff815b4b1c --- --- Cc: # v3.18+ Signed-off-by: Saurav Kashyap Signed-off-by: Himanshu Madhani Reviewed-by: Nicholas Bellinger Signed-off-by: Nicholas Bellinger --- drivers/scsi/qla2xxx/qla_init.c | 4 ++++ drivers/scsi/qla2xxx/qla_target.c | 6 ------ 2 files changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 664013115c9d..6c302c4fcb15 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -2924,6 +2924,7 @@ qla2x00_rport_del(void *data) struct fc_rport *rport; scsi_qla_host_t *vha = fcport->vha; unsigned long flags; + unsigned long vha_flags; spin_lock_irqsave(fcport->vha->host->host_lock, flags); rport = fcport->drport ? fcport->drport: fcport->rport; @@ -2935,7 +2936,9 @@ qla2x00_rport_del(void *data) * Release the target mode FC NEXUS in qla_target.c code * if target mod is enabled. */ + spin_lock_irqsave(&vha->hw->hardware_lock, vha_flags); qlt_fc_port_deleted(vha, fcport); + spin_unlock_irqrestore(&vha->hw->hardware_lock, vha_flags); } } @@ -3303,6 +3306,7 @@ qla2x00_reg_remote_port(scsi_qla_host_t *vha, fc_port_t *fcport) * Create target mode FC NEXUS in qla_target.c if target mode is * enabled.. */ + qlt_fc_port_added(vha, fcport); spin_lock_irqsave(fcport->vha->host->host_lock, flags); diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index b749026aa592..bce2bea03859 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -782,10 +782,8 @@ void qlt_fc_port_added(struct scsi_qla_host *vha, fc_port_t *fcport) void qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport) { - struct qla_hw_data *ha = vha->hw; struct qla_tgt *tgt = vha->vha_tgt.qla_tgt; struct qla_tgt_sess *sess; - unsigned long flags; if (!vha->hw->tgt.tgt_ops) return; @@ -793,14 +791,11 @@ void qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport) if (!tgt || (fcport->port_type != FCT_INITIATOR)) return; - spin_lock_irqsave(&ha->hardware_lock, flags); if (tgt->tgt_stop) { - spin_unlock_irqrestore(&ha->hardware_lock, flags); return; } sess = qlt_find_sess_by_port_name(tgt, fcport->port_name); if (!sess) { - spin_unlock_irqrestore(&ha->hardware_lock, flags); return; } @@ -808,7 +803,6 @@ void qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport) sess->local = 1; qlt_schedule_sess_for_deletion(sess, false); - spin_unlock_irqrestore(&ha->hardware_lock, flags); } static inline int test_tgt_sess_count(struct qla_tgt *tgt) From b20f02e1418d8a5617b81464c612de09aa55e552 Mon Sep 17 00:00:00 2001 From: Himanshu Madhani Date: Wed, 10 Jun 2015 11:05:18 -0400 Subject: [PATCH 098/428] qla2xxx: Enable target mode for ISP27XX Signed-off-by: Himanshu Madhani Signed-off-by: Giridhar Malavali Reviewed-by: Nicholas Bellinger Signed-off-by: Nicholas Bellinger --- drivers/scsi/qla2xxx/qla_attr.c | 2 +- drivers/scsi/qla2xxx/qla_def.h | 8 ++++---- drivers/scsi/qla2xxx/qla_init.c | 4 ++-- drivers/scsi/qla2xxx/qla_mbx.c | 7 ++++--- drivers/scsi/qla2xxx/qla_os.c | 1 + drivers/scsi/qla2xxx/qla_sup.c | 2 +- drivers/scsi/qla2xxx/qla_target.c | 2 +- 7 files changed, 14 insertions(+), 12 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index 82b92c414a9c..437254e1c4de 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -738,7 +738,7 @@ qla2x00_sysfs_write_reset(struct file *filp, struct kobject *kobj, ql_log(ql_log_info, vha, 0x706f, "Issuing MPI reset.\n"); - if (IS_QLA83XX(ha)) { + if (IS_QLA83XX(ha) || IS_QLA27XX(ha)) { uint32_t idc_control; qla83xx_idc_lock(vha, 0); diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index e86201d3b8c6..787f90107d16 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -3154,13 +3154,13 @@ struct qla_hw_data { /* Bit 21 of fw_attributes decides the MCTP capabilities */ #define IS_MCTP_CAPABLE(ha) (IS_QLA2031(ha) && \ ((ha)->fw_attributes_ext[0] & BIT_0)) -#define IS_PI_UNINIT_CAPABLE(ha) (IS_QLA83XX(ha)) -#define IS_PI_IPGUARD_CAPABLE(ha) (IS_QLA83XX(ha)) +#define IS_PI_UNINIT_CAPABLE(ha) (IS_QLA83XX(ha) || IS_QLA27XX(ha)) +#define IS_PI_IPGUARD_CAPABLE(ha) (IS_QLA83XX(ha) || IS_QLA27XX(ha)) #define IS_PI_DIFB_DIX0_CAPABLE(ha) (0) -#define IS_PI_SPLIT_DET_CAPABLE_HBA(ha) (IS_QLA83XX(ha)) +#define IS_PI_SPLIT_DET_CAPABLE_HBA(ha) (IS_QLA83XX(ha) || IS_QLA27XX(ha)) #define IS_PI_SPLIT_DET_CAPABLE(ha) (IS_PI_SPLIT_DET_CAPABLE_HBA(ha) && \ (((ha)->fw_attributes_h << 16 | (ha)->fw_attributes) & BIT_22)) -#define IS_ATIO_MSIX_CAPABLE(ha) (IS_QLA83XX(ha)) +#define IS_ATIO_MSIX_CAPABLE(ha) (IS_QLA83XX(ha) || IS_QLA27XX(ha)) #define IS_TGT_MODE_CAPABLE(ha) (ha->tgt.atio_q_length) #define IS_SHADOW_REG_CAPABLE(ha) (IS_QLA27XX(ha)) #define IS_DPORT_CAPABLE(ha) (IS_QLA83XX(ha) || IS_QLA27XX(ha)) diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 6c302c4fcb15..17c3bd919cf6 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -1538,7 +1538,7 @@ qla2x00_alloc_fw_dump(scsi_qla_host_t *vha) mem_size = (ha->fw_memory_size - 0x11000 + 1) * sizeof(uint16_t); } else if (IS_FWI2_CAPABLE(ha)) { - if (IS_QLA83XX(ha)) + if (IS_QLA83XX(ha) || IS_QLA27XX(ha)) fixed_size = offsetof(struct qla83xx_fw_dump, ext_mem); else if (IS_QLA81XX(ha)) fixed_size = offsetof(struct qla81xx_fw_dump, ext_mem); @@ -1550,7 +1550,7 @@ qla2x00_alloc_fw_dump(scsi_qla_host_t *vha) mem_size = (ha->fw_memory_size - 0x100000 + 1) * sizeof(uint32_t); if (ha->mqenable) { - if (!IS_QLA83XX(ha)) + if (!IS_QLA83XX(ha) && !IS_QLA27XX(ha)) mq_size = sizeof(struct qla2xxx_mq_chain); /* * Allocate maximum buffer size for all queues. diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 02b1c1c5355b..b2f713ad9034 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -2415,7 +2415,8 @@ qla2x00_get_resource_cnts(scsi_qla_host_t *vha, uint16_t *cur_xchg_cnt, *orig_iocb_cnt = mcp->mb[10]; if (vha->hw->flags.npiv_supported && max_npiv_vports) *max_npiv_vports = mcp->mb[11]; - if ((IS_QLA81XX(vha->hw) || IS_QLA83XX(vha->hw)) && max_fcfs) + if ((IS_QLA81XX(vha->hw) || IS_QLA83XX(vha->hw) || + IS_QLA27XX(vha->hw)) && max_fcfs) *max_fcfs = mcp->mb[12]; } @@ -3898,7 +3899,7 @@ qla25xx_init_rsp_que(struct scsi_qla_host *vha, struct rsp_que *rsp) spin_lock_irqsave(&ha->hardware_lock, flags); if (!(rsp->options & BIT_0)) { WRT_REG_DWORD(rsp->rsp_q_out, 0); - if (!IS_QLA83XX(ha)) + if (!IS_QLA83XX(ha) && !IS_QLA27XX(ha)) WRT_REG_DWORD(rsp->rsp_q_in, 0); } @@ -5345,7 +5346,7 @@ qla83xx_restart_nic_firmware(scsi_qla_host_t *vha) mbx_cmd_t *mcp = &mc; struct qla_hw_data *ha = vha->hw; - if (!IS_QLA83XX(ha)) + if (!IS_QLA83XX(ha) && !IS_QLA27XX(ha)) return QLA_FUNCTION_FAILED; ql_dbg(ql_dbg_mbx, vha, 0x1143, "Entered %s.\n", __func__); diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index a28815b8276f..7c7528b41230 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -2504,6 +2504,7 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) ha->mbx_count = MAILBOX_REGISTER_COUNT; req_length = REQUEST_ENTRY_CNT_24XX; rsp_length = RESPONSE_ENTRY_CNT_2300; + ha->tgt.atio_q_length = ATIO_ENTRY_CNT_24XX; ha->max_loop_id = SNS_LAST_LOOP_ID_2300; ha->init_cb_size = sizeof(struct mid_init_cb_81xx); ha->gid_list_info_size = 8; diff --git a/drivers/scsi/qla2xxx/qla_sup.c b/drivers/scsi/qla2xxx/qla_sup.c index 028e8c8a7de9..2feb5f38edcd 100644 --- a/drivers/scsi/qla2xxx/qla_sup.c +++ b/drivers/scsi/qla2xxx/qla_sup.c @@ -1697,7 +1697,7 @@ qla83xx_select_led_port(struct qla_hw_data *ha) { uint32_t led_select_value = 0; - if (!IS_QLA83XX(ha)) + if (!IS_QLA83XX(ha) && !IS_QLA27XX(ha)) goto out; if (ha->port_no == 0) diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index bce2bea03859..9c14d107d29a 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -5787,7 +5787,7 @@ qlt_probe_one_stage1(struct scsi_qla_host *base_vha, struct qla_hw_data *ha) if (!QLA_TGT_MODE_ENABLED()) return; - if (ha->mqenable || IS_QLA83XX(ha)) { + if (ha->mqenable || IS_QLA83XX(ha) || IS_QLA27XX(ha)) { ISP_ATIO_Q_IN(base_vha) = &ha->mqiobase->isp25mq.atio_q_in; ISP_ATIO_Q_OUT(base_vha) = &ha->mqiobase->isp25mq.atio_q_out; } else { From 3761f3e8704878b1d3db9751f5c6db6fc918032f Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Wed, 10 Jun 2015 11:05:19 -0400 Subject: [PATCH 099/428] qla2xxx: Add flush after updating ATIOQ consumer index. After updating the consumer index of ATIO Q, a read is required to flush the write to the adapter register. Signed-off-by: Quinn Tran Signed-off-by: Himanshu Madhani Reviewed-by: Nicholas Bellinger Signed-off-by: Nicholas Bellinger --- drivers/scsi/qla2xxx/qla_target.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 9c14d107d29a..5047c8566644 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -5546,6 +5546,7 @@ qlt_24xx_process_atio_queue(struct scsi_qla_host *vha) /* Adjust ring index */ WRT_REG_DWORD(ISP_ATIO_Q_OUT(vha), ha->tgt.atio_ring_index); + RD_REG_DWORD_RELAXED(ISP_ATIO_Q_OUT(vha)); } void From 810e30bc4658e9c069577bde52394a5af872803c Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Wed, 10 Jun 2015 11:05:20 -0400 Subject: [PATCH 100/428] qla2xxx: release request queue reservation. Request IOCB queue element(s) is reserved during good path IO. Under error condition such as unable to allocate IOCB handle condition, the IOCB count that was reserved is not released. Cc: # v3.18+ Signed-off-by: Quinn Tran Signed-off-by: Himanshu Madhani Reviewed-by: Nicholas Bellinger Signed-off-by: Nicholas Bellinger --- drivers/scsi/qla2xxx/qla_target.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 5047c8566644..49a184d30f1f 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -2339,9 +2339,10 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type, res = qlt_build_ctio_crc2_pkt(&prm, vha); else res = qlt_24xx_build_ctio_pkt(&prm, vha); - if (unlikely(res != 0)) + if (unlikely(res != 0)) { + vha->req->cnt += full_req_cnt; goto out_unmap_unlock; - + } pkt = (struct ctio7_to_24xx *)prm.pkt; @@ -2479,8 +2480,11 @@ int qlt_rdy_to_xfer(struct qla_tgt_cmd *cmd) else res = qlt_24xx_build_ctio_pkt(&prm, vha); - if (unlikely(res != 0)) + if (unlikely(res != 0)) { + vha->req->cnt += prm.req_cnt; goto out_unlock_free_unmap; + } + pkt = (struct ctio7_to_24xx *)prm.pkt; pkt->u.status0.flags |= __constant_cpu_to_le16(CTIO7_FLAGS_DATA_OUT | CTIO7_FLAGS_STATUS_MODE_0); From e5fdee875f7918b37f7c3fce3025197d8f214a27 Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Wed, 10 Jun 2015 11:05:21 -0400 Subject: [PATCH 101/428] qla2xxx: adjust debug flags Adjust debug flag to match debug comment. Signed-off-by: Quinn Tran Signed-off-by: Himanshu Madhani Reviewed-by: Nicholas Bellinger Signed-off-by: Nicholas Bellinger --- drivers/scsi/qla2xxx/qla_target.c | 7 ++++--- drivers/scsi/qla2xxx/qla_target.h | 3 +++ drivers/scsi/qla2xxx/tcm_qla2xxx.c | 3 +-- 3 files changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 49a184d30f1f..cda443462071 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -3013,7 +3013,7 @@ qlt_abort_cmd_on_host_reset(struct scsi_qla_host *vha, struct qla_tgt_cmd *cmd) dump_stack(); } - cmd->cmd_flags |= BIT_12; + cmd->cmd_flags |= BIT_17; ha->tgt.tgt_ops->free_cmd(cmd); } @@ -3175,7 +3175,7 @@ static void qlt_do_ctio_completion(struct scsi_qla_host *vha, uint32_t handle, skip_term: if (cmd->state == QLA_TGT_STATE_PROCESSED) { - ; + cmd->cmd_flags |= BIT_12; } else if (cmd->state == QLA_TGT_STATE_NEED_DATA) { int rx_status = 0; @@ -3189,9 +3189,11 @@ skip_term: ha->tgt.tgt_ops->handle_data(cmd); return; } else if (cmd->state == QLA_TGT_STATE_ABORTED) { + cmd->cmd_flags |= BIT_18; ql_dbg(ql_dbg_tgt_mgt, vha, 0xf01e, "Aborted command %p (tag %lld) finished\n", cmd, se_cmd->tag); } else { + cmd->cmd_flags |= BIT_19; ql_dbg(ql_dbg_tgt_mgt, vha, 0xf05c, "qla_target(%d): A command in state (%d) should " "not return a CTIO complete\n", vha->vp_idx, cmd->state); @@ -3203,7 +3205,6 @@ skip_term: dump_stack(); } - ha->tgt.tgt_ops->free_cmd(cmd); } diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h index 985d76dd706b..dfeeadf92fbb 100644 --- a/drivers/scsi/qla2xxx/qla_target.h +++ b/drivers/scsi/qla2xxx/qla_target.h @@ -961,6 +961,9 @@ struct qla_tgt_cmd { * BIT_14 - Back end data received/sent. * BIT_15 - SRR prepare ctio * BIT_16 - complete free + * BIT_17 - flush - qlt_abort_cmd_on_host_reset + * BIT_18 - completion w/abort status + * BIT_19 - completion w/unknown status */ uint32_t cmd_flags; }; diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index 33364b663cc9..32ff9d15e12d 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -374,7 +374,7 @@ static int tcm_qla2xxx_write_pending(struct se_cmd *se_cmd) { struct qla_tgt_cmd *cmd = container_of(se_cmd, struct qla_tgt_cmd, se_cmd); - + cmd->cmd_flags |= BIT_3; cmd->bufflen = se_cmd->data_length; cmd->dma_data_direction = target_reverse_dma_direction(se_cmd); @@ -546,7 +546,6 @@ static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd) cmd->sg_cnt = se_cmd->t_data_nents; cmd->sg = se_cmd->t_data_sg; cmd->offset = 0; - cmd->cmd_flags |= BIT_3; cmd->prot_sg_cnt = se_cmd->t_prot_nents; cmd->prot_sg = se_cmd->t_prot_sg; From 6bc85dd595a5438b50ec085668e53ef26058bb90 Mon Sep 17 00:00:00 2001 From: Himanshu Madhani Date: Wed, 10 Jun 2015 11:05:22 -0400 Subject: [PATCH 102/428] qla2xxx: Remove msleep in qlt_send_term_exchange Remove unnecessary msleep from qlt_send_term_exchange as it adds latency of 250 msec while sending terminate exchange to an aborted task. Cc: # v3.18+ Signed-off-by: Himanshu Madhani Signed-off-by: Giridhar Malavali Reviewed-by: Nicholas Bellinger Signed-off-by: Nicholas Bellinger --- drivers/scsi/qla2xxx/qla_target.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index cda443462071..2491bc9dd2a5 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -2713,7 +2713,7 @@ static int __qlt_send_term_exchange(struct scsi_qla_host *vha, static void qlt_send_term_exchange(struct scsi_qla_host *vha, struct qla_tgt_cmd *cmd, struct atio_from_isp *atio, int ha_locked) { - unsigned long flags; + unsigned long flags = 0; int rc; if (qlt_issue_marker(vha, ha_locked) < 0) @@ -2729,17 +2729,18 @@ static void qlt_send_term_exchange(struct scsi_qla_host *vha, rc = __qlt_send_term_exchange(vha, cmd, atio); if (rc == -ENOMEM) qlt_alloc_qfull_cmd(vha, atio, 0, 0); - spin_unlock_irqrestore(&vha->hw->hardware_lock, flags); done: if (cmd && ((cmd->state != QLA_TGT_STATE_ABORTED) || !cmd->cmd_sent_to_fw)) { - if (!ha_locked && !in_interrupt()) - msleep(250); /* just in case */ - - qlt_unmap_sg(vha, cmd); + if (cmd->sg_mapped) + qlt_unmap_sg(vha, cmd); vha->hw->tgt.tgt_ops->free_cmd(cmd); } + + if (!ha_locked) + spin_unlock_irqrestore(&vha->hw->hardware_lock, flags); + return; } From 9fce12540cb9f91e7f1f539a80b70f0b388bdae0 Mon Sep 17 00:00:00 2001 From: Kanoj Sarcar Date: Wed, 10 Jun 2015 11:05:23 -0400 Subject: [PATCH 103/428] qla2xxx: fix command initialization in target mode. Cc: # v3.18+ Signed-off-by: Kanoj Sarcar Signed-off-by: Himanshu Madhani Reviewed-by: Nicholas Bellinger Signed-off-by: Nicholas Bellinger --- drivers/scsi/qla2xxx/qla_target.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 2491bc9dd2a5..17d656b3af6a 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -3345,6 +3345,11 @@ static struct qla_tgt_cmd *qlt_get_tag(scsi_qla_host_t *vha, cmd->loop_id = sess->loop_id; cmd->conf_compl_supported = sess->conf_compl_supported; + cmd->cmd_flags = 0; + cmd->jiffies_at_alloc = get_jiffies_64(); + + cmd->reset_count = vha->hw->chip_reset; + return cmd; } @@ -3451,11 +3456,6 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha, return -ENOMEM; } - cmd->cmd_flags = 0; - cmd->jiffies_at_alloc = get_jiffies_64(); - - cmd->reset_count = vha->hw->chip_reset; - cmd->cmd_in_wq = 1; cmd->cmd_flags |= BIT_0; INIT_WORK(&cmd->work, qlt_do_work); From b2032fd567326ad0b2d443bb6d96d2580ec670a5 Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Tue, 14 Jul 2015 16:00:42 -0400 Subject: [PATCH 104/428] qla2xxx: kill sessions/log out initiator on RSCN and port down events To fix some issues talking to ESX, this patch modifies the qla2xxx driver so that it never logs into remote ports. This has the side effect of getting rid of the "rports" entirely, which means we never log out of initiators and never tear down sessions when an initiator goes away. This is mostly OK, except that we can run into trouble if we have initiator A assigned FC address X:Y:Z by the fabric talking to us, and then initiator A goes away. Some time (could be a long time) later, initiator B comes along and also gets FC address X:Y:Z (which is available again, because initiator A is gone). If initiator B starts talking to us, then we'll still have the session for initiator A, and since we look up incoming IO based on the FC address X:Y:Z, initiator B will end up using ACLs for initiator A. Fix this by: 1. Handling RSCN events somewhat differently; instead of completely skipping the processing of fcports, we look through the list, and if an fcport disappears, we tell the target code the tear down the session and tell the HBA FW to release the N_Port handle. 2. Handling "port down" events by flushing all of our sessions. The firmware was already releasing the N_Port handle but we want the target code to drop all the sessions too. Cc: # v3.18+ Signed-off-by: Roland Dreier Signed-off-by: Alexei Potashnik Acked-by: Quinn Tran Signed-off-by: Himanshu Madhani Signed-off-by: Nicholas Bellinger --- drivers/scsi/qla2xxx/qla_dbg.c | 2 +- drivers/scsi/qla2xxx/qla_init.c | 137 ++++++++++++++++++++++++------ drivers/scsi/qla2xxx/qla_target.c | 9 +- 3 files changed, 117 insertions(+), 31 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c index 0e6ee3ca30e6..e9ae6b924c70 100644 --- a/drivers/scsi/qla2xxx/qla_dbg.c +++ b/drivers/scsi/qla2xxx/qla_dbg.c @@ -68,7 +68,7 @@ * | | | 0xd101-0xd1fe | * | | | 0xd214-0xd2fe | * | Target Mode | 0xe079 | | - * | Target Mode Management | 0xf072 | 0xf002 | + * | Target Mode Management | 0xf080 | 0xf002 | * | | | 0xf046-0xf049 | * | Target Mode Task Management | 0x1000b | | * ---------------------------------------------------------------------- diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 17c3bd919cf6..e166c468a8b2 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -3464,20 +3464,43 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha) if ((fcport->flags & FCF_FABRIC_DEVICE) == 0) continue; - if (fcport->scan_state == QLA_FCPORT_SCAN && - atomic_read(&fcport->state) == FCS_ONLINE) { - qla2x00_mark_device_lost(vha, fcport, - ql2xplogiabsentdevice, 0); - if (fcport->loop_id != FC_NO_LOOP_ID && - (fcport->flags & FCF_FCP2_DEVICE) == 0 && - fcport->port_type != FCT_INITIATOR && - fcport->port_type != FCT_BROADCAST) { - ha->isp_ops->fabric_logout(vha, - fcport->loop_id, - fcport->d_id.b.domain, - fcport->d_id.b.area, - fcport->d_id.b.al_pa); - qla2x00_clear_loop_id(fcport); + if (fcport->scan_state == QLA_FCPORT_SCAN) { + if (qla_ini_mode_enabled(base_vha) && + atomic_read(&fcport->state) == FCS_ONLINE) { + qla2x00_mark_device_lost(vha, fcport, + ql2xplogiabsentdevice, 0); + if (fcport->loop_id != FC_NO_LOOP_ID && + (fcport->flags & FCF_FCP2_DEVICE) == 0 && + fcport->port_type != FCT_INITIATOR && + fcport->port_type != FCT_BROADCAST) { + ha->isp_ops->fabric_logout(vha, + fcport->loop_id, + fcport->d_id.b.domain, + fcport->d_id.b.area, + fcport->d_id.b.al_pa); + qla2x00_clear_loop_id(fcport); + } + } else if (!qla_ini_mode_enabled(base_vha)) { + /* + * In target mode, explicitly kill + * sessions and log out of devices + * that are gone, so that we don't + * end up with an initiator using the + * wrong ACL (if the fabric recycles + * an FC address and we have a stale + * session around) and so that we don't + * report initiators that are no longer + * on the fabric. + */ + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf077, + "port gone, logging out/killing session: " + "%8phC state 0x%x flags 0x%x fc4_type 0x%x " + "scan_state %d\n", + fcport->port_name, + atomic_read(&fcport->state), + fcport->flags, fcport->fc4_type, + fcport->scan_state); + qlt_fc_port_deleted(vha, fcport); } } } @@ -3498,6 +3521,28 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha) (fcport->flags & FCF_LOGIN_NEEDED) == 0) continue; + /* + * If we're not an initiator, skip looking for devices + * and logging in. There's no reason for us to do it, + * and it seems to actively cause problems in target + * mode if we race with the initiator logging into us + * (we might get the "port ID used" status back from + * our login command and log out the initiator, which + * seems to cause havoc). + */ + if (!qla_ini_mode_enabled(base_vha)) { + if (fcport->scan_state == QLA_FCPORT_FOUND) { + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf078, + "port %8phC state 0x%x flags 0x%x fc4_type 0x%x " + "scan_state %d (initiator mode disabled; skipping " + "login)\n", fcport->port_name, + atomic_read(&fcport->state), + fcport->flags, fcport->fc4_type, + fcport->scan_state); + } + continue; + } + if (fcport->loop_id == FC_NO_LOOP_ID) { fcport->loop_id = next_loopid; rval = qla2x00_find_new_loop_id( @@ -3524,16 +3569,38 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha) test_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags)) break; - /* Find a new loop ID to use. */ - fcport->loop_id = next_loopid; - rval = qla2x00_find_new_loop_id(base_vha, fcport); - if (rval != QLA_SUCCESS) { - /* Ran out of IDs to use */ - break; - } + /* + * If we're not an initiator, skip looking for devices + * and logging in. There's no reason for us to do it, + * and it seems to actively cause problems in target + * mode if we race with the initiator logging into us + * (we might get the "port ID used" status back from + * our login command and log out the initiator, which + * seems to cause havoc). + */ + if (qla_ini_mode_enabled(base_vha)) { + /* Find a new loop ID to use. */ + fcport->loop_id = next_loopid; + rval = qla2x00_find_new_loop_id(base_vha, + fcport); + if (rval != QLA_SUCCESS) { + /* Ran out of IDs to use */ + break; + } - /* Login and update database */ - qla2x00_fabric_dev_login(vha, fcport, &next_loopid); + /* Login and update database */ + qla2x00_fabric_dev_login(vha, fcport, + &next_loopid); + } else { + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf079, + "new port %8phC state 0x%x flags 0x%x fc4_type " + "0x%x scan_state %d (initiator mode disabled; " + "skipping login)\n", + fcport->port_name, + atomic_read(&fcport->state), + fcport->flags, fcport->fc4_type, + fcport->scan_state); + } list_move_tail(&fcport->list, &vha->vp_fcports); } @@ -3729,11 +3796,12 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha, fcport->fp_speed = new_fcport->fp_speed; /* - * If address the same and state FCS_ONLINE, nothing - * changed. + * If address the same and state FCS_ONLINE + * (or in target mode), nothing changed. */ if (fcport->d_id.b24 == new_fcport->d_id.b24 && - atomic_read(&fcport->state) == FCS_ONLINE) { + (atomic_read(&fcport->state) == FCS_ONLINE || + !qla_ini_mode_enabled(base_vha))) { break; } @@ -3753,6 +3821,22 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha, * Log it out if still logged in and mark it for * relogin later. */ + if (!qla_ini_mode_enabled(base_vha)) { + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf080, + "port changed FC ID, %8phC" + " old %x:%x:%x (loop_id 0x%04x)-> new %x:%x:%x\n", + fcport->port_name, + fcport->d_id.b.domain, + fcport->d_id.b.area, + fcport->d_id.b.al_pa, + fcport->loop_id, + new_fcport->d_id.b.domain, + new_fcport->d_id.b.area, + new_fcport->d_id.b.al_pa); + fcport->d_id.b24 = new_fcport->d_id.b24; + break; + } + fcport->d_id.b24 = new_fcport->d_id.b24; fcport->flags |= FCF_LOGIN_NEEDED; if (fcport->loop_id != FC_NO_LOOP_ID && @@ -3772,6 +3856,7 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha, if (found) continue; /* If device was not in our fcports list, then add it. */ + new_fcport->scan_state = QLA_FCPORT_FOUND; list_add_tail(&new_fcport->list, new_fcports); /* Allocate a new replacement fcport. */ diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 17d656b3af6a..d9dd354fcd28 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -113,6 +113,7 @@ static void qlt_abort_cmd_on_host_reset(struct scsi_qla_host *vha, static void qlt_alloc_qfull_cmd(struct scsi_qla_host *vha, struct atio_from_isp *atio, uint16_t status, int qfull); static void qlt_disable_vha(struct scsi_qla_host *vha); +static void qlt_clear_tgt_db(struct qla_tgt *tgt); /* * Global Variables */ @@ -431,10 +432,10 @@ static int qlt_reset(struct scsi_qla_host *vha, void *iocb, int mcmd) loop_id = le16_to_cpu(n->u.isp24.nport_handle); if (loop_id == 0xFFFF) { -#if 0 /* FIXME: Re-enable Global event handling.. */ /* Global event */ - atomic_inc(&ha->tgt.qla_tgt->tgt_global_resets_count); - qlt_clear_tgt_db(ha->tgt.qla_tgt); + atomic_inc(&vha->vha_tgt.qla_tgt->tgt_global_resets_count); + qlt_clear_tgt_db(vha->vha_tgt.qla_tgt); +#if 0 /* FIXME: do we need to choose a session here? */ if (!list_empty(&ha->tgt.qla_tgt->sess_list)) { sess = list_entry(ha->tgt.qla_tgt->sess_list.next, typeof(*sess), sess_list_entry); @@ -788,7 +789,7 @@ void qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport) if (!vha->hw->tgt.tgt_ops) return; - if (!tgt || (fcport->port_type != FCT_INITIATOR)) + if (!tgt) return; if (tgt->tgt_stop) { From 8b2f5ff3d05c2c48b722c3cc67b8226f1601042b Mon Sep 17 00:00:00 2001 From: Swapnil Nagle Date: Tue, 14 Jul 2015 16:00:43 -0400 Subject: [PATCH 105/428] qla2xxx: cleanup cmd in qla workqueue before processing TMR Since cmds go into qla_tgt_wq and TMRs don't, it's possible that TMR like TASK_ABORT can be queued over the cmd for which it was meant. To avoid this race, use a per-port list to keep track of cmds that are enqueued to qla_tgt_wq but not yet processed. When a TMR arrives, iterate through this list and remove any cmds that match the TMR. This patch supports TASK_ABORT and LUN_RESET. Cc: # v3.18+ Signed-off-by: Swapnil Nagle Signed-off-by: Alexei Potashnik Acked-by: Quinn Tran Signed-off-by: Himanshu Madhani Signed-off-by: Nicholas Bellinger --- drivers/scsi/qla2xxx/qla_dbg.c | 2 +- drivers/scsi/qla2xxx/qla_def.h | 5 ++ drivers/scsi/qla2xxx/qla_os.c | 3 + drivers/scsi/qla2xxx/qla_target.c | 123 +++++++++++++++++++++++++++-- drivers/scsi/qla2xxx/qla_target.h | 12 +++ drivers/scsi/qla2xxx/tcm_qla2xxx.c | 8 +- 6 files changed, 140 insertions(+), 13 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c index e9ae6b924c70..e63aa0780b52 100644 --- a/drivers/scsi/qla2xxx/qla_dbg.c +++ b/drivers/scsi/qla2xxx/qla_dbg.c @@ -68,7 +68,7 @@ * | | | 0xd101-0xd1fe | * | | | 0xd214-0xd2fe | * | Target Mode | 0xe079 | | - * | Target Mode Management | 0xf080 | 0xf002 | + * | Target Mode Management | 0xf083 | 0xf002 | * | | | 0xf046-0xf049 | * | Target Mode Task Management | 0x1000b | | * ---------------------------------------------------------------------- diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 787f90107d16..d9c4ed21b52f 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -3579,6 +3579,11 @@ typedef struct scsi_qla_host { uint16_t fcoe_fcf_idx; uint8_t fcoe_vn_port_mac[6]; + /* list of commands waiting on workqueue */ + struct list_head qla_cmd_list; + struct list_head qla_sess_op_cmd_list; + spinlock_t cmd_list_lock; + uint32_t vp_abort_cnt; struct fc_vport *fc_vport; /* holds fc_vport * for each vport */ diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 7c7528b41230..7ce395aaf033 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -3764,8 +3764,11 @@ struct scsi_qla_host *qla2x00_create_host(struct scsi_host_template *sht, INIT_LIST_HEAD(&vha->vp_fcports); INIT_LIST_HEAD(&vha->work_list); INIT_LIST_HEAD(&vha->list); + INIT_LIST_HEAD(&vha->qla_cmd_list); + INIT_LIST_HEAD(&vha->qla_sess_op_cmd_list); spin_lock_init(&vha->work_lock); + spin_lock_init(&vha->cmd_list_lock); sprintf(vha->host_str, "%s_%ld", QLA2XXX_DRIVER_NAME, vha->host_no); ql_dbg(ql_dbg_init, vha, 0x0041, diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index d9dd354fcd28..eca444827eae 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1170,6 +1170,70 @@ static void qlt_24xx_retry_term_exchange(struct scsi_qla_host *vha, FCP_TMF_CMPL, true); } +static int abort_cmd_for_tag(struct scsi_qla_host *vha, uint32_t tag) +{ + struct qla_tgt_sess_op *op; + struct qla_tgt_cmd *cmd; + + spin_lock(&vha->cmd_list_lock); + + list_for_each_entry(op, &vha->qla_sess_op_cmd_list, cmd_list) { + if (tag == op->atio.u.isp24.exchange_addr) { + op->aborted = true; + spin_unlock(&vha->cmd_list_lock); + return 1; + } + } + + list_for_each_entry(cmd, &vha->qla_cmd_list, cmd_list) { + if (tag == cmd->atio.u.isp24.exchange_addr) { + cmd->state = QLA_TGT_STATE_ABORTED; + spin_unlock(&vha->cmd_list_lock); + return 1; + } + } + + spin_unlock(&vha->cmd_list_lock); + return 0; +} + +/* drop cmds for the given lun + * XXX only looks for cmds on the port through which lun reset was recieved + * XXX does not go through the list of other port (which may have cmds + * for the same lun) + */ +static void abort_cmds_for_lun(struct scsi_qla_host *vha, + uint32_t lun, uint8_t *s_id) +{ + struct qla_tgt_sess_op *op; + struct qla_tgt_cmd *cmd; + uint32_t key; + + key = sid_to_key(s_id); + spin_lock(&vha->cmd_list_lock); + list_for_each_entry(op, &vha->qla_sess_op_cmd_list, cmd_list) { + uint32_t op_key; + uint32_t op_lun; + + op_key = sid_to_key(op->atio.u.isp24.fcp_hdr.s_id); + op_lun = scsilun_to_int( + (struct scsi_lun *)&op->atio.u.isp24.fcp_cmnd.lun); + if (op_key == key && op_lun == lun) + op->aborted = true; + } + list_for_each_entry(cmd, &vha->qla_cmd_list, cmd_list) { + uint32_t cmd_key; + uint32_t cmd_lun; + + cmd_key = sid_to_key(cmd->atio.u.isp24.fcp_hdr.s_id); + cmd_lun = scsilun_to_int( + (struct scsi_lun *)&cmd->atio.u.isp24.fcp_cmnd.lun); + if (cmd_key == key && cmd_lun == lun) + cmd->state = QLA_TGT_STATE_ABORTED; + } + spin_unlock(&vha->cmd_list_lock); +} + /* ha->hardware_lock supposed to be held on entry */ static int __qlt_24xx_handle_abts(struct scsi_qla_host *vha, struct abts_recv_from_24xx *abts, struct qla_tgt_sess *sess) @@ -1194,8 +1258,19 @@ static int __qlt_24xx_handle_abts(struct scsi_qla_host *vha, } spin_unlock(&se_sess->sess_cmd_lock); - if (!found_lun) - return -ENOENT; + /* cmd not in LIO lists, look in qla list */ + if (!found_lun) { + if (abort_cmd_for_tag(vha, abts->exchange_addr_to_abort)) { + /* send TASK_ABORT response immediately */ + qlt_24xx_send_abts_resp(vha, abts, FCP_TMF_CMPL, false); + return 0; + } else { + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf081, + "unable to find cmd in driver or LIO for tag 0x%x\n", + abts->exchange_addr_to_abort); + return -ENOENT; + } + } ql_dbg(ql_dbg_tgt_mgt, vha, 0xf00f, "qla_target(%d): task abort (tag=%d)\n", @@ -3264,6 +3339,13 @@ static void __qlt_do_work(struct qla_tgt_cmd *cmd) if (tgt->tgt_stop) goto out_term; + if (cmd->state == QLA_TGT_STATE_ABORTED) { + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf082, + "cmd with tag %u is aborted\n", + cmd->atio.u.isp24.exchange_addr); + goto out_term; + } + cdb = &atio->u.isp24.fcp_cmnd.cdb[0]; cmd->se_cmd.tag = atio->u.isp24.exchange_addr; cmd->unpacked_lun = scsilun_to_int( @@ -3317,6 +3399,12 @@ out_term: static void qlt_do_work(struct work_struct *work) { struct qla_tgt_cmd *cmd = container_of(work, struct qla_tgt_cmd, work); + scsi_qla_host_t *vha = cmd->vha; + unsigned long flags; + + spin_lock_irqsave(&vha->cmd_list_lock, flags); + list_del(&cmd->cmd_list); + spin_unlock_irqrestore(&vha->cmd_list_lock, flags); __qlt_do_work(cmd); } @@ -3368,14 +3456,25 @@ static void qlt_create_sess_from_atio(struct work_struct *work) unsigned long flags; uint8_t *s_id = op->atio.u.isp24.fcp_hdr.s_id; + spin_lock_irqsave(&vha->cmd_list_lock, flags); + list_del(&op->cmd_list); + spin_unlock_irqrestore(&vha->cmd_list_lock, flags); + + if (op->aborted) { + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf083, + "sess_op with tag %u is aborted\n", + op->atio.u.isp24.exchange_addr); + goto out_term; + } + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf022, - "qla_target(%d): Unable to find wwn login" - " (s_id %x:%x:%x), trying to create it manually\n", - vha->vp_idx, s_id[0], s_id[1], s_id[2]); + "qla_target(%d): Unable to find wwn login" + " (s_id %x:%x:%x), trying to create it manually\n", + vha->vp_idx, s_id[0], s_id[1], s_id[2]); if (op->atio.u.raw.entry_count > 1) { ql_dbg(ql_dbg_tgt_mgt, vha, 0xf023, - "Dropping multy entry atio %p\n", &op->atio); + "Dropping multy entry atio %p\n", &op->atio); goto out_term; } @@ -3440,6 +3539,11 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha, memcpy(&op->atio, atio, sizeof(*atio)); op->vha = vha; + + spin_lock(&vha->cmd_list_lock); + list_add_tail(&op->cmd_list, &vha->qla_sess_op_cmd_list); + spin_unlock(&vha->cmd_list_lock); + INIT_WORK(&op->work, qlt_create_sess_from_atio); queue_work(qla_tgt_wq, &op->work); return 0; @@ -3459,6 +3563,11 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha, cmd->cmd_in_wq = 1; cmd->cmd_flags |= BIT_0; + + spin_lock(&vha->cmd_list_lock); + list_add_tail(&cmd->cmd_list, &vha->qla_cmd_list); + spin_unlock(&vha->cmd_list_lock); + INIT_WORK(&cmd->work, qlt_do_work); queue_work(qla_tgt_wq, &cmd->work); return 0; @@ -3472,6 +3581,7 @@ static int qlt_issue_task_mgmt(struct qla_tgt_sess *sess, uint32_t lun, struct scsi_qla_host *vha = sess->vha; struct qla_hw_data *ha = vha->hw; struct qla_tgt_mgmt_cmd *mcmd; + struct atio_from_isp *a = (struct atio_from_isp *)iocb; int res; uint8_t tmr_func; @@ -3512,6 +3622,7 @@ static int qlt_issue_task_mgmt(struct qla_tgt_sess *sess, uint32_t lun, ql_dbg(ql_dbg_tgt_tmr, vha, 0x10002, "qla_target(%d): LUN_RESET received\n", sess->vha->vp_idx); tmr_func = TMR_LUN_RESET; + abort_cmds_for_lun(vha, lun, a->u.isp24.fcp_hdr.s_id); break; case QLA_TGT_CLEAR_TS: diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h index dfeeadf92fbb..310433504c0d 100644 --- a/drivers/scsi/qla2xxx/qla_target.h +++ b/drivers/scsi/qla2xxx/qla_target.h @@ -874,6 +874,8 @@ struct qla_tgt_sess_op { struct scsi_qla_host *vha; struct atio_from_isp atio; struct work_struct work; + struct list_head cmd_list; + bool aborted; }; /* @@ -1076,6 +1078,16 @@ static inline void qla_reverse_ini_mode(struct scsi_qla_host *ha) ha->host->active_mode |= MODE_INITIATOR; } +static inline uint32_t sid_to_key(const uint8_t *s_id) +{ + uint32_t key; + + key = (((unsigned long)s_id[0] << 16) | + ((unsigned long)s_id[1] << 8) | + (unsigned long)s_id[2]); + return key; +} + /* * Exported symbols from qla_target.c LLD logic used by qla2xxx code.. */ diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index 32ff9d15e12d..9ad9b6996a6a 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -1148,9 +1148,7 @@ static struct qla_tgt_sess *tcm_qla2xxx_find_sess_by_s_id( return NULL; } - key = (((unsigned long)s_id[0] << 16) | - ((unsigned long)s_id[1] << 8) | - (unsigned long)s_id[2]); + key = sid_to_key(s_id); pr_debug("find_sess_by_s_id: 0x%06x\n", key); se_nacl = btree_lookup32(&lport->lport_fcport_map, key); @@ -1185,9 +1183,7 @@ static void tcm_qla2xxx_set_sess_by_s_id( void *slot; int rc; - key = (((unsigned long)s_id[0] << 16) | - ((unsigned long)s_id[1] << 8) | - (unsigned long)s_id[2]); + key = sid_to_key(s_id); pr_debug("set_sess_by_s_id: %06x\n", key); slot = btree_lookup32(&lport->lport_fcport_map, key); From a6ca88780dd66b0700d89419abd17b6b4bb49483 Mon Sep 17 00:00:00 2001 From: Alexei Potashnik Date: Tue, 14 Jul 2015 16:00:44 -0400 Subject: [PATCH 106/428] qla2xxx: delay plogi/prli ack until existing sessions are deleted - keep qla_tgt_sess object on the session list until it's freed - modify use of sess->deleted flag to differentiate delayed session deletion that can be cancelled from irreversible one: QLA_SESS_DELETION_PENDING vs QLA_SESS_DELETION_IN_PROGRESS - during IN_PROGRESS deletion all newly arrived commands and TMRs will be rejected, existing commands and TMRs will be terminated when given by the core to the fabric or simply dropped if session logout has already happened (logout terminates all existing exchanges) - new PLOGI will initiate deletion of the following sessions (unless deletion is already IN_PROGRESS): - with the same port_name (with logout) - different port_name, different loop_id but the same port_id (with logout) - different port_name, different port_id, but the same loop_id (without logout) - additionally each new PLOGI will store imm notify iocb in the same port_name session being deleted. When deletion process completes this iocb will be acked. Only the most recent PLOGI iocb is stored. The older ones will be terminated when replaced. - new PRLI will initiate deletion of the following sessions (unless deletion is already IN_PROGRESS): - different port_name, different port_id, but the same loop_id (without logout) Cc: # v3.18+ Signed-off-by: Alexei Potashnik Acked-by: Quinn Tran Signed-off-by: Himanshu Madhani Signed-off-by: Nicholas Bellinger --- drivers/scsi/qla2xxx/qla_dbg.c | 6 +- drivers/scsi/qla2xxx/qla_def.h | 2 + drivers/scsi/qla2xxx/qla_init.c | 7 +- drivers/scsi/qla2xxx/qla_iocb.c | 3 + drivers/scsi/qla2xxx/qla_target.c | 438 +++++++++++++++++++++++++++-- drivers/scsi/qla2xxx/qla_target.h | 43 ++- drivers/scsi/qla2xxx/tcm_qla2xxx.c | 4 + 7 files changed, 481 insertions(+), 22 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c index e63aa0780b52..05793b7199a4 100644 --- a/drivers/scsi/qla2xxx/qla_dbg.c +++ b/drivers/scsi/qla2xxx/qla_dbg.c @@ -67,10 +67,10 @@ * | | | 0xd031-0xd0ff | * | | | 0xd101-0xd1fe | * | | | 0xd214-0xd2fe | - * | Target Mode | 0xe079 | | - * | Target Mode Management | 0xf083 | 0xf002 | + * | Target Mode | 0xe080 | | + * | Target Mode Management | 0xf091 | 0xf002 | * | | | 0xf046-0xf049 | - * | Target Mode Task Management | 0x1000b | | + * | Target Mode Task Management | 0x1000d | | * ---------------------------------------------------------------------- */ diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index d9c4ed21b52f..08a869f1ee03 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -274,6 +274,7 @@ #define RESPONSE_ENTRY_CNT_FX00 256 /* Number of response entries.*/ struct req_que; +struct qla_tgt_sess; /* * (sd.h is not exported, hence local inclusion) @@ -2026,6 +2027,7 @@ typedef struct fc_port { uint16_t port_id; unsigned long retry_delay_timestamp; + struct qla_tgt_sess *tgt_session; } fc_port_t; #include "qla_mr.h" diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index e166c468a8b2..bda7a0d08b56 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) QLA_LOGIO_LOGIN_RETRIED : 0; qla2x00_post_async_login_done_work(fcport->vha, fcport, lio->u.logio.data); + } else if (sp->type == SRB_LOGOUT_CMD) { + qlt_logo_completion_handler(fcport, QLA_FUNCTION_TIMEOUT); } } @@ -497,7 +499,10 @@ void qla2x00_async_logout_done(struct scsi_qla_host *vha, fc_port_t *fcport, uint16_t *data) { - qla2x00_mark_device_lost(vha, fcport, 1, 0); + /* Don't re-login in target mode */ + if (!fcport->tgt_session) + qla2x00_mark_device_lost(vha, fcport, 1, 0); + qlt_logo_completion_handler(fcport, data[0]); return; } diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index 36fbd4c7af8f..6f02b26a35cf 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -1943,6 +1943,9 @@ qla24xx_logout_iocb(srb_t *sp, struct logio_entry_24xx *logio) logio->entry_type = LOGINOUT_PORT_IOCB_TYPE; logio->control_flags = cpu_to_le16(LCF_COMMAND_LOGO|LCF_IMPL_LOGO); + if (!sp->fcport->tgt_session || + !sp->fcport->tgt_session->keep_nport_handle) + logio->control_flags |= cpu_to_le16(LCF_FREE_NPORT); logio->nport_handle = cpu_to_le16(sp->fcport->loop_id); logio->port_id[0] = sp->fcport->d_id.b.al_pa; logio->port_id[1] = sp->fcport->d_id.b.area; diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index eca444827eae..acb2a50d3c55 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -114,6 +114,10 @@ static void qlt_alloc_qfull_cmd(struct scsi_qla_host *vha, struct atio_from_isp *atio, uint16_t status, int qfull); static void qlt_disable_vha(struct scsi_qla_host *vha); static void qlt_clear_tgt_db(struct qla_tgt *tgt); +static void qlt_send_notify_ack(struct scsi_qla_host *vha, + struct imm_ntfy_from_isp *ntfy, + uint32_t add_flags, uint16_t resp_code, int resp_code_valid, + uint16_t srr_flags, uint16_t srr_reject_code, uint8_t srr_explan); /* * Global Variables */ @@ -382,14 +386,73 @@ static void qlt_free_session_done(struct work_struct *work) struct qla_tgt *tgt = sess->tgt; struct scsi_qla_host *vha = sess->vha; struct qla_hw_data *ha = vha->hw; + unsigned long flags; + bool logout_started = false; + fc_port_t fcport; + + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf084, + "%s: se_sess %p / sess %p from port %8phC loop_id %#04x" + " s_id %02x:%02x:%02x logout %d keep %d plogi %d\n", + __func__, sess->se_sess, sess, sess->port_name, sess->loop_id, + sess->s_id.b.domain, sess->s_id.b.area, sess->s_id.b.al_pa, + sess->logout_on_delete, sess->keep_nport_handle, + sess->plogi_ack_needed); BUG_ON(!tgt); + + if (sess->logout_on_delete) { + int rc; + + memset(&fcport, 0, sizeof(fcport)); + fcport.loop_id = sess->loop_id; + fcport.d_id = sess->s_id; + memcpy(fcport.port_name, sess->port_name, WWN_SIZE); + fcport.vha = vha; + fcport.tgt_session = sess; + + rc = qla2x00_post_async_logout_work(vha, &fcport, NULL); + if (rc != QLA_SUCCESS) + ql_log(ql_log_warn, vha, 0xf085, + "Schedule logo failed sess %p rc %d\n", + sess, rc); + else + logout_started = true; + } + /* * Release the target session for FC Nexus from fabric module code. */ if (sess->se_sess != NULL) ha->tgt.tgt_ops->free_session(sess); + if (logout_started) { + bool traced = false; + + while (!ACCESS_ONCE(sess->logout_completed)) { + if (!traced) { + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf086, + "%s: waiting for sess %p logout\n", + __func__, sess); + traced = true; + } + msleep(100); + } + + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf087, + "%s: sess %p logout completed\n", + __func__, sess); + } + + spin_lock_irqsave(&ha->hardware_lock, flags); + + if (sess->plogi_ack_needed) + qlt_send_notify_ack(vha, &sess->tm_iocb, + 0, 0, 0, 0, 0, 0); + + list_del(&sess->sess_list_entry); + + spin_unlock_irqrestore(&ha->hardware_lock, flags); + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf001, "Unregistration of sess %p finished\n", sess); @@ -410,9 +473,9 @@ void qlt_unreg_sess(struct qla_tgt_sess *sess) vha->hw->tgt.tgt_ops->clear_nacl_from_fcport_map(sess); - list_del(&sess->sess_list_entry); - if (sess->deleted) - list_del(&sess->del_list_entry); + if (!list_empty(&sess->del_list_entry)) + list_del_init(&sess->del_list_entry); + sess->deleted = QLA_SESS_DELETION_IN_PROGRESS; INIT_WORK(&sess->free_work, qlt_free_session_done); schedule_work(&sess->free_work); @@ -490,27 +553,36 @@ static void qlt_schedule_sess_for_deletion(struct qla_tgt_sess *sess, struct qla_tgt *tgt = sess->tgt; uint32_t dev_loss_tmo = tgt->ha->port_down_retry_count + 5; - if (sess->deleted) - return; + if (sess->deleted) { + /* Upgrade to unconditional deletion in case it was temporary */ + if (immediate && sess->deleted == QLA_SESS_DELETION_PENDING) + list_del(&sess->del_list_entry); + else + return; + } ql_dbg(ql_dbg_tgt, sess->vha, 0xe001, "Scheduling sess %p for deletion\n", sess); - list_add_tail(&sess->del_list_entry, &tgt->del_sess_list); - sess->deleted = 1; - if (immediate) + if (immediate) { dev_loss_tmo = 0; + sess->deleted = QLA_SESS_DELETION_IN_PROGRESS; + list_add(&sess->del_list_entry, &tgt->del_sess_list); + } else { + sess->deleted = QLA_SESS_DELETION_PENDING; + list_add_tail(&sess->del_list_entry, &tgt->del_sess_list); + } sess->expires = jiffies + dev_loss_tmo * HZ; ql_dbg(ql_dbg_tgt, sess->vha, 0xe048, "qla_target(%d): session for port %8phC (loop ID %d) scheduled for " - "deletion in %u secs (expires: %lu) immed: %d\n", + "deletion in %u secs (expires: %lu) immed: %d, logout: %d\n", sess->vha->vp_idx, sess->port_name, sess->loop_id, dev_loss_tmo, - sess->expires, immediate); + sess->expires, immediate, sess->logout_on_delete); if (immediate) - schedule_delayed_work(&tgt->sess_del_work, 0); + mod_delayed_work(system_wq, &tgt->sess_del_work, 0); else schedule_delayed_work(&tgt->sess_del_work, sess->expires - jiffies); @@ -579,9 +651,9 @@ out_free_id_list: /* ha->hardware_lock supposed to be held on entry */ static void qlt_undelete_sess(struct qla_tgt_sess *sess) { - BUG_ON(!sess->deleted); + BUG_ON(sess->deleted != QLA_SESS_DELETION_PENDING); - list_del(&sess->del_list_entry); + list_del_init(&sess->del_list_entry); sess->deleted = 0; } @@ -600,7 +672,9 @@ static void qlt_del_sess_work_fn(struct delayed_work *work) del_list_entry); elapsed = jiffies; if (time_after_eq(elapsed, sess->expires)) { - qlt_undelete_sess(sess); + /* No turning back */ + list_del_init(&sess->del_list_entry); + sess->deleted = QLA_SESS_DELETION_IN_PROGRESS; ql_dbg(ql_dbg_tgt_mgt, vha, 0xf004, "Timeout: sess %p about to be deleted\n", @@ -644,6 +718,13 @@ static struct qla_tgt_sess *qlt_create_sess( fcport->d_id.b.al_pa, fcport->d_id.b.area, fcport->loop_id); + /* Cannot undelete at this point */ + if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) { + spin_unlock_irqrestore(&ha->hardware_lock, + flags); + return NULL; + } + if (sess->deleted) qlt_undelete_sess(sess); @@ -674,6 +755,14 @@ static struct qla_tgt_sess *qlt_create_sess( sess->s_id = fcport->d_id; sess->loop_id = fcport->loop_id; sess->local = local; + INIT_LIST_HEAD(&sess->del_list_entry); + + /* Under normal circumstances we want to logout from firmware when + * session eventually ends and release corresponding nport handle. + * In the exception cases (e.g. when new PLOGI is waiting) corresponding + * code will adjust these flags as necessary. */ + sess->logout_on_delete = 1; + sess->keep_nport_handle = 0; ql_dbg(ql_dbg_tgt_mgt, vha, 0xf006, "Adding sess %p to tgt %p via ->check_initiator_node_acl()\n", @@ -751,6 +840,10 @@ void qlt_fc_port_added(struct scsi_qla_host *vha, fc_port_t *fcport) mutex_unlock(&vha->vha_tgt.tgt_mutex); spin_lock_irqsave(&ha->hardware_lock, flags); + } else if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) { + /* Point of no return */ + spin_unlock_irqrestore(&ha->hardware_lock, flags); + return; } else { kref_get(&sess->se_sess->sess_kref); @@ -2371,6 +2464,19 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type, unsigned long flags = 0; int res; + spin_lock_irqsave(&ha->hardware_lock, flags); + if (cmd->sess && cmd->sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) { + cmd->state = QLA_TGT_STATE_PROCESSED; + if (cmd->sess->logout_completed) + /* no need to terminate. FW already freed exchange. */ + qlt_abort_cmd_on_host_reset(cmd->vha, cmd); + else + qlt_send_term_exchange(vha, cmd, &cmd->atio, 1); + spin_unlock_irqrestore(&ha->hardware_lock, flags); + return 0; + } + spin_unlock_irqrestore(&ha->hardware_lock, flags); + memset(&prm, 0, sizeof(prm)); qlt_check_srr_debug(cmd, &xmit_type); @@ -2532,7 +2638,8 @@ int qlt_rdy_to_xfer(struct qla_tgt_cmd *cmd) spin_lock_irqsave(&ha->hardware_lock, flags); - if (qla2x00_reset_active(vha) || cmd->reset_count != ha->chip_reset) { + if (qla2x00_reset_active(vha) || (cmd->reset_count != ha->chip_reset) || + (cmd->sess && cmd->sess->deleted == QLA_SESS_DELETION_IN_PROGRESS)) { /* * Either a chip reset is active or this request was from * previous life, just abort the processing. @@ -2723,6 +2830,89 @@ out: } +/* If hardware_lock held on entry, might drop it, then reaquire */ +/* This function sends the appropriate CTIO to ISP 2xxx or 24xx */ +static int __qlt_send_term_imm_notif(struct scsi_qla_host *vha, + struct imm_ntfy_from_isp *ntfy) +{ + struct nack_to_isp *nack; + struct qla_hw_data *ha = vha->hw; + request_t *pkt; + int ret = 0; + + ql_dbg(ql_dbg_tgt_tmr, vha, 0xe01c, + "Sending TERM ELS CTIO (ha=%p)\n", ha); + + pkt = (request_t *)qla2x00_alloc_iocbs_ready(vha, NULL); + if (pkt == NULL) { + ql_dbg(ql_dbg_tgt, vha, 0xe080, + "qla_target(%d): %s failed: unable to allocate " + "request packet\n", vha->vp_idx, __func__); + return -ENOMEM; + } + + pkt->entry_type = NOTIFY_ACK_TYPE; + pkt->entry_count = 1; + pkt->handle = QLA_TGT_SKIP_HANDLE | CTIO_COMPLETION_HANDLE_MARK; + + nack = (struct nack_to_isp *)pkt; + nack->ox_id = ntfy->ox_id; + + nack->u.isp24.nport_handle = ntfy->u.isp24.nport_handle; + if (le16_to_cpu(ntfy->u.isp24.status) == IMM_NTFY_ELS) { + nack->u.isp24.flags = ntfy->u.isp24.flags & + __constant_cpu_to_le32(NOTIFY24XX_FLAGS_PUREX_IOCB); + } + + /* terminate */ + nack->u.isp24.flags |= + __constant_cpu_to_le16(NOTIFY_ACK_FLAGS_TERMINATE); + + nack->u.isp24.srr_rx_id = ntfy->u.isp24.srr_rx_id; + nack->u.isp24.status = ntfy->u.isp24.status; + nack->u.isp24.status_subcode = ntfy->u.isp24.status_subcode; + nack->u.isp24.fw_handle = ntfy->u.isp24.fw_handle; + nack->u.isp24.exchange_address = ntfy->u.isp24.exchange_address; + nack->u.isp24.srr_rel_offs = ntfy->u.isp24.srr_rel_offs; + nack->u.isp24.srr_ui = ntfy->u.isp24.srr_ui; + nack->u.isp24.vp_index = ntfy->u.isp24.vp_index; + + qla2x00_start_iocbs(vha, vha->req); + return ret; +} + +static void qlt_send_term_imm_notif(struct scsi_qla_host *vha, + struct imm_ntfy_from_isp *imm, int ha_locked) +{ + unsigned long flags = 0; + int rc; + + if (qlt_issue_marker(vha, ha_locked) < 0) + return; + + if (ha_locked) { + rc = __qlt_send_term_imm_notif(vha, imm); + +#if 0 /* Todo */ + if (rc == -ENOMEM) + qlt_alloc_qfull_cmd(vha, imm, 0, 0); +#endif + goto done; + } + + spin_lock_irqsave(&vha->hw->hardware_lock, flags); + rc = __qlt_send_term_imm_notif(vha, imm); + +#if 0 /* Todo */ + if (rc == -ENOMEM) + qlt_alloc_qfull_cmd(vha, imm, 0, 0); +#endif + +done: + if (!ha_locked) + spin_unlock_irqrestore(&vha->hw->hardware_lock, flags); +} + /* If hardware_lock held on entry, might drop it, then reaquire */ /* This function sends the appropriate CTIO to ISP 2xxx or 24xx */ static int __qlt_send_term_exchange(struct scsi_qla_host *vha, @@ -3776,22 +3966,237 @@ static int qlt_abort_task(struct scsi_qla_host *vha, return __qlt_abort_task(vha, iocb, sess); } +void qlt_logo_completion_handler(fc_port_t *fcport, int rc) +{ + if (fcport->tgt_session) { + if (rc != MBS_COMMAND_COMPLETE) { + ql_dbg(ql_dbg_tgt_mgt, fcport->vha, 0xf088, + "%s: se_sess %p / sess %p from" + " port %8phC loop_id %#04x s_id %02x:%02x:%02x" + " LOGO failed: %#x\n", + __func__, + fcport->tgt_session->se_sess, + fcport->tgt_session, + fcport->port_name, fcport->loop_id, + fcport->d_id.b.domain, fcport->d_id.b.area, + fcport->d_id.b.al_pa, rc); + } + + fcport->tgt_session->logout_completed = 1; + } +} + +static void qlt_swap_imm_ntfy_iocb(struct imm_ntfy_from_isp *a, + struct imm_ntfy_from_isp *b) +{ + struct imm_ntfy_from_isp tmp; + memcpy(&tmp, a, sizeof(struct imm_ntfy_from_isp)); + memcpy(a, b, sizeof(struct imm_ntfy_from_isp)); + memcpy(b, &tmp, sizeof(struct imm_ntfy_from_isp)); +} + +/* +* ha->hardware_lock supposed to be held on entry (to protect tgt->sess_list) +* +* Schedules sessions with matching port_id/loop_id but different wwn for +* deletion. Returns existing session with matching wwn if present. +* Null otherwise. +*/ +static struct qla_tgt_sess * +qlt_find_sess_invalidate_other(struct qla_tgt *tgt, uint64_t wwn, + port_id_t port_id, uint16_t loop_id) +{ + struct qla_tgt_sess *sess = NULL, *other_sess; + uint64_t other_wwn; + + list_for_each_entry(other_sess, &tgt->sess_list, sess_list_entry) { + + other_wwn = wwn_to_u64(other_sess->port_name); + + if (wwn == other_wwn) { + WARN_ON(sess); + sess = other_sess; + continue; + } + + /* find other sess with nport_id collision */ + if (port_id.b24 == other_sess->s_id.b24) { + if (loop_id != other_sess->loop_id) { + ql_dbg(ql_dbg_tgt_tmr, tgt->vha, 0x1000c, + "Invalidating sess %p loop_id %d wwn %llx.\n", + other_sess, other_sess->loop_id, other_wwn); + + /* + * logout_on_delete is set by default, but another + * session that has the same s_id/loop_id combo + * might have cleared it when requested this session + * deletion, so don't touch it + */ + qlt_schedule_sess_for_deletion(other_sess, true); + } else { + /* + * Another wwn used to have our s_id/loop_id + * combo - kill the session, but don't log out + */ + sess->logout_on_delete = 0; + qlt_schedule_sess_for_deletion(other_sess, + true); + } + continue; + } + + /* find other sess with nport handle collision */ + if (loop_id == other_sess->loop_id) { + ql_dbg(ql_dbg_tgt_tmr, tgt->vha, 0x1000d, + "Invalidating sess %p loop_id %d wwn %llx.\n", + other_sess, other_sess->loop_id, other_wwn); + + /* Same loop_id but different s_id + * Ok to kill and logout */ + qlt_schedule_sess_for_deletion(other_sess, true); + } + } + + return sess; +} + /* * ha->hardware_lock supposed to be held on entry. Might drop it, then reaquire */ static int qlt_24xx_handle_els(struct scsi_qla_host *vha, struct imm_ntfy_from_isp *iocb) { + struct qla_tgt *tgt = vha->vha_tgt.qla_tgt; + struct qla_tgt_sess *sess = NULL; + uint64_t wwn; + port_id_t port_id; + uint16_t loop_id; + uint16_t wd3_lo; int res = 0; + wwn = wwn_to_u64(iocb->u.isp24.port_name); + + port_id.b.domain = iocb->u.isp24.port_id[2]; + port_id.b.area = iocb->u.isp24.port_id[1]; + port_id.b.al_pa = iocb->u.isp24.port_id[0]; + port_id.b.rsvd_1 = 0; + + loop_id = le16_to_cpu(iocb->u.isp24.nport_handle); + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf026, "qla_target(%d): Port ID: 0x%3phC ELS opcode: 0x%02x\n", vha->vp_idx, iocb->u.isp24.port_id, iocb->u.isp24.status_subcode); + /* res = 1 means ack at the end of thread + * res = 0 means ack async/later. + */ switch (iocb->u.isp24.status_subcode) { case ELS_PLOGI: - case ELS_FLOGI: + + if (wwn) + sess = qlt_find_sess_invalidate_other(tgt, wwn, + port_id, loop_id); + + if (!sess || IS_SW_RESV_ADDR(sess->s_id)) { + res = 1; + break; + } + + if (sess->plogi_ack_needed) { + /* + * Initiator sent another PLOGI before last PLOGI could + * finish. Swap plogi iocbs and terminate old one + * without acking, new one will get acked when session + * deletion completes. + */ + ql_log(ql_log_warn, sess->vha, 0xf089, + "sess %p received double plogi.\n", sess); + + qlt_swap_imm_ntfy_iocb(iocb, &sess->tm_iocb); + + qlt_send_term_imm_notif(vha, iocb, 1); + + res = 0; + break; + } + + res = 0; + + /* + * Save immediate Notif IOCB for Ack when sess is done + * and being deleted. + */ + memcpy(&sess->tm_iocb, iocb, sizeof(sess->tm_iocb)); + sess->plogi_ack_needed = 1; + + /* + * Under normal circumstances we want to release nport handle + * during LOGO process to avoid nport handle leaks inside FW. + * The exception is when LOGO is done while another PLOGI with + * the same nport handle is waiting as might be the case here. + * Note: there is always a possibily of a race where session + * deletion has already started for other reasons (e.g. ACL + * removal) and now PLOGI arrives: + * 1. if PLOGI arrived in FW after nport handle has been freed, + * FW must have assigned this PLOGI a new/same handle and we + * can proceed ACK'ing it as usual when session deletion + * completes. + * 2. if PLOGI arrived in FW before LOGO with LCF_FREE_NPORT + * bit reached it, the handle has now been released. We'll + * get an error when we ACK this PLOGI. Nothing will be sent + * back to initiator. Initiator should eventually retry + * PLOGI and situation will correct itself. + */ + sess->keep_nport_handle = ((sess->loop_id == loop_id) && + (sess->s_id.b24 == port_id.b24)); + qlt_schedule_sess_for_deletion(sess, true); + break; + case ELS_PRLI: + wd3_lo = le16_to_cpu(iocb->u.isp24.u.prli.wd3_lo); + + if (wwn) + sess = qlt_find_sess_invalidate_other(tgt, wwn, port_id, + loop_id); + + if (sess != NULL) { + if (sess->deleted) { + /* + * Impatient initiator sent PRLI before last + * PLOGI could finish. Will force him to re-try, + * while last one finishes. + */ + ql_log(ql_log_warn, sess->vha, 0xf090, + "sess %p PRLI received, before plogi ack.\n", + sess); + qlt_send_term_imm_notif(vha, iocb, 1); + res = 0; + break; + } + + /* + * This shouldn't happen under normal circumstances, + * since we have deleted the old session during PLOGI + */ + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf091, + "PRLI (loop_id %#04x) for existing sess %p (loop_id %#04x)\n", + sess->loop_id, sess, iocb->u.isp24.nport_handle); + + sess->local = 0; + sess->loop_id = loop_id; + sess->s_id = port_id; + + if (wd3_lo & BIT_7) + sess->conf_compl_supported = 1; + + res = 1; + } else { + /* todo: else - create sess here. */ + res = 1; /* send notify ack */ + } + + break; + case ELS_LOGO: case ELS_PRLO: res = qlt_reset(vha, iocb, QLA_TGT_NEXUS_LOSS_SESS); @@ -3809,6 +4214,7 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha, break; } + case ELS_FLOGI: /* should never happen */ default: ql_dbg(ql_dbg_tgt_mgt, vha, 0xf061, "qla_target(%d): Unsupported ELS command %x " diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h index 310433504c0d..165efb5cc6c1 100644 --- a/drivers/scsi/qla2xxx/qla_target.h +++ b/drivers/scsi/qla2xxx/qla_target.h @@ -167,7 +167,24 @@ struct imm_ntfy_from_isp { uint32_t srr_rel_offs; uint16_t srr_ui; uint16_t srr_ox_id; - uint8_t reserved_4[19]; + union { + struct { + uint8_t node_name[8]; + } plogi; /* PLOGI/ADISC/PDISC */ + struct { + /* PRLI word 3 bit 0-15 */ + uint16_t wd3_lo; + uint8_t resv0[6]; + } prli; + struct { + uint8_t port_id[3]; + uint8_t resv1; + uint16_t nport_handle; + uint16_t resv2; + } req_els; + } u; + uint8_t port_name[8]; + uint8_t resv3[3]; uint8_t vp_index; uint32_t reserved_5; uint8_t port_id[3]; @@ -234,6 +251,7 @@ struct nack_to_isp { uint8_t reserved[2]; uint16_t ox_id; } __packed; +#define NOTIFY_ACK_FLAGS_TERMINATE BIT_3 #define NOTIFY_ACK_SRR_FLAGS_ACCEPT 0 #define NOTIFY_ACK_SRR_FLAGS_REJECT 1 @@ -878,6 +896,13 @@ struct qla_tgt_sess_op { bool aborted; }; +enum qla_sess_deletion { + QLA_SESS_DELETION_NONE = 0, + QLA_SESS_DELETION_PENDING = 1, /* hopefully we can get rid of + * this one */ + QLA_SESS_DELETION_IN_PROGRESS = 2, +}; + /* * Equivilant to IT Nexus (Initiator-Target) */ @@ -886,8 +911,13 @@ struct qla_tgt_sess { port_id_t s_id; unsigned int conf_compl_supported:1; - unsigned int deleted:1; + unsigned int deleted:2; unsigned int local:1; + unsigned int logout_on_delete:1; + unsigned int plogi_ack_needed:1; + unsigned int keep_nport_handle:1; + + unsigned char logout_completed; struct se_session *se_sess; struct scsi_qla_host *vha; @@ -899,6 +929,10 @@ struct qla_tgt_sess { uint8_t port_name[WWN_SIZE]; struct work_struct free_work; + + union { + struct imm_ntfy_from_isp tm_iocb; + }; }; struct qla_tgt_cmd { @@ -1031,6 +1065,10 @@ struct qla_tgt_srr_ctio { struct qla_tgt_cmd *cmd; }; +/* Check for Switch reserved address */ +#define IS_SW_RESV_ADDR(_s_id) \ + ((_s_id.b.domain == 0xff) && (_s_id.b.area == 0xfc)) + #define QLA_TGT_XMIT_DATA 1 #define QLA_TGT_XMIT_STATUS 2 #define QLA_TGT_XMIT_ALL (QLA_TGT_XMIT_STATUS|QLA_TGT_XMIT_DATA) @@ -1124,5 +1162,6 @@ extern void qlt_stop_phase2(struct qla_tgt *); extern irqreturn_t qla83xx_msix_atio_q(int, void *); extern void qlt_83xx_iospace_config(struct qla_hw_data *); extern int qlt_free_qfull_cmds(struct scsi_qla_host *); +extern void qlt_logo_completion_handler(fc_port_t *, int); #endif /* __QLA_TARGET_H */ diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index 9ad9b6996a6a..4e242c757947 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -1539,6 +1539,10 @@ static void tcm_qla2xxx_update_sess(struct qla_tgt_sess *sess, port_id_t s_id, } sess->conf_compl_supported = conf_compl_supported; + + /* Reset logout parameters to default */ + sess->logout_on_delete = 1; + sess->keep_nport_handle = 0; } /* From daddf5cf9b5c68b81b2bb7133f1dd0fda4552d0b Mon Sep 17 00:00:00 2001 From: Alexei Potashnik Date: Tue, 14 Jul 2015 16:00:45 -0400 Subject: [PATCH 107/428] qla2xxx: Abort stale cmds on qla_tgt_wq when plogi arrives cancel any commands from initiator's s_id that are still waiting on qla_tgt_wq when PLOGI arrives. Cc: # v3.18+ Signed-off-by: Alexei Potashnik Acked-by: Quinn Tran Signed-off-by: Himanshu Madhani Signed-off-by: Nicholas Bellinger --- drivers/scsi/qla2xxx/qla_target.c | 35 +++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index acb2a50d3c55..0b08bebea538 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -4060,6 +4060,38 @@ qlt_find_sess_invalidate_other(struct qla_tgt *tgt, uint64_t wwn, return sess; } +/* Abort any commands for this s_id waiting on qla_tgt_wq workqueue */ +static int abort_cmds_for_s_id(struct scsi_qla_host *vha, port_id_t *s_id) +{ + struct qla_tgt_sess_op *op; + struct qla_tgt_cmd *cmd; + uint32_t key; + int count = 0; + + key = (((u32)s_id->b.domain << 16) | + ((u32)s_id->b.area << 8) | + ((u32)s_id->b.al_pa)); + + spin_lock(&vha->cmd_list_lock); + list_for_each_entry(op, &vha->qla_sess_op_cmd_list, cmd_list) { + uint32_t op_key = sid_to_key(op->atio.u.isp24.fcp_hdr.s_id); + if (op_key == key) { + op->aborted = true; + count++; + } + } + list_for_each_entry(cmd, &vha->qla_cmd_list, cmd_list) { + uint32_t cmd_key = sid_to_key(cmd->atio.u.isp24.fcp_hdr.s_id); + if (cmd_key == key) { + cmd->state = QLA_TGT_STATE_ABORTED; + count++; + } + } + spin_unlock(&vha->cmd_list_lock); + + return count; +} + /* * ha->hardware_lock supposed to be held on entry. Might drop it, then reaquire */ @@ -4093,6 +4125,9 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha, switch (iocb->u.isp24.status_subcode) { case ELS_PLOGI: + /* Mark all stale commands in qla_tgt_wq for deletion */ + abort_cmds_for_s_id(vha, &port_id); + if (wwn) sess = qlt_find_sess_invalidate_other(tgt, wwn, port_id, loop_id); From df673274fa4896f25f0bf348d2a3535d74b4cbec Mon Sep 17 00:00:00 2001 From: Alexei Potashnik Date: Tue, 14 Jul 2015 16:00:46 -0400 Subject: [PATCH 108/428] qla2xxx: added sess generations to detect RSCN update races RSCN processing in qla2xxx driver can run in parallel with ELS/IO processing. As such the decision to remove disappeared fc port's session could be stale, because a new login sequence has occurred since and created a brand new session. Previous mechanism of dealing with this by delaying deletion request was prone to erroneous deletions if the event that was supposed to cancel the deletion never arrived or has been delayed in processing. New mechanism relies on a time-like generation counter to serialize RSCN updates relative to ELS/IO updates. Cc: # v3.18+ Signed-off-by: Alexei Potashnik Signed-off-by: Himanshu Madhani Signed-off-by: Nicholas Bellinger --- drivers/scsi/qla2xxx/qla_dbg.c | 2 +- drivers/scsi/qla2xxx/qla_def.h | 5 +++ drivers/scsi/qla2xxx/qla_init.c | 32 ++++++++++------- drivers/scsi/qla2xxx/qla_os.c | 5 ++- drivers/scsi/qla2xxx/qla_target.c | 60 +++++++++++++++++++++++++------ drivers/scsi/qla2xxx/qla_target.h | 5 ++- 6 files changed, 83 insertions(+), 26 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c index 05793b7199a4..8b011aef12bd 100644 --- a/drivers/scsi/qla2xxx/qla_dbg.c +++ b/drivers/scsi/qla2xxx/qla_dbg.c @@ -68,7 +68,7 @@ * | | | 0xd101-0xd1fe | * | | | 0xd214-0xd2fe | * | Target Mode | 0xe080 | | - * | Target Mode Management | 0xf091 | 0xf002 | + * | Target Mode Management | 0xf096 | 0xf002 | * | | | 0xf046-0xf049 | * | Target Mode Task Management | 0x1000d | | * ---------------------------------------------------------------------- diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 08a869f1ee03..9ad819edcd67 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -3586,6 +3586,11 @@ typedef struct scsi_qla_host { struct list_head qla_sess_op_cmd_list; spinlock_t cmd_list_lock; + /* Counter to detect races between ELS and RSCN events */ + atomic_t generation_tick; + /* Time when global fcport update has been scheduled */ + int total_fcport_update_gen; + uint32_t vp_abort_cnt; struct fc_vport *fc_vport; /* holds fc_vport * for each vport */ diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index bda7a0d08b56..506621d814ab 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -2927,24 +2927,14 @@ qla2x00_rport_del(void *data) { fc_port_t *fcport = data; struct fc_rport *rport; - scsi_qla_host_t *vha = fcport->vha; unsigned long flags; - unsigned long vha_flags; spin_lock_irqsave(fcport->vha->host->host_lock, flags); rport = fcport->drport ? fcport->drport: fcport->rport; fcport->drport = NULL; spin_unlock_irqrestore(fcport->vha->host->host_lock, flags); - if (rport) { + if (rport) fc_remote_port_delete(rport); - /* - * Release the target mode FC NEXUS in qla_target.c code - * if target mod is enabled. - */ - spin_lock_irqsave(&vha->hw->hardware_lock, vha_flags); - qlt_fc_port_deleted(vha, fcport); - spin_unlock_irqrestore(&vha->hw->hardware_lock, vha_flags); - } } /** @@ -3384,6 +3374,7 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha) LIST_HEAD(new_fcports); struct qla_hw_data *ha = vha->hw; struct scsi_qla_host *base_vha = pci_get_drvdata(ha->pdev); + int discovery_gen; /* If FL port exists, then SNS is present */ if (IS_FWI2_CAPABLE(ha)) @@ -3454,6 +3445,14 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha) fcport->scan_state = QLA_FCPORT_SCAN; } + /* Mark the time right before querying FW for connected ports. + * This process is long, asynchronous and by the time it's done, + * collected information might not be accurate anymore. E.g. + * disconnected port might have re-connected and a brand new + * session has been created. In this case session's generation + * will be newer than discovery_gen. */ + qlt_do_generation_tick(vha, &discovery_gen); + rval = qla2x00_find_all_fabric_devs(vha, &new_fcports); if (rval != QLA_SUCCESS) break; @@ -3505,7 +3504,8 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha) atomic_read(&fcport->state), fcport->flags, fcport->fc4_type, fcport->scan_state); - qlt_fc_port_deleted(vha, fcport); + qlt_fc_port_deleted(vha, fcport, + discovery_gen); } } } @@ -4282,6 +4282,14 @@ qla2x00_update_fcports(scsi_qla_host_t *base_vha) atomic_read(&fcport->state) != FCS_UNCONFIGURED) { spin_unlock_irqrestore(&ha->vport_slock, flags); qla2x00_rport_del(fcport); + + /* + * Release the target mode FC NEXUS in + * qla_target.c, if target mod is enabled. + */ + qlt_fc_port_deleted(vha, fcport, + base_vha->total_fcport_update_gen); + spin_lock_irqsave(&ha->vport_slock, flags); } } diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 7ce395aaf033..be6de2a1e36e 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -3230,11 +3230,14 @@ qla2x00_schedule_rport_del(struct scsi_qla_host *vha, fc_port_t *fcport, spin_lock_irqsave(vha->host->host_lock, flags); fcport->drport = rport; spin_unlock_irqrestore(vha->host->host_lock, flags); + qlt_do_generation_tick(vha, &base_vha->total_fcport_update_gen); set_bit(FCPORT_UPDATE_NEEDED, &base_vha->dpc_flags); qla2xxx_wake_dpc(base_vha); } else { + int now; fc_remote_port_delete(rport); - qlt_fc_port_deleted(vha, fcport); + qlt_do_generation_tick(vha, &now); + qlt_fc_port_deleted(vha, fcport, now); } } diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 0b08bebea538..0b5bd9cd7f0d 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -127,6 +127,16 @@ static struct workqueue_struct *qla_tgt_wq; static DEFINE_MUTEX(qla_tgt_mutex); static LIST_HEAD(qla_tgt_glist); +/* This API intentionally takes dest as a parameter, rather than returning + * int value to avoid caller forgetting to issue wmb() after the store */ +void qlt_do_generation_tick(struct scsi_qla_host *vha, int *dest) +{ + scsi_qla_host_t *base_vha = pci_get_drvdata(vha->hw->pdev); + *dest = atomic_inc_return(&base_vha->generation_tick); + /* memory barrier */ + wmb(); +} + /* ha->hardware_lock supposed to be held on entry (to protect tgt->sess_list) */ static struct qla_tgt_sess *qlt_find_sess_by_port_name( struct qla_tgt *tgt, @@ -576,10 +586,12 @@ static void qlt_schedule_sess_for_deletion(struct qla_tgt_sess *sess, sess->expires = jiffies + dev_loss_tmo * HZ; ql_dbg(ql_dbg_tgt, sess->vha, 0xe048, - "qla_target(%d): session for port %8phC (loop ID %d) scheduled for " - "deletion in %u secs (expires: %lu) immed: %d, logout: %d\n", - sess->vha->vp_idx, sess->port_name, sess->loop_id, dev_loss_tmo, - sess->expires, immediate, sess->logout_on_delete); + "qla_target(%d): session for port %8phC (loop ID %d s_id %02x:%02x:%02x)" + " scheduled for deletion in %u secs (expires: %lu) immed: %d, logout: %d, gen: %#x\n", + sess->vha->vp_idx, sess->port_name, sess->loop_id, + sess->s_id.b.domain, sess->s_id.b.area, sess->s_id.b.al_pa, + dev_loss_tmo, sess->expires, immediate, sess->logout_on_delete, + sess->generation); if (immediate) mod_delayed_work(system_wq, &tgt->sess_del_work, 0); @@ -734,6 +746,9 @@ static struct qla_tgt_sess *qlt_create_sess( if (sess->local && !local) sess->local = 0; + + qlt_do_generation_tick(vha, &sess->generation); + spin_unlock_irqrestore(&ha->hardware_lock, flags); return sess; @@ -795,6 +810,7 @@ static struct qla_tgt_sess *qlt_create_sess( spin_lock_irqsave(&ha->hardware_lock, flags); list_add_tail(&sess->sess_list_entry, &vha->vha_tgt.qla_tgt->sess_list); vha->vha_tgt.qla_tgt->sess_count++; + qlt_do_generation_tick(vha, &sess->generation); spin_unlock_irqrestore(&ha->hardware_lock, flags); ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04b, @@ -808,7 +824,7 @@ static struct qla_tgt_sess *qlt_create_sess( } /* - * Called from drivers/scsi/qla2xxx/qla_init.c:qla2x00_reg_remote_port() + * Called from qla2x00_reg_remote_port() */ void qlt_fc_port_added(struct scsi_qla_host *vha, fc_port_t *fcport) { @@ -874,7 +890,12 @@ void qlt_fc_port_added(struct scsi_qla_host *vha, fc_port_t *fcport) spin_unlock_irqrestore(&ha->hardware_lock, flags); } -void qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport) +/* + * max_gen - specifies maximum session generation + * at which this deletion requestion is still valid + */ +void +qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport, int max_gen) { struct qla_tgt *tgt = vha->vha_tgt.qla_tgt; struct qla_tgt_sess *sess; @@ -893,6 +914,15 @@ void qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport) return; } + if (max_gen - sess->generation < 0) { + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf092, + "Ignoring stale deletion request for se_sess %p / sess %p" + " for port %8phC, req_gen %d, sess_gen %d\n", + sess->se_sess, sess, sess->port_name, max_gen, + sess->generation); + return; + } + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf008, "qla_tgt_fc_port_deleted %p", sess); sess->local = 1; @@ -3970,7 +4000,7 @@ void qlt_logo_completion_handler(fc_port_t *fcport, int rc) { if (fcport->tgt_session) { if (rc != MBS_COMMAND_COMPLETE) { - ql_dbg(ql_dbg_tgt_mgt, fcport->vha, 0xf088, + ql_dbg(ql_dbg_tgt_mgt, fcport->vha, 0xf093, "%s: se_sess %p / sess %p from" " port %8phC loop_id %#04x s_id %02x:%02x:%02x" " LOGO failed: %#x\n", @@ -4099,6 +4129,7 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha, struct imm_ntfy_from_isp *iocb) { struct qla_tgt *tgt = vha->vha_tgt.qla_tgt; + struct qla_hw_data *ha = vha->hw; struct qla_tgt_sess *sess = NULL; uint64_t wwn; port_id_t port_id; @@ -4144,7 +4175,7 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha, * without acking, new one will get acked when session * deletion completes. */ - ql_log(ql_log_warn, sess->vha, 0xf089, + ql_log(ql_log_warn, sess->vha, 0xf094, "sess %p received double plogi.\n", sess); qlt_swap_imm_ntfy_iocb(iocb, &sess->tm_iocb); @@ -4201,7 +4232,7 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha, * PLOGI could finish. Will force him to re-try, * while last one finishes. */ - ql_log(ql_log_warn, sess->vha, 0xf090, + ql_log(ql_log_warn, sess->vha, 0xf095, "sess %p PRLI received, before plogi ack.\n", sess); qlt_send_term_imm_notif(vha, iocb, 1); @@ -4213,7 +4244,7 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha, * This shouldn't happen under normal circumstances, * since we have deleted the old session during PLOGI */ - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf091, + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf096, "PRLI (loop_id %#04x) for existing sess %p (loop_id %#04x)\n", sess->loop_id, sess, iocb->u.isp24.nport_handle); @@ -4224,7 +4255,14 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha, if (wd3_lo & BIT_7) sess->conf_compl_supported = 1; - res = 1; + } + res = 1; /* send notify ack */ + + /* Make session global (not used in fabric mode) */ + if (ha->current_topology != ISP_CFG_F) { + set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags); + set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags); + qla2xxx_wake_dpc(vha); } else { /* todo: else - create sess here. */ res = 1; /* send notify ack */ diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h index 165efb5cc6c1..2ceb60ffc5e9 100644 --- a/drivers/scsi/qla2xxx/qla_target.h +++ b/drivers/scsi/qla2xxx/qla_target.h @@ -919,6 +919,8 @@ struct qla_tgt_sess { unsigned char logout_completed; + int generation; + struct se_session *se_sess; struct scsi_qla_host *vha; struct qla_tgt *tgt; @@ -1086,7 +1088,7 @@ extern int qlt_lport_register(void *, u64, u64, u64, extern void qlt_lport_deregister(struct scsi_qla_host *); extern void qlt_unreg_sess(struct qla_tgt_sess *); extern void qlt_fc_port_added(struct scsi_qla_host *, fc_port_t *); -extern void qlt_fc_port_deleted(struct scsi_qla_host *, fc_port_t *); +extern void qlt_fc_port_deleted(struct scsi_qla_host *, fc_port_t *, int); extern int __init qlt_init(void); extern void qlt_exit(void); extern void qlt_update_vp_map(struct scsi_qla_host *, int); @@ -1163,5 +1165,6 @@ extern irqreturn_t qla83xx_msix_atio_q(int, void *); extern void qlt_83xx_iospace_config(struct qla_hw_data *); extern int qlt_free_qfull_cmds(struct scsi_qla_host *); extern void qlt_logo_completion_handler(fc_port_t *, int); +extern void qlt_do_generation_tick(struct scsi_qla_host *, int *); #endif /* __QLA_TARGET_H */ From d20ed91bb60ca54c42e3326251287ec51ed225a1 Mon Sep 17 00:00:00 2001 From: Alexei Potashnik Date: Tue, 14 Jul 2015 16:00:47 -0400 Subject: [PATCH 109/428] qla2xxx: disable scsi_transport_fc registration in target mode There are multiple reasons for disabling this: 1. It provides no functional benefit. We pretty much only get a few more sysfs entries for each port, but all that information is already available from /sys/kernel/debug/target/qla-session-X 2. It already only works in private-loop mode. By disabling we'll be getting more uniform behavior with fabric mode. 3. It creates complications for the new PLOGI handling mechanism: scsi_transport_fc port deletion timer could race with new session from initiator and cause logout after successful login. Cc: # v3.18+ Signed-off-by: Alexei Potashnik Signed-off-by: Himanshu Madhani Signed-off-by: Nicholas Bellinger --- drivers/scsi/qla2xxx/qla_init.c | 14 +++++++++++--- drivers/scsi/qla2xxx/qla_os.c | 3 ++- 2 files changed, 13 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 506621d814ab..11f2f3279eab 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -3340,8 +3340,7 @@ qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport) if (IS_QLAFX00(vha->hw)) { qla2x00_set_fcport_state(fcport, FCS_ONLINE); - qla2x00_reg_remote_port(vha, fcport); - return; + goto reg_port; } fcport->login_retry = 0; fcport->flags &= ~(FCF_LOGIN_NEEDED | FCF_ASYNC_SENT); @@ -3349,7 +3348,16 @@ qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport) qla2x00_set_fcport_state(fcport, FCS_ONLINE); qla2x00_iidma_fcport(vha, fcport); qla24xx_update_fcport_fcp_prio(vha, fcport); - qla2x00_reg_remote_port(vha, fcport); + +reg_port: + if (qla_ini_mode_enabled(vha)) + qla2x00_reg_remote_port(vha, fcport); + else { + /* + * Create target mode FC NEXUS in qla_target.c + */ + qlt_fc_port_added(vha, fcport); + } } /* diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index be6de2a1e36e..8a5cac8448c7 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -3235,7 +3235,8 @@ qla2x00_schedule_rport_del(struct scsi_qla_host *vha, fc_port_t *fcport, qla2xxx_wake_dpc(base_vha); } else { int now; - fc_remote_port_delete(rport); + if (rport) + fc_remote_port_delete(rport); qlt_do_generation_tick(vha, &now); qlt_fc_port_deleted(vha, fcport, now); } From e52a8b45b9c782937f74b701f8c656d4e5619eb5 Mon Sep 17 00:00:00 2001 From: Alexei Potashnik Date: Tue, 14 Jul 2015 16:00:48 -0400 Subject: [PATCH 110/428] qla2xxx: drop cmds/tmrs arrived while session is being deleted If a new initiator (different WWN) shows up on the same fcport, old initiator's session is scheduled for deletion. But there is a small window between it being marked with QLA_SESS_DELETION_IN_PROGRESS and qlt_unret_sess getting called when new session's commands will keep finding old session in the fcport map. This patch drops cmds/tmrs if they find session in the progress of being deleted. Cc: # v3.18+ Signed-off-by: Alexei Potashnik Acked-by: Quinn Tran Signed-off-by: Himanshu Madhani Signed-off-by: Nicholas Bellinger --- drivers/scsi/qla2xxx/qla_target.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 0b5bd9cd7f0d..b60f9075e9f7 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1477,6 +1477,11 @@ static void qlt_24xx_handle_abts(struct scsi_qla_host *vha, return; } + if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) { + qlt_24xx_send_abts_resp(vha, abts, FCP_TMF_REJECTED, false); + return; + } + rc = __qlt_24xx_handle_abts(vha, abts, sess); if (rc != 0) { ql_dbg(ql_dbg_tgt_mgt, vha, 0xf054, @@ -3768,6 +3773,16 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha, queue_work(qla_tgt_wq, &op->work); return 0; } + + /* Another WWN used to have our s_id. Our PLOGI scheduled its + * session deletion, but it's still in sess_del_work wq */ + if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) { + ql_dbg(ql_dbg_io, vha, 0x3061, + "New command while old session %p is being deleted\n", + sess); + return -EFAULT; + } + /* * Do kref_get() before returning + dropping qla_hw_data->hardware_lock. */ @@ -3931,6 +3946,9 @@ static int qlt_handle_task_mgmt(struct scsi_qla_host *vha, void *iocb) sizeof(struct atio_from_isp)); } + if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) + return -EFAULT; + return qlt_issue_task_mgmt(sess, unpacked_lun, fn, iocb, 0); } @@ -5603,6 +5621,11 @@ static void qlt_abort_work(struct qla_tgt *tgt, if (!sess) goto out_term; } else { + if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) { + sess = NULL; + goto out_term; + } + kref_get(&sess->se_sess->sess_kref); } @@ -5657,6 +5680,11 @@ static void qlt_tmr_work(struct qla_tgt *tgt, if (!sess) goto out_term; } else { + if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) { + sess = NULL; + goto out_term; + } + kref_get(&sess->se_sess->sess_kref); } From 7359df25a53386dd33c223672bbd12cb49d0ce4f Mon Sep 17 00:00:00 2001 From: Alexei Potashnik Date: Tue, 14 Jul 2015 16:00:49 -0400 Subject: [PATCH 111/428] qla2xxx: terminate exchange when command is aborted by LIO The newly introduced aborted_task TFO callback has to terminate exchange with QLogic driver, since command is being deleted and no status will be queued to the driver at a later point. This patch also moves the burden of releasing one cmd refcount to the aborted_task handler. Changed iSCSI aborted_task logic to satisfy the above requirement. Cc: # v3.18+ Signed-off-by: Alexei Potashnik Acked-by: Quinn Tran Signed-off-by: Himanshu Madhani Signed-off-by: Nicholas Bellinger --- drivers/scsi/qla2xxx/qla_target.c | 35 +++++++++++++++--------------- drivers/scsi/qla2xxx/qla_target.h | 9 +------- drivers/scsi/qla2xxx/tcm_qla2xxx.c | 11 +--------- 3 files changed, 20 insertions(+), 35 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index b60f9075e9f7..58651ecbd88c 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1924,20 +1924,6 @@ static int qlt_pre_xmit_response(struct qla_tgt_cmd *cmd, struct qla_hw_data *ha = vha->hw; struct se_cmd *se_cmd = &cmd->se_cmd; - if (unlikely(cmd->aborted)) { - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf014, - "qla_target(%d): terminating exchange for aborted cmd=%p (se_cmd=%p, tag=%lld)", - vha->vp_idx, cmd, se_cmd, se_cmd->tag); - - cmd->state = QLA_TGT_STATE_ABORTED; - cmd->cmd_flags |= BIT_6; - - qlt_send_term_exchange(vha, cmd, &cmd->atio, 0); - - /* !! At this point cmd could be already freed !! */ - return QLA_TGT_PRE_XMIT_RESP_CMD_ABORTED; - } - prm->cmd = cmd; prm->tgt = tgt; prm->rq_result = scsi_status; @@ -2524,9 +2510,6 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type, res = qlt_pre_xmit_response(cmd, &prm, xmit_type, scsi_status, &full_req_cnt); if (unlikely(res != 0)) { - if (res == QLA_TGT_PRE_XMIT_RESP_CMD_ABORTED) - return 0; - return res; } @@ -3092,6 +3075,24 @@ static void qlt_chk_exch_leak_thresh_hold(struct scsi_qla_host *vha) } +void qlt_abort_cmd(struct qla_tgt_cmd *cmd) +{ + struct qla_tgt *tgt = cmd->tgt; + struct scsi_qla_host *vha = tgt->vha; + struct se_cmd *se_cmd = &cmd->se_cmd; + + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf014, + "qla_target(%d): terminating exchange for aborted cmd=%p " + "(se_cmd=%p, tag=%llu)", vha->vp_idx, cmd, &cmd->se_cmd, + se_cmd->tag); + + cmd->state = QLA_TGT_STATE_ABORTED; + cmd->cmd_flags |= BIT_6; + + qlt_send_term_exchange(vha, cmd, &cmd->atio, 0); +} +EXPORT_SYMBOL(qlt_abort_cmd); + void qlt_free_cmd(struct qla_tgt_cmd *cmd) { struct qla_tgt_sess *sess = cmd->sess; diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h index 2ceb60ffc5e9..bca584ae45b7 100644 --- a/drivers/scsi/qla2xxx/qla_target.h +++ b/drivers/scsi/qla2xxx/qla_target.h @@ -808,13 +808,6 @@ int qla2x00_wait_for_hba_online(struct scsi_qla_host *); #define FC_TM_REJECT 4 #define FC_TM_FAILED 5 -/* - * Error code of qlt_pre_xmit_response() meaning that cmd's exchange was - * terminated, so no more actions is needed and success should be returned - * to target. - */ -#define QLA_TGT_PRE_XMIT_RESP_CMD_ABORTED 0x1717 - #if (BITS_PER_LONG > 32) || defined(CONFIG_HIGHMEM64G) #define pci_dma_lo32(a) (a & 0xffffffff) #define pci_dma_hi32(a) ((((a) >> 16)>>16) & 0xffffffff) @@ -950,7 +943,6 @@ struct qla_tgt_cmd { unsigned int conf_compl_supported:1; unsigned int sg_mapped:1; unsigned int free_sg:1; - unsigned int aborted:1; /* Needed in case of SRR */ unsigned int write_data_transferred:1; unsigned int ctx_dsd_alloced:1; unsigned int q_full:1; @@ -1134,6 +1126,7 @@ static inline uint32_t sid_to_key(const uint8_t *s_id) extern void qlt_response_pkt_all_vps(struct scsi_qla_host *, response_t *); extern int qlt_rdy_to_xfer(struct qla_tgt_cmd *); extern int qlt_xmit_response(struct qla_tgt_cmd *, int, uint8_t); +extern void qlt_abort_cmd(struct qla_tgt_cmd *); extern void qlt_xmit_tm_rsp(struct qla_tgt_mgmt_cmd *); extern void qlt_free_mcmd(struct qla_tgt_mgmt_cmd *); extern void qlt_free_cmd(struct qla_tgt_cmd *cmd); diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index 4e242c757947..9224a06646e6 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -541,7 +541,6 @@ static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd) cmd->cmd_flags |= BIT_4; cmd->bufflen = se_cmd->data_length; cmd->dma_data_direction = target_reverse_dma_direction(se_cmd); - cmd->aborted = (se_cmd->transport_state & CMD_T_ABORTED); cmd->sg_cnt = se_cmd->t_data_nents; cmd->sg = se_cmd->t_data_sg; @@ -570,7 +569,6 @@ static int tcm_qla2xxx_queue_status(struct se_cmd *se_cmd) cmd->sg_cnt = 0; cmd->offset = 0; cmd->dma_data_direction = target_reverse_dma_direction(se_cmd); - cmd->aborted = (se_cmd->transport_state & CMD_T_ABORTED); if (cmd->cmd_flags & BIT_5) { pr_crit("Bit_5 already set for cmd = %p.\n", cmd); dump_stack(); @@ -635,14 +633,7 @@ static void tcm_qla2xxx_aborted_task(struct se_cmd *se_cmd) { struct qla_tgt_cmd *cmd = container_of(se_cmd, struct qla_tgt_cmd, se_cmd); - struct scsi_qla_host *vha = cmd->vha; - struct qla_hw_data *ha = vha->hw; - - if (!cmd->sg_mapped) - return; - - pci_unmap_sg(ha->pdev, cmd->sg, cmd->sg_cnt, cmd->dma_data_direction); - cmd->sg_mapped = 0; + qlt_abort_cmd(cmd); } static void tcm_qla2xxx_clear_sess_lookup(struct tcm_qla2xxx_lport *, From 417c20a9bdd1e876384127cf096d8ae8b559066c Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Wed, 22 Jul 2015 00:24:09 -0700 Subject: [PATCH 112/428] iscsi-target: Fix use-after-free during TPG session shutdown This patch fixes a use-after-free bug in iscsit_release_sessions_for_tpg() where se_portal_group->session_lock was incorrectly released/re-acquired while walking the active se_portal_group->tpg_sess_list. The can result in a NULL pointer dereference when iscsit_close_session() shutdown happens in the normal path asynchronously to this code, causing a bogus dereference of an already freed list entry to occur. To address this bug, walk the session list checking for the same state as before, but move entries to a local list to avoid dropping the lock while walking the active list. As before, signal using iscsi_session->session_restatement=1 for those list entries to be released locally by iscsit_free_session() code. Reported-by: Sunilkumar Nadumuttlu Cc: Sunilkumar Nadumuttlu Cc: # v3.1+ Signed-off-by: Nicholas Bellinger --- drivers/target/iscsi/iscsi_target.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 4e68b62193ed..afab32376126 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -4765,6 +4765,7 @@ int iscsit_release_sessions_for_tpg(struct iscsi_portal_group *tpg, int force) struct iscsi_session *sess; struct se_portal_group *se_tpg = &tpg->tpg_se_tpg; struct se_session *se_sess, *se_sess_tmp; + LIST_HEAD(free_list); int session_count = 0; spin_lock_bh(&se_tpg->session_lock); @@ -4786,15 +4787,18 @@ int iscsit_release_sessions_for_tpg(struct iscsi_portal_group *tpg, int force) } atomic_set(&sess->session_reinstatement, 1); spin_unlock(&sess->conn_lock); - spin_unlock_bh(&se_tpg->session_lock); - iscsit_free_session(sess); - spin_lock_bh(&se_tpg->session_lock); - - session_count++; + list_move_tail(&se_sess->sess_list, &free_list); } spin_unlock_bh(&se_tpg->session_lock); + list_for_each_entry_safe(se_sess, se_sess_tmp, &free_list, sess_list) { + sess = (struct iscsi_session *)se_sess->fabric_sess_ptr; + + iscsit_free_session(sess); + session_count++; + } + pr_debug("Released %d iSCSI Session(s) from Target Portal" " Group: %hu\n", session_count, tpg->tpgt); return 0; From e54198657b65625085834847ab6271087323ffea Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Wed, 22 Jul 2015 23:14:19 -0700 Subject: [PATCH 113/428] iscsi-target: Fix iscsit_start_kthreads failure OOPs This patch fixes a regression introduced with the following commit in v4.0-rc1 code, where a iscsit_start_kthreads() failure triggers a NULL pointer dereference OOPs: commit 88dcd2dab5c23b1c9cfc396246d8f476c872f0ca Author: Nicholas Bellinger Date: Thu Feb 26 22:19:15 2015 -0800 iscsi-target: Convert iscsi_thread_set usage to kthread.h To address this bug, move iscsit_start_kthreads() immediately preceeding the transmit of last login response, before signaling a successful transition into full-feature-phase within existing iscsi_target_do_tx_login_io() logic. This ensures that no target-side resource allocation failures can occur after the final login response has been successfully sent. Also, it adds a iscsi_conn->rx_login_comp to allow the RX thread to sleep to prevent other socket related failures until the final iscsi_post_login_handler() call is able to complete. Cc: Sagi Grimberg Cc: # v3.10+ Signed-off-by: Nicholas Bellinger --- drivers/target/iscsi/iscsi_target.c | 18 +++++++-- drivers/target/iscsi/iscsi_target_login.c | 45 +++++++++-------------- drivers/target/iscsi/iscsi_target_login.h | 3 +- drivers/target/iscsi/iscsi_target_nego.c | 34 ++++++++++++++++- include/target/iscsi/iscsi_target_core.h | 1 + 5 files changed, 68 insertions(+), 33 deletions(-) diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index afab32376126..202a42858f25 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -3998,7 +3998,13 @@ get_immediate: } transport_err: - iscsit_take_action_for_connection_exit(conn); + /* + * Avoid the normal connection failure code-path if this connection + * is still within LOGIN mode, and iscsi_np process context is + * responsible for cleaning up the early connection failure. + */ + if (conn->conn_state != TARG_CONN_STATE_IN_LOGIN) + iscsit_take_action_for_connection_exit(conn); out: return 0; } @@ -4082,7 +4088,7 @@ reject: int iscsi_target_rx_thread(void *arg) { - int ret; + int ret, rc; u8 buffer[ISCSI_HDR_LEN], opcode; u32 checksum = 0, digest = 0; struct iscsi_conn *conn = arg; @@ -4092,10 +4098,16 @@ int iscsi_target_rx_thread(void *arg) * connection recovery / failure event can be triggered externally. */ allow_signal(SIGINT); + /* + * Wait for iscsi_post_login_handler() to complete before allowing + * incoming iscsi/tcp socket I/O, and/or failing the connection. + */ + rc = wait_for_completion_interruptible(&conn->rx_login_comp); + if (rc < 0) + return 0; if (conn->conn_transport->transport_type == ISCSI_INFINIBAND) { struct completion comp; - int rc; init_completion(&comp); rc = wait_for_completion_interruptible(&comp); diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 3d0fe4ff5590..7e8f65e5448f 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -82,6 +82,7 @@ static struct iscsi_login *iscsi_login_init_conn(struct iscsi_conn *conn) init_completion(&conn->conn_logout_comp); init_completion(&conn->rx_half_close_comp); init_completion(&conn->tx_half_close_comp); + init_completion(&conn->rx_login_comp); spin_lock_init(&conn->cmd_lock); spin_lock_init(&conn->conn_usage_lock); spin_lock_init(&conn->immed_queue_lock); @@ -644,7 +645,7 @@ static void iscsi_post_login_start_timers(struct iscsi_conn *conn) iscsit_start_nopin_timer(conn); } -static int iscsit_start_kthreads(struct iscsi_conn *conn) +int iscsit_start_kthreads(struct iscsi_conn *conn) { int ret = 0; @@ -679,6 +680,7 @@ static int iscsit_start_kthreads(struct iscsi_conn *conn) return 0; out_tx: + send_sig(SIGINT, conn->tx_thread, 1); kthread_stop(conn->tx_thread); conn->tx_thread_active = false; out_bitmap: @@ -689,7 +691,7 @@ out_bitmap: return ret; } -int iscsi_post_login_handler( +void iscsi_post_login_handler( struct iscsi_np *np, struct iscsi_conn *conn, u8 zero_tsih) @@ -699,7 +701,6 @@ int iscsi_post_login_handler( struct se_session *se_sess = sess->se_sess; struct iscsi_portal_group *tpg = sess->tpg; struct se_portal_group *se_tpg = &tpg->tpg_se_tpg; - int rc; iscsit_inc_conn_usage_count(conn); @@ -739,10 +740,6 @@ int iscsi_post_login_handler( sess->sess_ops->InitiatorName); spin_unlock_bh(&sess->conn_lock); - rc = iscsit_start_kthreads(conn); - if (rc) - return rc; - iscsi_post_login_start_timers(conn); /* * Determine CPU mask to ensure connection's RX and TX kthreads @@ -751,15 +748,20 @@ int iscsi_post_login_handler( iscsit_thread_get_cpumask(conn); conn->conn_rx_reset_cpumask = 1; conn->conn_tx_reset_cpumask = 1; - + /* + * Wakeup the sleeping iscsi_target_rx_thread() now that + * iscsi_conn is in TARG_CONN_STATE_LOGGED_IN state. + */ + complete(&conn->rx_login_comp); iscsit_dec_conn_usage_count(conn); + if (stop_timer) { spin_lock_bh(&se_tpg->session_lock); iscsit_stop_time2retain_timer(sess); spin_unlock_bh(&se_tpg->session_lock); } iscsit_dec_session_usage_count(sess); - return 0; + return; } iscsi_set_session_parameters(sess->sess_ops, conn->param_list, 1); @@ -800,10 +802,6 @@ int iscsi_post_login_handler( " iSCSI Target Portal Group: %hu\n", tpg->nsessions, tpg->tpgt); spin_unlock_bh(&se_tpg->session_lock); - rc = iscsit_start_kthreads(conn); - if (rc) - return rc; - iscsi_post_login_start_timers(conn); /* * Determine CPU mask to ensure connection's RX and TX kthreads @@ -812,10 +810,12 @@ int iscsi_post_login_handler( iscsit_thread_get_cpumask(conn); conn->conn_rx_reset_cpumask = 1; conn->conn_tx_reset_cpumask = 1; - + /* + * Wakeup the sleeping iscsi_target_rx_thread() now that + * iscsi_conn is in TARG_CONN_STATE_LOGGED_IN state. + */ + complete(&conn->rx_login_comp); iscsit_dec_conn_usage_count(conn); - - return 0; } static void iscsi_handle_login_thread_timeout(unsigned long data) @@ -1380,23 +1380,12 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) if (ret < 0) goto new_sess_out; - if (!conn->sess) { - pr_err("struct iscsi_conn session pointer is NULL!\n"); - goto new_sess_out; - } - iscsi_stop_login_thread_timer(np); - if (signal_pending(current)) - goto new_sess_out; - if (ret == 1) { tpg_np = conn->tpg_np; - ret = iscsi_post_login_handler(np, conn, zero_tsih); - if (ret < 0) - goto new_sess_out; - + iscsi_post_login_handler(np, conn, zero_tsih); iscsit_deaccess_np(np, tpg, tpg_np); } diff --git a/drivers/target/iscsi/iscsi_target_login.h b/drivers/target/iscsi/iscsi_target_login.h index 1c7358081533..57aa0d0fd820 100644 --- a/drivers/target/iscsi/iscsi_target_login.h +++ b/drivers/target/iscsi/iscsi_target_login.h @@ -12,7 +12,8 @@ extern int iscsit_accept_np(struct iscsi_np *, struct iscsi_conn *); extern int iscsit_get_login_rx(struct iscsi_conn *, struct iscsi_login *); extern int iscsit_put_login_tx(struct iscsi_conn *, struct iscsi_login *, u32); extern void iscsit_free_conn(struct iscsi_np *, struct iscsi_conn *); -extern int iscsi_post_login_handler(struct iscsi_np *, struct iscsi_conn *, u8); +extern int iscsit_start_kthreads(struct iscsi_conn *); +extern void iscsi_post_login_handler(struct iscsi_np *, struct iscsi_conn *, u8); extern void iscsi_target_login_sess_out(struct iscsi_conn *, struct iscsi_np *, bool, bool); extern int iscsi_target_login_thread(void *); diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c index 8c02fa34716f..f9cde9141836 100644 --- a/drivers/target/iscsi/iscsi_target_nego.c +++ b/drivers/target/iscsi/iscsi_target_nego.c @@ -17,6 +17,7 @@ ******************************************************************************/ #include +#include #include #include #include @@ -361,10 +362,24 @@ static int iscsi_target_do_tx_login_io(struct iscsi_conn *conn, struct iscsi_log ntohl(login_rsp->statsn), login->rsp_length); padding = ((-login->rsp_length) & 3); + /* + * Before sending the last login response containing the transition + * bit for full-feature-phase, go ahead and start up TX/RX threads + * now to avoid potential resource allocation failures after the + * final login response has been sent. + */ + if (login->login_complete) { + int rc = iscsit_start_kthreads(conn); + if (rc) { + iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR, + ISCSI_LOGIN_STATUS_NO_RESOURCES); + return -1; + } + } if (conn->conn_transport->iscsit_put_login_tx(conn, login, login->rsp_length + padding) < 0) - return -1; + goto err; login->rsp_length = 0; mutex_lock(&sess->cmdsn_mutex); @@ -373,6 +388,23 @@ static int iscsi_target_do_tx_login_io(struct iscsi_conn *conn, struct iscsi_log mutex_unlock(&sess->cmdsn_mutex); return 0; + +err: + if (login->login_complete) { + if (conn->rx_thread && conn->rx_thread_active) { + send_sig(SIGINT, conn->rx_thread, 1); + kthread_stop(conn->rx_thread); + } + if (conn->tx_thread && conn->tx_thread_active) { + send_sig(SIGINT, conn->tx_thread, 1); + kthread_stop(conn->tx_thread); + } + spin_lock(&iscsit_global->ts_bitmap_lock); + bitmap_release_region(iscsit_global->ts_bitmap, conn->bitmap_id, + get_order(1)); + spin_unlock(&iscsit_global->ts_bitmap_lock); + } + return -1; } static void iscsi_target_sk_data_ready(struct sock *sk) diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index 34117b8b72e4..0aedbb2c10e0 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -595,6 +595,7 @@ struct iscsi_conn { int bitmap_id; int rx_thread_active; struct task_struct *rx_thread; + struct completion rx_login_comp; int tx_thread_active; struct task_struct *tx_thread; /* list_head for session connection list */ From 007d038bdf95ccfe2491d0078be54040d110fd06 Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Thu, 23 Jul 2015 22:30:31 +0000 Subject: [PATCH 114/428] iscsi-target: Fix iser explicit logout TX kthread leak This patch fixes a regression introduced with the following commit in v4.0-rc1 code, where an explicit iser-target logout would result in ->tx_thread_active being incorrectly cleared by the logout post handler, and subsequent TX kthread leak: commit 88dcd2dab5c23b1c9cfc396246d8f476c872f0ca Author: Nicholas Bellinger Date: Thu Feb 26 22:19:15 2015 -0800 iscsi-target: Convert iscsi_thread_set usage to kthread.h To address this bug, change iscsit_logout_post_handler_closesession() and iscsit_logout_post_handler_samecid() to only cmpxchg() on ->tx_thread_active for traditional iscsi/tcp connections. This is required because iscsi/tcp connections are invoking logout post handler logic directly from TX kthread context, while iser connections are invoking logout post handler logic from a seperate workqueue context. Cc: Sagi Grimberg Cc: # v3.10+ Signed-off-by: Nicholas Bellinger --- drivers/target/iscsi/iscsi_target.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 202a42858f25..cd77a064c772 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -4544,7 +4544,18 @@ static void iscsit_logout_post_handler_closesession( struct iscsi_conn *conn) { struct iscsi_session *sess = conn->sess; - int sleep = cmpxchg(&conn->tx_thread_active, true, false); + int sleep = 1; + /* + * Traditional iscsi/tcp will invoke this logic from TX thread + * context during session logout, so clear tx_thread_active and + * sleep if iscsit_close_connection() has not already occured. + * + * Since iser-target invokes this logic from it's own workqueue, + * always sleep waiting for RX/TX thread shutdown to complete + * within iscsit_close_connection(). + */ + if (conn->conn_transport->transport_type == ISCSI_TCP) + sleep = cmpxchg(&conn->tx_thread_active, true, false); atomic_set(&conn->conn_logout_remove, 0); complete(&conn->conn_logout_comp); @@ -4558,7 +4569,10 @@ static void iscsit_logout_post_handler_closesession( static void iscsit_logout_post_handler_samecid( struct iscsi_conn *conn) { - int sleep = cmpxchg(&conn->tx_thread_active, true, false); + int sleep = 1; + + if (conn->conn_transport->transport_type == ISCSI_TCP) + sleep = cmpxchg(&conn->tx_thread_active, true, false); atomic_set(&conn->conn_logout_remove, 0); complete(&conn->conn_logout_comp); From ce9a9fc20a78ad1e5222fae3a83d105f2d2fb9b9 Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Fri, 24 Jul 2015 02:29:55 +0000 Subject: [PATCH 115/428] iser-target: Fix REJECT CM event use-after-free OOPs This patch fixes a bug in iser-target code where the REJECT CM event handler code currently performs a isert_put_conn() for the final isert_conn->kref put, while iscsi_np process context is still blocked in isert_get_login_rx(). Once isert_get_login_rx() is awoking due to login timeout, iscsi_np process context will attempt to invoke iscsi_target_login_sess_out() to cleanup iscsi_conn as expected, and calls isert_wait_conn() + isert_free_conn() which triggers the use-after-free OOPs. To address this bug, move the kref_get_unless_zero() call from isert_connected_handler() into isert_connect_request() immediately preceeding isert_rdma_accept() to ensure the CM handler cleanup paths and isert_free_conn() are always operating with two refs. Cc: Sagi Grimberg Cc: # v3.10+ Signed-off-by: Nicholas Bellinger --- drivers/infiniband/ulp/isert/ib_isert.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 771700963127..d851e1828d6f 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -775,6 +775,17 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) ret = isert_rdma_post_recvl(isert_conn); if (ret) goto out_conn_dev; + /* + * Obtain the second reference now before isert_rdma_accept() to + * ensure that any initiator generated REJECT CM event that occurs + * asynchronously won't drop the last reference until the error path + * in iscsi_target_login_sess_out() does it's ->iscsit_free_conn() -> + * isert_free_conn() -> isert_put_conn() -> kref_put(). + */ + if (!kref_get_unless_zero(&isert_conn->kref)) { + isert_warn("conn %p connect_release is running\n", isert_conn); + goto out_conn_dev; + } ret = isert_rdma_accept(isert_conn); if (ret) @@ -836,11 +847,6 @@ isert_connected_handler(struct rdma_cm_id *cma_id) isert_info("conn %p\n", isert_conn); - if (!kref_get_unless_zero(&isert_conn->kref)) { - isert_warn("conn %p connect_release is running\n", isert_conn); - return; - } - mutex_lock(&isert_conn->mutex); if (isert_conn->state != ISER_CONN_FULL_FEATURE) isert_conn->state = ISER_CONN_UP; From c4cfdd81c8fde84e2c75bc90533c7e1276937d3a Mon Sep 17 00:00:00 2001 From: Sebastian Herbszt Date: Mon, 20 Jul 2015 00:16:01 +0200 Subject: [PATCH 116/428] Documentation/target: Fix tcm_mod_builder.py build breakage Fix build breakage and set the protocol identifier based on the parameter. Fixes: 9ac8928e6a3e ("target: simplify the target template registration API") Fixes: e4aae5af810e ("target: change core_tpg_register prototype") Signed-off-by: Sebastian Herbszt Reviewed-by: Christoph Hellwig Signed-off-by: Nicholas Bellinger --- Documentation/target/tcm_mod_builder.py | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/Documentation/target/tcm_mod_builder.py b/Documentation/target/tcm_mod_builder.py index 949de191fcdc..cda56df9b8a7 100755 --- a/Documentation/target/tcm_mod_builder.py +++ b/Documentation/target/tcm_mod_builder.py @@ -199,7 +199,8 @@ def tcm_mod_build_configfs(proto_ident, fabric_mod_dir_var, fabric_mod_name): buf += "#include \n" buf += "#include \n" buf += "#include \n" - buf += "#include \n\n" + buf += "#include \n" + buf += "#include \n\n" buf += "#include \n" buf += "#include \n" buf += "#include \n" @@ -230,8 +231,14 @@ def tcm_mod_build_configfs(proto_ident, fabric_mod_dir_var, fabric_mod_name): buf += " }\n" buf += " tpg->" + fabric_mod_port + " = " + fabric_mod_port + ";\n" buf += " tpg->" + fabric_mod_port + "_tpgt = tpgt;\n\n" - buf += " ret = core_tpg_register(&" + fabric_mod_name + "_ops, wwn,\n" - buf += " &tpg->se_tpg, SCSI_PROTOCOL_SAS);\n" + + if proto_ident == "FC": + buf += " ret = core_tpg_register(wwn, &tpg->se_tpg, SCSI_PROTOCOL_FCP);\n" + elif proto_ident == "SAS": + buf += " ret = core_tpg_register(wwn, &tpg->se_tpg, SCSI_PROTOCOL_SAS);\n" + elif proto_ident == "iSCSI": + buf += " ret = core_tpg_register(wwn, &tpg->se_tpg, SCSI_PROTOCOL_ISCSI);\n" + buf += " if (ret < 0) {\n" buf += " kfree(tpg);\n" buf += " return NULL;\n" @@ -292,7 +299,7 @@ def tcm_mod_build_configfs(proto_ident, fabric_mod_dir_var, fabric_mod_name): buf += "static const struct target_core_fabric_ops " + fabric_mod_name + "_ops = {\n" buf += " .module = THIS_MODULE,\n" - buf += " .name = " + fabric_mod_name + ",\n" + buf += " .name = \"" + fabric_mod_name + "\",\n" buf += " .get_fabric_name = " + fabric_mod_name + "_get_fabric_name,\n" buf += " .tpg_get_wwn = " + fabric_mod_name + "_get_fabric_wwn,\n" buf += " .tpg_get_tag = " + fabric_mod_name + "_get_tag,\n" @@ -322,17 +329,17 @@ def tcm_mod_build_configfs(proto_ident, fabric_mod_dir_var, fabric_mod_name): buf += " .fabric_make_tpg = " + fabric_mod_name + "_make_tpg,\n" buf += " .fabric_drop_tpg = " + fabric_mod_name + "_drop_tpg,\n" buf += "\n" - buf += " .tfc_wwn_attrs = " + fabric_mod_name + "_wwn_attrs;\n" + buf += " .tfc_wwn_attrs = " + fabric_mod_name + "_wwn_attrs,\n" buf += "};\n\n" buf += "static int __init " + fabric_mod_name + "_init(void)\n" buf += "{\n" - buf += " return target_register_template(" + fabric_mod_name + "_ops);\n" + buf += " return target_register_template(&" + fabric_mod_name + "_ops);\n" buf += "};\n\n" buf += "static void __exit " + fabric_mod_name + "_exit(void)\n" buf += "{\n" - buf += " target_unregister_template(" + fabric_mod_name + "_ops);\n" + buf += " target_unregister_template(&" + fabric_mod_name + "_ops);\n" buf += "};\n\n" buf += "MODULE_DESCRIPTION(\"" + fabric_mod_name.upper() + " series fabric driver\");\n" From e053f96b1a00022b4e2c7ceb7ac0229646626507 Mon Sep 17 00:00:00 2001 From: Denis Carikli Date: Thu, 23 Jul 2015 10:31:12 +0200 Subject: [PATCH 117/428] ARM: dts: i.MX35: Fix can support. Since commit 3d42a379b6fa5b46058e3302b1802b29f64865bb ("can: flexcan: add 2nd clock to support imx53 and newer") the can driver requires a dt nodes to have a second clock. Add them to imx35 to fix probing the flex can driver on the respective platforms. Signed-off-by: Denis Carikli Cc: Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx35.dtsi | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm/boot/dts/imx35.dtsi b/arch/arm/boot/dts/imx35.dtsi index b6478e97d6a7..e6540b5cfa4c 100644 --- a/arch/arm/boot/dts/imx35.dtsi +++ b/arch/arm/boot/dts/imx35.dtsi @@ -286,8 +286,8 @@ can1: can@53fe4000 { compatible = "fsl,imx35-flexcan", "fsl,p1010-flexcan"; reg = <0x53fe4000 0x1000>; - clocks = <&clks 33>; - clock-names = "ipg"; + clocks = <&clks 33>, <&clks 33>; + clock-names = "ipg", "per"; interrupts = <43>; status = "disabled"; }; @@ -295,8 +295,8 @@ can2: can@53fe8000 { compatible = "fsl,imx35-flexcan", "fsl,p1010-flexcan"; reg = <0x53fe8000 0x1000>; - clocks = <&clks 34>; - clock-names = "ipg"; + clocks = <&clks 34>, <&clks 34>; + clock-names = "ipg", "per"; interrupts = <44>; status = "disabled"; }; From 18a912e9a832dcfc7db9e055c7e41701ff5f9e69 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Wed, 22 Jul 2015 10:43:22 +0300 Subject: [PATCH 118/428] ipv4: fib_select_default should match the prefix fib_trie starting from 4.1 can link fib aliases from different prefixes in same list. Make sure the alternative gateways are in same table and for same prefix (0) by checking tb_id and fa_slen. Fixes: 79e5ad2ceb00 ("fib_trie: Remove leaf_info") Signed-off-by: Julian Anastasov Signed-off-by: David S. Miller --- net/ipv4/fib_semantics.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index c7358ea4ae93..e1079583b8b7 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1207,12 +1207,17 @@ void fib_select_default(struct fib_result *res) struct fib_info *fi = NULL, *last_resort = NULL; struct hlist_head *fa_head = res->fa_head; struct fib_table *tb = res->table; + u8 slen = 32 - res->prefixlen; int order = -1, last_idx = -1; struct fib_alias *fa; hlist_for_each_entry_rcu(fa, fa_head, fa_list) { struct fib_info *next_fi = fa->fa_info; + if (fa->fa_slen != slen) + continue; + if (fa->tb_id != tb->tb_id) + continue; if (next_fi->fib_scope != res->scope || fa->fa_type != RTN_UNICAST) continue; From 2392debc2be721a7d5b907cbcbc0ebb858dead01 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Wed, 22 Jul 2015 10:43:23 +0300 Subject: [PATCH 119/428] ipv4: consider TOS in fib_select_default fib_select_default considers alternative routes only when res->fi is for the first alias in res->fa_head. In the common case this can happen only when the initial lookup matches the first alias with highest TOS value. This prevents the alternative routes to require specific TOS. This patch solves the problem as follows: - routes that require specific TOS should be returned by fib_select_default only when TOS matches, as already done in fib_table_lookup. This rule implies that depending on the TOS we can have many different lists of alternative gateways and we have to keep the last used gateway (fa_default) in first alias for the TOS instead of using single tb_default value. - as the aliases are ordered by many keys (TOS desc, fib_priority asc), we restrict the possible results to routes with matching TOS and lowest metric (fib_priority) and routes that match any TOS, again with lowest metric. For example, packet with TOS 8 can not use gw3 (not lowest metric), gw4 (different TOS) and gw6 (not lowest metric), all other gateways can be used: tos 8 via gw1 metric 2 <--- res->fa_head and res->fi tos 8 via gw2 metric 2 tos 8 via gw3 metric 3 tos 4 via gw4 tos 0 via gw5 tos 0 via gw6 metric 1 Reported-by: Hagen Paul Pfeifer Signed-off-by: Julian Anastasov Signed-off-by: David S. Miller --- include/net/ip_fib.h | 3 +-- net/ipv4/fib_lookup.h | 1 + net/ipv4/fib_semantics.c | 36 +++++++++++++++++++++++++----------- net/ipv4/fib_trie.c | 3 ++- net/ipv4/route.c | 2 +- 5 files changed, 30 insertions(+), 15 deletions(-) diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 49c142bdf01e..5fa643b4e891 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -183,7 +183,6 @@ __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh); struct fib_table { struct hlist_node tb_hlist; u32 tb_id; - int tb_default; int tb_num_default; struct rcu_head rcu; unsigned long *tb_data; @@ -290,7 +289,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb); int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, u8 tos, int oif, struct net_device *dev, struct in_device *idev, u32 *itag); -void fib_select_default(struct fib_result *res); +void fib_select_default(const struct flowi4 *flp, struct fib_result *res); #ifdef CONFIG_IP_ROUTE_CLASSID static inline int fib_num_tclassid_users(struct net *net) { diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index c6211ed60b03..9c02920725db 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -13,6 +13,7 @@ struct fib_alias { u8 fa_state; u8 fa_slen; u32 tb_id; + s16 fa_default; struct rcu_head rcu; }; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index e1079583b8b7..3a06586b170c 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1202,28 +1202,40 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event) } /* Must be invoked inside of an RCU protected region. */ -void fib_select_default(struct fib_result *res) +void fib_select_default(const struct flowi4 *flp, struct fib_result *res) { struct fib_info *fi = NULL, *last_resort = NULL; struct hlist_head *fa_head = res->fa_head; struct fib_table *tb = res->table; u8 slen = 32 - res->prefixlen; int order = -1, last_idx = -1; - struct fib_alias *fa; + struct fib_alias *fa, *fa1 = NULL; + u32 last_prio = res->fi->fib_priority; + u8 last_tos = 0; hlist_for_each_entry_rcu(fa, fa_head, fa_list) { struct fib_info *next_fi = fa->fa_info; if (fa->fa_slen != slen) continue; + if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos) + continue; if (fa->tb_id != tb->tb_id) continue; + if (next_fi->fib_priority > last_prio && + fa->fa_tos == last_tos) { + if (last_tos) + continue; + break; + } + if (next_fi->fib_flags & RTNH_F_DEAD) + continue; + last_tos = fa->fa_tos; + last_prio = next_fi->fib_priority; + if (next_fi->fib_scope != res->scope || fa->fa_type != RTN_UNICAST) continue; - - if (next_fi->fib_priority > res->fi->fib_priority) - break; if (!next_fi->fib_nh[0].nh_gw || next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK) continue; @@ -1233,10 +1245,11 @@ void fib_select_default(struct fib_result *res) if (!fi) { if (next_fi != res->fi) break; + fa1 = fa; } else if (!fib_detect_death(fi, order, &last_resort, - &last_idx, tb->tb_default)) { + &last_idx, fa1->fa_default)) { fib_result_assign(res, fi); - tb->tb_default = order; + fa1->fa_default = order; goto out; } fi = next_fi; @@ -1244,20 +1257,21 @@ void fib_select_default(struct fib_result *res) } if (order <= 0 || !fi) { - tb->tb_default = -1; + if (fa1) + fa1->fa_default = -1; goto out; } if (!fib_detect_death(fi, order, &last_resort, &last_idx, - tb->tb_default)) { + fa1->fa_default)) { fib_result_assign(res, fi); - tb->tb_default = order; + fa1->fa_default = order; goto out; } if (last_idx >= 0) fib_result_assign(res, last_resort); - tb->tb_default = last_idx; + fa1->fa_default = last_idx; out: return; } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 15d32612e3c6..81797e065b21 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1171,6 +1171,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) new_fa->fa_state = state & ~FA_S_ACCESSED; new_fa->fa_slen = fa->fa_slen; new_fa->tb_id = tb->tb_id; + new_fa->fa_default = -1; err = switchdev_fib_ipv4_add(key, plen, fi, new_fa->fa_tos, @@ -1222,6 +1223,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) new_fa->fa_state = 0; new_fa->fa_slen = slen; new_fa->tb_id = tb->tb_id; + new_fa->fa_default = -1; /* (Optionally) offload fib entry to switch hardware. */ err = switchdev_fib_ipv4_add(key, plen, fi, tos, cfg->fc_type, @@ -1990,7 +1992,6 @@ struct fib_table *fib_trie_table(u32 id, struct fib_table *alias) return NULL; tb->tb_id = id; - tb->tb_default = -1; tb->tb_num_default = 0; tb->tb_data = (alias ? alias->__data : tb->__data); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index d0362a2de3d3..e681b852ced1 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2176,7 +2176,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) if (!res.prefixlen && res.table->tb_num_default > 1 && res.type == RTN_UNICAST && !fl4->flowi4_oif) - fib_select_default(&res); + fib_select_default(fl4, &res); if (!fl4->saddr) fl4->saddr = FIB_RES_PREFSRC(net, res); From fe6bea7f1f3a09fc06d835446d34d3b3b6a543fb Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Tue, 21 Jul 2015 16:31:53 -0700 Subject: [PATCH 120/428] sch_plug: purge buffered packets during reset Otherwise the skbuff related structures are not correctly refcount'ed. Cc: Jamal Hadi Salim Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/sch_plug.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c index 89f8fcf73f18..ade9445a55ab 100644 --- a/net/sched/sch_plug.c +++ b/net/sched/sch_plug.c @@ -216,6 +216,7 @@ static struct Qdisc_ops plug_qdisc_ops __read_mostly = { .peek = qdisc_peek_head, .init = plug_init, .change = plug_change, + .reset = qdisc_reset_queue, .owner = THIS_MODULE, }; From 77e62da6e60c7772971f813f588d372a7f1a4167 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Tue, 21 Jul 2015 16:52:43 -0700 Subject: [PATCH 121/428] sch_choke: drop all packets in queue during reset Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/sch_choke.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index 93d5742dc7e0..6a783afe4960 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -385,6 +385,19 @@ static void choke_reset(struct Qdisc *sch) { struct choke_sched_data *q = qdisc_priv(sch); + while (q->head != q->tail) { + struct sk_buff *skb = q->tab[q->head]; + + q->head = (q->head + 1) & q->tab_mask; + if (!skb) + continue; + qdisc_qstats_backlog_dec(sch, skb); + --sch->q.qlen; + qdisc_drop(skb, sch); + } + + memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *)); + q->head = q->tail = 0; red_restart(&q->vars); } From 44008f0896ae205b02b0882dbf807f0de149efc4 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Sat, 25 Jul 2015 03:03:38 +0300 Subject: [PATCH 122/428] ALSA: hda - fix cs4210_spdif_automute() Smatch complains that we have nested checks for "spdif_present". It turns out the current behavior isn't correct, we should remove the first check and keep the second. Fixes: 1077a024812d ('ALSA: hda - Use generic parser for Cirrus codec driver') Signed-off-by: Dan Carpenter Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_cirrus.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c index 25ccf781fbe7..584a0343ab0c 100644 --- a/sound/pci/hda/patch_cirrus.c +++ b/sound/pci/hda/patch_cirrus.c @@ -999,9 +999,7 @@ static void cs4210_spdif_automute(struct hda_codec *codec, spec->spdif_present = spdif_present; /* SPDIF TX on/off */ - if (spdif_present) - snd_hda_set_pin_ctl(codec, spdif_pin, - spdif_present ? PIN_OUT : 0); + snd_hda_set_pin_ctl(codec, spdif_pin, spdif_present ? PIN_OUT : 0); cs_automute(codec); } From e9c28e16a0b7071c88a206ad8ce0c73f6605bba7 Mon Sep 17 00:00:00 2001 From: Woodrow Shen Date: Sat, 25 Jul 2015 10:36:16 +0800 Subject: [PATCH 123/428] ALSA: hda - Fix the headset mic that will not work on Dell desktop machine When the headset was plugged in the Dell desktop, the mic of headset can't be detected and workable. According to the alsa-info, we found the differece between alsa and init_pin_configs on the machine, so we need to add the pin configs to make headset work. Codec: Realtek ALC3234 Vendor Id: 0x10ec0255 Subsystem Id: 0x102806bb BugLink: https://bugs.launchpad.net/bugs/1477900 Signed-off-by: Woodrow Shen Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 742fc626f9e1..d94c0e33f58d 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5472,6 +5472,28 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x1d, 0x4054c029}, {0x1e, 0x411111f0}, {0x21, 0x0221103f}), + SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, + {0x12, 0x40000000}, + {0x14, 0x90170150}, + {0x17, 0x411111f0}, + {0x18, 0x411111f0}, + {0x19, 0x411111f0}, + {0x1a, 0x411111f0}, + {0x1b, 0x02011020}, + {0x1d, 0x4054c029}, + {0x1e, 0x411111f0}, + {0x21, 0x0221105f}), + SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, + {0x12, 0x40000000}, + {0x14, 0x90170110}, + {0x17, 0x411111f0}, + {0x18, 0x411111f0}, + {0x19, 0x411111f0}, + {0x1a, 0x411111f0}, + {0x1b, 0x01014020}, + {0x1d, 0x4054c029}, + {0x1e, 0x411111f0}, + {0x21, 0x0221101f}), SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, {0x12, 0x90a60160}, {0x14, 0x90170120}, From cc9f4daa638e660f7a910b8094122561470ac331 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Wed, 22 Jul 2015 12:23:20 +0300 Subject: [PATCH 124/428] cgroup: net_cls: fix false-positive "suspicious RCU usage" In dev_queue_xmit() net_cls protected with rcu-bh. [ 270.730026] =============================== [ 270.730029] [ INFO: suspicious RCU usage. ] [ 270.730033] 4.2.0-rc3+ #2 Not tainted [ 270.730036] ------------------------------- [ 270.730040] include/linux/cgroup.h:353 suspicious rcu_dereference_check() usage! [ 270.730041] other info that might help us debug this: [ 270.730043] rcu_scheduler_active = 1, debug_locks = 1 [ 270.730045] 2 locks held by dhclient/748: [ 270.730046] #0: (rcu_read_lock_bh){......}, at: [] __dev_queue_xmit+0x50/0x960 [ 270.730085] #1: (&qdisc_tx_lock){+.....}, at: [] __dev_queue_xmit+0x240/0x960 [ 270.730090] stack backtrace: [ 270.730096] CPU: 0 PID: 748 Comm: dhclient Not tainted 4.2.0-rc3+ #2 [ 270.730098] Hardware name: OpenStack Foundation OpenStack Nova, BIOS Bochs 01/01/2011 [ 270.730100] 0000000000000001 ffff8800bafeba58 ffffffff817ad487 0000000000000007 [ 270.730103] ffff880232a0a780 ffff8800bafeba88 ffffffff810ca4f2 ffff88022fb23e00 [ 270.730105] ffff880232a0a780 ffff8800bafebb68 ffff8800bafebb68 ffff8800bafebaa8 [ 270.730108] Call Trace: [ 270.730121] [] dump_stack+0x4c/0x65 [ 270.730148] [] lockdep_rcu_suspicious+0xe2/0x120 [ 270.730153] [] task_cls_state+0x92/0xa0 [ 270.730158] [] cls_cgroup_classify+0x4f/0x120 [cls_cgroup] [ 270.730164] [] tc_classify_compat+0x74/0xc0 [ 270.730166] [] tc_classify+0x33/0x90 [ 270.730170] [] htb_enqueue+0xaa/0x4a0 [sch_htb] [ 270.730172] [] __dev_queue_xmit+0x306/0x960 [ 270.730174] [] ? __dev_queue_xmit+0x50/0x960 [ 270.730176] [] dev_queue_xmit_sk+0x13/0x20 [ 270.730185] [] dev_queue_xmit+0x10/0x20 [ 270.730187] [] packet_snd.isra.62+0x54c/0x760 [ 270.730190] [] packet_sendmsg+0x2f5/0x3f0 [ 270.730203] [] ? sock_def_readable+0x5/0x190 [ 270.730210] [] ? _raw_spin_unlock+0x2b/0x40 [ 270.730216] [] ? unix_dgram_sendmsg+0x5cc/0x640 [ 270.730219] [] sock_sendmsg+0x47/0x50 [ 270.730221] [] sock_write_iter+0x7f/0xd0 [ 270.730232] [] __vfs_write+0xa7/0xf0 [ 270.730234] [] vfs_write+0xb8/0x190 [ 270.730236] [] SyS_write+0x52/0xb0 [ 270.730239] [] entry_SYSCALL_64_fastpath+0x12/0x76 Signed-off-by: Konstantin Khlebnikov Signed-off-by: David S. Miller --- net/core/netclassid_cgroup.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c index 1f2a126f4ffa..6441f47b1a8f 100644 --- a/net/core/netclassid_cgroup.c +++ b/net/core/netclassid_cgroup.c @@ -23,7 +23,8 @@ static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state struct cgroup_cls_state *task_cls_state(struct task_struct *p) { - return css_cls_state(task_css(p, net_cls_cgrp_id)); + return css_cls_state(task_css_check(p, net_cls_cgrp_id, + rcu_read_lock_bh_held())); } EXPORT_SYMBOL_GPL(task_cls_state); From 548aedac5128e4bb256bab5c8e1db88e626697fc Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Mon, 13 Jul 2015 17:44:14 -0700 Subject: [PATCH 125/428] f2fs: handle error cases in move_encrypted_block This patch fixes some missing error handlers. Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/gc.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index e1e73617d13b..883a841dfc6d 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -556,27 +556,34 @@ static void move_encrypted_block(struct inode *inode, block_t bidx) if (!fio.encrypted_page) goto put_out; - f2fs_submit_page_bio(&fio); - - /* allocate block address */ - f2fs_wait_on_page_writeback(dn.node_page, NODE); - - allocate_data_block(fio.sbi, NULL, fio.blk_addr, - &fio.blk_addr, &sum, CURSEG_COLD_DATA); - dn.data_blkaddr = fio.blk_addr; + err = f2fs_submit_page_bio(&fio); + if (err) + goto put_page_out; /* write page */ lock_page(fio.encrypted_page); + + if (unlikely(!PageUptodate(fio.encrypted_page))) + goto put_page_out; + if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi))) + goto put_page_out; + set_page_writeback(fio.encrypted_page); + + /* allocate block address */ + f2fs_wait_on_page_writeback(dn.node_page, NODE); + allocate_data_block(fio.sbi, NULL, fio.blk_addr, + &fio.blk_addr, &sum, CURSEG_COLD_DATA); fio.rw = WRITE_SYNC; f2fs_submit_page_mbio(&fio); + dn.data_blkaddr = fio.blk_addr; set_data_blkaddr(&dn); f2fs_update_extent_cache(&dn); set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE); if (page->index == 0) set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN); - +put_page_out: f2fs_put_page(fio.encrypted_page, 1); put_out: f2fs_put_dnode(&dn); From 6282adbf932c226f76e1b83e074448c79976fe75 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Sat, 25 Jul 2015 00:29:17 -0700 Subject: [PATCH 126/428] f2fs: call set_page_dirty to attach i_wb for cgroup The cgroup attaches inode->i_wb via mark_inode_dirty and when set_page_writeback is called, __inc_wb_stat() updates i_wb's stat. So, we need to explicitly call set_page_dirty->__mark_inode_dirty in prior to any writebacking pages. This patch should resolve the following kernel panic reported by Andreas Reis. https://bugzilla.kernel.org/show_bug.cgi?id=101801 --- Comment #2 from Andreas Reis --- BUG: unable to handle kernel NULL pointer dereference at 00000000000000a8 IP: [] __percpu_counter_add+0x1a/0x90 PGD 2951ff067 PUD 2df43f067 PMD 0 Oops: 0000 [#1] PREEMPT SMP Modules linked in: CPU: 7 PID: 10356 Comm: gcc Tainted: G W 4.2.0-1-cu #1 Hardware name: Gigabyte Technology Co., Ltd. G1.Sniper M5/G1.Sniper M5, BIOS T01 02/03/2015 task: ffff880295044f80 ti: ffff880295140000 task.ti: ffff880295140000 RIP: 0010:[] [] __percpu_counter_add+0x1a/0x90 RSP: 0018:ffff880295143ac8 EFLAGS: 00010082 RAX: 0000000000000003 RBX: ffffea000a526d40 RCX: 0000000000000001 RDX: 0000000000000020 RSI: 0000000000000001 RDI: 0000000000000088 RBP: ffff880295143ae8 R08: 0000000000000000 R09: ffff88008f69bb30 R10: 00000000fffffffa R11: 0000000000000000 R12: 0000000000000088 R13: 0000000000000001 R14: ffff88041d099000 R15: ffff880084a205d0 FS: 00007f8549374700(0000) GS:ffff88042f3c0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000a8 CR3: 000000033e1d5000 CR4: 00000000001406e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Stack: 0000000000000000 ffffea000a526d40 ffff880084a20738 ffff880084a20750 ffff880295143b48 ffffffff811cc91e ffff880000000000 0000000000000296 0000000000000000 ffff880417090198 0000000000000000 ffffea000a526d40 Call Trace: [] __test_set_page_writeback+0xde/0x1d0 [] do_write_data_page+0xe7/0x3a0 [] gc_data_segment+0x5aa/0x640 [] do_garbage_collect+0x138/0x150 [] f2fs_gc+0x1be/0x3e0 [] f2fs_balance_fs+0x81/0x90 [] f2fs_unlink+0x47/0x1d0 [] vfs_unlink+0x109/0x1b0 [] do_unlinkat+0x287/0x2c0 [] SyS_unlink+0x16/0x20 [] entry_SYSCALL_64_fastpath+0x12/0x71 Code: 41 5e 5d c3 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 55 48 89 e5 41 55 49 89 f5 41 54 49 89 fc 53 48 83 ec 08 65 ff 05 e6 d9 b6 7e <48> 8b 47 20 48 63 ca 65 8b 18 48 63 db 48 01 f3 48 39 cb 7d 0a RIP [] __percpu_counter_add+0x1a/0x90 RSP CR2: 00000000000000a8 ---[ end trace 5132449a58ed93a3 ]--- note: gcc[10356] exited with preempt_count 2 Signed-off-by: Jaegeuk Kim --- fs/f2fs/data.c | 2 -- fs/f2fs/file.c | 7 ++++--- fs/f2fs/gc.c | 7 ++++++- fs/f2fs/inline.c | 2 ++ fs/f2fs/segment.c | 1 + 5 files changed, 13 insertions(+), 6 deletions(-) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 9bedfa8dd3a5..f71e19a9dd3c 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -2072,8 +2072,6 @@ static int f2fs_set_data_page_dirty(struct page *page) return 1; } - mark_inode_dirty(inode); - if (!PageDirty(page)) { __set_page_dirty_nobuffers(page); update_dirty_page(inode, page); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index ada2a3dd701a..b0f38c3b37f4 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1331,12 +1331,13 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp) if (ret) return ret; - if (f2fs_is_atomic_file(inode)) + if (f2fs_is_atomic_file(inode)) { + clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); commit_inmem_pages(inode, false); + } ret = f2fs_sync_file(filp, 0, LONG_MAX, 0); mnt_drop_write_file(filp); - clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); return ret; } @@ -1387,8 +1388,8 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp) f2fs_balance_fs(F2FS_I_SB(inode)); if (f2fs_is_atomic_file(inode)) { - commit_inmem_pages(inode, false); clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); + commit_inmem_pages(inode, false); } if (f2fs_is_volatile_file(inode)) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 883a841dfc6d..22fb5ef37966 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -568,6 +568,11 @@ static void move_encrypted_block(struct inode *inode, block_t bidx) if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi))) goto put_page_out; + set_page_dirty(fio.encrypted_page); + f2fs_wait_on_page_writeback(fio.encrypted_page, META); + if (clear_page_dirty_for_io(fio.encrypted_page)) + dec_page_count(fio.sbi, F2FS_DIRTY_META); + set_page_writeback(fio.encrypted_page); /* allocate block address */ @@ -612,8 +617,8 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type) .page = page, .encrypted_page = NULL, }; + set_page_dirty(page); f2fs_wait_on_page_writeback(page, DATA); - if (clear_page_dirty_for_io(page)) inode_dec_dirty_pages(inode); set_cold_data(page); diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 38e75fb1e488..a13ffcc32992 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -141,6 +141,8 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page) kunmap_atomic(dst_addr); SetPageUptodate(page); no_update: + set_page_dirty(page); + /* clear dirty state */ dirty = clear_page_dirty_for_io(page); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 1eb343768781..61b97f9cb9f6 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -257,6 +257,7 @@ void commit_inmem_pages(struct inode *inode, bool abort) if (!abort) { lock_page(cur->page); if (cur->page->mapping == inode->i_mapping) { + set_page_dirty(cur->page); f2fs_wait_on_page_writeback(cur->page, DATA); if (clear_page_dirty_for_io(cur->page)) inode_dec_dirty_pages(inode); From a153790a788392e75d37262a9c5960d1d91ddb7e Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 25 Jul 2015 11:22:03 +0200 Subject: [PATCH 127/428] ARM: nomadik: disable UART0 on Nomadik boards The UART0 is not used on these boards, yet active and blocking other use. Fix this by disabling UART0 and setting port aliases to maintain port enumeration to userspace. Signed-off-by: Linus Walleij Signed-off-by: Olof Johansson --- arch/arm/boot/dts/ste-nomadik-nhk15.dts | 1 + arch/arm/boot/dts/ste-nomadik-s8815.dts | 4 ++++ arch/arm/boot/dts/ste-nomadik-stn8815.dtsi | 1 + 3 files changed, 6 insertions(+) diff --git a/arch/arm/boot/dts/ste-nomadik-nhk15.dts b/arch/arm/boot/dts/ste-nomadik-nhk15.dts index 3d0b8755caee..3d25dba143a5 100644 --- a/arch/arm/boot/dts/ste-nomadik-nhk15.dts +++ b/arch/arm/boot/dts/ste-nomadik-nhk15.dts @@ -17,6 +17,7 @@ }; aliases { + serial1 = &uart1; stmpe-i2c0 = &stmpe0; stmpe-i2c1 = &stmpe1; }; diff --git a/arch/arm/boot/dts/ste-nomadik-s8815.dts b/arch/arm/boot/dts/ste-nomadik-s8815.dts index 85d3b95dfdba..3c140d05f796 100644 --- a/arch/arm/boot/dts/ste-nomadik-s8815.dts +++ b/arch/arm/boot/dts/ste-nomadik-s8815.dts @@ -15,6 +15,10 @@ bootargs = "root=/dev/ram0 console=ttyAMA1,115200n8 earlyprintk"; }; + aliases { + serial1 = &uart1; + }; + src@101e0000 { /* These chrystal drivers are not used on this board */ disable-sxtalo; diff --git a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi index 9a5f2ba139b7..ef794a33b4dc 100644 --- a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi +++ b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi @@ -757,6 +757,7 @@ clock-names = "uartclk", "apb_pclk"; pinctrl-names = "default"; pinctrl-0 = <&uart0_default_mux>; + status = "disabled"; }; uart1: uart@101fb000 { From 0a927c2f02a2437a57679527e42ab7cbfa14efb1 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Tue, 21 Jul 2015 13:20:46 -0400 Subject: [PATCH 128/428] dm thin: return -ENOSPC when erroring retry list due to out of data space Otherwise -EIO would be returned when -ENOSPC should be used consistently. Signed-off-by: Mike Snitzer --- drivers/md/dm-thin.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 1c50c580215c..d2bbe8cc1e97 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -666,16 +666,21 @@ static void requeue_io(struct thin_c *tc) requeue_deferred_cells(tc); } -static void error_retry_list(struct pool *pool) +static void error_retry_list_with_code(struct pool *pool, int error) { struct thin_c *tc; rcu_read_lock(); list_for_each_entry_rcu(tc, &pool->active_thins, list) - error_thin_bio_list(tc, &tc->retry_on_resume_list, -EIO); + error_thin_bio_list(tc, &tc->retry_on_resume_list, error); rcu_read_unlock(); } +static void error_retry_list(struct pool *pool) +{ + return error_retry_list_with_code(pool, -EIO); +} + /* * This section of code contains the logic for processing a thin device's IO. * Much of the code depends on pool object resources (lists, workqueues, etc) @@ -2297,7 +2302,7 @@ static void do_no_space_timeout(struct work_struct *ws) if (get_pool_mode(pool) == PM_OUT_OF_DATA_SPACE && !pool->pf.error_if_no_space) { pool->pf.error_if_no_space = true; notify_of_pool_mode_change_to_oods(pool); - error_retry_list(pool); + error_retry_list_with_code(pool, -ENOSPC); } } From 963ad94853000ab100f5ff19eea80095660d41b4 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 22 Jul 2015 13:03:40 +0200 Subject: [PATCH 129/428] bridge: netlink: fix slave_changelink/br_setport race conditions Since slave_changelink support was added there have been a few race conditions when using br_setport() since some of the port functions it uses require the bridge lock. It is very easy to trigger a lockup due to some internal spin_lock() usage without bh disabled, also it's possible to get the bridge into an inconsistent state. Signed-off-by: Nikolay Aleksandrov Fixes: 3ac636b8591c ("bridge: implement rtnl_link_ops->slave_changelink") Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- net/bridge/br_netlink.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 364bdc98bd9b..3da5525eb8a2 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -693,9 +693,17 @@ static int br_port_slave_changelink(struct net_device *brdev, struct nlattr *tb[], struct nlattr *data[]) { + struct net_bridge *br = netdev_priv(brdev); + int ret; + if (!data) return 0; - return br_setport(br_port_get_rtnl(dev), data); + + spin_lock_bh(&br->lock); + ret = br_setport(br_port_get_rtnl(dev), data); + spin_unlock_bh(&br->lock); + + return ret; } static int br_port_fill_slave_info(struct sk_buff *skb, From 178d23e3cd4811ebe702d60ac31e8bee389a5847 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Wed, 22 Jul 2015 16:53:46 +0300 Subject: [PATCH 130/428] net/mlx4_core: Use sink counter for the VF default as fallback Some old PF drivers don't let VFs allocate counters, in that case, use the sink counter so the VF can load and operate properly. Fixes: 6de5f7f6a1fa ('net/mlx4_core: Allocate default counter per port') Reported-by: Sebastian Ott Signed-off-by: Or Gerlitz Signed-off-by: Eran Ben Elisha Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/main.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 12fbfcb44d8a..29c2a017a450 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -2273,6 +2273,11 @@ static int mlx4_allocate_default_counters(struct mlx4_dev *dev) } else if (err == -ENOENT) { err = 0; continue; + } else if (mlx4_is_slave(dev) && err == -EINVAL) { + priv->def_counter[port] = MLX4_SINK_COUNTER_INDEX(dev); + mlx4_warn(dev, "can't allocate counter from old PF driver, using index %d\n", + MLX4_SINK_COUNTER_INDEX(dev)); + err = 0; } else { mlx4_err(dev, "%s: failed to allocate default counter port %d err %d\n", __func__, port + 1, err); From 1c1bf34951e8d17941bf708d1901c47e81b15d55 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Wed, 22 Jul 2015 16:53:47 +0300 Subject: [PATCH 131/428] net/mlx4_core: Fix wrong index in propagating port change event to VFs The port-change event processing in procedure mlx4_eq_int() uses "slave" as the vf_oper array index. Since the value of "slave" is the PF function index, the result is that the PF link state is used for deciding to propagate the event for all the VFs. The VF link state should be used, so the VF function index should be used here. Fixes: 948e306d7d64 ('net/mlx4: Add VF link state support') Signed-off-by: Jack Morgenstein Signed-off-by: Matan Barak Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/eq.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index aae13adfb492..8e81e53c370e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -601,7 +601,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) continue; mlx4_dbg(dev, "%s: Sending MLX4_PORT_CHANGE_SUBTYPE_DOWN to slave: %d, port:%d\n", __func__, i, port); - s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state; + s_info = &priv->mfunc.master.vf_oper[i].vport[port].state; if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) { eqe->event.port_change.port = cpu_to_be32( @@ -640,7 +640,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) continue; if (i == mlx4_master_func_num(dev)) continue; - s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state; + s_info = &priv->mfunc.master.vf_oper[i].vport[port].state; if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) { eqe->event.port_change.port = cpu_to_be32( From 9f5b031770b9108b57881c83dffc02cd90ec3961 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Wed, 22 Jul 2015 16:53:48 +0300 Subject: [PATCH 132/428] net/mlx4_core: Relieve cpu load average on the port sending flow When a port is not attached, the FW requires a longer than usual time to execute the SENSE_PORT command. In the command flow, the wait_for_completion_timeout call used in mlx4_cmd_wait puts the kernel thread into the uninterruptible state during this time. This, in turn, due to the computation method, causes the CPU load average to increase. Fix this by using wait_for_completion_interruptible_timeout() for the SENSE_PORT command, which puts the thread in the interruptible state. In this state, the thread does not contribute to the CPU load average. Treat the interrupted case as if the SENSE_PORT command returned port_type = NONE. Fix suggested by Gideon Naim and Bart Van Assche . Signed-off-by: Jack Morgenstein Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/cmd.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 82040137d7d9..0a3202047569 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -686,6 +686,7 @@ static int mlx4_cmd_wait(struct mlx4_dev *dev, u64 in_param, u64 *out_param, { struct mlx4_cmd *cmd = &mlx4_priv(dev)->cmd; struct mlx4_cmd_context *context; + long ret_wait; int err = 0; down(&cmd->event_sem); @@ -711,8 +712,20 @@ static int mlx4_cmd_wait(struct mlx4_dev *dev, u64 in_param, u64 *out_param, if (err) goto out_reset; - if (!wait_for_completion_timeout(&context->done, - msecs_to_jiffies(timeout))) { + if (op == MLX4_CMD_SENSE_PORT) { + ret_wait = + wait_for_completion_interruptible_timeout(&context->done, + msecs_to_jiffies(timeout)); + if (ret_wait < 0) { + context->fw_status = 0; + context->out_param = 0; + context->result = 0; + } + } else { + ret_wait = (long)wait_for_completion_timeout(&context->done, + msecs_to_jiffies(timeout)); + } + if (!ret_wait) { mlx4_warn(dev, "command 0x%x timed out (go bit not cleared)\n", op); if (op == MLX4_CMD_NOP) { From 62e4c9b4fd3f8fd7d51951f0f10e3f27c58d4037 Mon Sep 17 00:00:00 2001 From: Ido Shamay Date: Wed, 22 Jul 2015 16:53:49 +0300 Subject: [PATCH 133/428] net/mlx4_en: Remove BUG_ON assert when checking if ring is full In mlx4_en_is_ring_empty we check if ring surpassed its size. Since the prod and cons indicators are u32, there might be a state where prod wrapped around and cons, making this assert false, although no actual bug exists (other code segment can cope with this state). Signed-off-by: Ido Shamay Signed-off-by: Eugenia Emantayev Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 7a4f20bb7fcb..9c145dddd717 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -246,7 +246,6 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv, static inline bool mlx4_en_is_ring_empty(struct mlx4_en_rx_ring *ring) { - BUG_ON((u32)(ring->prod - ring->cons) > ring->actual_size); return ring->prod == ring->cons; } From 81296fc67319d96ea6f7f43a07494394e1236a19 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 22 Jul 2015 16:31:49 +0200 Subject: [PATCH 134/428] net: sctp: stop spamming klog with rfc6458, 5.3.2. deprecation warnings Back then when we added support for SCTP_SNDINFO/SCTP_RCVINFO from RFC6458 5.3.4/5.3.5, we decided to add a deprecation warning for the (as per RFC deprecated) SCTP_SNDRCV via commit bbbea41d5e53 ("net: sctp: deprecate rfc6458, 5.3.2. SCTP_SNDRCV support"), see [1]. Imho, it was not a good idea, and we should just revert that message for a couple of reasons: 1) It's uapi and therefore set in stone forever. 2) To be able to run on older and newer kernels, an SCTP application would need to probe for both, SCTP_SNDRCV, but also SCTP_SNDINFO/ SCTP_RCVINFO support, so that on older kernels, it can make use of SCTP_SNDRCV, and on newer kernels SCTP_SNDINFO/SCTP_RCVINFO. In my (limited) experience, a lot of SCTP appliances are migrating to newer kernels only ve(ee)ry slowly. 3) Some people don't have the chance to change their applications, f.e. due to proprietary legacy stuff. So, they'll hit this warning in fast path and are stuck with older kernels. But i.e. due to point 1) I really fail to see the benefit of a warning. So just revert that for now, the issue was reported up Jamal. [1] http://thread.gmane.org/gmane.linux.network/321960/ Reported-by: Jamal Hadi Salim Signed-off-by: Daniel Borkmann Cc: Michael Tuexen Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- net/sctp/socket.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 1425ec2bbd5a..17bef01b9aa3 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2200,12 +2200,6 @@ static int sctp_setsockopt_events(struct sock *sk, char __user *optval, if (copy_from_user(&sctp_sk(sk)->subscribe, optval, optlen)) return -EFAULT; - if (sctp_sk(sk)->subscribe.sctp_data_io_event) - pr_warn_ratelimited(DEPRECATED "%s (pid %d) " - "Requested SCTP_SNDRCVINFO event.\n" - "Use SCTP_RCVINFO through SCTP_RECVRCVINFO option instead.\n", - current->comm, task_pid_nr(current)); - /* At the time when a user app subscribes to SCTP_SENDER_DRY_EVENT, * if there is no data to be sent or retransmit, the stack will * immediately send up this notification. From 69cefc273f942bd7bb347a02e8b5b738d5f6e6f3 Mon Sep 17 00:00:00 2001 From: Lukasz Anaczkowski Date: Tue, 21 Jul 2015 10:41:13 +0200 Subject: [PATCH 135/428] intel_pstate: Add get_scaling cpu_defaults param to Knights Landing Scaling for Knights Landing is same as the default scaling (100000). When Knigts Landing support was added to the pstate driver, this parameter was omitted resulting in a kernel panic during boot. Fixes: b34ef932d79a (intel_pstate: Knights Landing support) Reported-by: Yasuaki Ishimatsu Signed-off-by: Dasaratharaman Chandramouli Signed-off-by: Lukasz Anaczkowski Acked-by: Kristen Carlson Accardi Cc: 4.1+ # 4.1+ Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 15ada47bb720..fcb929ec5304 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -681,6 +681,7 @@ static struct cpu_defaults knl_params = { .get_max = core_get_max_pstate, .get_min = core_get_min_pstate, .get_turbo = knl_get_turbo_pstate, + .get_scaling = core_get_scaling, .set = core_set_pstate, }, }; From d1fe19444d82e399e38c1594c71b850eca8e9de0 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 23 Jul 2015 12:05:37 +0200 Subject: [PATCH 136/428] inet: frag: don't re-use chainlist for evictor commit 65ba1f1ec0eff ("inet: frags: fix a race between inet_evict_bucket and inet_frag_kill") describes the bug, but the fix doesn't work reliably. Problem is that ->flags member can be set on other cpu without chainlock being held by that task, i.e. the RMW-Cycle can clear INET_FRAG_EVICTED bit after we put the element on the evictor private list. We can crash when walking the 'private' evictor list since an element can be deleted from list underneath the evictor. Join work with Nikolay Alexandrov. Fixes: b13d3cbfb8e8 ("inet: frag: move eviction of queues to work queue") Reported-by: Johan Schuijt Tested-by: Frank Schreuder Signed-off-by: Nikolay Alexandrov Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/net/inet_frag.h | 2 ++ net/ipv4/inet_fragment.c | 8 +++----- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index e1300b3dd597..56a3a5685f76 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -45,6 +45,7 @@ enum { * @flags: fragment queue flags * @max_size: maximum received fragment size * @net: namespace that this frag belongs to + * @list_evictor: list of queues to forcefully evict (e.g. due to low memory) */ struct inet_frag_queue { spinlock_t lock; @@ -59,6 +60,7 @@ struct inet_frag_queue { __u8 flags; u16 max_size; struct netns_frags *net; + struct hlist_node list_evictor; }; #define INETFRAGS_HASHSZ 1024 diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 5e346a082e5f..172234864fec 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -151,14 +151,13 @@ evict_again: } fq->flags |= INET_FRAG_EVICTED; - hlist_del(&fq->list); - hlist_add_head(&fq->list, &expired); + hlist_add_head(&fq->list_evictor, &expired); ++evicted; } spin_unlock(&hb->chain_lock); - hlist_for_each_entry_safe(fq, n, &expired, list) + hlist_for_each_entry_safe(fq, n, &expired, list_evictor) f->frag_expire((unsigned long) fq); return evicted; @@ -284,8 +283,7 @@ static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f) struct inet_frag_bucket *hb; hb = get_frag_bucket_locked(fq, f); - if (!(fq->flags & INET_FRAG_EVICTED)) - hlist_del(&fq->list); + hlist_del(&fq->list); spin_unlock(&hb->chain_lock); } From 0e60d245a0be7fdbb723607f1d6621007916b252 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 23 Jul 2015 12:05:38 +0200 Subject: [PATCH 137/428] inet: frag: change *_frag_mem_limit functions to take netns_frags as argument Followup patch will call it after inet_frag_queue was freed, so q->net doesn't work anymore (but netf = q->net; free(q); mem_limit(netf) would). Tested-by: Frank Schreuder Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/net/inet_frag.h | 8 ++++---- net/ieee802154/6lowpan/reassembly.c | 6 +++--- net/ipv4/inet_fragment.c | 4 ++-- net/ipv4/ip_fragment.c | 10 +++++----- net/ipv6/netfilter/nf_conntrack_reasm.c | 6 +++--- net/ipv6/reassembly.c | 6 +++--- 6 files changed, 20 insertions(+), 20 deletions(-) diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 56a3a5685f76..e71ca17024f2 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -141,14 +141,14 @@ static inline int frag_mem_limit(struct netns_frags *nf) return percpu_counter_read(&nf->mem); } -static inline void sub_frag_mem_limit(struct inet_frag_queue *q, int i) +static inline void sub_frag_mem_limit(struct netns_frags *nf, int i) { - __percpu_counter_add(&q->net->mem, -i, frag_percpu_counter_batch); + __percpu_counter_add(&nf->mem, -i, frag_percpu_counter_batch); } -static inline void add_frag_mem_limit(struct inet_frag_queue *q, int i) +static inline void add_frag_mem_limit(struct netns_frags *nf, int i) { - __percpu_counter_add(&q->net->mem, i, frag_percpu_counter_batch); + __percpu_counter_add(&nf->mem, i, frag_percpu_counter_batch); } static inline void init_frag_mem_limit(struct netns_frags *nf) diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index f46e4d1306f2..214d44aef35b 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -207,7 +207,7 @@ found: } else { fq->q.meat += skb->len; } - add_frag_mem_limit(&fq->q, skb->truesize); + add_frag_mem_limit(fq->q.net, skb->truesize); if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) { @@ -287,7 +287,7 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev, clone->data_len = clone->len; head->data_len -= clone->len; head->len -= clone->len; - add_frag_mem_limit(&fq->q, clone->truesize); + add_frag_mem_limit(fq->q.net, clone->truesize); } WARN_ON(head == NULL); @@ -310,7 +310,7 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev, } fp = next; } - sub_frag_mem_limit(&fq->q, sum_truesize); + sub_frag_mem_limit(fq->q.net, sum_truesize); head->next = NULL; head->dev = dev; diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 172234864fec..4473232e4e88 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -328,7 +328,7 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f) fp = xp; } sum = sum_truesize + f->qsize; - sub_frag_mem_limit(q, sum); + sub_frag_mem_limit(q->net, sum); if (f->destructor) f->destructor(q); @@ -388,7 +388,7 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, q->net = nf; f->constructor(q, arg); - add_frag_mem_limit(q, f->qsize); + add_frag_mem_limit(nf, f->qsize); setup_timer(&q->timer, f->frag_expire, (unsigned long)q); spin_lock_init(&q->lock); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 31f71b15cfba..b4a77d021c0d 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -309,7 +309,7 @@ static int ip_frag_reinit(struct ipq *qp) kfree_skb(fp); fp = xp; } while (fp); - sub_frag_mem_limit(&qp->q, sum_truesize); + sub_frag_mem_limit(qp->q.net, sum_truesize); qp->q.flags = 0; qp->q.len = 0; @@ -455,7 +455,7 @@ found: qp->q.fragments = next; qp->q.meat -= free_it->len; - sub_frag_mem_limit(&qp->q, free_it->truesize); + sub_frag_mem_limit(qp->q.net, free_it->truesize); kfree_skb(free_it); } } @@ -479,7 +479,7 @@ found: qp->q.stamp = skb->tstamp; qp->q.meat += skb->len; qp->ecn |= ecn; - add_frag_mem_limit(&qp->q, skb->truesize); + add_frag_mem_limit(qp->q.net, skb->truesize); if (offset == 0) qp->q.flags |= INET_FRAG_FIRST_IN; @@ -587,7 +587,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, head->len -= clone->len; clone->csum = 0; clone->ip_summed = head->ip_summed; - add_frag_mem_limit(&qp->q, clone->truesize); + add_frag_mem_limit(qp->q.net, clone->truesize); } skb_push(head, head->data - skb_network_header(head)); @@ -615,7 +615,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, } fp = next; } - sub_frag_mem_limit(&qp->q, sum_truesize); + sub_frag_mem_limit(qp->q.net, sum_truesize); head->next = NULL; head->dev = dev; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 6f187c8d8a1b..6d02498172c1 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -348,7 +348,7 @@ found: fq->ecn |= ecn; if (payload_len > fq->q.max_size) fq->q.max_size = payload_len; - add_frag_mem_limit(&fq->q, skb->truesize); + add_frag_mem_limit(fq->q.net, skb->truesize); /* The first fragment. * nhoffset is obtained from the first fragment, of course. @@ -430,7 +430,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) clone->ip_summed = head->ip_summed; NFCT_FRAG6_CB(clone)->orig = NULL; - add_frag_mem_limit(&fq->q, clone->truesize); + add_frag_mem_limit(fq->q.net, clone->truesize); } /* We have to remove fragment header from datagram and to relocate @@ -454,7 +454,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) head->csum = csum_add(head->csum, fp->csum); head->truesize += fp->truesize; } - sub_frag_mem_limit(&fq->q, head->truesize); + sub_frag_mem_limit(fq->q.net, head->truesize); head->ignore_df = 1; head->next = NULL; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 8ffa2c8cce77..5c3bbca6a150 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -330,7 +330,7 @@ found: fq->q.stamp = skb->tstamp; fq->q.meat += skb->len; fq->ecn |= ecn; - add_frag_mem_limit(&fq->q, skb->truesize); + add_frag_mem_limit(fq->q.net, skb->truesize); /* The first fragment. * nhoffset is obtained from the first fragment, of course. @@ -443,7 +443,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, head->len -= clone->len; clone->csum = 0; clone->ip_summed = head->ip_summed; - add_frag_mem_limit(&fq->q, clone->truesize); + add_frag_mem_limit(fq->q.net, clone->truesize); } /* We have to remove fragment header from datagram and to relocate @@ -481,7 +481,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, } fp = next; } - sub_frag_mem_limit(&fq->q, sum_truesize); + sub_frag_mem_limit(fq->q.net, sum_truesize); head->next = NULL; head->dev = dev; From 5719b296fb81502d0dbbb4e87b3235e5bdcdfc6b Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 23 Jul 2015 12:05:39 +0200 Subject: [PATCH 138/428] inet: frag: don't wait for timer deletion when evicting Frank reports 'NMI watchdog: BUG: soft lockup' errors when load is high. Instead of (potentially) unbounded restarts of the eviction process, just skip to the next entry. One caveat is that, when a netns is exiting, a timer may still be running by the time inet_evict_bucket returns. We use the frag memory accounting to wait for outstanding timers, so that when we free the percpu counter we can be sure no running timer will trip over it. Reported-and-tested-by: Frank Schreuder Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- net/ipv4/inet_fragment.c | 29 +++++++++++------------------ 1 file changed, 11 insertions(+), 18 deletions(-) diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 4473232e4e88..a00ca4c00c35 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -131,24 +131,14 @@ inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb) unsigned int evicted = 0; HLIST_HEAD(expired); -evict_again: spin_lock(&hb->chain_lock); hlist_for_each_entry_safe(fq, n, &hb->chain, list) { if (!inet_fragq_should_evict(fq)) continue; - if (!del_timer(&fq->timer)) { - /* q expiring right now thus increment its refcount so - * it won't be freed under us and wait until the timer - * has finished executing then destroy it - */ - atomic_inc(&fq->refcnt); - spin_unlock(&hb->chain_lock); - del_timer_sync(&fq->timer); - inet_frag_put(fq, f); - goto evict_again; - } + if (!del_timer(&fq->timer)) + continue; fq->flags |= INET_FRAG_EVICTED; hlist_add_head(&fq->list_evictor, &expired); @@ -239,18 +229,20 @@ void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f) int i; nf->low_thresh = 0; - local_bh_disable(); evict_again: + local_bh_disable(); seq = read_seqbegin(&f->rnd_seqlock); for (i = 0; i < INETFRAGS_HASHSZ ; i++) inet_evict_bucket(f, &f->hash[i]); - if (read_seqretry(&f->rnd_seqlock, seq)) - goto evict_again; - local_bh_enable(); + cond_resched(); + + if (read_seqretry(&f->rnd_seqlock, seq) || + percpu_counter_sum(&nf->mem)) + goto evict_again; percpu_counter_destroy(&nf->mem); } @@ -284,6 +276,7 @@ static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f) hb = get_frag_bucket_locked(fq, f); hlist_del(&fq->list); + fq->flags |= INET_FRAG_COMPLETE; spin_unlock(&hb->chain_lock); } @@ -295,7 +288,6 @@ void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f) if (!(fq->flags & INET_FRAG_COMPLETE)) { fq_unlink(fq, f); atomic_dec(&fq->refcnt); - fq->flags |= INET_FRAG_COMPLETE; } } EXPORT_SYMBOL(inet_frag_kill); @@ -328,11 +320,12 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f) fp = xp; } sum = sum_truesize + f->qsize; - sub_frag_mem_limit(q->net, sum); if (f->destructor) f->destructor(q); kmem_cache_free(f->frags_cachep, q); + + sub_frag_mem_limit(nf, sum); } EXPORT_SYMBOL(inet_frag_destroy); From caaecdd3d3f8ec0ea9906c54b1dd8ec8316d26b9 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Thu, 23 Jul 2015 12:05:40 +0200 Subject: [PATCH 139/428] inet: frags: remove INET_FRAG_EVICTED and use list_evictor for the test We can simply remove the INET_FRAG_EVICTED flag to avoid all the flags race conditions with the evictor and use a participation test for the evictor list, when we're at that point (after inet_frag_kill) in the timer there're 2 possible cases: 1. The evictor added the entry to its evictor list while the timer was waiting for the chainlock or 2. The timer unchained the entry and the evictor won't see it In both cases we should be able to see list_evictor correctly due to the sync on the chainlock. Joint work with Florian Westphal. Tested-by: Frank Schreuder Signed-off-by: Nikolay Aleksandrov Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/net/inet_frag.h | 7 +++++-- net/ipv4/inet_fragment.c | 1 - net/ipv4/ip_fragment.c | 2 +- net/ipv6/reassembly.c | 2 +- 4 files changed, 7 insertions(+), 5 deletions(-) diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index e71ca17024f2..53eead2da743 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -21,13 +21,11 @@ struct netns_frags { * @INET_FRAG_FIRST_IN: first fragment has arrived * @INET_FRAG_LAST_IN: final fragment has arrived * @INET_FRAG_COMPLETE: frag queue has been processed and is due for destruction - * @INET_FRAG_EVICTED: frag queue is being evicted */ enum { INET_FRAG_FIRST_IN = BIT(0), INET_FRAG_LAST_IN = BIT(1), INET_FRAG_COMPLETE = BIT(2), - INET_FRAG_EVICTED = BIT(3) }; /** @@ -127,6 +125,11 @@ static inline void inet_frag_put(struct inet_frag_queue *q, struct inet_frags *f inet_frag_destroy(q, f); } +static inline bool inet_frag_evicting(struct inet_frag_queue *q) +{ + return !hlist_unhashed(&q->list_evictor); +} + /* Memory Tracking Functions. */ /* The default percpu_counter batch size is not big enough to scale to diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index a00ca4c00c35..d0a7c0319e3d 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -140,7 +140,6 @@ inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb) if (!del_timer(&fq->timer)) continue; - fq->flags |= INET_FRAG_EVICTED; hlist_add_head(&fq->list_evictor, &expired); ++evicted; } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index b4a77d021c0d..921138f6c97c 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -202,7 +202,7 @@ static void ip_expire(unsigned long arg) ipq_kill(qp); IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS); - if (!(qp->q.flags & INET_FRAG_EVICTED)) { + if (!inet_frag_evicting(&qp->q)) { struct sk_buff *head = qp->q.fragments; const struct iphdr *iph; int err; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 5c3bbca6a150..f1159bb76e0a 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -144,7 +144,7 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq, IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); - if (fq->q.flags & INET_FRAG_EVICTED) + if (inet_frag_evicting(&fq->q)) goto out_rcu_unlock; IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); From 42288830494cd51873ca745a7a229023df061226 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 23 Jul 2015 12:20:37 +0200 Subject: [PATCH 140/428] niu: don't count tx error twice in case of headroom realloc fails Fixes: a3138df9 ("[NIU]: Add Sun Neptune ethernet driver.") Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/sun/niu.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 0c5842aeb807..ab6051a43134 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -6658,10 +6658,8 @@ static netdev_tx_t niu_start_xmit(struct sk_buff *skb, struct sk_buff *skb_new; skb_new = skb_realloc_headroom(skb, len); - if (!skb_new) { - rp->tx_errors++; + if (!skb_new) goto out_drop; - } kfree_skb(skb); skb = skb_new; } else From c0a1a0a698bb0f90ec4719de34f37715abfad8a5 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Thu, 23 Jul 2015 16:06:19 +0200 Subject: [PATCH 141/428] net: fec: use managed DMA API functions to allocate BD ring So it gets freed when the device is going away. This fixes a DMA memory leak on driver probe() fail and driver remove(). Signed-off-by: Lucas Stach Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fec_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 1f89c59b4353..2945b62b6dc5 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3115,8 +3115,8 @@ static int fec_enet_init(struct net_device *ndev) fep->bufdesc_size; /* Allocate memory for buffer descriptors. */ - cbd_base = dma_alloc_coherent(NULL, bd_size, &bd_dma, - GFP_KERNEL); + cbd_base = dmam_alloc_coherent(&fep->pdev->dev, bd_size, &bd_dma, + GFP_KERNEL); if (!cbd_base) { return -ENOMEM; } From 32cba57ba74be58589aeb4cb6496183e46a5e3e5 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Thu, 23 Jul 2015 16:06:20 +0200 Subject: [PATCH 142/428] net: fec: introduce fec_ptp_stop and use in probe fail path This function frees resources and cancels delayed work item that have been initialized in fec_ptp_init(). Use this to do proper error handling if something goes wrong in probe function after fec_ptp_init has been called. Signed-off-by: Lucas Stach Acked-by: Fugang Duan Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fec.h | 1 + drivers/net/ethernet/freescale/fec_main.c | 5 ++--- drivers/net/ethernet/freescale/fec_ptp.c | 10 ++++++++++ 3 files changed, 13 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index 1eee73cccdf5..99d33e2d35e6 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -562,6 +562,7 @@ struct fec_enet_private { }; void fec_ptp_init(struct platform_device *pdev); +void fec_ptp_stop(struct platform_device *pdev); void fec_ptp_start_cyclecounter(struct net_device *ndev); int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr); int fec_ptp_get(struct net_device *ndev, struct ifreq *ifr); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 2945b62b6dc5..5e8b8370b5a7 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3454,6 +3454,7 @@ failed_register: failed_mii_init: failed_irq: failed_init: + fec_ptp_stop(pdev); if (fep->reg_phy) regulator_disable(fep->reg_phy); failed_regulator: @@ -3473,14 +3474,12 @@ fec_drv_remove(struct platform_device *pdev) struct net_device *ndev = platform_get_drvdata(pdev); struct fec_enet_private *fep = netdev_priv(ndev); - cancel_delayed_work_sync(&fep->time_keep); cancel_work_sync(&fep->tx_timeout_work); + fec_ptp_stop(pdev); unregister_netdev(ndev); fec_enet_mii_remove(fep); if (fep->reg_phy) regulator_disable(fep->reg_phy); - if (fep->ptp_clock) - ptp_clock_unregister(fep->ptp_clock); of_node_put(fep->phy_node); free_netdev(ndev); diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index a15663ad7f5e..f457a23d0bfb 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -604,6 +604,16 @@ void fec_ptp_init(struct platform_device *pdev) schedule_delayed_work(&fep->time_keep, HZ); } +void fec_ptp_stop(struct platform_device *pdev) +{ + struct net_device *ndev = platform_get_drvdata(pdev); + struct fec_enet_private *fep = netdev_priv(ndev); + + cancel_delayed_work_sync(&fep->time_keep); + if (fep->ptp_clock) + ptp_clock_unregister(fep->ptp_clock); +} + /** * fec_ptp_check_pps_event * @fep: the fec_enet_private structure handle From 30342fe65e511007672437741158d493472f427f Mon Sep 17 00:00:00 2001 From: Michael Holzheu Date: Thu, 23 Jul 2015 19:26:15 +0200 Subject: [PATCH 143/428] s390/bpf: clear correct BPF accumulator register Currently we assumed the following BPF to eBPF register mapping: - BPF_REG_A -> BPF_REG_7 - BPF_REG_X -> BPF_REG_8 Unfortunately this mapping is wrong. The correct mapping is: - BPF_REG_A -> BPF_REG_0 - BPF_REG_X -> BPF_REG_7 So clear the correct registers and use the BPF_REG_A and BPF_REG_X macros instead of BPF_REG_0/7. Fixes: 054623105728 ("s390/bpf: Add s390x eBPF JIT compiler backend") Cc: stable@vger.kernel.org # 4.0+ Signed-off-by: Michael Holzheu Signed-off-by: Martin Schwidefsky --- arch/s390/net/bpf_jit_comp.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index fee782acc2ee..8d2e5165865f 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -448,13 +448,13 @@ static void bpf_jit_prologue(struct bpf_jit *jit) EMIT6_DISP_LH(0xe3000000, 0x0004, REG_SKB_DATA, REG_0, BPF_REG_1, offsetof(struct sk_buff, data)); } - /* BPF compatibility: clear A (%b7) and X (%b8) registers */ - if (REG_SEEN(BPF_REG_7)) - /* lghi %b7,0 */ - EMIT4_IMM(0xa7090000, BPF_REG_7, 0); - if (REG_SEEN(BPF_REG_8)) - /* lghi %b8,0 */ - EMIT4_IMM(0xa7090000, BPF_REG_8, 0); + /* BPF compatibility: clear A (%b0) and X (%b7) registers */ + if (REG_SEEN(BPF_REG_A)) + /* lghi %ba,0 */ + EMIT4_IMM(0xa7090000, BPF_REG_A, 0); + if (REG_SEEN(BPF_REG_X)) + /* lghi %bx,0 */ + EMIT4_IMM(0xa7090000, BPF_REG_X, 0); } /* From 5c02a4206538da12c040b51778d310df84c6bf6c Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 24 Jul 2015 13:49:48 +0300 Subject: [PATCH 144/428] avr32: handle NULL as a valid clock object Since NULL is used as valid clock object on optional clocks we have to handle this case in avr32 implementation as well. Fixes: e1824dfe0d8e (net: macb: Adjust tx_clk when link speed changes) Signed-off-by: Andy Shevchenko Acked-by: Hans-Christian Egtvedt --- arch/avr32/mach-at32ap/clock.c | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) diff --git a/arch/avr32/mach-at32ap/clock.c b/arch/avr32/mach-at32ap/clock.c index 23b1a97fae7a..52c179bec0cc 100644 --- a/arch/avr32/mach-at32ap/clock.c +++ b/arch/avr32/mach-at32ap/clock.c @@ -80,6 +80,9 @@ int clk_enable(struct clk *clk) { unsigned long flags; + if (!clk) + return 0; + spin_lock_irqsave(&clk_lock, flags); __clk_enable(clk); spin_unlock_irqrestore(&clk_lock, flags); @@ -106,6 +109,9 @@ void clk_disable(struct clk *clk) { unsigned long flags; + if (IS_ERR_OR_NULL(clk)) + return; + spin_lock_irqsave(&clk_lock, flags); __clk_disable(clk); spin_unlock_irqrestore(&clk_lock, flags); @@ -117,6 +123,9 @@ unsigned long clk_get_rate(struct clk *clk) unsigned long flags; unsigned long rate; + if (!clk) + return 0; + spin_lock_irqsave(&clk_lock, flags); rate = clk->get_rate(clk); spin_unlock_irqrestore(&clk_lock, flags); @@ -129,6 +138,9 @@ long clk_round_rate(struct clk *clk, unsigned long rate) { unsigned long flags, actual_rate; + if (!clk) + return 0; + if (!clk->set_rate) return -ENOSYS; @@ -145,6 +157,9 @@ int clk_set_rate(struct clk *clk, unsigned long rate) unsigned long flags; long ret; + if (!clk) + return 0; + if (!clk->set_rate) return -ENOSYS; @@ -161,6 +176,9 @@ int clk_set_parent(struct clk *clk, struct clk *parent) unsigned long flags; int ret; + if (!clk) + return 0; + if (!clk->set_parent) return -ENOSYS; @@ -174,7 +192,7 @@ EXPORT_SYMBOL(clk_set_parent); struct clk *clk_get_parent(struct clk *clk) { - return clk->parent; + return !clk ? NULL : clk->parent; } EXPORT_SYMBOL(clk_get_parent); From b214396fb5890af58ff04b42deba7de5a2686338 Mon Sep 17 00:00:00 2001 From: hayeswang Date: Fri, 24 Jul 2015 13:54:23 +0800 Subject: [PATCH 145/428] r8152: fix the issue about U1/U2 - Disable U1/U2 during initialization. - Disable lpm when linking is on, and enable it when linking is off. - Disable U1/U2 when enabling runtime suspend. It is possible to let hw stop working, if the U1/U2 request occurs during some situations. The patch is used to avoid it. Signed-off-by: Hayes Wang Signed-off-by: David S. Miller --- drivers/net/usb/r8152.c | 94 +++++++++++++++++++++++------------------ 1 file changed, 54 insertions(+), 40 deletions(-) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 7f6419ebb5e1..e3a011046540 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -2166,6 +2166,7 @@ static int rtl8153_enable(struct r8152 *tp) if (test_bit(RTL8152_UNPLUG, &tp->flags)) return -ENODEV; + usb_disable_lpm(tp->udev); set_tx_qlen(tp); rtl_set_eee_plus(tp); r8153_set_rx_early_timeout(tp); @@ -2337,11 +2338,54 @@ static void __rtl_set_wol(struct r8152 *tp, u32 wolopts) device_set_wakeup_enable(&tp->udev->dev, false); } +static void r8153_u1u2en(struct r8152 *tp, bool enable) +{ + u8 u1u2[8]; + + if (enable) + memset(u1u2, 0xff, sizeof(u1u2)); + else + memset(u1u2, 0x00, sizeof(u1u2)); + + usb_ocp_write(tp, USB_TOLERANCE, BYTE_EN_SIX_BYTES, sizeof(u1u2), u1u2); +} + +static void r8153_u2p3en(struct r8152 *tp, bool enable) +{ + u32 ocp_data; + + ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL); + if (enable && tp->version != RTL_VER_03 && tp->version != RTL_VER_04) + ocp_data |= U2P3_ENABLE; + else + ocp_data &= ~U2P3_ENABLE; + ocp_write_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL, ocp_data); +} + +static void r8153_power_cut_en(struct r8152 *tp, bool enable) +{ + u32 ocp_data; + + ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_POWER_CUT); + if (enable) + ocp_data |= PWR_EN | PHASE2_EN; + else + ocp_data &= ~(PWR_EN | PHASE2_EN); + ocp_write_word(tp, MCU_TYPE_USB, USB_POWER_CUT, ocp_data); + + ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_MISC_0); + ocp_data &= ~PCUT_STATUS; + ocp_write_word(tp, MCU_TYPE_USB, USB_MISC_0, ocp_data); +} + static void rtl_runtime_suspend_enable(struct r8152 *tp, bool enable) { if (enable) { u32 ocp_data; + r8153_u1u2en(tp, false); + r8153_u2p3en(tp, false); + __rtl_set_wol(tp, WAKE_ANY); ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_CONFIG); @@ -2353,6 +2397,8 @@ static void rtl_runtime_suspend_enable(struct r8152 *tp, bool enable) ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML); } else { __rtl_set_wol(tp, tp->saved_wolopts); + r8153_u2p3en(tp, true); + r8153_u1u2en(tp, true); } } @@ -2599,46 +2645,6 @@ static void r8153_hw_phy_cfg(struct r8152 *tp) set_bit(PHY_RESET, &tp->flags); } -static void r8153_u1u2en(struct r8152 *tp, bool enable) -{ - u8 u1u2[8]; - - if (enable) - memset(u1u2, 0xff, sizeof(u1u2)); - else - memset(u1u2, 0x00, sizeof(u1u2)); - - usb_ocp_write(tp, USB_TOLERANCE, BYTE_EN_SIX_BYTES, sizeof(u1u2), u1u2); -} - -static void r8153_u2p3en(struct r8152 *tp, bool enable) -{ - u32 ocp_data; - - ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL); - if (enable) - ocp_data |= U2P3_ENABLE; - else - ocp_data &= ~U2P3_ENABLE; - ocp_write_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL, ocp_data); -} - -static void r8153_power_cut_en(struct r8152 *tp, bool enable) -{ - u32 ocp_data; - - ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_POWER_CUT); - if (enable) - ocp_data |= PWR_EN | PHASE2_EN; - else - ocp_data &= ~(PWR_EN | PHASE2_EN); - ocp_write_word(tp, MCU_TYPE_USB, USB_POWER_CUT, ocp_data); - - ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_MISC_0); - ocp_data &= ~PCUT_STATUS; - ocp_write_word(tp, MCU_TYPE_USB, USB_MISC_0, ocp_data); -} - static void r8153_first_init(struct r8152 *tp) { u32 ocp_data; @@ -2781,6 +2787,7 @@ static void rtl8153_disable(struct r8152 *tp) r8153_disable_aldps(tp); rtl_disable(tp); r8153_enable_aldps(tp); + usb_enable_lpm(tp->udev); } static int rtl8152_set_speed(struct r8152 *tp, u8 autoneg, u16 speed, u8 duplex) @@ -2901,9 +2908,13 @@ static void rtl8153_up(struct r8152 *tp) if (test_bit(RTL8152_UNPLUG, &tp->flags)) return; + r8153_u1u2en(tp, false); r8153_disable_aldps(tp); r8153_first_init(tp); r8153_enable_aldps(tp); + r8153_u2p3en(tp, true); + r8153_u1u2en(tp, true); + usb_enable_lpm(tp->udev); } static void rtl8153_down(struct r8152 *tp) @@ -2914,6 +2925,7 @@ static void rtl8153_down(struct r8152 *tp) } r8153_u1u2en(tp, false); + r8153_u2p3en(tp, false); r8153_power_cut_en(tp, false); r8153_disable_aldps(tp); r8153_enter_oob(tp); @@ -3252,6 +3264,7 @@ static void r8153_init(struct r8152 *tp) msleep(20); } + usb_disable_lpm(tp->udev); r8153_u2p3en(tp, false); if (tp->version == RTL_VER_04) { @@ -3319,6 +3332,7 @@ static void r8153_init(struct r8152 *tp) r8153_enable_aldps(tp); r8152b_enable_fc(tp); rtl_tally_reset(tp); + r8153_u2p3en(tp, true); } static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message) From 7daed8dc2a4b48c5a7ea5b3243d01837ec1aed0a Mon Sep 17 00:00:00 2001 From: hayeswang Date: Fri, 24 Jul 2015 13:54:24 +0800 Subject: [PATCH 146/428] r8152: fix wakeup settings Avoid the driver to enable WOL if the device doesn't support it. Signed-off-by: Hayes Wang Signed-off-by: David S. Miller --- drivers/net/usb/r8152.c | 28 ++++++++++++++++++++++------ 1 file changed, 22 insertions(+), 6 deletions(-) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index e3a011046540..d537c303dfd8 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -2378,6 +2378,13 @@ static void r8153_power_cut_en(struct r8152 *tp, bool enable) ocp_write_word(tp, MCU_TYPE_USB, USB_MISC_0, ocp_data); } +static bool rtl_can_wakeup(struct r8152 *tp) +{ + struct usb_device *udev = tp->udev; + + return (udev->actconfig->desc.bmAttributes & USB_CONFIG_ATT_WAKEUP); +} + static void rtl_runtime_suspend_enable(struct r8152 *tp, bool enable) { if (enable) { @@ -3417,12 +3424,15 @@ static void rtl8152_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) if (usb_autopm_get_interface(tp->intf) < 0) return; - mutex_lock(&tp->control); - - wol->supported = WAKE_ANY; - wol->wolopts = __rtl_get_wol(tp); - - mutex_unlock(&tp->control); + if (!rtl_can_wakeup(tp)) { + wol->supported = 0; + wol->wolopts = 0; + } else { + mutex_lock(&tp->control); + wol->supported = WAKE_ANY; + wol->wolopts = __rtl_get_wol(tp); + mutex_unlock(&tp->control); + } usb_autopm_put_interface(tp->intf); } @@ -3432,6 +3442,9 @@ static int rtl8152_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) struct r8152 *tp = netdev_priv(dev); int ret; + if (!rtl_can_wakeup(tp)) + return -EOPNOTSUPP; + ret = usb_autopm_get_interface(tp->intf); if (ret < 0) goto out_set_wol; @@ -4073,6 +4086,9 @@ static int rtl8152_probe(struct usb_interface *intf, goto out1; } + if (!rtl_can_wakeup(tp)) + __rtl_set_wol(tp, 0); + tp->saved_wolopts = __rtl_get_wol(tp); if (tp->saved_wolopts) device_set_wakeup_enable(&udev->dev, true); From 41cec84cf2858b59121a1cec5e9b09fc1bf1d882 Mon Sep 17 00:00:00 2001 From: hayeswang Date: Fri, 24 Jul 2015 13:54:25 +0800 Subject: [PATCH 147/428] r8152: don't enable napi before rx ready Adjust napi_disable() and napi_enable() to avoid r8152_poll() start working before rx ready. Otherwise, it may have race condition for rx_agg. Signed-off-by: Hayes Wang Signed-off-by: David S. Miller --- drivers/net/usb/r8152.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index d537c303dfd8..144dc641c239 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -2075,7 +2075,6 @@ static int rtl_start_rx(struct r8152 *tp) { int i, ret = 0; - napi_disable(&tp->napi); INIT_LIST_HEAD(&tp->rx_done); for (i = 0; i < RTL8152_MAX_RX; i++) { INIT_LIST_HEAD(&tp->rx_info[i].list); @@ -2083,7 +2082,6 @@ static int rtl_start_rx(struct r8152 *tp) if (ret) break; } - napi_enable(&tp->napi); if (ret && ++i < RTL8152_MAX_RX) { struct list_head rx_queue; @@ -2951,8 +2949,10 @@ static void set_carrier(struct r8152 *tp) if (!netif_carrier_ok(netdev)) { tp->rtl_ops.enable(tp); set_bit(RTL8152_SET_RX_MODE, &tp->flags); + napi_disable(&tp->napi); netif_carrier_on(netdev); rtl_start_rx(tp); + napi_enable(&tp->napi); } } else { if (netif_carrier_ok(netdev)) { @@ -3395,9 +3395,11 @@ static int rtl8152_resume(struct usb_interface *intf) if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) { rtl_runtime_suspend_enable(tp, false); clear_bit(SELECTIVE_SUSPEND, &tp->flags); + napi_disable(&tp->napi); set_bit(WORK_ENABLE, &tp->flags); if (netif_carrier_ok(tp->netdev)) rtl_start_rx(tp); + napi_enable(&tp->napi); } else { tp->rtl_ops.up(tp); rtl8152_set_speed(tp, AUTONEG_ENABLE, From dfbafc995304ebb9a9b03f65083e6e9cea143b20 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 24 Jul 2015 18:19:25 +0200 Subject: [PATCH 148/428] tcp: fix recv with flags MSG_WAITALL | MSG_PEEK Currently, tcp_recvmsg enters a busy loop in sk_wait_data if called with flags = MSG_WAITALL | MSG_PEEK. sk_wait_data waits for sk_receive_queue not empty, but in this case, the receive queue is not empty, but does not contain any skb that we can use. Add a "last skb seen on receive queue" argument to sk_wait_data, so that it sleeps until the receive queue has new skbs. Link: https://bugzilla.kernel.org/show_bug.cgi?id=99461 Link: https://sourceware.org/bugzilla/show_bug.cgi?id=18493 Link: https://bugzilla.redhat.com/show_bug.cgi?id=1205258 Reported-by: Enrico Scholz Reported-by: Dan Searle Signed-off-by: Sabrina Dubroca Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 2 +- net/core/sock.c | 5 +++-- net/dccp/proto.c | 2 +- net/ipv4/tcp.c | 11 +++++++---- net/llc/af_llc.c | 4 ++-- 5 files changed, 14 insertions(+), 10 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index 05a8c1aea251..f21f0708ec59 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -902,7 +902,7 @@ void sk_stream_kill_queues(struct sock *sk); void sk_set_memalloc(struct sock *sk); void sk_clear_memalloc(struct sock *sk); -int sk_wait_data(struct sock *sk, long *timeo); +int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb); struct request_sock_ops; struct timewait_sock_ops; diff --git a/net/core/sock.c b/net/core/sock.c index 08f16db46070..8a14f1285fc4 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1967,20 +1967,21 @@ static void __release_sock(struct sock *sk) * sk_wait_data - wait for data to arrive at sk_receive_queue * @sk: sock to wait on * @timeo: for how long + * @skb: last skb seen on sk_receive_queue * * Now socket state including sk->sk_err is changed only under lock, * hence we may omit checks after joining wait queue. * We check receive queue before schedule() only as optimization; * it is very likely that release_sock() added new data. */ -int sk_wait_data(struct sock *sk, long *timeo) +int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb) { int rc; DEFINE_WAIT(wait); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); - rc = sk_wait_event(sk, timeo, !skb_queue_empty(&sk->sk_receive_queue)); + rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb); clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); finish_wait(sk_sleep(sk), &wait); return rc; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 52a94016526d..b5cf13a28009 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -886,7 +886,7 @@ verify_sock_status: break; } - sk_wait_data(sk, &timeo); + sk_wait_data(sk, &timeo, NULL); continue; found_ok_skb: if (len > skb->len) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7f4056785acc..45534a5ab430 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -780,7 +780,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, ret = -EAGAIN; break; } - sk_wait_data(sk, &timeo); + sk_wait_data(sk, &timeo, NULL); if (signal_pending(current)) { ret = sock_intr_errno(timeo); break; @@ -1575,7 +1575,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int target; /* Read at least this many bytes */ long timeo; struct task_struct *user_recv = NULL; - struct sk_buff *skb; + struct sk_buff *skb, *last; u32 urg_hole = 0; if (unlikely(flags & MSG_ERRQUEUE)) @@ -1635,7 +1635,9 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, /* Next get a buffer. */ + last = skb_peek_tail(&sk->sk_receive_queue); skb_queue_walk(&sk->sk_receive_queue, skb) { + last = skb; /* Now that we have two receive queues this * shouldn't happen. */ @@ -1754,8 +1756,9 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, /* Do not sleep, just process backlog. */ release_sock(sk); lock_sock(sk); - } else - sk_wait_data(sk, &timeo); + } else { + sk_wait_data(sk, &timeo, last); + } if (user_recv) { int chunk; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 8fd9febaa5ba..8dab4e569571 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -613,7 +613,7 @@ static int llc_wait_data(struct sock *sk, long timeo) if (signal_pending(current)) break; rc = 0; - if (sk_wait_data(sk, &timeo)) + if (sk_wait_data(sk, &timeo, NULL)) break; } return rc; @@ -802,7 +802,7 @@ static int llc_ui_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, release_sock(sk); lock_sock(sk); } else - sk_wait_data(sk, &timeo); + sk_wait_data(sk, &timeo, NULL); if ((flags & MSG_PEEK) && peek_seq != llc->copied_seq) { net_dbg_ratelimited("LLC(%s:%d): Application bug, race in MSG_PEEK\n", From f2ce8a9e48385f444389e75cfe293637c3eb5410 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 24 Jul 2015 21:23:59 +0300 Subject: [PATCH 149/428] net/macb: improve big endian CPU support The commit a50dad355a53 (net: macb: Add big endian CPU support) converted I/O accessors to readl_relaxed() and writel_relaxed() and consequentially broke MACB driver on AVR32 platforms such as ATNGW100. This patch improves I/O access by checking endiannes first and use the corresponding methods. Fixes: a50dad355a53 (net: macb: Add big endian CPU support) Signed-off-by: Andy Shevchenko Signed-off-by: David S. Miller --- drivers/net/ethernet/cadence/macb.c | 103 ++++++++++++++++++++-------- drivers/net/ethernet/cadence/macb.h | 28 +++----- 2 files changed, 87 insertions(+), 44 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index caeb39561567..9d06e3d73939 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -104,6 +104,57 @@ static void *macb_rx_buffer(struct macb *bp, unsigned int index) return bp->rx_buffers + bp->rx_buffer_size * macb_rx_ring_wrap(index); } +/* I/O accessors */ +static u32 hw_readl_native(struct macb *bp, int offset) +{ + return __raw_readl(bp->regs + offset); +} + +static void hw_writel_native(struct macb *bp, int offset, u32 value) +{ + __raw_writel(value, bp->regs + offset); +} + +static u32 hw_readl(struct macb *bp, int offset) +{ + return readl_relaxed(bp->regs + offset); +} + +static void hw_writel(struct macb *bp, int offset, u32 value) +{ + writel_relaxed(value, bp->regs + offset); +} + +/* + * Find the CPU endianness by using the loopback bit of NCR register. When the + * CPU is in big endian we need to program swaped mode for management + * descriptor access. + */ +static bool hw_is_native_io(void __iomem *addr) +{ + u32 value = MACB_BIT(LLB); + + __raw_writel(value, addr + MACB_NCR); + value = __raw_readl(addr + MACB_NCR); + + /* Write 0 back to disable everything */ + __raw_writel(0, addr + MACB_NCR); + + return value == MACB_BIT(LLB); +} + +static bool hw_is_gem(void __iomem *addr, bool native_io) +{ + u32 id; + + if (native_io) + id = __raw_readl(addr + MACB_MID); + else + id = readl_relaxed(addr + MACB_MID); + + return MACB_BFEXT(IDNUM, id) >= 0x2; +} + static void macb_set_hwaddr(struct macb *bp) { u32 bottom; @@ -449,14 +500,14 @@ err_out: static void macb_update_stats(struct macb *bp) { - u32 __iomem *reg = bp->regs + MACB_PFR; u32 *p = &bp->hw_stats.macb.rx_pause_frames; u32 *end = &bp->hw_stats.macb.tx_pause_frames + 1; + int offset = MACB_PFR; WARN_ON((unsigned long)(end - p - 1) != (MACB_TPF - MACB_PFR) / 4); - for(; p < end; p++, reg++) - *p += readl_relaxed(reg); + for(; p < end; p++, offset += 4) + *p += bp->readl(bp, offset); } static int macb_halt_tx(struct macb *bp) @@ -1603,7 +1654,6 @@ static u32 macb_dbw(struct macb *bp) static void macb_configure_dma(struct macb *bp) { u32 dmacfg; - u32 tmp, ncr; if (macb_is_gem(bp)) { dmacfg = gem_readl(bp, DMACFG) & ~GEM_BF(RXBS, -1L); @@ -1613,22 +1663,11 @@ static void macb_configure_dma(struct macb *bp) dmacfg |= GEM_BIT(TXPBMS) | GEM_BF(RXBMS, -1L); dmacfg &= ~GEM_BIT(ENDIA_PKT); - /* Find the CPU endianness by using the loopback bit of net_ctrl - * register. save it first. When the CPU is in big endian we - * need to program swaped mode for management descriptor access. - */ - ncr = macb_readl(bp, NCR); - __raw_writel(MACB_BIT(LLB), bp->regs + MACB_NCR); - tmp = __raw_readl(bp->regs + MACB_NCR); - - if (tmp == MACB_BIT(LLB)) + if (bp->native_io) dmacfg &= ~GEM_BIT(ENDIA_DESC); else dmacfg |= GEM_BIT(ENDIA_DESC); /* CPU in big endian */ - /* Restore net_ctrl */ - macb_writel(bp, NCR, ncr); - if (bp->dev->features & NETIF_F_HW_CSUM) dmacfg |= GEM_BIT(TXCOEN); else @@ -1902,14 +1941,14 @@ static void gem_update_stats(struct macb *bp) for (i = 0; i < GEM_STATS_LEN; ++i, ++p) { u32 offset = gem_statistics[i].offset; - u64 val = readl_relaxed(bp->regs + offset); + u64 val = bp->readl(bp, offset); bp->ethtool_stats[i] += val; *p += val; if (offset == GEM_OCTTXL || offset == GEM_OCTRXL) { /* Add GEM_OCTTXH, GEM_OCTRXH */ - val = readl_relaxed(bp->regs + offset + 4); + val = bp->readl(bp, offset + 4); bp->ethtool_stats[i] += ((u64)val) << 32; *(++p) += val; } @@ -2190,7 +2229,7 @@ static void macb_configure_caps(struct macb *bp, const struct macb_config *dt_co if (dt_conf) bp->caps = dt_conf->caps; - if (macb_is_gem_hw(bp->regs)) { + if (hw_is_gem(bp->regs, bp->native_io)) { bp->caps |= MACB_CAPS_MACB_IS_GEM; dcfg = gem_readl(bp, DCFG1); @@ -2205,6 +2244,7 @@ static void macb_configure_caps(struct macb *bp, const struct macb_config *dt_co } static void macb_probe_queues(void __iomem *mem, + bool native_io, unsigned int *queue_mask, unsigned int *num_queues) { @@ -2219,7 +2259,7 @@ static void macb_probe_queues(void __iomem *mem, * we are early in the probe process and don't have the * MACB_CAPS_MACB_IS_GEM flag positioned */ - if (!macb_is_gem_hw(mem)) + if (!hw_is_gem(mem, native_io)) return; /* bit 0 is never set but queue 0 always exists */ @@ -2786,6 +2826,7 @@ static int macb_probe(struct platform_device *pdev) struct clk *pclk, *hclk, *tx_clk; unsigned int queue_mask, num_queues; struct macb_platform_data *pdata; + bool native_io; struct phy_device *phydev; struct net_device *dev; struct resource *regs; @@ -2794,6 +2835,11 @@ static int macb_probe(struct platform_device *pdev) struct macb *bp; int err; + regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); + mem = devm_ioremap_resource(&pdev->dev, regs); + if (IS_ERR(mem)) + return PTR_ERR(mem); + if (np) { const struct of_device_id *match; @@ -2809,14 +2855,9 @@ static int macb_probe(struct platform_device *pdev) if (err) return err; - regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); - mem = devm_ioremap_resource(&pdev->dev, regs); - if (IS_ERR(mem)) { - err = PTR_ERR(mem); - goto err_disable_clocks; - } + native_io = hw_is_native_io(mem); - macb_probe_queues(mem, &queue_mask, &num_queues); + macb_probe_queues(mem, native_io, &queue_mask, &num_queues); dev = alloc_etherdev_mq(sizeof(*bp), num_queues); if (!dev) { err = -ENOMEM; @@ -2831,6 +2872,14 @@ static int macb_probe(struct platform_device *pdev) bp->pdev = pdev; bp->dev = dev; bp->regs = mem; + bp->native_io = native_io; + if (native_io) { + bp->readl = hw_readl_native; + bp->writel = hw_writel_native; + } else { + bp->readl = hw_readl; + bp->writel = hw_writel; + } bp->num_queues = num_queues; bp->queue_mask = queue_mask; if (macb_config) diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index d74655993d4b..f245340f4dde 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -429,18 +429,12 @@ | GEM_BF(name, value)) /* Register access macros */ -#define macb_readl(port,reg) \ - readl_relaxed((port)->regs + MACB_##reg) -#define macb_writel(port,reg,value) \ - writel_relaxed((value), (port)->regs + MACB_##reg) -#define gem_readl(port, reg) \ - readl_relaxed((port)->regs + GEM_##reg) -#define gem_writel(port, reg, value) \ - writel_relaxed((value), (port)->regs + GEM_##reg) -#define queue_readl(queue, reg) \ - readl_relaxed((queue)->bp->regs + (queue)->reg) -#define queue_writel(queue, reg, value) \ - writel_relaxed((value), (queue)->bp->regs + (queue)->reg) +#define macb_readl(port, reg) (port)->readl((port), MACB_##reg) +#define macb_writel(port, reg, value) (port)->writel((port), MACB_##reg, (value)) +#define gem_readl(port, reg) (port)->readl((port), GEM_##reg) +#define gem_writel(port, reg, value) (port)->writel((port), GEM_##reg, (value)) +#define queue_readl(queue, reg) (queue)->bp->readl((queue)->bp, (queue)->reg) +#define queue_writel(queue, reg, value) (queue)->bp->writel((queue)->bp, (queue)->reg, (value)) /* Conditional GEM/MACB macros. These perform the operation to the correct * register dependent on whether the device is a GEM or a MACB. For registers @@ -785,6 +779,11 @@ struct macb_queue { struct macb { void __iomem *regs; + bool native_io; + + /* hardware IO accessors */ + u32 (*readl)(struct macb *bp, int offset); + void (*writel)(struct macb *bp, int offset, u32 value); unsigned int rx_tail; unsigned int rx_prepared_head; @@ -843,9 +842,4 @@ static inline bool macb_is_gem(struct macb *bp) return !!(bp->caps & MACB_CAPS_MACB_IS_GEM); } -static inline bool macb_is_gem_hw(void __iomem *addr) -{ - return !!(MACB_BFEXT(IDNUM, readl_relaxed(addr + MACB_MID)) >= 0x2); -} - #endif /* _MACB_H */ From f36dbe6a285e0628e67b7bd9d3b08599184d7d2c Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 24 Jul 2015 21:24:00 +0300 Subject: [PATCH 150/428] net/macb: check if macb_config present The commit 98b5a0f4a228 introduces jumbo frame support, but also it assumes that macb_config present which is not always true. The configuration without macb_config fails to boot. Unable to handle kernel NULL pointer dereference at virtual address 00000010 ptbr = 90350000 pgd = 00000000 Oops: Kernel access of bad area, sig: 11 [#1] FRAME_POINTER chip: 0x01f:0x1e82 rev 2 Modules linked in: CPU: 0 PID: 1 Comm: swapper Not tainted 4.2.0-rc3-next-20150723+ #13 task: 91c26000 ti: 91c28000 task.ti: 91c28000 PC is at macb_probe+0x140/0x61c Fixes: 98b5a0f4a228 (net: macb: Add support for jumbo frames) Signed-off-by: Andy Shevchenko Signed-off-by: David S. Miller --- drivers/net/ethernet/cadence/macb.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index 9d06e3d73939..6433232a1a2f 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -2887,9 +2887,8 @@ static int macb_probe(struct platform_device *pdev) bp->pclk = pclk; bp->hclk = hclk; bp->tx_clk = tx_clk; - if (macb_config->jumbo_max_len) { + if (macb_config) bp->jumbo_max_len = macb_config->jumbo_max_len; - } spin_lock_init(&bp->lock); From a35919e174350d3e236ea5f179177396e87b6894 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 24 Jul 2015 21:24:01 +0300 Subject: [PATCH 151/428] net/macb: use dev_*() when netdev is not yet registered To avoid messages like macb macb.0 (unnamed net_device) (uninitialized): Cadence caps 0x00000000 macb macb.0 (unnamed net_device) (uninitialized): invalid hw address, using random let's use dev_*() macros. Signed-off-by: Andy Shevchenko Signed-off-by: David S. Miller --- drivers/net/ethernet/cadence/macb.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index 6433232a1a2f..c4ffab9af563 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -211,7 +211,7 @@ static void macb_get_hwaddr(struct macb *bp) } } - netdev_info(bp->dev, "invalid hw address, using random\n"); + dev_info(&bp->pdev->dev, "invalid hw address, using random\n"); eth_hw_addr_random(bp->dev); } @@ -2240,7 +2240,7 @@ static void macb_configure_caps(struct macb *bp, const struct macb_config *dt_co bp->caps |= MACB_CAPS_FIFO_MODE; } - netdev_dbg(bp->dev, "Cadence caps 0x%08x\n", bp->caps); + dev_dbg(&bp->pdev->dev, "Cadence caps 0x%08x\n", bp->caps); } static void macb_probe_queues(void __iomem *mem, From 8bcbf82f31a94f8e4f939ac57478d808263c3890 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 24 Jul 2015 21:24:02 +0300 Subject: [PATCH 152/428] net/macb: suppress compiler warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch fixes the following warnings: drivers/net/ethernet/cadence/macb.c: In function ‘macb_handle_link_change’: drivers/net/ethernet/cadence/macb.c:266: warning: comparison between signed and unsigned drivers/net/ethernet/cadence/macb.c:267: warning: comparison between signed and unsigned drivers/net/ethernet/cadence/macb.c:291: warning: comparison between signed and unsigned drivers/net/ethernet/cadence/macb.c: In function ‘gem_update_stats’: drivers/net/ethernet/cadence/macb.c:1908: warning: comparison between signed and unsigned drivers/net/ethernet/cadence/macb.c: In function ‘gem_get_ethtool_strings’: drivers/net/ethernet/cadence/macb.c:1988: warning: comparison between signed and unsigned Signed-off-by: Andy Shevchenko Signed-off-by: David S. Miller --- drivers/net/ethernet/cadence/macb.c | 5 ++--- drivers/net/ethernet/cadence/macb.h | 6 +++--- 2 files changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index c4ffab9af563..77a5270ccae5 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -303,7 +303,6 @@ static void macb_handle_link_change(struct net_device *dev) struct macb *bp = netdev_priv(dev); struct phy_device *phydev = bp->phy_dev; unsigned long flags; - int status_change = 0; spin_lock_irqsave(&bp->lock, flags); @@ -1936,7 +1935,7 @@ static int macb_change_mtu(struct net_device *dev, int new_mtu) static void gem_update_stats(struct macb *bp) { - int i; + unsigned int i; u32 *p = &bp->hw_stats.gem.tx_octets_31_0; for (i = 0; i < GEM_STATS_LEN; ++i, ++p) { @@ -2015,7 +2014,7 @@ static int gem_get_sset_count(struct net_device *dev, int sset) static void gem_get_ethtool_strings(struct net_device *dev, u32 sset, u8 *p) { - int i; + unsigned int i; switch (sset) { case ETH_SS_STATS: diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index f245340f4dde..2aa102ecff6c 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -816,9 +816,9 @@ struct macb { struct mii_bus *mii_bus; struct phy_device *phy_dev; - unsigned int link; - unsigned int speed; - unsigned int duplex; + int link; + int speed; + int duplex; u32 caps; unsigned int dma_burst_length; From 94b295edc2c678212376a8aca9308cf6ee430b89 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 24 Jul 2015 21:24:03 +0300 Subject: [PATCH 153/428] net/macb: replace macb_count_tx_descriptors() by DIV_ROUND_UP() macb_count_tx_descriptors() repeats the generic macro DIV_ROUND_UP(). The patch does a replacement. There is no functional change. Signed-off-by: Andy Shevchenko Signed-off-by: David S. Miller --- drivers/net/ethernet/cadence/macb.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index 77a5270ccae5..c638757251e6 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -1157,12 +1157,6 @@ static void macb_poll_controller(struct net_device *dev) } #endif -static inline unsigned int macb_count_tx_descriptors(struct macb *bp, - unsigned int len) -{ - return (len + bp->max_tx_length - 1) / bp->max_tx_length; -} - static unsigned int macb_tx_map(struct macb *bp, struct macb_queue *queue, struct sk_buff *skb) @@ -1313,11 +1307,11 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev) * socket buffer: skb fragments of jumbo frames may need to be * splitted into many buffer descriptors. */ - count = macb_count_tx_descriptors(bp, skb_headlen(skb)); + count = DIV_ROUND_UP(skb_headlen(skb), bp->max_tx_length); nr_frags = skb_shinfo(skb)->nr_frags; for (f = 0; f < nr_frags; f++) { frag_size = skb_frag_size(&skb_shinfo(skb)->frags[f]); - count += macb_count_tx_descriptors(bp, frag_size); + count += DIV_ROUND_UP(frag_size, bp->max_tx_length); } spin_lock_irqsave(&bp->lock, flags); From e018a0cce3d849bc73e72686c571420adc40bad2 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 24 Jul 2015 21:24:04 +0300 Subject: [PATCH 154/428] net/macb: convert to kernel doc This patch coverts struct description to the kernel doc format. There is no functional change. Signed-off-by: Andy Shevchenko Signed-off-by: David S. Miller --- include/linux/platform_data/macb.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/include/linux/platform_data/macb.h b/include/linux/platform_data/macb.h index 044a124bfbbc..21b15f6fee25 100644 --- a/include/linux/platform_data/macb.h +++ b/include/linux/platform_data/macb.h @@ -8,11 +8,19 @@ #ifndef __MACB_PDATA_H__ #define __MACB_PDATA_H__ +/** + * struct macb_platform_data - platform data for MACB Ethernet + * @phy_mask: phy mask passed when register the MDIO bus + * within the driver + * @phy_irq_pin: PHY IRQ + * @is_rmii: using RMII interface? + * @rev_eth_addr: reverse Ethernet address byte order + */ struct macb_platform_data { u32 phy_mask; - int phy_irq_pin; /* PHY IRQ */ - u8 is_rmii; /* using RMII interface? */ - u8 rev_eth_addr; /* reverse Ethernet address byte order */ + int phy_irq_pin; + u8 is_rmii; + u8 rev_eth_addr; }; #endif /* __MACB_PDATA_H__ */ From 9c6893e0be38b6ca9a56a854226e51dee0a16a5a Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Sun, 26 Jul 2015 16:10:09 +0900 Subject: [PATCH 155/428] ALSA: fireworks: add support for AudioFire2 quirk Fireworks uses TSB43CB43(IceLynx-Micro) as its IEC 61883-1/6 interface. This chip includes ARM7 core, and loads and runs program. The firmware is stored in on-board memory and loaded every powering-on. Echo Audio ships several versions of firmwares for each model. These firmwares have each quirk and the quirk changes a sequence of packets. AudioFire2 has a quirk to transfer a first packet with non-zero in its dbc field. This causes ALSA Fireworks driver to detect discontinuity. As long as I investigated, firmware 5.7, 5.7.6 and 5.8 have this quirk. This commit adds a support for the quirk to handle AudioFire2 packets. For safe, CIP_SKIP_INIT_DBC_CHECK is applied to all versions of AudioFire2's firmwares. 02 00050002 90ffffff <- 42 0005000a 90013000 42 00050012 90014400 42 0005001a 90015800 02 0005001a 90ffffff 42 00050022 90019000 42 0005002a 9001a400 42 00050032 9001b800 02 00050032 90ffffff 42 0005003a 9001d000 42 00050042 9001e400 42 0005004a 9001f800 02 0005004a 90ffffff Signed-off-by: Takashi Sakamoto Signed-off-by: Takashi Iwai --- sound/firewire/fireworks/fireworks.c | 2 ++ sound/firewire/fireworks/fireworks.h | 1 + sound/firewire/fireworks/fireworks_stream.c | 3 +++ 3 files changed, 6 insertions(+) diff --git a/sound/firewire/fireworks/fireworks.c b/sound/firewire/fireworks/fireworks.c index 2682e7e3e5c9..c670db4eee70 100644 --- a/sound/firewire/fireworks/fireworks.c +++ b/sound/firewire/fireworks/fireworks.c @@ -248,6 +248,8 @@ efw_probe(struct fw_unit *unit, err = get_hardware_info(efw); if (err < 0) goto error; + if (entry->model_id == MODEL_ECHO_AUDIOFIRE_2) + efw->is_af2 = true; if (entry->model_id == MODEL_ECHO_AUDIOFIRE_9) efw->is_af9 = true; diff --git a/sound/firewire/fireworks/fireworks.h b/sound/firewire/fireworks/fireworks.h index 4f0201a95222..c33252b7bc84 100644 --- a/sound/firewire/fireworks/fireworks.h +++ b/sound/firewire/fireworks/fireworks.h @@ -70,6 +70,7 @@ struct snd_efw { bool resp_addr_changable; /* for quirks */ + bool is_af2; bool is_af9; u32 firmware_version; diff --git a/sound/firewire/fireworks/fireworks_stream.c b/sound/firewire/fireworks/fireworks_stream.c index c55db1bddc80..a0762dd6231e 100644 --- a/sound/firewire/fireworks/fireworks_stream.c +++ b/sound/firewire/fireworks/fireworks_stream.c @@ -172,6 +172,9 @@ int snd_efw_stream_init_duplex(struct snd_efw *efw) efw->tx_stream.flags |= CIP_DBC_IS_END_EVENT; /* Fireworks reset dbc at bus reset. */ efw->tx_stream.flags |= CIP_SKIP_DBC_ZERO_CHECK; + /* AudioFire2 starts packets with non-zero dbc. */ + if (efw->is_af2) + efw->tx_stream.flags |= CIP_SKIP_INIT_DBC_CHECK; /* AudioFire9 always reports wrong dbs. */ if (efw->is_af9) efw->tx_stream.flags |= CIP_WRONG_DBS; From 7025e88a79d64aa4ba58fd03d630a78b12cce6ae Mon Sep 17 00:00:00 2001 From: WingMan Kwok Date: Fri, 24 Jul 2015 15:02:29 -0400 Subject: [PATCH 156/428] net: netcp: Fixes SGMII reset on network interface shutdown This patch asserts SGMII RTRESET, i.e. resetting the SGMII Tx/Rx logic, during network interface shutdown to avoid having the hardware wedge when shutting down with high incoming traffic rates. This is cleared (brought out of RTRESET) when the interface is brought back up. Signed-off-by: WingMan Kwok Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/netcp.h | 1 + drivers/net/ethernet/ti/netcp_ethss.c | 18 ++++++++++++++++ drivers/net/ethernet/ti/netcp_sgmii.c | 30 +++++++++++++++++++++++++-- 3 files changed, 47 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/ti/netcp.h b/drivers/net/ethernet/ti/netcp.h index bbacf5cccec2..a8a730641bbb 100644 --- a/drivers/net/ethernet/ti/netcp.h +++ b/drivers/net/ethernet/ti/netcp.h @@ -223,6 +223,7 @@ void *netcp_device_find_module(struct netcp_device *netcp_device, /* SGMII functions */ int netcp_sgmii_reset(void __iomem *sgmii_ofs, int port); +bool netcp_sgmii_rtreset(void __iomem *sgmii_ofs, int port, bool set); int netcp_sgmii_get_port_link(void __iomem *sgmii_ofs, int port); int netcp_sgmii_config(void __iomem *sgmii_ofs, int port, u32 interface); diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index 9b7e0a34c98b..a21881219865 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -1901,11 +1901,28 @@ static void gbe_port_config(struct gbe_priv *gbe_dev, struct gbe_slave *slave, writel(slave->mac_control, GBE_REG_ADDR(slave, emac_regs, mac_control)); } +static void gbe_sgmii_rtreset(struct gbe_priv *priv, + struct gbe_slave *slave, bool set) +{ + void __iomem *sgmii_port_regs; + + if (SLAVE_LINK_IS_XGMII(slave)) + return; + + if ((priv->ss_version == GBE_SS_VERSION_14) && (slave->slave_num >= 2)) + sgmii_port_regs = priv->sgmii_port34_regs; + else + sgmii_port_regs = priv->sgmii_port_regs; + + netcp_sgmii_rtreset(sgmii_port_regs, slave->slave_num, set); +} + static void gbe_slave_stop(struct gbe_intf *intf) { struct gbe_priv *gbe_dev = intf->gbe_dev; struct gbe_slave *slave = intf->slave; + gbe_sgmii_rtreset(gbe_dev, slave, true); gbe_port_reset(slave); /* Disable forwarding */ cpsw_ale_control_set(gbe_dev->ale, slave->port_num, @@ -1947,6 +1964,7 @@ static int gbe_slave_open(struct gbe_intf *gbe_intf) gbe_sgmii_config(priv, slave); gbe_port_reset(slave); + gbe_sgmii_rtreset(priv, slave, false); gbe_port_config(priv, slave, priv->rx_packet_max); gbe_set_slave_mac(slave, gbe_intf); /* enable forwarding */ diff --git a/drivers/net/ethernet/ti/netcp_sgmii.c b/drivers/net/ethernet/ti/netcp_sgmii.c index dbeb14266e2f..5d8419f658d0 100644 --- a/drivers/net/ethernet/ti/netcp_sgmii.c +++ b/drivers/net/ethernet/ti/netcp_sgmii.c @@ -18,6 +18,9 @@ #include "netcp.h" +#define SGMII_SRESET_RESET BIT(0) +#define SGMII_SRESET_RTRESET BIT(1) + #define SGMII_REG_STATUS_LOCK BIT(4) #define SGMII_REG_STATUS_LINK BIT(0) #define SGMII_REG_STATUS_AUTONEG BIT(2) @@ -51,12 +54,35 @@ static void sgmii_write_reg_bit(void __iomem *base, int reg, u32 val) int netcp_sgmii_reset(void __iomem *sgmii_ofs, int port) { /* Soft reset */ - sgmii_write_reg_bit(sgmii_ofs, SGMII_SRESET_REG(port), 0x1); - while (sgmii_read_reg(sgmii_ofs, SGMII_SRESET_REG(port)) != 0x0) + sgmii_write_reg_bit(sgmii_ofs, SGMII_SRESET_REG(port), + SGMII_SRESET_RESET); + + while ((sgmii_read_reg(sgmii_ofs, SGMII_SRESET_REG(port)) & + SGMII_SRESET_RESET) != 0x0) ; + return 0; } +/* port is 0 based */ +bool netcp_sgmii_rtreset(void __iomem *sgmii_ofs, int port, bool set) +{ + u32 reg; + bool oldval; + + /* Initiate a soft reset */ + reg = sgmii_read_reg(sgmii_ofs, SGMII_SRESET_REG(port)); + oldval = (reg & SGMII_SRESET_RTRESET) != 0x0; + if (set) + reg |= SGMII_SRESET_RTRESET; + else + reg &= ~SGMII_SRESET_RTRESET; + sgmii_write_reg(sgmii_ofs, SGMII_SRESET_REG(port), reg); + wmb(); + + return oldval; +} + int netcp_sgmii_get_port_link(void __iomem *sgmii_ofs, int port) { u32 status = 0, link = 0; From b9d9c9efc292dd0ffe172780f915ed74eba3556c Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 27 Jul 2015 10:13:37 +0200 Subject: [PATCH 157/428] ALSA: hda - Apply fixup for another Toshiba Satellite S50D Toshiba Satellite S50D has another model with a different PCI SSID (1179:fa93) while the previous fixup was for 1179:fa91. Adjust the fixup entry with SND_PCI_QUIRK_MASK() to match with both devices. Reported-by: Tim Sample Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_sigmatel.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c index dcc7fe91244c..9d947aef2c8b 100644 --- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -2920,7 +2920,8 @@ static const struct snd_pci_quirk stac92hd83xxx_fixup_tbl[] = { SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x148a, "HP Mini", STAC_92HD83XXX_HP_LED), SND_PCI_QUIRK_VENDOR(PCI_VENDOR_ID_HP, "HP", STAC_92HD83XXX_HP), - SND_PCI_QUIRK(PCI_VENDOR_ID_TOSHIBA, 0xfa91, + /* match both for 0xfa91 and 0xfa93 */ + SND_PCI_QUIRK_MASK(PCI_VENDOR_ID_TOSHIBA, 0xfffd, 0xfa91, "Toshiba Satellite S50D", STAC_92HD83XXX_GPIO10_EAPD), {} /* terminator */ }; From 8fff755e9f8d0f70a595e79f248695ce6aef5cc3 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 25 Jul 2015 22:38:02 +0200 Subject: [PATCH 158/428] net: fec: Ensure clocks are enabled while using mdio bus When a switch is attached to the mdio bus, the mdio bus can be used while the interface is not open. If the IPG clock is not enabled, MDIO reads/writes will simply time out. Add support for runtime PM to control this clock. Enable/disable this clock using runtime PM, with open()/close() and mdio read()/write() function triggering runtime PM operations. Since PM is optional, the IPG clock is enabled at probe and is no longer modified by fec_enet_clk_enable(), thus if PM is not enabled in the kernel, it is guaranteed the clock is running when MDIO operations are performed. Signed-off-by: Andrew Lunn Signed-off-by: Lucas Stach Cc: tyler.baker@linaro.org Cc: fabio.estevam@freescale.com Cc: shawn.guo@linaro.org Tested-by: Fabio Estevam Tested-by: Tyler Baker Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fec_main.c | 89 +++++++++++++++++++---- 1 file changed, 76 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 5e8b8370b5a7..32e3807c650e 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -77,6 +78,7 @@ static void fec_enet_itr_coal_init(struct net_device *ndev); #define FEC_ENET_RAEM_V 0x8 #define FEC_ENET_RAFL_V 0x8 #define FEC_ENET_OPD_V 0xFFF0 +#define FEC_MDIO_PM_TIMEOUT 100 /* ms */ static struct platform_device_id fec_devtype[] = { { @@ -1767,7 +1769,13 @@ static void fec_enet_adjust_link(struct net_device *ndev) static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum) { struct fec_enet_private *fep = bus->priv; + struct device *dev = &fep->pdev->dev; unsigned long time_left; + int ret = 0; + + ret = pm_runtime_get_sync(dev); + if (IS_ERR_VALUE(ret)) + return ret; fep->mii_timeout = 0; init_completion(&fep->mdio_done); @@ -1783,18 +1791,30 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum) if (time_left == 0) { fep->mii_timeout = 1; netdev_err(fep->netdev, "MDIO read timeout\n"); - return -ETIMEDOUT; + ret = -ETIMEDOUT; + goto out; } - /* return value */ - return FEC_MMFR_DATA(readl(fep->hwp + FEC_MII_DATA)); + ret = FEC_MMFR_DATA(readl(fep->hwp + FEC_MII_DATA)); + +out: + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); + + return ret; } static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum, u16 value) { struct fec_enet_private *fep = bus->priv; + struct device *dev = &fep->pdev->dev; unsigned long time_left; + int ret = 0; + + ret = pm_runtime_get_sync(dev); + if (IS_ERR_VALUE(ret)) + return ret; fep->mii_timeout = 0; init_completion(&fep->mdio_done); @@ -1811,10 +1831,13 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum, if (time_left == 0) { fep->mii_timeout = 1; netdev_err(fep->netdev, "MDIO write timeout\n"); - return -ETIMEDOUT; + ret = -ETIMEDOUT; } - return 0; + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); + + return ret; } static int fec_enet_clk_enable(struct net_device *ndev, bool enable) @@ -1826,9 +1849,6 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable) ret = clk_prepare_enable(fep->clk_ahb); if (ret) return ret; - ret = clk_prepare_enable(fep->clk_ipg); - if (ret) - goto failed_clk_ipg; if (fep->clk_enet_out) { ret = clk_prepare_enable(fep->clk_enet_out); if (ret) @@ -1852,7 +1872,6 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable) } } else { clk_disable_unprepare(fep->clk_ahb); - clk_disable_unprepare(fep->clk_ipg); if (fep->clk_enet_out) clk_disable_unprepare(fep->clk_enet_out); if (fep->clk_ptp) { @@ -1874,8 +1893,6 @@ failed_clk_ptp: if (fep->clk_enet_out) clk_disable_unprepare(fep->clk_enet_out); failed_clk_enet_out: - clk_disable_unprepare(fep->clk_ipg); -failed_clk_ipg: clk_disable_unprepare(fep->clk_ahb); return ret; @@ -2847,10 +2864,14 @@ fec_enet_open(struct net_device *ndev) struct fec_enet_private *fep = netdev_priv(ndev); int ret; + ret = pm_runtime_get_sync(&fep->pdev->dev); + if (IS_ERR_VALUE(ret)) + return ret; + pinctrl_pm_select_default_state(&fep->pdev->dev); ret = fec_enet_clk_enable(ndev, true); if (ret) - return ret; + goto clk_enable; /* I should reset the ring buffers here, but I don't yet know * a simple way to do that. @@ -2881,6 +2902,9 @@ err_enet_mii_probe: fec_enet_free_buffers(ndev); err_enet_alloc: fec_enet_clk_enable(ndev, false); +clk_enable: + pm_runtime_mark_last_busy(&fep->pdev->dev); + pm_runtime_put_autosuspend(&fep->pdev->dev); pinctrl_pm_select_sleep_state(&fep->pdev->dev); return ret; } @@ -2903,6 +2927,9 @@ fec_enet_close(struct net_device *ndev) fec_enet_clk_enable(ndev, false); pinctrl_pm_select_sleep_state(&fep->pdev->dev); + pm_runtime_mark_last_busy(&fep->pdev->dev); + pm_runtime_put_autosuspend(&fep->pdev->dev); + fec_enet_free_buffers(ndev); return 0; @@ -3388,6 +3415,10 @@ fec_probe(struct platform_device *pdev) if (ret) goto failed_clk; + ret = clk_prepare_enable(fep->clk_ipg); + if (ret) + goto failed_clk_ipg; + fep->reg_phy = devm_regulator_get(&pdev->dev, "phy"); if (!IS_ERR(fep->reg_phy)) { ret = regulator_enable(fep->reg_phy); @@ -3400,6 +3431,11 @@ fec_probe(struct platform_device *pdev) fep->reg_phy = NULL; } + pm_runtime_set_autosuspend_delay(&pdev->dev, FEC_MDIO_PM_TIMEOUT); + pm_runtime_use_autosuspend(&pdev->dev); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + fec_reset_phy(pdev); if (fep->bufdesc_ex) @@ -3447,6 +3483,10 @@ fec_probe(struct platform_device *pdev) fep->rx_copybreak = COPYBREAK_DEFAULT; INIT_WORK(&fep->tx_timeout_work, fec_enet_timeout_work); + + pm_runtime_mark_last_busy(&pdev->dev); + pm_runtime_put_autosuspend(&pdev->dev); + return 0; failed_register: @@ -3458,6 +3498,8 @@ failed_init: if (fep->reg_phy) regulator_disable(fep->reg_phy); failed_regulator: + clk_disable_unprepare(fep->clk_ipg); +failed_clk_ipg: fec_enet_clk_enable(ndev, false); failed_clk: failed_phy: @@ -3567,7 +3609,28 @@ failed_clk: return ret; } -static SIMPLE_DEV_PM_OPS(fec_pm_ops, fec_suspend, fec_resume); +static int __maybe_unused fec_runtime_suspend(struct device *dev) +{ + struct net_device *ndev = dev_get_drvdata(dev); + struct fec_enet_private *fep = netdev_priv(ndev); + + clk_disable_unprepare(fep->clk_ipg); + + return 0; +} + +static int __maybe_unused fec_runtime_resume(struct device *dev) +{ + struct net_device *ndev = dev_get_drvdata(dev); + struct fec_enet_private *fep = netdev_priv(ndev); + + return clk_prepare_enable(fep->clk_ipg); +} + +static const struct dev_pm_ops fec_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(fec_suspend, fec_resume) + SET_RUNTIME_PM_OPS(fec_runtime_suspend, fec_runtime_resume, NULL) +}; static struct platform_driver fec_driver = { .driver = { From ac8c79304280da6ef05c348a9da03ab04898b994 Mon Sep 17 00:00:00 2001 From: Kamil Dudka Date: Wed, 15 Jul 2015 17:18:15 +0200 Subject: [PATCH 159/428] drm/nouveau: hold mutex when calling nouveau_abi16_fini() This was the only access to cli->abi16 without holding the mutex. Signed-off-by: Kamil Dudka --- drivers/gpu/drm/nouveau/nouveau_drm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 649024d4daf1..01c78a4a3efa 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -865,8 +865,10 @@ nouveau_drm_preclose(struct drm_device *dev, struct drm_file *fpriv) pm_runtime_get_sync(dev->dev); + mutex_lock(&cli->mutex); if (cli->abi16) nouveau_abi16_fini(cli->abi16); + mutex_unlock(&cli->mutex); mutex_lock(&drm->client.mutex); list_del(&cli->head); From 7512223b1ece29a5968ed8b67ccb891d21b7834b Mon Sep 17 00:00:00 2001 From: Kamil Dudka Date: Wed, 15 Jul 2015 22:57:43 +0200 Subject: [PATCH 160/428] drm/nouveau/drm/nv04-nv40/instmem: protect access to priv->heap by mutex This fixes the list_del corruption reported at . Signed-off-by: Kamil Dudka --- drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv04.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv04.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv04.c index 80614f1b2074..282143f49d72 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv04.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv04.c @@ -50,7 +50,12 @@ nv04_instobj_dtor(struct nvkm_object *object) { struct nv04_instmem_priv *priv = (void *)nvkm_instmem(object); struct nv04_instobj_priv *node = (void *)object; + struct nvkm_subdev *subdev = (void *)priv; + + mutex_lock(&subdev->mutex); nvkm_mm_free(&priv->heap, &node->mem); + mutex_unlock(&subdev->mutex); + nvkm_instobj_destroy(&node->base); } @@ -62,6 +67,7 @@ nv04_instobj_ctor(struct nvkm_object *parent, struct nvkm_object *engine, struct nv04_instmem_priv *priv = (void *)nvkm_instmem(parent); struct nv04_instobj_priv *node; struct nvkm_instobj_args *args = data; + struct nvkm_subdev *subdev = (void *)priv; int ret; if (!args->align) @@ -72,8 +78,10 @@ nv04_instobj_ctor(struct nvkm_object *parent, struct nvkm_object *engine, if (ret) return ret; + mutex_lock(&subdev->mutex); ret = nvkm_mm_head(&priv->heap, 0, 1, args->size, args->size, args->align, &node->mem); + mutex_unlock(&subdev->mutex); if (ret) return ret; From 9694554691d26226f84fa1d6f500b7e7c9288510 Mon Sep 17 00:00:00 2001 From: Roy Spliet Date: Sat, 23 May 2015 10:37:42 +0200 Subject: [PATCH 161/428] drm/nouveau/clk/gt215: u32->s32 for difference in req. and set clock This difference can of course be negative too... Signed-off-by: Roy Spliet Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c index 822d32a28d6e..065e9f5c8db9 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c @@ -180,7 +180,8 @@ gt215_clk_info(struct nvkm_clk *clock, int clk, u32 khz, struct gt215_clk_info *info) { struct gt215_clk_priv *priv = (void *)clock; - u32 oclk, sclk, sdiv, diff; + u32 oclk, sclk, sdiv; + s32 diff; info->clk = 0; From f5654d9555b470d05be9d6d26cfb8fb79239ac3e Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 16 Oct 2014 11:54:54 +0200 Subject: [PATCH 162/428] drm/nouveau: Do not leak client objects The memory allocated for a nouveau_cli object in nouveau_cli_create() is never freed. Free the memory in nouveau_cli_destroy() to plug this leak. kmemleak recorded this after running a couple of nouveau test programs. Note that kmemleak points at drm_open_helper() because for some reason it thinks that skipping the first two stack frames is a good idea. Signed-off-by: Thierry Reding Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nouveau_drm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 01c78a4a3efa..477cbb12809b 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -128,6 +128,7 @@ nouveau_cli_destroy(struct nouveau_cli *cli) nvkm_vm_ref(NULL, &nvxx_client(&cli->base)->vm, NULL); nvif_client_fini(&cli->base); usif_client_fini(cli); + kfree(cli); } static void From a67e14b0b6e35355411a4f2b05f8d087a196dac9 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Wed, 8 Apr 2015 18:08:13 +0900 Subject: [PATCH 163/428] drm/nouveau/platform: fix compile error if !CONFIG_IOMMU The lack of IOMMU API support can make nouveau_platform_probe_iommu() fail to compile because struct iommu_ops is then empty. Fix this by skipping IOMMU probe in that case - lack of IOMMU on platform devices is sub-optimal, but is not an error. Signed-off-by: Alexandre Courbot Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nouveau_platform.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nouveau_platform.c b/drivers/gpu/drm/nouveau/nouveau_platform.c index 775277f1edb0..dcfbbfaf1739 100644 --- a/drivers/gpu/drm/nouveau/nouveau_platform.c +++ b/drivers/gpu/drm/nouveau/nouveau_platform.c @@ -92,6 +92,8 @@ static int nouveau_platform_power_down(struct nouveau_platform_gpu *gpu) return 0; } +#if IS_ENABLED(CONFIG_IOMMU_API) + static void nouveau_platform_probe_iommu(struct device *dev, struct nouveau_platform_gpu *gpu) { @@ -158,6 +160,20 @@ static void nouveau_platform_remove_iommu(struct device *dev, } } +#else + +static void nouveau_platform_probe_iommu(struct device *dev, + struct nouveau_platform_gpu *gpu) +{ +} + +static void nouveau_platform_remove_iommu(struct device *dev, + struct nouveau_platform_gpu *gpu) +{ +} + +#endif + static int nouveau_platform_probe(struct platform_device *pdev) { struct nouveau_platform_gpu *gpu; From 9c56be4cf3d6db5a20c3b6483bd4cdc21c15cf4f Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Tue, 28 Apr 2015 16:17:07 +0900 Subject: [PATCH 164/428] drm/nouveau/ibus/gk20a: increase SM wait timeout Increase clock timeout for SYS, FPB and GPC in order to avoid operation failure at high gpcclk rate. Signed-off-by: Alexandre Courbot Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk20a.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk20a.c index c0fdb89e74ac..24dcdfb58a8d 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk20a.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk20a.c @@ -38,6 +38,14 @@ gk20a_ibus_init_priv_ring(struct gk20a_ibus_priv *priv) nv_wr32(priv, 0x12004c, 0x4); nv_wr32(priv, 0x122204, 0x2); nv_rd32(priv, 0x122204); + + /* + * Bug: increase clock timeout to avoid operation failure at high + * gpcclk rate. + */ + nv_wr32(priv, 0x122354, 0x800); + nv_wr32(priv, 0x128328, 0x800); + nv_wr32(priv, 0x124320, 0x800); } static void From 1addc12648521d15ef33c1a88d0354850190dfa7 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Thu, 16 Apr 2015 11:33:32 +0900 Subject: [PATCH 165/428] drm/nouveau/fifo/gk104: kick channels when deactivating them Kicking channels is part of their deactivation process. Maxwell chips are particularly sensitive to this, and can start fetching the previous pushbuffer of a recycled channel if this is not done. While we are at it, improve the channel preemption code to only wait for bit 20 of 0x002634 to turn to 0, as it is the bit indicating a preempt is pending. Signed-off-by: Alexandre Courbot Signed-off-by: Ben Skeggs --- .../gpu/drm/nouveau/nvkm/engine/fifo/gk104.c | 29 ++++++++++++++----- 1 file changed, 21 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c index e10f9644140f..52c22b026005 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c @@ -165,15 +165,31 @@ gk104_fifo_context_attach(struct nvkm_object *parent, return 0; } +static int +gk104_fifo_chan_kick(struct gk104_fifo_chan *chan) +{ + struct nvkm_object *obj = (void *)chan; + struct gk104_fifo_priv *priv = (void *)obj->engine; + + nv_wr32(priv, 0x002634, chan->base.chid); + if (!nv_wait(priv, 0x002634, 0x100000, 0x000000)) { + nv_error(priv, "channel %d [%s] kick timeout\n", + chan->base.chid, nvkm_client_name(chan)); + return -EBUSY; + } + + return 0; +} + static int gk104_fifo_context_detach(struct nvkm_object *parent, bool suspend, struct nvkm_object *object) { struct nvkm_bar *bar = nvkm_bar(parent); - struct gk104_fifo_priv *priv = (void *)parent->engine; struct gk104_fifo_base *base = (void *)parent->parent; struct gk104_fifo_chan *chan = (void *)parent; u32 addr; + int ret; switch (nv_engidx(object->engine)) { case NVDEV_ENGINE_SW : return 0; @@ -188,13 +204,9 @@ gk104_fifo_context_detach(struct nvkm_object *parent, bool suspend, return -EINVAL; } - nv_wr32(priv, 0x002634, chan->base.chid); - if (!nv_wait(priv, 0x002634, 0xffffffff, chan->base.chid)) { - nv_error(priv, "channel %d [%s] kick timeout\n", - chan->base.chid, nvkm_client_name(chan)); - if (suspend) - return -EBUSY; - } + ret = gk104_fifo_chan_kick(chan); + if (ret && suspend) + return ret; if (addr) { nv_wo32(base, addr + 0x00, 0x00000000); @@ -319,6 +331,7 @@ gk104_fifo_chan_fini(struct nvkm_object *object, bool suspend) gk104_fifo_runlist_update(priv, chan->engine); } + gk104_fifo_chan_kick(chan); nv_wr32(priv, 0x800000 + (chid * 8), 0x00000000); return nvkm_fifo_channel_fini(&chan->base, suspend); } From 19bf09cecfec1891069f1d5353a0298debd98713 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Wed, 29 Apr 2015 23:04:23 +0900 Subject: [PATCH 166/428] drm/nouveau/gr/gf100: wait on bottom half of FE's pipeline When emitting the ICMD bundle, wait on the bottom half (bit 3 of the GR_STATUS register) instead of upper half (bit 2) to make sure methods are effectively emitted. Signed-off-by: Alexandre Courbot Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c index 5606c25e5d02..01efc2c96045 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c @@ -699,7 +699,7 @@ gf100_gr_icmd(struct gf100_gr_priv *priv, const struct gf100_gr_pack *p) while (addr < next) { nv_wr32(priv, 0x400200, addr); - nv_wait(priv, 0x400700, 0x00000002, 0x00000000); + nv_wait(priv, 0x400700, 0x00000004, 0x00000000); addr += init->pitch; } } From 4a8cf4513dd4279d342eb41abdb9db65285732b3 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Mon, 27 Apr 2015 17:25:11 +0900 Subject: [PATCH 167/428] drm/nouveau/gr/gf100: wait for GR idle after GO_IDLE bundle After submitting a GO_IDLE bundle, one must wait for GR to effectively be idle before submitting the next bundle. Failure to do so may result in undefined behavior in some rare cases. Signed-off-by: Alexandre Courbot Reported-by: Kary Jin Signed-off-by: Ben Skeggs --- .../gpu/drm/nouveau/nvkm/engine/gr/gf100.c | 37 +++++++++++++++++++ .../gpu/drm/nouveau/nvkm/engine/gr/gf100.h | 1 + 2 files changed, 38 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c index 01efc2c96045..ca11ddb6ed46 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c @@ -663,6 +663,37 @@ gf100_gr_zbc_init(struct gf100_gr_priv *priv) gf100_gr_zbc_clear_depth(priv, index); } +/** + * Wait until GR goes idle. GR is considered idle if it is disabled by the + * MC (0x200) register, or GR is not busy and a context switch is not in + * progress. + */ +int +gf100_gr_wait_idle(struct gf100_gr_priv *priv) +{ + unsigned long end_jiffies = jiffies + msecs_to_jiffies(2000); + bool gr_enabled, ctxsw_active, gr_busy; + + do { + /* + * required to make sure FIFO_ENGINE_STATUS (0x2640) is + * up-to-date + */ + nv_rd32(priv, 0x400700); + + gr_enabled = nv_rd32(priv, 0x200) & 0x1000; + ctxsw_active = nv_rd32(priv, 0x2640) & 0x8000; + gr_busy = nv_rd32(priv, 0x40060c) & 0x1; + + if (!gr_enabled || (!gr_busy && !ctxsw_active)) + return 0; + } while (time_before(jiffies, end_jiffies)); + + nv_error(priv, "wait for idle timeout (en: %d, ctxsw: %d, busy: %d)\n", + gr_enabled, ctxsw_active, gr_busy); + return -EAGAIN; +} + void gf100_gr_mmio(struct gf100_gr_priv *priv, const struct gf100_gr_pack *p) { @@ -699,6 +730,12 @@ gf100_gr_icmd(struct gf100_gr_priv *priv, const struct gf100_gr_pack *p) while (addr < next) { nv_wr32(priv, 0x400200, addr); + /** + * Wait for GR to go idle after submitting a + * GO_IDLE bundle + */ + if ((addr & 0xffff) == 0xe100) + gf100_gr_wait_idle(priv); nv_wait(priv, 0x400700, 0x00000004, 0x00000000); addr += init->pitch; } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h index 8af1a89eda84..c9533fdac4fc 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h @@ -181,6 +181,7 @@ struct gf100_gr_oclass { int ppc_nr; }; +int gf100_gr_wait_idle(struct gf100_gr_priv *); void gf100_gr_mmio(struct gf100_gr_priv *, const struct gf100_gr_pack *); void gf100_gr_icmd(struct gf100_gr_priv *, const struct gf100_gr_pack *); void gf100_gr_mthd(struct gf100_gr_priv *, const struct gf100_gr_pack *); From 3693d544056b822f7f2454da5acb7eda9471b902 Mon Sep 17 00:00:00 2001 From: Samuel Pitoiset Date: Sun, 7 Jun 2015 22:40:11 +0200 Subject: [PATCH 168/428] drm/nouveau/pm: prevent freeing the wrong engine context This fixes a crash when multiple PM engine contexts are created. Signed-off-by: Samuel Pitoiset Reviewed-by: Martin Peres Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c index 2006c445938d..274457ca3fef 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c @@ -332,9 +332,12 @@ static void nvkm_perfctx_dtor(struct nvkm_object *object) { struct nvkm_pm *ppm = (void *)object->engine; + struct nvkm_perfctx *ctx = (void *)object; + mutex_lock(&nv_subdev(ppm)->mutex); - nvkm_engctx_destroy(&ppm->context->base); - ppm->context = NULL; + nvkm_engctx_destroy(&ctx->base); + if (ppm->context == ctx) + ppm->context = NULL; mutex_unlock(&nv_subdev(ppm)->mutex); } From 305c1959ea60ddcae5142a20c50db849a40c2a35 Mon Sep 17 00:00:00 2001 From: Samuel Pitoiset Date: Sun, 7 Jun 2015 22:40:12 +0200 Subject: [PATCH 169/428] drm/nouveau/pm: fix a potential race condition when creating an engine context There is always the possiblity that the ppm->context pointer would get partially updated and accidentally would equal ctx. This would allow two contexts to co-exist, which is not acceptable. Moving the test to the critical section takes care of this problem. Signed-off-by: Samuel Pitoiset Signed-off-by: Martin Peres Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c index 274457ca3fef..4cf36a3aa814 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c @@ -358,12 +358,11 @@ nvkm_perfctx_ctor(struct nvkm_object *parent, struct nvkm_object *engine, mutex_lock(&nv_subdev(ppm)->mutex); if (ppm->context == NULL) ppm->context = ctx; + if (ctx != ppm->context) + ret = -EBUSY; mutex_unlock(&nv_subdev(ppm)->mutex); - if (ctx != ppm->context) - return -EBUSY; - - return 0; + return ret; } struct nvkm_oclass From 1196bcf92142ad6f022df01ab8120aefa908eaea Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Mon, 21 Jul 2014 14:02:58 +0200 Subject: [PATCH 170/428] drm/nouveau/disp: Use NULL for pointers The return type of exec_lookup() is struct nvkm_output *, so it should return NULL rather than 0. Signed-off-by: Thierry Reding Reviewed-by: Emil Velikov Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nvkm/engine/disp/gf110.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf110.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf110.c index 9ef6728c528d..7f2f05f78cc8 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf110.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf110.c @@ -809,7 +809,7 @@ exec_lookup(struct nv50_disp_priv *priv, int head, int or, u32 ctrl, case 0x00000900: type = DCB_OUTPUT_DP; mask = 2; break; default: nv_error(priv, "unknown SOR mc 0x%08x\n", ctrl); - return 0x0000; + return NULL; } } From 360ccb8436ce83b9c25f969cee7b1b607899063b Mon Sep 17 00:00:00 2001 From: Ilia Mirkin Date: Thu, 18 Jun 2015 23:59:06 -0400 Subject: [PATCH 171/428] drm/nouveau/bios: add 0x59 and 0x5a opcodes Opcode 0x5a is a register write for data looked up from another part of the VBIOS image. 0x59 is a more complex opcode, but we may as well recognize it. These occur on a single known instance of Riva TNT2 hardware. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=91025 Signed-off-by: Ilia Mirkin Signed-off-by: Ben Skeggs --- .../gpu/drm/nouveau/nvkm/subdev/bios/init.c | 24 +++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c index f67cdae1e90a..1f590f839f76 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c @@ -577,6 +577,9 @@ init_reserved(struct nvbios_init *init) u8 length, i; switch (opcode) { + case 0x59: + length = 7; + break; case 0xaa: length = 4; break; @@ -1284,6 +1287,25 @@ init_zm_reg_sequence(struct nvbios_init *init) } } +/** + * INIT_ZM_REG_INDIRECT - opcode 0x5a + * + */ +static void +init_zm_reg_indirect(struct nvbios_init *init) +{ + struct nvkm_bios *bios = init->bios; + u32 reg = nv_ro32(bios, init->offset + 1); + u16 addr = nv_ro16(bios, init->offset + 5); + u32 data = nv_ro32(bios, addr); + + trace("ZM_REG_INDIRECT\tR[0x%06x] = VBIOS[0x%04x] = 0x%08x\n", + reg, addr, data); + init->offset += 7; + + init_wr32(init, addr, data); +} + /** * INIT_SUB_DIRECT - opcode 0x5b * @@ -2145,6 +2167,8 @@ static struct nvbios_init_opcode { [0x56] = { init_condition_time }, [0x57] = { init_ltime }, [0x58] = { init_zm_reg_sequence }, + [0x59] = { init_reserved }, + [0x5a] = { init_zm_reg_indirect }, [0x5b] = { init_sub_direct }, [0x5c] = { init_jump }, [0x5e] = { init_i2c_if }, From d31b11d85814ff669cfeb93c0f85b9d659a85ef8 Mon Sep 17 00:00:00 2001 From: Ilia Mirkin Date: Fri, 19 Jun 2015 01:19:40 -0400 Subject: [PATCH 172/428] drm/nouveau/bios: add proper support for opcode 0x59 More analysis shows that this is identical to 0x79 except that it loads the frequency indirectly from elsewhere in the VBIOS. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=91025 Signed-off-by: Ilia Mirkin Signed-off-by: Ben Skeggs --- .../gpu/drm/nouveau/nvkm/subdev/bios/init.c | 24 +++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c index 1f590f839f76..f4611e3f0971 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c @@ -577,9 +577,6 @@ init_reserved(struct nvbios_init *init) u8 length, i; switch (opcode) { - case 0x59: - length = 7; - break; case 0xaa: length = 4; break; @@ -1287,6 +1284,25 @@ init_zm_reg_sequence(struct nvbios_init *init) } } +/** + * INIT_PLL_INDIRECT - opcode 0x59 + * + */ +static void +init_pll_indirect(struct nvbios_init *init) +{ + struct nvkm_bios *bios = init->bios; + u32 reg = nv_ro32(bios, init->offset + 1); + u16 addr = nv_ro16(bios, init->offset + 5); + u32 freq = (u32)nv_ro16(bios, addr) * 1000; + + trace("PLL_INDIRECT\tR[0x%06x] =PLL= VBIOS[%04x] = %dkHz\n", + reg, addr, freq); + init->offset += 7; + + init_prog_pll(init, reg, freq); +} + /** * INIT_ZM_REG_INDIRECT - opcode 0x5a * @@ -2167,7 +2183,7 @@ static struct nvbios_init_opcode { [0x56] = { init_condition_time }, [0x57] = { init_ltime }, [0x58] = { init_zm_reg_sequence }, - [0x59] = { init_reserved }, + [0x59] = { init_pll_indirect }, [0x5a] = { init_zm_reg_indirect }, [0x5b] = { init_sub_direct }, [0x5c] = { init_jump }, From d108142c0840ce389cd9898aa76943b3fb430b83 Mon Sep 17 00:00:00 2001 From: Ilia Mirkin Date: Mon, 29 Jun 2015 04:07:20 -0400 Subject: [PATCH 173/428] drm/nouveau/fbcon/nv11-: correctly account for ring space usage The RING_SPACE macro accounts how much space is used up so it's important to ask it for the right amount. Incorrect accounting of this can cause page faults down the line as writes are attempted outside of the ring. Signed-off-by: Ilia Mirkin Cc: stable@vger.kernel.org Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nv04_fbcon.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nv04_fbcon.c b/drivers/gpu/drm/nouveau/nv04_fbcon.c index 4ef602c5469d..495c57644ced 100644 --- a/drivers/gpu/drm/nouveau/nv04_fbcon.c +++ b/drivers/gpu/drm/nouveau/nv04_fbcon.c @@ -203,7 +203,7 @@ nv04_fbcon_accel_init(struct fb_info *info) if (ret) return ret; - if (RING_SPACE(chan, 49)) { + if (RING_SPACE(chan, 49 + (device->info.chipset >= 0x11 ? 4 : 0))) { nouveau_fbcon_gpu_lockup(info); return 0; } From 4fd26cb1e4049c7a630d86d52864a5722c7453ac Mon Sep 17 00:00:00 2001 From: Ilia Mirkin Date: Mon, 29 Jun 2015 20:43:46 -0400 Subject: [PATCH 174/428] drm/nouveau/fbcon/gf100-: reduce RING_SPACE allocation We only emit 58 words to the ring, not 60. Signed-off-by: Ilia Mirkin Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nvc0_fbcon.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nvc0_fbcon.c b/drivers/gpu/drm/nouveau/nvc0_fbcon.c index 61246677e8dc..fcd2e5f27bb9 100644 --- a/drivers/gpu/drm/nouveau/nvc0_fbcon.c +++ b/drivers/gpu/drm/nouveau/nvc0_fbcon.c @@ -188,7 +188,7 @@ nvc0_fbcon_accel_init(struct fb_info *info) return -EINVAL; } - ret = RING_SPACE(chan, 60); + ret = RING_SPACE(chan, 58); if (ret) { WARN_ON(1); nouveau_fbcon_gpu_lockup(info); From b7eea2d7e67cd4b65f42c00624277dae780f7009 Mon Sep 17 00:00:00 2001 From: Ilia Mirkin Date: Mon, 29 Jun 2015 20:49:48 -0400 Subject: [PATCH 175/428] drm/nouveau/fbcon/g80: reduce PUSH_SPACE alloc, fire ring on accel init Only 58 words get written to the ring, not 59. Also, normalize the accel init wrt nvc0 and nv04 fbcon impls by firing the ring at accel init time rather than waiting until "later". Signed-off-by: Ilia Mirkin Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nv50_fbcon.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nv50_fbcon.c b/drivers/gpu/drm/nouveau/nv50_fbcon.c index 394c89abcc97..901130b06072 100644 --- a/drivers/gpu/drm/nouveau/nv50_fbcon.c +++ b/drivers/gpu/drm/nouveau/nv50_fbcon.c @@ -188,7 +188,7 @@ nv50_fbcon_accel_init(struct fb_info *info) if (ret) return ret; - ret = RING_SPACE(chan, 59); + ret = RING_SPACE(chan, 58); if (ret) { nouveau_fbcon_gpu_lockup(info); return ret; @@ -252,6 +252,7 @@ nv50_fbcon_accel_init(struct fb_info *info) OUT_RING(chan, info->var.yres_virtual); OUT_RING(chan, upper_32_bits(fb->vma.offset)); OUT_RING(chan, lower_32_bits(fb->vma.offset)); + FIRE_RING(chan); return 0; } From 5ce000b297a1c1bb126a14b02acb40318b88a903 Mon Sep 17 00:00:00 2001 From: Woodrow Shen Date: Mon, 27 Jul 2015 18:34:31 +0800 Subject: [PATCH 176/428] ALSA: hda - Add pin quirk for the headset mic jack detection on Dell laptop The new Dell laptop with codec 256 can't detect headset mic when headset was inserted on the machine. From alsa-info, we check init_pin_configs and need to define the new register value for pin 0x1d & 0x1e because the original macro ALC256_STANDARD_PINS can't match pin definition. Also, the macro ALC256_STANDARD_PINS is simplified by removing them. This makes headset mic works on laptop. Codec: Realtek ALC256 Vendor Id: 0x10ec0256 Subsystem Id: 0x102806f2 BugLink: https://bugs.launchpad.net/bugs/1478497 Signed-off-by: Woodrow Shen Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index d94c0e33f58d..4ae877c3b6a1 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5398,8 +5398,6 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {0x19, 0x411111f0}, \ {0x1a, 0x411111f0}, \ {0x1b, 0x411111f0}, \ - {0x1d, 0x40700001}, \ - {0x1e, 0x411111f0}, \ {0x21, 0x02211020} #define ALC282_STANDARD_PINS \ @@ -5556,10 +5554,19 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x21, 0x02211030}), SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, ALC256_STANDARD_PINS, - {0x13, 0x40000000}), + {0x13, 0x40000000}, + {0x1d, 0x40700001}, + {0x1e, 0x411111f0}), SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, ALC256_STANDARD_PINS, - {0x13, 0x411111f0}), + {0x13, 0x411111f0}, + {0x1d, 0x40700001}, + {0x1e, 0x411111f0}), + SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, + ALC256_STANDARD_PINS, + {0x13, 0x411111f0}, + {0x1d, 0x4077992d}, + {0x1e, 0x411111ff}), SND_HDA_PIN_QUIRK(0x10ec0280, 0x103c, "HP", ALC280_FIXUP_HP_GPIO4, {0x12, 0x90a60130}, {0x13, 0x40000000}, From 134bf30c06f057d6b8d90132e8f8b3cd2be79572 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 23 Jul 2015 16:47:59 +0100 Subject: [PATCH 177/428] dm cache policy smq: fix alloc_bitset check that always evaluates as false static analysis by cppcheck has found a check on alloc_bitset that always evaluates as false and hence never finds an allocation failure: [drivers/md/dm-cache-policy-smq.c:1689]: (warning) Logical conjunction always evaluates to false: !EXPR && EXPR. Fix this by removing the incorrect mq->cache_hit_bits check Signed-off-by: Colin Ian King Signed-off-by: Mike Snitzer --- drivers/md/dm-cache-policy-smq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/dm-cache-policy-smq.c b/drivers/md/dm-cache-policy-smq.c index b6f22651dd35..48a4a826ae07 100644 --- a/drivers/md/dm-cache-policy-smq.c +++ b/drivers/md/dm-cache-policy-smq.c @@ -1686,7 +1686,7 @@ static struct dm_cache_policy *smq_create(dm_cblock_t cache_size, if (from_cblock(cache_size)) { mq->cache_hit_bits = alloc_bitset(from_cblock(cache_size)); - if (!mq->cache_hit_bits && mq->cache_hit_bits) { + if (!mq->cache_hit_bits) { DMERR("couldn't allocate cache hit bitset"); goto bad_cache_hit_bits; } From 6ed443c07f1e7f819983422b16598facb152250d Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Sun, 5 Jul 2015 09:55:44 +0300 Subject: [PATCH 178/428] dm crypt: update wiki page URL Cryptsetup moved to gitlab. This is a leftover from commit e44f23b32dc7 (dm crypt: update URLs to new cryptsetup project page, 2015-04-05). Signed-off-by: Baruch Siach Signed-off-by: Mike Snitzer --- drivers/md/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index b59727309072..bfec3bdfe598 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -259,7 +259,7 @@ config DM_CRYPT the ciphers you're going to use in the cryptoapi configuration. For further information on dm-crypt and userspace tools see: - + To compile this code as a module, choose M here: the module will be called dm-crypt. From 39da809e86274abbd9010365906045e02da3944a Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Sun, 5 Jul 2015 10:18:41 -0500 Subject: [PATCH 179/428] of: add HAS_IOMEM depends to OF_ADDRESS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On UML builds, of_address.c fails to compile: ../drivers/of/address.c:873:2: error: implicit declaration of function ‘ioremap’ [-Werror=implicit-function-declaration] This is due to CONFIG_OF now being user selectable. Add a dependency on HAS_IOMEM to OF_ADDRESS in order to fix this. Signed-off-by: Rob Herring Cc: Grant Likely --- drivers/of/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig index 8df1b1777745..59bb8556e43a 100644 --- a/drivers/of/Kconfig +++ b/drivers/of/Kconfig @@ -47,7 +47,7 @@ config OF_DYNAMIC config OF_ADDRESS def_bool y - depends on !SPARC + depends on !SPARC && HAS_IOMEM select OF_ADDRESS_PCI if PCI config OF_ADDRESS_PCI From 35068ce8cbf1749ef1a4b9b1493af83b8488c37b Mon Sep 17 00:00:00 2001 From: Tomeu Vizoso Date: Wed, 1 Jul 2015 09:10:43 +0200 Subject: [PATCH 180/428] of: constify drv arg of of_driver_match_device stub With this change the stub has the same signature as the actual function, preventing this compiler warning when building without CONFIG_OF: drivers/base/property.c: In function 'fwnode_driver_match_device': >> drivers/base/property.c:608:38: warning: passing argument 2 of 'of_driver_match_device' discards 'const' qualifier from pointer target type return of_driver_match_device(dev, drv); ^ In file included from drivers/base/property.c:18:0: include/linux/of_device.h:61:19: note: expected 'struct device_driver *' but argument is of type 'const struct device_driver *' static inline int of_driver_match_device(struct device *dev, ^ Signed-off-by: Tomeu Vizoso Signed-off-by: Rob Herring --- include/linux/of_device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 4c508549833a..cc7dd687a89d 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -59,7 +59,7 @@ void of_dma_configure(struct device *dev, struct device_node *np); #else /* CONFIG_OF */ static inline int of_driver_match_device(struct device *dev, - struct device_driver *drv) + const struct device_driver *drv) { return 0; } From 3b6e644e6540405fd3582e0a90412fccbddd0e45 Mon Sep 17 00:00:00 2001 From: Alban Bedel Date: Fri, 3 Jul 2015 10:14:57 +0200 Subject: [PATCH 181/428] DEVICETREE: Misc fix for the AR7100 SPI controller binding Fix the clocks property documentation and use lower case for hex values in the example. Signed-off-by: Alban Bedel Signed-off-by: Rob Herring --- Documentation/devicetree/bindings/spi/spi-ath79.txt | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/devicetree/bindings/spi/spi-ath79.txt b/Documentation/devicetree/bindings/spi/spi-ath79.txt index f1ad9c367532..9c696fa66f81 100644 --- a/Documentation/devicetree/bindings/spi/spi-ath79.txt +++ b/Documentation/devicetree/bindings/spi/spi-ath79.txt @@ -3,7 +3,7 @@ Binding for Qualcomm Atheros AR7xxx/AR9xxx SPI controller Required properties: - compatible: has to be "qca,-spi", "qca,ar7100-spi" as fallback. - reg: Base address and size of the controllers memory area -- clocks: phandle to the AHB clock. +- clocks: phandle of the AHB clock. - clock-names: has to be "ahb". - #address-cells: <1>, as required by generic SPI binding. - #size-cells: <0>, also as required by generic SPI binding. @@ -12,9 +12,9 @@ Child nodes as per the generic SPI binding. Example: - spi@1F000000 { + spi@1f000000 { compatible = "qca,ar9132-spi", "qca,ar7100-spi"; - reg = <0x1F000000 0x10>; + reg = <0x1f000000 0x10>; clocks = <&pll 2>; clock-names = "ahb"; From 599ad5ac9a59587a46f6540a8e2ab79dff811f7d Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 10 Jul 2015 15:26:12 +0900 Subject: [PATCH 182/428] of: Drop owner assignment from platform and i2c driver platform_driver and i2c_driver do not need to set an owner because core will set it. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Rob Herring --- drivers/of/unittest.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index 18016341d5a9..9f71770b6226 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -979,7 +979,6 @@ static struct platform_driver unittest_driver = { .remove = unittest_remove, .driver = { .name = "unittest", - .owner = THIS_MODULE, .of_match_table = of_match_ptr(unittest_match), }, }; @@ -1666,7 +1665,6 @@ static const struct i2c_device_id unittest_i2c_dev_id[] = { static struct i2c_driver unittest_i2c_dev_driver = { .driver = { .name = "unittest-i2c-dev", - .owner = THIS_MODULE, }, .probe = unittest_i2c_dev_probe, .remove = unittest_i2c_dev_remove, @@ -1761,7 +1759,6 @@ static const struct i2c_device_id unittest_i2c_mux_id[] = { static struct i2c_driver unittest_i2c_mux_driver = { .driver = { .name = "unittest-i2c-mux", - .owner = THIS_MODULE, }, .probe = unittest_i2c_mux_probe, .remove = unittest_i2c_mux_remove, From 03d5eb65b53889fe98a5ecddfe205c16e3093190 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 27 Jul 2015 10:23:19 -0400 Subject: [PATCH 183/428] NFS: Fix a memory leak in nfs_do_recoalesce If the function exits early, then we must put those requests that were not processed back onto the &mirror->pg_list so they can be cleaned up by nfs_pgio_error(). Fixes: a7d42ddb30997 ("nfs: add mirroring support to pgio layer") Cc: stable@vger.kernel.org # v4.0+ Signed-off-by: Trond Myklebust --- fs/nfs/pagelist.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 1da68d3b1eda..8ea5920fb777 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -1109,8 +1109,11 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) nfs_list_remove_request(req); if (__nfs_pageio_add_request(desc, req)) continue; - if (desc->pg_error < 0) + if (desc->pg_error < 0) { + list_splice_tail(&head, &mirror->pg_list); + mirror->pg_recoalesce = 1; return 0; + } break; } } while (mirror->pg_recoalesce); From d4c30454db732d5a377abfc309c7a629f3bbaeb0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 24 Jul 2015 12:31:33 -0400 Subject: [PATCH 184/428] NFS: Don't clear desc->pg_moreio in nfs_do_recoalesce() Recoalescing does not affect whether or not we've already sent off I/O, and doing so means that we end up sending a bunch of synchronous for cases where we actually need to be using unstable writes. Signed-off-by: Trond Myklebust --- fs/nfs/pagelist.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 8ea5920fb777..4984bbe55ff1 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -1100,8 +1100,6 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) mirror->pg_base = 0; mirror->pg_recoalesce = 0; - desc->pg_moreio = 0; - while (!list_empty(&head)) { struct nfs_page *req; From 7932c0bd7740f4cd2aa168d3ce0199e7af7d72d5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?= Date: Fri, 17 Jul 2015 15:32:03 +0200 Subject: [PATCH 185/428] vhost: actually track log eventfd file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit While reviewing vhost log code, I found out that log_file is never set. Note: I haven't tested the change (QEMU doesn't use LOG_FD yet). Cc: stable@vger.kernel.org Signed-off-by: Marc-André Lureau Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vhost.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index a9fe859f43c8..95bdb90fd7f0 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -995,6 +995,7 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp) } if (eventfp != d->log_file) { filep = d->log_file; + d->log_file = eventfp; ctx = d->log_ctx; d->log_ctx = eventfp ? eventfd_ctx_fileget(eventfp) : NULL; From 1e0994730f772580ff98754eb5595190cdf371ef Mon Sep 17 00:00:00 2001 From: Igor Mammedov Date: Wed, 15 Jul 2015 16:48:50 +0200 Subject: [PATCH 186/428] vhost: fix error handling for memory region alloc callers of vhost_kvzalloc() expect the same behaviour on allocation error as from kmalloc/vmalloc i.e. NULL return value. So just return vzmalloc() returned value instead of returning ERR_PTR(-ENOMEM) Fixes: 4de7255f7d2be5 ("vhost: extend memory regions allocation to vmalloc") Spotted-by: Dan Carpenter Suggested-by: Julia Lawall Signed-off-by: Igor Mammedov Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vhost.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 95bdb90fd7f0..eec2f11809ff 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -683,11 +683,8 @@ static void *vhost_kvzalloc(unsigned long size) { void *n = kzalloc(size, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); - if (!n) { + if (!n) n = vzalloc(size); - if (!n) - return ERR_PTR(-ENOMEM); - } return n; } From 02c3b4c75994888e58a6e6e8176640cde9822597 Mon Sep 17 00:00:00 2001 From: Al Cooper Date: Fri, 24 Jul 2015 16:09:36 -0400 Subject: [PATCH 187/428] usb: gadget: bdc: fix a driver crash on disconnect ep_dequeue() in bdc_ep.c was capturing the hw dequeue pointer incorrectly by reading the wrong register for the upper 32 bits. Signed-off-by: Al Cooper Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/bdc/bdc_ep.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/udc/bdc/bdc_ep.c b/drivers/usb/gadget/udc/bdc/bdc_ep.c index b04980cf6dc4..1efa61265d8d 100644 --- a/drivers/usb/gadget/udc/bdc/bdc_ep.c +++ b/drivers/usb/gadget/udc/bdc/bdc_ep.c @@ -779,7 +779,7 @@ static int ep_dequeue(struct bdc_ep *ep, struct bdc_req *req) /* The current hw dequeue pointer */ tmp_32 = bdc_readl(bdc->regs, BDC_EPSTS0(0)); deq_ptr_64 = tmp_32; - tmp_32 = bdc_readl(bdc->regs, BDC_EPSTS0(1)); + tmp_32 = bdc_readl(bdc->regs, BDC_EPSTS1(0)); deq_ptr_64 |= ((u64)tmp_32 << 32); /* we have the dma addr of next bd that will be fetched by hardware */ From bdcc2cd14e4e86f1fb19c78e191a1b8da3d6dea0 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Thu, 23 Jul 2015 11:08:43 -0400 Subject: [PATCH 188/428] NFSv4.2: handle NFS-specific llseek errors Handle NFS-specific llseek errors instead of letting them leak out to userspace. Reported-by: Benjamin Coddington Signed-off-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- fs/nfs/nfs42proc.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index f486b80f927a..d731bbf974aa 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -135,7 +135,7 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len) return err; } -loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) +static loff_t _nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) { struct inode *inode = file_inode(filep); struct nfs42_seek_args args = { @@ -171,6 +171,23 @@ loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) return vfs_setpos(filep, res.sr_offset, inode->i_sb->s_maxbytes); } +loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) +{ + struct nfs_server *server = NFS_SERVER(file_inode(filep)); + struct nfs4_exception exception = { }; + int err; + + do { + err = _nfs42_proc_llseek(filep, offset, whence); + if (err == -ENOTSUPP) + return -EOPNOTSUPP; + err = nfs4_handle_exception(server, err, &exception); + } while (exception.retry); + + return err; +} + + static void nfs42_layoutstat_prepare(struct rpc_task *task, void *calldata) { From 743c69e7c089ba1bea1b207c5829dd079a4e98f9 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 27 Jul 2015 10:55:35 +1000 Subject: [PATCH 189/428] sunrpc: translate -EAGAIN to -ENOBUFS when socket is writable. The networking layer does not reliably report the distinction between a non-block write failing because: 1/ the queue is too full already and 2/ a memory allocation attempt failed. The distinction is important because in the first case it is appropriate to retry as soon as the socket reports that it is writable, and in the second case a small delay is required as the socket will most likely report as writable but kmalloc could still fail. sk_stream_wait_memory() exhibits this distinction nicely, setting 'vm_wait' if a small wait is needed. However in the non-blocking case it always returns -EAGAIN no matter the cause of the failure. This -EAGAIN call get all the way to sunrpc. The sunrpc layer expects EAGAIN to indicate the first cause, and ENOBUFS to indicate the second. Various documentation suggests that this is not unreasonable, but does not guarantee the desired error codes. The result of getting -EAGAIN when -ENOBUFS is expected is that the send is tried again in a tight loop and soft lockups are reported. so: add tests after calls to xs_sendpages() to translate -EAGAIN into -ENOBUFS if the socket is writable. This cannot happen inside xs_sendpages() as the test for "is socket writable" is different between TCP and UDP. With this change, the tight loop retrying xs_sendpages() becomes a loop which only retries every 250ms, and so will not trigger a soft-lockup warning. It is possible that the write did fail because the queue was too full and by the time xs_sendpages() completed, the queue was writable again. In this case an extra 250ms delay is inserted that isn't really needed. This circumstance suggests a degree of congestion so a delay is not necessarily a bad thing, and it can only cause a single 250ms delay, not a series of them. Signed-off-by: NeilBrown Signed-off-by: Trond Myklebust --- net/sunrpc/xprtsock.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 44c1927b68c7..4f48b1a19e9f 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -527,6 +527,10 @@ static int xs_local_send_request(struct rpc_task *task) true, &sent); dprintk("RPC: %s(%u) = %d\n", __func__, xdr->len - req->rq_bytes_sent, status); + + if (status == -EAGAIN && sock_writeable(transport->inet)) + status = -ENOBUFS; + if (likely(sent > 0) || status == 0) { req->rq_bytes_sent += sent; req->rq_xmit_bytes_sent += sent; @@ -590,6 +594,9 @@ static int xs_udp_send_request(struct rpc_task *task) if (status == -EPERM) goto process_status; + if (status == -EAGAIN && sock_writeable(transport->inet)) + status = -ENOBUFS; + if (sent > 0 || status == 0) { req->rq_xmit_bytes_sent += sent; if (sent >= req->rq_slen) @@ -687,6 +694,8 @@ static int xs_tcp_send_request(struct rpc_task *task) status = -EAGAIN; break; } + if (status == -EAGAIN && sk_stream_is_writeable(transport->inet)) + status = -ENOBUFS; switch (status) { case -ENOTSOCK: From c41b7767673cb76adeb2b5fde220209f717ea13c Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Mon, 27 Jul 2015 14:51:47 +0800 Subject: [PATCH 190/428] usb: gadget: f_uac2: fix calculation of uac2->p_interval The p_interval should be less if the 'bInterval' at the descriptor is larger, eg, if 'bInterval' is 5 for HS, the p_interval should be 8000 / 16 = 500. It fixes the patch 9bb87f168931 ("usb: gadget: f_uac2: send reasonably sized packets") Cc: # v3.18+ Fixes: 9bb87f168931 ("usb: gadget: f_uac2: send reasonably sized packets") Acked-by: Daniel Mack Signed-off-by: Peter Chen Signed-off-by: Felipe Balbi --- drivers/usb/gadget/function/f_uac2.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c index 6d3eb8b00a48..531861547253 100644 --- a/drivers/usb/gadget/function/f_uac2.c +++ b/drivers/usb/gadget/function/f_uac2.c @@ -1162,14 +1162,14 @@ afunc_set_alt(struct usb_function *fn, unsigned intf, unsigned alt) factor = 1000; } else { ep_desc = &hs_epin_desc; - factor = 125; + factor = 8000; } /* pre-compute some values for iso_complete() */ uac2->p_framesize = opts->p_ssize * num_channels(opts->p_chmask); rate = opts->p_srate * uac2->p_framesize; - uac2->p_interval = (1 << (ep_desc->bInterval - 1)) * factor; + uac2->p_interval = factor / (1 << (ep_desc->bInterval - 1)); uac2->p_pktsize = min_t(unsigned int, rate / uac2->p_interval, prm->max_psize); From 774cf72f8ad971031428f8057d2947c8780a7b8c Mon Sep 17 00:00:00 2001 From: Andrzej Pietrasiewicz Date: Fri, 24 Jul 2015 09:48:40 +0200 Subject: [PATCH 191/428] usb: gadget: f_hid: actually limit the number of instances There is a predefined maximum number of hid instances, currently 4. A chrdev region is allocated accordingly, but with configfs the user can create as many hid function directories as they like. To make the number of hid instances consistent with the number of allocated minors, the limit is enforced at directory creation time. Signed-off-by: Andrzej Pietrasiewicz Signed-off-by: Felipe Balbi --- drivers/usb/gadget/function/f_hid.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c index f7f35a36c09a..6df9715a4bcd 100644 --- a/drivers/usb/gadget/function/f_hid.c +++ b/drivers/usb/gadget/function/f_hid.c @@ -699,6 +699,10 @@ static inline int hidg_get_minor(void) int ret; ret = ida_simple_get(&hidg_ida, 0, 0, GFP_KERNEL); + if (ret >= HIDG_MINORS) { + ida_simple_remove(&hidg_ida, ret); + ret = -ENODEV; + } return ret; } From 4248bd7d3e2c7c87ff695d812018b8c22b5a5ab1 Mon Sep 17 00:00:00 2001 From: Andrzej Pietrasiewicz Date: Fri, 24 Jul 2015 09:48:41 +0200 Subject: [PATCH 192/428] usb: gadget: f_printer: actually limit the number of instances There is a predefined maximum number of printer instances, currently 4. A chrdev region is allocated accordingly, but with configfs the user can create as many printer function directories as they like. To make the number of printer instances consistent with the number of allocated minors, the limit is enforced at directory creation time. Signed-off-by: Andrzej Pietrasiewicz Signed-off-by: Felipe Balbi --- drivers/usb/gadget/function/f_printer.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/usb/gadget/function/f_printer.c b/drivers/usb/gadget/function/f_printer.c index 44173df27273..357f63f47b42 100644 --- a/drivers/usb/gadget/function/f_printer.c +++ b/drivers/usb/gadget/function/f_printer.c @@ -1248,7 +1248,15 @@ static struct config_item_type printer_func_type = { static inline int gprinter_get_minor(void) { - return ida_simple_get(&printer_ida, 0, 0, GFP_KERNEL); + int ret; + + ret = ida_simple_get(&printer_ida, 0, 0, GFP_KERNEL); + if (ret >= PRINTER_MINORS) { + ida_simple_remove(&printer_ida, ret); + ret = -ENODEV; + } + + return ret; } static inline void gprinter_put_minor(int minor) From f91b1feada0b6f0a4d33648155b3ded2c4e0707e Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Sun, 26 Jul 2015 14:59:00 +0200 Subject: [PATCH 193/428] arm64/efi: map the entire UEFI vendor string before reading it At boot, the UTF-16 UEFI vendor string is copied from the system table into a char array with a size of 100 bytes. However, this size of 100 bytes is also used for memremapping() the source, which may not be sufficient if the vendor string exceeds 50 UTF-16 characters, and the placement of the vendor string inside a 4 KB page happens to leave the end unmapped. So use the correct '100 * sizeof(efi_char16_t)' for the size of the mapping. Signed-off-by: Ard Biesheuvel Fixes: f84d02755f5a ("arm64: add EFI runtime services") Cc: # 3.16+ Signed-off-by: Catalin Marinas --- arch/arm64/kernel/efi.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 9d4aa18f2a82..e8ca6eaedd02 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -122,12 +122,12 @@ static int __init uefi_init(void) /* Show what we know for posterity */ c16 = early_memremap(efi_to_phys(efi.systab->fw_vendor), - sizeof(vendor)); + sizeof(vendor) * sizeof(efi_char16_t)); if (c16) { for (i = 0; i < (int) sizeof(vendor) - 1 && *c16; ++i) vendor[i] = c16[i]; vendor[i] = '\0'; - early_memunmap(c16, sizeof(vendor)); + early_memunmap(c16, sizeof(vendor) * sizeof(efi_char16_t)); } pr_info("EFI v%u.%.02u by %s\n", From 7a6e0706c09b121d4656b055d9b0494320246f4f Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 27 Jul 2015 14:24:48 -0700 Subject: [PATCH 194/428] macb: Fix build with macro'ized readl/writel. If an architecture defines readl/writel using CPP macros, we get the following kinds of build failure: > > > drivers/net/ethernet/cadence/macb.c:164:1: error: macro "writel" > > > passed 3 arguments, but takes just 2 > macb_or_gem_writel(bp, SA1B, bottom); > ^ Rename the methods so that this doesn't happen. Signed-off-by: David S. Miller --- drivers/net/ethernet/cadence/macb.c | 14 +++++++------- drivers/net/ethernet/cadence/macb.h | 16 ++++++++-------- 2 files changed, 15 insertions(+), 15 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index c638757251e6..bf9eb2ecf960 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -506,7 +506,7 @@ static void macb_update_stats(struct macb *bp) WARN_ON((unsigned long)(end - p - 1) != (MACB_TPF - MACB_PFR) / 4); for(; p < end; p++, offset += 4) - *p += bp->readl(bp, offset); + *p += bp->macb_reg_readl(bp, offset); } static int macb_halt_tx(struct macb *bp) @@ -1934,14 +1934,14 @@ static void gem_update_stats(struct macb *bp) for (i = 0; i < GEM_STATS_LEN; ++i, ++p) { u32 offset = gem_statistics[i].offset; - u64 val = bp->readl(bp, offset); + u64 val = bp->macb_reg_readl(bp, offset); bp->ethtool_stats[i] += val; *p += val; if (offset == GEM_OCTTXL || offset == GEM_OCTRXL) { /* Add GEM_OCTTXH, GEM_OCTRXH */ - val = bp->readl(bp, offset + 4); + val = bp->macb_reg_readl(bp, offset + 4); bp->ethtool_stats[i] += ((u64)val) << 32; *(++p) += val; } @@ -2867,11 +2867,11 @@ static int macb_probe(struct platform_device *pdev) bp->regs = mem; bp->native_io = native_io; if (native_io) { - bp->readl = hw_readl_native; - bp->writel = hw_writel_native; + bp->macb_reg_readl = hw_readl_native; + bp->macb_reg_writel = hw_writel_native; } else { - bp->readl = hw_readl; - bp->writel = hw_writel; + bp->macb_reg_readl = hw_readl; + bp->macb_reg_writel = hw_writel; } bp->num_queues = num_queues; bp->queue_mask = queue_mask; diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index 2aa102ecff6c..1895b6b2addd 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -429,12 +429,12 @@ | GEM_BF(name, value)) /* Register access macros */ -#define macb_readl(port, reg) (port)->readl((port), MACB_##reg) -#define macb_writel(port, reg, value) (port)->writel((port), MACB_##reg, (value)) -#define gem_readl(port, reg) (port)->readl((port), GEM_##reg) -#define gem_writel(port, reg, value) (port)->writel((port), GEM_##reg, (value)) -#define queue_readl(queue, reg) (queue)->bp->readl((queue)->bp, (queue)->reg) -#define queue_writel(queue, reg, value) (queue)->bp->writel((queue)->bp, (queue)->reg, (value)) +#define macb_readl(port, reg) (port)->macb_reg_readl((port), MACB_##reg) +#define macb_writel(port, reg, value) (port)->macb_reg_writel((port), MACB_##reg, (value)) +#define gem_readl(port, reg) (port)->macb_reg_readl((port), GEM_##reg) +#define gem_writel(port, reg, value) (port)->macb_reg_writel((port), GEM_##reg, (value)) +#define queue_readl(queue, reg) (queue)->bp->macb_reg_readl((queue)->bp, (queue)->reg) +#define queue_writel(queue, reg, value) (queue)->bp->macb_reg_writel((queue)->bp, (queue)->reg, (value)) /* Conditional GEM/MACB macros. These perform the operation to the correct * register dependent on whether the device is a GEM or a MACB. For registers @@ -782,8 +782,8 @@ struct macb { bool native_io; /* hardware IO accessors */ - u32 (*readl)(struct macb *bp, int offset); - void (*writel)(struct macb *bp, int offset, u32 value); + u32 (*macb_reg_readl)(struct macb *bp, int offset); + void (*macb_reg_writel)(struct macb *bp, int offset, u32 value); unsigned int rx_tail; unsigned int rx_prepared_head; From 1513069edcf8dd86cfd8d5daef482b97d6b93df6 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 27 Jul 2015 13:08:06 -0700 Subject: [PATCH 195/428] fib_trie: Drop unnecessary calls to leaf_pull_suffix It was reported that update_suffix was taking a long time on systems where a large number of leaves were attached to a single node. As it turns out fib_table_flush was calling update_suffix for each leaf that didn't have all of the aliases stripped from it. As a result, on this large node removing one leaf would result in us calling update_suffix for every other leaf on the node. The fix is to just remove the calls to leaf_pull_suffix since they are redundant as we already have a call in resize that will go through and update the suffix length for the node before we exit out of fib_table_flush or fib_table_flush_external. Reported-by: David Ahern Signed-off-by: Alexander Duyck Tested-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/fib_trie.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 81797e065b21..37c4bb89a708 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1793,8 +1793,6 @@ void fib_table_flush_external(struct fib_table *tb) if (hlist_empty(&n->leaf)) { put_child_root(pn, n->key, NULL); node_free(n); - } else { - leaf_pull_suffix(pn, n); } } } @@ -1864,8 +1862,6 @@ int fib_table_flush(struct fib_table *tb) if (hlist_empty(&n->leaf)) { put_child_root(pn, n->key, NULL); node_free(n); - } else { - leaf_pull_suffix(pn, n); } } From c5c62f1bb0e1fc94ab77ec01e92ccab5cb249742 Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Thu, 23 Jul 2015 16:37:43 +0200 Subject: [PATCH 196/428] macvtap: fix network header pointer for VLAN tagged pkts Network header is set with offset ETH_HLEN but it is not true for VLAN (multiple-)tagged and results in checksum issues in lower devices. v2: leave skb->protocol untouched (thx Vlad), comment added v3: moved after skb_probe_transport_header() call (thx Toshiaki) Signed-off-by: Ivan Vecera Signed-off-by: David S. Miller --- drivers/net/macvtap.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 3b933bb5a8d5..edd77342773a 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -719,6 +719,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, struct virtio_net_hdr vnet_hdr = { 0 }; int vnet_hdr_len = 0; int copylen = 0; + int depth; bool zerocopy = false; size_t linear; ssize_t n; @@ -804,6 +805,12 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, skb_probe_transport_header(skb, ETH_HLEN); + /* Move network header to the right position for VLAN tagged packets */ + if ((skb->protocol == htons(ETH_P_8021Q) || + skb->protocol == htons(ETH_P_8021AD)) && + __vlan_get_protocol(skb, skb->protocol, &depth) != 0) + skb_set_network_header(skb, depth); + rcu_read_lock(); vlan = rcu_dereference(q->vlan); /* copy skb_ubuf_info for callback when skb has no error */ From f580dd042823294b5b548e0f8bf1ba7a4b114fa5 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 11 Jul 2015 17:48:52 +0200 Subject: [PATCH 197/428] SUNRPC: Report TCP errors to the caller Signed-off-by: Trond Myklebust --- net/sunrpc/xprtsock.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 4f48b1a19e9f..6a21368bdd8e 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -677,9 +677,6 @@ static int xs_tcp_send_request(struct rpc_task *task) dprintk("RPC: xs_tcp_send_request(%u) = %d\n", xdr->len - req->rq_bytes_sent, status); - if (unlikely(sent == 0 && status < 0)) - break; - /* If we've sent the entire packet, immediately * reset the count of bytes sent. */ req->rq_bytes_sent += sent; @@ -689,10 +686,12 @@ static int xs_tcp_send_request(struct rpc_task *task) return 0; } - if (sent != 0) - continue; - status = -EAGAIN; - break; + if (status < 0) + break; + if (sent == 0) { + status = -EAGAIN; + break; + } } if (status == -EAGAIN && sk_stream_is_writeable(transport->inet)) status = -ENOBUFS; From 158cd4af8dedbda0d612d448c724c715d0dda649 Mon Sep 17 00:00:00 2001 From: Lars Westerhoff Date: Tue, 28 Jul 2015 01:32:21 +0300 Subject: [PATCH 198/428] packet: missing dev_put() in packet_do_bind() When binding a PF_PACKET socket, the use count of the bound interface is always increased with dev_hold in dev_get_by_{index,name}. However, when rebound with the same protocol and device as in the previous bind the use count of the interface was not decreased. Ultimately, this caused the deletion of the interface to fail with the following message: unregister_netdevice: waiting for dummy0 to become free. Usage count = 1 This patch moves the dev_put out of the conditional part that was only executed when either the protocol or device changed on a bind. Fixes: 902fefb82ef7 ('packet: improve socket create/bind latency in some cases') Signed-off-by: Lars Westerhoff Signed-off-by: Dan Carpenter Reviewed-by: Daniel Borkmann Signed-off-by: David S. Miller --- net/packet/af_packet.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c9e8741226c6..c7c42eb617ef 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2784,7 +2784,7 @@ static int packet_release(struct socket *sock) static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto) { struct packet_sock *po = pkt_sk(sk); - const struct net_device *dev_curr; + struct net_device *dev_curr; __be16 proto_curr; bool need_rehook; @@ -2808,15 +2808,13 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto) po->num = proto; po->prot_hook.type = proto; - - if (po->prot_hook.dev) - dev_put(po->prot_hook.dev); - po->prot_hook.dev = dev; po->ifindex = dev ? dev->ifindex : 0; packet_cached_dev_assign(po, dev); } + if (dev_curr) + dev_put(dev_curr); if (proto == 0 || !need_rehook) goto out_unlock; From ab80ee3895a76f1beba35847911d89833fbb68ab Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Fri, 24 Jul 2015 14:33:21 -0700 Subject: [PATCH 199/428] Input: synaptics - dump ext10 capabilities as well Make extended capabilities obtained through $10 query also available in touchpad identification. Signed-off-by: Jiri Kosina Reviewed-by: Benjamin Tissoires Signed-off-by: Dmitry Torokhov --- drivers/input/mouse/synaptics.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index 3a32caf06bf1..6025eb430c0a 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -1484,12 +1484,12 @@ static int __synaptics_init(struct psmouse *psmouse, bool absolute_mode) priv->pkt_type = SYN_MODEL_NEWABS(priv->model_id) ? SYN_NEWABS : SYN_OLDABS; psmouse_info(psmouse, - "Touchpad model: %ld, fw: %ld.%ld, id: %#lx, caps: %#lx/%#lx/%#lx, board id: %lu, fw id: %lu\n", + "Touchpad model: %ld, fw: %ld.%ld, id: %#lx, caps: %#lx/%#lx/%#lx/%#lx, board id: %lu, fw id: %lu\n", SYN_ID_MODEL(priv->identity), SYN_ID_MAJOR(priv->identity), SYN_ID_MINOR(priv->identity), priv->model_id, priv->capabilities, priv->ext_cap, priv->ext_cap_0c, - priv->board_id, priv->firmware_id); + priv->ext_cap_10, priv->board_id, priv->firmware_id); set_input_params(psmouse, priv); From efbd34702fb1cb66e08606a623a8a76f86b300f9 Mon Sep 17 00:00:00 2001 From: Henrik Rydberg Date: Fri, 24 Jul 2015 14:44:37 -0700 Subject: [PATCH 200/428] Input: bcm5974 - prepare for a new trackpad generation With the advent of the Macbook Pro 12, we see a new generation of trackpads, capable of force sensoring and haptic feedback. This patch prepares for the new device by adding configuration data for the code paths that would otherwise look different. Tested-by: John Horan Tested-by: Jochen Radmacher Tested-by: Yang Hongyang Tested-by: Yen-Chin, Lee Tested-by: George Hilios Tested-by: Janez Urevc Signed-off-by: Henrik Rydberg Signed-off-by: Dmitry Torokhov --- drivers/input/mouse/bcm5974.c | 132 +++++++++++++++++++++------------- 1 file changed, 81 insertions(+), 51 deletions(-) diff --git a/drivers/input/mouse/bcm5974.c b/drivers/input/mouse/bcm5974.c index b10709f04615..a596b9b9d604 100644 --- a/drivers/input/mouse/bcm5974.c +++ b/drivers/input/mouse/bcm5974.c @@ -184,17 +184,37 @@ enum tp_type { }; /* trackpad finger data offsets, le16-aligned */ -#define FINGER_TYPE1 (13 * sizeof(__le16)) -#define FINGER_TYPE2 (15 * sizeof(__le16)) -#define FINGER_TYPE3 (19 * sizeof(__le16)) +#define HEADER_TYPE1 (13 * sizeof(__le16)) +#define HEADER_TYPE2 (15 * sizeof(__le16)) +#define HEADER_TYPE3 (19 * sizeof(__le16)) /* trackpad button data offsets */ +#define BUTTON_TYPE1 0 #define BUTTON_TYPE2 15 #define BUTTON_TYPE3 23 /* list of device capability bits */ #define HAS_INTEGRATED_BUTTON 1 +/* trackpad finger data block size */ +#define FSIZE_TYPE1 (14 * sizeof(__le16)) +#define FSIZE_TYPE2 (14 * sizeof(__le16)) +#define FSIZE_TYPE3 (14 * sizeof(__le16)) + +/* offset from header to finger struct */ +#define DELTA_TYPE1 (0 * sizeof(__le16)) +#define DELTA_TYPE2 (0 * sizeof(__le16)) +#define DELTA_TYPE3 (0 * sizeof(__le16)) + +/* usb control message mode switch data */ +#define USBMSG_TYPE1 8, 0x300, 0, 0, 0x1, 0x8 +#define USBMSG_TYPE2 8, 0x300, 0, 0, 0x1, 0x8 +#define USBMSG_TYPE3 8, 0x300, 0, 0, 0x1, 0x8 + +/* Wellspring initialization constants */ +#define BCM5974_WELLSPRING_MODE_READ_REQUEST_ID 1 +#define BCM5974_WELLSPRING_MODE_WRITE_REQUEST_ID 9 + /* trackpad finger structure, le16-aligned */ struct tp_finger { __le16 origin; /* zero when switching track finger */ @@ -213,8 +233,6 @@ struct tp_finger { /* trackpad finger data size, empirically at least ten fingers */ #define MAX_FINGERS 16 -#define SIZEOF_FINGER sizeof(struct tp_finger) -#define SIZEOF_ALL_FINGERS (MAX_FINGERS * SIZEOF_FINGER) #define MAX_FINGER_ORIENTATION 16384 /* device-specific parameters */ @@ -232,8 +250,17 @@ struct bcm5974_config { int bt_datalen; /* data length of the button interface */ int tp_ep; /* the endpoint of the trackpad interface */ enum tp_type tp_type; /* type of trackpad interface */ - int tp_offset; /* offset to trackpad finger data */ + int tp_header; /* bytes in header block */ int tp_datalen; /* data length of the trackpad interface */ + int tp_button; /* offset to button data */ + int tp_fsize; /* bytes in single finger block */ + int tp_delta; /* offset from header to finger struct */ + int um_size; /* usb control message length */ + int um_req_val; /* usb control message value */ + int um_req_idx; /* usb control message index */ + int um_switch_idx; /* usb control message mode switch index */ + int um_switch_on; /* usb control message mode switch on */ + int um_switch_off; /* usb control message mode switch off */ struct bcm5974_param p; /* finger pressure limits */ struct bcm5974_param w; /* finger width limits */ struct bcm5974_param x; /* horizontal limits */ @@ -259,6 +286,24 @@ struct bcm5974 { int slots[MAX_FINGERS]; /* slot assignments */ }; +/* trackpad finger block data, le16-aligned */ +static const struct tp_finger *get_tp_finger(const struct bcm5974 *dev, int i) +{ + const struct bcm5974_config *c = &dev->cfg; + u8 *f_base = dev->tp_data + c->tp_header + c->tp_delta; + + return (const struct tp_finger *)(f_base + i * c->tp_fsize); +} + +#define DATAFORMAT(type) \ + type, \ + HEADER_##type, \ + HEADER_##type + (MAX_FINGERS) * (FSIZE_##type), \ + BUTTON_##type, \ + FSIZE_##type, \ + DELTA_##type, \ + USBMSG_##type + /* logical signal quality */ #define SN_PRESSURE 45 /* pressure signal-to-noise ratio */ #define SN_WIDTH 25 /* width signal-to-noise ratio */ @@ -273,7 +318,7 @@ static const struct bcm5974_config bcm5974_config_table[] = { USB_DEVICE_ID_APPLE_WELLSPRING_JIS, 0, 0x84, sizeof(struct bt_data), - 0x81, TYPE1, FINGER_TYPE1, FINGER_TYPE1 + SIZEOF_ALL_FINGERS, + 0x81, DATAFORMAT(TYPE1), { SN_PRESSURE, 0, 256 }, { SN_WIDTH, 0, 2048 }, { SN_COORD, -4824, 5342 }, @@ -286,7 +331,7 @@ static const struct bcm5974_config bcm5974_config_table[] = { USB_DEVICE_ID_APPLE_WELLSPRING2_JIS, 0, 0x84, sizeof(struct bt_data), - 0x81, TYPE1, FINGER_TYPE1, FINGER_TYPE1 + SIZEOF_ALL_FINGERS, + 0x81, DATAFORMAT(TYPE1), { SN_PRESSURE, 0, 256 }, { SN_WIDTH, 0, 2048 }, { SN_COORD, -4824, 4824 }, @@ -299,7 +344,7 @@ static const struct bcm5974_config bcm5974_config_table[] = { USB_DEVICE_ID_APPLE_WELLSPRING3_JIS, HAS_INTEGRATED_BUTTON, 0x84, sizeof(struct bt_data), - 0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS, + 0x81, DATAFORMAT(TYPE2), { SN_PRESSURE, 0, 300 }, { SN_WIDTH, 0, 2048 }, { SN_COORD, -4460, 5166 }, @@ -312,7 +357,7 @@ static const struct bcm5974_config bcm5974_config_table[] = { USB_DEVICE_ID_APPLE_WELLSPRING4_JIS, HAS_INTEGRATED_BUTTON, 0x84, sizeof(struct bt_data), - 0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS, + 0x81, DATAFORMAT(TYPE2), { SN_PRESSURE, 0, 300 }, { SN_WIDTH, 0, 2048 }, { SN_COORD, -4620, 5140 }, @@ -325,7 +370,7 @@ static const struct bcm5974_config bcm5974_config_table[] = { USB_DEVICE_ID_APPLE_WELLSPRING4A_JIS, HAS_INTEGRATED_BUTTON, 0x84, sizeof(struct bt_data), - 0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS, + 0x81, DATAFORMAT(TYPE2), { SN_PRESSURE, 0, 300 }, { SN_WIDTH, 0, 2048 }, { SN_COORD, -4616, 5112 }, @@ -338,7 +383,7 @@ static const struct bcm5974_config bcm5974_config_table[] = { USB_DEVICE_ID_APPLE_WELLSPRING5_JIS, HAS_INTEGRATED_BUTTON, 0x84, sizeof(struct bt_data), - 0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS, + 0x81, DATAFORMAT(TYPE2), { SN_PRESSURE, 0, 300 }, { SN_WIDTH, 0, 2048 }, { SN_COORD, -4415, 5050 }, @@ -351,7 +396,7 @@ static const struct bcm5974_config bcm5974_config_table[] = { USB_DEVICE_ID_APPLE_WELLSPRING6_JIS, HAS_INTEGRATED_BUTTON, 0x84, sizeof(struct bt_data), - 0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS, + 0x81, DATAFORMAT(TYPE2), { SN_PRESSURE, 0, 300 }, { SN_WIDTH, 0, 2048 }, { SN_COORD, -4620, 5140 }, @@ -364,7 +409,7 @@ static const struct bcm5974_config bcm5974_config_table[] = { USB_DEVICE_ID_APPLE_WELLSPRING5A_JIS, HAS_INTEGRATED_BUTTON, 0x84, sizeof(struct bt_data), - 0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS, + 0x81, DATAFORMAT(TYPE2), { SN_PRESSURE, 0, 300 }, { SN_WIDTH, 0, 2048 }, { SN_COORD, -4750, 5280 }, @@ -377,7 +422,7 @@ static const struct bcm5974_config bcm5974_config_table[] = { USB_DEVICE_ID_APPLE_WELLSPRING6A_JIS, HAS_INTEGRATED_BUTTON, 0x84, sizeof(struct bt_data), - 0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS, + 0x81, DATAFORMAT(TYPE2), { SN_PRESSURE, 0, 300 }, { SN_WIDTH, 0, 2048 }, { SN_COORD, -4620, 5140 }, @@ -390,7 +435,7 @@ static const struct bcm5974_config bcm5974_config_table[] = { USB_DEVICE_ID_APPLE_WELLSPRING7_JIS, HAS_INTEGRATED_BUTTON, 0x84, sizeof(struct bt_data), - 0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS, + 0x81, DATAFORMAT(TYPE2), { SN_PRESSURE, 0, 300 }, { SN_WIDTH, 0, 2048 }, { SN_COORD, -4750, 5280 }, @@ -403,7 +448,7 @@ static const struct bcm5974_config bcm5974_config_table[] = { USB_DEVICE_ID_APPLE_WELLSPRING7A_JIS, HAS_INTEGRATED_BUTTON, 0x84, sizeof(struct bt_data), - 0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS, + 0x81, DATAFORMAT(TYPE2), { SN_PRESSURE, 0, 300 }, { SN_WIDTH, 0, 2048 }, { SN_COORD, -4750, 5280 }, @@ -416,7 +461,7 @@ static const struct bcm5974_config bcm5974_config_table[] = { USB_DEVICE_ID_APPLE_WELLSPRING8_JIS, HAS_INTEGRATED_BUTTON, 0, sizeof(struct bt_data), - 0x83, TYPE3, FINGER_TYPE3, FINGER_TYPE3 + SIZEOF_ALL_FINGERS, + 0x83, DATAFORMAT(TYPE3), { SN_PRESSURE, 0, 300 }, { SN_WIDTH, 0, 2048 }, { SN_COORD, -4620, 5140 }, @@ -549,19 +594,18 @@ static int report_tp_state(struct bcm5974 *dev, int size) struct input_dev *input = dev->input; int raw_n, i, n = 0; - if (size < c->tp_offset || (size - c->tp_offset) % SIZEOF_FINGER != 0) + if (size < c->tp_header || (size - c->tp_header) % c->tp_fsize != 0) return -EIO; - /* finger data, le16-aligned */ - f = (const struct tp_finger *)(dev->tp_data + c->tp_offset); - raw_n = (size - c->tp_offset) / SIZEOF_FINGER; + raw_n = (size - c->tp_header) / c->tp_fsize; for (i = 0; i < raw_n; i++) { - if (raw2int(f[i].touch_major) == 0) + f = get_tp_finger(dev, i); + if (raw2int(f->touch_major) == 0) continue; - dev->pos[n].x = raw2int(f[i].abs_x); - dev->pos[n].y = c->y.min + c->y.max - raw2int(f[i].abs_y); - dev->index[n++] = &f[i]; + dev->pos[n].x = raw2int(f->abs_x); + dev->pos[n].y = c->y.min + c->y.max - raw2int(f->abs_y); + dev->index[n++] = f; } input_mt_assign_slots(input, dev->slots, dev->pos, n, 0); @@ -572,32 +616,22 @@ static int report_tp_state(struct bcm5974 *dev, int size) input_mt_sync_frame(input); - report_synaptics_data(input, c, f, raw_n); + report_synaptics_data(input, c, get_tp_finger(dev, 0), raw_n); - /* type 2 reports button events via ibt only */ - if (c->tp_type == TYPE2) { - int ibt = raw2int(dev->tp_data[BUTTON_TYPE2]); + /* later types report button events via integrated button only */ + if (c->caps & HAS_INTEGRATED_BUTTON) { + int ibt = raw2int(dev->tp_data[c->tp_button]); input_report_key(input, BTN_LEFT, ibt); } - if (c->tp_type == TYPE3) - input_report_key(input, BTN_LEFT, dev->tp_data[BUTTON_TYPE3]); - input_sync(input); return 0; } -/* Wellspring initialization constants */ -#define BCM5974_WELLSPRING_MODE_READ_REQUEST_ID 1 -#define BCM5974_WELLSPRING_MODE_WRITE_REQUEST_ID 9 -#define BCM5974_WELLSPRING_MODE_REQUEST_VALUE 0x300 -#define BCM5974_WELLSPRING_MODE_REQUEST_INDEX 0 -#define BCM5974_WELLSPRING_MODE_VENDOR_VALUE 0x01 -#define BCM5974_WELLSPRING_MODE_NORMAL_VALUE 0x08 - static int bcm5974_wellspring_mode(struct bcm5974 *dev, bool on) { + const struct bcm5974_config *c = &dev->cfg; int retval = 0, size; char *data; @@ -605,7 +639,7 @@ static int bcm5974_wellspring_mode(struct bcm5974 *dev, bool on) if (dev->cfg.tp_type == TYPE3) return 0; - data = kmalloc(8, GFP_KERNEL); + data = kmalloc(c->um_size, GFP_KERNEL); if (!data) { dev_err(&dev->intf->dev, "out of memory\n"); retval = -ENOMEM; @@ -616,28 +650,24 @@ static int bcm5974_wellspring_mode(struct bcm5974 *dev, bool on) size = usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0), BCM5974_WELLSPRING_MODE_READ_REQUEST_ID, USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_INTERFACE, - BCM5974_WELLSPRING_MODE_REQUEST_VALUE, - BCM5974_WELLSPRING_MODE_REQUEST_INDEX, data, 8, 5000); + c->um_req_val, c->um_req_idx, data, c->um_size, 5000); - if (size != 8) { + if (size != c->um_size) { dev_err(&dev->intf->dev, "could not read from device\n"); retval = -EIO; goto out; } /* apply the mode switch */ - data[0] = on ? - BCM5974_WELLSPRING_MODE_VENDOR_VALUE : - BCM5974_WELLSPRING_MODE_NORMAL_VALUE; + data[c->um_switch_idx] = on ? c->um_switch_on : c->um_switch_off; /* write configuration */ size = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0), BCM5974_WELLSPRING_MODE_WRITE_REQUEST_ID, USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE, - BCM5974_WELLSPRING_MODE_REQUEST_VALUE, - BCM5974_WELLSPRING_MODE_REQUEST_INDEX, data, 8, 5000); + c->um_req_val, c->um_req_idx, data, c->um_size, 5000); - if (size != 8) { + if (size != c->um_size) { dev_err(&dev->intf->dev, "could not write to device\n"); retval = -EIO; goto out; From a4a2c54560f2c57b88ba0283f141b44f594c2337 Mon Sep 17 00:00:00 2001 From: Henrik Rydberg Date: Fri, 24 Jul 2015 14:45:05 -0700 Subject: [PATCH 201/428] HID: apple: Add support for the 2015 Macbook Pro This patch adds keyboard support for MacbookPro12,1 as WELLSPRING9 (0x0272, 0x0273, 0x0274). The touchpad is handled in a separate bcm5974 patch, as usual. Tested-by: John Horan Tested-by: Jochen Radmacher Tested-by: Yang Hongyang Tested-by: Yen-Chin, Lee Tested-by: George Hilios Tested-by: Janez Urevc Signed-off-by: Henrik Rydberg Acked-by: Jiri Kosina Signed-off-by: Dmitry Torokhov --- drivers/hid/hid-apple.c | 6 ++++++ drivers/hid/hid-core.c | 6 ++++++ drivers/hid/hid-ids.h | 3 +++ 3 files changed, 15 insertions(+) diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index f822fd2a1ada..884d82f9190e 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -546,6 +546,12 @@ static const struct hid_device_id apple_devices[] = { .driver_data = APPLE_HAS_FN | APPLE_ISO_KEYBOARD }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_JIS), .driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI), + .driver_data = APPLE_HAS_FN }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ISO), + .driver_data = APPLE_HAS_FN | APPLE_ISO_KEYBOARD }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_JIS), + .driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI), .driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO), diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 56ce8c2b5530..c57c007d8e57 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1760,6 +1760,9 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ISO) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_JIS) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ISO) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_JIS) }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI) }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO) }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_JIS) }, @@ -2450,6 +2453,9 @@ static const struct hid_device_id hid_mouse_ignore_list[] = { { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ISO) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_JIS) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ISO) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_JIS) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY) }, { } diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 9c4786759f16..5274e9daa8a3 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -142,6 +142,9 @@ #define USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI 0x0290 #define USB_DEVICE_ID_APPLE_WELLSPRING8_ISO 0x0291 #define USB_DEVICE_ID_APPLE_WELLSPRING8_JIS 0x0292 +#define USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI 0x0272 +#define USB_DEVICE_ID_APPLE_WELLSPRING9_ISO 0x0273 +#define USB_DEVICE_ID_APPLE_WELLSPRING9_JIS 0x0274 #define USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY 0x030a #define USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY 0x030b #define USB_DEVICE_ID_APPLE_IRCONTROL 0x8240 From d58069265c9d15c04c9e3832cd1d9dffe9d4d5f6 Mon Sep 17 00:00:00 2001 From: John Horan Date: Fri, 24 Jul 2015 14:45:33 -0700 Subject: [PATCH 202/428] Input: bcm5974 - add support for the 2015 Macbook Pro Add support for the MacBookPro12,1 model. This patch needs to be applied together with the accompanied HID patch, as usual. Tested-by: John Horan Tested-by: Jochen Radmacher Tested-by: Yang Hongyang Tested-by: Yen-Chin, Lee Tested-by: George Hilios Tested-by: Janez Urevc Signed-off-by: Henrik Rydberg Signed-off-by: Dmitry Torokhov --- drivers/input/mouse/bcm5974.c | 33 +++++++++++++++++++++++++++++++-- 1 file changed, 31 insertions(+), 2 deletions(-) diff --git a/drivers/input/mouse/bcm5974.c b/drivers/input/mouse/bcm5974.c index a596b9b9d604..30e3442518f8 100644 --- a/drivers/input/mouse/bcm5974.c +++ b/drivers/input/mouse/bcm5974.c @@ -2,6 +2,7 @@ * Apple USB BCM5974 (Macbook Air and Penryn Macbook Pro) multitouch driver * * Copyright (C) 2008 Henrik Rydberg (rydberg@euromail.se) + * Copyright (C) 2015 John Horan (knasher@gmail.com) * * The USB initialization and package decoding was made by * Scott Shawcroft as part of the touchd user-space driver project: @@ -91,6 +92,10 @@ #define USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI 0x0290 #define USB_DEVICE_ID_APPLE_WELLSPRING8_ISO 0x0291 #define USB_DEVICE_ID_APPLE_WELLSPRING8_JIS 0x0292 +/* MacbookPro12,1 (2015) */ +#define USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI 0x0272 +#define USB_DEVICE_ID_APPLE_WELLSPRING9_ISO 0x0273 +#define USB_DEVICE_ID_APPLE_WELLSPRING9_JIS 0x0274 #define BCM5974_DEVICE(prod) { \ .match_flags = (USB_DEVICE_ID_MATCH_DEVICE | \ @@ -152,6 +157,10 @@ static const struct usb_device_id bcm5974_table[] = { BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI), BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING8_ISO), BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING8_JIS), + /* MacbookPro12,1 */ + BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI), + BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING9_ISO), + BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING9_JIS), /* Terminating entry */ {} }; @@ -180,18 +189,21 @@ struct bt_data { enum tp_type { TYPE1, /* plain trackpad */ TYPE2, /* button integrated in trackpad */ - TYPE3 /* additional header fields since June 2013 */ + TYPE3, /* additional header fields since June 2013 */ + TYPE4 /* additional header field for pressure data */ }; /* trackpad finger data offsets, le16-aligned */ #define HEADER_TYPE1 (13 * sizeof(__le16)) #define HEADER_TYPE2 (15 * sizeof(__le16)) #define HEADER_TYPE3 (19 * sizeof(__le16)) +#define HEADER_TYPE4 (23 * sizeof(__le16)) /* trackpad button data offsets */ #define BUTTON_TYPE1 0 #define BUTTON_TYPE2 15 #define BUTTON_TYPE3 23 +#define BUTTON_TYPE4 31 /* list of device capability bits */ #define HAS_INTEGRATED_BUTTON 1 @@ -200,16 +212,19 @@ enum tp_type { #define FSIZE_TYPE1 (14 * sizeof(__le16)) #define FSIZE_TYPE2 (14 * sizeof(__le16)) #define FSIZE_TYPE3 (14 * sizeof(__le16)) +#define FSIZE_TYPE4 (15 * sizeof(__le16)) /* offset from header to finger struct */ #define DELTA_TYPE1 (0 * sizeof(__le16)) #define DELTA_TYPE2 (0 * sizeof(__le16)) #define DELTA_TYPE3 (0 * sizeof(__le16)) +#define DELTA_TYPE4 (1 * sizeof(__le16)) /* usb control message mode switch data */ #define USBMSG_TYPE1 8, 0x300, 0, 0, 0x1, 0x8 #define USBMSG_TYPE2 8, 0x300, 0, 0, 0x1, 0x8 #define USBMSG_TYPE3 8, 0x300, 0, 0, 0x1, 0x8 +#define USBMSG_TYPE4 2, 0x302, 2, 1, 0x1, 0x0 /* Wellspring initialization constants */ #define BCM5974_WELLSPRING_MODE_READ_REQUEST_ID 1 @@ -227,7 +242,8 @@ struct tp_finger { __le16 orientation; /* 16384 when point, else 15 bit angle */ __le16 touch_major; /* touch area, major axis */ __le16 touch_minor; /* touch area, minor axis */ - __le16 unused[3]; /* zeros */ + __le16 unused[2]; /* zeros */ + __le16 pressure; /* pressure on forcetouch touchpad */ __le16 multi; /* one finger: varies, more fingers: constant */ } __attribute__((packed,aligned(2))); @@ -468,6 +484,19 @@ static const struct bcm5974_config bcm5974_config_table[] = { { SN_COORD, -150, 6600 }, { SN_ORIENT, -MAX_FINGER_ORIENTATION, MAX_FINGER_ORIENTATION } }, + { + USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI, + USB_DEVICE_ID_APPLE_WELLSPRING9_ISO, + USB_DEVICE_ID_APPLE_WELLSPRING9_JIS, + HAS_INTEGRATED_BUTTON, + 0, sizeof(struct bt_data), + 0x83, DATAFORMAT(TYPE4), + { SN_PRESSURE, 0, 300 }, + { SN_WIDTH, 0, 2048 }, + { SN_COORD, -4828, 5345 }, + { SN_COORD, -203, 6803 }, + { SN_ORIENT, -MAX_FINGER_ORIENTATION, MAX_FINGER_ORIENTATION } + }, {} }; From ca4da5dd1f99fe9c59f1709fb43e818b18ad20e0 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 27 Jul 2015 15:23:43 +0100 Subject: [PATCH 203/428] KEYS: ensure we free the assoc array edit if edit is valid __key_link_end is not freeing the associated array edit structure and this leads to a 512 byte memory leak each time an identical existing key is added with add_key(). The reason the add_key() system call returns okay is that key_create_or_update() calls __key_link_begin() before checking to see whether it can update a key directly rather than adding/replacing - which it turns out it can. Thus __key_link() is not called through __key_instantiate_and_link() and __key_link_end() must cancel the edit. CVE-2015-1333 Signed-off-by: Colin Ian King Signed-off-by: David Howells Signed-off-by: James Morris --- security/keys/keyring.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/security/keys/keyring.c b/security/keys/keyring.c index e72548b5897e..d33437007ad2 100644 --- a/security/keys/keyring.c +++ b/security/keys/keyring.c @@ -1181,9 +1181,11 @@ void __key_link_end(struct key *keyring, if (index_key->type == &key_type_keyring) up_write(&keyring_serialise_link_sem); - if (edit && !edit->dead_leaf) { - key_payload_reserve(keyring, - keyring->datalen - KEYQUOTA_LINK_BYTES); + if (edit) { + if (!edit->dead_leaf) { + key_payload_reserve(keyring, + keyring->datalen - KEYQUOTA_LINK_BYTES); + } assoc_array_cancel_edit(edit); } up_write(&keyring->sem); From 0b991f5cdcd6201e5401f83ca3a672343c3bfc49 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 27 Jul 2015 09:53:49 +0200 Subject: [PATCH 204/428] s390/cachinfo: add missing facility check to init_cache_level() Stephen Powell reported the following crash on a z890 machine: Kernel BUG at 00000000001219d0 [verbose debug info unavailable] illegal operation: 0001 ilc:3 [#1] SMP Krnl PSW : 0704e00180000000 00000000001219d0 (init_cache_level+0x38/0xe0) R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:3 CC:2 PM:0 EA:3 Krnl Code: 00000000001219c2: a7840056 brc 8,121a6e 00000000001219c6: a7190000 lghi %r1,0 #00000000001219ca: eb101000004c ecag %r1,%r0,0(%r1) >00000000001219d0: a7390000 lghi %r3,0 00000000001219d4: e310f0a00024 stg %r1,160(%r15) 00000000001219da: a7080000 lhi %r0,0 00000000001219de: a7b9f000 lghi %r11,-4096 00000000001219e2: c0a0002899d9 larl %r10,634d94 Call Trace: [<0000000000478ee2>] detect_cache_attributes+0x2a/0x2b8 [<000000000097c9b0>] cacheinfo_sysfs_init+0x60/0xc8 [<00000000001001c0>] do_one_initcall+0x98/0x1c8 [<000000000094fdc2>] kernel_init_freeable+0x212/0x2d8 [<000000000062352e>] kernel_init+0x26/0x118 [<000000000062fd2e>] kernel_thread_starter+0x6/0xc The illegal operation was executed because of a missing facility check, which should have made sure that the ECAG execution would only be executed on machines which have the general-instructions-extension facility installed. Reported-and-tested-by: Stephen Powell Cc: stable@vger.kernel.org # v4.0+ Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/cache.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/s390/kernel/cache.c b/arch/s390/kernel/cache.c index bff5e3b6d822..8ba32436effe 100644 --- a/arch/s390/kernel/cache.c +++ b/arch/s390/kernel/cache.c @@ -138,6 +138,8 @@ int init_cache_level(unsigned int cpu) union cache_topology ct; enum cache_type ctype; + if (!test_facility(34)) + return -EOPNOTSUPP; if (!this_cpu_ci) return -EINVAL; ct.raw = ecag(EXTRACT_TOPOLOGY, 0, 0); From 17fb874dee093139923af8ed36061faa92cc8e79 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Fri, 24 Jul 2015 13:13:30 +0200 Subject: [PATCH 205/428] hwrng: core - correct error check of kthread_run call The kthread_run() function can return two different error values but the hwrng core only checks for -ENOMEM. If the other error value -EINTR is returned it is assigned to hwrng_fill and later used on a kthread_stop() call which naturally crashes. Cc: stable@vger.kernel.org Signed-off-by: Martin Schwidefsky Signed-off-by: Herbert Xu --- drivers/char/hw_random/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c index da8faf78536a..5643b65cee20 100644 --- a/drivers/char/hw_random/core.c +++ b/drivers/char/hw_random/core.c @@ -429,7 +429,7 @@ static int hwrng_fillfn(void *unused) static void start_khwrngd(void) { hwrng_fill = kthread_run(hwrng_fillfn, NULL, "hwrng"); - if (hwrng_fill == ERR_PTR(-ENOMEM)) { + if (IS_ERR(hwrng_fill)) { pr_err("hwrng_fill thread creation failed"); hwrng_fill = NULL; } From 697bb728d9e2367020aa0c5af7363809d7658e43 Mon Sep 17 00:00:00 2001 From: Ben Skeggs Date: Tue, 28 Jul 2015 17:20:57 +1000 Subject: [PATCH 206/428] drm/nouveau/kms/nv50-: guard against enabling cursor on disabled heads Userspace has started doing this, which upsets the display class hw error checking in various unpleasant ways. Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nv50_display.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c index 7da7958556a3..981342d142ff 100644 --- a/drivers/gpu/drm/nouveau/nv50_display.c +++ b/drivers/gpu/drm/nouveau/nv50_display.c @@ -979,7 +979,7 @@ nv50_crtc_cursor_show_hide(struct nouveau_crtc *nv_crtc, bool show, bool update) { struct nv50_mast *mast = nv50_mast(nv_crtc->base.dev); - if (show && nv_crtc->cursor.nvbo) + if (show && nv_crtc->cursor.nvbo && nv_crtc->base.enabled) nv50_crtc_cursor_show(nv_crtc); else nv50_crtc_cursor_hide(nv_crtc); From eb48b12ee5e05dd3ea473d008873f5228a63eb7a Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Thu, 9 Jul 2015 17:15:14 +0900 Subject: [PATCH 207/428] drm/nouveau/nouveau/ttm: fix tiled system memory with Maxwell Add Maxwell to the switch statement that sets node->memtype, otherwise all tiling information is ignored for buffers in system memory. While we are at it, make that switch statement explicitly complain the next time we meet a non-handled card family. Signed-off-by: Alexandre Courbot Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nouveau_ttm.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c index 18f449715788..7464aef34674 100644 --- a/drivers/gpu/drm/nouveau/nouveau_ttm.c +++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c @@ -175,15 +175,24 @@ nouveau_gart_manager_new(struct ttm_mem_type_manager *man, node->page_shift = 12; switch (drm->device.info.family) { + case NV_DEVICE_INFO_V0_TNT: + case NV_DEVICE_INFO_V0_CELSIUS: + case NV_DEVICE_INFO_V0_KELVIN: + case NV_DEVICE_INFO_V0_RANKINE: + case NV_DEVICE_INFO_V0_CURIE: + break; case NV_DEVICE_INFO_V0_TESLA: if (drm->device.info.chipset != 0x50) node->memtype = (nvbo->tile_flags & 0x7f00) >> 8; break; case NV_DEVICE_INFO_V0_FERMI: case NV_DEVICE_INFO_V0_KEPLER: + case NV_DEVICE_INFO_V0_MAXWELL: node->memtype = (nvbo->tile_flags & 0xff00) >> 8; break; default: + NV_WARN(drm, "%s: unhandled family type %x\n", __func__, + drm->device.info.family); break; } From 74472233233f577eaa0ca6d6e17d9017b6e53150 Mon Sep 17 00:00:00 2001 From: Dirk Behme Date: Mon, 27 Jul 2015 08:56:05 +0200 Subject: [PATCH 208/428] USB: sierra: add 1199:68AB device ID Add support for the Sierra Wireless AR8550 device with USB descriptor 0x1199, 0x68AB. It is common with MC879x modules 1199:683c/683d which also are composite devices with 7 interfaces (0..6) and also MDM62xx based as the AR8550. The major difference are only the interface attributes 02/02/01 on interfaces 3 and 4 on the AR8550. They are vendor specific ff/ff/ff on MC879x modules. lsusb reports: Bus 001 Device 004: ID 1199:68ab Sierra Wireless, Inc. Device Descriptor: bLength 18 bDescriptorType 1 bcdUSB 2.00 bDeviceClass 0 (Defined at Interface level) bDeviceSubClass 0 bDeviceProtocol 0 bMaxPacketSize0 64 idVendor 0x1199 Sierra Wireless, Inc. idProduct 0x68ab bcdDevice 0.06 iManufacturer 3 Sierra Wireless, Incorporated iProduct 2 AR8550 iSerial 0 bNumConfigurations 1 Configuration Descriptor: bLength 9 bDescriptorType 2 wTotalLength 198 bNumInterfaces 7 bConfigurationValue 1 iConfiguration 1 Sierra Configuration bmAttributes 0xe0 Self Powered Remote Wakeup MaxPower 0mA Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 0 bAlternateSetting 0 bNumEndpoints 2 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 255 Vendor Specific Subclass bInterfaceProtocol 255 Vendor Specific Protocol iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x81 EP 1 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 32 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x01 EP 1 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 32 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 1 bAlternateSetting 0 bNumEndpoints 2 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 255 Vendor Specific Subclass bInterfaceProtocol 255 Vendor Specific Protocol iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x82 EP 2 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 32 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x02 EP 2 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 32 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 2 bAlternateSetting 0 bNumEndpoints 2 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 255 Vendor Specific Subclass bInterfaceProtocol 255 Vendor Specific Protocol iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x83 EP 3 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 32 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x03 EP 3 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 32 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 3 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 2 Communications bInterfaceSubClass 2 Abstract (modem) bInterfaceProtocol 1 AT-commands (v.25ter) iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x84 EP 4 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 5 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x85 EP 5 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 32 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x04 EP 4 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 32 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 4 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 2 Communications bInterfaceSubClass 2 Abstract (modem) bInterfaceProtocol 1 AT-commands (v.25ter) iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x86 EP 6 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 5 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x87 EP 7 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 32 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x05 EP 5 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 32 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 5 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 255 Vendor Specific Subclass bInterfaceProtocol 255 Vendor Specific Protocol iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x88 EP 8 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 5 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x89 EP 9 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 32 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x06 EP 6 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 32 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 6 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 255 Vendor Specific Subclass bInterfaceProtocol 255 Vendor Specific Protocol iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x8a EP 10 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 5 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x8b EP 11 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 32 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x07 EP 7 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 32 Device Qualifier (for other device speed): bLength 10 bDescriptorType 6 bcdUSB 2.00 bDeviceClass 0 (Defined at Interface level) bDeviceSubClass 0 bDeviceProtocol 0 bMaxPacketSize0 64 bNumConfigurations 1 Device Status: 0x0001 Self Powered Signed-off-by: Dirk Behme Cc: Lars Melin Cc: stable Signed-off-by: Johan Hovold --- drivers/usb/serial/sierra.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/serial/sierra.c b/drivers/usb/serial/sierra.c index 46179a0828eb..07d1ecd564f7 100644 --- a/drivers/usb/serial/sierra.c +++ b/drivers/usb/serial/sierra.c @@ -289,6 +289,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x68AA, 0xFF, 0xFF, 0xFF), .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist }, + { USB_DEVICE(0x1199, 0x68AB) }, /* Sierra Wireless AR8550 */ /* AT&T Direct IP LTE modems */ { USB_DEVICE_AND_INTERFACE_INFO(0x0F3D, 0x68AA, 0xFF, 0xFF, 0xFF), .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist From 3471648a7569512e10f154cdfe5076c341a5c099 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 10 Jul 2015 15:58:42 -0400 Subject: [PATCH 209/428] nfs: plug memory leak when ->prepare_layoutcommit fails "data" is currently leaked when the prepare_layoutcommit operation returns an error. Put the cred before taking the spinlock in that case, take the lock and then goto out_unlock which will drop the lock and then free "data". Signed-off-by: Jeff Layton Signed-off-by: Trond Myklebust --- fs/nfs/pnfs.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 18aa3b7962eb..70bf706b1090 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -2221,13 +2221,12 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync) if (ld->prepare_layoutcommit) { status = ld->prepare_layoutcommit(&data->args); if (status) { + put_rpccred(data->cred); spin_lock(&inode->i_lock); set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags); if (end_pos > nfsi->layout->plh_lwb) nfsi->layout->plh_lwb = end_pos; - spin_unlock(&inode->i_lock); - put_rpccred(data->cred); - goto clear_layoutcommitting; + goto out_unlock; } } From a49c269111a5b3c1fd2a98f36fa27423b94549f8 Mon Sep 17 00:00:00 2001 From: Kinglong Mee Date: Mon, 27 Jul 2015 15:31:38 +0800 Subject: [PATCH 210/428] nfs: Fix an oops caused by using other thread's stack space in ASYNC mode An oops caused by using other thread's stack space in sunrpc ASYNC sending thread. [ 9839.007187] ------------[ cut here ]------------ [ 9839.007923] kernel BUG at fs/nfs/nfs4xdr.c:910! [ 9839.008069] invalid opcode: 0000 [#1] SMP [ 9839.008069] Modules linked in: blocklayoutdriver rpcsec_gss_krb5 nfsv4 dns_resolver nfs fscache snd_hda_codec_generic snd_hda_intel snd_hda_controller snd_hda_codec snd_hwdep snd_seq snd_seq_device snd_pcm joydev iosf_mbi crct10dif_pclmul snd_timer crc32_pclmul crc32c_intel ghash_clmulni_intel snd soundcore ppdev pvpanic parport_pc i2c_piix4 serio_raw virtio_balloon parport acpi_cpufreq nfsd nfs_acl lockd grace auth_rpcgss sunrpc qxl drm_kms_helper virtio_net virtio_console virtio_blk ttm drm virtio_pci virtio_ring virtio ata_generic pata_acpi [ 9839.008069] CPU: 0 PID: 308 Comm: kworker/0:1H Not tainted 4.0.0-0.rc4.git1.3.fc23.x86_64 #1 [ 9839.008069] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 9839.008069] Workqueue: rpciod rpc_async_schedule [sunrpc] [ 9839.008069] task: ffff8800d8b4d8e0 ti: ffff880036678000 task.ti: ffff880036678000 [ 9839.008069] RIP: 0010:[] [] reserve_space.part.73+0x9/0x10 [nfsv4] [ 9839.008069] RSP: 0018:ffff88003667ba58 EFLAGS: 00010246 [ 9839.008069] RAX: 0000000000000000 RBX: 000000001fc15e18 RCX: ffff8800c0193800 [ 9839.008069] RDX: ffff8800e4ae3f24 RSI: 000000001fc15e2c RDI: ffff88003667bcd0 [ 9839.008069] RBP: ffff88003667ba58 R08: ffff8800d9173008 R09: 0000000000000003 [ 9839.008069] R10: ffff88003667bcd0 R11: 000000000000000c R12: 0000000000010000 [ 9839.008069] R13: ffff8800d9173350 R14: 0000000000000000 R15: ffff8800c0067b98 [ 9839.008069] FS: 0000000000000000(0000) GS:ffff88011fc00000(0000) knlGS:0000000000000000 [ 9839.008069] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 9839.008069] CR2: 00007f988c9c8bb0 CR3: 00000000d99b6000 CR4: 00000000000407f0 [ 9839.008069] Stack: [ 9839.008069] ffff88003667bbc8 ffffffffa03412c5 00000000c6c55680 ffff880000000003 [ 9839.008069] 0000000000000088 00000010c6c55680 0001000000000002 ffffffff816e87e9 [ 9839.008069] 0000000000000000 00000000477290e2 ffff88003667bab8 ffffffff81327ba3 [ 9839.008069] Call Trace: [ 9839.008069] [] encode_attrs+0x435/0x530 [nfsv4] [ 9839.008069] [] ? inet_sendmsg+0x69/0xb0 [ 9839.008069] [] ? selinux_socket_sendmsg+0x23/0x30 [ 9839.008069] [] ? do_sock_sendmsg+0x9f/0xc0 [ 9839.008069] [] ? kernel_sendmsg+0x58/0x70 [ 9839.008069] [] ? xdr_reserve_space+0x20/0x170 [sunrpc] [ 9839.008069] [] ? xdr_reserve_space+0x20/0x170 [sunrpc] [ 9839.008069] [] ? nfs4_xdr_enc_open_noattr+0x130/0x130 [nfsv4] [ 9839.008069] [] encode_open+0x2d5/0x340 [nfsv4] [ 9839.008069] [] ? nfs4_xdr_enc_open_noattr+0x130/0x130 [nfsv4] [ 9839.008069] [] ? xdr_encode_opaque+0x19/0x20 [sunrpc] [ 9839.008069] [] ? encode_string+0x2b/0x40 [nfsv4] [ 9839.008069] [] nfs4_xdr_enc_open+0xb3/0x140 [nfsv4] [ 9839.008069] [] rpcauth_wrap_req+0xac/0xf0 [sunrpc] [ 9839.008069] [] call_transmit+0x18b/0x2d0 [sunrpc] [ 9839.008069] [] ? call_decode+0x860/0x860 [sunrpc] [ 9839.008069] [] ? call_decode+0x860/0x860 [sunrpc] [ 9839.008069] [] __rpc_execute+0x90/0x460 [sunrpc] [ 9839.008069] [] rpc_async_schedule+0x15/0x20 [sunrpc] [ 9839.008069] [] process_one_work+0x1bb/0x410 [ 9839.008069] [] worker_thread+0x53/0x470 [ 9839.008069] [] ? process_one_work+0x410/0x410 [ 9839.008069] [] ? process_one_work+0x410/0x410 [ 9839.008069] [] kthread+0xd8/0xf0 [ 9839.008069] [] ? kthread_worker_fn+0x180/0x180 [ 9839.008069] [] ret_from_fork+0x58/0x90 [ 9839.008069] [] ? kthread_worker_fn+0x180/0x180 [ 9839.008069] Code: 00 00 48 c7 c7 21 fa 37 a0 e8 94 1c d6 e0 c6 05 d2 17 05 00 01 8b 03 eb d7 66 0f 1f 84 00 00 00 00 00 66 66 66 66 90 55 48 89 e5 <0f> 0b 0f 1f 44 00 00 66 66 66 66 90 55 48 89 e5 41 54 53 89 f3 [ 9839.008069] RIP [] reserve_space.part.73+0x9/0x10 [nfsv4] [ 9839.008069] RSP [ 9839.071114] ---[ end trace cc14c03adb522e94 ]--- Signed-off-by: Kinglong Mee Signed-off-by: Trond Myklebust --- fs/nfs/internal.h | 21 +++++++++++++++++++++ fs/nfs/nfs4proc.c | 10 +++++++++- 2 files changed, 30 insertions(+), 1 deletion(-) diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 9e6475bc5ba2..797013822765 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -296,6 +296,22 @@ extern struct rpc_procinfo nfs4_procedures[]; #ifdef CONFIG_NFS_V4_SECURITY_LABEL extern struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags); +static inline struct nfs4_label * +nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src) +{ + if (!dst || !src) + return NULL; + + if (src->len > NFS4_MAXLABELLEN) + return NULL; + + dst->lfs = src->lfs; + dst->pi = src->pi; + dst->len = src->len; + memcpy(dst->label, src->label, src->len); + + return dst; +} static inline void nfs4_label_free(struct nfs4_label *label) { if (label) { @@ -316,6 +332,11 @@ static inline void nfs4_label_free(void *label) {} static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) { } +static inline struct nfs4_label * +nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src) +{ + return NULL; +} #endif /* CONFIG_NFS_V4_SECURITY_LABEL */ /* proc.c */ diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index c85ffe67b5f3..e94a964e9b4f 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -912,6 +912,7 @@ struct nfs4_opendata { struct nfs_open_confirmres c_res; struct nfs4_string owner_name; struct nfs4_string group_name; + struct nfs4_label *a_label; struct nfs_fattr f_attr; struct nfs4_label *f_label; struct dentry *dir; @@ -1015,6 +1016,10 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, if (IS_ERR(p->f_label)) goto err_free_p; + p->a_label = nfs4_label_alloc(server, gfp_mask); + if (IS_ERR(p->a_label)) + goto err_free_f; + alloc_seqid = server->nfs_client->cl_mvops->alloc_seqid; p->o_arg.seqid = alloc_seqid(&sp->so_seqid, gfp_mask); if (IS_ERR(p->o_arg.seqid)) @@ -1043,7 +1048,7 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, p->o_arg.server = server; p->o_arg.bitmask = nfs4_bitmask(server, label); p->o_arg.open_bitmap = &nfs4_fattr_bitmap[0]; - p->o_arg.label = label; + p->o_arg.label = nfs4_label_copy(p->a_label, label); p->o_arg.claim = nfs4_map_atomic_open_claim(server, claim); switch (p->o_arg.claim) { case NFS4_OPEN_CLAIM_NULL: @@ -1076,6 +1081,8 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, return p; err_free_label: + nfs4_label_free(p->a_label); +err_free_f: nfs4_label_free(p->f_label); err_free_p: kfree(p); @@ -1095,6 +1102,7 @@ static void nfs4_opendata_free(struct kref *kref) nfs4_put_open_state(p->state); nfs4_put_state_owner(p->owner); + nfs4_label_free(p->a_label); nfs4_label_free(p->f_label); dput(p->dir); From 71b65445f0ed04c2afe3660f829779fddb2890c1 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Tue, 28 Jul 2015 13:51:21 +0300 Subject: [PATCH 211/428] ACPI / PM: Use target_state to set the device power state Commit 20dacb71ad28 ("ACPI / PM: Rework device power management to follow ACPI 6") changed the device power management to use D3hot if the device in question does not have _PR3 method even if D3cold was requested by the caller. However, if the device has _PR3 device->power.state is also set to D3hot instead of D3Cold after power resources have been turned off because device->power.state will be assigned from "state" instead of "target_state". Next time the device is transitioned to D0, acpi_power_transition() will find that the current power state of the device is D3hot instead of D3cold which causes it to power down all resources required for the current (wrong) state D3hot. Below is a simplified ASL example of a real touch panel device which triggers the problem: Scope (TPL1) { Name (_PR0, Package (1) { \_SB.PCI0.I2C1.PXTC }) Name (_PR3, Package (1) { \_SB.PCI0.I2C1.PXTC }) ... } In both D0 and D3hot the same power resource is required. However, when acpi_power_transition() turns off power resources required for D3hot (as the device is transitioned to D0) it powers down PXTC which then makes the device to lose its power. Fix this by assigning "target_state" to the device power state instead of "state" that is always D3hot even for devices with valid _PR3. Fixes: 20dacb71ad28 (ACPI / PM: Rework device power management to follow ACPI 6) Signed-off-by: Mika Westerberg Signed-off-by: Rafael J. Wysocki --- drivers/acpi/device_pm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index 717afcdb5f4a..88dbbb115285 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -231,7 +231,7 @@ int acpi_device_set_power(struct acpi_device *device, int state) dev_warn(&device->dev, "Failed to change power state to %s\n", acpi_power_state_string(state)); } else { - device->power.state = state; + device->power.state = target_state; ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device [%s] transitioned to %s\n", device->pnp.bus_id, From 559ed40752dc63e68f9b9ad301b20e6a3fe5cf21 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 26 Jul 2015 02:07:47 +0200 Subject: [PATCH 212/428] cpufreq: Avoid attempts to create duplicate symbolic links After commit 87549141d516 (cpufreq: Stop migrating sysfs files on hotplug) there is a problem with CPUs that share cpufreq policy objects with other CPUs and are initially offline. Say CPU1 shares a policy with CPU0 which is online and is registered first. As part of the registration process, cpufreq_add_dev() is called for it. It creates the policy object and a symbolic link to it from the CPU1's sysfs directory. If CPU1 is registered subsequently and it is offline at that time, cpufreq_add_dev() will attempt to create a symbolic link to the policy object for it, but that link is present already, so a warning about that will be triggered. To avoid that warning, make cpufreq use an additional CPU mask containing related CPUs that are actually present for each policy object. That mask is initialized when the policy object is populated after its creation (for the first online CPU using it) and it includes CPUs from the "policy CPUs" mask returned by the cpufreq driver's ->init() callback that are physically present at that time. Symbolic links to the policy are created only for the CPUs in that mask. If cpufreq_add_dev() is invoked for an offline CPU, it checks the new mask and only creates the symlink if the CPU was not in it (the CPU is added to the mask at the same time). In turn, cpufreq_remove_dev() drops the given CPU from the new mask, removes its symlink to the policy object and returns, unless it is the CPU owning the policy object. In that case, the policy object is moved to a new CPU's sysfs directory or deleted if the CPU being removed was the last user of the policy. While at it, notice that cpufreq_remove_dev() can't fail, because its return value is ignored, so make it ignore return values from __cpufreq_remove_dev_prepare() and __cpufreq_remove_dev_finish() and prevent these functions from aborting on errors returned by __cpufreq_governor(). Also drop the now unused sif argument from them. Fixes: 87549141d516 (cpufreq: Stop migrating sysfs files on hotplug) Signed-off-by: Rafael J. Wysocki Reported-and-tested-by: Russell King Acked-by: Viresh Kumar --- drivers/cpufreq/cpufreq.c | 108 +++++++++++++++++++------------------- include/linux/cpufreq.h | 1 + 2 files changed, 56 insertions(+), 53 deletions(-) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 26063afb3eba..7a3c30c4336f 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1002,7 +1002,7 @@ static int cpufreq_add_dev_symlink(struct cpufreq_policy *policy) int ret = 0; /* Some related CPUs might not be present (physically hotplugged) */ - for_each_cpu_and(j, policy->related_cpus, cpu_present_mask) { + for_each_cpu(j, policy->real_cpus) { if (j == policy->kobj_cpu) continue; @@ -1019,7 +1019,7 @@ static void cpufreq_remove_dev_symlink(struct cpufreq_policy *policy) unsigned int j; /* Some related CPUs might not be present (physically hotplugged) */ - for_each_cpu_and(j, policy->related_cpus, cpu_present_mask) { + for_each_cpu(j, policy->real_cpus) { if (j == policy->kobj_cpu) continue; @@ -1163,11 +1163,14 @@ static struct cpufreq_policy *cpufreq_policy_alloc(struct device *dev) if (!zalloc_cpumask_var(&policy->related_cpus, GFP_KERNEL)) goto err_free_cpumask; + if (!zalloc_cpumask_var(&policy->real_cpus, GFP_KERNEL)) + goto err_free_rcpumask; + ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq, &dev->kobj, "cpufreq"); if (ret) { pr_err("%s: failed to init policy->kobj: %d\n", __func__, ret); - goto err_free_rcpumask; + goto err_free_real_cpus; } INIT_LIST_HEAD(&policy->policy_list); @@ -1184,6 +1187,8 @@ static struct cpufreq_policy *cpufreq_policy_alloc(struct device *dev) return policy; +err_free_real_cpus: + free_cpumask_var(policy->real_cpus); err_free_rcpumask: free_cpumask_var(policy->related_cpus); err_free_cpumask: @@ -1234,6 +1239,7 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy, bool notify) write_unlock_irqrestore(&cpufreq_driver_lock, flags); cpufreq_policy_put_kobj(policy, notify); + free_cpumask_var(policy->real_cpus); free_cpumask_var(policy->related_cpus); free_cpumask_var(policy->cpus); kfree(policy); @@ -1258,14 +1264,17 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif) pr_debug("adding CPU %u\n", cpu); - /* - * Only possible if 'cpu' wasn't physically present earlier and we are - * here from subsys_interface add callback. A hotplug notifier will - * follow and we will handle it like logical CPU hotplug then. For now, - * just create the sysfs link. - */ - if (cpu_is_offline(cpu)) - return add_cpu_dev_symlink(per_cpu(cpufreq_cpu_data, cpu), cpu); + if (cpu_is_offline(cpu)) { + /* + * Only possible if we are here from the subsys_interface add + * callback. A hotplug notifier will follow and we will handle + * it as CPU online then. For now, just create the sysfs link, + * unless there is no policy or the link is already present. + */ + policy = per_cpu(cpufreq_cpu_data, cpu); + return policy && !cpumask_test_and_set_cpu(cpu, policy->real_cpus) + ? add_cpu_dev_symlink(policy, cpu) : 0; + } if (!down_read_trylock(&cpufreq_rwsem)) return 0; @@ -1307,6 +1316,10 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif) /* related cpus should atleast have policy->cpus */ cpumask_or(policy->related_cpus, policy->related_cpus, policy->cpus); + /* Remember which CPUs have been present at the policy creation time. */ + if (!recover_policy) + cpumask_and(policy->real_cpus, policy->cpus, cpu_present_mask); + /* * affected cpus must always be the one, which are online. We aren't * managing offline cpus here. @@ -1420,8 +1433,7 @@ nomem_out: return ret; } -static int __cpufreq_remove_dev_prepare(struct device *dev, - struct subsys_interface *sif) +static int __cpufreq_remove_dev_prepare(struct device *dev) { unsigned int cpu = dev->id; int ret = 0; @@ -1437,10 +1449,8 @@ static int __cpufreq_remove_dev_prepare(struct device *dev, if (has_target()) { ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP); - if (ret) { + if (ret) pr_err("%s: Failed to stop governor\n", __func__); - return ret; - } } down_write(&policy->rwsem); @@ -1473,8 +1483,7 @@ static int __cpufreq_remove_dev_prepare(struct device *dev, return ret; } -static int __cpufreq_remove_dev_finish(struct device *dev, - struct subsys_interface *sif) +static int __cpufreq_remove_dev_finish(struct device *dev) { unsigned int cpu = dev->id; int ret; @@ -1492,10 +1501,8 @@ static int __cpufreq_remove_dev_finish(struct device *dev, /* If cpu is last user of policy, free policy */ if (has_target()) { ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT); - if (ret) { + if (ret) pr_err("%s: Failed to exit governor\n", __func__); - return ret; - } } /* @@ -1506,10 +1513,6 @@ static int __cpufreq_remove_dev_finish(struct device *dev, if (cpufreq_driver->exit) cpufreq_driver->exit(policy); - /* Free the policy only if the driver is getting removed. */ - if (sif) - cpufreq_policy_free(policy, true); - return 0; } @@ -1521,42 +1524,41 @@ static int __cpufreq_remove_dev_finish(struct device *dev, static int cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif) { unsigned int cpu = dev->id; - int ret; + struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu); - /* - * Only possible if 'cpu' is getting physically removed now. A hotplug - * notifier should have already been called and we just need to remove - * link or free policy here. - */ - if (cpu_is_offline(cpu)) { - struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu); - struct cpumask mask; + if (!policy) + return 0; - if (!policy) - return 0; + if (cpu_online(cpu)) { + __cpufreq_remove_dev_prepare(dev); + __cpufreq_remove_dev_finish(dev); + } - cpumask_copy(&mask, policy->related_cpus); - cpumask_clear_cpu(cpu, &mask); - - /* - * Free policy only if all policy->related_cpus are removed - * physically. - */ - if (cpumask_intersects(&mask, cpu_present_mask)) { - remove_cpu_dev_symlink(policy, cpu); - return 0; - } + cpumask_clear_cpu(cpu, policy->real_cpus); + if (cpumask_empty(policy->real_cpus)) { cpufreq_policy_free(policy, true); return 0; } - ret = __cpufreq_remove_dev_prepare(dev, sif); + if (cpu != policy->kobj_cpu) { + remove_cpu_dev_symlink(policy, cpu); + } else { + /* + * The CPU owning the policy object is going away. Move it to + * another suitable CPU. + */ + unsigned int new_cpu = cpumask_first(policy->real_cpus); + struct device *new_dev = get_cpu_device(new_cpu); - if (!ret) - ret = __cpufreq_remove_dev_finish(dev, sif); + dev_dbg(dev, "%s: Moving policy object to CPU%u\n", __func__, new_cpu); - return ret; + sysfs_remove_link(&new_dev->kobj, "cpufreq"); + policy->kobj_cpu = new_cpu; + WARN_ON(kobject_move(&policy->kobj, &new_dev->kobj)); + } + + return 0; } static void handle_update(struct work_struct *work) @@ -2395,11 +2397,11 @@ static int cpufreq_cpu_callback(struct notifier_block *nfb, break; case CPU_DOWN_PREPARE: - __cpufreq_remove_dev_prepare(dev, NULL); + __cpufreq_remove_dev_prepare(dev); break; case CPU_POST_DEAD: - __cpufreq_remove_dev_finish(dev, NULL); + __cpufreq_remove_dev_finish(dev); break; case CPU_DOWN_FAILED: diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 29ad97c34fd5..bde1e567b3a9 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -62,6 +62,7 @@ struct cpufreq_policy { /* CPUs sharing clock, require sw coordination */ cpumask_var_t cpus; /* Online CPUs only */ cpumask_var_t related_cpus; /* Online + Offline CPUs */ + cpumask_var_t real_cpus; /* Related and present */ unsigned int shared_type; /* ACPI: ANY or ALL affected CPUs should set cpufreq */ From 3213afb8bf5cf8d8c68a2c2376bf1dda52afae5d Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Tue, 28 Jul 2015 10:25:03 -0700 Subject: [PATCH 213/428] Revert "Input: zforce - don't overwrite the stack" This reverts commit 7d01cd261c76f95913c81554a751968a1d282d3a because with given FRAME_MAXSIZE of 257 the check will never trigger and it causes warnings from GCC (with -Wtype-limits). Also the check was incorrect as it was not accounting for the already read 2 bytes of data stored in the buffer. --- drivers/input/touchscreen/zforce_ts.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/input/touchscreen/zforce_ts.c b/drivers/input/touchscreen/zforce_ts.c index 80285c71786e..f58a196521a9 100644 --- a/drivers/input/touchscreen/zforce_ts.c +++ b/drivers/input/touchscreen/zforce_ts.c @@ -429,7 +429,7 @@ static int zforce_read_packet(struct zforce_ts *ts, u8 *buf) goto unlock; } - if (buf[PAYLOAD_LENGTH] == 0 || buf[PAYLOAD_LENGTH] > FRAME_MAXSIZE) { + if (buf[PAYLOAD_LENGTH] == 0) { dev_err(&client->dev, "invalid payload length: %d\n", buf[PAYLOAD_LENGTH]); ret = -EIO; From fe0d34d242fa1e0dec059e774d146a705420bc9a Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 29 Jul 2015 05:52:14 +0930 Subject: [PATCH 214/428] module: weaken locking assertion for oops path. We don't actually hold the module_mutex when calling find_module_all from module_kallsyms_lookup_name: that's because it's used by the oops code and we don't want to deadlock. However, access to the list read-only is safe if preempt is disabled, so we can weaken the assertion. Keep a strong version for external callers though. Fixes: 0be964be0d45 ("module: Sanitize RCU usage and locking") Reported-by: He Kuang Cc: stable@kernel.org Acked-by: Peter Zijlstra (Intel) Signed-off-by: Rusty Russell --- kernel/module.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/kernel/module.c b/kernel/module.c index 4d2b82e610e2..b86b7bf1be38 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -602,13 +602,16 @@ const struct kernel_symbol *find_symbol(const char *name, } EXPORT_SYMBOL_GPL(find_symbol); -/* Search for module by name: must hold module_mutex. */ +/* + * Search for module by name: must hold module_mutex (or preempt disabled + * for read-only access). + */ static struct module *find_module_all(const char *name, size_t len, bool even_unformed) { struct module *mod; - module_assert_mutex(); + module_assert_mutex_or_preempt(); list_for_each_entry(mod, &modules, list) { if (!even_unformed && mod->state == MODULE_STATE_UNFORMED) @@ -621,6 +624,7 @@ static struct module *find_module_all(const char *name, size_t len, struct module *find_module(const char *name) { + module_assert_mutex(); return find_module_all(name, strlen(name), false); } EXPORT_SYMBOL_GPL(find_module); From b2442c5a7fe92cca08437070c8a45a7aa0d1703e Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 29 Jul 2015 11:48:00 +1000 Subject: [PATCH 215/428] xfs: call dax_fault on read page faults for DAX When modifying the patch series to handle the XFS MMAP_LOCK nesting of page faults, I botched the conversion of the read page fault path, and so it is only every calling through the page cache. Re-add the necessary __dax_fault() call for such files. Because the get_blocks callback on read faults may not set up the mapping buffer correctly to allow unwritten extent completion to be run, we need to allow callers of __dax_fault() to pass a null complete_unwritten() callback. The DAX code always zeros the unwritten page when it is read faulted so there are no stale data exposure issues with not doing the conversion. The only downside will be the potential for increased CPU overhead on repeated read faults of the same page. If this proves to be a problem, then the filesystem needs to fix it's get_block callback and provide a convert_unwritten() callback to the read fault path. Signed-off-by: Dave Chinner Reviewed-by: Matthew Wilcox Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/dax.c | 14 ++++++++++++-- fs/xfs/xfs_file.c | 21 +++++++++++++++------ 2 files changed, 27 insertions(+), 8 deletions(-) diff --git a/fs/dax.c b/fs/dax.c index c3e21ccfc358..a7f77e1fa18c 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -319,6 +319,12 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, * @vma: The virtual memory area where the fault occurred * @vmf: The description of the fault * @get_block: The filesystem method used to translate file offsets to blocks + * @complete_unwritten: The filesystem method used to convert unwritten blocks + * to written so the data written to them is exposed. This is required for + * required by write faults for filesystems that will return unwritten + * extent mappings from @get_block, but it is optional for reads as + * dax_insert_mapping() will always zero unwritten blocks. If the fs does + * not support unwritten extents, the it should pass NULL. * * When a page fault occurs, filesystems may call this helper in their * fault handler for DAX files. __dax_fault() assumes the caller has done all @@ -437,8 +443,12 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, * as for normal BH based IO completions. */ error = dax_insert_mapping(inode, &bh, vma, vmf); - if (buffer_unwritten(&bh)) - complete_unwritten(&bh, !error); + if (buffer_unwritten(&bh)) { + if (complete_unwritten) + complete_unwritten(&bh, !error); + else + WARN_ON_ONCE(!(vmf->flags & FAULT_FLAG_WRITE)); + } out: if (error == -ENOMEM) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index f0e8249722d4..db4acc1c3e73 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1514,18 +1514,27 @@ xfs_filemap_fault( struct vm_area_struct *vma, struct vm_fault *vmf) { - struct xfs_inode *ip = XFS_I(file_inode(vma->vm_file)); + struct inode *inode = file_inode(vma->vm_file); int ret; - trace_xfs_filemap_fault(ip); + trace_xfs_filemap_fault(XFS_I(inode)); /* DAX can shortcut the normal fault path on write faults! */ - if ((vmf->flags & FAULT_FLAG_WRITE) && IS_DAX(VFS_I(ip))) + if ((vmf->flags & FAULT_FLAG_WRITE) && IS_DAX(inode)) return xfs_filemap_page_mkwrite(vma, vmf); - xfs_ilock(ip, XFS_MMAPLOCK_SHARED); - ret = filemap_fault(vma, vmf); - xfs_iunlock(ip, XFS_MMAPLOCK_SHARED); + xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); + if (IS_DAX(inode)) { + /* + * we do not want to trigger unwritten extent conversion on read + * faults - that is unnecessary overhead and would also require + * changes to xfs_get_blocks_direct() to map unwritten extent + * ioend for conversion on read-only mappings. + */ + ret = __dax_fault(vma, vmf, xfs_get_blocks_direct, NULL); + } else + ret = filemap_fault(vma, vmf); + xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); return ret; } From e3c32ee9e3e747fec01eb38e6610a9157d44c3ea Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 29 Jul 2015 11:48:01 +1000 Subject: [PATCH 216/428] xfs: remote attribute headers contain an invalid LSN In recent testing, a system that crashed failed log recovery on restart with a bad symlink buffer magic number: XFS (vda): Starting recovery (logdev: internal) XFS (vda): Bad symlink block magic! XFS: Assertion failed: 0, file: fs/xfs/xfs_log_recover.c, line: 2060 On examination of the log via xfs_logprint, none of the symlink buffers in the log had a bad magic number, nor were any other types of buffer log format headers mis-identified as symlink buffers. Tracing was used to find the buffer the kernel was tripping over, and xfs_db identified it's contents as: 000: 5841524d 00000000 00000346 64d82b48 8983e692 d71e4680 a5f49e2c b317576e 020: 00000000 00602038 00000000 006034ce d0020000 00000000 4d4d4d4d 4d4d4d4d 040: 4d4d4d4d 4d4d4d4d 4d4d4d4d 4d4d4d4d 4d4d4d4d 4d4d4d4d 4d4d4d4d 4d4d4d4d 060: 4d4d4d4d 4d4d4d4d 4d4d4d4d 4d4d4d4d 4d4d4d4d 4d4d4d4d 4d4d4d4d 4d4d4d4d ..... This is a remote attribute buffer, which are notable in that they are not logged but are instead written synchronously by the remote attribute code so that they exist on disk before the attribute transactions are committed to the journal. The above remote attribute block has an invalid LSN in it - cycle 0xd002000, block 0 - which means when log recovery comes along to determine if the transaction that writes to the underlying block should be replayed, it sees a block that has a future LSN and so does not replay the buffer data in the transaction. Instead, it validates the buffer magic number and attaches the buffer verifier to it. It is this buffer magic number check that is failing in the above assert, indicating that we skipped replay due to the LSN of the underlying buffer. The problem here is that the remote attribute buffers cannot have a valid LSN placed into them, because the transaction that contains the attribute tree pointer changes and the block allocation that the attribute data is being written to hasn't yet been committed. Hence the LSN field in the attribute block is completely unwritten, thereby leaving the underlying contents of the block in the LSN field. It could have any value, and hence a future overwrite of the block by log recovery may or may not work correctly. Fix this by always writing an invalid LSN to the remote attribute block, as any buffer in log recovery that needs to write over the remote attribute should occur. We are protected from having old data written over the attribute by the fact that freeing the block before the remote attribute is written will result in the buffer being marked stale in the log and so all changes prior to the buffer stale transaction will be cancelled by log recovery. Hence it is safe to ignore the LSN in the case or synchronously written, unlogged metadata such as remote attribute blocks, and to ensure we do that correctly, we need to write an invalid LSN to all remote attribute blocks to trigger immediate recovery of metadata that is written over the top. As a further protection for filesystems that may already have remote attribute blocks with bad LSNs on disk, change the log recovery code to always trigger immediate recovery of metadata over remote attribute blocks. cc: Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_attr_remote.c | 29 +++++++++++++++++++++++------ fs/xfs/xfs_log_recover.c | 11 ++++++++--- 2 files changed, 31 insertions(+), 9 deletions(-) diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c index 20de88d1bf86..2faec26962e8 100644 --- a/fs/xfs/libxfs/xfs_attr_remote.c +++ b/fs/xfs/libxfs/xfs_attr_remote.c @@ -159,11 +159,10 @@ xfs_attr3_rmt_write_verify( struct xfs_buf *bp) { struct xfs_mount *mp = bp->b_target->bt_mount; - struct xfs_buf_log_item *bip = bp->b_fspriv; + int blksize = mp->m_attr_geo->blksize; char *ptr; int len; xfs_daddr_t bno; - int blksize = mp->m_attr_geo->blksize; /* no verification of non-crc buffers */ if (!xfs_sb_version_hascrc(&mp->m_sb)) @@ -175,16 +174,22 @@ xfs_attr3_rmt_write_verify( ASSERT(len >= blksize); while (len > 0) { + struct xfs_attr3_rmt_hdr *rmt = (struct xfs_attr3_rmt_hdr *)ptr; + if (!xfs_attr3_rmt_verify(mp, ptr, blksize, bno)) { xfs_buf_ioerror(bp, -EFSCORRUPTED); xfs_verifier_error(bp); return; } - if (bip) { - struct xfs_attr3_rmt_hdr *rmt; - rmt = (struct xfs_attr3_rmt_hdr *)ptr; - rmt->rm_lsn = cpu_to_be64(bip->bli_item.li_lsn); + /* + * Ensure we aren't writing bogus LSNs to disk. See + * xfs_attr3_rmt_hdr_set() for the explanation. + */ + if (rmt->rm_lsn != cpu_to_be64(NULLCOMMITLSN)) { + xfs_buf_ioerror(bp, -EFSCORRUPTED); + xfs_verifier_error(bp); + return; } xfs_update_cksum(ptr, blksize, XFS_ATTR3_RMT_CRC_OFF); @@ -221,6 +226,18 @@ xfs_attr3_rmt_hdr_set( rmt->rm_owner = cpu_to_be64(ino); rmt->rm_blkno = cpu_to_be64(bno); + /* + * Remote attribute blocks are written synchronously, so we don't + * have an LSN that we can stamp in them that makes any sense to log + * recovery. To ensure that log recovery handles overwrites of these + * blocks sanely (i.e. once they've been freed and reallocated as some + * other type of metadata) we need to ensure that the LSN has a value + * that tells log recovery to ignore the LSN and overwrite the buffer + * with whatever is in it's log. To do this, we use the magic + * NULLCOMMITLSN to indicate that the LSN is invalid. + */ + rmt->rm_lsn = cpu_to_be64(NULLCOMMITLSN); + return sizeof(struct xfs_attr3_rmt_hdr); } diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 01dd228ca05e..480ebba8464f 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1886,9 +1886,14 @@ xlog_recover_get_buf_lsn( uuid = &((struct xfs_dir3_blk_hdr *)blk)->uuid; break; case XFS_ATTR3_RMT_MAGIC: - lsn = be64_to_cpu(((struct xfs_attr3_rmt_hdr *)blk)->rm_lsn); - uuid = &((struct xfs_attr3_rmt_hdr *)blk)->rm_uuid; - break; + /* + * Remote attr blocks are written synchronously, rather than + * being logged. That means they do not contain a valid LSN + * (i.e. transactionally ordered) in them, and hence any time we + * see a buffer to replay over the top of a remote attribute + * block we should simply do so. + */ + goto recover_immediately; case XFS_SB_MAGIC: lsn = be64_to_cpu(((struct xfs_dsb *)blk)->sb_lsn); uuid = &((struct xfs_dsb *)blk)->sb_uuid; From df150ed102baa0e78c06e08e975dfb47147dd677 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 29 Jul 2015 11:48:02 +1000 Subject: [PATCH 217/428] xfs: remote attributes need to be considered data We don't log remote attribute contents, and instead write them synchronously before we commit the block allocation and attribute tree update transaction. As a result we are writing to the allocated space before the allcoation has been made permanent. As a result, we cannot consider this allocation to be a metadata allocation. Metadata allocation can take blocks from the free list and so reuse them before the transaction that freed the block is committed to disk. This behaviour is perfectly fine for journalled metadata changes as log recovery will ensure the free operation is replayed before the overwrite, but for remote attribute writes this is not the case. Hence we have to consider the remote attribute blocks to contain data and allocate accordingly. We do this by dropping the XFS_BMAPI_METADATA flag from the block allocation. This means the allocation will not use blocks that are on the busy list without first ensuring that the freeing transaction has been committed to disk and the blocks removed from the busy list. This ensures we will never overwrite a freed block without first ensuring that it is really free. cc: Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_attr_remote.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c index 2faec26962e8..dd714037c322 100644 --- a/fs/xfs/libxfs/xfs_attr_remote.c +++ b/fs/xfs/libxfs/xfs_attr_remote.c @@ -451,14 +451,21 @@ xfs_attr_rmtval_set( /* * Allocate a single extent, up to the size of the value. + * + * Note that we have to consider this a data allocation as we + * write the remote attribute without logging the contents. + * Hence we must ensure that we aren't using blocks that are on + * the busy list so that we don't overwrite blocks which have + * recently been freed but their transactions are not yet + * committed to disk. If we overwrite the contents of a busy + * extent and then crash then the block may not contain the + * correct metadata after log recovery occurs. */ xfs_bmap_init(args->flist, args->firstblock); nmap = 1; error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno, - blkcnt, - XFS_BMAPI_ATTRFORK | XFS_BMAPI_METADATA, - args->firstblock, args->total, &map, &nmap, - args->flist); + blkcnt, XFS_BMAPI_ATTRFORK, args->firstblock, + args->total, &map, &nmap, args->flist); if (!error) { error = xfs_bmap_finish(&args->trans, args->flist, &committed); From 76b91c32dd86f624b5df038dcb68cddd5a18d355 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Thu, 23 Jul 2015 11:01:05 -0700 Subject: [PATCH 218/428] bridge: stp: when using userspace stp stop kernel hello and hold timers These should be handled only by the respective STP which is in control. They become problematic for devices with limited resources with many ports because the hold_timer is per port and fires each second and the hello timer fires each 2 seconds even though it's global. While in user-space STP mode these timers are completely unnecessary so it's better to keep them off. Also ensure that when the bridge is up these timers are started only when running with kernel STP. Signed-off-by: Satish Ashok Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/bridge/br_stp.c | 5 +++-- net/bridge/br_stp_if.c | 13 ++++++++++++- net/bridge/br_stp_timer.c | 4 +++- 3 files changed, 18 insertions(+), 4 deletions(-) diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index b4b6dab9c285..ed74ffaa851f 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -209,8 +209,9 @@ void br_transmit_config(struct net_bridge_port *p) br_send_config_bpdu(p, &bpdu); p->topology_change_ack = 0; p->config_pending = 0; - mod_timer(&p->hold_timer, - round_jiffies(jiffies + BR_HOLD_TIME)); + if (p->br->stp_enabled == BR_KERNEL_STP) + mod_timer(&p->hold_timer, + round_jiffies(jiffies + BR_HOLD_TIME)); } } diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index a2730e7196cd..4ca449a16132 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -48,7 +48,8 @@ void br_stp_enable_bridge(struct net_bridge *br) struct net_bridge_port *p; spin_lock_bh(&br->lock); - mod_timer(&br->hello_timer, jiffies + br->hello_time); + if (br->stp_enabled == BR_KERNEL_STP) + mod_timer(&br->hello_timer, jiffies + br->hello_time); mod_timer(&br->gc_timer, jiffies + HZ/10); br_config_bpdu_generation(br); @@ -127,6 +128,7 @@ static void br_stp_start(struct net_bridge *br) int r; char *argv[] = { BR_STP_PROG, br->dev->name, "start", NULL }; char *envp[] = { NULL }; + struct net_bridge_port *p; r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC); @@ -140,6 +142,10 @@ static void br_stp_start(struct net_bridge *br) if (r == 0) { br->stp_enabled = BR_USER_STP; br_debug(br, "userspace STP started\n"); + /* Stop hello and hold timers */ + del_timer(&br->hello_timer); + list_for_each_entry(p, &br->port_list, list) + del_timer(&p->hold_timer); } else { br->stp_enabled = BR_KERNEL_STP; br_debug(br, "using kernel STP\n"); @@ -156,12 +162,17 @@ static void br_stp_stop(struct net_bridge *br) int r; char *argv[] = { BR_STP_PROG, br->dev->name, "stop", NULL }; char *envp[] = { NULL }; + struct net_bridge_port *p; if (br->stp_enabled == BR_USER_STP) { r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC); br_info(br, "userspace STP stopped, return code %d\n", r); /* To start timers on any ports left in blocking */ + mod_timer(&br->hello_timer, jiffies + br->hello_time); + list_for_each_entry(p, &br->port_list, list) + mod_timer(&p->hold_timer, + round_jiffies(jiffies + BR_HOLD_TIME)); spin_lock_bh(&br->lock); br_port_state_selection(br); spin_unlock_bh(&br->lock); diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c index 7caf7fae2d5b..5f0f5af0ec35 100644 --- a/net/bridge/br_stp_timer.c +++ b/net/bridge/br_stp_timer.c @@ -40,7 +40,9 @@ static void br_hello_timer_expired(unsigned long arg) if (br->dev->flags & IFF_UP) { br_config_bpdu_generation(br); - mod_timer(&br->hello_timer, round_jiffies(jiffies + br->hello_time)); + if (br->stp_enabled != BR_USER_STP) + mod_timer(&br->hello_timer, + round_jiffies(jiffies + br->hello_time)); } spin_unlock(&br->lock); } From 865b804244f228e80fb62abe464296399253cce8 Mon Sep 17 00:00:00 2001 From: David Ward Date: Sun, 26 Jul 2015 12:18:58 -0400 Subject: [PATCH 219/428] net/ipv4: suppress NETDEV_UP notification on address lifetime update This notification causes the FIB to be updated, which is not needed because the address already exists, and more importantly it may undo intentional changes that were made to the FIB after the address was originally added. (As a point of comparison, when an address becomes deprecated because its preferred lifetime expired, a notification on this chain is not generated.) The motivation for this commit is fixing an incompatibility between DHCP clients which set and update the address lifetime according to the lease, and a commercial VPN client which replaces kernel routes in a way that outbound traffic is sent only through the tunnel (and disconnects if any further route changes are detected via netlink). Signed-off-by: David Ward Signed-off-by: David S. Miller --- net/ipv4/devinet.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index e813196c91c7..2d9cb1748f81 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -882,7 +882,6 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) queue_delayed_work(system_power_efficient_wq, &check_lifetime_work, 0); rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid); - blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa); } return 0; } From 11c91ef98f37cd743098de26160fffd7f9bd40e1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 27 Jul 2015 11:33:50 +0200 Subject: [PATCH 220/428] arp: filter NOARP neighbours for SIOCGARP When arp is off on a device, and ioctl(SIOCGARP) is queried, a buggy answer is given with MAC address of the device, instead of the mac address of the destination/gateway. We filter out NUD_NOARP neighbours for /proc/net/arp, we must do the same for SIOCGARP ioctl. Tested: lpaa23:~# ./arp 10.246.7.190 MAC=00:01:e8:22:cb:1d // correct answer lpaa23:~# ip link set dev eth0 arp off lpaa23:~# cat /proc/net/arp # check arp table is now 'empty' IP address HW type Flags HW address Mask Device lpaa23:~# ./arp 10.246.7.190 MAC=00:1a:11:c3:0d:7f // buggy answer before patch (this is eth0 mac) After patch : lpaa23:~# ip link set dev eth0 arp off lpaa23:~# ./arp 10.246.7.190 ioctl(SIOCGARP) failed: No such device or address Signed-off-by: Eric Dumazet Reported-by: Vytautas Valancius Cc: Willem de Bruijn Signed-off-by: David S. Miller --- net/ipv4/arp.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 933a92820d26..6c8b1fbafce8 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1017,14 +1017,16 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev) neigh = neigh_lookup(&arp_tbl, &ip, dev); if (neigh) { - read_lock_bh(&neigh->lock); - memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len); - r->arp_flags = arp_state_to_flags(neigh); - read_unlock_bh(&neigh->lock); - r->arp_ha.sa_family = dev->type; - strlcpy(r->arp_dev, dev->name, sizeof(r->arp_dev)); + if (!(neigh->nud_state & NUD_NOARP)) { + read_lock_bh(&neigh->lock); + memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len); + r->arp_flags = arp_state_to_flags(neigh); + read_unlock_bh(&neigh->lock); + r->arp_ha.sa_family = dev->type; + strlcpy(r->arp_dev, dev->name, sizeof(r->arp_dev)); + err = 0; + } neigh_release(neigh); - err = 0; } return err; } From 3a05d12f46cb95a6a685114819363a56e6170996 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 29 Jul 2015 09:04:52 +0200 Subject: [PATCH 221/428] ALSA: hda - Apply a fixup to Dell Vostro 5480 Dell Vostro 5480 (1028:069a) needs the very same quirk used for Vostro 5470 model to make bass speakers properly working. Reported-and-tested-by: Paulo Roberto de Oliveira Castro Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 4ae877c3b6a1..18ae17ebb356 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5185,6 +5185,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x064a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x064b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0665, "Dell XPS 13", ALC288_FIXUP_DELL_XPS_13), + SND_PCI_QUIRK(0x1028, 0x069a, "Dell Vostro 5480", ALC290_FIXUP_SUBWOOFER_HSJACK), SND_PCI_QUIRK(0x1028, 0x06c7, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x06d9, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x06da, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), From dbd46ab412b8fb395f2b0ff6f6a7eec9df311550 Mon Sep 17 00:00:00 2001 From: Alexander Drozdov Date: Tue, 28 Jul 2015 13:57:01 +0300 Subject: [PATCH 222/428] packet: tpacket_snd(): fix signed/unsigned comparison tpacket_fill_skb() can return a negative value (-errno) which is stored in tp_len variable. In that case the following condition will be (but shouldn't be) true: tp_len > dev->mtu + dev->hard_header_len as dev->mtu and dev->hard_header_len are both unsigned. That may lead to just returning an incorrect EMSGSIZE errno to the user. Fixes: 52f1454f629fa ("packet: allow to transmit +4 byte in TX_RING slot for VLAN case") Signed-off-by: Alexander Drozdov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- net/packet/af_packet.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c7c42eb617ef..ed458b315ef4 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2403,7 +2403,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) } tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto, addr, hlen); - if (tp_len > dev->mtu + dev->hard_header_len) { + if (likely(tp_len >= 0) && + tp_len > dev->mtu + dev->hard_header_len) { struct ethhdr *ehdr; /* Earlier code assumed this would be a VLAN pkt, * double-check this now that we have the actual From 2d1cb7f658fb9c3ba8f9dab8aca297d4dfdec835 Mon Sep 17 00:00:00 2001 From: Yao-Wen Mao Date: Wed, 29 Jul 2015 15:13:54 +0800 Subject: [PATCH 223/428] ALSA: usb-audio: add dB range mapping for some devices Add the correct dB ranges of Bose Companion 5 and Drangonfly DAC 1.2. Signed-off-by: Yao-Wen Mao Cc: Signed-off-by: Takashi Iwai --- sound/usb/mixer_maps.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c index e5000da9e9d7..6a803eff87f7 100644 --- a/sound/usb/mixer_maps.c +++ b/sound/usb/mixer_maps.c @@ -341,6 +341,20 @@ static const struct usbmix_name_map scms_usb3318_map[] = { { 0 } }; +/* Bose companion 5, the dB conversion factor is 16 instead of 256 */ +static struct usbmix_dB_map bose_companion5_dB = {-5006, -6}; +static struct usbmix_name_map bose_companion5_map[] = { + { 3, NULL, .dB = &bose_companion5_dB }, + { 0 } /* terminator */ +}; + +/* Dragonfly DAC 1.2, the dB conversion factor is 1 instead of 256 */ +static struct usbmix_dB_map dragonfly_1_2_dB = {0, 5000}; +static struct usbmix_name_map dragonfly_1_2_map[] = { + { 7, NULL, .dB = &dragonfly_1_2_dB }, + { 0 } /* terminator */ +}; + /* * Control map entries */ @@ -451,6 +465,16 @@ static struct usbmix_ctl_map usbmix_ctl_maps[] = { .id = USB_ID(0x25c4, 0x0003), .map = scms_usb3318_map, }, + { + /* Bose Companion 5 */ + .id = USB_ID(0x05a7, 0x1020), + .map = bose_companion5_map, + }, + { + /* Dragonfly DAC 1.2 */ + .id = USB_ID(0x21b4, 0x0081), + .map = dragonfly_1_2_map, + }, { 0 } /* terminator */ }; From ee0a227b7ac6e75f28e10269f81c7ec6eb600952 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 15 Jul 2015 09:50:42 +0100 Subject: [PATCH 224/428] drm/i915: Replace WARN inside I915_READ64_2x32 with retry loop MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since we may conceivably encounter situations where the upper part of the 64bit register changes between reads, for example when a timestamp counter overflows, change the WARN into a retry loop. Signed-off-by: Chris Wilson Cc: Michał Winiarski Cc: stable@vger.kernel.org Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_drv.h | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 5f27290201e0..fd1de451c8c6 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -3303,15 +3303,14 @@ int intel_freq_opcode(struct drm_i915_private *dev_priv, int val); #define I915_READ64(reg) dev_priv->uncore.funcs.mmio_readq(dev_priv, (reg), true) #define I915_READ64_2x32(lower_reg, upper_reg) ({ \ - u32 upper = I915_READ(upper_reg); \ - u32 lower = I915_READ(lower_reg); \ - u32 tmp = I915_READ(upper_reg); \ - if (upper != tmp) { \ - upper = tmp; \ - lower = I915_READ(lower_reg); \ - WARN_ON(I915_READ(upper_reg) != upper); \ - } \ - (u64)upper << 32 | lower; }) + u32 upper, lower, tmp; \ + tmp = I915_READ(upper_reg); \ + do { \ + upper = tmp; \ + lower = I915_READ(lower_reg); \ + tmp = I915_READ(upper_reg); \ + } while (upper != tmp); \ + (u64)upper << 32 | lower; }) #define POSTING_READ(reg) (void)I915_READ_NOTRACE(reg) #define POSTING_READ16(reg) (void)I915_READ16_NOTRACE(reg) From e350f8045f642dfc4c28a81c57d2103e1f7ceead Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Thu, 11 Jun 2015 20:19:25 +0900 Subject: [PATCH 225/428] extcon: palmas: Fix NULL pointer error This patch fixes NULL pointer error by removing the unneeded kfree() call of edev->name because extcon-palmas no longer allocate the memory for edev->name. Fixes: d71aadda19f8 ("extcon: Remove the optional name of extcon device") Signed-off-by: Chanwoo Choi Reviewed-by: Krzysztof Kozlowski --- drivers/extcon/extcon-palmas.c | 13 ------------- 1 file changed, 13 deletions(-) diff --git a/drivers/extcon/extcon-palmas.c b/drivers/extcon/extcon-palmas.c index 080d5cc27055..eebdf2a33bfe 100644 --- a/drivers/extcon/extcon-palmas.c +++ b/drivers/extcon/extcon-palmas.c @@ -200,7 +200,6 @@ static int palmas_usb_probe(struct platform_device *pdev) status = devm_extcon_dev_register(&pdev->dev, palmas_usb->edev); if (status) { dev_err(&pdev->dev, "failed to register extcon device\n"); - kfree(palmas_usb->edev->name); return status; } @@ -214,7 +213,6 @@ static int palmas_usb_probe(struct platform_device *pdev) if (status < 0) { dev_err(&pdev->dev, "can't get IRQ %d, err %d\n", palmas_usb->id_irq, status); - kfree(palmas_usb->edev->name); return status; } } @@ -229,7 +227,6 @@ static int palmas_usb_probe(struct platform_device *pdev) if (status < 0) { dev_err(&pdev->dev, "can't get IRQ %d, err %d\n", palmas_usb->vbus_irq, status); - kfree(palmas_usb->edev->name); return status; } } @@ -239,15 +236,6 @@ static int palmas_usb_probe(struct platform_device *pdev) return 0; } -static int palmas_usb_remove(struct platform_device *pdev) -{ - struct palmas_usb *palmas_usb = platform_get_drvdata(pdev); - - kfree(palmas_usb->edev->name); - - return 0; -} - #ifdef CONFIG_PM_SLEEP static int palmas_usb_suspend(struct device *dev) { @@ -288,7 +276,6 @@ static const struct of_device_id of_palmas_match_tbl[] = { static struct platform_driver palmas_usb_driver = { .probe = palmas_usb_probe, - .remove = palmas_usb_remove, .driver = { .name = "palmas-usb", .of_match_table = of_palmas_match_tbl, From 4b563ea317c2262987f0675abf15066614f536a1 Mon Sep 17 00:00:00 2001 From: Jie Yang Date: Tue, 28 Jul 2015 16:01:05 +0800 Subject: [PATCH 226/428] ASoC: Intel: haswell: fix initialize 'NULL device *' issue Add initialization for sst_hsw.dev at init stage, which fix the 'NULL device *' warning issues. Signed-off-by: Jie Yang Signed-off-by: Mark Brown --- sound/soc/intel/haswell/sst-haswell-ipc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/soc/intel/haswell/sst-haswell-ipc.c b/sound/soc/intel/haswell/sst-haswell-ipc.c index f95f271aab0c..f6efa9d4acad 100644 --- a/sound/soc/intel/haswell/sst-haswell-ipc.c +++ b/sound/soc/intel/haswell/sst-haswell-ipc.c @@ -2119,6 +2119,8 @@ int sst_hsw_dsp_init(struct device *dev, struct sst_pdata *pdata) if (hsw == NULL) return -ENOMEM; + hsw->dev = dev; + ipc = &hsw->ipc; ipc->dev = dev; ipc->ops.tx_msg = hsw_tx_msg; From 45f503df1ba445359b94e1758c5e4f2c3460c8e4 Mon Sep 17 00:00:00 2001 From: Jie Yang Date: Tue, 28 Jul 2015 16:01:06 +0800 Subject: [PATCH 227/428] ASoC: Intel: sst_byt: fix initialize 'NULL device *' issue Add initialization for sst_byt.dev at init stage, which fix the 'NULL device *' warning issues. Signed-off-by: Jie Yang Signed-off-by: Mark Brown --- sound/soc/intel/baytrail/sst-baytrail-ipc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/soc/intel/baytrail/sst-baytrail-ipc.c b/sound/soc/intel/baytrail/sst-baytrail-ipc.c index 4c01bb43928d..5bbaa667bec1 100644 --- a/sound/soc/intel/baytrail/sst-baytrail-ipc.c +++ b/sound/soc/intel/baytrail/sst-baytrail-ipc.c @@ -701,6 +701,8 @@ int sst_byt_dsp_init(struct device *dev, struct sst_pdata *pdata) if (byt == NULL) return -ENOMEM; + byt->dev = dev; + ipc = &byt->ipc; ipc->dev = dev; ipc->ops.tx_msg = byt_tx_msg; From 342e84490574cbb2a9c5b1d0886a112ad2bcf4d7 Mon Sep 17 00:00:00 2001 From: "U. Artie Eoff" Date: Tue, 28 Jul 2015 13:29:56 -0700 Subject: [PATCH 228/428] ALSA: hda - Fix race between PM ops and HDA init/probe PM ops could be triggered before HDA is done initializing and cause PM to set HDA controller to D3Hot. This can result in "CORB reset timeout#2, CORBRP = 65535" and "no codecs initialized". Additionally, PM ops can be triggered before azx_probe_continue finishes (async probe). This can result in a NULL deref kernel crash. To fix this, avoid PM ops if !chip->running. Signed-off-by: U. Artie Eoff Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_intel.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 735bdcb04ce8..c38c68f57938 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -867,7 +867,7 @@ static int azx_suspend(struct device *dev) chip = card->private_data; hda = container_of(chip, struct hda_intel, chip); - if (chip->disabled || hda->init_failed) + if (chip->disabled || hda->init_failed || !chip->running) return 0; bus = azx_bus(chip); @@ -902,7 +902,7 @@ static int azx_resume(struct device *dev) chip = card->private_data; hda = container_of(chip, struct hda_intel, chip); - if (chip->disabled || hda->init_failed) + if (chip->disabled || hda->init_failed || !chip->running) return 0; if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL @@ -1027,7 +1027,7 @@ static int azx_runtime_idle(struct device *dev) return 0; if (!power_save_controller || !azx_has_pm_runtime(chip) || - azx_bus(chip)->codec_powered) + azx_bus(chip)->codec_powered || !chip->running) return -EBUSY; return 0; From 3508e6590d4729ac07f01f7ae2256c2f9dc738b8 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 29 Jul 2015 14:11:28 -0400 Subject: [PATCH 229/428] Revert "dm cache: do not wake_worker() in free_migration()" This reverts commit 386cb7cdeeef97e0bf082a8d6bbfc07a2ccce07b. Taking the wake_worker() out of free_migration() will slow writeback dramatically, and hence adaptability. Say we have 10k blocks that need writing back, but are only able to issue 5 concurrently due to the migration bandwidth: it's imperative that we wake_worker() immediately after migration completion; waiting for the next 1 second wake up (via do_waker) means it'll take a long time to write that all back. Reported-by: Joe Thornber Signed-off-by: Mike Snitzer --- drivers/md/dm-cache-target.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index b680da5d7b93..64e96a2bed58 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -424,6 +424,7 @@ static void free_migration(struct dm_cache_migration *mg) wake_up(&cache->migration_wait); mempool_free(mg, cache->migration_pool); + wake_worker(cache); } static int prealloc_data_structs(struct cache *cache, struct prealloc *p) From 795e633a2dc6cbbeac68bc7f6006082150d38bb7 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 29 Jul 2015 13:48:23 -0400 Subject: [PATCH 230/428] dm cache: fix device destroy hang due to improper prealloc_used accounting Commit 665022d72f9 ("dm cache: avoid calls to prealloc_free_structs() if possible") introduced a regression that caused the removal of a DM cache device to hang in cache_postsuspend()'s call to wait_for_migrations() with the following stack trace: [] schedule+0x37/0x80 [] cache_postsuspend+0xbb/0x470 [dm_cache] [] ? prepare_to_wait_event+0xf0/0xf0 [] dm_table_postsuspend_targets+0x47/0x60 [dm_mod] [] __dm_destroy+0x215/0x250 [dm_mod] [] dm_destroy+0x13/0x20 [dm_mod] [] dev_remove+0x10d/0x170 [dm_mod] [] ? dev_suspend+0x240/0x240 [dm_mod] [] ctl_ioctl+0x255/0x4d0 [dm_mod] [] ? SYSC_semtimedop+0x280/0xe10 [] dm_ctl_ioctl+0x13/0x20 [dm_mod] [] do_vfs_ioctl+0x2d2/0x4b0 [] ? __audit_syscall_entry+0xaf/0x100 [] ? do_audit_syscall_entry+0x66/0x70 [] SyS_ioctl+0x79/0x90 [] ? syscall_trace_leave+0xb8/0x110 [] entry_SYSCALL_64_fastpath+0x12/0x71 Fix this by accounting for the call to prealloc_data_structs() immediately _before_ the call as opposed to after. This is needed because it is possible to break out of the control loop after the call to prealloc_data_structs() but before prealloc_used was set to true. Signed-off-by: Mike Snitzer --- drivers/md/dm-cache-target.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 64e96a2bed58..1fe93cfea7d3 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -1967,6 +1967,7 @@ static void process_deferred_bios(struct cache *cache) * this bio might require one, we pause until there are some * prepared mappings to process. */ + prealloc_used = true; if (prealloc_data_structs(cache, &structs)) { spin_lock_irqsave(&cache->lock, flags); bio_list_merge(&cache->deferred_bios, &bios); @@ -1982,7 +1983,6 @@ static void process_deferred_bios(struct cache *cache) process_discard_bio(cache, &structs, bio); else process_bio(cache, &structs, bio); - prealloc_used = true; } if (prealloc_used) @@ -2011,6 +2011,7 @@ static void process_deferred_cells(struct cache *cache) * this bio might require one, we pause until there are some * prepared mappings to process. */ + prealloc_used = true; if (prealloc_data_structs(cache, &structs)) { spin_lock_irqsave(&cache->lock, flags); list_splice(&cells, &cache->deferred_cells); @@ -2019,7 +2020,6 @@ static void process_deferred_cells(struct cache *cache) } process_cell(cache, &structs, cell); - prealloc_used = true; } if (prealloc_used) @@ -2081,6 +2081,7 @@ static void writeback_some_dirty_blocks(struct cache *cache) if (policy_writeback_work(cache->policy, &oblock, &cblock, busy)) break; /* no work to do */ + prealloc_used = true; if (prealloc_data_structs(cache, &structs) || get_cell(cache, oblock, &structs, &old_ocell)) { policy_set_dirty(cache->policy, oblock); @@ -2088,7 +2089,6 @@ static void writeback_some_dirty_blocks(struct cache *cache) } writeback(cache, &structs, oblock, cblock, old_ocell); - prealloc_used = true; } if (prealloc_used) From df356d5e81b04dd51dd9f23f2bce7d73dd929899 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Tue, 28 Jul 2015 19:05:37 +0900 Subject: [PATCH 231/428] bridge: Fix network header pointer for vlan tagged packets There are several devices that can receive vlan tagged packets with CHECKSUM_PARTIAL like tap, possibly veth and xennet. When (multiple) vlan tagged packets with CHECKSUM_PARTIAL are forwarded by bridge to a device with the IP_CSUM feature, they end up with checksum error because before entering bridge, the network header is set to ETH_HLEN (not including vlan header length) in __netif_receive_skb_core(), get_rps_cpu(), or drivers' rx functions, and nobody fixes the pointer later. Since the network header is exepected to be ETH_HLEN in flow-dissection and hash-calculation in RPS in rx path, and since the header pointer fix is needed only in tx path, set the appropriate network header on forwarding packets. Signed-off-by: Toshiaki Makita Signed-off-by: David S. Miller --- net/bridge/br_forward.c | 29 ++++++++++++++++++++++------- 1 file changed, 22 insertions(+), 7 deletions(-) diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 0ff6e1bbca91..fa7bfced888e 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -37,15 +37,30 @@ static inline int should_deliver(const struct net_bridge_port *p, int br_dev_queue_push_xmit(struct sock *sk, struct sk_buff *skb) { - if (!is_skb_forwardable(skb->dev, skb)) { - kfree_skb(skb); - } else { - skb_push(skb, ETH_HLEN); - br_drop_fake_rtable(skb); - skb_sender_cpu_clear(skb); - dev_queue_xmit(skb); + if (!is_skb_forwardable(skb->dev, skb)) + goto drop; + + skb_push(skb, ETH_HLEN); + br_drop_fake_rtable(skb); + skb_sender_cpu_clear(skb); + + if (skb->ip_summed == CHECKSUM_PARTIAL && + (skb->protocol == htons(ETH_P_8021Q) || + skb->protocol == htons(ETH_P_8021AD))) { + int depth; + + if (!__vlan_get_protocol(skb, skb->protocol, &depth)) + goto drop; + + skb_set_network_header(skb, depth); } + dev_queue_xmit(skb); + + return 0; + +drop: + kfree_skb(skb); return 0; } EXPORT_SYMBOL_GPL(br_dev_queue_push_xmit); From e13af53e7d5a8cea8992d9b61fac69bd0ed8d845 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michel=20D=C3=A4nzer?= Date: Wed, 22 Jul 2015 17:29:00 +0900 Subject: [PATCH 232/428] drm/radeon: Drop drm/ prefix for including drm.h in radeon_drm.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This allows radeon_drm.h to be reused verbatim in libdrm. Reviewed-by: Christian König Signed-off-by: Michel Dänzer --- include/uapi/drm/radeon_drm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h index 1ef76661e1a1..01aa2a8e3f8d 100644 --- a/include/uapi/drm/radeon_drm.h +++ b/include/uapi/drm/radeon_drm.h @@ -33,7 +33,7 @@ #ifndef __RADEON_DRM_H__ #define __RADEON_DRM_H__ -#include +#include "drm.h" /* WARNING: If you change any of these defines, make sure to change the * defines in the X server file (radeon_sarea.h) From b3fcf36aeef3aeb890d9413c2066048ec7fda7e5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michel=20D=C3=A4nzer?= Date: Wed, 22 Jul 2015 17:29:01 +0900 Subject: [PATCH 233/428] drm/amdgpu: Drop drm/ prefix for including drm.h in amdgpu_drm.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This allows amdgpu_drm.h to be reused verbatim in libdrm. Reviewed-by: Alex Deucher Reviewed-by: Christian König Signed-off-by: Michel Dänzer --- include/uapi/drm/amdgpu_drm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index d708a53b8fb1..fbdd11851725 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -32,7 +32,7 @@ #ifndef __AMDGPU_DRM_H__ #define __AMDGPU_DRM_H__ -#include +#include "drm.h" #define DRM_AMDGPU_GEM_CREATE 0x00 #define DRM_AMDGPU_GEM_MMAP 0x01 From d0ea397e22f9ad0113c1dbdaab14eded050472eb Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 23 Jul 2015 10:01:09 -0400 Subject: [PATCH 234/428] drm/radeon: rework audio detect (v4) 1. Always assign audio function pointers even if the display does not support audio. We need to properly disable the audio stream when when using a non-audio capable monitor. Fixes purple line on some hdmi monitors. 2. Check if a pin is in use by another encoder before disabling it. v2: make sure we've fetched the edid before checking audio and look up the encoder before calling audio_detect since connector->encoder may not be assigned yet. Separate pin and afmt. They are allocated at different times and have no dependency on eachother. v3: fix connector fetching in encoder functions v4: fix missed dig->pin check in dce6_afmt_write_latency_fields bugs: https://bugzilla.kernel.org/show_bug.cgi?id=93701 https://bugzilla.redhat.com/show_bug.cgi?id=1236337 https://bugs.freedesktop.org/show_bug.cgi?id=91041 Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/radeon/dce6_afmt.c | 62 ++++----- drivers/gpu/drm/radeon/radeon_audio.c | 145 +++++++++------------ drivers/gpu/drm/radeon/radeon_audio.h | 3 +- drivers/gpu/drm/radeon/radeon_connectors.c | 18 ++- drivers/gpu/drm/radeon/radeon_mode.h | 2 +- 5 files changed, 106 insertions(+), 124 deletions(-) diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c index 68fd9fc677e3..44480c1b9738 100644 --- a/drivers/gpu/drm/radeon/dce6_afmt.c +++ b/drivers/gpu/drm/radeon/dce6_afmt.c @@ -93,30 +93,26 @@ void dce6_afmt_select_pin(struct drm_encoder *encoder) struct radeon_device *rdev = encoder->dev->dev_private; struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; - u32 offset; - if (!dig || !dig->afmt || !dig->afmt->pin) + if (!dig || !dig->afmt || !dig->pin) return; - offset = dig->afmt->offset; - - WREG32(AFMT_AUDIO_SRC_CONTROL + offset, - AFMT_AUDIO_SRC_SELECT(dig->afmt->pin->id)); + WREG32(AFMT_AUDIO_SRC_CONTROL + dig->afmt->offset, + AFMT_AUDIO_SRC_SELECT(dig->pin->id)); } void dce6_afmt_write_latency_fields(struct drm_encoder *encoder, - struct drm_connector *connector, struct drm_display_mode *mode) + struct drm_connector *connector, + struct drm_display_mode *mode) { struct radeon_device *rdev = encoder->dev->dev_private; struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; - u32 tmp = 0, offset; + u32 tmp = 0; - if (!dig || !dig->afmt || !dig->afmt->pin) + if (!dig || !dig->afmt || !dig->pin) return; - offset = dig->afmt->pin->offset; - if (mode->flags & DRM_MODE_FLAG_INTERLACE) { if (connector->latency_present[1]) tmp = VIDEO_LIPSYNC(connector->video_latency[1]) | @@ -130,24 +126,24 @@ void dce6_afmt_write_latency_fields(struct drm_encoder *encoder, else tmp = VIDEO_LIPSYNC(0) | AUDIO_LIPSYNC(0); } - WREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_RESPONSE_LIPSYNC, tmp); + WREG32_ENDPOINT(dig->pin->offset, + AZ_F0_CODEC_PIN_CONTROL_RESPONSE_LIPSYNC, tmp); } void dce6_afmt_hdmi_write_speaker_allocation(struct drm_encoder *encoder, - u8 *sadb, int sad_count) + u8 *sadb, int sad_count) { struct radeon_device *rdev = encoder->dev->dev_private; struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; - u32 offset, tmp; + u32 tmp; - if (!dig || !dig->afmt || !dig->afmt->pin) + if (!dig || !dig->afmt || !dig->pin) return; - offset = dig->afmt->pin->offset; - /* program the speaker allocation */ - tmp = RREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER); + tmp = RREG32_ENDPOINT(dig->pin->offset, + AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER); tmp &= ~(DP_CONNECTION | SPEAKER_ALLOCATION_MASK); /* set HDMI mode */ tmp |= HDMI_CONNECTION; @@ -155,24 +151,24 @@ void dce6_afmt_hdmi_write_speaker_allocation(struct drm_encoder *encoder, tmp |= SPEAKER_ALLOCATION(sadb[0]); else tmp |= SPEAKER_ALLOCATION(5); /* stereo */ - WREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER, tmp); + WREG32_ENDPOINT(dig->pin->offset, + AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER, tmp); } void dce6_afmt_dp_write_speaker_allocation(struct drm_encoder *encoder, - u8 *sadb, int sad_count) + u8 *sadb, int sad_count) { struct radeon_device *rdev = encoder->dev->dev_private; struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; - u32 offset, tmp; + u32 tmp; - if (!dig || !dig->afmt || !dig->afmt->pin) + if (!dig || !dig->afmt || !dig->pin) return; - offset = dig->afmt->pin->offset; - /* program the speaker allocation */ - tmp = RREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER); + tmp = RREG32_ENDPOINT(dig->pin->offset, + AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER); tmp &= ~(HDMI_CONNECTION | SPEAKER_ALLOCATION_MASK); /* set DP mode */ tmp |= DP_CONNECTION; @@ -180,13 +176,13 @@ void dce6_afmt_dp_write_speaker_allocation(struct drm_encoder *encoder, tmp |= SPEAKER_ALLOCATION(sadb[0]); else tmp |= SPEAKER_ALLOCATION(5); /* stereo */ - WREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER, tmp); + WREG32_ENDPOINT(dig->pin->offset, + AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER, tmp); } void dce6_afmt_write_sad_regs(struct drm_encoder *encoder, - struct cea_sad *sads, int sad_count) + struct cea_sad *sads, int sad_count) { - u32 offset; int i; struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; @@ -206,11 +202,9 @@ void dce6_afmt_write_sad_regs(struct drm_encoder *encoder, { AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR13, HDMI_AUDIO_CODING_TYPE_WMA_PRO }, }; - if (!dig || !dig->afmt || !dig->afmt->pin) + if (!dig || !dig->afmt || !dig->pin) return; - offset = dig->afmt->pin->offset; - for (i = 0; i < ARRAY_SIZE(eld_reg_to_type); i++) { u32 value = 0; u8 stereo_freqs = 0; @@ -237,7 +231,7 @@ void dce6_afmt_write_sad_regs(struct drm_encoder *encoder, value |= SUPPORTED_FREQUENCIES_STEREO(stereo_freqs); - WREG32_ENDPOINT(offset, eld_reg_to_type[i][0], value); + WREG32_ENDPOINT(dig->pin->offset, eld_reg_to_type[i][0], value); } } @@ -253,7 +247,7 @@ void dce6_audio_enable(struct radeon_device *rdev, } void dce6_hdmi_audio_set_dto(struct radeon_device *rdev, - struct radeon_crtc *crtc, unsigned int clock) + struct radeon_crtc *crtc, unsigned int clock) { /* Two dtos; generally use dto0 for HDMI */ u32 value = 0; @@ -272,7 +266,7 @@ void dce6_hdmi_audio_set_dto(struct radeon_device *rdev, } void dce6_dp_audio_set_dto(struct radeon_device *rdev, - struct radeon_crtc *crtc, unsigned int clock) + struct radeon_crtc *crtc, unsigned int clock) { /* Two dtos; generally use dto1 for DP */ u32 value = 0; diff --git a/drivers/gpu/drm/radeon/radeon_audio.c b/drivers/gpu/drm/radeon/radeon_audio.c index fa719c53449b..59b3d3221294 100644 --- a/drivers/gpu/drm/radeon/radeon_audio.c +++ b/drivers/gpu/drm/radeon/radeon_audio.c @@ -245,6 +245,28 @@ static struct radeon_audio_funcs dce6_dp_funcs = { static void radeon_audio_enable(struct radeon_device *rdev, struct r600_audio_pin *pin, u8 enable_mask) { + struct drm_encoder *encoder; + struct radeon_encoder *radeon_encoder; + struct radeon_encoder_atom_dig *dig; + int pin_count = 0; + + if (!pin) + return; + + if (rdev->mode_info.mode_config_initialized) { + list_for_each_entry(encoder, &rdev->ddev->mode_config.encoder_list, head) { + if (radeon_encoder_is_digital(encoder)) { + radeon_encoder = to_radeon_encoder(encoder); + dig = radeon_encoder->enc_priv; + if (dig->pin == pin) + pin_count++; + } + } + + if ((pin_count > 1) && (enable_mask == 0)) + return; + } + if (rdev->audio.funcs->enable) rdev->audio.funcs->enable(rdev, pin, enable_mask); } @@ -336,24 +358,13 @@ void radeon_audio_endpoint_wreg(struct radeon_device *rdev, u32 offset, static void radeon_audio_write_sad_regs(struct drm_encoder *encoder) { - struct radeon_encoder *radeon_encoder; - struct drm_connector *connector; - struct radeon_connector *radeon_connector = NULL; + struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); + struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); struct cea_sad *sads; int sad_count; - list_for_each_entry(connector, - &encoder->dev->mode_config.connector_list, head) { - if (connector->encoder == encoder) { - radeon_connector = to_radeon_connector(connector); - break; - } - } - - if (!radeon_connector) { - DRM_ERROR("Couldn't find encoder's connector\n"); + if (!connector) return; - } sad_count = drm_edid_to_sad(radeon_connector_edid(connector), &sads); if (sad_count <= 0) { @@ -362,8 +373,6 @@ static void radeon_audio_write_sad_regs(struct drm_encoder *encoder) } BUG_ON(!sads); - radeon_encoder = to_radeon_encoder(encoder); - if (radeon_encoder->audio && radeon_encoder->audio->write_sad_regs) radeon_encoder->audio->write_sad_regs(encoder, sads, sad_count); @@ -372,27 +381,16 @@ static void radeon_audio_write_sad_regs(struct drm_encoder *encoder) static void radeon_audio_write_speaker_allocation(struct drm_encoder *encoder) { + struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); - struct drm_connector *connector; - struct radeon_connector *radeon_connector = NULL; u8 *sadb = NULL; int sad_count; - list_for_each_entry(connector, - &encoder->dev->mode_config.connector_list, head) { - if (connector->encoder == encoder) { - radeon_connector = to_radeon_connector(connector); - break; - } - } - - if (!radeon_connector) { - DRM_ERROR("Couldn't find encoder's connector\n"); + if (!connector) return; - } - sad_count = drm_edid_to_speaker_allocation( - radeon_connector_edid(connector), &sadb); + sad_count = drm_edid_to_speaker_allocation(radeon_connector_edid(connector), + &sadb); if (sad_count < 0) { DRM_DEBUG("Couldn't read Speaker Allocation Data Block: %d\n", sad_count); @@ -406,26 +404,13 @@ static void radeon_audio_write_speaker_allocation(struct drm_encoder *encoder) } static void radeon_audio_write_latency_fields(struct drm_encoder *encoder, - struct drm_display_mode *mode) + struct drm_display_mode *mode) { - struct radeon_encoder *radeon_encoder; - struct drm_connector *connector; - struct radeon_connector *radeon_connector = 0; + struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); + struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); - list_for_each_entry(connector, - &encoder->dev->mode_config.connector_list, head) { - if (connector->encoder == encoder) { - radeon_connector = to_radeon_connector(connector); - break; - } - } - - if (!radeon_connector) { - DRM_ERROR("Couldn't find encoder's connector\n"); + if (!connector) return; - } - - radeon_encoder = to_radeon_encoder(encoder); if (radeon_encoder->audio && radeon_encoder->audio->write_latency_fields) radeon_encoder->audio->write_latency_fields(encoder, connector, mode); @@ -451,29 +436,23 @@ static void radeon_audio_select_pin(struct drm_encoder *encoder) } void radeon_audio_detect(struct drm_connector *connector, + struct drm_encoder *encoder, enum drm_connector_status status) { - struct radeon_device *rdev; - struct radeon_encoder *radeon_encoder; + struct drm_device *dev = connector->dev; + struct radeon_device *rdev = dev->dev_private; + struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); struct radeon_encoder_atom_dig *dig; - if (!connector || !connector->encoder) - return; - - rdev = connector->encoder->dev->dev_private; - if (!radeon_audio_chipset_supported(rdev)) return; - radeon_encoder = to_radeon_encoder(connector->encoder); + if (!radeon_encoder_is_digital(encoder)) + return; + dig = radeon_encoder->enc_priv; if (status == connector_status_connected) { - if (!drm_detect_monitor_audio(radeon_connector_edid(connector))) { - radeon_encoder->audio = NULL; - return; - } - if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort) { struct radeon_connector *radeon_connector = to_radeon_connector(connector); @@ -486,11 +465,17 @@ void radeon_audio_detect(struct drm_connector *connector, radeon_encoder->audio = rdev->audio.hdmi_funcs; } - dig->afmt->pin = radeon_audio_get_pin(connector->encoder); - radeon_audio_enable(rdev, dig->afmt->pin, 0xf); + if (drm_detect_monitor_audio(radeon_connector_edid(connector))) { + if (!dig->pin) + dig->pin = radeon_audio_get_pin(encoder); + radeon_audio_enable(rdev, dig->pin, 0xf); + } else { + radeon_audio_enable(rdev, dig->pin, 0); + dig->pin = NULL; + } } else { - radeon_audio_enable(rdev, dig->afmt->pin, 0); - dig->afmt->pin = NULL; + radeon_audio_enable(rdev, dig->pin, 0); + dig->pin = NULL; } } @@ -518,29 +503,18 @@ static void radeon_audio_set_dto(struct drm_encoder *encoder, unsigned int clock } static int radeon_audio_set_avi_packet(struct drm_encoder *encoder, - struct drm_display_mode *mode) + struct drm_display_mode *mode) { struct radeon_device *rdev = encoder->dev->dev_private; struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; - struct drm_connector *connector; - struct radeon_connector *radeon_connector = NULL; + struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); u8 buffer[HDMI_INFOFRAME_HEADER_SIZE + HDMI_AVI_INFOFRAME_SIZE]; struct hdmi_avi_infoframe frame; int err; - list_for_each_entry(connector, - &encoder->dev->mode_config.connector_list, head) { - if (connector->encoder == encoder) { - radeon_connector = to_radeon_connector(connector); - break; - } - } - - if (!radeon_connector) { - DRM_ERROR("Couldn't find encoder's connector\n"); - return -ENOENT; - } + if (!connector) + return -EINVAL; err = drm_hdmi_avi_infoframe_from_display_mode(&frame, mode); if (err < 0) { @@ -563,8 +537,8 @@ static int radeon_audio_set_avi_packet(struct drm_encoder *encoder, return err; } - if (dig && dig->afmt && - radeon_encoder->audio && radeon_encoder->audio->set_avi_packet) + if (dig && dig->afmt && radeon_encoder->audio && + radeon_encoder->audio->set_avi_packet) radeon_encoder->audio->set_avi_packet(rdev, dig->afmt->offset, buffer, sizeof(buffer)); @@ -745,7 +719,7 @@ static void radeon_audio_hdmi_mode_set(struct drm_encoder *encoder, } static void radeon_audio_dp_mode_set(struct drm_encoder *encoder, - struct drm_display_mode *mode) + struct drm_display_mode *mode) { struct drm_device *dev = encoder->dev; struct radeon_device *rdev = dev->dev_private; @@ -756,6 +730,9 @@ static void radeon_audio_dp_mode_set(struct drm_encoder *encoder, struct radeon_connector_atom_dig *dig_connector = radeon_connector->con_priv; + if (!connector) + return; + if (!dig || !dig->afmt) return; @@ -774,7 +751,7 @@ static void radeon_audio_dp_mode_set(struct drm_encoder *encoder, } void radeon_audio_mode_set(struct drm_encoder *encoder, - struct drm_display_mode *mode) + struct drm_display_mode *mode) { struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); diff --git a/drivers/gpu/drm/radeon/radeon_audio.h b/drivers/gpu/drm/radeon/radeon_audio.h index 8438304f7139..059cc3012062 100644 --- a/drivers/gpu/drm/radeon/radeon_audio.h +++ b/drivers/gpu/drm/radeon/radeon_audio.h @@ -68,7 +68,8 @@ struct radeon_audio_funcs int radeon_audio_init(struct radeon_device *rdev); void radeon_audio_detect(struct drm_connector *connector, - enum drm_connector_status status); + struct drm_encoder *encoder, + enum drm_connector_status status); u32 radeon_audio_endpoint_rreg(struct radeon_device *rdev, u32 offset, u32 reg); void radeon_audio_endpoint_wreg(struct radeon_device *rdev, diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c index cebb65e07e1d..94b21ae70ef7 100644 --- a/drivers/gpu/drm/radeon/radeon_connectors.c +++ b/drivers/gpu/drm/radeon/radeon_connectors.c @@ -1379,8 +1379,16 @@ out: /* updated in get modes as well since we need to know if it's analog or digital */ radeon_connector_update_scratch_regs(connector, ret); - if (radeon_audio != 0) - radeon_audio_detect(connector, ret); + if ((radeon_audio != 0) && radeon_connector->use_digital) { + const struct drm_connector_helper_funcs *connector_funcs = + connector->helper_private; + + encoder = connector_funcs->best_encoder(connector); + if (encoder && (encoder->encoder_type == DRM_MODE_ENCODER_TMDS)) { + radeon_connector_get_edid(connector); + radeon_audio_detect(connector, encoder, ret); + } + } exit: pm_runtime_mark_last_busy(connector->dev->dev); @@ -1717,8 +1725,10 @@ radeon_dp_detect(struct drm_connector *connector, bool force) radeon_connector_update_scratch_regs(connector, ret); - if (radeon_audio != 0) - radeon_audio_detect(connector, ret); + if ((radeon_audio != 0) && encoder) { + radeon_connector_get_edid(connector); + radeon_audio_detect(connector, encoder, ret); + } out: pm_runtime_mark_last_busy(connector->dev->dev); diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h index 07909d817381..aecc3e3dec0c 100644 --- a/drivers/gpu/drm/radeon/radeon_mode.h +++ b/drivers/gpu/drm/radeon/radeon_mode.h @@ -237,7 +237,6 @@ struct radeon_afmt { int offset; bool last_buffer_filled_status; int id; - struct r600_audio_pin *pin; }; struct radeon_mode_info { @@ -439,6 +438,7 @@ struct radeon_encoder_atom_dig { uint8_t backlight_level; int panel_mode; struct radeon_afmt *afmt; + struct r600_audio_pin *pin; int active_mst_links; }; From 7726e72b3d6879ee5fc743a230eb6f5afa12844b Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 24 Jul 2015 00:42:02 -0400 Subject: [PATCH 235/428] drm/radeon: rework audio modeset to handle non-audio hdmi features Need to setup the deep color and avi packets regardless of audio setup. Signed-off-by: Alex Deucher --- drivers/gpu/drm/radeon/atombios_encoders.c | 3 +- drivers/gpu/drm/radeon/radeon_audio.c | 69 +++++++++++++--------- 2 files changed, 42 insertions(+), 30 deletions(-) diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c index dd39f434b4a7..c3872598b85a 100644 --- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -2299,8 +2299,7 @@ radeon_atom_encoder_mode_set(struct drm_encoder *encoder, encoder_mode = atombios_get_encoder_mode(encoder); if (connector && (radeon_audio != 0) && ((encoder_mode == ATOM_ENCODER_MODE_HDMI) || - (ENCODER_MODE_IS_DP(encoder_mode) && - drm_detect_monitor_audio(radeon_connector_edid(connector))))) + ENCODER_MODE_IS_DP(encoder_mode))) radeon_audio_mode_set(encoder, adjusted_mode); } diff --git a/drivers/gpu/drm/radeon/radeon_audio.c b/drivers/gpu/drm/radeon/radeon_audio.c index 59b3d3221294..fbc8d88d6e5d 100644 --- a/drivers/gpu/drm/radeon/radeon_audio.c +++ b/drivers/gpu/drm/radeon/radeon_audio.c @@ -696,26 +696,37 @@ static void radeon_audio_hdmi_mode_set(struct drm_encoder *encoder, { struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; + struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); if (!dig || !dig->afmt) return; - radeon_audio_set_mute(encoder, true); - - radeon_audio_write_speaker_allocation(encoder); - radeon_audio_write_sad_regs(encoder); - radeon_audio_write_latency_fields(encoder, mode); - radeon_audio_set_dto(encoder, mode->clock); - radeon_audio_set_vbi_packet(encoder); - radeon_hdmi_set_color_depth(encoder); - radeon_audio_update_acr(encoder, mode->clock); - radeon_audio_set_audio_packet(encoder); - radeon_audio_select_pin(encoder); - - if (radeon_audio_set_avi_packet(encoder, mode) < 0) + if (!connector) return; - radeon_audio_set_mute(encoder, false); + if (drm_detect_monitor_audio(radeon_connector_edid(connector))) { + radeon_audio_set_mute(encoder, true); + + radeon_audio_write_speaker_allocation(encoder); + radeon_audio_write_sad_regs(encoder); + radeon_audio_write_latency_fields(encoder, mode); + radeon_audio_set_dto(encoder, mode->clock); + radeon_audio_set_vbi_packet(encoder); + radeon_hdmi_set_color_depth(encoder); + radeon_audio_update_acr(encoder, mode->clock); + radeon_audio_set_audio_packet(encoder); + radeon_audio_select_pin(encoder); + + if (radeon_audio_set_avi_packet(encoder, mode) < 0) + return; + + radeon_audio_set_mute(encoder, false); + } else { + radeon_hdmi_set_color_depth(encoder); + + if (radeon_audio_set_avi_packet(encoder, mode) < 0) + return; + } } static void radeon_audio_dp_mode_set(struct drm_encoder *encoder, @@ -730,24 +741,26 @@ static void radeon_audio_dp_mode_set(struct drm_encoder *encoder, struct radeon_connector_atom_dig *dig_connector = radeon_connector->con_priv; - if (!connector) - return; - if (!dig || !dig->afmt) return; - radeon_audio_write_speaker_allocation(encoder); - radeon_audio_write_sad_regs(encoder); - radeon_audio_write_latency_fields(encoder, mode); - if (rdev->clock.dp_extclk || ASIC_IS_DCE5(rdev)) - radeon_audio_set_dto(encoder, rdev->clock.default_dispclk * 10); - else - radeon_audio_set_dto(encoder, dig_connector->dp_clock); - radeon_audio_set_audio_packet(encoder); - radeon_audio_select_pin(encoder); - - if (radeon_audio_set_avi_packet(encoder, mode) < 0) + if (!connector) return; + + if (drm_detect_monitor_audio(radeon_connector_edid(connector))) { + radeon_audio_write_speaker_allocation(encoder); + radeon_audio_write_sad_regs(encoder); + radeon_audio_write_latency_fields(encoder, mode); + if (rdev->clock.dp_extclk || ASIC_IS_DCE5(rdev)) + radeon_audio_set_dto(encoder, rdev->clock.default_dispclk * 10); + else + radeon_audio_set_dto(encoder, dig_connector->dp_clock); + radeon_audio_set_audio_packet(encoder); + radeon_audio_select_pin(encoder); + + if (radeon_audio_set_avi_packet(encoder, mode) < 0) + return; + } } void radeon_audio_mode_set(struct drm_encoder *encoder, From 0a90a0cff9f429f886f423967ae053150dce9259 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 27 Jul 2015 19:24:31 -0400 Subject: [PATCH 236/428] drm/radeon/combios: add some validation of lvds values Fixes a broken hsync start value uncovered by: abc0b1447d4974963548777a5ba4a4457c82c426 (drm: Perform basic sanity checks on probed modes) The driver handled the bad hsync start elsewhere, but the above commit prevented it from getting added. bug: https://bugs.freedesktop.org/show_bug.cgi?id=91401 Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/radeon/radeon_combios.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c index 3e5f6b71f3ad..c097d3a82bda 100644 --- a/drivers/gpu/drm/radeon/radeon_combios.c +++ b/drivers/gpu/drm/radeon/radeon_combios.c @@ -1255,10 +1255,15 @@ struct radeon_encoder_lvds *radeon_combios_get_lvds_info(struct radeon_encoder if ((RBIOS16(tmp) == lvds->native_mode.hdisplay) && (RBIOS16(tmp + 2) == lvds->native_mode.vdisplay)) { + u32 hss = (RBIOS16(tmp + 21) - RBIOS16(tmp + 19) - 1) * 8; + + if (hss > lvds->native_mode.hdisplay) + hss = (10 - 1) * 8; + lvds->native_mode.htotal = lvds->native_mode.hdisplay + (RBIOS16(tmp + 17) - RBIOS16(tmp + 19)) * 8; lvds->native_mode.hsync_start = lvds->native_mode.hdisplay + - (RBIOS16(tmp + 21) - RBIOS16(tmp + 19) - 1) * 8; + hss; lvds->native_mode.hsync_end = lvds->native_mode.hsync_start + (RBIOS8(tmp + 23) * 8); From 8faf0e08d5a78ae5f1752b1d69f97ed70afa625f Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 28 Jul 2015 11:50:31 -0400 Subject: [PATCH 237/428] drm/amdgpu: clean up init sequence for failures MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If we fail during device init, record what state each block is in so that we can tear down clearly. Fixes various problems on device init failure. Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 8 ++++- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 38 +++++++++++++--------- drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 4 +-- 3 files changed, 31 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index e9fde72cf038..31b00f91cfcd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1866,6 +1866,12 @@ typedef void (*amdgpu_wreg_t)(struct amdgpu_device*, uint32_t, uint32_t); typedef uint32_t (*amdgpu_block_rreg_t)(struct amdgpu_device*, uint32_t, uint32_t); typedef void (*amdgpu_block_wreg_t)(struct amdgpu_device*, uint32_t, uint32_t, uint32_t); +struct amdgpu_ip_block_status { + bool valid; + bool sw; + bool hw; +}; + struct amdgpu_device { struct device *dev; struct drm_device *ddev; @@ -2008,7 +2014,7 @@ struct amdgpu_device { const struct amdgpu_ip_block_version *ip_blocks; int num_ip_blocks; - bool *ip_block_enabled; + struct amdgpu_ip_block_status *ip_block_status; struct mutex mn_lock; DECLARE_HASHTABLE(mn_hash, 7); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index d79009b65867..99f158e1baff 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1191,8 +1191,9 @@ static int amdgpu_early_init(struct amdgpu_device *adev) return -EINVAL; } - adev->ip_block_enabled = kcalloc(adev->num_ip_blocks, sizeof(bool), GFP_KERNEL); - if (adev->ip_block_enabled == NULL) + adev->ip_block_status = kcalloc(adev->num_ip_blocks, + sizeof(struct amdgpu_ip_block_status), GFP_KERNEL); + if (adev->ip_block_status == NULL) return -ENOMEM; if (adev->ip_blocks == NULL) { @@ -1203,18 +1204,18 @@ static int amdgpu_early_init(struct amdgpu_device *adev) for (i = 0; i < adev->num_ip_blocks; i++) { if ((amdgpu_ip_block_mask & (1 << i)) == 0) { DRM_ERROR("disabled ip block: %d\n", i); - adev->ip_block_enabled[i] = false; + adev->ip_block_status[i].valid = false; } else { if (adev->ip_blocks[i].funcs->early_init) { r = adev->ip_blocks[i].funcs->early_init((void *)adev); if (r == -ENOENT) - adev->ip_block_enabled[i] = false; + adev->ip_block_status[i].valid = false; else if (r) return r; else - adev->ip_block_enabled[i] = true; + adev->ip_block_status[i].valid = true; } else { - adev->ip_block_enabled[i] = true; + adev->ip_block_status[i].valid = true; } } } @@ -1227,11 +1228,12 @@ static int amdgpu_init(struct amdgpu_device *adev) int i, r; for (i = 0; i < adev->num_ip_blocks; i++) { - if (!adev->ip_block_enabled[i]) + if (!adev->ip_block_status[i].valid) continue; r = adev->ip_blocks[i].funcs->sw_init((void *)adev); if (r) return r; + adev->ip_block_status[i].sw = true; /* need to do gmc hw init early so we can allocate gpu mem */ if (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_GMC) { r = amdgpu_vram_scratch_init(adev); @@ -1243,11 +1245,12 @@ static int amdgpu_init(struct amdgpu_device *adev) r = amdgpu_wb_init(adev); if (r) return r; + adev->ip_block_status[i].hw = true; } } for (i = 0; i < adev->num_ip_blocks; i++) { - if (!adev->ip_block_enabled[i]) + if (!adev->ip_block_status[i].sw) continue; /* gmc hw init is done early */ if (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_GMC) @@ -1255,6 +1258,7 @@ static int amdgpu_init(struct amdgpu_device *adev) r = adev->ip_blocks[i].funcs->hw_init((void *)adev); if (r) return r; + adev->ip_block_status[i].hw = true; } return 0; @@ -1265,7 +1269,7 @@ static int amdgpu_late_init(struct amdgpu_device *adev) int i = 0, r; for (i = 0; i < adev->num_ip_blocks; i++) { - if (!adev->ip_block_enabled[i]) + if (!adev->ip_block_status[i].valid) continue; /* enable clockgating to save power */ r = adev->ip_blocks[i].funcs->set_clockgating_state((void *)adev, @@ -1287,7 +1291,7 @@ static int amdgpu_fini(struct amdgpu_device *adev) int i, r; for (i = adev->num_ip_blocks - 1; i >= 0; i--) { - if (!adev->ip_block_enabled[i]) + if (!adev->ip_block_status[i].hw) continue; if (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_GMC) { amdgpu_wb_fini(adev); @@ -1300,14 +1304,16 @@ static int amdgpu_fini(struct amdgpu_device *adev) return r; r = adev->ip_blocks[i].funcs->hw_fini((void *)adev); /* XXX handle errors */ + adev->ip_block_status[i].hw = false; } for (i = adev->num_ip_blocks - 1; i >= 0; i--) { - if (!adev->ip_block_enabled[i]) + if (!adev->ip_block_status[i].sw) continue; r = adev->ip_blocks[i].funcs->sw_fini((void *)adev); /* XXX handle errors */ - adev->ip_block_enabled[i] = false; + adev->ip_block_status[i].sw = false; + adev->ip_block_status[i].valid = false; } return 0; @@ -1318,7 +1324,7 @@ static int amdgpu_suspend(struct amdgpu_device *adev) int i, r; for (i = adev->num_ip_blocks - 1; i >= 0; i--) { - if (!adev->ip_block_enabled[i]) + if (!adev->ip_block_status[i].valid) continue; /* ungate blocks so that suspend can properly shut them down */ r = adev->ip_blocks[i].funcs->set_clockgating_state((void *)adev, @@ -1336,7 +1342,7 @@ static int amdgpu_resume(struct amdgpu_device *adev) int i, r; for (i = 0; i < adev->num_ip_blocks; i++) { - if (!adev->ip_block_enabled[i]) + if (!adev->ip_block_status[i].valid) continue; r = adev->ip_blocks[i].funcs->resume(adev); if (r) @@ -1582,8 +1588,8 @@ void amdgpu_device_fini(struct amdgpu_device *adev) amdgpu_fence_driver_fini(adev); amdgpu_fbdev_fini(adev); r = amdgpu_fini(adev); - kfree(adev->ip_block_enabled); - adev->ip_block_enabled = NULL; + kfree(adev->ip_block_status); + adev->ip_block_status = NULL; adev->accel_working = false; /* free i2c buses */ amdgpu_i2c_fini(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 31ad444c6386..d316bda3d7ae 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -235,7 +235,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file for (i = 0; i < adev->num_ip_blocks; i++) { if (adev->ip_blocks[i].type == type && - adev->ip_block_enabled[i]) { + adev->ip_block_status[i].valid) { ip.hw_ip_version_major = adev->ip_blocks[i].major; ip.hw_ip_version_minor = adev->ip_blocks[i].minor; ip.capabilities_flags = 0; @@ -274,7 +274,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file for (i = 0; i < adev->num_ip_blocks; i++) if (adev->ip_blocks[i].type == type && - adev->ip_block_enabled[i] && + adev->ip_block_status[i].valid && count < AMDGPU_HW_IP_INSTANCE_MAX_COUNT) count++; From c193fa91b9182465a4a01665ad4096a6cdb4db2d Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 28 Jul 2015 18:51:29 +0300 Subject: [PATCH 238/428] drm/amdgpu: information leak in amdgpu_info_ioctl() We recently changed the drm_amdgpu_info_device struct so now there is a 4 byte hole at the end. We need to initialize it so we don't disclose secret information from the stack. Fixes: fa92754e9c47 ('drm/amdgpu: add VCE harvesting instance query') Signed-off-by: Dan Carpenter Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index d316bda3d7ae..9736892bcdf9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -416,7 +416,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file return n ? -EFAULT : 0; } case AMDGPU_INFO_DEV_INFO: { - struct drm_amdgpu_info_device dev_info; + struct drm_amdgpu_info_device dev_info = {}; struct amdgpu_cu_info cu_info; dev_info.device_id = dev->pdev->device; From 93323131d66db68802e646204c0562cddc81a651 Mon Sep 17 00:00:00 2001 From: "monk.liu" Date: Wed, 15 Jul 2015 17:21:45 +0800 Subject: [PATCH 239/428] drm/amdgpu: different emit_ib for gfx and compute MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit compute ring didn't use const engine byfar, so ignore CE things in compute routine Signed-off-by: monk.liu Reviewed-by: Christian König --- drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 46 +++++++++++++++++++------- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 47 ++++++++++++++++++++------- 2 files changed, 71 insertions(+), 22 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index 2c188fb9fd22..2db6ab0a543d 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -2561,7 +2561,7 @@ static bool gfx_v7_0_ring_emit_semaphore(struct amdgpu_ring *ring, * sheduling on the ring. This function schedules the IB * on the gfx ring for execution by the GPU. */ -static void gfx_v7_0_ring_emit_ib(struct amdgpu_ring *ring, +static void gfx_v7_0_ring_emit_ib_gfx(struct amdgpu_ring *ring, struct amdgpu_ib *ib) { bool need_ctx_switch = ring->current_ctx != ib->ctx; @@ -2569,15 +2569,10 @@ static void gfx_v7_0_ring_emit_ib(struct amdgpu_ring *ring, u32 next_rptr = ring->wptr + 5; /* drop the CE preamble IB for the same context */ - if ((ring->type == AMDGPU_RING_TYPE_GFX) && - (ib->flags & AMDGPU_IB_FLAG_PREAMBLE) && - !need_ctx_switch) + if ((ib->flags & AMDGPU_IB_FLAG_PREAMBLE) && !need_ctx_switch) return; - if (ring->type == AMDGPU_RING_TYPE_COMPUTE) - control |= INDIRECT_BUFFER_VALID; - - if (need_ctx_switch && ring->type == AMDGPU_RING_TYPE_GFX) + if (need_ctx_switch) next_rptr += 2; next_rptr += 4; @@ -2588,7 +2583,7 @@ static void gfx_v7_0_ring_emit_ib(struct amdgpu_ring *ring, amdgpu_ring_write(ring, next_rptr); /* insert SWITCH_BUFFER packet before first IB in the ring frame */ - if (need_ctx_switch && ring->type == AMDGPU_RING_TYPE_GFX) { + if (need_ctx_switch) { amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0)); amdgpu_ring_write(ring, 0); } @@ -2611,6 +2606,35 @@ static void gfx_v7_0_ring_emit_ib(struct amdgpu_ring *ring, amdgpu_ring_write(ring, control); } +static void gfx_v7_0_ring_emit_ib_compute(struct amdgpu_ring *ring, + struct amdgpu_ib *ib) +{ + u32 header, control = 0; + u32 next_rptr = ring->wptr + 5; + + control |= INDIRECT_BUFFER_VALID; + next_rptr += 4; + amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3)); + amdgpu_ring_write(ring, WRITE_DATA_DST_SEL(5) | WR_CONFIRM); + amdgpu_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc); + amdgpu_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff); + amdgpu_ring_write(ring, next_rptr); + + header = PACKET3(PACKET3_INDIRECT_BUFFER, 2); + + control |= ib->length_dw | + (ib->vm ? (ib->vm->ids[ring->idx].id << 24) : 0); + + amdgpu_ring_write(ring, header); + amdgpu_ring_write(ring, +#ifdef __BIG_ENDIAN + (2 << 0) | +#endif + (ib->gpu_addr & 0xFFFFFFFC)); + amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr) & 0xFFFF); + amdgpu_ring_write(ring, control); +} + /** * gfx_v7_0_ring_test_ib - basic ring IB test * @@ -5555,7 +5579,7 @@ static const struct amdgpu_ring_funcs gfx_v7_0_ring_funcs_gfx = { .get_wptr = gfx_v7_0_ring_get_wptr_gfx, .set_wptr = gfx_v7_0_ring_set_wptr_gfx, .parse_cs = NULL, - .emit_ib = gfx_v7_0_ring_emit_ib, + .emit_ib = gfx_v7_0_ring_emit_ib_gfx, .emit_fence = gfx_v7_0_ring_emit_fence_gfx, .emit_semaphore = gfx_v7_0_ring_emit_semaphore, .emit_vm_flush = gfx_v7_0_ring_emit_vm_flush, @@ -5571,7 +5595,7 @@ static const struct amdgpu_ring_funcs gfx_v7_0_ring_funcs_compute = { .get_wptr = gfx_v7_0_ring_get_wptr_compute, .set_wptr = gfx_v7_0_ring_set_wptr_compute, .parse_cs = NULL, - .emit_ib = gfx_v7_0_ring_emit_ib, + .emit_ib = gfx_v7_0_ring_emit_ib_compute, .emit_fence = gfx_v7_0_ring_emit_fence_compute, .emit_semaphore = gfx_v7_0_ring_emit_semaphore, .emit_vm_flush = gfx_v7_0_ring_emit_vm_flush, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 1c7c992dea37..9e1d4ddbf475 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -3753,7 +3753,7 @@ static void gfx_v8_0_ring_emit_hdp_flush(struct amdgpu_ring *ring) amdgpu_ring_write(ring, 0x20); /* poll interval */ } -static void gfx_v8_0_ring_emit_ib(struct amdgpu_ring *ring, +static void gfx_v8_0_ring_emit_ib_gfx(struct amdgpu_ring *ring, struct amdgpu_ib *ib) { bool need_ctx_switch = ring->current_ctx != ib->ctx; @@ -3761,15 +3761,10 @@ static void gfx_v8_0_ring_emit_ib(struct amdgpu_ring *ring, u32 next_rptr = ring->wptr + 5; /* drop the CE preamble IB for the same context */ - if ((ring->type == AMDGPU_RING_TYPE_GFX) && - (ib->flags & AMDGPU_IB_FLAG_PREAMBLE) && - !need_ctx_switch) + if ((ib->flags & AMDGPU_IB_FLAG_PREAMBLE) && !need_ctx_switch) return; - if (ring->type == AMDGPU_RING_TYPE_COMPUTE) - control |= INDIRECT_BUFFER_VALID; - - if (need_ctx_switch && ring->type == AMDGPU_RING_TYPE_GFX) + if (need_ctx_switch) next_rptr += 2; next_rptr += 4; @@ -3780,7 +3775,7 @@ static void gfx_v8_0_ring_emit_ib(struct amdgpu_ring *ring, amdgpu_ring_write(ring, next_rptr); /* insert SWITCH_BUFFER packet before first IB in the ring frame */ - if (need_ctx_switch && ring->type == AMDGPU_RING_TYPE_GFX) { + if (need_ctx_switch) { amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0)); amdgpu_ring_write(ring, 0); } @@ -3803,6 +3798,36 @@ static void gfx_v8_0_ring_emit_ib(struct amdgpu_ring *ring, amdgpu_ring_write(ring, control); } +static void gfx_v8_0_ring_emit_ib_compute(struct amdgpu_ring *ring, + struct amdgpu_ib *ib) +{ + u32 header, control = 0; + u32 next_rptr = ring->wptr + 5; + + control |= INDIRECT_BUFFER_VALID; + + next_rptr += 4; + amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3)); + amdgpu_ring_write(ring, WRITE_DATA_DST_SEL(5) | WR_CONFIRM); + amdgpu_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc); + amdgpu_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff); + amdgpu_ring_write(ring, next_rptr); + + header = PACKET3(PACKET3_INDIRECT_BUFFER, 2); + + control |= ib->length_dw | + (ib->vm ? (ib->vm->ids[ring->idx].id << 24) : 0); + + amdgpu_ring_write(ring, header); + amdgpu_ring_write(ring, +#ifdef __BIG_ENDIAN + (2 << 0) | +#endif + (ib->gpu_addr & 0xFFFFFFFC)); + amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr) & 0xFFFF); + amdgpu_ring_write(ring, control); +} + static void gfx_v8_0_ring_emit_fence_gfx(struct amdgpu_ring *ring, u64 addr, u64 seq, unsigned flags) { @@ -4224,7 +4249,7 @@ static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_gfx = { .get_wptr = gfx_v8_0_ring_get_wptr_gfx, .set_wptr = gfx_v8_0_ring_set_wptr_gfx, .parse_cs = NULL, - .emit_ib = gfx_v8_0_ring_emit_ib, + .emit_ib = gfx_v8_0_ring_emit_ib_gfx, .emit_fence = gfx_v8_0_ring_emit_fence_gfx, .emit_semaphore = gfx_v8_0_ring_emit_semaphore, .emit_vm_flush = gfx_v8_0_ring_emit_vm_flush, @@ -4240,7 +4265,7 @@ static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_compute = { .get_wptr = gfx_v8_0_ring_get_wptr_compute, .set_wptr = gfx_v8_0_ring_set_wptr_compute, .parse_cs = NULL, - .emit_ib = gfx_v8_0_ring_emit_ib, + .emit_ib = gfx_v8_0_ring_emit_ib_compute, .emit_fence = gfx_v8_0_ring_emit_fence_compute, .emit_semaphore = gfx_v8_0_ring_emit_semaphore, .emit_vm_flush = gfx_v8_0_ring_emit_vm_flush, From e722b71a540362eebdbae060430dc5b06b990c38 Mon Sep 17 00:00:00 2001 From: "monk.liu" Date: Fri, 17 Jul 2015 17:10:09 +0800 Subject: [PATCH 240/428] drm/amdgpu: hdp_flush is not needed for inside IB MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit hdp flush is not needed for IBs that dispatched from kernel inside because there is no video memory host access Signed-off-by: monk.liu Reviewed-by: Christian König --- drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c index 52dff75aac6f..bc0fac618a3f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c @@ -180,17 +180,17 @@ int amdgpu_ib_schedule(struct amdgpu_device *adev, unsigned num_ibs, if (vm) { /* do context switch */ amdgpu_vm_flush(ring, vm, ib->sync.last_vm_update); + + if (ring->funcs->emit_gds_switch) + amdgpu_ring_emit_gds_switch(ring, ib->vm->ids[ring->idx].id, + ib->gds_base, ib->gds_size, + ib->gws_base, ib->gws_size, + ib->oa_base, ib->oa_size); + + if (ring->funcs->emit_hdp_flush) + amdgpu_ring_emit_hdp_flush(ring); } - if (vm && ring->funcs->emit_gds_switch) - amdgpu_ring_emit_gds_switch(ring, ib->vm->ids[ring->idx].id, - ib->gds_base, ib->gds_size, - ib->gws_base, ib->gws_size, - ib->oa_base, ib->oa_size); - - if (ring->funcs->emit_hdp_flush) - amdgpu_ring_emit_hdp_flush(ring); - old_ctx = ring->current_ctx; for (i = 0; i < num_ibs; ++i) { ib = &ibs[i]; From 194a33643b1161fe7a054fa9bf43875ae0f6e1e8 Mon Sep 17 00:00:00 2001 From: "monk.liu" Date: Wed, 22 Jul 2015 13:29:28 +0800 Subject: [PATCH 241/428] drm/amdgpu: add new parameter to seperate map and unmap MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: monk.liu Reviewed-by: Christian König --- drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index ae43b58c9733..4afc507820c0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -449,7 +449,7 @@ out: * vital here, so they are not reported back to userspace. */ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev, - struct amdgpu_bo_va *bo_va) + struct amdgpu_bo_va *bo_va, uint32_t operation) { struct ttm_validate_buffer tv, *entry; struct amdgpu_bo_list_entry *vm_bos; @@ -485,7 +485,9 @@ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev, if (r) goto error_unlock; - r = amdgpu_vm_bo_update(adev, bo_va, &bo_va->bo->tbo.mem); + + if (operation == AMDGPU_VA_OP_MAP) + r = amdgpu_vm_bo_update(adev, bo_va, &bo_va->bo->tbo.mem); error_unlock: mutex_unlock(&bo_va->vm->mutex); @@ -580,7 +582,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, } if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE)) - amdgpu_gem_va_update_vm(adev, bo_va); + amdgpu_gem_va_update_vm(adev, bo_va, args->operation); drm_gem_object_unreference_unlocked(gobj); return r; From ac45146733b03a1c8e3a6a33720bdc42804cc09b Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Thu, 23 Jul 2015 13:44:56 -0400 Subject: [PATCH 242/428] drm/msm: fix msm_gem_prime_get_sg_table() We need to return a new sgt, since the caller takes ownership of it. Reported-by: Stanimir Varbanov Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/msm_gem_prime.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c index dd7a7ab603e2..831461bc98a5 100644 --- a/drivers/gpu/drm/msm/msm_gem_prime.c +++ b/drivers/gpu/drm/msm/msm_gem_prime.c @@ -23,8 +23,12 @@ struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj) { struct msm_gem_object *msm_obj = to_msm_bo(obj); - BUG_ON(!msm_obj->sgt); /* should have already pinned! */ - return msm_obj->sgt; + int npages = obj->size >> PAGE_SHIFT; + + if (WARN_ON(!msm_obj->pages)) /* should have already pinned! */ + return NULL; + + return drm_prime_pages_to_sg(msm_obj->pages, npages); } void *msm_gem_prime_vmap(struct drm_gem_object *obj) From a1c3e3e01ee301de6a13e696ef8775f40ca339ac Mon Sep 17 00:00:00 2001 From: Archit Taneja Date: Fri, 26 Jun 2015 15:49:43 +0530 Subject: [PATCH 243/428] drm/msm: mdp4: Fix drm_framebuffer dereference crash mdp4_get_frame_format() can dereference a drm_framebuffer when it's NULL. Call it in mdp4_plane_mode_set only when we know fb is non-NULL. Signed-off-by: Archit Taneja Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c index 0d1dbb737933..247a424445f7 100644 --- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c +++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c @@ -220,13 +220,15 @@ static int mdp4_plane_mode_set(struct drm_plane *plane, uint32_t op_mode = 0; uint32_t phasex_step = MDP4_VG_PHASE_STEP_DEFAULT; uint32_t phasey_step = MDP4_VG_PHASE_STEP_DEFAULT; - enum mdp4_frame_format frame_type = mdp4_get_frame_format(fb); + enum mdp4_frame_format frame_type; if (!(crtc && fb)) { DBG("%s: disabled!", mdp4_plane->name); return 0; } + frame_type = mdp4_get_frame_format(fb); + /* src values are in Q16 fixed point, convert to integer: */ src_x = src_x >> 16; src_y = src_y >> 16; From 99fc1bc48f352185f1711795f0829bbf503c0712 Mon Sep 17 00:00:00 2001 From: Wentao Xu Date: Mon, 22 Jun 2015 11:53:42 -0400 Subject: [PATCH 244/428] drm/msm: change to uninterruptible wait in atomic commit The atomic commit cannot easily undo and return an error once the state is swapped. Change to uninterruptible wait, and ignore the timeout error. Signed-off-by: Wentao Xu Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/msm_atomic.c | 8 ++------ drivers/gpu/drm/msm/msm_drv.c | 13 +++++++++---- drivers/gpu/drm/msm/msm_drv.h | 4 ++-- drivers/gpu/drm/msm/msm_gem.c | 2 +- 4 files changed, 14 insertions(+), 13 deletions(-) diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c index 1b22d8bfe142..1ceb4f22dd89 100644 --- a/drivers/gpu/drm/msm/msm_atomic.c +++ b/drivers/gpu/drm/msm/msm_atomic.c @@ -283,12 +283,8 @@ int msm_atomic_commit(struct drm_device *dev, timeout = ktime_add_ms(ktime_get(), 1000); - ret = msm_wait_fence_interruptable(dev, c->fence, &timeout); - if (ret) { - WARN_ON(ret); // TODO unswap state back? or?? - commit_destroy(c); - return ret; - } + /* uninterruptible wait */ + msm_wait_fence(dev, c->fence, &timeout, false); complete_commit(c); diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index b7ef56ed8d1c..d3467b115e04 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -637,8 +637,8 @@ static void msm_debugfs_cleanup(struct drm_minor *minor) * Fences: */ -int msm_wait_fence_interruptable(struct drm_device *dev, uint32_t fence, - ktime_t *timeout) +int msm_wait_fence(struct drm_device *dev, uint32_t fence, + ktime_t *timeout , bool interruptible) { struct msm_drm_private *priv = dev->dev_private; int ret; @@ -667,7 +667,12 @@ int msm_wait_fence_interruptable(struct drm_device *dev, uint32_t fence, remaining_jiffies = timespec_to_jiffies(&ts); } - ret = wait_event_interruptible_timeout(priv->fence_event, + if (interruptible) + ret = wait_event_interruptible_timeout(priv->fence_event, + fence_completed(dev, fence), + remaining_jiffies); + else + ret = wait_event_timeout(priv->fence_event, fence_completed(dev, fence), remaining_jiffies); @@ -853,7 +858,7 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data, return -EINVAL; } - return msm_wait_fence_interruptable(dev, args->fence, &timeout); + return msm_wait_fence(dev, args->fence, &timeout, true); } static const struct drm_ioctl_desc msm_ioctls[] = { diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index e7c5ea125d45..4ff0ec9c994b 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -164,8 +164,8 @@ int msm_atomic_commit(struct drm_device *dev, int msm_register_mmu(struct drm_device *dev, struct msm_mmu *mmu); -int msm_wait_fence_interruptable(struct drm_device *dev, uint32_t fence, - ktime_t *timeout); +int msm_wait_fence(struct drm_device *dev, uint32_t fence, + ktime_t *timeout, bool interruptible); int msm_queue_fence_cb(struct drm_device *dev, struct msm_fence_cb *cb, uint32_t fence); void msm_update_fence(struct drm_device *dev, uint32_t fence); diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index f211b80e3a1e..c76cc853b08a 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -460,7 +460,7 @@ int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout) if (op & MSM_PREP_NOSYNC) timeout = NULL; - ret = msm_wait_fence_interruptable(dev, fence, timeout); + ret = msm_wait_fence(dev, fence, timeout, true); } /* TODO cache maintenance */ From b4cba04f05ed6b9b2278547295ecc5c40180e612 Mon Sep 17 00:00:00 2001 From: Wentao Xu Date: Fri, 19 Jun 2015 14:03:42 -0400 Subject: [PATCH 245/428] drm/msm/mdp5: release SMB (shared memory blocks) in various cases Release all blocks after the pipe is disabled, even when vsync didn't happen in some error cases. Allow requesting SMB multiple times before configuring to hardware, by releasing blocks not programmed to hardware yet for shrinking case. This fixes a potential leak of shared memory pool blocks. Signed-off-by: Wentao Xu Tested-by: Archit Taneja Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c | 13 ++++ drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h | 2 + drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c | 33 ++++----- drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.c | 87 +++++++++++++++++++---- drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.h | 1 + 5 files changed, 104 insertions(+), 32 deletions(-) diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c index 206f758f7d64..e253db5de5aa 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c @@ -76,7 +76,20 @@ static void mdp5_prepare_commit(struct msm_kms *kms, struct drm_atomic_state *st static void mdp5_complete_commit(struct msm_kms *kms, struct drm_atomic_state *state) { + int i; struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms)); + int nplanes = mdp5_kms->dev->mode_config.num_total_plane; + + for (i = 0; i < nplanes; i++) { + struct drm_plane *plane = state->planes[i]; + struct drm_plane_state *plane_state = state->plane_states[i]; + + if (!plane) + continue; + + mdp5_plane_complete_commit(plane, plane_state); + } + mdp5_disable(mdp5_kms); } diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h index e0eb24587c84..e79ac09b7216 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h @@ -227,6 +227,8 @@ void mdp5_plane_install_properties(struct drm_plane *plane, struct drm_mode_object *obj); uint32_t mdp5_plane_get_flush(struct drm_plane *plane); void mdp5_plane_complete_flip(struct drm_plane *plane); +void mdp5_plane_complete_commit(struct drm_plane *plane, + struct drm_plane_state *state); enum mdp5_pipe mdp5_plane_pipe(struct drm_plane *plane); struct drm_plane *mdp5_plane_init(struct drm_device *dev, enum mdp5_pipe pipe, bool private_plane, uint32_t reg_offset); diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c index 57b8f56ae9d0..22275568ab8b 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c @@ -31,8 +31,6 @@ struct mdp5_plane { uint32_t nformats; uint32_t formats[32]; - - bool enabled; }; #define to_mdp5_plane(x) container_of(x, struct mdp5_plane, base) @@ -56,22 +54,6 @@ static bool plane_enabled(struct drm_plane_state *state) return state->fb && state->crtc; } -static int mdp5_plane_disable(struct drm_plane *plane) -{ - struct mdp5_plane *mdp5_plane = to_mdp5_plane(plane); - struct mdp5_kms *mdp5_kms = get_kms(plane); - enum mdp5_pipe pipe = mdp5_plane->pipe; - - DBG("%s: disable", mdp5_plane->name); - - if (mdp5_kms) { - /* Release the memory we requested earlier from the SMP: */ - mdp5_smp_release(mdp5_kms->smp, pipe); - } - - return 0; -} - static void mdp5_plane_destroy(struct drm_plane *plane) { struct mdp5_plane *mdp5_plane = to_mdp5_plane(plane); @@ -224,7 +206,6 @@ static void mdp5_plane_atomic_update(struct drm_plane *plane, if (!plane_enabled(state)) { to_mdp5_plane_state(state)->pending = true; - mdp5_plane_disable(plane); } else if (to_mdp5_plane_state(state)->mode_changed) { int ret; to_mdp5_plane_state(state)->pending = true; @@ -602,6 +583,20 @@ uint32_t mdp5_plane_get_flush(struct drm_plane *plane) return mdp5_plane->flush_mask; } +/* called after vsync in thread context */ +void mdp5_plane_complete_commit(struct drm_plane *plane, + struct drm_plane_state *state) +{ + struct mdp5_kms *mdp5_kms = get_kms(plane); + struct mdp5_plane *mdp5_plane = to_mdp5_plane(plane); + enum mdp5_pipe pipe = mdp5_plane->pipe; + + if (!plane_enabled(plane->state)) { + DBG("%s: free SMP", mdp5_plane->name); + mdp5_smp_release(mdp5_kms->smp, pipe); + } +} + /* initialize plane */ struct drm_plane *mdp5_plane_init(struct drm_device *dev, enum mdp5_pipe pipe, bool private_plane, uint32_t reg_offset) diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.c index 16702aecf0df..64a27d86f2f5 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.c +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.c @@ -34,22 +34,44 @@ * and CANNOT be re-allocated (eg: MMB0 and MMB1 both tied to RGB0). * * For each block that can be dynamically allocated, it can be either - * free, or pending/in-use by a client. The updates happen in three steps: + * free: + * The block is free. + * + * pending: + * The block is allocated to some client and not free. + * + * configured: + * The block is allocated to some client, and assigned to that + * client in MDP5_MDP_SMP_ALLOC registers. + * + * inuse: + * The block is being actively used by a client. + * + * The updates happen in the following steps: * * 1) mdp5_smp_request(): * When plane scanout is setup, calculate required number of - * blocks needed per client, and request. Blocks not inuse or - * pending by any other client are added to client's pending - * set. + * blocks needed per client, and request. Blocks neither inuse nor + * configured nor pending by any other client are added to client's + * pending set. + * For shrinking, blocks in pending but not in configured can be freed + * directly, but those already in configured will be freed later by + * mdp5_smp_commit. * * 2) mdp5_smp_configure(): * As hw is programmed, before FLUSH, MDP5_MDP_SMP_ALLOC registers * are configured for the union(pending, inuse) + * Current pending is copied to configured. + * It is assumed that mdp5_smp_request and mdp5_smp_configure not run + * concurrently for the same pipe. * * 3) mdp5_smp_commit(): - * After next vblank, copy pending -> inuse. Optionally update + * After next vblank, copy configured -> inuse. Optionally update * MDP5_SMP_ALLOC registers if there are newly unused blocks * + * 4) mdp5_smp_release(): + * Must be called after the pipe is disabled and no longer uses any SMB + * * On the next vblank after changes have been committed to hw, the * client's pending blocks become it's in-use blocks (and no-longer * in-use blocks become available to other clients). @@ -77,6 +99,9 @@ struct mdp5_smp { struct mdp5_client_smp_state client_state[MAX_CLIENTS]; }; +static void update_smp_state(struct mdp5_smp *smp, + u32 cid, mdp5_smp_state_t *assigned); + static inline struct mdp5_kms *get_kms(struct mdp5_smp *smp) { @@ -149,7 +174,12 @@ static int smp_request_block(struct mdp5_smp *smp, for (i = cur_nblks; i > nblks; i--) { int blk = find_first_bit(ps->pending, cnt); clear_bit(blk, ps->pending); - /* don't clear in global smp_state until _commit() */ + + /* clear in global smp_state if not in configured + * otherwise until _commit() + */ + if (!test_bit(blk, ps->configured)) + clear_bit(blk, smp->state); } } @@ -223,10 +253,33 @@ int mdp5_smp_request(struct mdp5_smp *smp, enum mdp5_pipe pipe, u32 fmt, u32 wid /* Release SMP blocks for all clients of the pipe */ void mdp5_smp_release(struct mdp5_smp *smp, enum mdp5_pipe pipe) { - int i, nblks; + int i; + unsigned long flags; + int cnt = smp->blk_cnt; + + for (i = 0; i < pipe2nclients(pipe); i++) { + mdp5_smp_state_t assigned; + u32 cid = pipe2client(pipe, i); + struct mdp5_client_smp_state *ps = &smp->client_state[cid]; + + spin_lock_irqsave(&smp->state_lock, flags); + + /* clear hw assignment */ + bitmap_or(assigned, ps->inuse, ps->configured, cnt); + update_smp_state(smp, CID_UNUSED, &assigned); + + /* free to global pool */ + bitmap_andnot(smp->state, smp->state, ps->pending, cnt); + bitmap_andnot(smp->state, smp->state, assigned, cnt); + + /* clear client's infor */ + bitmap_zero(ps->pending, cnt); + bitmap_zero(ps->configured, cnt); + bitmap_zero(ps->inuse, cnt); + + spin_unlock_irqrestore(&smp->state_lock, flags); + } - for (i = 0, nblks = 0; i < pipe2nclients(pipe); i++) - smp_request_block(smp, pipe2client(pipe, i), 0); set_fifo_thresholds(smp, pipe, 0); } @@ -274,12 +327,20 @@ void mdp5_smp_configure(struct mdp5_smp *smp, enum mdp5_pipe pipe) u32 cid = pipe2client(pipe, i); struct mdp5_client_smp_state *ps = &smp->client_state[cid]; - bitmap_or(assigned, ps->inuse, ps->pending, cnt); + /* + * if vblank has not happened since last smp_configure + * skip the configure for now + */ + if (!bitmap_equal(ps->inuse, ps->configured, cnt)) + continue; + + bitmap_copy(ps->configured, ps->pending, cnt); + bitmap_or(assigned, ps->inuse, ps->configured, cnt); update_smp_state(smp, cid, &assigned); } } -/* step #3: after vblank, copy pending -> inuse: */ +/* step #3: after vblank, copy configured -> inuse: */ void mdp5_smp_commit(struct mdp5_smp *smp, enum mdp5_pipe pipe) { int cnt = smp->blk_cnt; @@ -295,7 +356,7 @@ void mdp5_smp_commit(struct mdp5_smp *smp, enum mdp5_pipe pipe) * using, which can be released and made available to other * clients: */ - if (bitmap_andnot(released, ps->inuse, ps->pending, cnt)) { + if (bitmap_andnot(released, ps->inuse, ps->configured, cnt)) { unsigned long flags; spin_lock_irqsave(&smp->state_lock, flags); @@ -306,7 +367,7 @@ void mdp5_smp_commit(struct mdp5_smp *smp, enum mdp5_pipe pipe) update_smp_state(smp, CID_UNUSED, &released); } - bitmap_copy(ps->inuse, ps->pending, cnt); + bitmap_copy(ps->inuse, ps->configured, cnt); } } diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.h b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.h index e47179f63585..5b6c2363f592 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.h +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.h @@ -23,6 +23,7 @@ struct mdp5_client_smp_state { mdp5_smp_state_t inuse; + mdp5_smp_state_t configured; mdp5_smp_state_t pending; }; From 544586f742b43c6fd5fcb74c794d33b2ef189e64 Mon Sep 17 00:00:00 2001 From: Satish Ashok Date: Tue, 28 Jul 2015 03:28:27 -0700 Subject: [PATCH 246/428] bridge: mcast: give fast leave precedence over multicast router and querier When fast leave is configured on a bridge port and an IGMP leave is received for a group, the group is not deleted immediately if there is a router detected or if multicast querier is configured. Ideally the group should be deleted immediately when fast leave is configured. Signed-off-by: Satish Ashok Signed-off-by: David S. Miller --- net/bridge/br_multicast.c | 50 ++++++++++++++++++++------------------- 1 file changed, 26 insertions(+), 24 deletions(-) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 79db489cdade..0b39dcc65b94 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1416,8 +1416,7 @@ br_multicast_leave_group(struct net_bridge *br, spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || - (port && port->state == BR_STATE_DISABLED) || - timer_pending(&other_query->timer)) + (port && port->state == BR_STATE_DISABLED)) goto out; mdb = mlock_dereference(br->mdb, br); @@ -1425,6 +1424,31 @@ br_multicast_leave_group(struct net_bridge *br, if (!mp) goto out; + if (port && (port->flags & BR_MULTICAST_FAST_LEAVE)) { + struct net_bridge_port_group __rcu **pp; + + for (pp = &mp->ports; + (p = mlock_dereference(*pp, br)) != NULL; + pp = &p->next) { + if (p->port != port) + continue; + + rcu_assign_pointer(*pp, p->next); + hlist_del_init(&p->mglist); + del_timer(&p->timer); + call_rcu_bh(&p->rcu, br_multicast_free_pg); + br_mdb_notify(br->dev, port, group, RTM_DELMDB); + + if (!mp->ports && !mp->mglist && + netif_running(br->dev)) + mod_timer(&mp->timer, jiffies); + } + goto out; + } + + if (timer_pending(&other_query->timer)) + goto out; + if (br->multicast_querier) { __br_multicast_send_query(br, port, &mp->addr); @@ -1450,28 +1474,6 @@ br_multicast_leave_group(struct net_bridge *br, } } - if (port && (port->flags & BR_MULTICAST_FAST_LEAVE)) { - struct net_bridge_port_group __rcu **pp; - - for (pp = &mp->ports; - (p = mlock_dereference(*pp, br)) != NULL; - pp = &p->next) { - if (p->port != port) - continue; - - rcu_assign_pointer(*pp, p->next); - hlist_del_init(&p->mglist); - del_timer(&p->timer); - call_rcu_bh(&p->rcu, br_multicast_free_pg); - br_mdb_notify(br->dev, port, group, RTM_DELMDB); - - if (!mp->ports && !mp->mglist && - netif_running(br->dev)) - mod_timer(&mp->timer, jiffies); - } - goto out; - } - now = jiffies; time = now + br->multicast_last_member_count * br->multicast_last_member_interval; From 7ae90a4f96486e3e20274afa1b8329802f5e1981 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 28 Jul 2015 13:10:44 +0200 Subject: [PATCH 247/428] bridge: mdb: fix delmdb state in the notification Since mdb states were introduced when deleting an entry the state was left as it was set in the delete request from the user which leads to the following output when doing a monitor (for example): $ bridge mdb add dev br0 port eth3 grp 239.0.0.1 permanent (monitor) dev br0 port eth3 grp 239.0.0.1 permanent $ bridge mdb del dev br0 port eth3 grp 239.0.0.1 permanent (monitor) dev br0 port eth3 grp 239.0.0.1 temp ^^^ Note the "temp" state in the delete notification which is wrong since the entry was permanent, the state in a delete is always reported as "temp" regardless of the real state of the entry. After this patch: $ bridge mdb add dev br0 port eth3 grp 239.0.0.1 permanent (monitor) dev br0 port eth3 grp 239.0.0.1 permanent $ bridge mdb del dev br0 port eth3 grp 239.0.0.1 permanent (monitor) dev br0 port eth3 grp 239.0.0.1 permanent There's one important note to make here that the state is actually not matched when doing a delete, so one can delete a permanent entry by stating "temp" in the end of the command, I've chosen this fix in order not to break user-space tools which rely on this (incorrect) behaviour. So to give an example after this patch and using the wrong state: $ bridge mdb add dev br0 port eth3 grp 239.0.0.1 permanent (monitor) dev br0 port eth3 grp 239.0.0.1 permanent $ bridge mdb del dev br0 port eth3 grp 239.0.0.1 temp (monitor) dev br0 port eth3 grp 239.0.0.1 permanent Note the state of the entry that got deleted is correct in the notification. Signed-off-by: Nikolay Aleksandrov Fixes: ccb1c31a7a87 ("bridge: add flags to distinguish permanent mdb entires") Signed-off-by: David S. Miller --- net/bridge/br_mdb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 1198a3dbad95..c94321955db7 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -445,6 +445,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) if (p->port->state == BR_STATE_DISABLED) goto unlock; + entry->state = p->state; rcu_assign_pointer(*pp, p->next); hlist_del_init(&p->mglist); del_timer(&p->timer); From 2482abb93ebf7bfbf85965ca907f0058ff968c59 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 28 Jul 2015 15:26:36 +0200 Subject: [PATCH 248/428] ebpf, x86: fix general protection fault when tail call is invoked With eBPF JIT compiler enabled on x86_64, I was able to reliably trigger the following general protection fault out of an eBPF program with a simple tail call, f.e. tracex5 (or a stripped down version of it): [ 927.097918] general protection fault: 0000 [#1] SMP DEBUG_PAGEALLOC [...] [ 927.100870] task: ffff8801f228b780 ti: ffff880016a64000 task.ti: ffff880016a64000 [ 927.102096] RIP: 0010:[] [] 0xffffffffa002440d [ 927.103390] RSP: 0018:ffff880016a67a68 EFLAGS: 00010006 [ 927.104683] RAX: 5a5a5a5a5a5a5a5a RBX: 0000000000000000 RCX: 0000000000000001 [ 927.105921] RDX: 0000000000000000 RSI: ffff88014e438000 RDI: ffff880016a67e00 [ 927.107137] RBP: ffff880016a67c90 R08: 0000000000000000 R09: 0000000000000001 [ 927.108351] R10: 0000000000000000 R11: 0000000000000000 R12: ffff880016a67e00 [ 927.109567] R13: 0000000000000000 R14: ffff88026500e460 R15: ffff880220a81520 [ 927.110787] FS: 00007fe7d5c1f740(0000) GS:ffff880265000000(0000) knlGS:0000000000000000 [ 927.112021] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 927.113255] CR2: 0000003e7bbb91a0 CR3: 000000006e04b000 CR4: 00000000001407e0 [ 927.114500] Stack: [ 927.115737] ffffc90008cdb000 ffff880016a67e00 ffff88026500e460 ffff880220a81520 [ 927.117005] 0000000100000000 000000000000001b ffff880016a67aa8 ffffffff8106c548 [ 927.118276] 00007ffcdaf22e58 0000000000000000 0000000000000000 ffff880016a67ff0 [ 927.119543] Call Trace: [ 927.120797] [] ? lookup_address+0x28/0x30 [ 927.122058] [] ? __module_text_address+0x16/0x70 [ 927.123314] [] ? is_ftrace_trampoline+0x3e/0x70 [ 927.124562] [] ? __kernel_text_address+0x5f/0x80 [ 927.125806] [] ? print_context_stack+0x7f/0xf0 [ 927.127033] [] ? __lock_acquire+0x572/0x2050 [ 927.128254] [] ? __lock_acquire+0x572/0x2050 [ 927.129461] [] ? trace_call_bpf+0x3a/0x140 [ 927.130654] [] trace_call_bpf+0x8a/0x140 [ 927.131837] [] ? trace_call_bpf+0x3a/0x140 [ 927.133015] [] kprobe_perf_func+0x28/0x220 [ 927.134195] [] kprobe_dispatcher+0x38/0x60 [ 927.135367] [] ? seccomp_phase1+0x1/0x230 [ 927.136523] [] kprobe_ftrace_handler+0xf0/0x150 [ 927.137666] [] ? seccomp_phase1+0x5/0x230 [ 927.138802] [] ftrace_ops_recurs_func+0x5c/0xb0 [ 927.139934] [] 0xffffffffa022b0d5 [ 927.141066] [] ? seccomp_phase1+0x1/0x230 [ 927.142199] [] seccomp_phase1+0x5/0x230 [ 927.143323] [] syscall_trace_enter_phase1+0xc4/0x150 [ 927.144450] [] ? seccomp_phase1+0x5/0x230 [ 927.145572] [] ? syscall_trace_enter_phase1+0xc4/0x150 [ 927.146666] [] tracesys+0xd/0x44 [ 927.147723] Code: 48 8b 46 10 48 39 d0 76 2c 8b 85 fc fd ff ff 83 f8 20 77 21 83 c0 01 89 85 fc fd ff ff 48 8d 44 d6 80 48 8b 00 48 83 f8 00 74 0a <48> 8b 40 20 48 83 c0 33 ff e0 48 89 d8 48 8b 9d d8 fd ff ff 4c [ 927.150046] RIP [] 0xffffffffa002440d The code section with the instructions that traps points into the eBPF JIT image of the root program (the one invoking the tail call instruction). Using bpf_jit_disasm -o on the eBPF root program image: [...] 4e: mov -0x204(%rbp),%eax 8b 85 fc fd ff ff 54: cmp $0x20,%eax <--- if (tail_call_cnt > MAX_TAIL_CALL_CNT) 83 f8 20 57: ja 0x000000000000007a 77 21 59: add $0x1,%eax <--- tail_call_cnt++ 83 c0 01 5c: mov %eax,-0x204(%rbp) 89 85 fc fd ff ff 62: lea -0x80(%rsi,%rdx,8),%rax <--- prog = array->prog[index] 48 8d 44 d6 80 67: mov (%rax),%rax 48 8b 00 6a: cmp $0x0,%rax <--- check for NULL 48 83 f8 00 6e: je 0x000000000000007a 74 0a 70: mov 0x20(%rax),%rax <--- GPF triggered here! fetch of bpf_func 48 8b 40 20 [ matches <48> 8b 40 20 ... from above ] 74: add $0x33,%rax <--- prologue skip of new prog 48 83 c0 33 78: jmpq *%rax <--- jump to new prog insns ff e0 [...] The problem is that rax has 5a5a5a5a5a5a5a5a, which suggests a tail call jump to map slot 0 is pointing to a poisoned page. The issue is the following: lea instruction has a wrong offset, i.e. it should be ... lea 0x80(%rsi,%rdx,8),%rax ... but it actually seems to be ... lea -0x80(%rsi,%rdx,8),%rax ... where 0x80 is offsetof(struct bpf_array, prog), thus the offset needs to be positive instead of negative. Disassembling the interpreter, we btw similarly do: [...] c88: lea 0x80(%rax,%rdx,8),%rax <--- prog = array->prog[index] 48 8d 84 d0 80 00 00 00 c90: add $0x1,%r13d 41 83 c5 01 c94: mov (%rax),%rax 48 8b 00 [...] Now the other interesting fact is that this panic triggers only when things like CONFIG_LOCKDEP are being used. In that case offsetof(struct bpf_array, prog) starts at offset 0x80 and in non-CONFIG_LOCKDEP case at offset 0x50. Reason is that the work_struct inside struct bpf_map grows by 48 bytes in my case due to the lockdep_map member (which also has CONFIG_LOCK_STAT enabled members). Changing the emitter to always use the 4 byte displacement in the lea instruction fixes the panic on my side. It increases the tail call instruction emission by 3 more byte, but it should cover us from various combinations (and perhaps other future increases on related structures). After patch, disassembly: [...] 9e: lea 0x80(%rsi,%rdx,8),%rax <--- CONFIG_LOCKDEP/CONFIG_LOCK_STAT 48 8d 84 d6 80 00 00 00 a6: mov (%rax),%rax 48 8b 00 [...] [...] 9e: lea 0x50(%rsi,%rdx,8),%rax <--- No CONFIG_LOCKDEP 48 8d 84 d6 50 00 00 00 a6: mov (%rax),%rax 48 8b 00 [...] Fixes: b52f00e6a715 ("x86: bpf_jit: implement bpf_tail_call() helper") Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- arch/x86/net/bpf_jit_comp.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 579a8fd74be0..be2e7a2b10d7 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -269,7 +269,7 @@ static void emit_bpf_tail_call(u8 **pprog) EMIT4(0x48, 0x8B, 0x46, /* mov rax, qword ptr [rsi + 16] */ offsetof(struct bpf_array, map.max_entries)); EMIT3(0x48, 0x39, 0xD0); /* cmp rax, rdx */ -#define OFFSET1 44 /* number of bytes to jump */ +#define OFFSET1 47 /* number of bytes to jump */ EMIT2(X86_JBE, OFFSET1); /* jbe out */ label1 = cnt; @@ -278,15 +278,15 @@ static void emit_bpf_tail_call(u8 **pprog) */ EMIT2_off32(0x8B, 0x85, -STACKSIZE + 36); /* mov eax, dword ptr [rbp - 516] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ -#define OFFSET2 33 +#define OFFSET2 36 EMIT2(X86_JA, OFFSET2); /* ja out */ label2 = cnt; EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ EMIT2_off32(0x89, 0x85, -STACKSIZE + 36); /* mov dword ptr [rbp - 516], eax */ /* prog = array->prog[index]; */ - EMIT4(0x48, 0x8D, 0x44, 0xD6); /* lea rax, [rsi + rdx * 8 + 0x50] */ - EMIT1(offsetof(struct bpf_array, prog)); + EMIT4_off32(0x48, 0x8D, 0x84, 0xD6, /* lea rax, [rsi + rdx * 8 + offsetof(...)] */ + offsetof(struct bpf_array, prog)); EMIT3(0x48, 0x8B, 0x00); /* mov rax, qword ptr [rax] */ /* if (prog == NULL) From 01a030996e1e2c268a4a484e2cbd3722b705414d Mon Sep 17 00:00:00 2001 From: "Karicheri, Muralidharan" Date: Tue, 28 Jul 2015 18:20:12 -0400 Subject: [PATCH 249/428] net: netcp: fix cleanup interface list in netcp_remove() Currently if user do rmmod keystone_netcp.ko following warning is seen :- [ 59.035891] ------------[ cut here ]------------ [ 59.040535] WARNING: CPU: 2 PID: 1619 at drivers/net/ethernet/ti/ netcp_core.c:2127 netcp_remove) This is because the interface list is not cleaned up in netcp_remove. This patch fixes this. Also fix some checkpatch related warnings. Signed-off-by: Murali Karicheri Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/netcp_core.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index ec8ed30196f3..a1c6961323dc 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -2112,6 +2112,7 @@ probe_quit: static int netcp_remove(struct platform_device *pdev) { struct netcp_device *netcp_device = platform_get_drvdata(pdev); + struct netcp_intf *netcp_intf, *netcp_tmp; struct netcp_inst_modpriv *inst_modpriv, *tmp; struct netcp_module *module; @@ -2123,8 +2124,16 @@ static int netcp_remove(struct platform_device *pdev) list_del(&inst_modpriv->inst_list); kfree(inst_modpriv); } - WARN(!list_empty(&netcp_device->interface_head), "%s interface list not empty!\n", - pdev->name); + + /* now that all modules are removed, clean up the interfaces */ + list_for_each_entry_safe(netcp_intf, netcp_tmp, + &netcp_device->interface_head, + interface_list) { + netcp_delete_interface(netcp_device, netcp_intf->ndev); + } + + WARN(!list_empty(&netcp_device->interface_head), + "%s interface list not empty!\n", pdev->name); devm_kfree(&pdev->dev, netcp_device); pm_runtime_put_sync(&pdev->dev); From c20afae75c32ec69eccc4ee432fa27d426e85a83 Mon Sep 17 00:00:00 2001 From: "Karicheri, Muralidharan" Date: Tue, 28 Jul 2015 18:20:13 -0400 Subject: [PATCH 250/428] net: netcp: ethss: fix up incorrect use of list api The code seems to assume a null is returned when the list is empty from first_sec_slave() to break the loop which is incorrect. Fix the code by using list_empty(). Signed-off-by: Murali Karicheri Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/netcp_ethss.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index a21881219865..d11d6172941a 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -2508,10 +2508,9 @@ static void free_secondary_ports(struct gbe_priv *gbe_dev) { struct gbe_slave *slave; - for (;;) { + while (!list_empty(&gbe_dev->secondary_slaves)) { slave = first_sec_slave(gbe_dev); - if (!slave) - break; + if (slave->phy) phy_disconnect(slave->phy); list_del(&slave->slave_list); From 31a184b7acbc06d894c562ef884a94d6d78d0236 Mon Sep 17 00:00:00 2001 From: "Karicheri, Muralidharan" Date: Tue, 28 Jul 2015 18:20:14 -0400 Subject: [PATCH 251/428] net: netcp: ethss: cleanup gbe_probe() and gbe_remove() functions This patch clean up error handle code to use goto label properly. In some cases, the code unnecessarily use goto instead of just returning the error code. Code also make explicit calls to devm_* APIs on error which is not necessary. In the gbe_remove() also it makes similar calls which is also unnecessary. Also fix few checkpatch warnings Signed-off-by: Murali Karicheri Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/netcp_core.c | 1 - drivers/net/ethernet/ti/netcp_ethss.c | 44 +++++++++++---------------- 2 files changed, 17 insertions(+), 28 deletions(-) diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index a1c6961323dc..9749dfd78c43 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -2135,7 +2135,6 @@ static int netcp_remove(struct platform_device *pdev) WARN(!list_empty(&netcp_device->interface_head), "%s interface list not empty!\n", pdev->name); - devm_kfree(&pdev->dev, netcp_device); pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); platform_set_drvdata(pdev, NULL); diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index d11d6172941a..1974a8ae764a 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -2856,14 +2856,13 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, &gbe_dev->dma_chan_name); if (ret < 0) { dev_err(dev, "missing \"tx-channel\" parameter\n"); - ret = -ENODEV; - goto quit; + return -EINVAL; } if (!strcmp(node->name, "gbe")) { ret = get_gbe_resource_version(gbe_dev, node); if (ret) - goto quit; + return ret; dev_dbg(dev, "ss_version: 0x%08x\n", gbe_dev->ss_version); @@ -2874,22 +2873,20 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, else ret = -ENODEV; - if (ret) - goto quit; } else if (!strcmp(node->name, "xgbe")) { ret = set_xgbe_ethss10_priv(gbe_dev, node); if (ret) - goto quit; + return ret; ret = netcp_xgbe_serdes_init(gbe_dev->xgbe_serdes_regs, gbe_dev->ss_regs); - if (ret) - goto quit; } else { dev_err(dev, "unknown GBE node(%s)\n", node->name); ret = -ENODEV; - goto quit; } + if (ret) + return ret; + interfaces = of_get_child_by_name(node, "interfaces"); if (!interfaces) dev_err(dev, "could not find interfaces\n"); @@ -2897,11 +2894,11 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, ret = netcp_txpipe_init(&gbe_dev->tx_pipe, netcp_device, gbe_dev->dma_chan_name, gbe_dev->tx_queue_id); if (ret) - goto quit; + return ret; ret = netcp_txpipe_open(&gbe_dev->tx_pipe); if (ret) - goto quit; + return ret; /* Create network interfaces */ INIT_LIST_HEAD(&gbe_dev->gbe_intf_head); @@ -2916,6 +2913,7 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, if (gbe_dev->num_slaves >= gbe_dev->max_num_slaves) break; } + of_node_put(interfaces); if (!gbe_dev->num_slaves) dev_warn(dev, "No network interface configured\n"); @@ -2928,9 +2926,10 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, of_node_put(secondary_ports); if (!gbe_dev->num_slaves) { - dev_err(dev, "No network interface or secondary ports configured\n"); + dev_err(dev, + "No network interface or secondary ports configured\n"); ret = -ENODEV; - goto quit; + goto free_sec_ports; } memset(&ale_params, 0, sizeof(ale_params)); @@ -2944,7 +2943,7 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, if (!gbe_dev->ale) { dev_err(gbe_dev->dev, "error initializing ale engine\n"); ret = -ENODEV; - goto quit; + goto free_sec_ports; } else { dev_dbg(gbe_dev->dev, "Created a gbe ale engine\n"); } @@ -2960,14 +2959,8 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, *inst_priv = gbe_dev; return 0; -quit: - if (gbe_dev->hw_stats) - devm_kfree(dev, gbe_dev->hw_stats); - cpsw_ale_destroy(gbe_dev->ale); - if (gbe_dev->ss_regs) - devm_iounmap(dev, gbe_dev->ss_regs); - of_node_put(interfaces); - devm_kfree(dev, gbe_dev); +free_sec_ports: + free_secondary_ports(gbe_dev); return ret; } @@ -3040,12 +3033,9 @@ static int gbe_remove(struct netcp_device *netcp_device, void *inst_priv) free_secondary_ports(gbe_dev); if (!list_empty(&gbe_dev->gbe_intf_head)) - dev_alert(gbe_dev->dev, "unreleased ethss interfaces present\n"); + dev_alert(gbe_dev->dev, + "unreleased ethss interfaces present\n"); - devm_kfree(gbe_dev->dev, gbe_dev->hw_stats); - devm_iounmap(gbe_dev->dev, gbe_dev->ss_regs); - memset(gbe_dev, 0x00, sizeof(*gbe_dev)); - devm_kfree(gbe_dev->dev, gbe_dev); return 0; } From 0d6aaffc3a6db642e0a165ba4d17d6d7bbaf5201 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Mon, 27 Jul 2015 10:21:46 -0700 Subject: [PATCH 252/428] hwmon: (nct7904) Rename pwm attributes to match hwmon ABI pwm attributes have well defined names, which should be used. Cc: Vadim V. Vlasov Cc: stable@vger.kernel.org #v4.1+ Signed-off-by: Guenter Roeck --- Documentation/hwmon/nct7904 | 4 +-- drivers/hwmon/nct7904.c | 57 +++++++++++++++++++------------------ 2 files changed, 31 insertions(+), 30 deletions(-) diff --git a/Documentation/hwmon/nct7904 b/Documentation/hwmon/nct7904 index 014f112e2a14..57fffe33ebfc 100644 --- a/Documentation/hwmon/nct7904 +++ b/Documentation/hwmon/nct7904 @@ -35,11 +35,11 @@ temp1_input Local temperature (1/1000 degree, temp[2-9]_input CPU temperatures (1/1000 degree, 0.125 degree resolution) -fan[1-4]_mode R/W, 0/1 for manual or SmartFan mode +pwm[1-4]_enable R/W, 1/2 for manual or SmartFan mode Setting SmartFan mode is supported only if it has been previously configured by BIOS (or configuration EEPROM) -fan[1-4]_pwm R/O in SmartFan mode, R/W in manual control mode +pwm[1-4] R/O in SmartFan mode, R/W in manual control mode The driver checks sensor control registers and does not export the sensors that are not enabled. Anyway, a sensor that is enabled may actually be not diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c index b77b82f24480..6153df735e82 100644 --- a/drivers/hwmon/nct7904.c +++ b/drivers/hwmon/nct7904.c @@ -412,8 +412,9 @@ static ssize_t show_pwm(struct device *dev, return sprintf(buf, "%d\n", val); } -static ssize_t store_mode(struct device *dev, struct device_attribute *devattr, - const char *buf, size_t count) +static ssize_t store_enable(struct device *dev, + struct device_attribute *devattr, + const char *buf, size_t count) { int index = to_sensor_dev_attr(devattr)->index; struct nct7904_data *data = dev_get_drvdata(dev); @@ -422,18 +423,18 @@ static ssize_t store_mode(struct device *dev, struct device_attribute *devattr, if (kstrtoul(buf, 10, &val) < 0) return -EINVAL; - if (val > 1 || (val && !data->fan_mode[index])) + if (val < 1 || val > 2 || (val == 2 && !data->fan_mode[index])) return -EINVAL; ret = nct7904_write_reg(data, BANK_3, FANCTL1_FMR_REG + index, - val ? data->fan_mode[index] : 0); + val == 2 ? data->fan_mode[index] : 0); return ret ? ret : count; } -/* Return 0 for manual mode or 1 for SmartFan mode */ -static ssize_t show_mode(struct device *dev, - struct device_attribute *devattr, char *buf) +/* Return 1 for manual mode or 2 for SmartFan mode */ +static ssize_t show_enable(struct device *dev, + struct device_attribute *devattr, char *buf) { int index = to_sensor_dev_attr(devattr)->index; struct nct7904_data *data = dev_get_drvdata(dev); @@ -443,36 +444,36 @@ static ssize_t show_mode(struct device *dev, if (val < 0) return val; - return sprintf(buf, "%d\n", val ? 1 : 0); + return sprintf(buf, "%d\n", val ? 2 : 1); } /* 2 attributes per channel: pwm and mode */ -static SENSOR_DEVICE_ATTR(fan1_pwm, S_IRUGO | S_IWUSR, +static SENSOR_DEVICE_ATTR(pwm1, S_IRUGO | S_IWUSR, show_pwm, store_pwm, 0); -static SENSOR_DEVICE_ATTR(fan1_mode, S_IRUGO | S_IWUSR, - show_mode, store_mode, 0); -static SENSOR_DEVICE_ATTR(fan2_pwm, S_IRUGO | S_IWUSR, +static SENSOR_DEVICE_ATTR(pwm1_enable, S_IRUGO | S_IWUSR, + show_enable, store_enable, 0); +static SENSOR_DEVICE_ATTR(pwm2, S_IRUGO | S_IWUSR, show_pwm, store_pwm, 1); -static SENSOR_DEVICE_ATTR(fan2_mode, S_IRUGO | S_IWUSR, - show_mode, store_mode, 1); -static SENSOR_DEVICE_ATTR(fan3_pwm, S_IRUGO | S_IWUSR, +static SENSOR_DEVICE_ATTR(pwm2_enable, S_IRUGO | S_IWUSR, + show_enable, store_enable, 1); +static SENSOR_DEVICE_ATTR(pwm3, S_IRUGO | S_IWUSR, show_pwm, store_pwm, 2); -static SENSOR_DEVICE_ATTR(fan3_mode, S_IRUGO | S_IWUSR, - show_mode, store_mode, 2); -static SENSOR_DEVICE_ATTR(fan4_pwm, S_IRUGO | S_IWUSR, +static SENSOR_DEVICE_ATTR(pwm3_enable, S_IRUGO | S_IWUSR, + show_enable, store_enable, 2); +static SENSOR_DEVICE_ATTR(pwm4, S_IRUGO | S_IWUSR, show_pwm, store_pwm, 3); -static SENSOR_DEVICE_ATTR(fan4_mode, S_IRUGO | S_IWUSR, - show_mode, store_mode, 3); +static SENSOR_DEVICE_ATTR(pwm4_enable, S_IRUGO | S_IWUSR, + show_enable, store_enable, 3); static struct attribute *nct7904_fanctl_attrs[] = { - &sensor_dev_attr_fan1_pwm.dev_attr.attr, - &sensor_dev_attr_fan1_mode.dev_attr.attr, - &sensor_dev_attr_fan2_pwm.dev_attr.attr, - &sensor_dev_attr_fan2_mode.dev_attr.attr, - &sensor_dev_attr_fan3_pwm.dev_attr.attr, - &sensor_dev_attr_fan3_mode.dev_attr.attr, - &sensor_dev_attr_fan4_pwm.dev_attr.attr, - &sensor_dev_attr_fan4_mode.dev_attr.attr, + &sensor_dev_attr_pwm1.dev_attr.attr, + &sensor_dev_attr_pwm1_enable.dev_attr.attr, + &sensor_dev_attr_pwm2.dev_attr.attr, + &sensor_dev_attr_pwm2_enable.dev_attr.attr, + &sensor_dev_attr_pwm3.dev_attr.attr, + &sensor_dev_attr_pwm3_enable.dev_attr.attr, + &sensor_dev_attr_pwm4.dev_attr.attr, + &sensor_dev_attr_pwm4_enable.dev_attr.attr, NULL }; From 9200bc4c28cd8992eb5379345abd6b4f0c93df16 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sat, 4 Jul 2015 13:23:42 -0700 Subject: [PATCH 253/428] hwmon: (nct7802) Fix integer overflow seen when writing voltage limits Writing a large value into a voltage limit attribute can result in an overflow due to an auto-conversion from unsigned long to unsigned int. Cc: Constantine Shulyupin Reviewed-by: Jean Delvare Cc: stable@vger.kernel.org # v4.1+ Signed-off-by: Guenter Roeck --- drivers/hwmon/nct7802.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwmon/nct7802.c b/drivers/hwmon/nct7802.c index 28fcb2e246d5..fbfc02bb2cfa 100644 --- a/drivers/hwmon/nct7802.c +++ b/drivers/hwmon/nct7802.c @@ -195,7 +195,7 @@ abort: } static int nct7802_write_voltage(struct nct7802_data *data, int nr, int index, - unsigned int voltage) + unsigned long voltage) { int shift = 8 - REG_VOLTAGE_LIMIT_MSB_SHIFT[index - 1][nr]; int err; From c8507fb235bea3314a02a67ddda0d4e6cf01fa78 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 29 Jul 2015 12:01:41 +0200 Subject: [PATCH 254/428] ipv6: flush nd cache on IFF_NOARP change This patch is the IPv6 equivalent of commit 6c8b4e3ff81b ("arp: flush arp cache on IFF_NOARP change") Without it, we keep buggy neighbours in the cache, with destination MAC address equal to our own MAC address. Tested: tcpdump -i eth0 -s 0 ip6 -n -e & ip link set dev eth0 arp off ping6 remote // sends buggy frames ip link set dev eth0 arp on ping6 remote // should work once kernel is patched Signed-off-by: Eric Dumazet Reported-by: Mario Fanelli Signed-off-by: David S. Miller --- net/ipv6/ndisc.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 0a05b35a90fc..c53331cfed95 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1650,6 +1650,7 @@ int ndisc_rcv(struct sk_buff *skb) static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_change_info *change_info; struct net *net = dev_net(dev); struct inet6_dev *idev; @@ -1664,6 +1665,11 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, ndisc_send_unsol_na(dev); in6_dev_put(idev); break; + case NETDEV_CHANGE: + change_info = ptr; + if (change_info->flags_changed & IFF_NOARP) + neigh_changeaddr(&nd_tbl, dev); + break; case NETDEV_DOWN: neigh_ifdown(&nd_tbl, dev); fib6_run_gc(0, net, false); From 4b561c17d91e9311639dd856255de0987f7ed9b2 Mon Sep 17 00:00:00 2001 From: Sunil Goutham Date: Wed, 29 Jul 2015 16:49:36 +0300 Subject: [PATCH 255/428] net: thunderx: Fix data integrity issues with LDWB Switching back to LDD transactions from LDWB. While transmitting packets out with LDWB transactions data integrity issues are seen very frequently. hence switching back to LDD. Signed-off-by: Sunil Goutham Signed-off-by: Robert Richter Signed-off-by: Aleksey Makarov Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/thunder/nicvf_queues.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c index d69d228d11a0..4dae6aa750d8 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c @@ -992,7 +992,7 @@ static inline void nicvf_sq_add_gather_subdesc(struct snd_queue *sq, int qentry, memset(gather, 0, SND_QUEUE_DESC_SIZE); gather->subdesc_type = SQ_DESC_TYPE_GATHER; - gather->ld_type = NIC_SEND_LD_TYPE_E_LDWB; + gather->ld_type = NIC_SEND_LD_TYPE_E_LDD; gather->size = size; gather->addr = data; } From 143ceb0b8a1570d1f899900bf05df19ecd673a18 Mon Sep 17 00:00:00 2001 From: Sunil Goutham Date: Wed, 29 Jul 2015 16:49:37 +0300 Subject: [PATCH 256/428] net: thunderx: Fix memory leak while tearing down interface Fixed 'tso_hdrs' memory not being freed properly. Also fixed SQ skbuff maintenance issues. Signed-off-by: Sunil Goutham Signed-off-by: Aleksey Makarov Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/thunder/nicvf_main.c | 1 + drivers/net/ethernet/cavium/thunder/nicvf_queues.c | 8 +++++--- 2 files changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 8b119a035b7e..2890cd65ba62 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -425,6 +425,7 @@ static void nicvf_snd_pkt_handler(struct net_device *netdev, if (skb) { prefetch(skb); dev_consume_skb_any(skb); + sq->skbuff[cqe_tx->sqe_ptr] = (u64)NULL; } } diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c index 4dae6aa750d8..4c91959f1d0e 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c @@ -382,7 +382,8 @@ static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq) return; if (sq->tso_hdrs) - dma_free_coherent(&nic->pdev->dev, sq->dmem.q_len, + dma_free_coherent(&nic->pdev->dev, + sq->dmem.q_len * TSO_HEADER_SIZE, sq->tso_hdrs, sq->tso_hdrs_phys); kfree(sq->skbuff); @@ -863,10 +864,11 @@ void nicvf_sq_free_used_descs(struct net_device *netdev, struct snd_queue *sq, continue; } skb = (struct sk_buff *)sq->skbuff[sq->head]; + if (skb) + dev_kfree_skb_any(skb); atomic64_add(1, (atomic64_t *)&netdev->stats.tx_packets); atomic64_add(hdr->tot_len, (atomic64_t *)&netdev->stats.tx_bytes); - dev_kfree_skb_any(skb); nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1); } } @@ -1048,7 +1050,7 @@ static int nicvf_sq_append_tso(struct nicvf *nic, struct snd_queue *sq, } nicvf_sq_add_hdr_subdesc(sq, hdr_qentry, seg_subdescs - 1, skb, seg_len); - sq->skbuff[hdr_qentry] = 0; + sq->skbuff[hdr_qentry] = (u64)NULL; qentry = nicvf_get_nxt_sqentry(sq, qentry); desc_cnt += seg_subdescs; From 32c1b965f41639081af84cd3f320a81d9c30a06e Mon Sep 17 00:00:00 2001 From: Sunil Goutham Date: Wed, 29 Jul 2015 16:49:38 +0300 Subject: [PATCH 257/428] net: thunderx: Fix RQ_DROP miscalculation With earlier configured value sufficient number of CQEs are not being reserved for transmitted packets. Hence under heavy incoming traffic load, receive notifications will take away most of the CQ thus transmit notifications will be lost resulting in tx skbs not being freed. Finally SQ will be full and it will be stopped, watchdog timer will kick in. After this fix receive notifications will not take morethan half of CQ reserving the rest for transmit notifications. Also changed CQ & SQ sizes from 16k to 4k. This is also due to the receive notifications taking first half of CQ under heavy load and time taken by NAPI to clear transmit notifications will increase with higher queue sizes. Again results in SQ being stopped. Signed-off-by: Sunil Goutham Signed-off-by: Aleksey Makarov Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/thunder/nicvf_queues.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h index 8341bdf755d1..f0937b7bfe9f 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h @@ -62,7 +62,7 @@ #define SND_QUEUE_CNT 8 #define CMP_QUEUE_CNT 8 /* Max of RCV and SND qcount */ -#define SND_QSIZE SND_QUEUE_SIZE4 +#define SND_QSIZE SND_QUEUE_SIZE2 #define SND_QUEUE_LEN (1ULL << (SND_QSIZE + 10)) #define MAX_SND_QUEUE_LEN (1ULL << (SND_QUEUE_SIZE6 + 10)) #define SND_QUEUE_THRESH 2ULL @@ -70,7 +70,10 @@ /* Since timestamp not enabled, otherwise 2 */ #define MAX_CQE_PER_PKT_XMIT 1 -#define CMP_QSIZE CMP_QUEUE_SIZE4 +/* Keep CQ and SQ sizes same, if timestamping + * is enabled this equation will change. + */ +#define CMP_QSIZE CMP_QUEUE_SIZE2 #define CMP_QUEUE_LEN (1ULL << (CMP_QSIZE + 10)) #define CMP_QUEUE_CQE_THRESH 0 #define CMP_QUEUE_TIMER_THRESH 220 /* 10usec */ @@ -87,7 +90,12 @@ #define MAX_CQES_FOR_TX ((SND_QUEUE_LEN / MIN_SQ_DESC_PER_PKT_XMIT) * \ MAX_CQE_PER_PKT_XMIT) -#define RQ_CQ_DROP ((CMP_QUEUE_LEN - MAX_CQES_FOR_TX) / 256) +/* Calculate number of CQEs to reserve for all SQEs. + * Its 1/256th level of CQ size. + * '+ 1' to account for pipelining + */ +#define RQ_CQ_DROP ((256 / (CMP_QUEUE_LEN / \ + (CMP_QUEUE_LEN - MAX_CQES_FOR_TX))) + 1) /* Descriptor size in bytes */ #define SND_QUEUE_DESC_SIZE 16 From c62cd3c45198c212f85f53bfc254dd83f01b0fbc Mon Sep 17 00:00:00 2001 From: Sunil Goutham Date: Wed, 29 Jul 2015 16:49:39 +0300 Subject: [PATCH 258/428] net: thunderx: Fix memory leak when changing queue count Fix for memory leak when changing queue/channel count via ethtool Signed-off-by: Sunil Goutham Signed-off-by: Aleksey Makarov Signed-off-by: David S. Miller --- .../ethernet/cavium/thunder/nicvf_ethtool.c | 23 +++++++++++-------- 1 file changed, 14 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c index 16bd2d772db9..b22dee6e7b4f 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c @@ -126,6 +126,7 @@ static void nicvf_set_msglevel(struct net_device *netdev, u32 lvl) static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data) { + struct nicvf *nic = netdev_priv(netdev); int stats, qidx; if (sset != ETH_SS_STATS) @@ -141,7 +142,7 @@ static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data) data += ETH_GSTRING_LEN; } - for (qidx = 0; qidx < MAX_RCV_QUEUES_PER_QS; qidx++) { + for (qidx = 0; qidx < nic->qs->rq_cnt; qidx++) { for (stats = 0; stats < nicvf_n_queue_stats; stats++) { sprintf(data, "rxq%d: %s", qidx, nicvf_queue_stats[stats].name); @@ -149,7 +150,7 @@ static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data) } } - for (qidx = 0; qidx < MAX_SND_QUEUES_PER_QS; qidx++) { + for (qidx = 0; qidx < nic->qs->sq_cnt; qidx++) { for (stats = 0; stats < nicvf_n_queue_stats; stats++) { sprintf(data, "txq%d: %s", qidx, nicvf_queue_stats[stats].name); @@ -170,12 +171,14 @@ static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data) static int nicvf_get_sset_count(struct net_device *netdev, int sset) { + struct nicvf *nic = netdev_priv(netdev); + if (sset != ETH_SS_STATS) return -EINVAL; return nicvf_n_hw_stats + nicvf_n_drv_stats + (nicvf_n_queue_stats * - (MAX_RCV_QUEUES_PER_QS + MAX_SND_QUEUES_PER_QS)) + + (nic->qs->rq_cnt + nic->qs->sq_cnt)) + BGX_RX_STATS_COUNT + BGX_TX_STATS_COUNT; } @@ -197,13 +200,13 @@ static void nicvf_get_ethtool_stats(struct net_device *netdev, *(data++) = ((u64 *)&nic->drv_stats) [nicvf_drv_stats[stat].index]; - for (qidx = 0; qidx < MAX_RCV_QUEUES_PER_QS; qidx++) { + for (qidx = 0; qidx < nic->qs->rq_cnt; qidx++) { for (stat = 0; stat < nicvf_n_queue_stats; stat++) *(data++) = ((u64 *)&nic->qs->rq[qidx].stats) [nicvf_queue_stats[stat].index]; } - for (qidx = 0; qidx < MAX_SND_QUEUES_PER_QS; qidx++) { + for (qidx = 0; qidx < nic->qs->sq_cnt; qidx++) { for (stat = 0; stat < nicvf_n_queue_stats; stat++) *(data++) = ((u64 *)&nic->qs->sq[qidx].stats) [nicvf_queue_stats[stat].index]; @@ -543,6 +546,7 @@ static int nicvf_set_channels(struct net_device *dev, { struct nicvf *nic = netdev_priv(dev); int err = 0; + bool if_up = netif_running(dev); if (!channel->rx_count || !channel->tx_count) return -EINVAL; @@ -551,6 +555,9 @@ static int nicvf_set_channels(struct net_device *dev, if (channel->tx_count > MAX_SND_QUEUES_PER_QS) return -EINVAL; + if (if_up) + nicvf_stop(dev); + nic->qs->rq_cnt = channel->rx_count; nic->qs->sq_cnt = channel->tx_count; nic->qs->cq_cnt = max(nic->qs->rq_cnt, nic->qs->sq_cnt); @@ -559,11 +566,9 @@ static int nicvf_set_channels(struct net_device *dev, if (err) return err; - if (!netif_running(dev)) - return err; + if (if_up) + nicvf_open(dev); - nicvf_stop(dev); - nicvf_open(dev); netdev_info(dev, "Setting num Tx rings to %d, Rx rings to %d success\n", nic->qs->sq_cnt, nic->qs->rq_cnt); From 2cb468e01e6fdad3d8a00da6cda71094e0e05676 Mon Sep 17 00:00:00 2001 From: Sunil Goutham Date: Wed, 29 Jul 2015 16:49:40 +0300 Subject: [PATCH 259/428] net: thunderx: Fix TSO packet statistic Fixing TSO packages not being counted. Signed-off-by: Sunil Goutham Signed-off-by: Aleksey Makarov Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/thunder/nicvf_queues.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c index 4c91959f1d0e..500fdbe08ceb 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c @@ -1064,6 +1064,7 @@ static int nicvf_sq_append_tso(struct nicvf *nic, struct snd_queue *sq, /* Inform HW to xmit all TSO segments */ nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_DOOR, skb_get_queue_mapping(skb), desc_cnt); + nic->drv_stats.tx_tso++; return 1; } From f8ce9666fa63da7e5afd9ff6e3221f86555621f3 Mon Sep 17 00:00:00 2001 From: Sunil Goutham Date: Wed, 29 Jul 2015 16:49:41 +0300 Subject: [PATCH 260/428] net: thunderx: Suppress alloc_pages() failure warnings Suppressing standard alloc_pages() warnings. Some kernel configs limit alloc size and the network driver may fail. Do not drop a kernel warning in this case, instead just drop a oneliner that the network driver could not be loaded since the buffer could not be allocated. Signed-off-by: Sunil Goutham Signed-off-by: Aleksey Makarov Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/thunder/nicvf_queues.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c index 500fdbe08ceb..ca4240aa6d15 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c @@ -103,9 +103,11 @@ static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, gfp_t gfp, /* Allocate a new page */ if (!nic->rb_page) { - nic->rb_page = alloc_pages(gfp | __GFP_COMP, order); + nic->rb_page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN, + order); if (!nic->rb_page) { - netdev_err(nic->netdev, "Failed to allocate new rcv buffer\n"); + netdev_err(nic->netdev, + "Failed to allocate new rcv buffer\n"); return -ENOMEM; } nic->rb_page_offset = 0; From 74840b83bd59ee51c591714470c6629ac18f424a Mon Sep 17 00:00:00 2001 From: Sunil Goutham Date: Wed, 29 Jul 2015 16:49:42 +0300 Subject: [PATCH 261/428] net: thunderx: Wakeup TXQ only if CQE_TX are processed Previously TXQ is wakedup whenever napi is executed and irrespective of if any CQE_TX are processed or not. Added 'txq_stop' and 'txq_wake' counters to aid in debugging if there are any future issues. Signed-off-by: Sunil Goutham Signed-off-by: Aleksey Makarov Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/thunder/nic.h | 3 +- .../ethernet/cavium/thunder/nicvf_ethtool.c | 3 +- .../net/ethernet/cavium/thunder/nicvf_main.c | 40 +++++++++++++------ 3 files changed, 31 insertions(+), 15 deletions(-) diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h index dda8a02b7322..a0be076eba83 100644 --- a/drivers/net/ethernet/cavium/thunder/nic.h +++ b/drivers/net/ethernet/cavium/thunder/nic.h @@ -216,8 +216,9 @@ struct nicvf_drv_stats { /* Tx */ u64 tx_frames_ok; u64 tx_drops; - u64 tx_busy; u64 tx_tso; + u64 txq_stop; + u64 txq_wake; }; struct nicvf { diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c index b22dee6e7b4f..a4228e664567 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c @@ -66,9 +66,10 @@ static const struct nicvf_stat nicvf_drv_stats[] = { NICVF_DRV_STAT(rx_frames_jumbo), NICVF_DRV_STAT(rx_drops), NICVF_DRV_STAT(tx_frames_ok), - NICVF_DRV_STAT(tx_busy), NICVF_DRV_STAT(tx_tso), NICVF_DRV_STAT(tx_drops), + NICVF_DRV_STAT(txq_stop), + NICVF_DRV_STAT(txq_wake), }; static const struct nicvf_stat nicvf_queue_stats[] = { diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 2890cd65ba62..422d46ec509d 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -477,12 +477,13 @@ static void nicvf_rcv_pkt_handler(struct net_device *netdev, static int nicvf_cq_intr_handler(struct net_device *netdev, u8 cq_idx, struct napi_struct *napi, int budget) { - int processed_cqe, work_done = 0; + int processed_cqe, work_done = 0, tx_done = 0; int cqe_count, cqe_head; struct nicvf *nic = netdev_priv(netdev); struct queue_set *qs = nic->qs; struct cmp_queue *cq = &qs->cq[cq_idx]; struct cqe_rx_t *cq_desc; + struct netdev_queue *txq; spin_lock_bh(&cq->lock); loop: @@ -497,8 +498,8 @@ loop: cqe_head = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_HEAD, cq_idx) >> 9; cqe_head &= 0xFFFF; - netdev_dbg(nic->netdev, "%s cqe_count %d cqe_head %d\n", - __func__, cqe_count, cqe_head); + netdev_dbg(nic->netdev, "%s CQ%d cqe_count %d cqe_head %d\n", + __func__, cq_idx, cqe_count, cqe_head); while (processed_cqe < cqe_count) { /* Get the CQ descriptor */ cq_desc = (struct cqe_rx_t *)GET_CQ_DESC(cq, cqe_head); @@ -512,8 +513,8 @@ loop: break; } - netdev_dbg(nic->netdev, "cq_desc->cqe_type %d\n", - cq_desc->cqe_type); + netdev_dbg(nic->netdev, "CQ%d cq_desc->cqe_type %d\n", + cq_idx, cq_desc->cqe_type); switch (cq_desc->cqe_type) { case CQE_TYPE_RX: nicvf_rcv_pkt_handler(netdev, napi, cq, @@ -523,6 +524,7 @@ loop: case CQE_TYPE_SEND: nicvf_snd_pkt_handler(netdev, cq, (void *)cq_desc, CQE_TYPE_SEND); + tx_done++; break; case CQE_TYPE_INVALID: case CQE_TYPE_RX_SPLIT: @@ -533,8 +535,9 @@ loop: } processed_cqe++; } - netdev_dbg(nic->netdev, "%s processed_cqe %d work_done %d budget %d\n", - __func__, processed_cqe, work_done, budget); + netdev_dbg(nic->netdev, + "%s CQ%d processed_cqe %d work_done %d budget %d\n", + __func__, cq_idx, processed_cqe, work_done, budget); /* Ring doorbell to inform H/W to reuse processed CQEs */ nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_DOOR, @@ -544,6 +547,19 @@ loop: goto loop; done: + /* Wakeup TXQ if its stopped earlier due to SQ full */ + if (tx_done) { + txq = netdev_get_tx_queue(netdev, cq_idx); + if (netif_tx_queue_stopped(txq)) { + netif_tx_wake_queue(txq); + nic->drv_stats.txq_wake++; + if (netif_msg_tx_err(nic)) + netdev_warn(netdev, + "%s: Transmit queue wakeup SQ%d\n", + netdev->name, cq_idx); + } + } + spin_unlock_bh(&cq->lock); return work_done; } @@ -555,15 +571,10 @@ static int nicvf_poll(struct napi_struct *napi, int budget) struct net_device *netdev = napi->dev; struct nicvf *nic = netdev_priv(netdev); struct nicvf_cq_poll *cq; - struct netdev_queue *txq; cq = container_of(napi, struct nicvf_cq_poll, napi); work_done = nicvf_cq_intr_handler(netdev, cq->cq_idx, napi, budget); - txq = netdev_get_tx_queue(netdev, cq->cq_idx); - if (netif_tx_queue_stopped(txq)) - netif_tx_wake_queue(txq); - if (work_done < budget) { /* Slow packet rate, exit polling */ napi_complete(napi); @@ -836,7 +847,7 @@ static netdev_tx_t nicvf_xmit(struct sk_buff *skb, struct net_device *netdev) if (!nicvf_sq_append_skb(nic, skb) && !netif_tx_queue_stopped(txq)) { netif_tx_stop_queue(txq); - nic->drv_stats.tx_busy++; + nic->drv_stats.txq_stop++; if (netif_msg_tx_err(nic)) netdev_warn(netdev, "%s: Transmit ring full, stopping SQ%d\n", @@ -989,6 +1000,9 @@ int nicvf_open(struct net_device *netdev) for (qidx = 0; qidx < qs->rbdr_cnt; qidx++) nicvf_enable_intr(nic, NICVF_INTR_RBDR, qidx); + nic->drv_stats.txq_stop = 0; + nic->drv_stats.txq_wake = 0; + netif_carrier_on(netdev); netif_tx_start_all_queues(netdev); From 3d7a8aaad8720edb301d40d4a9d7fa906c76ba34 Mon Sep 17 00:00:00 2001 From: Sunil Goutham Date: Wed, 29 Jul 2015 16:49:43 +0300 Subject: [PATCH 262/428] net: thunderx: Set watchdog timeout value If a txq (SQ) remains in stopped state after this timeout its considered as stuck and interface is reinited. Signed-off-by: Sunil Goutham Signed-off-by: Aleksey Makarov Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/thunder/nic.h | 9 +++++++++ drivers/net/ethernet/cavium/thunder/nicvf_main.c | 1 + 2 files changed, 10 insertions(+) diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h index a0be076eba83..8aee250904ec 100644 --- a/drivers/net/ethernet/cavium/thunder/nic.h +++ b/drivers/net/ethernet/cavium/thunder/nic.h @@ -125,6 +125,15 @@ */ #define NICPF_CLK_PER_INT_TICK 2 +/* Time to wait before we decide that a SQ is stuck. + * + * Since both pkt rx and tx notifications are done with same CQ, + * when packets are being received at very high rate (eg: L2 forwarding) + * then freeing transmitted skbs will be delayed and watchdog + * will kick in, resetting interface. Hence keeping this value high. + */ +#define NICVF_TX_TIMEOUT (50 * HZ) + struct nicvf_cq_poll { u8 cq_idx; /* Completion queue index */ struct napi_struct napi; diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 422d46ec509d..abee2d7cedb5 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -1293,6 +1293,7 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->hw_features = netdev->features; netdev->netdev_ops = &nicvf_netdev_ops; + netdev->watchdog_timeo = NICVF_TX_TIMEOUT; INIT_WORK(&nic->reset_task, nicvf_reset_task); From b49087dd0fa27d61b55f7c77d0b857e3b5055161 Mon Sep 17 00:00:00 2001 From: Sunil Goutham Date: Wed, 29 Jul 2015 16:49:44 +0300 Subject: [PATCH 263/428] net: thunderx: Fix crash when changing rss with mutliple traffic flows This fixes a crash when changing rss with multiple traffic flows. While interface teardown, disable tx queues after all NAPI threads are done. If done otherwise tx queues might be woken up inside NAPI if any CQE_TX are processed. Signed-off-by: Sunil Goutham Signed-off-by: Aleksey Makarov Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/thunder/nicvf_main.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index abee2d7cedb5..c7a29a3fce89 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -234,7 +234,7 @@ static void nicvf_handle_mbx_intr(struct nicvf *nic) nic->duplex == DUPLEX_FULL ? "Full duplex" : "Half duplex"); netif_carrier_on(nic->netdev); - netif_tx_wake_all_queues(nic->netdev); + netif_tx_start_all_queues(nic->netdev); } else { netdev_info(nic->netdev, "%s: Link is Down\n", nic->netdev->name); @@ -551,7 +551,7 @@ done: if (tx_done) { txq = netdev_get_tx_queue(netdev, cq_idx); if (netif_tx_queue_stopped(txq)) { - netif_tx_wake_queue(txq); + netif_tx_start_queue(txq); nic->drv_stats.txq_wake++; if (netif_msg_tx_err(nic)) netdev_warn(netdev, @@ -845,7 +845,7 @@ static netdev_tx_t nicvf_xmit(struct sk_buff *skb, struct net_device *netdev) return NETDEV_TX_OK; } - if (!nicvf_sq_append_skb(nic, skb) && !netif_tx_queue_stopped(txq)) { + if (!netif_tx_queue_stopped(txq) && !nicvf_sq_append_skb(nic, skb)) { netif_tx_stop_queue(txq); nic->drv_stats.txq_stop++; if (netif_msg_tx_err(nic)) @@ -871,7 +871,6 @@ int nicvf_stop(struct net_device *netdev) nicvf_send_msg_to_pf(nic, &mbx); netif_carrier_off(netdev); - netif_tx_disable(netdev); /* Disable RBDR & QS error interrupts */ for (qidx = 0; qidx < qs->rbdr_cnt; qidx++) { @@ -906,6 +905,8 @@ int nicvf_stop(struct net_device *netdev) kfree(cq_poll); } + netif_tx_disable(netdev); + /* Free resources */ nicvf_config_data_transfer(nic, false); From 4adf4351145e65dd98407299496ef00d82430b48 Mon Sep 17 00:00:00 2001 From: Sunil Goutham Date: Wed, 29 Jul 2015 16:49:45 +0300 Subject: [PATCH 264/428] net: thunderx: Add PCI driver shutdown routine Signed-off-by: Sunil Goutham Signed-off-by: Aleksey Makarov Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/thunder/nicvf_main.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index c7a29a3fce89..3b90afb8c293 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -1335,11 +1335,17 @@ static void nicvf_remove(struct pci_dev *pdev) pci_disable_device(pdev); } +static void nicvf_shutdown(struct pci_dev *pdev) +{ + nicvf_remove(pdev); +} + static struct pci_driver nicvf_driver = { .name = DRV_NAME, .id_table = nicvf_id_table, .probe = nicvf_probe, .remove = nicvf_remove, + .shutdown = nicvf_shutdown, }; static int __init nicvf_init_module(void) From 60f83c898776c363ef8ebb66f14cbc748c1df1e8 Mon Sep 17 00:00:00 2001 From: Thanneeru Srinivasulu Date: Wed, 29 Jul 2015 16:49:46 +0300 Subject: [PATCH 265/428] net: thunderx: Fix for crash while BGX teardown Cortina phy does not have kernel driver and we don't attach device with phy layer for intefaces like XFI, XLAUI etc, Hence check for interface type before calling disconnect. Signed-off-by: Thanneeru Srinivasulu Signed-off-by: Aleksey Makarov Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/thunder/thunder_bgx.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 633ec05dfe05..b961a89dc626 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -673,7 +673,10 @@ static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid) bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cmrx_cfg); bgx_flush_dmac_addrs(bgx, lmacid); - if (lmac->phydev) + if ((bgx->lmac_type != BGX_MODE_XFI) && + (bgx->lmac_type != BGX_MODE_XLAUI) && + (bgx->lmac_type != BGX_MODE_40G_KR) && + (bgx->lmac_type != BGX_MODE_10G_KR) && lmac->phydev) phy_disconnect(lmac->phydev); lmac->phydev = NULL; From f4eaed28c7834fc049c754f63e6988bbd73778d9 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 29 Jul 2015 18:40:56 +0200 Subject: [PATCH 266/428] act_bpf: fix memory leaks when replacing bpf programs We currently trigger multiple memory leaks when replacing bpf actions, besides others: comm "tc", pid 1909, jiffies 4294851310 (age 1602.796s) hex dump (first 32 bytes): 01 00 00 00 03 00 00 00 00 00 00 00 00 00 00 00 ................ 18 b0 98 6d 00 88 ff ff 00 00 00 00 00 00 00 00 ...m............ backtrace: [] kmemleak_alloc+0x4e/0xb0 [] __vmalloc_node_range+0x1bd/0x2c0 [] __vmalloc+0x4a/0x50 [] bpf_prog_alloc+0x3a/0xa0 [] bpf_prog_create+0x44/0xa0 [] tcf_bpf_init+0x28b/0x3c0 [act_bpf] [] tcf_action_init_1+0x191/0x1b0 [] tcf_action_init+0x82/0xf0 [] tcf_exts_validate+0xb2/0xc0 [] cls_bpf_modify_existing+0x98/0x340 [cls_bpf] [] cls_bpf_change+0x1a6/0x274 [cls_bpf] [] tc_ctl_tfilter+0x335/0x910 [] rtnetlink_rcv_msg+0x95/0x240 [] netlink_rcv_skb+0xaf/0xc0 [] rtnetlink_rcv+0x2e/0x40 [] netlink_unicast+0xef/0x1b0 Issue is that the old content from tcf_bpf is allocated and needs to be released when we replace it. We seem to do that since the beginning of act_bpf on the filter and insns, later on the name as well. Example test case, after patch: # FOO="1,6 0 0 4294967295," # BAR="1,6 0 0 4294967294," # tc actions add action bpf bytecode "$FOO" index 2 # tc actions show action bpf action order 0: bpf bytecode '1,6 0 0 4294967295' default-action pipe index 2 ref 1 bind 0 # tc actions replace action bpf bytecode "$BAR" index 2 # tc actions show action bpf action order 0: bpf bytecode '1,6 0 0 4294967294' default-action pipe index 2 ref 1 bind 0 # tc actions replace action bpf bytecode "$FOO" index 2 # tc actions show action bpf action order 0: bpf bytecode '1,6 0 0 4294967295' default-action pipe index 2 ref 1 bind 0 # tc actions del action bpf index 2 [...] # echo "scan" > /sys/kernel/debug/kmemleak # cat /sys/kernel/debug/kmemleak | grep "comm \"tc\"" | wc -l 0 Fixes: d23b8ad8ab23 ("tc: add BPF based action") Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- net/sched/act_bpf.c | 53 ++++++++++++++++++++++++++++++--------------- 1 file changed, 35 insertions(+), 18 deletions(-) diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 1df78289e248..d0edeb7a1950 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -27,9 +27,10 @@ struct tcf_bpf_cfg { struct bpf_prog *filter; struct sock_filter *bpf_ops; - char *bpf_name; + const char *bpf_name; u32 bpf_fd; u16 bpf_num_ops; + bool is_ebpf; }; static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act, @@ -207,6 +208,7 @@ static int tcf_bpf_init_from_ops(struct nlattr **tb, struct tcf_bpf_cfg *cfg) cfg->bpf_ops = bpf_ops; cfg->bpf_num_ops = bpf_num_ops; cfg->filter = fp; + cfg->is_ebpf = false; return 0; } @@ -241,18 +243,40 @@ static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg) cfg->bpf_fd = bpf_fd; cfg->bpf_name = name; cfg->filter = fp; + cfg->is_ebpf = true; return 0; } +static void tcf_bpf_cfg_cleanup(const struct tcf_bpf_cfg *cfg) +{ + if (cfg->is_ebpf) + bpf_prog_put(cfg->filter); + else + bpf_prog_destroy(cfg->filter); + + kfree(cfg->bpf_ops); + kfree(cfg->bpf_name); +} + +static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog, + struct tcf_bpf_cfg *cfg) +{ + cfg->is_ebpf = tcf_bpf_is_ebpf(prog); + cfg->filter = prog->filter; + + cfg->bpf_ops = prog->bpf_ops; + cfg->bpf_name = prog->bpf_name; +} + static int tcf_bpf_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action *act, int replace, int bind) { struct nlattr *tb[TCA_ACT_BPF_MAX + 1]; + struct tcf_bpf_cfg cfg, old; struct tc_act_bpf *parm; struct tcf_bpf *prog; - struct tcf_bpf_cfg cfg; bool is_bpf, is_ebpf; int ret; @@ -301,6 +325,9 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, prog = to_bpf(act); spin_lock_bh(&prog->tcf_lock); + if (ret != ACT_P_CREATED) + tcf_bpf_prog_fill_cfg(prog, &old); + prog->bpf_ops = cfg.bpf_ops; prog->bpf_name = cfg.bpf_name; @@ -316,32 +343,22 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, if (ret == ACT_P_CREATED) tcf_hash_insert(act); + else + tcf_bpf_cfg_cleanup(&old); return ret; destroy_fp: - if (is_ebpf) - bpf_prog_put(cfg.filter); - else - bpf_prog_destroy(cfg.filter); - - kfree(cfg.bpf_ops); - kfree(cfg.bpf_name); - + tcf_bpf_cfg_cleanup(&cfg); return ret; } static void tcf_bpf_cleanup(struct tc_action *act, int bind) { - const struct tcf_bpf *prog = act->priv; + struct tcf_bpf_cfg tmp; - if (tcf_bpf_is_ebpf(prog)) - bpf_prog_put(prog->filter); - else - bpf_prog_destroy(prog->filter); - - kfree(prog->bpf_ops); - kfree(prog->bpf_name); + tcf_bpf_prog_fill_cfg(act->priv, &tmp); + tcf_bpf_cfg_cleanup(&tmp); } static struct tc_action_ops act_bpf_ops __read_mostly = { From 15f1bb1f1e067be7088ed43ef23d59629bd24348 Mon Sep 17 00:00:00 2001 From: Shahed Shaikh Date: Wed, 29 Jul 2015 07:55:35 -0400 Subject: [PATCH 267/428] qlcnic: Fix corruption while copying Use proper typecasting while performing byte-by-byte copy Signed-off-by: Shahed Shaikh Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c index 33669c29b341..753ea8bad953 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c @@ -1415,7 +1415,7 @@ static int qlcnic_83xx_copy_fw_file(struct qlcnic_adapter *adapter) if (fw->size & 0xF) { addr = dest + size; for (i = 0; i < (fw->size & 0xF); i++) - data[i] = temp[size + i]; + data[i] = ((u8 *)temp)[size + i]; for (; i < 16; i++) data[i] = 0; ret = qlcnic_ms_mem_write128(adapter, addr, From 55c99a4dc50fb749076592e8c66c235ca0124360 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 28 Jul 2015 16:58:47 +0200 Subject: [PATCH 268/428] iommu/amd: Use iommu_attach_group() Since the conversion to default domains the iommu_attach_device function only works for devices with their own group. But this isn't always true for current IOMMUv2 capable devices, so use iommu_attach_group instead. Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu_v2.c | 24 +++++++++++++++++++++--- 1 file changed, 21 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c index 3465faf1809e..f7b875bb70d4 100644 --- a/drivers/iommu/amd_iommu_v2.c +++ b/drivers/iommu/amd_iommu_v2.c @@ -132,11 +132,19 @@ static struct device_state *get_device_state(u16 devid) static void free_device_state(struct device_state *dev_state) { + struct iommu_group *group; + /* * First detach device from domain - No more PRI requests will arrive * from that device after it is unbound from the IOMMUv2 domain. */ - iommu_detach_device(dev_state->domain, &dev_state->pdev->dev); + group = iommu_group_get(&dev_state->pdev->dev); + if (WARN_ON(!group)) + return; + + iommu_detach_group(dev_state->domain, group); + + iommu_group_put(group); /* Everything is down now, free the IOMMUv2 domain */ iommu_domain_free(dev_state->domain); @@ -731,6 +739,7 @@ EXPORT_SYMBOL(amd_iommu_unbind_pasid); int amd_iommu_init_device(struct pci_dev *pdev, int pasids) { struct device_state *dev_state; + struct iommu_group *group; unsigned long flags; int ret, tmp; u16 devid; @@ -776,10 +785,16 @@ int amd_iommu_init_device(struct pci_dev *pdev, int pasids) if (ret) goto out_free_domain; - ret = iommu_attach_device(dev_state->domain, &pdev->dev); - if (ret != 0) + group = iommu_group_get(&pdev->dev); + if (!group) goto out_free_domain; + ret = iommu_attach_group(dev_state->domain, group); + if (ret != 0) + goto out_drop_group; + + iommu_group_put(group); + spin_lock_irqsave(&state_lock, flags); if (__get_device_state(devid) != NULL) { @@ -794,6 +809,9 @@ int amd_iommu_init_device(struct pci_dev *pdev, int pasids) return 0; +out_drop_group: + iommu_group_put(group); + out_free_domain: iommu_domain_free(dev_state->domain); From 1e6a7b04c033fe76ec7fe746ef6a3b22ab9502b2 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 28 Jul 2015 16:58:48 +0200 Subject: [PATCH 269/428] iommu/amd: Use iommu core for passthrough mode Remove the AMD IOMMU driver implementation for passthrough mode and rely on the new iommu core features for that. Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 58 ++-------------------------------- drivers/iommu/amd_iommu_init.c | 10 +----- 2 files changed, 3 insertions(+), 65 deletions(-) diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index a57e9b749895..89e6d4b2cdb6 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -76,8 +76,6 @@ LIST_HEAD(hpet_map); * Domain for untranslated devices - only allocated * if iommu=pt passed on kernel cmd line. */ -static struct protection_domain *pt_domain; - static const struct iommu_ops amd_iommu_ops; static ATOMIC_NOTIFIER_HEAD(ppr_notifier); @@ -96,7 +94,7 @@ struct iommu_dev_data { struct protection_domain *domain; /* Domain the device is bound to */ u16 devid; /* PCI Device ID */ bool iommu_v2; /* Device can make use of IOMMUv2 */ - bool passthrough; /* Default for device is pt_domain */ + bool passthrough; /* Device is identity mapped */ struct { bool enabled; int qdep; @@ -116,7 +114,6 @@ struct iommu_cmd { struct kmem_cache *amd_iommu_irq_cache; static void update_domain(struct protection_domain *domain); -static int alloc_passthrough_domain(void); static int protection_domain_init(struct protection_domain *domain); /**************************************************************************** @@ -2221,15 +2218,6 @@ static void __detach_device(struct iommu_dev_data *dev_data) do_detach(head); spin_unlock_irqrestore(&domain->lock, flags); - - /* - * If we run in passthrough mode the device must be assigned to the - * passthrough domain if it is detached from any other domain. - * Make sure we can deassign from the pt_domain itself. - */ - if (dev_data->passthrough && - (dev_data->domain == NULL && domain != pt_domain)) - __attach_device(dev_data, pt_domain); } /* @@ -2287,7 +2275,7 @@ static int amd_iommu_add_device(struct device *dev) BUG_ON(!dev_data); - if (dev_data->iommu_v2) + if (iommu_pass_through || dev_data->iommu_v2) iommu_request_dm_for_dev(dev); /* Domains are initialized for this device - have a look what we ended up with */ @@ -2947,21 +2935,6 @@ out_err: return NULL; } -static int alloc_passthrough_domain(void) -{ - if (pt_domain != NULL) - return 0; - - /* allocate passthrough domain */ - pt_domain = protection_domain_alloc(); - if (!pt_domain) - return -ENOMEM; - - pt_domain->mode = PAGE_MODE_NONE; - - return 0; -} - static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) { struct protection_domain *pdomain; @@ -3222,33 +3195,6 @@ static const struct iommu_ops amd_iommu_ops = { * *****************************************************************************/ -int __init amd_iommu_init_passthrough(void) -{ - struct iommu_dev_data *dev_data; - struct pci_dev *dev = NULL; - int ret; - - ret = alloc_passthrough_domain(); - if (ret) - return ret; - - for_each_pci_dev(dev) { - if (!check_device(&dev->dev)) - continue; - - dev_data = get_dev_data(&dev->dev); - dev_data->passthrough = true; - - attach_device(&dev->dev, pt_domain); - } - - amd_iommu_stats_init(); - - pr_info("AMD-Vi: Initialized for Passthrough Mode\n"); - - return 0; -} - /* IOMMUv2 specific functions */ int amd_iommu_register_ppr_notifier(struct notifier_block *nb) { diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index dbda9ae68c5d..a24495eb4e26 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -2026,14 +2026,6 @@ static bool detect_ivrs(void) return true; } -static int amd_iommu_init_dma(void) -{ - if (iommu_pass_through) - return amd_iommu_init_passthrough(); - else - return amd_iommu_init_dma_ops(); -} - /**************************************************************************** * * AMD IOMMU Initialization State Machine @@ -2073,7 +2065,7 @@ static int __init state_next(void) init_state = ret ? IOMMU_INIT_ERROR : IOMMU_INTERRUPTS_EN; break; case IOMMU_INTERRUPTS_EN: - ret = amd_iommu_init_dma(); + ret = amd_iommu_init_dma_ops(); init_state = ret ? IOMMU_INIT_ERROR : IOMMU_DMA_OPS; break; case IOMMU_DMA_OPS: From 02ca20212f0dde5c90be8de19cc159726b5561aa Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 28 Jul 2015 16:58:49 +0200 Subject: [PATCH 270/428] iommu/amd: Allow non-IOMMUv2 devices in IOMMUv2 domains Since devices with IOMMUv2 functionality might be in the same group as devices without it, allow those devices in IOMMUv2 domains too. Otherwise attaching the group with the IOMMUv2 device to the domain will fail. Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 89e6d4b2cdb6..6d3dae962867 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -2164,15 +2164,17 @@ static int attach_device(struct device *dev, dev_data = get_dev_data(dev); if (domain->flags & PD_IOMMUV2_MASK) { - if (!dev_data->iommu_v2 || !dev_data->passthrough) + if (!dev_data->passthrough) return -EINVAL; - if (pdev_iommuv2_enable(pdev) != 0) - return -EINVAL; + if (dev_data->iommu_v2) { + if (pdev_iommuv2_enable(pdev) != 0) + return -EINVAL; - dev_data->ats.enabled = true; - dev_data->ats.qdep = pci_ats_queue_depth(pdev); - dev_data->pri_tlp = pci_pri_tlp_required(pdev); + dev_data->ats.enabled = true; + dev_data->ats.qdep = pci_ats_queue_depth(pdev); + dev_data->pri_tlp = pci_pri_tlp_required(pdev); + } } else if (amd_iommu_iotlb_sup && pci_enable_ats(pdev, PAGE_SHIFT) == 0) { dev_data->ats.enabled = true; @@ -2237,7 +2239,7 @@ static void detach_device(struct device *dev) __detach_device(dev_data); write_unlock_irqrestore(&amd_iommu_devtable_lock, flags); - if (domain->flags & PD_IOMMUV2_MASK) + if (domain->flags & PD_IOMMUV2_MASK && dev_data->iommu_v2) pdev_iommuv2_disable(to_pci_dev(dev)); else if (dev_data->ats.enabled) pci_disable_ats(to_pci_dev(dev)); From 323023245771589c53869396e3297c703d347852 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 28 Jul 2015 16:58:50 +0200 Subject: [PATCH 271/428] iommu/amd: Use swiotlb in passthrough mode In passthrough mode (iommu=pt) all devices are identity mapped. If a device does not support 64bit DMA it might still need remapping. Make sure swiotlb is initialized to provide this remapping. Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 6d3dae962867..e29baa6c64e3 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -2282,12 +2282,10 @@ static int amd_iommu_add_device(struct device *dev) /* Domains are initialized for this device - have a look what we ended up with */ domain = iommu_get_domain_for_dev(dev); - if (domain->type == IOMMU_DOMAIN_IDENTITY) { + if (domain->type == IOMMU_DOMAIN_IDENTITY) dev_data->passthrough = true; - dev->archdata.dma_ops = &nommu_dma_ops; - } else { + else dev->archdata.dma_ops = &amd_iommu_dma_ops; - } out: iommu_completion_wait(iommu); @@ -2852,8 +2850,8 @@ int __init amd_iommu_init_api(void) int __init amd_iommu_init_dma_ops(void) { + swiotlb = iommu_pass_through ? 1 : 0; iommu_detected = 1; - swiotlb = 0; amd_iommu_stats_init(); From 52717828356b643a1650fca845b4af488a954cca Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 28 Jul 2015 16:58:51 +0200 Subject: [PATCH 272/428] iommu/amd: Set global dma_ops if swiotlb is disabled Some AMD systems also have non-PCI devices which can do DMA. Those can't be handled by the AMD IOMMU, as the hardware can only handle PCI. These devices would end up with no dma_ops, as neither the per-device nor the global dma_ops will get set. SWIOTLB provides global dma_ops when it is active, so make sure there are global dma_ops too when swiotlb is disabled. Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index e29baa6c64e3..fa9508bb76dd 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -2853,6 +2853,15 @@ int __init amd_iommu_init_dma_ops(void) swiotlb = iommu_pass_through ? 1 : 0; iommu_detected = 1; + /* + * In case we don't initialize SWIOTLB (actually the common case + * when AMD IOMMU is enabled), make sure there are global + * dma_ops set as a fall-back for devices not handled by this + * driver (for example non-PCI devices). + */ + if (!swiotlb) + dma_ops = &nommu_dma_ops; + amd_iommu_stats_init(); if (amd_iommu_unmap_flush) From b8d65e9662b1ffb3b52a65fd11b0b968022dc6a1 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Thu, 30 Jul 2015 16:53:54 +1000 Subject: [PATCH 273/428] powerpc/eeh-powernv: Fix unbalanced IRQ warning pnv_eeh_next_error() re-enables the eeh opal event interrupt but it gets called from a loop if there are more outstanding events to process, resulting in a warning due to enabling an already enabled interrupt. Instead the interrupt should only be re-enabled once the last outstanding event has been processed. Tested-by: Daniel Axtens Reported-by: Daniel Axtens Signed-off-by: Alistair Popple Acked-by: Gavin Shan Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/powernv/eeh-powernv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index 5cf5e6ea213b..7cf0df859d05 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -1478,7 +1478,7 @@ static int pnv_eeh_next_error(struct eeh_pe **pe) } /* Unmask the event */ - if (eeh_enabled()) + if (ret == EEH_NEXT_ERR_NONE && eeh_enabled()) enable_irq(eeh_event_irq); return ret; From 586b7ccdb7143b6a9b975d2c6ad52b6ca5c162b9 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 28 Jul 2015 15:03:05 +0200 Subject: [PATCH 274/428] KVM: s390: Fix hang VCPU hang/loop regression commit 785dbef407d8 ("KVM: s390: optimize round trip time in request handling") introduced a regression. This regression was seen with CPU hotplug in the guest and switching between 1 or 2 CPUs. This will set/reset the IBS control via synced request. Whenever we make a synced request, we first set the vcpu->requests bit and then block the vcpu. The handler, on the other hand, unblocks itself, processes vcpu->requests (by clearing them) and unblocks itself once again. Now, if the requester sleeps between setting of vcpu->requests and blocking, the handler will clear the vcpu->requests bit and try to unblock itself (although no bit is set). When the requester wakes up, it blocks the VCPU and we have a blocked VCPU without requests. Solution is to always unset the block bit. Signed-off-by: Christian Borntraeger Reviewed-by: David Hildenbrand Fixes: 785dbef407d8 ("KVM: s390: optimize round trip time in request handling") --- arch/s390/kvm/kvm-s390.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 2078f92d15ac..f32f843a3631 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1742,10 +1742,10 @@ static bool ibs_enabled(struct kvm_vcpu *vcpu) static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu) { - if (!vcpu->requests) - return 0; retry: kvm_s390_vcpu_request_handled(vcpu); + if (!vcpu->requests) + return 0; /* * We use MMU_RELOAD just to re-arm the ipte notifier for the * guest prefix page. gmap_ipte_notify will wait on the ptl lock. From d0e30adc42d979e4adc36b6c112b57337423b70c Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 29 Jul 2015 20:02:48 +0100 Subject: [PATCH 275/428] drm/i915: Mark PIN_USER binding as GLOBAL_BIND without the aliasing ppgtt If the device does not support the aliasing ppgtt, we must translate user bind requests (PIN_USER) from LOCAL_BIND to a GLOBAL_BIND. However, since this is device specific we cannot do this conveniently in the upper layers and so must manage the vma->bound flags in the backend. Partial revert of commit 75d04a3773ecee617847de963ae4195d6aa74c28 [4.2-rc1] Author: Mika Kuoppala Date: Tue Apr 28 17:56:17 2015 +0300 drm/i915/gtt: Allocate va range only if vma is not bound Note this was spotted by Daniel originally, but we dropped the ball in getting the fix in before the bug going wild. Sorry all. Reported-by: Vincent Legoll vincent.legoll@gmail.com Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=91133 References: https://bugs.freedesktop.org/show_bug.cgi?id=90224 Signed-off-by: Chris Wilson Cc: Michel Thierry Cc: Daniel Vetter Cc: Mika Kuoppala Cc: Jani Nikula Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_gem_gtt.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 56b52a4767d4..31e8269e6e3d 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -1923,6 +1923,17 @@ static int ggtt_bind_vma(struct i915_vma *vma, vma->vm->insert_entries(vma->vm, pages, vma->node.start, cache_level, pte_flags); + + /* Note the inconsistency here is due to absence of the + * aliasing ppgtt on gen4 and earlier. Though we always + * request PIN_USER for execbuffer (translated to LOCAL_BIND), + * without the appgtt, we cannot honour that request and so + * must substitute it with a global binding. Since we do this + * behind the upper layers back, we need to explicitly set + * the bound flag ourselves. + */ + vma->bound |= GLOBAL_BIND; + } if (dev_priv->mm.aliasing_ppgtt && flags & LOCAL_BIND) { From 5eb3e5a5e11d14f9deb2a4b83555443b69ab9940 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Sun, 28 Jun 2015 09:19:26 +0100 Subject: [PATCH 276/428] drm/i915: Declare the swizzling unknown for L-shaped configurations The old style of memory interleaving swizzled upto the end of the first even bank of memory, and then used the remainder as unswizzled on the unpaired bank - i.e. swizzling is not constant for all memory. This causes problems when we try to migrate memory and so the kernel prevents migration at all when we detect L-shaped inconsistent swizzling. However, this issue also extends to userspace who try to manually detile into memory as the swizzling for an individual page is unknown (it depends on its physical address only known to the kernel), userspace cannot correctly swizzle. Note that this is a new attempt for the previously merged one, reverted in commit d82c0ba6e306f079407f07003e53c262d683397b Author: Daniel Vetter Date: Tue Jul 14 12:29:27 2015 +0200 Revert "drm/i915: Declare the swizzling unknown for L-shaped configurations" This is cc: stable since we need it to fix up troubles with wc cpu mmaps that userspace recently started to use widely. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=91105 Signed-off-by: Chris Wilson Cc: Daniel Vetter Cc: stable@vger.kernel.org [danvet: Add note about previous (failed attempt).] Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_gem_tiling.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c index 633bd1fcab69..d19c9db5e18c 100644 --- a/drivers/gpu/drm/i915/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/i915_gem_tiling.c @@ -464,7 +464,10 @@ i915_gem_get_tiling(struct drm_device *dev, void *data, } /* Hide bit 17 from the user -- see comment in i915_gem_set_tiling */ - args->phys_swizzle_mode = args->swizzle_mode; + if (dev_priv->quirks & QUIRK_PIN_SWIZZLED_PAGES) + args->phys_swizzle_mode = I915_BIT_6_SWIZZLE_UNKNOWN; + else + args->phys_swizzle_mode = args->swizzle_mode; if (args->swizzle_mode == I915_BIT_6_SWIZZLE_9_17) args->swizzle_mode = I915_BIT_6_SWIZZLE_9; if (args->swizzle_mode == I915_BIT_6_SWIZZLE_9_10_17) From 7cc03e48965453b5df1cce5062c826189b04b960 Mon Sep 17 00:00:00 2001 From: Dmitry Skorodumov Date: Tue, 28 Jul 2015 18:38:32 +0400 Subject: [PATCH 277/428] x86/efi: Use all 64 bit of efi_memmap in setup_e820() The efi_info structure stores low 32 bits of memory map in efi_memmap and high 32 bits in efi_memmap_hi. While constructing pointer in the setup_e820(), need to take into account all 64 bit of the pointer. It is because on 64bit machine the function efi_get_memory_map() may return full 64bit pointer and before the patch that pointer was truncated. The issue is triggered on Parallles virtual machine and fixed with this patch. Signed-off-by: Dmitry Skorodumov Cc: Denis V. Lunev Cc: Signed-off-by: Matt Fleming --- arch/x86/boot/compressed/eboot.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 2c82bd150d43..7d69afd8b6fa 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -1193,6 +1193,10 @@ static efi_status_t setup_e820(struct boot_params *params, unsigned int e820_type = 0; unsigned long m = efi->efi_memmap; +#ifdef CONFIG_X86_64 + m |= (u64)efi->efi_memmap_hi << 32; +#endif + d = (efi_memory_desc_t *)(m + (i * efi->efi_memdesc_size)); switch (d->type) { case EFI_RESERVED_TYPE: From 9115c7589b11349a1c3099758b4bded579ff69e0 Mon Sep 17 00:00:00 2001 From: Ricardo Neri Date: Wed, 15 Jul 2015 19:36:03 -0700 Subject: [PATCH 278/428] efi: Check for NULL efi kernel parameters Even though it is documented how to specifiy efi parameters, it is possible to cause a kernel panic due to a dereference of a NULL pointer when parsing such parameters if "efi" alone is given: PANIC: early exception 0e rip 10:ffffffff812fb361 error 0 cr2 0 [ 0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 4.2.0-rc1+ #450 [ 0.000000] ffffffff81fe20a9 ffffffff81e03d50 ffffffff8184bb0f 00000000000003f8 [ 0.000000] 0000000000000000 ffffffff81e03e08 ffffffff81f371a1 64656c62616e6520 [ 0.000000] 0000000000000069 000000000000005f 0000000000000000 0000000000000000 [ 0.000000] Call Trace: [ 0.000000] [] dump_stack+0x45/0x57 [ 0.000000] [] early_idt_handler_common+0x81/0xae [ 0.000000] [] ? parse_option_str+0x11/0x90 [ 0.000000] [] arch_parse_efi_cmdline+0x15/0x42 [ 0.000000] [] do_early_param+0x50/0x8a [ 0.000000] [] parse_args+0x1e3/0x400 [ 0.000000] [] parse_early_options+0x24/0x28 [ 0.000000] [] ? loglevel+0x31/0x31 [ 0.000000] [] parse_early_param+0x31/0x3d [ 0.000000] [] setup_arch+0x2de/0xc08 [ 0.000000] [] ? vprintk_default+0x1a/0x20 [ 0.000000] [] start_kernel+0x90/0x423 [ 0.000000] [] x86_64_start_reservations+0x2a/0x2c [ 0.000000] [] x86_64_start_kernel+0xeb/0xef [ 0.000000] RIP 0xffffffff81ba2efc This panic is not reproducible with "efi=" as this will result in a non-NULL zero-length string. Thus, verify that the pointer to the parameter string is not NULL. This is consistent with other parameter-parsing functions which check for NULL pointers. Signed-off-by: Ricardo Neri Cc: Dave Young Cc: Signed-off-by: Matt Fleming --- arch/x86/platform/efi/efi.c | 5 +++++ drivers/firmware/efi/efi.c | 5 +++++ 2 files changed, 10 insertions(+) diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index cfba30f27392..e4308fe6afe8 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -972,6 +972,11 @@ u64 efi_mem_attributes(unsigned long phys_addr) static int __init arch_parse_efi_cmdline(char *str) { + if (!str) { + pr_warn("need at least one option\n"); + return -EINVAL; + } + if (parse_option_str(str, "old_map")) set_bit(EFI_OLD_MEMMAP, &efi.flags); if (parse_option_str(str, "debug")) diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 9fa8084a7c8d..d6144e3b97c5 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -58,6 +58,11 @@ bool efi_runtime_disabled(void) static int __init parse_efi_cmdline(char *str) { + if (!str) { + pr_warn("need at least one option\n"); + return -EINVAL; + } + if (parse_option_str(str, "noruntime")) disable_runtime = true; From 36b8e180e1e929e00b351c3b72aab3147fc14116 Mon Sep 17 00:00:00 2001 From: Brian King Date: Tue, 14 Jul 2015 11:41:29 -0500 Subject: [PATCH 279/428] ipr: Fix locking for unit attention handling Make sure we have the host lock held when calling scsi_report_bus_reset. Fixes a crash seen as the __devices list in the scsi host was changing as we were iterating through it. Cc: Reviewed-by: Wen Xiong Reviewed-by: Gabriel Krisman Bertazi Signed-off-by: Brian King Reviewed-by: Martin K. Petersen Signed-off-by: James Bottomley --- drivers/scsi/ipr.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 882744852aac..486ffaf5109a 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -6263,21 +6263,23 @@ static void ipr_scsi_done(struct ipr_cmnd *ipr_cmd) struct ipr_ioa_cfg *ioa_cfg = ipr_cmd->ioa_cfg; struct scsi_cmnd *scsi_cmd = ipr_cmd->scsi_cmd; u32 ioasc = be32_to_cpu(ipr_cmd->s.ioasa.hdr.ioasc); - unsigned long hrrq_flags; + unsigned long lock_flags; scsi_set_resid(scsi_cmd, be32_to_cpu(ipr_cmd->s.ioasa.hdr.residual_data_len)); if (likely(IPR_IOASC_SENSE_KEY(ioasc) == 0)) { scsi_dma_unmap(scsi_cmd); - spin_lock_irqsave(ipr_cmd->hrrq->lock, hrrq_flags); + spin_lock_irqsave(ipr_cmd->hrrq->lock, lock_flags); list_add_tail(&ipr_cmd->queue, &ipr_cmd->hrrq->hrrq_free_q); scsi_cmd->scsi_done(scsi_cmd); - spin_unlock_irqrestore(ipr_cmd->hrrq->lock, hrrq_flags); + spin_unlock_irqrestore(ipr_cmd->hrrq->lock, lock_flags); } else { - spin_lock_irqsave(ipr_cmd->hrrq->lock, hrrq_flags); + spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags); + spin_lock(&ipr_cmd->hrrq->_lock); ipr_erp_start(ioa_cfg, ipr_cmd); - spin_unlock_irqrestore(ipr_cmd->hrrq->lock, hrrq_flags); + spin_unlock(&ipr_cmd->hrrq->_lock); + spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); } } From bb7c54339e6a10ecce5c4961adf5e75b3cf0af30 Mon Sep 17 00:00:00 2001 From: Brian King Date: Tue, 14 Jul 2015 11:41:31 -0500 Subject: [PATCH 280/428] ipr: Fix incorrect trace indexing When ipr's internal driver trace was changed to an atomic, a signed/unsigned bug slipped in which results in us indexing backwards in our memory buffer writing on memory that does not belong to us. This patch fixes this by removing the modulo and instead just mask off the low bits. Cc: Tested-by: Wen Xiong Reviewed-by: Wen Xiong Reviewed-by: Gabriel Krisman Bertazi Signed-off-by: Brian King Reviewed-by: Martin K. Petersen Signed-off-by: James Bottomley --- drivers/scsi/ipr.c | 5 +++-- drivers/scsi/ipr.h | 1 + 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 486ffaf5109a..7ae9cd743eb2 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -599,9 +599,10 @@ static void ipr_trc_hook(struct ipr_cmnd *ipr_cmd, { struct ipr_trace_entry *trace_entry; struct ipr_ioa_cfg *ioa_cfg = ipr_cmd->ioa_cfg; + unsigned int trace_index; - trace_entry = &ioa_cfg->trace[atomic_add_return - (1, &ioa_cfg->trace_index)%IPR_NUM_TRACE_ENTRIES]; + trace_index = atomic_add_return(1, &ioa_cfg->trace_index) & IPR_TRACE_INDEX_MASK; + trace_entry = &ioa_cfg->trace[trace_index]; trace_entry->time = jiffies; trace_entry->op_code = ipr_cmd->ioarcb.cmd_pkt.cdb[0]; trace_entry->type = type; diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h index 73790a1d0969..6b97ee45c7b4 100644 --- a/drivers/scsi/ipr.h +++ b/drivers/scsi/ipr.h @@ -1486,6 +1486,7 @@ struct ipr_ioa_cfg { #define IPR_NUM_TRACE_INDEX_BITS 8 #define IPR_NUM_TRACE_ENTRIES (1 << IPR_NUM_TRACE_INDEX_BITS) +#define IPR_TRACE_INDEX_MASK (IPR_NUM_TRACE_ENTRIES - 1) #define IPR_TRACE_SIZE (sizeof(struct ipr_trace_entry) * IPR_NUM_TRACE_ENTRIES) char trace_start[8]; #define IPR_TRACE_START_LABEL "trace" From 3f1c0581310d5d94bd72740231507e763a6252a4 Mon Sep 17 00:00:00 2001 From: Brian King Date: Tue, 14 Jul 2015 11:41:33 -0500 Subject: [PATCH 281/428] ipr: Fix invalid array indexing for HRRQ Fixes another signed / unsigned array indexing bug in the ipr driver. Currently, when hrrq_index wraps, it becomes a negative number. We do the modulo, but still have a negative number, so we end up indexing backwards in the array. Given where the hrrq array is located in memory, we probably won't actually reference memory we don't own, but nonetheless ipr is still looking at data within struct ipr_ioa_cfg and interpreting it as struct ipr_hrr_queue data, so bad things could certainly happen. Each ipr adapter has anywhere from 1 to 16 HRRQs. By default, we use 2 on new adapters. Let's take an example: Assume ioa_cfg->hrrq_index=0x7fffffffe and ioa_cfg->hrrq_num=4: The atomic_add_return will then return -1. We mod this with 3 and get -2, add one and get -1 for an array index. On adapters which support more than a single HRRQ, we dedicate HRRQ to adapter initialization and error interrupts so that we can optimize the other queues for fast path I/O. So all normal I/O uses HRRQ 1-15. So we want to spread the I/O requests across those HRRQs. With the default module parameter settings, this bug won't hit, only when someone sets the ipr.number_of_msix parameter to a value larger than 3 is when bad things start to happen. Cc: Tested-by: Wen Xiong Reviewed-by: Wen Xiong Reviewed-by: Gabriel Krisman Bertazi Signed-off-by: Brian King Reviewed-by: Martin K. Petersen Signed-off-by: James Bottomley --- drivers/scsi/ipr.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 7ae9cd743eb2..a9aa38903efe 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -1052,10 +1052,15 @@ static void ipr_send_blocking_cmd(struct ipr_cmnd *ipr_cmd, static int ipr_get_hrrq_index(struct ipr_ioa_cfg *ioa_cfg) { + unsigned int hrrq; + if (ioa_cfg->hrrq_num == 1) - return 0; - else - return (atomic_add_return(1, &ioa_cfg->hrrq_index) % (ioa_cfg->hrrq_num - 1)) + 1; + hrrq = 0; + else { + hrrq = atomic_add_return(1, &ioa_cfg->hrrq_index); + hrrq = (hrrq % (ioa_cfg->hrrq_num - 1)) + 1; + } + return hrrq; } /** From 0c958ecc69c277b25f38f72bc6d18ab145e8167c Mon Sep 17 00:00:00 2001 From: Tony Battersby Date: Thu, 16 Jul 2015 11:40:41 -0400 Subject: [PATCH 282/428] scsi: fix memory leak with scsi-mq Fix a memory leak with scsi-mq triggered by commands with large data transfer length. __sg_alloc_table() sets both table->nents and table->orig_nents to the same value. When the scatterlist is DMA-mapped, table->nents is overwritten with the (possibly smaller) size of the DMA-mapped scatterlist, while table->orig_nents retains the original size of the allocated scatterlist. scsi_free_sgtable() should therefore check orig_nents instead of nents, and all code that initializes sdb->table without calling __sg_alloc_table() should set both nents and orig_nents. Fixes: d285203cf647 ("scsi: add support for a blk-mq based I/O path.") Cc: # 3.17+ Signed-off-by: Tony Battersby Reviewed-by: Christoph Hellwig Reviewed-by: Ewan D. Milne Signed-off-by: James Bottomley --- drivers/scsi/scsi_error.c | 2 +- drivers/scsi/scsi_lib.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 106884a5444e..cfadccef045c 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -944,7 +944,7 @@ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses, scmd->sdb.length); scmd->sdb.table.sgl = &ses->sense_sgl; scmd->sc_data_direction = DMA_FROM_DEVICE; - scmd->sdb.table.nents = 1; + scmd->sdb.table.nents = scmd->sdb.table.orig_nents = 1; scmd->cmnd[0] = REQUEST_SENSE; scmd->cmnd[4] = scmd->sdb.length; scmd->cmd_len = COMMAND_SIZE(scmd->cmnd[0]); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index b1a263137a23..448ebdaa3d69 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -583,7 +583,7 @@ static struct scatterlist *scsi_sg_alloc(unsigned int nents, gfp_t gfp_mask) static void scsi_free_sgtable(struct scsi_data_buffer *sdb, bool mq) { - if (mq && sdb->table.nents <= SCSI_MAX_SG_SEGMENTS) + if (mq && sdb->table.orig_nents <= SCSI_MAX_SG_SEGMENTS) return; __sg_free_table(&sdb->table, SCSI_MAX_SG_SEGMENTS, mq, scsi_sg_free); } @@ -597,8 +597,8 @@ static int scsi_alloc_sgtable(struct scsi_data_buffer *sdb, int nents, bool mq) if (mq) { if (nents <= SCSI_MAX_SG_SEGMENTS) { - sdb->table.nents = nents; - sg_init_table(sdb->table.sgl, sdb->table.nents); + sdb->table.nents = sdb->table.orig_nents = nents; + sg_init_table(sdb->table.sgl, nents); return 0; } first_chunk = sdb->table.sgl; From 646c4b75494747887f936513b669bb8a2d794459 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Thu, 30 Jul 2015 15:51:32 +0800 Subject: [PATCH 283/428] x86/irq: Use the caller provided polarity setting in mp_check_pin_attr() Commit d32932d02e18 ("x86/irq: Convert IOAPIC to use hierarchical irqdomain interfaces") introduced a regression which causes malfunction of interrupt lines. The reason is that the conversion of mp_check_pin_attr() missed to update the polarity selection of the interrupt pin with the caller provided setting and instead uses a stale attribute value. That in turn results in chosing the wrong interrupt flow handler. Use the caller supplied setting to configure the pin correctly which also choses the correct interrupt flow handler. This restores the original behaviour and on the affected machine/driver (Surface Pro 3, i2c controller) all IOAPIC IRQ configuration are identical to v4.1. Fixes: d32932d02e18 ("x86/irq: Convert IOAPIC to use hierarchical irqdomain interfaces") Reported-and-tested-by: Matt Fleming Reported-and-tested-by: Chen Yu Signed-off-by: Jiang Liu Cc: Tony Luck Cc: Chen Yu Cc: Yinghai Lu Link: http://lkml.kernel.org/r/1438242695-23531-1-git-send-email-jiang.liu@linux.intel.com Signed-off-by: Thomas Gleixner --- arch/x86/kernel/apic/io_apic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 845dc0df2002..206052e55517 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -943,7 +943,7 @@ static bool mp_check_pin_attr(int irq, struct irq_alloc_info *info) */ if (irq < nr_legacy_irqs() && data->count == 1) { if (info->ioapic_trigger != data->trigger) - mp_register_handler(irq, data->trigger); + mp_register_handler(irq, info->ioapic_trigger); data->entry.trigger = data->trigger = info->ioapic_trigger; data->entry.polarity = data->polarity = info->ioapic_polarity; } From 54d9ffc416022cf82649fe5665875d8962dfac41 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 30 Jul 2015 12:38:06 +0200 Subject: [PATCH 284/428] MAINTAINERS: Appoint Marc Zyngier as irqchips co-maintainer Signed-off-by: Thomas Gleixner Acked-by: Jason Cooper Cc: Marc Zyngier --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 9289ecb57b68..577be68aa8ba 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5600,6 +5600,7 @@ F: kernel/irq/ IRQCHIP DRIVERS M: Thomas Gleixner M: Jason Cooper +M: Marc Zyngier L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core From b09dec2c77dc0ef0bb43ade1628ab4b390e74c6d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 30 Jul 2015 12:40:55 +0200 Subject: [PATCH 285/428] MAINTAINERS: Appoint Jiang and Marc as irqdomain maintainers Ben was pretty surprised that he is still listed as the maintainer and he has no objections against transferring the duty to those who rumaged in and revamped that code in the recent past. Add kernel/irq/msi.c to the affected files as it's part of the shiny new hierarchical irqdomain machinery. Signed-off-by: Thomas Gleixner Acked-by: Benjamin Herrenschmidt Cc: Jiang Liu Cc: Marc Zyngier Cc: Grant Likely --- MAINTAINERS | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 577be68aa8ba..a9ae6c105520 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5609,11 +5609,14 @@ F: Documentation/devicetree/bindings/interrupt-controller/ F: drivers/irqchip/ IRQ DOMAINS (IRQ NUMBER MAPPING LIBRARY) -M: Benjamin Herrenschmidt +M: Jiang Liu +M: Marc Zyngier S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core F: Documentation/IRQ-domain.txt F: include/linux/irqdomain.h F: kernel/irq/irqdomain.c +F: kernel/irq/msi.c ISAPNP M: Jaroslav Kysela From 649ccd08534ee26deb2e5b08509800d0e95167f5 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 30 Jul 2015 22:30:29 +0200 Subject: [PATCH 286/428] ALSA: hda - Fix MacBook Pro 5,2 quirk MacBook Pro 5,2 with ALC889 codec had already a fixup entry, but this seems not working correctly, a fix for pin NID 0x15 is needed in addition. It's equivalent with the fixup for MacBook Air 1,1, so use this instead. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=102131 Reported-and-tested-by: Jeffery Miller Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 18ae17ebb356..c456c04e0928 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2222,7 +2222,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x106b, 0x4300, "iMac 9,1", ALC889_FIXUP_IMAC91_VREF), SND_PCI_QUIRK(0x106b, 0x4600, "MacbookPro 5,2", ALC889_FIXUP_IMAC91_VREF), SND_PCI_QUIRK(0x106b, 0x4900, "iMac 9,1 Aluminum", ALC889_FIXUP_IMAC91_VREF), - SND_PCI_QUIRK(0x106b, 0x4a00, "Macbook 5,2", ALC889_FIXUP_IMAC91_VREF), + SND_PCI_QUIRK(0x106b, 0x4a00, "Macbook 5,2", ALC889_FIXUP_MBA11_VREF), SND_PCI_QUIRK(0x1071, 0x8258, "Evesham Voyaeger", ALC882_FIXUP_EAPD), SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD), From e501139a515018f913761d3bf4239313c87e721c Mon Sep 17 00:00:00 2001 From: hayeswang Date: Wed, 29 Jul 2015 20:39:08 +0800 Subject: [PATCH 287/428] r8152: add pre_reset and post_reset Add rtl8152_pre_reset() and rtl8152_post_reset() which are used when calling usb_reset_device(). The two functions could reduce the time of reset when calling usb_reset_device() after probe(). Signed-off-by: Hayes Wang Signed-off-by: David S. Miller --- drivers/net/usb/r8152.c | 54 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 144dc641c239..e1b6d6d67768 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -3342,6 +3342,58 @@ static void r8153_init(struct r8152 *tp) r8153_u2p3en(tp, true); } +static int rtl8152_pre_reset(struct usb_interface *intf) +{ + struct r8152 *tp = usb_get_intfdata(intf); + struct net_device *netdev; + + if (!tp) + return 0; + + netdev = tp->netdev; + if (!netif_running(netdev)) + return 0; + + napi_disable(&tp->napi); + clear_bit(WORK_ENABLE, &tp->flags); + usb_kill_urb(tp->intr_urb); + cancel_delayed_work_sync(&tp->schedule); + if (netif_carrier_ok(netdev)) { + netif_stop_queue(netdev); + mutex_lock(&tp->control); + tp->rtl_ops.disable(tp); + mutex_unlock(&tp->control); + } + + return 0; +} + +static int rtl8152_post_reset(struct usb_interface *intf) +{ + struct r8152 *tp = usb_get_intfdata(intf); + struct net_device *netdev; + + if (!tp) + return 0; + + netdev = tp->netdev; + if (!netif_running(netdev)) + return 0; + + set_bit(WORK_ENABLE, &tp->flags); + if (netif_carrier_ok(netdev)) { + mutex_lock(&tp->control); + tp->rtl_ops.enable(tp); + rtl8152_set_rx_mode(netdev); + mutex_unlock(&tp->control); + netif_wake_queue(netdev); + } + + napi_enable(&tp->napi); + + return 0; +} + static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message) { struct r8152 *tp = usb_get_intfdata(intf); @@ -4164,6 +4216,8 @@ static struct usb_driver rtl8152_driver = { .suspend = rtl8152_suspend, .resume = rtl8152_resume, .reset_resume = rtl8152_resume, + .pre_reset = rtl8152_pre_reset, + .post_reset = rtl8152_post_reset, .supports_autosuspend = 1, .disable_hub_initiated_lpm = 1, }; From 37608f3e57dda037a230afb7dc8da9a63f100e06 Mon Sep 17 00:00:00 2001 From: hayeswang Date: Wed, 29 Jul 2015 20:39:09 +0800 Subject: [PATCH 288/428] r8152: reset device when tx timeout The device reset is necessary if the hw becomes abnormal and stops transmitting packets. Signed-off-by: Hayes Wang Signed-off-by: David S. Miller --- drivers/net/usb/r8152.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index e1b6d6d67768..ad8cbc6c9ee7 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -27,7 +27,7 @@ #include /* Version Information */ -#define DRIVER_VERSION "v1.08.0 (2015/01/13)" +#define DRIVER_VERSION "v1.08.1 (2015/07/28)" #define DRIVER_AUTHOR "Realtek linux nic maintainers " #define DRIVER_DESC "Realtek RTL8152/RTL8153 Based USB Ethernet Adapters" #define MODULENAME "r8152" @@ -1902,11 +1902,10 @@ static void rtl_drop_queued_tx(struct r8152 *tp) static void rtl8152_tx_timeout(struct net_device *netdev) { struct r8152 *tp = netdev_priv(netdev); - int i; netif_warn(tp, tx_err, netdev, "Tx timeout\n"); - for (i = 0; i < RTL8152_MAX_TX; i++) - usb_unlink_urb(tp->tx_info[i].urb); + + usb_queue_reset_device(tp->intf); } static void rtl8152_set_rx_mode(struct net_device *netdev) From 28e6b67f0b292f557468c139085303b15f1a678f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 29 Jul 2015 23:35:25 +0200 Subject: [PATCH 289/428] net: sched: fix refcount imbalance in actions Since commit 55334a5db5cd ("net_sched: act: refuse to remove bound action outside"), we end up with a wrong reference count for a tc action. Test case 1: FOO="1,6 0 0 4294967295," BAR="1,6 0 0 4294967294," tc filter add dev foo parent 1: bpf bytecode "$FOO" flowid 1:1 \ action bpf bytecode "$FOO" tc actions show action bpf action order 0: bpf bytecode '1,6 0 0 4294967295' default-action pipe index 1 ref 1 bind 1 tc actions replace action bpf bytecode "$BAR" index 1 tc actions show action bpf action order 0: bpf bytecode '1,6 0 0 4294967294' default-action pipe index 1 ref 2 bind 1 tc actions replace action bpf bytecode "$FOO" index 1 tc actions show action bpf action order 0: bpf bytecode '1,6 0 0 4294967295' default-action pipe index 1 ref 3 bind 1 Test case 2: FOO="1,6 0 0 4294967295," tc filter add dev foo parent 1: bpf bytecode "$FOO" flowid 1:1 action ok tc actions show action gact action order 0: gact action pass random type none pass val 0 index 1 ref 1 bind 1 tc actions add action drop index 1 RTNETLINK answers: File exists [...] tc actions show action gact action order 0: gact action pass random type none pass val 0 index 1 ref 2 bind 1 tc actions add action drop index 1 RTNETLINK answers: File exists [...] tc actions show action gact action order 0: gact action pass random type none pass val 0 index 1 ref 3 bind 1 What happens is that in tcf_hash_check(), we check tcf_common for a given index and increase tcfc_refcnt and conditionally tcfc_bindcnt when we've found an existing action. Now there are the following cases: 1) We do a late binding of an action. In that case, we leave the tcfc_refcnt/tcfc_bindcnt increased and are done with the ->init() handler. This is correctly handeled. 2) We replace the given action, or we try to add one without replacing and find out that the action at a specific index already exists (thus, we go out with error in that case). In case of 2), we have to undo the reference count increase from tcf_hash_check() in the tcf_hash_check() function. Currently, we fail to do so because of the 'tcfc_bindcnt > 0' check which bails out early with an -EPERM error. Now, while commit 55334a5db5cd prevents 'tc actions del action ...' on an already classifier-bound action to drop the reference count (which could then become negative, wrap around etc), this restriction only accounts for invocations outside a specific action's ->init() handler. One possible solution would be to add a flag thus we possibly trigger the -EPERM ony in situations where it is indeed relevant. After the patch, above test cases have correct reference count again. Fixes: 55334a5db5cd ("net_sched: act: refuse to remove bound action outside") Signed-off-by: Daniel Borkmann Reviewed-by: Cong Wang Signed-off-by: David S. Miller --- include/net/act_api.h | 8 +++++++- net/sched/act_api.c | 11 ++++++----- 2 files changed, 13 insertions(+), 6 deletions(-) diff --git a/include/net/act_api.h b/include/net/act_api.h index 3ee4c92afd1b..931738bc5bba 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -99,7 +99,6 @@ struct tc_action_ops { int tcf_hash_search(struct tc_action *a, u32 index); void tcf_hash_destroy(struct tc_action *a); -int tcf_hash_release(struct tc_action *a, int bind); u32 tcf_hash_new_index(struct tcf_hashinfo *hinfo); int tcf_hash_check(u32 index, struct tc_action *a, int bind); int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a, @@ -107,6 +106,13 @@ int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a, void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est); void tcf_hash_insert(struct tc_action *a); +int __tcf_hash_release(struct tc_action *a, bool bind, bool strict); + +static inline int tcf_hash_release(struct tc_action *a, bool bind) +{ + return __tcf_hash_release(a, bind, false); +} + int tcf_register_action(struct tc_action_ops *a, unsigned int mask); int tcf_unregister_action(struct tc_action_ops *a); int tcf_action_destroy(struct list_head *actions, int bind); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index af427a3dbcba..43ec92680ae8 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -45,7 +45,7 @@ void tcf_hash_destroy(struct tc_action *a) } EXPORT_SYMBOL(tcf_hash_destroy); -int tcf_hash_release(struct tc_action *a, int bind) +int __tcf_hash_release(struct tc_action *a, bool bind, bool strict) { struct tcf_common *p = a->priv; int ret = 0; @@ -53,7 +53,7 @@ int tcf_hash_release(struct tc_action *a, int bind) if (p) { if (bind) p->tcfc_bindcnt--; - else if (p->tcfc_bindcnt > 0) + else if (strict && p->tcfc_bindcnt > 0) return -EPERM; p->tcfc_refcnt--; @@ -64,9 +64,10 @@ int tcf_hash_release(struct tc_action *a, int bind) ret = 1; } } + return ret; } -EXPORT_SYMBOL(tcf_hash_release); +EXPORT_SYMBOL(__tcf_hash_release); static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb, struct tc_action *a) @@ -136,7 +137,7 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a) head = &hinfo->htab[tcf_hash(i, hinfo->hmask)]; hlist_for_each_entry_safe(p, n, head, tcfc_head) { a->priv = p; - ret = tcf_hash_release(a, 0); + ret = __tcf_hash_release(a, false, true); if (ret == ACT_P_DELETED) { module_put(a->ops->owner); n_i++; @@ -408,7 +409,7 @@ int tcf_action_destroy(struct list_head *actions, int bind) int ret = 0; list_for_each_entry_safe(a, tmp, actions, list) { - ret = tcf_hash_release(a, bind); + ret = __tcf_hash_release(a, bind, true); if (ret == ACT_P_DELETED) module_put(a->ops->owner); else if (ret < 0) From 8a68173691f036613e3d4e6bf8dc129d4a7bf383 Mon Sep 17 00:00:00 2001 From: Sowmini Varadhan Date: Thu, 30 Jul 2015 15:50:36 +0200 Subject: [PATCH 290/428] net: sk_clone_lock() should only do get_net() if the parent is not a kernel socket The newsk returned by sk_clone_lock should hold a get_net() reference if, and only if, the parent is not a kernel socket (making this similar to sk_alloc()). E.g,. for the SYN_RECV path, tcp_v4_syn_recv_sock->..inet_csk_clone_lock sets up the syn_recv newsk from sk_clone_lock. When the parent (listen) socket is a kernel socket (defined in sk_alloc() as having sk_net_refcnt == 0), then the newsk should also have a 0 sk_net_refcnt and should not hold a get_net() reference. Fixes: 26abe14379f8 ("net: Modify sk_alloc to not reference count the netns of kernel sockets.") Acked-by: Eric Dumazet Cc: Eric W. Biederman Signed-off-by: Sowmini Varadhan Signed-off-by: David S. Miller --- net/core/sock.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/core/sock.c b/net/core/sock.c index 8a14f1285fc4..193901d09757 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1497,7 +1497,8 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) sock_copy(newsk, sk); /* SANITY */ - get_net(sock_net(newsk)); + if (likely(newsk->sk_net_refcnt)) + get_net(sock_net(newsk)); sk_node_init(&newsk->sk_node); sock_lock_init(newsk); bh_lock_sock(newsk); From be052cc87745e01846fb036eb81567c784439078 Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Tue, 7 Jul 2015 16:06:15 +0300 Subject: [PATCH 291/428] extcon: Fix hang and extcon_get/set_cable_state(). Users of find_cable_index_by_name() will cause a kernel hang as the while loop counter is never incremented and end condition is never reached. extcon_get_cable_state() and extcon_set_cable_state() are broken because they use cable index instead of cable id. This causes the first cable state (cable.0) to be always invalid in sysfs or extcon_get_cable_state() users. Introduce a new function find_cable_id_by_name() that fixes both of the above issues. Fixes: commit 73b6ecdb93e8 ("extcon: Redefine the unique id of supported external connectors without 'enum extcon' type") Cc: Greg Kroah-Hartman Signed-off-by: Roger Quadros Tested-by: Ivan T. Ivanov [cw00.choi: Fix minor coding style] Signed-off-by: Chanwoo Choi --- drivers/extcon/extcon.c | 46 ++++++++++++++++++++++++++++++----------- 1 file changed, 34 insertions(+), 12 deletions(-) diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c index 76157ab9faf3..0e2af1728965 100644 --- a/drivers/extcon/extcon.c +++ b/drivers/extcon/extcon.c @@ -124,25 +124,35 @@ static int find_cable_index_by_id(struct extcon_dev *edev, const unsigned int id return -EINVAL; } -static int find_cable_index_by_name(struct extcon_dev *edev, const char *name) +static int find_cable_id_by_name(struct extcon_dev *edev, const char *name) { - unsigned int id = EXTCON_NONE; + unsigned int id = -EINVAL; int i = 0; - if (edev->max_supported == 0) - return -EINVAL; - - /* Find the the number of extcon cable */ + /* Find the id of extcon cable */ while (extcon_name[i]) { if (!strncmp(extcon_name[i], name, CABLE_NAME_MAX)) { id = i; break; } + i++; } - if (id == EXTCON_NONE) + return id; +} + +static int find_cable_index_by_name(struct extcon_dev *edev, const char *name) +{ + unsigned int id; + + if (edev->max_supported == 0) return -EINVAL; + /* Find the the number of extcon cable */ + id = find_cable_id_by_name(edev, name); + if (id < 0) + return id; + return find_cable_index_by_id(edev, id); } @@ -228,9 +238,11 @@ static ssize_t cable_state_show(struct device *dev, struct extcon_cable *cable = container_of(attr, struct extcon_cable, attr_state); + int i = cable->cable_index; + return sprintf(buf, "%d\n", extcon_get_cable_state_(cable->edev, - cable->cable_index)); + cable->edev->supported_cable[i])); } /** @@ -361,8 +373,13 @@ EXPORT_SYMBOL_GPL(extcon_get_cable_state_); */ int extcon_get_cable_state(struct extcon_dev *edev, const char *cable_name) { - return extcon_get_cable_state_(edev, find_cable_index_by_name - (edev, cable_name)); + unsigned int id; + + id = find_cable_id_by_name(edev, cable_name); + if (id < 0) + return id; + + return extcon_get_cable_state_(edev, id); } EXPORT_SYMBOL_GPL(extcon_get_cable_state); @@ -404,8 +421,13 @@ EXPORT_SYMBOL_GPL(extcon_set_cable_state_); int extcon_set_cable_state(struct extcon_dev *edev, const char *cable_name, bool cable_state) { - return extcon_set_cable_state_(edev, find_cable_index_by_name - (edev, cable_name), cable_state); + unsigned int id; + + id = find_cable_id_by_name(edev, cable_name); + if (id < 0) + return id; + + return extcon_set_cable_state_(edev, id, cable_state); } EXPORT_SYMBOL_GPL(extcon_set_cable_state); From f7a898117aebf3d52370fe637f4d7aff7a237afc Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Mon, 6 Jul 2015 17:46:58 +0300 Subject: [PATCH 292/428] extcon: Fix extcon_cable_get_state() from getting old state after notification Currently the extcon code notifiers the interested listeners before it updates the extcon state with the new state. This will cause the listeners that use extcon_cable_get_state() to get the stale state and loose the new state. Fix this by first changing the extcon state variable and then notifying listeners. Signed-off-by: Roger Quadros Tested-by: Ivan T. Ivanov Signed-off-by: Chanwoo Choi --- drivers/extcon/extcon.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c index 0e2af1728965..43b57b02d050 100644 --- a/drivers/extcon/extcon.c +++ b/drivers/extcon/extcon.c @@ -275,20 +275,25 @@ int extcon_update_state(struct extcon_dev *edev, u32 mask, u32 state) spin_lock_irqsave(&edev->lock, flags); if (edev->state != ((edev->state & ~mask) | (state & mask))) { + u32 old_state; + if (check_mutually_exclusive(edev, (edev->state & ~mask) | (state & mask))) { spin_unlock_irqrestore(&edev->lock, flags); return -EPERM; } - for (index = 0; index < edev->max_supported; index++) { - if (is_extcon_changed(edev->state, state, index, &attached)) - raw_notifier_call_chain(&edev->nh[index], attached, edev); - } - + old_state = edev->state; edev->state &= ~mask; edev->state |= state & mask; + for (index = 0; index < edev->max_supported; index++) { + if (is_extcon_changed(old_state, edev->state, index, + &attached)) + raw_notifier_call_chain(&edev->nh[index], + attached, edev); + } + /* This could be in interrupt handler */ prop_buf = (char *)get_zeroed_page(GFP_ATOMIC); if (prop_buf) { From aa1acff356bbedfd03b544051f5b371746735d89 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 30 Jul 2015 14:31:31 -0700 Subject: [PATCH 293/428] x86/xen: Probe target addresses in set_aliased_prot() before the hypercall The update_va_mapping hypercall can fail if the VA isn't present in the guest's page tables. Under certain loads, this can result in an OOPS when the target address is in unpopulated vmap space. While we're at it, add comments to help explain what's going on. This isn't a great long-term fix. This code should probably be changed to use something like set_memory_ro. Signed-off-by: Andy Lutomirski Cc: Andrew Cooper Cc: Andy Lutomirski Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Brian Gerst Cc: David Vrabel Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Jan Beulich Cc: Konrad Rzeszutek Wilk Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Sasha Levin Cc: Steven Rostedt Cc: Thomas Gleixner Cc: security@kernel.org Cc: Cc: xen-devel Link: http://lkml.kernel.org/r/0b0e55b995cda11e7829f140b833ef932fcabe3a.1438291540.git.luto@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/xen/enlighten.c | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 0b95c9b8283f..11d6fb4e8483 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -483,6 +483,7 @@ static void set_aliased_prot(void *v, pgprot_t prot) pte_t pte; unsigned long pfn; struct page *page; + unsigned char dummy; ptep = lookup_address((unsigned long)v, &level); BUG_ON(ptep == NULL); @@ -492,6 +493,32 @@ static void set_aliased_prot(void *v, pgprot_t prot) pte = pfn_pte(pfn, prot); + /* + * Careful: update_va_mapping() will fail if the virtual address + * we're poking isn't populated in the page tables. We don't + * need to worry about the direct map (that's always in the page + * tables), but we need to be careful about vmap space. In + * particular, the top level page table can lazily propagate + * entries between processes, so if we've switched mms since we + * vmapped the target in the first place, we might not have the + * top-level page table entry populated. + * + * We disable preemption because we want the same mm active when + * we probe the target and when we issue the hypercall. We'll + * have the same nominal mm, but if we're a kernel thread, lazy + * mm dropping could change our pgd. + * + * Out of an abundance of caution, this uses __get_user() to fault + * in the target address just in case there's some obscure case + * in which the target address isn't readable. + */ + + preempt_disable(); + + pagefault_disable(); /* Avoid warnings due to being atomic. */ + __get_user(dummy, (unsigned char __user __force *)v); + pagefault_enable(); + if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0)) BUG(); @@ -503,6 +530,8 @@ static void set_aliased_prot(void *v, pgprot_t prot) BUG(); } else kmap_flush_unused(); + + preempt_enable(); } static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries) @@ -510,6 +539,17 @@ static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries) const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE; int i; + /* + * We need to mark the all aliases of the LDT pages RO. We + * don't need to call vm_flush_aliases(), though, since that's + * only responsible for flushing aliases out the TLBs, not the + * page tables, and Xen will flush the TLB for us if needed. + * + * To avoid confusing future readers: none of this is necessary + * to load the LDT. The hypervisor only checks this when the + * LDT is faulted in due to subsequent descriptor access. + */ + for(i = 0; i < entries; i += entries_per_page) set_aliased_prot(ldt + i, PAGE_KERNEL_RO); } From 37868fe113ff2ba814b3b4eb12df214df555f8dc Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 30 Jul 2015 14:31:32 -0700 Subject: [PATCH 294/428] x86/ldt: Make modify_ldt synchronous modify_ldt() has questionable locking and does not synchronize threads. Improve it: redesign the locking and synchronize all threads' LDTs using an IPI on all modifications. This will dramatically slow down modify_ldt in multithreaded programs, but there shouldn't be any multithreaded programs that care about modify_ldt's performance in the first place. This fixes some fallout from the CVE-2015-5157 fixes. Signed-off-by: Andy Lutomirski Reviewed-by: Borislav Petkov Cc: Andrew Cooper Cc: Andy Lutomirski Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Jan Beulich Cc: Konrad Rzeszutek Wilk Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Sasha Levin Cc: Steven Rostedt Cc: Thomas Gleixner Cc: security@kernel.org Cc: Cc: xen-devel Link: http://lkml.kernel.org/r/4c6978476782160600471bd865b318db34c7b628.1438291540.git.luto@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/desc.h | 15 -- arch/x86/include/asm/mmu.h | 3 +- arch/x86/include/asm/mmu_context.h | 54 +++++- arch/x86/kernel/cpu/common.c | 4 +- arch/x86/kernel/cpu/perf_event.c | 12 +- arch/x86/kernel/ldt.c | 262 ++++++++++++++++------------- arch/x86/kernel/process_64.c | 4 +- arch/x86/kernel/step.c | 6 +- arch/x86/power/cpu.c | 3 +- 9 files changed, 210 insertions(+), 153 deletions(-) diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index a0bf89fd2647..4e10d73cf018 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -280,21 +280,6 @@ static inline void clear_LDT(void) set_ldt(NULL, 0); } -/* - * load one particular LDT into the current CPU - */ -static inline void load_LDT_nolock(mm_context_t *pc) -{ - set_ldt(pc->ldt, pc->size); -} - -static inline void load_LDT(mm_context_t *pc) -{ - preempt_disable(); - load_LDT_nolock(pc); - preempt_enable(); -} - static inline unsigned long get_desc_base(const struct desc_struct *desc) { return (unsigned)(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24)); diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 09b9620a73b4..364d27481a52 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -9,8 +9,7 @@ * we put the segment information here. */ typedef struct { - void *ldt; - int size; + struct ldt_struct *ldt; #ifdef CONFIG_X86_64 /* True if mm supports a task running in 32 bit compatibility mode. */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 804a3a6030ca..984abfe47edc 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -33,6 +33,50 @@ static inline void load_mm_cr4(struct mm_struct *mm) static inline void load_mm_cr4(struct mm_struct *mm) {} #endif +/* + * ldt_structs can be allocated, used, and freed, but they are never + * modified while live. + */ +struct ldt_struct { + /* + * Xen requires page-aligned LDTs with special permissions. This is + * needed to prevent us from installing evil descriptors such as + * call gates. On native, we could merge the ldt_struct and LDT + * allocations, but it's not worth trying to optimize. + */ + struct desc_struct *entries; + int size; +}; + +static inline void load_mm_ldt(struct mm_struct *mm) +{ + struct ldt_struct *ldt; + + /* lockless_dereference synchronizes with smp_store_release */ + ldt = lockless_dereference(mm->context.ldt); + + /* + * Any change to mm->context.ldt is followed by an IPI to all + * CPUs with the mm active. The LDT will not be freed until + * after the IPI is handled by all such CPUs. This means that, + * if the ldt_struct changes before we return, the values we see + * will be safe, and the new values will be loaded before we run + * any user code. + * + * NB: don't try to convert this to use RCU without extreme care. + * We would still need IRQs off, because we don't want to change + * the local LDT after an IPI loaded a newer value than the one + * that we can see. + */ + + if (unlikely(ldt)) + set_ldt(ldt->entries, ldt->size); + else + clear_LDT(); + + DEBUG_LOCKS_WARN_ON(preemptible()); +} + /* * Used for LDT copy/destruction. */ @@ -78,12 +122,12 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, * was called and then modify_ldt changed * prev->context.ldt but suppressed an IPI to this CPU. * In this case, prev->context.ldt != NULL, because we - * never free an LDT while the mm still exists. That - * means that next->context.ldt != prev->context.ldt, - * because mms never share an LDT. + * never set context.ldt to NULL while the mm still + * exists. That means that next->context.ldt != + * prev->context.ldt, because mms never share an LDT. */ if (unlikely(prev->context.ldt != next->context.ldt)) - load_LDT_nolock(&next->context); + load_mm_ldt(next); } #ifdef CONFIG_SMP else { @@ -106,7 +150,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, load_cr3(next->pgd); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); load_mm_cr4(next); - load_LDT_nolock(&next->context); + load_mm_ldt(next); } } #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 922c5e0cea4c..cb9e5df42dd2 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1410,7 +1410,7 @@ void cpu_init(void) load_sp0(t, ¤t->thread); set_tss_desc(cpu, t); load_TR_desc(); - load_LDT(&init_mm.context); + load_mm_ldt(&init_mm); clear_all_debug_regs(); dbg_restore_debug_regs(); @@ -1459,7 +1459,7 @@ void cpu_init(void) load_sp0(t, thread); set_tss_desc(cpu, t); load_TR_desc(); - load_LDT(&init_mm.context); + load_mm_ldt(&init_mm); t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap); diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 3658de47900f..9469dfa55607 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -2179,21 +2179,25 @@ static unsigned long get_segment_base(unsigned int segment) int idx = segment >> 3; if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) { + struct ldt_struct *ldt; + if (idx > LDT_ENTRIES) return 0; - if (idx > current->active_mm->context.size) + /* IRQs are off, so this synchronizes with smp_store_release */ + ldt = lockless_dereference(current->active_mm->context.ldt); + if (!ldt || idx > ldt->size) return 0; - desc = current->active_mm->context.ldt; + desc = &ldt->entries[idx]; } else { if (idx > GDT_ENTRIES) return 0; - desc = raw_cpu_ptr(gdt_page.gdt); + desc = raw_cpu_ptr(gdt_page.gdt) + idx; } - return get_desc_base(desc + idx); + return get_desc_base(desc); } #ifdef CONFIG_COMPAT diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index c37886d759cc..2bcc0525f1c1 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include @@ -20,82 +21,82 @@ #include #include -#ifdef CONFIG_SMP +/* context.lock is held for us, so we don't need any locking. */ static void flush_ldt(void *current_mm) { - if (current->active_mm == current_mm) - load_LDT(¤t->active_mm->context); + mm_context_t *pc; + + if (current->active_mm != current_mm) + return; + + pc = ¤t->active_mm->context; + set_ldt(pc->ldt->entries, pc->ldt->size); } -#endif -static int alloc_ldt(mm_context_t *pc, int mincount, int reload) +/* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */ +static struct ldt_struct *alloc_ldt_struct(int size) { - void *oldldt, *newldt; - int oldsize; + struct ldt_struct *new_ldt; + int alloc_size; - if (mincount <= pc->size) - return 0; - oldsize = pc->size; - mincount = (mincount + (PAGE_SIZE / LDT_ENTRY_SIZE - 1)) & - (~(PAGE_SIZE / LDT_ENTRY_SIZE - 1)); - if (mincount * LDT_ENTRY_SIZE > PAGE_SIZE) - newldt = vmalloc(mincount * LDT_ENTRY_SIZE); + if (size > LDT_ENTRIES) + return NULL; + + new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL); + if (!new_ldt) + return NULL; + + BUILD_BUG_ON(LDT_ENTRY_SIZE != sizeof(struct desc_struct)); + alloc_size = size * LDT_ENTRY_SIZE; + + /* + * Xen is very picky: it requires a page-aligned LDT that has no + * trailing nonzero bytes in any page that contains LDT descriptors. + * Keep it simple: zero the whole allocation and never allocate less + * than PAGE_SIZE. + */ + if (alloc_size > PAGE_SIZE) + new_ldt->entries = vzalloc(alloc_size); else - newldt = (void *)__get_free_page(GFP_KERNEL); + new_ldt->entries = kzalloc(PAGE_SIZE, GFP_KERNEL); - if (!newldt) - return -ENOMEM; - - if (oldsize) - memcpy(newldt, pc->ldt, oldsize * LDT_ENTRY_SIZE); - oldldt = pc->ldt; - memset(newldt + oldsize * LDT_ENTRY_SIZE, 0, - (mincount - oldsize) * LDT_ENTRY_SIZE); - - paravirt_alloc_ldt(newldt, mincount); - -#ifdef CONFIG_X86_64 - /* CHECKME: Do we really need this ? */ - wmb(); -#endif - pc->ldt = newldt; - wmb(); - pc->size = mincount; - wmb(); - - if (reload) { -#ifdef CONFIG_SMP - preempt_disable(); - load_LDT(pc); - if (!cpumask_equal(mm_cpumask(current->mm), - cpumask_of(smp_processor_id()))) - smp_call_function(flush_ldt, current->mm, 1); - preempt_enable(); -#else - load_LDT(pc); -#endif + if (!new_ldt->entries) { + kfree(new_ldt); + return NULL; } - if (oldsize) { - paravirt_free_ldt(oldldt, oldsize); - if (oldsize * LDT_ENTRY_SIZE > PAGE_SIZE) - vfree(oldldt); - else - put_page(virt_to_page(oldldt)); - } - return 0; + + new_ldt->size = size; + return new_ldt; } -static inline int copy_ldt(mm_context_t *new, mm_context_t *old) +/* After calling this, the LDT is immutable. */ +static void finalize_ldt_struct(struct ldt_struct *ldt) { - int err = alloc_ldt(new, old->size, 0); - int i; + paravirt_alloc_ldt(ldt->entries, ldt->size); +} - if (err < 0) - return err; +/* context.lock is held */ +static void install_ldt(struct mm_struct *current_mm, + struct ldt_struct *ldt) +{ + /* Synchronizes with lockless_dereference in load_mm_ldt. */ + smp_store_release(¤t_mm->context.ldt, ldt); - for (i = 0; i < old->size; i++) - write_ldt_entry(new->ldt, i, old->ldt + i * LDT_ENTRY_SIZE); - return 0; + /* Activate the LDT for all CPUs using current_mm. */ + on_each_cpu_mask(mm_cpumask(current_mm), flush_ldt, current_mm, true); +} + +static void free_ldt_struct(struct ldt_struct *ldt) +{ + if (likely(!ldt)) + return; + + paravirt_free_ldt(ldt->entries, ldt->size); + if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE) + vfree(ldt->entries); + else + kfree(ldt->entries); + kfree(ldt); } /* @@ -104,17 +105,37 @@ static inline int copy_ldt(mm_context_t *new, mm_context_t *old) */ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { + struct ldt_struct *new_ldt; struct mm_struct *old_mm; int retval = 0; mutex_init(&mm->context.lock); - mm->context.size = 0; old_mm = current->mm; - if (old_mm && old_mm->context.size > 0) { - mutex_lock(&old_mm->context.lock); - retval = copy_ldt(&mm->context, &old_mm->context); - mutex_unlock(&old_mm->context.lock); + if (!old_mm) { + mm->context.ldt = NULL; + return 0; } + + mutex_lock(&old_mm->context.lock); + if (!old_mm->context.ldt) { + mm->context.ldt = NULL; + goto out_unlock; + } + + new_ldt = alloc_ldt_struct(old_mm->context.ldt->size); + if (!new_ldt) { + retval = -ENOMEM; + goto out_unlock; + } + + memcpy(new_ldt->entries, old_mm->context.ldt->entries, + new_ldt->size * LDT_ENTRY_SIZE); + finalize_ldt_struct(new_ldt); + + mm->context.ldt = new_ldt; + +out_unlock: + mutex_unlock(&old_mm->context.lock); return retval; } @@ -125,53 +146,47 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) */ void destroy_context(struct mm_struct *mm) { - if (mm->context.size) { -#ifdef CONFIG_X86_32 - /* CHECKME: Can this ever happen ? */ - if (mm == current->active_mm) - clear_LDT(); -#endif - paravirt_free_ldt(mm->context.ldt, mm->context.size); - if (mm->context.size * LDT_ENTRY_SIZE > PAGE_SIZE) - vfree(mm->context.ldt); - else - put_page(virt_to_page(mm->context.ldt)); - mm->context.size = 0; - } + free_ldt_struct(mm->context.ldt); + mm->context.ldt = NULL; } static int read_ldt(void __user *ptr, unsigned long bytecount) { - int err; + int retval; unsigned long size; struct mm_struct *mm = current->mm; - if (!mm->context.size) - return 0; + mutex_lock(&mm->context.lock); + + if (!mm->context.ldt) { + retval = 0; + goto out_unlock; + } + if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES) bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES; - mutex_lock(&mm->context.lock); - size = mm->context.size * LDT_ENTRY_SIZE; + size = mm->context.ldt->size * LDT_ENTRY_SIZE; if (size > bytecount) size = bytecount; - err = 0; - if (copy_to_user(ptr, mm->context.ldt, size)) - err = -EFAULT; - mutex_unlock(&mm->context.lock); - if (err < 0) - goto error_return; + if (copy_to_user(ptr, mm->context.ldt->entries, size)) { + retval = -EFAULT; + goto out_unlock; + } + if (size != bytecount) { - /* zero-fill the rest */ - if (clear_user(ptr + size, bytecount - size) != 0) { - err = -EFAULT; - goto error_return; + /* Zero-fill the rest and pretend we read bytecount bytes. */ + if (clear_user(ptr + size, bytecount - size)) { + retval = -EFAULT; + goto out_unlock; } } - return bytecount; -error_return: - return err; + retval = bytecount; + +out_unlock: + mutex_unlock(&mm->context.lock); + return retval; } static int read_default_ldt(void __user *ptr, unsigned long bytecount) @@ -195,6 +210,8 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) struct desc_struct ldt; int error; struct user_desc ldt_info; + int oldsize, newsize; + struct ldt_struct *new_ldt, *old_ldt; error = -EINVAL; if (bytecount != sizeof(ldt_info)) @@ -213,34 +230,39 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) goto out; } - mutex_lock(&mm->context.lock); - if (ldt_info.entry_number >= mm->context.size) { - error = alloc_ldt(¤t->mm->context, - ldt_info.entry_number + 1, 1); - if (error < 0) - goto out_unlock; - } - - /* Allow LDTs to be cleared by the user. */ - if (ldt_info.base_addr == 0 && ldt_info.limit == 0) { - if (oldmode || LDT_empty(&ldt_info)) { - memset(&ldt, 0, sizeof(ldt)); - goto install; + if ((oldmode && !ldt_info.base_addr && !ldt_info.limit) || + LDT_empty(&ldt_info)) { + /* The user wants to clear the entry. */ + memset(&ldt, 0, sizeof(ldt)); + } else { + if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { + error = -EINVAL; + goto out; } + + fill_ldt(&ldt, &ldt_info); + if (oldmode) + ldt.avl = 0; } - if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { - error = -EINVAL; + mutex_lock(&mm->context.lock); + + old_ldt = mm->context.ldt; + oldsize = old_ldt ? old_ldt->size : 0; + newsize = max((int)(ldt_info.entry_number + 1), oldsize); + + error = -ENOMEM; + new_ldt = alloc_ldt_struct(newsize); + if (!new_ldt) goto out_unlock; - } - fill_ldt(&ldt, &ldt_info); - if (oldmode) - ldt.avl = 0; + if (old_ldt) + memcpy(new_ldt->entries, old_ldt->entries, oldsize * LDT_ENTRY_SIZE); + new_ldt->entries[ldt_info.entry_number] = ldt; + finalize_ldt_struct(new_ldt); - /* Install the new entry ... */ -install: - write_ldt_entry(mm->context.ldt, ldt_info.entry_number, &ldt); + install_ldt(mm, new_ldt); + free_ldt_struct(old_ldt); error = 0; out_unlock: diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 71d7849a07f7..f6b916387590 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -121,11 +121,11 @@ void __show_regs(struct pt_regs *regs, int all) void release_thread(struct task_struct *dead_task) { if (dead_task->mm) { - if (dead_task->mm->context.size) { + if (dead_task->mm->context.ldt) { pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n", dead_task->comm, dead_task->mm->context.ldt, - dead_task->mm->context.size); + dead_task->mm->context.ldt->size); BUG(); } } diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 9b4d51d0c0d0..6273324186ac 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -5,6 +5,7 @@ #include #include #include +#include unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs) { @@ -30,10 +31,11 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re seg &= ~7UL; mutex_lock(&child->mm->context.lock); - if (unlikely((seg >> 3) >= child->mm->context.size)) + if (unlikely(!child->mm->context.ldt || + (seg >> 3) >= child->mm->context.ldt->size)) addr = -1L; /* bogus selector, access would fault */ else { - desc = child->mm->context.ldt + seg; + desc = &child->mm->context.ldt->entries[seg]; base = get_desc_base(desc); /* 16-bit code segment? */ diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 0d7dd1f5ac36..9ab52791fed5 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -22,6 +22,7 @@ #include #include #include +#include #ifdef CONFIG_X86_32 __visible unsigned long saved_context_ebx; @@ -153,7 +154,7 @@ static void fix_processor_context(void) syscall_init(); /* This sets MSR_*STAR and related */ #endif load_TR_desc(); /* This does ltr */ - load_LDT(¤t->active_mm->context); /* This does lldt */ + load_mm_ldt(current->active_mm); /* This does lldt */ fpu__resume_cpu(); } From f6762cb2ca48e9052b5233c338fa254fa58d8981 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Tue, 7 Jul 2015 16:18:46 +0800 Subject: [PATCH 295/428] ceph: fix ceph_encode_locks_to_buffer() posix locks should be in ctx->flc_posix list Signed-off-by: Yan, Zheng Signed-off-by: Ilya Dryomov --- fs/ceph/locks.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index 4347039ecc18..6706bde9ad1b 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -287,7 +287,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode, return 0; spin_lock(&ctx->flc_lock); - list_for_each_entry(lock, &ctx->flc_flock, fl_list) { + list_for_each_entry(lock, &ctx->flc_posix, fl_list) { ++seen_fcntl; if (seen_fcntl > num_fcntl_locks) { err = -ENOSPC; From fc927cd32feca2acefd90a4ac317fa4f0a2e5955 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Mon, 20 Jul 2015 09:50:58 +0800 Subject: [PATCH 296/428] ceph: always re-send cap flushes when MDS recovers commit e548e9b93d3e565e42b938a99804114565be1f81 makes the kclient only re-send cap flush once during MDS failover. If the kclient sends a cap flush after MDS enters reconnect stage but before MDS recovers. The kclient will skip re-sending the same cap flush when MDS recovers. This causes problem for newly created inode. The MDS handles cap flushes before replaying unsafe requests, so it's possible that MDS find corresponding inode is missing when handling cap flush. The fix is reverting to old behaviour: always re-send when MDS recovers Signed-off-by: Yan, Zheng Signed-off-by: Ilya Dryomov --- fs/ceph/caps.c | 22 +++++----------------- fs/ceph/super.h | 1 - 2 files changed, 5 insertions(+), 18 deletions(-) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index dc10c9dd36c1..ddd5e9471290 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1506,7 +1506,6 @@ static int __mark_caps_flushing(struct inode *inode, swap(cf, ci->i_prealloc_cap_flush); cf->caps = flushing; - cf->kick = false; spin_lock(&mdsc->cap_dirty_lock); list_del_init(&ci->i_dirty_item); @@ -2123,8 +2122,7 @@ static void kick_flushing_capsnaps(struct ceph_mds_client *mdsc, static int __kick_flushing_caps(struct ceph_mds_client *mdsc, struct ceph_mds_session *session, - struct ceph_inode_info *ci, - bool kick_all) + struct ceph_inode_info *ci) { struct inode *inode = &ci->vfs_inode; struct ceph_cap *cap; @@ -2150,9 +2148,7 @@ static int __kick_flushing_caps(struct ceph_mds_client *mdsc, for (n = rb_first(&ci->i_cap_flush_tree); n; n = rb_next(n)) { cf = rb_entry(n, struct ceph_cap_flush, i_node); - if (cf->tid < first_tid) - continue; - if (kick_all || cf->kick) + if (cf->tid >= first_tid) break; } if (!n) { @@ -2161,7 +2157,6 @@ static int __kick_flushing_caps(struct ceph_mds_client *mdsc, } cf = rb_entry(n, struct ceph_cap_flush, i_node); - cf->kick = false; first_tid = cf->tid + 1; @@ -2181,8 +2176,6 @@ void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc, { struct ceph_inode_info *ci; struct ceph_cap *cap; - struct ceph_cap_flush *cf; - struct rb_node *n; dout("early_kick_flushing_caps mds%d\n", session->s_mds); list_for_each_entry(ci, &session->s_cap_flushing, i_flushing_item) { @@ -2205,16 +2198,11 @@ void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc, if ((cap->issued & ci->i_flushing_caps) != ci->i_flushing_caps) { spin_unlock(&ci->i_ceph_lock); - if (!__kick_flushing_caps(mdsc, session, ci, true)) + if (!__kick_flushing_caps(mdsc, session, ci)) continue; spin_lock(&ci->i_ceph_lock); } - for (n = rb_first(&ci->i_cap_flush_tree); n; n = rb_next(n)) { - cf = rb_entry(n, struct ceph_cap_flush, i_node); - cf->kick = true; - } - spin_unlock(&ci->i_ceph_lock); } } @@ -2228,7 +2216,7 @@ void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc, dout("kick_flushing_caps mds%d\n", session->s_mds); list_for_each_entry(ci, &session->s_cap_flushing, i_flushing_item) { - int delayed = __kick_flushing_caps(mdsc, session, ci, false); + int delayed = __kick_flushing_caps(mdsc, session, ci); if (delayed) { spin_lock(&ci->i_ceph_lock); __cap_delay_requeue(mdsc, ci); @@ -2261,7 +2249,7 @@ static void kick_flushing_inode_caps(struct ceph_mds_client *mdsc, spin_unlock(&ci->i_ceph_lock); - delayed = __kick_flushing_caps(mdsc, session, ci, true); + delayed = __kick_flushing_caps(mdsc, session, ci); if (delayed) { spin_lock(&ci->i_ceph_lock); __cap_delay_requeue(mdsc, ci); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 860cc016e70d..2f2460d23a06 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -189,7 +189,6 @@ static inline void ceph_put_cap_snap(struct ceph_cap_snap *capsnap) struct ceph_cap_flush { u64 tid; int caps; - bool kick; struct rb_node g_node; // global union { struct rb_node i_node; // inode From 2761713d35e370fd640b5781109f753066b746c4 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Thu, 16 Jul 2015 17:36:11 +0300 Subject: [PATCH 297/428] rbd: fix copyup completion race For write/discard obj_requests that involved a copyup method call, the opcode of the first op is CEPH_OSD_OP_CALL and the ->callback is rbd_img_obj_copyup_callback(). The latter frees copyup pages, sets ->xferred and delegates to rbd_img_obj_callback(), the "normal" image object callback, for reporting to block layer and putting refs. rbd_osd_req_callback() however treats CEPH_OSD_OP_CALL as a trivial op, which means obj_request is marked done in rbd_osd_trivial_callback(), *before* ->callback is invoked and rbd_img_obj_copyup_callback() has a chance to run. Marking obj_request done essentially means giving rbd_img_obj_callback() a license to end it at any moment, so if another obj_request from the same img_request is being completed concurrently, rbd_img_obj_end_request() may very well be called on such prematurally marked done request: handle_reply() rbd_osd_req_callback() rbd_osd_trivial_callback() rbd_obj_request_complete() rbd_img_obj_copyup_callback() rbd_img_obj_callback() handle_reply() rbd_osd_req_callback() rbd_osd_trivial_callback() for_each_obj_request(obj_request->img_request) { rbd_img_obj_end_request(obj_request-1/2) rbd_img_obj_end_request(obj_request-2/2) <-- } Calling rbd_img_obj_end_request() on such a request leads to trouble, in particular because its ->xfferred is 0. We report 0 to the block layer with blk_update_request(), get back 1 for "this request has more data in flight" and then trip on rbd_assert(more ^ (which == img_request->obj_request_count)); with rhs (which == ...) being 1 because rbd_img_obj_end_request() has been called for both requests and lhs (more) being 1 because we haven't got a chance to set ->xfferred in rbd_img_obj_copyup_callback() yet. To fix this, leverage that rbd wants to call class methods in only two cases: one is a generic method call wrapper (obj_request is standalone) and the other is a copyup (obj_request is part of an img_request). So make a dedicated handler for CEPH_OSD_OP_CALL and directly invoke rbd_img_obj_copyup_callback() from it if obj_request is part of an img_request, similar to how CEPH_OSD_OP_READ handler invokes rbd_img_obj_request_read_callback(). Since rbd_img_obj_copyup_callback() is now being called from the OSD request callback (only), it is renamed to rbd_osd_copyup_callback(). Cc: Alex Elder Cc: stable@vger.kernel.org # 3.10+, needs backporting for < 3.18 Signed-off-by: Ilya Dryomov Reviewed-by: Alex Elder --- drivers/block/rbd.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index d94529d5c8e9..bc67a93aa4f4 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -523,6 +523,7 @@ void rbd_warn(struct rbd_device *rbd_dev, const char *fmt, ...) # define rbd_assert(expr) ((void) 0) #endif /* !RBD_DEBUG */ +static void rbd_osd_copyup_callback(struct rbd_obj_request *obj_request); static int rbd_img_obj_request_submit(struct rbd_obj_request *obj_request); static void rbd_img_parent_read(struct rbd_obj_request *obj_request); static void rbd_dev_remove_parent(struct rbd_device *rbd_dev); @@ -1818,6 +1819,16 @@ static void rbd_osd_stat_callback(struct rbd_obj_request *obj_request) obj_request_done_set(obj_request); } +static void rbd_osd_call_callback(struct rbd_obj_request *obj_request) +{ + dout("%s: obj %p\n", __func__, obj_request); + + if (obj_request_img_data_test(obj_request)) + rbd_osd_copyup_callback(obj_request); + else + obj_request_done_set(obj_request); +} + static void rbd_osd_req_callback(struct ceph_osd_request *osd_req, struct ceph_msg *msg) { @@ -1866,6 +1877,8 @@ static void rbd_osd_req_callback(struct ceph_osd_request *osd_req, rbd_osd_discard_callback(obj_request); break; case CEPH_OSD_OP_CALL: + rbd_osd_call_callback(obj_request); + break; case CEPH_OSD_OP_NOTIFY_ACK: case CEPH_OSD_OP_WATCH: rbd_osd_trivial_callback(obj_request); @@ -2530,13 +2543,15 @@ out_unwind: } static void -rbd_img_obj_copyup_callback(struct rbd_obj_request *obj_request) +rbd_osd_copyup_callback(struct rbd_obj_request *obj_request) { struct rbd_img_request *img_request; struct rbd_device *rbd_dev; struct page **pages; u32 page_count; + dout("%s: obj %p\n", __func__, obj_request); + rbd_assert(obj_request->type == OBJ_REQUEST_BIO || obj_request->type == OBJ_REQUEST_NODATA); rbd_assert(obj_request_img_data_test(obj_request)); @@ -2563,9 +2578,7 @@ rbd_img_obj_copyup_callback(struct rbd_obj_request *obj_request) if (!obj_request->result) obj_request->xferred = obj_request->length; - /* Finish up with the normal image object callback */ - - rbd_img_obj_callback(obj_request); + obj_request_done_set(obj_request); } static void @@ -2650,7 +2663,6 @@ rbd_img_obj_parent_read_full_callback(struct rbd_img_request *img_request) /* All set, send it off. */ - orig_request->callback = rbd_img_obj_copyup_callback; osdc = &rbd_dev->rbd_client->client->osdc; img_result = rbd_obj_request_submit(osdc, orig_request); if (!img_result) From 1f023297f7f77d434ecc221018d2e181eac0ae36 Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Mon, 27 Jul 2015 00:16:31 +0300 Subject: [PATCH 298/428] i2c: slave eeprom: clean up sysfs bin attribute read()/write() The change removes redundant sysfs binary file boundary checks, since this task is already done on caller side in fs/sysfs/file.c Note, on file size overflow read() now returns 0, and this is a correct and expected EOF notification according to POSIX. Signed-off-by: Vladimir Zapolskiy Signed-off-by: Wolfram Sang --- drivers/i2c/i2c-slave-eeprom.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/i2c/i2c-slave-eeprom.c b/drivers/i2c/i2c-slave-eeprom.c index 822374654609..1da449614779 100644 --- a/drivers/i2c/i2c-slave-eeprom.c +++ b/drivers/i2c/i2c-slave-eeprom.c @@ -80,9 +80,6 @@ static ssize_t i2c_slave_eeprom_bin_read(struct file *filp, struct kobject *kobj struct eeprom_data *eeprom; unsigned long flags; - if (off + count > attr->size) - return -EFBIG; - eeprom = dev_get_drvdata(container_of(kobj, struct device, kobj)); spin_lock_irqsave(&eeprom->buffer_lock, flags); @@ -98,9 +95,6 @@ static ssize_t i2c_slave_eeprom_bin_write(struct file *filp, struct kobject *kob struct eeprom_data *eeprom; unsigned long flags; - if (off + count > attr->size) - return -EFBIG; - eeprom = dev_get_drvdata(container_of(kobj, struct device, kobj)); spin_lock_irqsave(&eeprom->buffer_lock, flags); From d12c0aaf3780c5b26b4ea9e795252381f586c063 Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Mon, 27 Jul 2015 00:18:51 +0300 Subject: [PATCH 299/428] misc: eeprom: at24: clean up at24_bin_write() The change removes redundant sysfs binary file boundary check, since this task is already done on caller side in fs/sysfs/file.c Signed-off-by: Vladimir Zapolskiy Signed-off-by: Wolfram Sang --- drivers/misc/eeprom/at24.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index 2d3db81be099..6ded3dc36644 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -438,9 +438,6 @@ static ssize_t at24_bin_write(struct file *filp, struct kobject *kobj, { struct at24_data *at24; - if (unlikely(off >= attr->size)) - return -EFBIG; - at24 = dev_get_drvdata(container_of(kobj, struct device, kobj)); return at24_write(at24, buf, off, count); } From 8b06260836ab47abbb5ea49d889660a0ed8adf90 Mon Sep 17 00:00:00 2001 From: Jan Luebbe Date: Wed, 8 Jul 2015 16:35:06 +0200 Subject: [PATCH 300/428] i2c: core: only use set_scl for bus recovery after calling prepare_recovery Using set_scl may be ineffective before calling the driver specific prepare_recovery callback, which might change into a test mode. So instead of setting SCL in i2c_generic_scl_recovery, move it to i2c_generic_recovery (after the optional prepare_recovery). Signed-off-by: Jan Luebbe Acked-by: Alexander Sverdlin Tested-by: Alexander Sverdlin Signed-off-by: Wolfram Sang --- drivers/i2c/i2c-core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c index e6d4935161e4..8b64cf38beac 100644 --- a/drivers/i2c/i2c-core.c +++ b/drivers/i2c/i2c-core.c @@ -567,6 +567,9 @@ static int i2c_generic_recovery(struct i2c_adapter *adap) if (bri->prepare_recovery) bri->prepare_recovery(adap); + bri->set_scl(adap, val); + ndelay(RECOVERY_NDELAY); + /* * By this time SCL is high, as we need to give 9 falling-rising edges */ @@ -597,7 +600,6 @@ static int i2c_generic_recovery(struct i2c_adapter *adap) int i2c_generic_scl_recovery(struct i2c_adapter *adap) { - adap->bus_recovery_info->set_scl(adap, 1); return i2c_generic_recovery(adap); } EXPORT_SYMBOL_GPL(i2c_generic_scl_recovery); From 828e66c0edf97bcb79b59b1ddd803a50629b3937 Mon Sep 17 00:00:00 2001 From: Jan Luebbe Date: Wed, 8 Jul 2015 16:35:27 +0200 Subject: [PATCH 301/428] i2c: omap: fix bus recovery setup At least on the AM335x, enabling OMAP_I2C_SYSTEST_ST_EN is not enough to allow direct access to the SCL and SDA pins. In addition to ST_EN, we need to set the TMODE to 0b11 (Loop back & SDA/SCL IO mode select). Also, as the reset values of SCL_O and SDA_O are 0 (which means "drive low level"), we need to set them to 1 (which means "high-impedance") to avoid unwanted changes on the pins. As a precaution, reset all these bits to their default values after recovery is complete. Signed-off-by: Jan Luebbe Tested-by: Alexander Sverdlin Reviewed-by: Grygorii Strashko Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-omap.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c index d1c22e3fdd14..fc9bf7f30e35 100644 --- a/drivers/i2c/busses/i2c-omap.c +++ b/drivers/i2c/busses/i2c-omap.c @@ -1247,7 +1247,14 @@ static void omap_i2c_prepare_recovery(struct i2c_adapter *adap) u32 reg; reg = omap_i2c_read_reg(dev, OMAP_I2C_SYSTEST_REG); + /* enable test mode */ reg |= OMAP_I2C_SYSTEST_ST_EN; + /* select SDA/SCL IO mode */ + reg |= 3 << OMAP_I2C_SYSTEST_TMODE_SHIFT; + /* set SCL to high-impedance state (reset value is 0) */ + reg |= OMAP_I2C_SYSTEST_SCL_O; + /* set SDA to high-impedance state (reset value is 0) */ + reg |= OMAP_I2C_SYSTEST_SDA_O; omap_i2c_write_reg(dev, OMAP_I2C_SYSTEST_REG, reg); } @@ -1257,7 +1264,11 @@ static void omap_i2c_unprepare_recovery(struct i2c_adapter *adap) u32 reg; reg = omap_i2c_read_reg(dev, OMAP_I2C_SYSTEST_REG); + /* restore reset values */ reg &= ~OMAP_I2C_SYSTEST_ST_EN; + reg &= ~OMAP_I2C_SYSTEST_TMODE_MASK; + reg &= ~OMAP_I2C_SYSTEST_SCL_O; + reg &= ~OMAP_I2C_SYSTEST_SDA_O; omap_i2c_write_reg(dev, OMAP_I2C_SYSTEST_REG, reg); } From e952849a02524a247967bf7105f36fbb13cd00c2 Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Tue, 28 Jul 2015 20:11:23 +0900 Subject: [PATCH 302/428] i2c: Fix typo in i2c-bfin-twi.c This patch fix some typos found in a printk message and MODULE_DESCRIPTION. Signed-off-by: Masanari Iida Acked-by: Sonic Zhang Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-bfin-twi.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/i2c/busses/i2c-bfin-twi.c b/drivers/i2c/busses/i2c-bfin-twi.c index af162b4c7a6d..025686d41640 100644 --- a/drivers/i2c/busses/i2c-bfin-twi.c +++ b/drivers/i2c/busses/i2c-bfin-twi.c @@ -692,7 +692,7 @@ static int i2c_bfin_twi_probe(struct platform_device *pdev) platform_set_drvdata(pdev, iface); - dev_info(&pdev->dev, "Blackfin BF5xx on-chip I2C TWI Contoller, " + dev_info(&pdev->dev, "Blackfin BF5xx on-chip I2C TWI Controller, " "regs_base@%p\n", iface->regs_base); return 0; @@ -735,6 +735,6 @@ subsys_initcall(i2c_bfin_twi_init); module_exit(i2c_bfin_twi_exit); MODULE_AUTHOR("Bryan Wu, Sonic Zhang"); -MODULE_DESCRIPTION("Blackfin BF5xx on-chip I2C TWI Contoller Driver"); +MODULE_DESCRIPTION("Blackfin BF5xx on-chip I2C TWI Controller Driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS("platform:i2c-bfin-twi"); From 1c1cc454aa694a89572689515fdaaf27b8c9f42a Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 30 Jul 2015 11:24:45 +0200 Subject: [PATCH 303/428] iommu/amd: Allow non-ATS devices in IOMMUv2 domains With the grouping of multi-function devices a non-ATS capable device might also end up in the same domain as an IOMMUv2 capable device. So handle this situation gracefully and don't consider it a bug anymore. Tested-by: Oded Gabbay Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index fa9508bb76dd..658ee39e6569 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -3318,7 +3318,12 @@ static int __flush_pasid(struct protection_domain *domain, int pasid, struct amd_iommu *iommu; int qdep; - BUG_ON(!dev_data->ats.enabled); + /* + There might be non-IOMMUv2 capable devices in an IOMMUv2 + * domain. + */ + if (!dev_data->ats.enabled) + continue; qdep = dev_data->ats.qdep; iommu = amd_iommu_rlookup_table[dev_data->devid]; From 20cadcb4df3eebd82410eab4aa91d5b083e16cd1 Mon Sep 17 00:00:00 2001 From: Ludovic Desroches Date: Wed, 17 Jun 2015 16:22:26 +0200 Subject: [PATCH 304/428] dmaengine: at_xdmac: fix bug about channel configuration When using descriptor view 2 or higher, we don't write the configuration into AT_XDMAC_CC register because this configuration will be fetch from the descriptor. Unfortunately, the PROT bit is not updated with this method, we have to do it manually before enabling the channel. Signed-off-by: Ludovic Desroches Signed-off-by: Vinod Koul --- drivers/dma/at_xdmac.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index cf1213de7865..52ca1ccefa3f 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -359,18 +359,19 @@ static void at_xdmac_start_xfer(struct at_xdmac_chan *atchan, * descriptor view 2 since some fields of the configuration register * depend on transfer size and src/dest addresses. */ - if (at_xdmac_chan_is_cyclic(atchan)) { + if (at_xdmac_chan_is_cyclic(atchan)) reg = AT_XDMAC_CNDC_NDVIEW_NDV1; - at_xdmac_chan_write(atchan, AT_XDMAC_CC, first->lld.mbr_cfg); - } else if (first->lld.mbr_ubc & AT_XDMAC_MBR_UBC_NDV3) { + else if (first->lld.mbr_ubc & AT_XDMAC_MBR_UBC_NDV3) reg = AT_XDMAC_CNDC_NDVIEW_NDV3; - } else { - /* - * No need to write AT_XDMAC_CC reg, it will be done when the - * descriptor is fecthed. - */ + else reg = AT_XDMAC_CNDC_NDVIEW_NDV2; - } + /* + * Even if the register will be updated from the configuration in the + * descriptor when using view 2 or higher, the PROT bit won't be set + * properly. This bit can be modified only by using the channel + * configuration register. + */ + at_xdmac_chan_write(atchan, AT_XDMAC_CC, first->lld.mbr_cfg); reg |= AT_XDMAC_CNDC_NDDUP | AT_XDMAC_CNDC_NDSUP From 93dce3a6434f632dbd684ec1d9c3dc66a14e27e1 Mon Sep 17 00:00:00 2001 From: Cyrille Pitchen Date: Thu, 18 Jun 2015 13:25:41 +0200 Subject: [PATCH 305/428] dmaengine: at_hdmac: fix residue computation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As claimed by the programmer datasheet and confirmed by the IP designer, the Block Transfer Size (BTSIZE) bitfield of the Channel x Control A Register (CTRLAx) always refers to a number of Source Width (SRC_WIDTH) transfers. Both the SRC_WIDTH and BTSIZE bitfields can be extacted from the CTRLAx register to compute the DMA residue. So the 'tx_width' field is useless and can be removed from the struct at_desc. Before this patch, atc_prep_slave_sg() was not consistent: BTSIZE was correctly initialized according to the SRC_WIDTH but 'tx_width' was always set to reg_width, which was incorrect for MEM_TO_DEV transfers. It led to bad DMA residue when 'tx_width' != SRC_WIDTH. Also the 'tx_width' field was mostly set only in the first and last descriptors. Depending on the kind of DMA transfer, this field remained uninitialized for intermediate descriptors. The accurate DMA residue was computed only when the currently processed descriptor was the first or the last of the chain. This algorithm was a little bit odd. An accurate DMA residue can always be computed using the SRC_WIDTH and BTSIZE bitfields in the CTRLAx register. Finally, the test to check whether the currently processed descriptor is the last of the chain was wrong: for cyclic transfer, last_desc->lli.dscr is NOT equal to zero, since set_desc_eol() is never called, but logically equal to first_desc->txd.phys. This bug has a side effect on the drivers/tty/serial/atmel_serial.c driver, which uses cyclic DMA transfer to receive data. Since the DMA residue was wrong each time the DMA transfer reaches the second (and last) period of the transfer, no more data were received by the USART driver till the cyclic DMA transfer loops back to the first period. Signed-off-by: Cyrille Pitchen Acked-by: Torsten Fleischer Tested-by: Jirí Prchal Acked-by: Nicolas Ferre Signed-off-by: Vinod Koul --- drivers/dma/at_hdmac.c | 132 ++++++++++++++++++++++++------------ drivers/dma/at_hdmac_regs.h | 3 +- 2 files changed, 88 insertions(+), 47 deletions(-) diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c index 59892126d175..d3629b7482dd 100644 --- a/drivers/dma/at_hdmac.c +++ b/drivers/dma/at_hdmac.c @@ -48,6 +48,8 @@ BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) |\ BIT(DMA_SLAVE_BUSWIDTH_4_BYTES)) +#define ATC_MAX_DSCR_TRIALS 10 + /* * Initial number of descriptors to allocate for each channel. This could * be increased during dma usage. @@ -285,28 +287,19 @@ static struct at_desc *atc_get_desc_by_cookie(struct at_dma_chan *atchan, * * @current_len: the number of bytes left before reading CTRLA * @ctrla: the value of CTRLA - * @desc: the descriptor containing the transfer width */ -static inline int atc_calc_bytes_left(int current_len, u32 ctrla, - struct at_desc *desc) +static inline int atc_calc_bytes_left(int current_len, u32 ctrla) { - return current_len - ((ctrla & ATC_BTSIZE_MAX) << desc->tx_width); -} + u32 btsize = (ctrla & ATC_BTSIZE_MAX); + u32 src_width = ATC_REG_TO_SRC_WIDTH(ctrla); -/** - * atc_calc_bytes_left_from_reg - calculates the number of bytes left according - * to the current value of CTRLA. - * - * @current_len: the number of bytes left before reading CTRLA - * @atchan: the channel to read CTRLA for - * @desc: the descriptor containing the transfer width - */ -static inline int atc_calc_bytes_left_from_reg(int current_len, - struct at_dma_chan *atchan, struct at_desc *desc) -{ - u32 ctrla = channel_readl(atchan, CTRLA); - - return atc_calc_bytes_left(current_len, ctrla, desc); + /* + * According to the datasheet, when reading the Control A Register + * (ctrla), the Buffer Transfer Size (btsize) bitfield refers to the + * number of transfers completed on the Source Interface. + * So btsize is always a number of source width transfers. + */ + return current_len - (btsize << src_width); } /** @@ -320,7 +313,7 @@ static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie) struct at_desc *desc_first = atc_first_active(atchan); struct at_desc *desc; int ret; - u32 ctrla, dscr; + u32 ctrla, dscr, trials; /* * If the cookie doesn't match to the currently running transfer then @@ -346,15 +339,82 @@ static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie) * the channel's DSCR register and compare it against the value * of the hardware linked list structure of each child * descriptor. + * + * The CTRLA register provides us with the amount of data + * already read from the source for the current child + * descriptor. So we can compute a more accurate residue by also + * removing the number of bytes corresponding to this amount of + * data. + * + * However, the DSCR and CTRLA registers cannot be read both + * atomically. Hence a race condition may occur: the first read + * register may refer to one child descriptor whereas the second + * read may refer to a later child descriptor in the list + * because of the DMA transfer progression inbetween the two + * reads. + * + * One solution could have been to pause the DMA transfer, read + * the DSCR and CTRLA then resume the DMA transfer. Nonetheless, + * this approach presents some drawbacks: + * - If the DMA transfer is paused, RX overruns or TX underruns + * are more likey to occur depending on the system latency. + * Taking the USART driver as an example, it uses a cyclic DMA + * transfer to read data from the Receive Holding Register + * (RHR) to avoid RX overruns since the RHR is not protected + * by any FIFO on most Atmel SoCs. So pausing the DMA transfer + * to compute the residue would break the USART driver design. + * - The atc_pause() function masks interrupts but we'd rather + * avoid to do so for system latency purpose. + * + * Then we'd rather use another solution: the DSCR is read a + * first time, the CTRLA is read in turn, next the DSCR is read + * a second time. If the two consecutive read values of the DSCR + * are the same then we assume both refers to the very same + * child descriptor as well as the CTRLA value read inbetween + * does. For cyclic tranfers, the assumption is that a full loop + * is "not so fast". + * If the two DSCR values are different, we read again the CTRLA + * then the DSCR till two consecutive read values from DSCR are + * equal or till the maxium trials is reach. + * This algorithm is very unlikely not to find a stable value for + * DSCR. */ - ctrla = channel_readl(atchan, CTRLA); - rmb(); /* ensure CTRLA is read before DSCR */ dscr = channel_readl(atchan, DSCR); + rmb(); /* ensure DSCR is read before CTRLA */ + ctrla = channel_readl(atchan, CTRLA); + for (trials = 0; trials < ATC_MAX_DSCR_TRIALS; ++trials) { + u32 new_dscr; + + rmb(); /* ensure DSCR is read after CTRLA */ + new_dscr = channel_readl(atchan, DSCR); + + /* + * If the DSCR register value has not changed inside the + * DMA controller since the previous read, we assume + * that both the dscr and ctrla values refers to the + * very same descriptor. + */ + if (likely(new_dscr == dscr)) + break; + + /* + * DSCR has changed inside the DMA controller, so the + * previouly read value of CTRLA may refer to an already + * processed descriptor hence could be outdated. + * We need to update ctrla to match the current + * descriptor. + */ + dscr = new_dscr; + rmb(); /* ensure DSCR is read before CTRLA */ + ctrla = channel_readl(atchan, CTRLA); + } + if (unlikely(trials >= ATC_MAX_DSCR_TRIALS)) + return -ETIMEDOUT; /* for the first descriptor we can be more accurate */ if (desc_first->lli.dscr == dscr) - return atc_calc_bytes_left(ret, ctrla, desc_first); + return atc_calc_bytes_left(ret, ctrla); ret -= desc_first->len; list_for_each_entry(desc, &desc_first->tx_list, desc_node) { @@ -365,16 +425,14 @@ static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie) } /* - * For the last descriptor in the chain we can calculate + * For the current descriptor in the chain we can calculate * the remaining bytes using the channel's register. - * Note that the transfer width of the first and last - * descriptor may differ. */ - if (!desc->lli.dscr) - ret = atc_calc_bytes_left_from_reg(ret, atchan, desc); + ret = atc_calc_bytes_left(ret, ctrla); } else { /* single transfer */ - ret = atc_calc_bytes_left_from_reg(ret, atchan, desc_first); + ctrla = channel_readl(atchan, CTRLA); + ret = atc_calc_bytes_left(ret, ctrla); } return ret; @@ -726,7 +784,6 @@ atc_prep_dma_interleaved(struct dma_chan *chan, desc->txd.cookie = -EBUSY; desc->total_len = desc->len = len; - desc->tx_width = dwidth; /* set end-of-link to the last link descriptor of list*/ set_desc_eol(desc); @@ -804,10 +861,6 @@ atc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, first->txd.cookie = -EBUSY; first->total_len = len; - /* set transfer width for the calculation of the residue */ - first->tx_width = src_width; - prev->tx_width = src_width; - /* set end-of-link to the last link descriptor of list*/ set_desc_eol(desc); @@ -956,10 +1009,6 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, first->txd.cookie = -EBUSY; first->total_len = total_len; - /* set transfer width for the calculation of the residue */ - first->tx_width = reg_width; - prev->tx_width = reg_width; - /* first link descriptor of list is responsible of flags */ first->txd.flags = flags; /* client is in control of this ack */ @@ -1077,12 +1126,6 @@ atc_prep_dma_sg(struct dma_chan *chan, desc->txd.cookie = 0; desc->len = len; - /* - * Although we only need the transfer width for the first and - * the last descriptor, its easier to set it to all descriptors. - */ - desc->tx_width = src_width; - atc_desc_chain(&first, &prev, desc); /* update the lengths and addresses for the next loop cycle */ @@ -1256,7 +1299,6 @@ atc_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len, /* First descriptor of the chain embedds additional information */ first->txd.cookie = -EBUSY; first->total_len = buf_len; - first->tx_width = reg_width; return &first->txd; diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h index bc8d5ebedd19..7f5a08230f76 100644 --- a/drivers/dma/at_hdmac_regs.h +++ b/drivers/dma/at_hdmac_regs.h @@ -112,6 +112,7 @@ #define ATC_SRC_WIDTH_BYTE (0x0 << 24) #define ATC_SRC_WIDTH_HALFWORD (0x1 << 24) #define ATC_SRC_WIDTH_WORD (0x2 << 24) +#define ATC_REG_TO_SRC_WIDTH(r) (((r) >> 24) & 0x3) #define ATC_DST_WIDTH_MASK (0x3 << 28) /* Destination Single Transfer Size */ #define ATC_DST_WIDTH(x) ((x) << 28) #define ATC_DST_WIDTH_BYTE (0x0 << 28) @@ -182,7 +183,6 @@ struct at_lli { * @txd: support for the async_tx api * @desc_node: node on the channed descriptors list * @len: descriptor byte count - * @tx_width: transfer width * @total_len: total transaction byte count */ struct at_desc { @@ -194,7 +194,6 @@ struct at_desc { struct dma_async_tx_descriptor txd; struct list_head desc_node; size_t len; - u32 tx_width; size_t total_len; /* Interleaved data */ From 1c8a38b1268aebc1a903b21b11575077e02d2cf7 Mon Sep 17 00:00:00 2001 From: Cyrille Pitchen Date: Tue, 30 Jun 2015 14:36:57 +0200 Subject: [PATCH 306/428] dmaengine: at_xdmac: fix transfer data width in at_xdmac_prep_slave_sg() This patch adds the missing update of the transfer data width in at_xdmac_prep_slave_sg(). Indeed, for each item in the scatter-gather list, we check whether the transfer length is aligned with the data width provided by dmaengine_slave_config(). If so, we directly use this data width for the current part of the transfer we are preparing. Otherwise, the data width is reduced to 8 bits (1 byte). Of course, the actual number of register accesses must also be updated to match the new data width. So one chunk was missing in the original patch (see Fixes tag below): the number of register accesses was correctly set to (len >> fixed_dwidth) in mbr_ubc but the real data width was not updated in mbr_cfg. Since mbr_cfg may change for each part of the scatter-gather transfer this also explains why the original patch used the Descriptor View 2 instead of the Descriptor View 1. Let's take the example of a DMA transfer to write 8bit data into an Atmel USART with FIFOs. When FIFOs are enabled in the USART, its Transmit Holding Register (THR) works in multidata mode, that is to say that up to 4 8bit data can be written into the THR in a single 32bit access and it is still possible to write only one data with a 8bit access. To take advantage of this new feature, the DMA driver was modified to allow multiple dwidths when doing slave transfers. For instance, when the total length is 22 bytes, the USART driver splits the transfer into 2 parts: First part: 20 bytes transferred through 5 32bit writes into THR Second part: 2 bytes transferred though 2 8bit writes into THR For the second part, the data width was first set to 4_BYTES by the USART driver thanks to dmaengine_slave_config() then at_xdmac_prep_slave_sg() reduces this data width to 1_BYTE because the 2 byte length is not aligned with the original 4_BYTES data width. Since the data width is modified, the actual number of writes into THR must be set accordingly. Signed-off-by: Cyrille Pitchen Fixes: 6d3a7d9e3ada ("dmaengine: at_xdmac: allow muliple dwidths when doing slave transfers") Cc: stable@vger.kernel.org #4.0 and later Acked-by: Nicolas Ferre Acked-by: Ludovic Desroches Signed-off-by: Vinod Koul --- drivers/dma/at_xdmac.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 52ca1ccefa3f..40afa2a16cfc 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -682,15 +682,16 @@ at_xdmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, desc->lld.mbr_sa = mem; desc->lld.mbr_da = atchan->sconfig.dst_addr; } - desc->lld.mbr_cfg = atchan->cfg; - dwidth = at_xdmac_get_dwidth(desc->lld.mbr_cfg); + dwidth = at_xdmac_get_dwidth(atchan->cfg); fixed_dwidth = IS_ALIGNED(len, 1 << dwidth) - ? at_xdmac_get_dwidth(desc->lld.mbr_cfg) + ? dwidth : AT_XDMAC_CC_DWIDTH_BYTE; desc->lld.mbr_ubc = AT_XDMAC_MBR_UBC_NDV2 /* next descriptor view */ | AT_XDMAC_MBR_UBC_NDEN /* next descriptor dst parameter update */ | AT_XDMAC_MBR_UBC_NSEN /* next descriptor src parameter update */ | (len >> fixed_dwidth); /* microblock length */ + desc->lld.mbr_cfg = (atchan->cfg & ~AT_XDMAC_CC_DWIDTH_MASK) | + AT_XDMAC_CC_DWIDTH(fixed_dwidth); dev_dbg(chan2dev(chan), "%s: lld: mbr_sa=%pad, mbr_da=%pad, mbr_ubc=0x%08x\n", __func__, &desc->lld.mbr_sa, &desc->lld.mbr_da, desc->lld.mbr_ubc); From cda8e937191c100025168ba3e22ab316c7298007 Mon Sep 17 00:00:00 2001 From: Rameshwar Prasad Sahu Date: Tue, 7 Jul 2015 15:34:25 +0530 Subject: [PATCH 307/428] dmaengine: xgene-dma: Fix the resource map to handle overlapping There is an overlap in dma ring cmd csr region due to sharing of ethernet ring cmd csr region. This patch fix the resource overlapping by mapping the entire dma ring cmd csr region. Signed-off-by: Rameshwar Prasad Sahu Signed-off-by: Vinod Koul --- Documentation/devicetree/bindings/dma/apm-xgene-dma.txt | 2 +- arch/arm64/boot/dts/apm/apm-storm.dtsi | 2 +- drivers/dma/xgene-dma.c | 3 +++ 3 files changed, 5 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/dma/apm-xgene-dma.txt b/Documentation/devicetree/bindings/dma/apm-xgene-dma.txt index d3058768b23d..c53e0b08032f 100644 --- a/Documentation/devicetree/bindings/dma/apm-xgene-dma.txt +++ b/Documentation/devicetree/bindings/dma/apm-xgene-dma.txt @@ -35,7 +35,7 @@ Example: device_type = "dma"; reg = <0x0 0x1f270000 0x0 0x10000>, <0x0 0x1f200000 0x0 0x10000>, - <0x0 0x1b008000 0x0 0x2000>, + <0x0 0x1b000000 0x0 0x400000>, <0x0 0x1054a000 0x0 0x100>; interrupts = <0x0 0x82 0x4>, <0x0 0xb8 0x4>, diff --git a/arch/arm64/boot/dts/apm/apm-storm.dtsi b/arch/arm64/boot/dts/apm/apm-storm.dtsi index 0689c3fb56e3..58093edeea2e 100644 --- a/arch/arm64/boot/dts/apm/apm-storm.dtsi +++ b/arch/arm64/boot/dts/apm/apm-storm.dtsi @@ -823,7 +823,7 @@ device_type = "dma"; reg = <0x0 0x1f270000 0x0 0x10000>, <0x0 0x1f200000 0x0 0x10000>, - <0x0 0x1b008000 0x0 0x2000>, + <0x0 0x1b000000 0x0 0x400000>, <0x0 0x1054a000 0x0 0x100>; interrupts = <0x0 0x82 0x4>, <0x0 0xb8 0x4>, diff --git a/drivers/dma/xgene-dma.c b/drivers/dma/xgene-dma.c index 620fd55ec766..dff22ab01851 100644 --- a/drivers/dma/xgene-dma.c +++ b/drivers/dma/xgene-dma.c @@ -111,6 +111,7 @@ #define XGENE_DMA_MEM_RAM_SHUTDOWN 0xD070 #define XGENE_DMA_BLK_MEM_RDY 0xD074 #define XGENE_DMA_BLK_MEM_RDY_VAL 0xFFFFFFFF +#define XGENE_DMA_RING_CMD_SM_OFFSET 0x8000 /* X-Gene SoC EFUSE csr register and bit defination */ #define XGENE_SOC_JTAG1_SHADOW 0x18 @@ -1887,6 +1888,8 @@ static int xgene_dma_get_resources(struct platform_device *pdev, return -ENOMEM; } + pdma->csr_ring_cmd += XGENE_DMA_RING_CMD_SM_OFFSET; + /* Get efuse csr region */ res = platform_get_resource(pdev, IORESOURCE_MEM, 3); if (!res) { From 0ec9ebc706fbd394bc233d87ac7aaad1c4f3ab54 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Wed, 8 Jul 2015 16:28:14 +0200 Subject: [PATCH 308/428] dmaengine: mv_xor: fix big endian operation in register mode Commit 6f166312c6ea2 ("dmaengine: mv_xor: add support for a38x command in descriptor mode") introduced the support for a feature that appeared in Armada 38x: specifying the operation to be performed in a per-descriptor basis rather than globally per channel. However, when doing so, it changed the function mv_chan_set_mode() to use: if (IS_ENABLED(__BIG_ENDIAN)) instead of: #if defined(__BIG_ENDIAN) While IS_ENABLED() is perfectly fine for CONFIG_* symbols, it is not for other symbols such as __BIG_ENDIAN that is provided directly by the compiler. Consequently, the commit broke support for big-endian, as the XOR_DESCRIPTOR_SWAP flag was not set in the XOR channel configuration register. The primarily visible effect was some nasty warnings and failures appearing during the self-test of the XOR unit: [ 1.197368] mv_xor d0060900.xor: error on chan 0. intr cause 0x00000082 [ 1.197393] mv_xor d0060900.xor: config 0x00008440 [ 1.197410] mv_xor d0060900.xor: activation 0x00000000 [ 1.197427] mv_xor d0060900.xor: intr cause 0x00000082 [ 1.197443] mv_xor d0060900.xor: intr mask 0x000003f7 [ 1.197460] mv_xor d0060900.xor: error cause 0x00000000 [ 1.197477] mv_xor d0060900.xor: error addr 0x00000000 [ 1.197491] ------------[ cut here ]------------ [ 1.197513] WARNING: CPU: 0 PID: 1 at ../drivers/dma/mv_xor.c:664 mv_xor_interrupt_handler+0x14c/0x170() See also: http://storage.kernelci.org/next/next-20150617/arm-mvebu_v7_defconfig+CONFIG_CPU_BIG_ENDIAN=y/lab-khilman/boot-armada-xp-openblocks-ax3-4.txt Signed-off-by: Thomas Petazzoni Fixes: 6f166312c6ea2 ("dmaengine: mv_xor: add support for a38x command in descriptor mode") Reviewed-by: Maxime Ripard Signed-off-by: Vinod Koul --- drivers/dma/mv_xor.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c index fbaf1ead2597..f1325f62563e 100644 --- a/drivers/dma/mv_xor.c +++ b/drivers/dma/mv_xor.c @@ -162,10 +162,11 @@ static void mv_chan_set_mode(struct mv_xor_chan *chan, config &= ~0x7; config |= op_mode; - if (IS_ENABLED(__BIG_ENDIAN)) - config |= XOR_DESCRIPTOR_SWAP; - else - config &= ~XOR_DESCRIPTOR_SWAP; +#if defined(__BIG_ENDIAN) + config |= XOR_DESCRIPTOR_SWAP; +#else + config &= ~XOR_DESCRIPTOR_SWAP; +#endif writel_relaxed(config, XOR_CONFIG(chan)); chan->current_type = type; From 8c8fe97b2b8a216523e2faf1ccca66ddab634e3e Mon Sep 17 00:00:00 2001 From: Jun Nie Date: Fri, 10 Jul 2015 20:02:49 +0800 Subject: [PATCH 309/428] Revert "dmaengine: virt-dma: don't always free descriptor upon completion" This reverts commit b9855f03d560d351e95301b9de0bc3cad3b31fe9. The patch break existing DMA usage case. For example, audio SOC dmaengine never release channel and cause virt-dma to cache too much memory in descriptor to exhaust system memory. Signed-off-by: Vinod Koul --- drivers/dma/virt-dma.c | 19 ++++++------------- drivers/dma/virt-dma.h | 13 +------------ 2 files changed, 7 insertions(+), 25 deletions(-) diff --git a/drivers/dma/virt-dma.c b/drivers/dma/virt-dma.c index 7d2c17d8d30f..6f80432a3f0a 100644 --- a/drivers/dma/virt-dma.c +++ b/drivers/dma/virt-dma.c @@ -29,7 +29,7 @@ dma_cookie_t vchan_tx_submit(struct dma_async_tx_descriptor *tx) spin_lock_irqsave(&vc->lock, flags); cookie = dma_cookie_assign(tx); - list_move_tail(&vd->node, &vc->desc_submitted); + list_add_tail(&vd->node, &vc->desc_submitted); spin_unlock_irqrestore(&vc->lock, flags); dev_dbg(vc->chan.device->dev, "vchan %p: txd %p[%x]: submitted\n", @@ -83,10 +83,8 @@ static void vchan_complete(unsigned long arg) cb_data = vd->tx.callback_param; list_del(&vd->node); - if (async_tx_test_ack(&vd->tx)) - list_add(&vd->node, &vc->desc_allocated); - else - vc->desc_free(vd); + + vc->desc_free(vd); if (cb) cb(cb_data); @@ -98,13 +96,9 @@ void vchan_dma_desc_free_list(struct virt_dma_chan *vc, struct list_head *head) while (!list_empty(head)) { struct virt_dma_desc *vd = list_first_entry(head, struct virt_dma_desc, node); - if (async_tx_test_ack(&vd->tx)) { - list_move_tail(&vd->node, &vc->desc_allocated); - } else { - dev_dbg(vc->chan.device->dev, "txd %p: freeing\n", vd); - list_del(&vd->node); - vc->desc_free(vd); - } + list_del(&vd->node); + dev_dbg(vc->chan.device->dev, "txd %p: freeing\n", vd); + vc->desc_free(vd); } } EXPORT_SYMBOL_GPL(vchan_dma_desc_free_list); @@ -114,7 +108,6 @@ void vchan_init(struct virt_dma_chan *vc, struct dma_device *dmadev) dma_cookie_init(&vc->chan); spin_lock_init(&vc->lock); - INIT_LIST_HEAD(&vc->desc_allocated); INIT_LIST_HEAD(&vc->desc_submitted); INIT_LIST_HEAD(&vc->desc_issued); INIT_LIST_HEAD(&vc->desc_completed); diff --git a/drivers/dma/virt-dma.h b/drivers/dma/virt-dma.h index 189e75dbcb15..181b95267866 100644 --- a/drivers/dma/virt-dma.h +++ b/drivers/dma/virt-dma.h @@ -29,7 +29,6 @@ struct virt_dma_chan { spinlock_t lock; /* protected by vc.lock */ - struct list_head desc_allocated; struct list_head desc_submitted; struct list_head desc_issued; struct list_head desc_completed; @@ -56,16 +55,11 @@ static inline struct dma_async_tx_descriptor *vchan_tx_prep(struct virt_dma_chan struct virt_dma_desc *vd, unsigned long tx_flags) { extern dma_cookie_t vchan_tx_submit(struct dma_async_tx_descriptor *); - unsigned long flags; dma_async_tx_descriptor_init(&vd->tx, &vc->chan); vd->tx.flags = tx_flags; vd->tx.tx_submit = vchan_tx_submit; - spin_lock_irqsave(&vc->lock, flags); - list_add_tail(&vd->node, &vc->desc_allocated); - spin_unlock_irqrestore(&vc->lock, flags); - return &vd->tx; } @@ -128,8 +122,7 @@ static inline struct virt_dma_desc *vchan_next_desc(struct virt_dma_chan *vc) } /** - * vchan_get_all_descriptors - obtain all allocated, submitted and issued - * descriptors + * vchan_get_all_descriptors - obtain all submitted and issued descriptors * vc: virtual channel to get descriptors from * head: list of descriptors found * @@ -141,7 +134,6 @@ static inline struct virt_dma_desc *vchan_next_desc(struct virt_dma_chan *vc) static inline void vchan_get_all_descriptors(struct virt_dma_chan *vc, struct list_head *head) { - list_splice_tail_init(&vc->desc_allocated, head); list_splice_tail_init(&vc->desc_submitted, head); list_splice_tail_init(&vc->desc_issued, head); list_splice_tail_init(&vc->desc_completed, head); @@ -149,14 +141,11 @@ static inline void vchan_get_all_descriptors(struct virt_dma_chan *vc, static inline void vchan_free_chan_resources(struct virt_dma_chan *vc) { - struct virt_dma_desc *vd; unsigned long flags; LIST_HEAD(head); spin_lock_irqsave(&vc->lock, flags); vchan_get_all_descriptors(vc, &head); - list_for_each_entry(vd, &head, node) - async_tx_clear_ack(&vd->tx); spin_unlock_irqrestore(&vc->lock, flags); vchan_dma_desc_free_list(vc, &head); From c1bfa985ded82cacdfc6403e78f329c44e35534a Mon Sep 17 00:00:00 2001 From: Murali Karicheri Date: Fri, 29 May 2015 12:04:13 -0400 Subject: [PATCH 310/428] ARM: dts: keystone: fix dt bindings to use post div register for mainpll All of the keystone devices have a separate register to hold post divider value for main pll clock. Currently the fixed-postdiv value used for k2hk/l/e SoCs works by sheer luck as u-boot happens to use a value of 2 for this. Now that we have fixed this in the pll clock driver change the dt bindings for the same. Signed-off-by: Murali Karicheri Acked-by: Santosh Shilimkar Signed-off-by: Olof Johansson --- arch/arm/boot/dts/k2e-clocks.dtsi | 5 ++--- arch/arm/boot/dts/k2hk-clocks.dtsi | 5 ++--- arch/arm/boot/dts/k2l-clocks.dtsi | 5 ++--- 3 files changed, 6 insertions(+), 9 deletions(-) diff --git a/arch/arm/boot/dts/k2e-clocks.dtsi b/arch/arm/boot/dts/k2e-clocks.dtsi index 4773d6af66a0..d56d68fe7ffc 100644 --- a/arch/arm/boot/dts/k2e-clocks.dtsi +++ b/arch/arm/boot/dts/k2e-clocks.dtsi @@ -13,9 +13,8 @@ clocks { #clock-cells = <0>; compatible = "ti,keystone,main-pll-clock"; clocks = <&refclksys>; - reg = <0x02620350 4>, <0x02310110 4>; - reg-names = "control", "multiplier"; - fixed-postdiv = <2>; + reg = <0x02620350 4>, <0x02310110 4>, <0x02310108 4>; + reg-names = "control", "multiplier", "post-divider"; }; papllclk: papllclk@2620358 { diff --git a/arch/arm/boot/dts/k2hk-clocks.dtsi b/arch/arm/boot/dts/k2hk-clocks.dtsi index d5adee3c0067..af9b7190533a 100644 --- a/arch/arm/boot/dts/k2hk-clocks.dtsi +++ b/arch/arm/boot/dts/k2hk-clocks.dtsi @@ -22,9 +22,8 @@ clocks { #clock-cells = <0>; compatible = "ti,keystone,main-pll-clock"; clocks = <&refclksys>; - reg = <0x02620350 4>, <0x02310110 4>; - reg-names = "control", "multiplier"; - fixed-postdiv = <2>; + reg = <0x02620350 4>, <0x02310110 4>, <0x02310108 4>; + reg-names = "control", "multiplier", "post-divider"; }; papllclk: papllclk@2620358 { diff --git a/arch/arm/boot/dts/k2l-clocks.dtsi b/arch/arm/boot/dts/k2l-clocks.dtsi index eb1e3e29f073..ef8464bb11ff 100644 --- a/arch/arm/boot/dts/k2l-clocks.dtsi +++ b/arch/arm/boot/dts/k2l-clocks.dtsi @@ -22,9 +22,8 @@ clocks { #clock-cells = <0>; compatible = "ti,keystone,main-pll-clock"; clocks = <&refclksys>; - reg = <0x02620350 4>, <0x02310110 4>; - reg-names = "control", "multiplier"; - fixed-postdiv = <2>; + reg = <0x02620350 4>, <0x02310110 4>, <0x02310108 4>; + reg-names = "control", "multiplier", "post-divider"; }; papllclk: papllclk@2620358 { From 8fcd461db7c09337b6d2e22d25eb411123f379e3 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 30 Jul 2015 06:57:46 -0400 Subject: [PATCH 311/428] nfsd: do nfs4_check_fh in nfs4_check_file instead of nfs4_check_olstateid Currently, preprocess_stateid_op calls nfs4_check_olstateid which verifies that the open stateid corresponds to the current filehandle in the call by calling nfs4_check_fh. If the stateid is a NFS4_DELEG_STID however, then no such check is done. This could cause incorrect enforcement of permissions, because the nfsd_permission() call in nfs4_check_file uses current the current filehandle, but any subsequent IO operation will use the file descriptor in the stateid. Move the call to nfs4_check_fh into nfs4_check_file instead so that it can be done for all stateid types. Signed-off-by: Jeff Layton Cc: stable@vger.kernel.org [bfields: moved fh check to avoid NULL deref in special stateid case] Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 61dfb33f0559..95202719a1fd 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -4396,9 +4396,9 @@ laundromat_main(struct work_struct *laundry) queue_delayed_work(laundry_wq, &nn->laundromat_work, t*HZ); } -static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_ol_stateid *stp) +static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stid *stp) { - if (!fh_match(&fhp->fh_handle, &stp->st_stid.sc_file->fi_fhandle)) + if (!fh_match(&fhp->fh_handle, &stp->sc_file->fi_fhandle)) return nfserr_bad_stateid; return nfs_ok; } @@ -4601,9 +4601,6 @@ nfs4_check_olstateid(struct svc_fh *fhp, struct nfs4_ol_stateid *ols, int flags) { __be32 status; - status = nfs4_check_fh(fhp, ols); - if (status) - return status; status = nfsd4_check_openowner_confirmed(ols); if (status) return status; @@ -4690,6 +4687,9 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, status = nfserr_bad_stateid; break; } + if (status) + goto out; + status = nfs4_check_fh(fhp, s); done: if (!status && filpp) @@ -4798,7 +4798,7 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_ status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate)); if (status) return status; - return nfs4_check_fh(current_fh, stp); + return nfs4_check_fh(current_fh, &stp->st_stid); } /* From 5175f7106cc55a1bcf97bf7d5ba0900017ebcef8 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Thu, 30 Jul 2015 17:12:21 -0700 Subject: [PATCH 312/428] act_pedit: check binding before calling tcf_hash_release() When we share an action within a filter, the bind refcnt should increase, therefore we should not call tcf_hash_release(). Fixes: 1a29321ed045 ("net_sched: act: Dont increment refcnt on replace") Cc: Jamal Hadi Salim Cc: Daniel Borkmann Signed-off-by: Cong Wang Signed-off-by: Cong Wang Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- net/sched/act_pedit.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 17e6d6669c7f..ff8b466a73f6 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -68,13 +68,12 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, } ret = ACT_P_CREATED; } else { - p = to_pedit(a); - tcf_hash_release(a, bind); if (bind) return 0; + tcf_hash_release(a, bind); if (!ovr) return -EEXIST; - + p = to_pedit(a); if (p->tcfp_nkeys && p->tcfp_nkeys != parm->nkeys) { keys = kmalloc(ksize, GFP_KERNEL); if (keys == NULL) From 8486830549189b109bfd40e8d38c6dd8b8f476db Mon Sep 17 00:00:00 2001 From: Claudiu Manoil Date: Fri, 31 Jul 2015 18:38:31 +0300 Subject: [PATCH 313/428] gianfar: Fix warning when CONFIG_PM off CC drivers/net/ethernet/freescale/gianfar.o drivers/net/ethernet/freescale/gianfar.c:568:13: warning: 'lock_tx_qs' defined but not used [-Wunused-function] static void lock_tx_qs(struct gfar_private *priv) ^ drivers/net/ethernet/freescale/gianfar.c:576:13: warning: 'unlock_tx_qs' defined but not used [-Wunused-function] static void unlock_tx_qs(struct gfar_private *priv) ^ Reported-by: Scott Wood Signed-off-by: Claudiu Manoil Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/gianfar.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index ff875028fdff..caad327e3f22 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -565,6 +565,7 @@ static void gfar_ints_enable(struct gfar_private *priv) } } +#ifdef CONFIG_PM static void lock_tx_qs(struct gfar_private *priv) { int i; @@ -580,6 +581,7 @@ static void unlock_tx_qs(struct gfar_private *priv) for (i = 0; i < priv->num_tx_queues; i++) spin_unlock(&priv->tx_queue[i]->txlock); } +#endif static int gfar_alloc_tx_queues(struct gfar_private *priv) { From 614b42426cc3483e8d5bc68a158c2dd47dc831d0 Mon Sep 17 00:00:00 2001 From: Claudiu Manoil Date: Fri, 31 Jul 2015 18:38:32 +0300 Subject: [PATCH 314/428] gianfar: Fix suspend/resume for wol magic packet If we disable NAPI in the first place we can mask the device's interrupts (and halt it) without fearing that imask may be concurrently accessed from interrupt context, so there's no need to do local_irq_save() around gfar_halt_nodisable(). lock_rx_qs()/unlock_tx_qs() are just obsoleted and potentially buggy routines. The txlock is currently used in the driver only to manage TX congestion, it has nothing to do with halting the device. With these changes, the TX processing is stopped before gfar_halt(). Compact gfar_halt() is used instead of gfar_halt_nodisable(), as it disables Rx/TX DMA h/w blocks and the Rx/TX h/w queues. gfar_start() re-enables all these blocks on resume. Enabling the magic-packet mode remains the same, note that the RX block is re-enabled just before entering sleep mode. Add IRQF_NO_SUSPEND flag for the error interrupt line, to signal that the interrupt line must remain active during sleep in order to wake the system by magic packet (MAG) reception interrupt. (On some systems the MAG interrupt did trigger w/o this flag as well, but on others it didn't.) Without these fixes, when suspended during fair Tx traffic the interface occasionally failed to be woken up by magic packet. Signed-off-by: Claudiu Manoil Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/gianfar.c | 98 ++++++++---------------- 1 file changed, 30 insertions(+), 68 deletions(-) diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index caad327e3f22..084c25d1467f 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -565,24 +565,6 @@ static void gfar_ints_enable(struct gfar_private *priv) } } -#ifdef CONFIG_PM -static void lock_tx_qs(struct gfar_private *priv) -{ - int i; - - for (i = 0; i < priv->num_tx_queues; i++) - spin_lock(&priv->tx_queue[i]->txlock); -} - -static void unlock_tx_qs(struct gfar_private *priv) -{ - int i; - - for (i = 0; i < priv->num_tx_queues; i++) - spin_unlock(&priv->tx_queue[i]->txlock); -} -#endif - static int gfar_alloc_tx_queues(struct gfar_private *priv) { int i; @@ -1542,48 +1524,37 @@ static int gfar_suspend(struct device *dev) struct gfar_private *priv = dev_get_drvdata(dev); struct net_device *ndev = priv->ndev; struct gfar __iomem *regs = priv->gfargrp[0].regs; - unsigned long flags; u32 tempval; - int magic_packet = priv->wol_en && (priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET); + if (!netif_running(ndev)) + return 0; + + disable_napi(priv); + netif_tx_lock(ndev); netif_device_detach(ndev); + netif_tx_unlock(ndev); - if (netif_running(ndev)) { + gfar_halt(priv); - local_irq_save(flags); - lock_tx_qs(priv); + if (magic_packet) { + /* Enable interrupt on Magic Packet */ + gfar_write(®s->imask, IMASK_MAG); - gfar_halt_nodisable(priv); + /* Enable Magic Packet mode */ + tempval = gfar_read(®s->maccfg2); + tempval |= MACCFG2_MPEN; + gfar_write(®s->maccfg2, tempval); - /* Disable Tx, and Rx if wake-on-LAN is disabled. */ + /* re-enable the Rx block */ tempval = gfar_read(®s->maccfg1); - - tempval &= ~MACCFG1_TX_EN; - - if (!magic_packet) - tempval &= ~MACCFG1_RX_EN; - + tempval |= MACCFG1_RX_EN; gfar_write(®s->maccfg1, tempval); - unlock_tx_qs(priv); - local_irq_restore(flags); - - disable_napi(priv); - - if (magic_packet) { - /* Enable interrupt on Magic Packet */ - gfar_write(®s->imask, IMASK_MAG); - - /* Enable Magic Packet mode */ - tempval = gfar_read(®s->maccfg2); - tempval |= MACCFG2_MPEN; - gfar_write(®s->maccfg2, tempval); - } else { - phy_stop(priv->phydev); - } + } else { + phy_stop(priv->phydev); } return 0; @@ -1594,37 +1565,26 @@ static int gfar_resume(struct device *dev) struct gfar_private *priv = dev_get_drvdata(dev); struct net_device *ndev = priv->ndev; struct gfar __iomem *regs = priv->gfargrp[0].regs; - unsigned long flags; u32 tempval; int magic_packet = priv->wol_en && (priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET); - if (!netif_running(ndev)) { - netif_device_attach(ndev); + if (!netif_running(ndev)) return 0; - } - if (!magic_packet && priv->phydev) + if (magic_packet) { + /* Disable Magic Packet mode */ + tempval = gfar_read(®s->maccfg2); + tempval &= ~MACCFG2_MPEN; + gfar_write(®s->maccfg2, tempval); + } else { phy_start(priv->phydev); - - /* Disable Magic Packet mode, in case something - * else woke us up. - */ - local_irq_save(flags); - lock_tx_qs(priv); - - tempval = gfar_read(®s->maccfg2); - tempval &= ~MACCFG2_MPEN; - gfar_write(®s->maccfg2, tempval); + } gfar_start(priv); - unlock_tx_qs(priv); - local_irq_restore(flags); - netif_device_attach(ndev); - enable_napi(priv); return 0; @@ -2047,7 +2007,8 @@ static int register_grp_irqs(struct gfar_priv_grp *grp) /* Install our interrupt handlers for Error, * Transmit, and Receive */ - err = request_irq(gfar_irq(grp, ER)->irq, gfar_error, 0, + err = request_irq(gfar_irq(grp, ER)->irq, gfar_error, + IRQF_NO_SUSPEND, gfar_irq(grp, ER)->name, grp); if (err < 0) { netif_err(priv, intr, dev, "Can't get IRQ %d\n", @@ -2070,7 +2031,8 @@ static int register_grp_irqs(struct gfar_priv_grp *grp) goto rx_irq_fail; } } else { - err = request_irq(gfar_irq(grp, TX)->irq, gfar_interrupt, 0, + err = request_irq(gfar_irq(grp, TX)->irq, gfar_interrupt, + IRQF_NO_SUSPEND, gfar_irq(grp, TX)->name, grp); if (err < 0) { netif_err(priv, intr, dev, "Can't get IRQ %d\n", From b0734b6dc895258b74c6e7a441cb47b6b0ba3465 Mon Sep 17 00:00:00 2001 From: Claudiu Manoil Date: Fri, 31 Jul 2015 18:38:33 +0300 Subject: [PATCH 315/428] gianfar: Enable device wakeup when appropriate The wol_en flag is 0 by default anyway, and we have the following inconsistency: a MAGIC packet wol capable eth interface is registered as a wake-up source but unable to wake-up the system as wol_en is 0 (wake-on flag set to 'd'). Calling set_wakeup_enable() at netdev open is just redundant because wol_en is 0 by default. Let only ethtool call set_wakeup_enable() for now. The bflock is obviously obsoleted, its utility has been corroded over time. The bitfield flags used today in gianfar are accessed only on the init/ config path, with no real possibility of concurrency - nothing that would justify smth. like bflock. Signed-off-by: Claudiu Manoil Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/gianfar.c | 8 ++------ drivers/net/ethernet/freescale/gianfar.h | 3 --- drivers/net/ethernet/freescale/gianfar_ethtool.c | 5 +---- 3 files changed, 3 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 084c25d1467f..2b7610f341b0 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -1360,7 +1360,6 @@ static int gfar_probe(struct platform_device *ofdev) priv->dev = &ofdev->dev; SET_NETDEV_DEV(dev, &ofdev->dev); - spin_lock_init(&priv->bflock); INIT_WORK(&priv->reset_task, gfar_reset_task); platform_set_drvdata(ofdev, priv); @@ -1454,9 +1453,8 @@ static int gfar_probe(struct platform_device *ofdev) goto register_fail; } - device_init_wakeup(&dev->dev, - priv->device_flags & - FSL_GIANFAR_DEV_HAS_MAGIC_PACKET); + device_set_wakeup_capable(&dev->dev, priv->device_flags & + FSL_GIANFAR_DEV_HAS_MAGIC_PACKET); /* fill out IRQ number and name fields */ for (i = 0; i < priv->num_grps; i++) { @@ -2133,8 +2131,6 @@ static int gfar_enet_open(struct net_device *dev) if (err) return err; - device_set_wakeup_enable(&dev->dev, priv->wol_en); - return err; } diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h index daa1d37de642..5545e4103368 100644 --- a/drivers/net/ethernet/freescale/gianfar.h +++ b/drivers/net/ethernet/freescale/gianfar.h @@ -1145,9 +1145,6 @@ struct gfar_private { int oldduplex; int oldlink; - /* Bitfield update lock */ - spinlock_t bflock; - uint32_t msg_enable; struct work_struct reset_task; diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c index fda12fb32ec7..3c0a8f825b63 100644 --- a/drivers/net/ethernet/freescale/gianfar_ethtool.c +++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c @@ -653,7 +653,6 @@ static void gfar_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) static int gfar_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) { struct gfar_private *priv = netdev_priv(dev); - unsigned long flags; if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET) && wol->wolopts != 0) @@ -664,9 +663,7 @@ static int gfar_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) device_set_wakeup_enable(&dev->dev, wol->wolopts & WAKE_MAGIC); - spin_lock_irqsave(&priv->bflock, flags); - priv->wol_en = !!device_may_wakeup(&dev->dev); - spin_unlock_irqrestore(&priv->bflock, flags); + priv->wol_en = !!device_may_wakeup(&dev->dev); return 0; } From ea111545843e657504193e4f726e1116b96b8141 Mon Sep 17 00:00:00 2001 From: Joachim Eastwood Date: Fri, 31 Jul 2015 19:13:22 +0200 Subject: [PATCH 316/428] stmmac: fix missing MODULE_LICENSE in stmmac_platform Commit 50649ab14982 ("stmmac: drop driver from stmmac platform code") was a bit overzealous in removing code and dropped the MODULE_* macro's that are still needed since stmmac_platform can be a module. Fix this by putting the macro's remvoed in 50649ab14982 back. This fixes the following errors when used as a module: stmmac_platform: module license 'unspecified' taints kernel. Disabling lock debugging due to kernel taint stmmac_platform: Unknown symbol devm_kmalloc (err 0) stmmac_platform: Unknown symbol stmmac_suspend (err 0) stmmac_platform: Unknown symbol platform_get_irq_byname (err 0) stmmac_platform: Unknown symbol stmmac_dvr_remove (err 0) stmmac_platform: Unknown symbol platform_get_resource (err 0) stmmac_platform: Unknown symbol of_get_phy_mode (err 0) stmmac_platform: Unknown symbol of_property_read_u32_array (err 0) stmmac_platform: Unknown symbol of_alias_get_id (err 0) stmmac_platform: Unknown symbol stmmac_resume (err 0) stmmac_platform: Unknown symbol stmmac_dvr_probe (err 0) Fixes: 50649ab14982 ("stmmac: drop driver from stmmac platform code") Reported-by: Igor Gnatenko Signed-off-by: Joachim Eastwood Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index f3918c7e7eeb..bcdc8955c719 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -413,3 +413,7 @@ static int stmmac_pltfr_resume(struct device *dev) SIMPLE_DEV_PM_OPS(stmmac_pltfr_pm_ops, stmmac_pltfr_suspend, stmmac_pltfr_resume); EXPORT_SYMBOL_GPL(stmmac_pltfr_pm_ops); + +MODULE_DESCRIPTION("STMMAC 10/100/1000 Ethernet platform support"); +MODULE_AUTHOR("Giuseppe Cavallaro "); +MODULE_LICENSE("GPL"); From 40c3ef9d2f14cce91dbd6ae9c9ccf6210d8c5df7 Mon Sep 17 00:00:00 2001 From: H Hartley Sweeten Date: Mon, 27 Jul 2015 10:27:21 -0700 Subject: [PATCH 317/428] staging: comedi: das1800: add missing break in switch Commit 06ad6bd8 "staging: comedi: das1800: cleanup das1800_probe()" Accidently removed the 'break' statement for case 0x8 of the switch. Add it back. Reported-by: coverity (CID 1309550) Signed-off-by: H Hartley Sweeten Reviewed-by: Ian Abbott Signed-off-by: Greg Kroah-Hartman --- drivers/staging/comedi/drivers/das1800.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/staging/comedi/drivers/das1800.c b/drivers/staging/comedi/drivers/das1800.c index bfa42620a3f6..940781183fac 100644 --- a/drivers/staging/comedi/drivers/das1800.c +++ b/drivers/staging/comedi/drivers/das1800.c @@ -1266,6 +1266,7 @@ static const struct das1800_board *das1800_probe(struct comedi_device *dev) if (index == das1801hc || index == das1802hc) return board; index = das1801hc; + break; default: dev_err(dev->class_dev, "Board model: probe returned 0x%x (unknown, please report)\n", From e3311469734093724b10c2a81c1193197db03b78 Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Mon, 27 Jul 2015 17:30:48 +0300 Subject: [PATCH 318/428] i2c: fix leaked device refcount on of_find_i2c_* error path If of_find_i2c_device_by_node() or of_find_i2c_adapter_by_node() find a device by node, but its type does not match, a reference to that device is still held. This change fixes the problem. Signed-off-by: Vladimir Zapolskiy Signed-off-by: Wolfram Sang --- drivers/i2c/i2c-core.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c index 8b64cf38beac..c83e4d13cfc5 100644 --- a/drivers/i2c/i2c-core.c +++ b/drivers/i2c/i2c-core.c @@ -1340,13 +1340,17 @@ static int of_dev_node_match(struct device *dev, void *data) struct i2c_client *of_find_i2c_device_by_node(struct device_node *node) { struct device *dev; + struct i2c_client *client; - dev = bus_find_device(&i2c_bus_type, NULL, node, - of_dev_node_match); + dev = bus_find_device(&i2c_bus_type, NULL, node, of_dev_node_match); if (!dev) return NULL; - return i2c_verify_client(dev); + client = i2c_verify_client(dev); + if (!client) + put_device(dev); + + return client; } EXPORT_SYMBOL(of_find_i2c_device_by_node); @@ -1354,13 +1358,17 @@ EXPORT_SYMBOL(of_find_i2c_device_by_node); struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node *node) { struct device *dev; + struct i2c_adapter *adapter; - dev = bus_find_device(&i2c_bus_type, NULL, node, - of_dev_node_match); + dev = bus_find_device(&i2c_bus_type, NULL, node, of_dev_node_match); if (!dev) return NULL; - return i2c_verify_adapter(dev); + adapter = i2c_verify_adapter(dev); + if (!adapter) + put_device(dev); + + return adapter; } EXPORT_SYMBOL(of_find_i2c_adapter_by_node); #else From 7167bf8b7f3f19eeea4602ccc39f26a26a636d8e Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Fri, 31 Jul 2015 10:01:40 +0200 Subject: [PATCH 319/428] phy-sun4i-usb: Add missing EXPORT_SYMBOL_GPL for sun4i_usb_phy_set_squelch_detect sun4i_usb_phy_set_squelch_detect is used by other code, which may be built as a module, so it should be exported. Signed-off-by: Hans de Goede Signed-off-by: Kishon Vijay Abraham I --- drivers/phy/phy-sun4i-usb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/phy/phy-sun4i-usb.c b/drivers/phy/phy-sun4i-usb.c index e17c539e4f6f..2dad7e820ff0 100644 --- a/drivers/phy/phy-sun4i-usb.c +++ b/drivers/phy/phy-sun4i-usb.c @@ -212,6 +212,7 @@ void sun4i_usb_phy_set_squelch_detect(struct phy *_phy, bool enabled) sun4i_usb_phy_write(phy, PHY_SQUELCH_DETECT, enabled ? 0 : 2, 2); } +EXPORT_SYMBOL_GPL(sun4i_usb_phy_set_squelch_detect); static struct phy_ops sun4i_usb_phy_ops = { .init = sun4i_usb_phy_init, From c934b3612747bde6c81cf10c2bbde956c6690aec Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Fri, 17 Jul 2015 16:47:22 +0300 Subject: [PATCH 320/428] phy: ti-pipe3: i783 workaround for SATA lockup after dpll unlock/relock SATA_PLL_SOFT_RESET bit of CTRL_CORE_SMA_SW_0 must be toggled between a SATA DPLL unlock and re-lock to prevent SATA lockup. Introduce a new DT parameter 'syscon-pllreset' to provide the syscon regmap access to this register which sits in the control module. If the register is not provided we fallback to the old behaviour i.e. SATA DPLL refclk will not be disabled and we prevent SoC low power states. Signed-off-by: Roger Quadros Signed-off-by: Kishon Vijay Abraham I --- .../devicetree/bindings/phy/ti-phy.txt | 16 +++++ drivers/phy/phy-ti-pipe3.c | 61 +++++++++++++++++-- 2 files changed, 71 insertions(+), 6 deletions(-) diff --git a/Documentation/devicetree/bindings/phy/ti-phy.txt b/Documentation/devicetree/bindings/phy/ti-phy.txt index 305e3df3d9b1..9cf9446eaf2e 100644 --- a/Documentation/devicetree/bindings/phy/ti-phy.txt +++ b/Documentation/devicetree/bindings/phy/ti-phy.txt @@ -82,6 +82,9 @@ Optional properties: - id: If there are multiple instance of the same type, in order to differentiate between each instance "id" can be used (e.g., multi-lane PCIe PHY). If "id" is not provided, it is set to default value of '1'. + - syscon-pllreset: Handle to system control region that contains the + CTRL_CORE_SMA_SW_0 register and register offset to the CTRL_CORE_SMA_SW_0 + register that contains the SATA_PLL_SOFT_RESET bit. Only valid for sata_phy. This is usually a subnode of ocp2scp to which it is connected. @@ -100,3 +103,16 @@ usb3phy@4a084400 { "sysclk", "refclk"; }; + +sata_phy: phy@4A096000 { + compatible = "ti,phy-pipe3-sata"; + reg = <0x4A096000 0x80>, /* phy_rx */ + <0x4A096400 0x64>, /* phy_tx */ + <0x4A096800 0x40>; /* pll_ctrl */ + reg-names = "phy_rx", "phy_tx", "pll_ctrl"; + ctrl-module = <&omap_control_sata>; + clocks = <&sys_clkin1>, <&sata_ref_clk>; + clock-names = "sysclk", "refclk"; + syscon-pllreset = <&scm_conf 0x3fc>; + #phy-cells = <0>; +}; diff --git a/drivers/phy/phy-ti-pipe3.c b/drivers/phy/phy-ti-pipe3.c index 3510b81db3fa..08020dc2c7c8 100644 --- a/drivers/phy/phy-ti-pipe3.c +++ b/drivers/phy/phy-ti-pipe3.c @@ -28,6 +28,8 @@ #include #include #include +#include +#include #define PLL_STATUS 0x00000004 #define PLL_GO 0x00000008 @@ -52,6 +54,8 @@ #define PLL_LOCK 0x2 #define PLL_IDLE 0x1 +#define SATA_PLL_SOFT_RESET BIT(18) + /* * This is an Empirical value that works, need to confirm the actual * value required for the PIPE3PHY_PLL_CONFIGURATION2.PLL_IDLE status @@ -82,6 +86,9 @@ struct ti_pipe3 { struct clk *refclk; struct clk *div_clk; struct pipe3_dpll_map *dpll_map; + struct regmap *dpll_reset_syscon; /* ctrl. reg. acces */ + unsigned int dpll_reset_reg; /* reg. index within syscon */ + bool sata_refclk_enabled; }; static struct pipe3_dpll_map dpll_map_usb[] = { @@ -249,8 +256,11 @@ static int ti_pipe3_exit(struct phy *x) u32 val; unsigned long timeout; - /* SATA DPLL can't be powered down due to Errata i783 */ - if (of_device_is_compatible(phy->dev->of_node, "ti,phy-pipe3-sata")) + /* If dpll_reset_syscon is not present we wont power down SATA DPLL + * due to Errata i783 + */ + if (of_device_is_compatible(phy->dev->of_node, "ti,phy-pipe3-sata") && + !phy->dpll_reset_syscon) return 0; /* PCIe doesn't have internal DPLL */ @@ -276,6 +286,14 @@ static int ti_pipe3_exit(struct phy *x) } } + /* i783: SATA needs control bit toggle after PLL unlock */ + if (of_device_is_compatible(phy->dev->of_node, "ti,phy-pipe3-sata")) { + regmap_update_bits(phy->dpll_reset_syscon, phy->dpll_reset_reg, + SATA_PLL_SOFT_RESET, SATA_PLL_SOFT_RESET); + regmap_update_bits(phy->dpll_reset_syscon, phy->dpll_reset_reg, + SATA_PLL_SOFT_RESET, 0); + } + ti_pipe3_disable_clocks(phy); return 0; @@ -350,6 +368,21 @@ static int ti_pipe3_probe(struct platform_device *pdev) } } else { phy->wkupclk = ERR_PTR(-ENODEV); + phy->dpll_reset_syscon = syscon_regmap_lookup_by_phandle(node, + "syscon-pllreset"); + if (IS_ERR(phy->dpll_reset_syscon)) { + dev_info(&pdev->dev, + "can't get syscon-pllreset, sata dpll won't idle\n"); + phy->dpll_reset_syscon = NULL; + } else { + if (of_property_read_u32_index(node, + "syscon-pllreset", 1, + &phy->dpll_reset_reg)) { + dev_err(&pdev->dev, + "couldn't get pllreset reg. offset\n"); + return -EINVAL; + } + } } if (of_device_is_compatible(node, "ti,phy-pipe3-pcie")) { @@ -402,10 +435,16 @@ static int ti_pipe3_probe(struct platform_device *pdev) platform_set_drvdata(pdev, phy); pm_runtime_enable(phy->dev); - /* Prevent auto-disable of refclk for SATA PHY due to Errata i783 */ - if (of_device_is_compatible(node, "ti,phy-pipe3-sata")) - if (!IS_ERR(phy->refclk)) + + /* + * Prevent auto-disable of refclk for SATA PHY due to Errata i783 + */ + if (of_device_is_compatible(node, "ti,phy-pipe3-sata")) { + if (!IS_ERR(phy->refclk)) { clk_prepare_enable(phy->refclk); + phy->sata_refclk_enabled = true; + } + } generic_phy = devm_phy_create(phy->dev, NULL, &ops); if (IS_ERR(generic_phy)) @@ -472,8 +511,18 @@ static void ti_pipe3_disable_clocks(struct ti_pipe3 *phy) { if (!IS_ERR(phy->wkupclk)) clk_disable_unprepare(phy->wkupclk); - if (!IS_ERR(phy->refclk)) + if (!IS_ERR(phy->refclk)) { clk_disable_unprepare(phy->refclk); + /* + * SATA refclk needs an additional disable as we left it + * on in probe to avoid Errata i783 + */ + if (phy->sata_refclk_enabled) { + clk_disable_unprepare(phy->refclk); + phy->sata_refclk_enabled = false; + } + } + if (!IS_ERR(phy->div_clk)) clk_disable_unprepare(phy->div_clk); } From 97242f99a013950af63effa0732f8ef7db4e31ec Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 1 Aug 2015 19:59:28 -0400 Subject: [PATCH 321/428] link_path_walk(): be careful when failing with ENOTDIR In RCU mode we might end up with dentry evicted just we check that it's a directory. In such case we should return ECHILD rather than ENOTDIR, so that pathwalk would be retries in non-RCU mode. Breakage had been introduced in commit b18825a - prior to that we were looking at nd->inode, which had been fetched before verifying that ->d_seq was still valid. That form of check would only be satisfied if at some point the pathname prefix would indeed have resolved to a non-directory. The fix consists of checking ->d_seq after we'd run into a non-directory dentry, and failing with ECHILD in case of mismatch. Note that all branches since 3.12 have that problem... Signed-off-by: Al Viro --- fs/namei.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/namei.c b/fs/namei.c index ae4e4c18b2ac..fbbcf0993312 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1954,8 +1954,13 @@ OK: continue; } } - if (unlikely(!d_can_lookup(nd->path.dentry))) + if (unlikely(!d_can_lookup(nd->path.dentry))) { + if (nd->flags & LOOKUP_RCU) { + if (unlazy_walk(nd, NULL, 0)) + return -ECHILD; + } return -ENOTDIR; + } } } From 27667f4744fc5a0f3e50910e78740bac5670d18b Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 29 Jul 2015 22:18:16 -0700 Subject: [PATCH 322/428] i915: temporary fix for DP MST docking station NULL pointer dereference Ted Ts'o reports that his Lenovo T540p ThinkPad crashes at boot if attached to the docking station. This is a regression that he was able to bisect to commit 8c7b5ccb7298: "drm/i915: Use atomic helpers for computing changed flags:" The reason seems to be the new call to drm_atomic_helper_check_modeset() added to intel_modeset_compute_config(), which in turn calls update_connector_routing(), and somehow ends up picking a NULL crtc for the connector state, causing the subsequent drm_crtc_index() to OOPS. Daniel Vetter says that the fundamental issue seems to be confusion in the encoder selection, and this isn't the right fix, but while he chases down the proper fix, this at least avoids the NULL pointer dereference and makes Ted's docking station work again. Reported-bisected-and-tested-by: Theodore Ts'o Cc: Daniel Vetter Cc: Mani Nikula Cc: Dave Airlie Signed-off-by: Linus Torvalds --- drivers/gpu/drm/drm_atomic_helper.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 5b59d5ad7d1c..aac212297b49 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -230,10 +230,12 @@ update_connector_routing(struct drm_atomic_state *state, int conn_idx) } connector_state->best_encoder = new_encoder; - idx = drm_crtc_index(connector_state->crtc); + if (connector_state->crtc) { + idx = drm_crtc_index(connector_state->crtc); - crtc_state = state->crtc_states[idx]; - crtc_state->mode_changed = true; + crtc_state = state->crtc_states[idx]; + crtc_state->mode_changed = true; + } DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] using [ENCODER:%d:%s] on [CRTC:%d]\n", connector->base.id, From 74d33293e467df61de1b1d8b2fbe29e550dec33b Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 2 Aug 2015 18:34:55 -0700 Subject: [PATCH 323/428] Linux 4.2-rc5 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index afabc44a349b..e79448d90f19 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 2 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc5 NAME = Hurr durr I'ma sheep # *DOCUMENTATION* From 423f04d63cf421ea436bcc5be02543d549ce4b28 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 27 Jul 2015 11:48:52 +1000 Subject: [PATCH 324/428] md/raid1: extend spinlock to protect raid1_end_read_request against inconsistencies raid1_end_read_request() assumes that the In_sync bits are consistent with the ->degaded count. raid1_spare_active updates the In_sync bit before the ->degraded count and so exposes an inconsistency, as does error() So extend the spinlock in raid1_spare_active() and error() to hide those inconsistencies. This should probably be part of Commit: 34cab6f42003 ("md/raid1: fix test for 'was read error from last working device'.") as it addresses the same issue. It fixes the same bug and should go to -stable for same reasons. Fixes: 76073054c95b ("md/raid1: clean up read_balance.") Cc: stable@vger.kernel.org (v3.0+) Signed-off-by: NeilBrown --- drivers/md/raid1.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 94f5b55069e0..967a4ed73929 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1476,6 +1476,7 @@ static void error(struct mddev *mddev, struct md_rdev *rdev) { char b[BDEVNAME_SIZE]; struct r1conf *conf = mddev->private; + unsigned long flags; /* * If it is not operational, then we have already marked it as dead @@ -1495,14 +1496,13 @@ static void error(struct mddev *mddev, struct md_rdev *rdev) return; } set_bit(Blocked, &rdev->flags); + spin_lock_irqsave(&conf->device_lock, flags); if (test_and_clear_bit(In_sync, &rdev->flags)) { - unsigned long flags; - spin_lock_irqsave(&conf->device_lock, flags); mddev->degraded++; set_bit(Faulty, &rdev->flags); - spin_unlock_irqrestore(&conf->device_lock, flags); } else set_bit(Faulty, &rdev->flags); + spin_unlock_irqrestore(&conf->device_lock, flags); /* * if recovery is running, make sure it aborts. */ @@ -1568,7 +1568,10 @@ static int raid1_spare_active(struct mddev *mddev) * Find all failed disks within the RAID1 configuration * and mark them readable. * Called under mddev lock, so rcu protection not needed. + * device_lock used to avoid races with raid1_end_read_request + * which expects 'In_sync' flags and ->degraded to be consistent. */ + spin_lock_irqsave(&conf->device_lock, flags); for (i = 0; i < conf->raid_disks; i++) { struct md_rdev *rdev = conf->mirrors[i].rdev; struct md_rdev *repl = conf->mirrors[conf->raid_disks + i].rdev; @@ -1599,7 +1602,6 @@ static int raid1_spare_active(struct mddev *mddev) sysfs_notify_dirent_safe(rdev->sysfs_state); } } - spin_lock_irqsave(&conf->device_lock, flags); mddev->degraded -= count; spin_unlock_irqrestore(&conf->device_lock, flags); From 528464eaa46ae1bd319882e4dd3495802e55b8c4 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 23 Jul 2015 14:32:32 +0530 Subject: [PATCH 325/428] thermal: remove dangling 'weight_attr' device file This file isn't getting removed while we unbind a device from thermal zone. And this causes following messages when the device is registered again: WARNING: CPU: 0 PID: 2228 at /home/viresh/linux/fs/sysfs/dir.c:31 sysfs_warn_dup+0x60/0x70() sysfs: cannot create duplicate filename '/devices/virtual/thermal/thermal_zone0/cdev0_weight' Modules linked in: cpufreq_dt(+) [last unloaded: cpufreq_dt] CPU: 0 PID: 2228 Comm: insmod Not tainted 4.2.0-rc3-00059-g44fffd9473eb #272 Hardware name: SAMSUNG EXYNOS (Flattened Device Tree) [] (unwind_backtrace) from [] (show_stack+0x10/0x14) [] (show_stack) from [] (dump_stack+0x84/0xc4) [] (dump_stack) from [] (warn_slowpath_common+0x80/0xb0) [] (warn_slowpath_common) from [] (warn_slowpath_fmt+0x30/0x40) [] (warn_slowpath_fmt) from [] (sysfs_warn_dup+0x60/0x70) [] (sysfs_warn_dup) from [] (sysfs_add_file_mode_ns+0x13c/0x190) [] (sysfs_add_file_mode_ns) from [] (sysfs_create_file_ns+0x3c/0x48) [] (sysfs_create_file_ns) from [] (thermal_zone_bind_cooling_device+0x260/0x358) [] (thermal_zone_bind_cooling_device) from [] (of_thermal_bind+0x88/0xb4) [] (of_thermal_bind) from [] (__thermal_cooling_device_register+0x17c/0x2e0) [] (__thermal_cooling_device_register) from [] (__cpufreq_cooling_register+0x3a0/0x51c) [] (__cpufreq_cooling_register) from [] (cpufreq_ready+0x44/0x88 [cpufreq_dt]) [] (cpufreq_ready [cpufreq_dt]) from [] (cpufreq_add_dev+0x4a0/0x7dc) [] (cpufreq_add_dev) from [] (subsys_interface_register+0x94/0xd8) [] (subsys_interface_register) from [] (cpufreq_register_driver+0x10c/0x1f0) [] (cpufreq_register_driver) from [] (dt_cpufreq_probe+0x60/0x8c [cpufreq_dt]) [] (dt_cpufreq_probe [cpufreq_dt]) from [] (platform_drv_probe+0x44/0xa4) [] (platform_drv_probe) from [] (driver_probe_device+0x174/0x2b4) [] (driver_probe_device) from [] (__driver_attach+0x8c/0x90) [] (__driver_attach) from [] (bus_for_each_dev+0x68/0x9c) [] (bus_for_each_dev) from [] (bus_add_driver+0x19c/0x214) [] (bus_add_driver) from [] (driver_register+0x78/0xf8) [] (driver_register) from [] (do_one_initcall+0x8c/0x1d4) [] (do_one_initcall) from [] (do_init_module+0x5c/0x1b8) [] (do_init_module) from [] (load_module+0xd34/0xed8) [] (load_module) from [] (SyS_init_module+0xd0/0x120) [] (SyS_init_module) from [] (ret_fast_syscall+0x0/0x3c) ---[ end trace 3be0e7b7dc6e3c4f ]--- Fixes: db91651311c8 ("thermal: export weight to sysfs") Acked-by: Javi Merino Signed-off-by: Viresh Kumar Signed-off-by: Eduardo Valentin --- drivers/thermal/thermal_core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 04659bfb888b..4ca211be4c0f 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -1333,6 +1333,7 @@ int thermal_zone_unbind_cooling_device(struct thermal_zone_device *tz, return -ENODEV; unbind: + device_remove_file(&tz->device, &pos->weight_attr); device_remove_file(&tz->device, &pos->attr); sysfs_remove_link(&tz->device.kobj, pos->name); release_idr(&tz->idr, &tz->lock, pos->id); From d5f831090191fa26a539e12456af64547ab11dde Mon Sep 17 00:00:00 2001 From: Javi Merino Date: Fri, 3 Jul 2015 10:24:33 +0100 Subject: [PATCH 326/428] thermal: power_allocator: trace the real requested power The power allocator governor uses ftrace to output a bunch of internal data for debugging and tuning. Currently, the requested power it outputs is the "weighted" requested power, that is, what each cooling device has requested multiplied by the cooling device weight. It is more useful to trace the real request, without any weight being applied. This commit only affects the data traced, there is no functional change. Cc: Zhang Rui Cc: Eduardo Valentin Signed-off-by: Javi Merino Signed-off-by: Eduardo Valentin --- drivers/thermal/power_allocator.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/drivers/thermal/power_allocator.c b/drivers/thermal/power_allocator.c index 4672250b329f..63a448f9d93b 100644 --- a/drivers/thermal/power_allocator.c +++ b/drivers/thermal/power_allocator.c @@ -229,7 +229,8 @@ static int allocate_power(struct thermal_zone_device *tz, struct thermal_instance *instance; struct power_allocator_params *params = tz->governor_data; u32 *req_power, *max_power, *granted_power, *extra_actor_power; - u32 total_req_power, max_allocatable_power; + u32 *weighted_req_power; + u32 total_req_power, max_allocatable_power, total_weighted_req_power; u32 total_granted_power, power_range; int i, num_actors, total_weight, ret = 0; int trip_max_desired_temperature = params->trip_max_desired_temperature; @@ -247,16 +248,17 @@ static int allocate_power(struct thermal_zone_device *tz, } /* - * We need to allocate three arrays of the same size: - * req_power, max_power and granted_power. They are going to - * be needed until this function returns. Allocate them all - * in one go to simplify the allocation and deallocation - * logic. + * We need to allocate five arrays of the same size: + * req_power, max_power, granted_power, extra_actor_power and + * weighted_req_power. They are going to be needed until this + * function returns. Allocate them all in one go to simplify + * the allocation and deallocation logic. */ BUILD_BUG_ON(sizeof(*req_power) != sizeof(*max_power)); BUILD_BUG_ON(sizeof(*req_power) != sizeof(*granted_power)); BUILD_BUG_ON(sizeof(*req_power) != sizeof(*extra_actor_power)); - req_power = devm_kcalloc(&tz->device, num_actors * 4, + BUILD_BUG_ON(sizeof(*req_power) != sizeof(*weighted_req_power)); + req_power = devm_kcalloc(&tz->device, num_actors * 5, sizeof(*req_power), GFP_KERNEL); if (!req_power) { ret = -ENOMEM; @@ -266,8 +268,10 @@ static int allocate_power(struct thermal_zone_device *tz, max_power = &req_power[num_actors]; granted_power = &req_power[2 * num_actors]; extra_actor_power = &req_power[3 * num_actors]; + weighted_req_power = &req_power[4 * num_actors]; i = 0; + total_weighted_req_power = 0; total_req_power = 0; max_allocatable_power = 0; @@ -289,13 +293,14 @@ static int allocate_power(struct thermal_zone_device *tz, else weight = instance->weight; - req_power[i] = frac_to_int(weight * req_power[i]); + weighted_req_power[i] = frac_to_int(weight * req_power[i]); if (power_actor_get_max_power(cdev, tz, &max_power[i])) continue; total_req_power += req_power[i]; max_allocatable_power += max_power[i]; + total_weighted_req_power += weighted_req_power[i]; i++; } @@ -303,8 +308,9 @@ static int allocate_power(struct thermal_zone_device *tz, power_range = pid_controller(tz, current_temp, control_temp, max_allocatable_power); - divvy_up_power(req_power, max_power, num_actors, total_req_power, - power_range, granted_power, extra_actor_power); + divvy_up_power(weighted_req_power, max_power, num_actors, + total_weighted_req_power, power_range, granted_power, + extra_actor_power); total_granted_power = 0; i = 0; From 5f09a5cbd14ae16e93866040fa44d930ff885650 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 8 Jun 2015 10:35:49 +0900 Subject: [PATCH 327/428] thermal: exynos: Disable the regulator on probe failure During probe the regulator (if present) was enabled but not disabled in case of failure. So an unsuccessful probe lead to enabling the regulator which was actually not needed because the device was not enabled. Additionally each deferred probe lead to increase of regulator enable count so it would not be effectively disabled during removal of the device. Test HW: Exynos4412 - Trats2 board Signed-off-by: Krzysztof Kozlowski Fixes: 498d22f616f6 ("thermal: exynos: Support for TMU regulator defined at device tree") Cc: Reviewed-by: Javier Martinez Canillas Signed-off-by: Lukasz Majewski Tested-by: Lukasz Majewski Signed-off-by: Eduardo Valentin --- drivers/thermal/samsung/exynos_tmu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/thermal/samsung/exynos_tmu.c b/drivers/thermal/samsung/exynos_tmu.c index 531f4b179871..13c3aceed19d 100644 --- a/drivers/thermal/samsung/exynos_tmu.c +++ b/drivers/thermal/samsung/exynos_tmu.c @@ -1392,6 +1392,8 @@ err_clk_sec: if (!IS_ERR(data->clk_sec)) clk_unprepare(data->clk_sec); err_sensor: + if (!IS_ERR_OR_NULL(data->regulator)) + regulator_disable(data->regulator); thermal_zone_of_sensor_unregister(&pdev->dev, data->tzd); return ret; From f87e6bd3f7401ee3c04248d8ea2dc32883a1f8fb Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Thu, 2 Jul 2015 15:40:00 +0900 Subject: [PATCH 328/428] thermal: exynos: Add the dependency of CONFIG_THERMAL_OF instead of CONFIG_OF The exynos thermal driver use the of_thermal_*() API to parse the basic data for thermal management from devicetree file. So, if CONFIG_EXYNOS_THERMAL is selected without CONFIG_THERMAL_OF, kernel can build it without any problem. But, exynos thermal driver is not working with following error log. This patch add the dependency of CONFIG_THERMAL_OF instead of CONFIG_OF. [ 1.458644] get_th_reg: Cannot get trip points from of-thermal.c! [ 1.459096] get_th_reg: Cannot get trip points from of-thermal.c! [ 1.465211] exynos4412_tmu_initialize: No CRITICAL trip point defined at of-thermal.c! Cc: Zhang Rui Cc: Eduardo Valentin Cc: Lukasz Majewski Signed-off-by: Chanwoo Choi Signed-off-by: Lukasz Majewski Signed-off-by: Eduardo Valentin --- drivers/thermal/samsung/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/thermal/samsung/Kconfig b/drivers/thermal/samsung/Kconfig index c8e35c1a43dc..e0da3865e060 100644 --- a/drivers/thermal/samsung/Kconfig +++ b/drivers/thermal/samsung/Kconfig @@ -1,6 +1,6 @@ config EXYNOS_THERMAL tristate "Exynos thermal management unit driver" - depends on OF + depends on THERMAL_OF help If you say yes here you get support for the TMU (Thermal Management Unit) driver for SAMSUNG EXYNOS series of SoCs. This driver initialises From 3c19d237dd8148926e49259e495ee41dddd1f09c Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Thu, 2 Jul 2015 15:40:01 +0900 Subject: [PATCH 329/428] thermal: exynos: Remove unused code related to platform_data on probe() This patch removes the unused code related to struct exynos_tmu_platform_data because exynos_tmu_probe() don't handle the struct exynos_tmu_platform_data *pdata. Test HW: Exynos4412 - Trats2 board Cc: Zhang Rui Cc: Eduardo Valentin Cc: Lukasz Majewski Signed-off-by: Chanwoo Choi Signed-off-by: Lukasz Majewski Tested-by: Lukasz Majewski Signed-off-by: Eduardo Valentin --- drivers/thermal/samsung/exynos_tmu.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/thermal/samsung/exynos_tmu.c b/drivers/thermal/samsung/exynos_tmu.c index 13c3aceed19d..c96ff10b869e 100644 --- a/drivers/thermal/samsung/exynos_tmu.c +++ b/drivers/thermal/samsung/exynos_tmu.c @@ -1296,7 +1296,6 @@ static struct thermal_zone_of_device_ops exynos_sensor_ops = { static int exynos_tmu_probe(struct platform_device *pdev) { - struct exynos_tmu_platform_data *pdata; struct exynos_tmu_data *data; int ret; @@ -1318,8 +1317,6 @@ static int exynos_tmu_probe(struct platform_device *pdev) if (ret) goto err_sensor; - pdata = data->pdata; - INIT_WORK(&data->irq_work, exynos_tmu_work); data->clk = devm_clk_get(&pdev->dev, "tmu_apbif"); From b6878d9e03043695dbf3fa1caa6dfc09db225b16 Mon Sep 17 00:00:00 2001 From: Benjamin Randazzo Date: Sat, 25 Jul 2015 16:36:50 +0200 Subject: [PATCH 330/428] md: use kzalloc() when bitmap is disabled In drivers/md/md.c get_bitmap_file() uses kmalloc() for creating a mdu_bitmap_file_t called "file". 5769 file = kmalloc(sizeof(*file), GFP_NOIO); 5770 if (!file) 5771 return -ENOMEM; This structure is copied to user space at the end of the function. 5786 if (err == 0 && 5787 copy_to_user(arg, file, sizeof(*file))) 5788 err = -EFAULT But if bitmap is disabled only the first byte of "file" is initialized with zero, so it's possible to read some bytes (up to 4095) of kernel space memory from user space. This is an information leak. 5775 /* bitmap disabled, zero the first byte and copy out */ 5776 if (!mddev->bitmap_info.file) 5777 file->pathname[0] = '\0'; Signed-off-by: Benjamin Randazzo Signed-off-by: NeilBrown --- drivers/md/md.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 0c2a4e8b873c..e25f00f0138a 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5759,7 +5759,7 @@ static int get_bitmap_file(struct mddev *mddev, void __user * arg) char *ptr; int err; - file = kmalloc(sizeof(*file), GFP_NOIO); + file = kzalloc(sizeof(*file), GFP_NOIO); if (!file) return -ENOMEM; From 49895bcc7e566ba455eb2996607d6fbd3447ce16 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 3 Aug 2015 17:09:57 +1000 Subject: [PATCH 331/428] md/raid5: don't let shrink_slab shrink too far. I have a report of drop_one_stripe() called from raid5_cache_scan() apparently finding ->max_nr_stripes == 0. This should not be allowed. So add a test to keep max_nr_stripes above min_nr_stripes. Also use a 'mask' rather than a 'mod' in drop_one_stripe to ensure 'hash' is valid even if max_nr_stripes does reach zero. Fixes: edbe83ab4c27 ("md/raid5: allow the stripe_cache to grow and shrink.") Cc: stable@vger.kernel.org (4.1 - please release with 2d5b569b665) Reported-by: Tomas Papan Signed-off-by: NeilBrown --- drivers/md/raid5.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 643d217bfa13..f757023fc458 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2256,7 +2256,7 @@ static int resize_stripes(struct r5conf *conf, int newsize) static int drop_one_stripe(struct r5conf *conf) { struct stripe_head *sh; - int hash = (conf->max_nr_stripes - 1) % NR_STRIPE_HASH_LOCKS; + int hash = (conf->max_nr_stripes - 1) & STRIPE_HASH_LOCKS_MASK; spin_lock_irq(conf->hash_locks + hash); sh = get_free_stripe(conf, hash); @@ -6388,7 +6388,8 @@ static unsigned long raid5_cache_scan(struct shrinker *shrink, if (mutex_trylock(&conf->cache_size_mutex)) { ret= 0; - while (ret < sc->nr_to_scan) { + while (ret < sc->nr_to_scan && + conf->max_nr_stripes > conf->min_nr_stripes) { if (drop_one_stripe(conf) == 0) { ret = SHRINK_STOP; break; From 9b2b6f7f357d9a2473017295bb26ff907e149d34 Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Sun, 19 Jul 2015 23:27:50 +0200 Subject: [PATCH 332/428] CPUFREQ: Loongson2: Fix broken build due to incorrect include. 71eeedcf51544831ae356a773814401143ed32d4 (MIPS: Lemote 2F: Fix build caused by recent mass rename.) only fixed one instance of this issue in arch/mips but missed a 2nd one in drivers/cpufreq/loongson2_cpufreq.c. [ralf@linux-mips.org: dropped the one segment for the already fixed instance and changed the other avoiding an include without a / because that's generally is a bad idea.] Signed-off-by: Ralf Baechle Acked-by: Viresh Kumar Patchwork: https://patchwork.linux-mips.org/patch/10659/ --- drivers/cpufreq/loongson2_cpufreq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/cpufreq/loongson2_cpufreq.c b/drivers/cpufreq/loongson2_cpufreq.c index e362860c2b50..cd593c1f66dc 100644 --- a/drivers/cpufreq/loongson2_cpufreq.c +++ b/drivers/cpufreq/loongson2_cpufreq.c @@ -20,7 +20,7 @@ #include #include -#include +#include static uint nowait; From d3557d96163d7d8250549a438232c5dd62d96959 Mon Sep 17 00:00:00 2001 From: Jonas Gorski Date: Sun, 19 Jul 2015 14:42:49 +0200 Subject: [PATCH 333/428] MIPS: Fix build with CONFIG_OF=y for non OF-enabled targets Commit 01306aeadd75 ("MIPS: prepare for user enabling of CONFIG_OF") changed the guards in asm/prom.h from CONFIG_OF to CONFIG_USE_OF, but missed the actual function declarations in kernel/prom.c, which have additional dependencies. Fixes the following build error: CC arch/mips/kernel/prom.o arch/mips/kernel/prom.c: In function '__dt_setup_arch': arch/mips/kernel/prom.c:54:2: error: implicit declaration of function 'early_init_dt_scan' [-Werror=implicit-function-declaration] if (!early_init_dt_scan(bph)) ^ Fixes: 01306aeadd75 ("MIPS: prepare for user enabling of CONFIG_OF") Signed-off-by: Jonas Gorski Acked-by: Rob Herring Cc: linux-mips@linux-mips.org Cc: devicetree@vger.kernel.org Cc: Grant Likely Patchwork: https://patchwork.linux-mips.org/patch/10741/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/prom.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/kernel/prom.c b/arch/mips/kernel/prom.c index b130033838ba..5fcec3032f38 100644 --- a/arch/mips/kernel/prom.c +++ b/arch/mips/kernel/prom.c @@ -38,7 +38,7 @@ char *mips_get_machine_name(void) return mips_machine_name; } -#ifdef CONFIG_OF +#ifdef CONFIG_USE_OF void __init early_init_dt_add_memory_arch(u64 base, u64 size) { return add_memory_region(base, size, BOOT_MEM_RAM); From 1d62d737555e1378eb62a8bba26644f7d97139d2 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Sun, 19 Jul 2015 00:38:41 +0200 Subject: [PATCH 334/428] MIPS: Fix sched_getaffinity with MT FPAFF enabled p->thread.user_cpus_allowed is zero-initialized and is only filled on the first sched_setaffinity call. To avoid adding overhead in the task initialization codepath, simply OR the returned mask in sched_getaffinity with p->cpus_allowed. Cc: stable@vger.kernel.org Signed-off-by: Felix Fietkau Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/10740/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/mips-mt-fpaff.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c index 3e4491aa6d6b..789d7bf4fef3 100644 --- a/arch/mips/kernel/mips-mt-fpaff.c +++ b/arch/mips/kernel/mips-mt-fpaff.c @@ -154,7 +154,7 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len, unsigned long __user *user_mask_ptr) { unsigned int real_len; - cpumask_t mask; + cpumask_t allowed, mask; int retval; struct task_struct *p; @@ -173,7 +173,8 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len, if (retval) goto out_unlock; - cpumask_and(&mask, &p->thread.user_cpus_allowed, cpu_possible_mask); + cpumask_or(&allowed, &p->thread.user_cpus_allowed, &p->cpus_allowed); + cpumask_and(&mask, &allowed, cpu_active_mask); out_unlock: read_unlock(&tasklist_lock); From 531a6d599f4304156236ebdd531aaa80be61868d Mon Sep 17 00:00:00 2001 From: James Cowgill Date: Tue, 23 Jun 2015 12:02:00 +0100 Subject: [PATCH 335/428] MIPS: unaligned: Fix build error on big endian R6 kernels Commit eeb538950367 ("MIPS: unaligned: Prevent EVA instructions on kernel unaligned accesses") renamed the Load* and Store* defines in unaligned.c to _Load* and _Store* as part of its fix. One define was missed out which causes big endian R6 kernels to fail to build. arch/mips/kernel/unaligned.c:880:35: error: implicit declaration of function '_StoreDW' #define StoreDW(addr, value, res) _StoreDW(addr, value, res) ^ Signed-off-by: James Cowgill Fixes: eeb538950367 ("MIPS: unaligned: Prevent EVA instructions on kernel unaligned accesses") Cc: Markos Chandras Cc: # 4.0+ Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/10575/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/unaligned.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c index af84bef0c90d..eb3efd137fd1 100644 --- a/arch/mips/kernel/unaligned.c +++ b/arch/mips/kernel/unaligned.c @@ -438,7 +438,7 @@ do { \ : "memory"); \ } while(0) -#define StoreDW(addr, value, res) \ +#define _StoreDW(addr, value, res) \ do { \ __asm__ __volatile__ ( \ ".set\tpush\n\t" \ From 106eccb4d20f35ebc58ff2286c170d9e79c5ff68 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Fri, 17 Jul 2015 15:54:41 +0100 Subject: [PATCH 336/428] MIPS: Malta: Don't reinitialise RTC On Malta, since commit a87ea88d8f6c ("MIPS: Malta: initialise the RTC at boot"), the RTC is reinitialised and forced into binary coded decimal (BCD) mode during init, even if the bootloader has already initialised it, and may even have already put it into binary mode (as YAMON does). This corrupts the current time, can result in the RTC seconds being an invalid BCD (e.g. 0x1a..0x1f) for up to 6 seconds, as well as confusing YAMON for a while after reset, enough for it to report timeouts when attempting to load from TFTP (it actually uses the RTC in that code). Therefore only initialise the RTC to the extent that is necessary so that Linux avoids interfering with the bootloader setup, while also allowing it to estimate the CPU frequency without hanging, without a bootloader necessarily having done anything with the RTC (for example when the kernel is loaded via EJTAG). The divider control is configured for a 32KHZ reference clock if necessary, and the SET bit of the RTC_CONTROL register is cleared if necessary without changing any other bits (this bit will be set when coming out of reset if the battery has been disconnected). Fixes: a87ea88d8f6c ("MIPS: Malta: initialise the RTC at boot") Signed-off-by: James Hogan Reviewed-by: Paul Burton Cc: Ralf Baechle Cc: Maciej W. Rozycki Cc: linux-mips@linux-mips.org Cc: # 3.14+ Patchwork: https://patchwork.linux-mips.org/patch/10739/ Signed-off-by: Ralf Baechle --- arch/mips/mti-malta/malta-time.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/arch/mips/mti-malta/malta-time.c b/arch/mips/mti-malta/malta-time.c index 5625b190edc0..c1dc730471e0 100644 --- a/arch/mips/mti-malta/malta-time.c +++ b/arch/mips/mti-malta/malta-time.c @@ -171,14 +171,17 @@ unsigned int get_c0_compare_int(void) static void __init init_rtc(void) { - /* stop the clock whilst setting it up */ - CMOS_WRITE(RTC_SET | RTC_24H, RTC_CONTROL); + unsigned char freq, ctrl; - /* 32KHz time base */ - CMOS_WRITE(RTC_REF_CLCK_32KHZ, RTC_FREQ_SELECT); + /* Set 32KHz time base if not already set */ + freq = CMOS_READ(RTC_FREQ_SELECT); + if ((freq & RTC_DIV_CTL) != RTC_REF_CLCK_32KHZ) + CMOS_WRITE(RTC_REF_CLCK_32KHZ, RTC_FREQ_SELECT); - /* start the clock */ - CMOS_WRITE(RTC_24H, RTC_CONTROL); + /* Ensure SET bit is clear so RTC can run */ + ctrl = CMOS_READ(RTC_CONTROL); + if (ctrl & RTC_SET) + CMOS_WRITE(ctrl & ~RTC_SET, RTC_CONTROL); } void __init plat_time_init(void) From e070dab73523bcbf2409ba8b5c342d53bccc0959 Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Thu, 23 Jul 2015 11:10:38 +0200 Subject: [PATCH 337/428] MIPS: Handle page faults of executable but unreadable pages correctly. Without this we end taking execeptions in an endless loop hanging the thread. Signed-off-by: Ralf Baechle --- arch/mips/mm/fault.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index 36c0f26fac6b..852a41c6da45 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -133,7 +133,8 @@ good_area: #endif goto bad_area; } - if (!(vma->vm_flags & VM_READ)) { + if (!(vma->vm_flags & VM_READ) && + exception_epc(regs) != address) { #if 0 pr_notice("Cpu%d[%s:%d:%0*lx:%ld:%0*lx] RI violation\n", raw_smp_processor_id(), From 55fdcb2d56b6edc027657fde9da0c4f224d32303 Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Thu, 23 Jul 2015 11:10:59 +0200 Subject: [PATCH 338/428] MIPS: Partially disable RIXI support. Execution of break instruction, trap instructions, emulation of unaligned loads or floating point instructions - anything that tries to read the instruction's opcode from userspace - needs read access to a page. RIXI (Read Inhibit / Execute Inhibit) support however allows the creation of pags that are executable but not readable. On such a mapping the attempted load of the opcode by the kernel is going to cause an endless loop of page faults. The quick workaround for this is to disable the combinations that the kernel currently isn't able to handle which are executable mappings. Signed-off-by: Ralf Baechle --- arch/mips/mm/cache.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c index 77d96db8253c..aab218c36e0d 100644 --- a/arch/mips/mm/cache.c +++ b/arch/mips/mm/cache.c @@ -160,18 +160,18 @@ static inline void setup_protection_map(void) protection_map[1] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC); protection_map[2] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ); protection_map[3] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC); - protection_map[4] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_READ); + protection_map[4] = __pgprot(_page_cachable_default | _PAGE_PRESENT); protection_map[5] = __pgprot(_page_cachable_default | _PAGE_PRESENT); - protection_map[6] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_READ); + protection_map[6] = __pgprot(_page_cachable_default | _PAGE_PRESENT); protection_map[7] = __pgprot(_page_cachable_default | _PAGE_PRESENT); protection_map[8] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ); protection_map[9] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC); protection_map[10] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE | _PAGE_NO_READ); protection_map[11] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE); - protection_map[12] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_READ); + protection_map[12] = __pgprot(_page_cachable_default | _PAGE_PRESENT); protection_map[13] = __pgprot(_page_cachable_default | _PAGE_PRESENT); - protection_map[14] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_WRITE | _PAGE_NO_READ); + protection_map[14] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_WRITE); protection_map[15] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_WRITE); } else { From 4ace6139bf23ab4f152ba4207fc10b76cc01d2a5 Mon Sep 17 00:00:00 2001 From: Alex Smith Date: Fri, 24 Jul 2015 16:57:49 +0100 Subject: [PATCH 339/428] MIPS: SMP: Don't increment irq_count multiple times for call function IPIs The majority of SMP platforms handle their IPIs through do_IRQ() which calls irq_{enter/exit}(). When a call function IPI is received, smp_call_function_interrupt() is called which also calls irq_{enter,exit}(), meaning irq_count is raised twice. When tick broadcasting is used (which is implemented via a call function IPI), this incorrectly causes all CPU idle time on the core receiving broadcast ticks to be accounted as time spent servicing IRQs, as account_process_tick() will account as such if irq_count is greater than 1. This results in 100% CPU usage being reported on a core which receives its ticks via broadcast. This patch removes the SMP smp_call_function_interrupt() wrapper which calls irq_{enter,exit}(). Platforms which handle their IPIs through do_IRQ() now call generic_smp_call_function_interrupt() directly to avoid incrementing irq_count a second time. Platforms which don't (loongson, sgi-ip27, sibyte) call generic_smp_call_function_interrupt() wrapped in irq_{enter,exit}(). Signed-off-by: Alex Smith Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/10770/ Signed-off-by: Ralf Baechle --- arch/mips/cavium-octeon/smp.c | 2 +- arch/mips/include/asm/smp.h | 2 -- arch/mips/kernel/smp-bmips.c | 4 ++-- arch/mips/kernel/smp.c | 10 ---------- arch/mips/lantiq/irq.c | 2 +- arch/mips/loongson64/loongson-3/smp.c | 7 +++++-- arch/mips/mti-malta/malta-int.c | 2 +- arch/mips/netlogic/common/smp.c | 2 +- arch/mips/paravirt/paravirt-smp.c | 2 +- arch/mips/pmcs-msp71xx/msp_smp.c | 2 +- arch/mips/sgi-ip27/ip27-irq.c | 8 ++++++-- arch/mips/sibyte/bcm1480/smp.c | 9 +++++---- arch/mips/sibyte/sb1250/smp.c | 7 +++++-- drivers/irqchip/irq-mips-gic.c | 2 +- 14 files changed, 30 insertions(+), 31 deletions(-) diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c index 56f5d080ef9d..b7fa9ae28c36 100644 --- a/arch/mips/cavium-octeon/smp.c +++ b/arch/mips/cavium-octeon/smp.c @@ -42,7 +42,7 @@ static irqreturn_t mailbox_interrupt(int irq, void *dev_id) cvmx_write_csr(CVMX_CIU_MBOX_CLRX(coreid), action); if (action & SMP_CALL_FUNCTION) - smp_call_function_interrupt(); + generic_smp_call_function_interrupt(); if (action & SMP_RESCHEDULE_YOURSELF) scheduler_ipi(); diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h index 16f1ea9ab191..03722d4326a1 100644 --- a/arch/mips/include/asm/smp.h +++ b/arch/mips/include/asm/smp.h @@ -83,8 +83,6 @@ static inline void __cpu_die(unsigned int cpu) extern void play_dead(void); #endif -extern asmlinkage void smp_call_function_interrupt(void); - static inline void arch_send_call_function_single_ipi(int cpu) { extern struct plat_smp_ops *mp_ops; /* private */ diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index 336708ae5c5b..78cf8c2f1de0 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -284,7 +284,7 @@ static irqreturn_t bmips5000_ipi_interrupt(int irq, void *dev_id) if (action == 0) scheduler_ipi(); else - smp_call_function_interrupt(); + generic_smp_call_function_interrupt(); return IRQ_HANDLED; } @@ -336,7 +336,7 @@ static irqreturn_t bmips43xx_ipi_interrupt(int irq, void *dev_id) if (action & SMP_RESCHEDULE_YOURSELF) scheduler_ipi(); if (action & SMP_CALL_FUNCTION) - smp_call_function_interrupt(); + generic_smp_call_function_interrupt(); return IRQ_HANDLED; } diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index d0744cc77ea7..a31896c33716 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -192,16 +192,6 @@ asmlinkage void start_secondary(void) cpu_startup_entry(CPUHP_ONLINE); } -/* - * Call into both interrupt handlers, as we share the IPI for them - */ -void __irq_entry smp_call_function_interrupt(void) -{ - irq_enter(); - generic_smp_call_function_interrupt(); - irq_exit(); -} - static void stop_this_cpu(void *dummy) { /* diff --git a/arch/mips/lantiq/irq.c b/arch/mips/lantiq/irq.c index 6ab10573490d..be18648cb8c8 100644 --- a/arch/mips/lantiq/irq.c +++ b/arch/mips/lantiq/irq.c @@ -293,7 +293,7 @@ static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id) static irqreturn_t ipi_call_interrupt(int irq, void *dev_id) { - smp_call_function_interrupt(); + generic_smp_call_function_interrupt(); return IRQ_HANDLED; } diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/loongson-3/smp.c index 509877c6e9d9..1a4738a8f2d3 100644 --- a/arch/mips/loongson64/loongson-3/smp.c +++ b/arch/mips/loongson64/loongson-3/smp.c @@ -266,8 +266,11 @@ void loongson3_ipi_interrupt(struct pt_regs *regs) if (action & SMP_RESCHEDULE_YOURSELF) scheduler_ipi(); - if (action & SMP_CALL_FUNCTION) - smp_call_function_interrupt(); + if (action & SMP_CALL_FUNCTION) { + irq_enter(); + generic_smp_call_function_interrupt(); + irq_exit(); + } if (action & SMP_ASK_C0COUNT) { BUG_ON(cpu != 0); diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c index d1392f8f5811..fa8f591f3713 100644 --- a/arch/mips/mti-malta/malta-int.c +++ b/arch/mips/mti-malta/malta-int.c @@ -222,7 +222,7 @@ static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id) static irqreturn_t ipi_call_interrupt(int irq, void *dev_id) { - smp_call_function_interrupt(); + generic_smp_call_function_interrupt(); return IRQ_HANDLED; } diff --git a/arch/mips/netlogic/common/smp.c b/arch/mips/netlogic/common/smp.c index dc3e327fbbac..f5fff228b347 100644 --- a/arch/mips/netlogic/common/smp.c +++ b/arch/mips/netlogic/common/smp.c @@ -86,7 +86,7 @@ void nlm_smp_function_ipi_handler(unsigned int irq, struct irq_desc *desc) { clear_c0_eimr(irq); ack_c0_eirr(irq); - smp_call_function_interrupt(); + generic_smp_call_function_interrupt(); set_c0_eimr(irq); } diff --git a/arch/mips/paravirt/paravirt-smp.c b/arch/mips/paravirt/paravirt-smp.c index 42181c7105df..f8d3e081b2eb 100644 --- a/arch/mips/paravirt/paravirt-smp.c +++ b/arch/mips/paravirt/paravirt-smp.c @@ -114,7 +114,7 @@ static irqreturn_t paravirt_reched_interrupt(int irq, void *dev_id) static irqreturn_t paravirt_function_interrupt(int irq, void *dev_id) { - smp_call_function_interrupt(); + generic_smp_call_function_interrupt(); return IRQ_HANDLED; } diff --git a/arch/mips/pmcs-msp71xx/msp_smp.c b/arch/mips/pmcs-msp71xx/msp_smp.c index 10170580a2de..ffa0f7101a97 100644 --- a/arch/mips/pmcs-msp71xx/msp_smp.c +++ b/arch/mips/pmcs-msp71xx/msp_smp.c @@ -44,7 +44,7 @@ static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id) static irqreturn_t ipi_call_interrupt(int irq, void *dev_id) { - smp_call_function_interrupt(); + generic_smp_call_function_interrupt(); return IRQ_HANDLED; } diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c index 3fbaef97a1b8..16ec4e12daa3 100644 --- a/arch/mips/sgi-ip27/ip27-irq.c +++ b/arch/mips/sgi-ip27/ip27-irq.c @@ -107,10 +107,14 @@ static void ip27_do_irq_mask0(void) scheduler_ipi(); } else if (pend0 & (1UL << CPU_CALL_A_IRQ)) { LOCAL_HUB_CLR_INTR(CPU_CALL_A_IRQ); - smp_call_function_interrupt(); + irq_enter(); + generic_smp_call_function_interrupt(); + irq_exit(); } else if (pend0 & (1UL << CPU_CALL_B_IRQ)) { LOCAL_HUB_CLR_INTR(CPU_CALL_B_IRQ); - smp_call_function_interrupt(); + irq_enter(); + generic_smp_call_function_interrupt(); + irq_exit(); } else #endif { diff --git a/arch/mips/sibyte/bcm1480/smp.c b/arch/mips/sibyte/bcm1480/smp.c index af7d44edd9a8..4c71aea25663 100644 --- a/arch/mips/sibyte/bcm1480/smp.c +++ b/arch/mips/sibyte/bcm1480/smp.c @@ -29,8 +29,6 @@ #include #include -extern void smp_call_function_interrupt(void); - /* * These are routines for dealing with the bcm1480 smp capabilities * independent of board/firmware @@ -184,6 +182,9 @@ void bcm1480_mailbox_interrupt(void) if (action & SMP_RESCHEDULE_YOURSELF) scheduler_ipi(); - if (action & SMP_CALL_FUNCTION) - smp_call_function_interrupt(); + if (action & SMP_CALL_FUNCTION) { + irq_enter(); + generic_smp_call_function_interrupt(); + irq_exit(); + } } diff --git a/arch/mips/sibyte/sb1250/smp.c b/arch/mips/sibyte/sb1250/smp.c index c0c4b3f88a08..1cf66f5ff23d 100644 --- a/arch/mips/sibyte/sb1250/smp.c +++ b/arch/mips/sibyte/sb1250/smp.c @@ -172,6 +172,9 @@ void sb1250_mailbox_interrupt(void) if (action & SMP_RESCHEDULE_YOURSELF) scheduler_ipi(); - if (action & SMP_CALL_FUNCTION) - smp_call_function_interrupt(); + if (action & SMP_CALL_FUNCTION) { + irq_enter(); + generic_smp_call_function_interrupt(); + irq_exit(); + } } diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index b7d54d428b5e..ff4be0515a0d 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -538,7 +538,7 @@ static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id) static irqreturn_t ipi_call_interrupt(int irq, void *dev_id) { - smp_call_function_interrupt(); + generic_smp_call_function_interrupt(); return IRQ_HANDLED; } From 55c723e181ccec30fb5c672397fe69ec35967d97 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Mon, 27 Jul 2015 13:50:21 +0100 Subject: [PATCH 340/428] MIPS: do_mcheck: Fix kernel code dump with EVA If a machine check exception is raised in kernel mode, user context, with EVA enabled, then the do_mcheck handler will attempt to read the code around the EPC using EVA load instructions, i.e. as if the reads were from user mode. This will either read random user data if the process has anything mapped at the same address, or it will cause an exception which is handled by __get_user, resulting in this output: Code: (Bad address in epc) Fix by setting the current user access mode to kernel if the saved register context indicates the exception was taken in kernel mode. This causes __get_user to use normal loads to read the kernel code. Signed-off-by: James Hogan Cc: Markos Chandras Cc: Leonid Yegoshin Cc: linux-mips@linux-mips.org Cc: # 3.15+ Patchwork: https://patchwork.linux-mips.org/patch/10777/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/traps.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index e207a43b5f8f..02484d17fb6f 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -1519,6 +1519,7 @@ asmlinkage void do_mcheck(struct pt_regs *regs) const int field = 2 * sizeof(unsigned long); int multi_match = regs->cp0_status & ST0_TS; enum ctx_state prev_state; + mm_segment_t old_fs = get_fs(); prev_state = exception_enter(); show_regs(regs); @@ -1540,8 +1541,13 @@ asmlinkage void do_mcheck(struct pt_regs *regs) dump_tlb_all(); } + if (!user_mode(regs)) + set_fs(KERNEL_DS); + show_code((unsigned int __user *) regs->cp0_epc); + set_fs(old_fs); + /* * Some chips may have other causes of machine check (e.g. SB1 * graduation timer) From 1e77863a51698c4319587df34171bd823691a66a Mon Sep 17 00:00:00 2001 From: James Hogan Date: Mon, 27 Jul 2015 13:50:22 +0100 Subject: [PATCH 341/428] MIPS: show_stack: Fix stack trace with EVA The show_stack() function deals exclusively with kernel contexts, but if it gets called in user context with EVA enabled, show_stacktrace() will attempt to access the stack using EVA accesses, which will either read other user mapped data, or more likely cause an exception which will be handled by __get_user(). This is easily reproduced using SysRq t to show all task states, which results in the following stack dump output: Stack : (Bad stack address) Fix by setting the current user access mode to kernel around the call to show_stacktrace(). This causes __get_user() to use normal loads to read the kernel stack. Now we get the correct output, like this: Stack : 00000000 80168960 00000000 004a0000 00000000 00000000 8060016c 1f3abd0c 1f172cd8 8056f09c 7ff1e450 8014fc3c 00000001 806dd0b0 0000001d 00000002 1f17c6a0 1f17c804 1f17c6a0 8066f6e0 00000000 0000000a 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 0110e800 1f3abd6c 1f17c6a0 ... Signed-off-by: James Hogan Cc: Markos Chandras Cc: Leonid Yegoshin Cc: linux-mips@linux-mips.org Cc: # 3.15+ Patchwork: https://patchwork.linux-mips.org/patch/10778/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/traps.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 02484d17fb6f..8ea28e6ab37d 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -192,6 +192,7 @@ static void show_stacktrace(struct task_struct *task, void show_stack(struct task_struct *task, unsigned long *sp) { struct pt_regs regs; + mm_segment_t old_fs = get_fs(); if (sp) { regs.regs[29] = (unsigned long)sp; regs.regs[31] = 0; @@ -210,7 +211,13 @@ void show_stack(struct task_struct *task, unsigned long *sp) prepare_frametrace(®s); } } + /* + * show_stack() deals exclusively with kernel mode, so be sure to access + * the stack in the kernel (not user) address space. + */ + set_fs(KERNEL_DS); show_stacktrace(task, ®s); + set_fs(old_fs); } static void show_code(unsigned int __user *pc) From 0cb0985f57783c2f3c6c8ffe7e7665e80c56bd92 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Thu, 23 Jul 2015 18:59:52 +0200 Subject: [PATCH 342/428] MIPS: Export get_c0_perfcount_int() get_c0_perfcount_int is tested from oprofile code. If oprofile is compiled as module, get_c0_perfcount_int needs to be exported, otherwise it cannot be resolved. Fixes: a669efc4a3b4 ("MIPS: Add hook to get C0 performance counter interrupt") Cc: stable@vger.kernel.org # v3.19+ Signed-off-by: Felix Fietkau Cc: linux-mips@linux-mips.org Cc: abrestic@chromium.org Patchwork: https://patchwork.linux-mips.org/patch/10763/ Signed-off-by: Ralf Baechle --- arch/mips/ath79/setup.c | 1 + arch/mips/lantiq/irq.c | 1 + arch/mips/mti-malta/malta-time.c | 1 + arch/mips/mti-sead3/sead3-time.c | 1 + arch/mips/pistachio/time.c | 1 + arch/mips/ralink/irq.c | 1 + 6 files changed, 6 insertions(+) diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c index 01a644f174dd..1ba21204ebe0 100644 --- a/arch/mips/ath79/setup.c +++ b/arch/mips/ath79/setup.c @@ -190,6 +190,7 @@ int get_c0_perfcount_int(void) { return ATH79_MISC_IRQ(5); } +EXPORT_SYMBOL_GPL(get_c0_perfcount_int); unsigned int get_c0_compare_int(void) { diff --git a/arch/mips/lantiq/irq.c b/arch/mips/lantiq/irq.c index be18648cb8c8..2c218c3bbca5 100644 --- a/arch/mips/lantiq/irq.c +++ b/arch/mips/lantiq/irq.c @@ -466,6 +466,7 @@ int get_c0_perfcount_int(void) { return ltq_perfcount_irq; } +EXPORT_SYMBOL_GPL(get_c0_perfcount_int); unsigned int get_c0_compare_int(void) { diff --git a/arch/mips/mti-malta/malta-time.c b/arch/mips/mti-malta/malta-time.c index c1dc730471e0..b7bf721eabf5 100644 --- a/arch/mips/mti-malta/malta-time.c +++ b/arch/mips/mti-malta/malta-time.c @@ -154,6 +154,7 @@ int get_c0_perfcount_int(void) return mips_cpu_perf_irq; } +EXPORT_SYMBOL_GPL(get_c0_perfcount_int); unsigned int get_c0_compare_int(void) { diff --git a/arch/mips/mti-sead3/sead3-time.c b/arch/mips/mti-sead3/sead3-time.c index e1d69895fb1d..a120b7a5a8fe 100644 --- a/arch/mips/mti-sead3/sead3-time.c +++ b/arch/mips/mti-sead3/sead3-time.c @@ -77,6 +77,7 @@ int get_c0_perfcount_int(void) return MIPS_CPU_IRQ_BASE + cp0_perfcount_irq; return -1; } +EXPORT_SYMBOL_GPL(get_c0_perfcount_int); unsigned int get_c0_compare_int(void) { diff --git a/arch/mips/pistachio/time.c b/arch/mips/pistachio/time.c index 7c73fcb92a10..8a377346f0ca 100644 --- a/arch/mips/pistachio/time.c +++ b/arch/mips/pistachio/time.c @@ -26,6 +26,7 @@ int get_c0_perfcount_int(void) { return gic_get_c0_perfcount_int(); } +EXPORT_SYMBOL_GPL(get_c0_perfcount_int); int get_c0_fdc_int(void) { diff --git a/arch/mips/ralink/irq.c b/arch/mips/ralink/irq.c index 53707aacc0f8..8c624a8b9ea2 100644 --- a/arch/mips/ralink/irq.c +++ b/arch/mips/ralink/irq.c @@ -89,6 +89,7 @@ int get_c0_perfcount_int(void) { return rt_perfcount_irq; } +EXPORT_SYMBOL_GPL(get_c0_perfcount_int); unsigned int get_c0_compare_int(void) { From 3592bb08fb2da21157bc2837c4c9a951b84d0c7a Mon Sep 17 00:00:00 2001 From: Kevin Cernekee Date: Tue, 28 Apr 2015 10:52:50 -0700 Subject: [PATCH 343/428] MIPS: BMIPS: Delete unused Kconfig symbol This was left over from an earlier iteration of the BMIPS irqchip changes. It doesn't actually have an effect, so let's nuke it. Reported-by: Valentin Rothberg Signed-off-by: Kevin Cernekee Acked-by: Florian Fainelli Cc: stable@vger.kernel.org # v4.1+ Cc: linux-mips@linux-mips.org Cc: linux-kernel@vger.kernel.org Patchwork: https://patchwork.linux-mips.org/patch/9910/ Signed-off-by: Ralf Baechle --- arch/mips/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index cee5f93e5712..199a8357838c 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -151,7 +151,6 @@ config BMIPS_GENERIC select BCM7120_L2_IRQ select BRCMSTB_L2_IRQ select IRQ_MIPS_CPU - select RAW_IRQ_ACCESSORS select DMA_NONCOHERENT select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_LITTLE_ENDIAN From 8ec7cfce3762299ae289c384e281b2f4010ae231 Mon Sep 17 00:00:00 2001 From: Tomer Barletz Date: Sun, 2 Aug 2015 02:08:57 -0700 Subject: [PATCH 344/428] ALSA: oxygen: Fix logical-not-parentheses warning This fixes the following warning, that is seen with gcc 5.1: warning: logical not is only applied to the left hand side of comparison [-Wlogical-not-parentheses]. Signed-off-by: Tomer Barletz Signed-off-by: Takashi Iwai --- sound/pci/oxygen/oxygen_mixer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/oxygen/oxygen_mixer.c b/sound/pci/oxygen/oxygen_mixer.c index 6492bca8c70f..4ca12665ff73 100644 --- a/sound/pci/oxygen/oxygen_mixer.c +++ b/sound/pci/oxygen/oxygen_mixer.c @@ -88,7 +88,7 @@ static int dac_mute_put(struct snd_kcontrol *ctl, int changed; mutex_lock(&chip->mutex); - changed = !value->value.integer.value[0] != chip->dac_mute; + changed = (!value->value.integer.value[0]) != chip->dac_mute; if (changed) { chip->dac_mute = !value->value.integer.value[0]; chip->model.update_dac_mute(chip); From 247bfb65d731350093f5d1a0a8b3d65e49c17baa Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 28 Jul 2015 19:24:24 -0700 Subject: [PATCH 345/428] Revert "MIPS: BCM63xx: Provide a plat_post_dma_flush hook" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit 3cf29543413207d3ab1c3f62a88c09bb46f2264e ("MIPS: BCM63xx: Provide a plat_post_dma_flush hook") since this commit was found to prevent BCM6358 (early BMIPS4350 cores) and some BCM6368 (BMIPS4380 cores) from booting reliably. Alvaro was able to track this down to an issue specifically located to devices that use the second thread (TP1) when booting. Since BCM63xx did not have a need for plat_post_dma_flush() hook before, let's just keep things the way they were. Reported-by: Álvaro Fernández Rojas Reported-by: Jonas Gorski Signed-off-by: Florian Fainelli Cc: stable@vger.kernel.org Cc: Kevin Cernekee Cc: Nicolas Schichan Cc: linux-mips@linux-mips.org Cc: blogic@openwrt.org Cc: noltari@gmail.com Cc: jogo@openwrt.org Cc: Florian Fainelli Cc: stable@vger.kernel.org Patchwork: https://patchwork.linux-mips.org/patch/10804/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/mach-bcm63xx/dma-coherence.h | 10 ---------- 1 file changed, 10 deletions(-) delete mode 100644 arch/mips/include/asm/mach-bcm63xx/dma-coherence.h diff --git a/arch/mips/include/asm/mach-bcm63xx/dma-coherence.h b/arch/mips/include/asm/mach-bcm63xx/dma-coherence.h deleted file mode 100644 index 11d3b572b1b3..000000000000 --- a/arch/mips/include/asm/mach-bcm63xx/dma-coherence.h +++ /dev/null @@ -1,10 +0,0 @@ -#ifndef __ASM_MACH_BCM63XX_DMA_COHERENCE_H -#define __ASM_MACH_BCM63XX_DMA_COHERENCE_H - -#include - -#define plat_post_dma_flush bmips_post_dma_flush - -#include - -#endif /* __ASM_MACH_BCM63XX_DMA_COHERENCE_H */ From 3aff47c062b944a5e1f9af56a37a23f5295628fc Mon Sep 17 00:00:00 2001 From: James Hogan Date: Fri, 31 Jul 2015 16:29:38 +0100 Subject: [PATCH 346/428] MIPS: Flush RPS on kernel entry with EVA When EVA is enabled, flush the Return Prediction Stack (RPS) present on some MIPS cores on entry to the kernel from user mode. This is important specifically for interAptiv with EVA enabled, otherwise kernel mode RPS mispredicts may trigger speculative fetches of user return addresses, which may be sensitive in the kernel address space due to EVA's overlapping user/kernel address spaces. Signed-off-by: James Hogan Cc: Ralf Baechle Cc: Markos Chandras Cc: Leonid Yegoshin Cc: linux-mips@linux-mips.org Cc: # 3.15.x- Patchwork: https://patchwork.linux-mips.org/patch/10812/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/stackframe.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/arch/mips/include/asm/stackframe.h b/arch/mips/include/asm/stackframe.h index 28d6d9364bd1..a71da576883c 100644 --- a/arch/mips/include/asm/stackframe.h +++ b/arch/mips/include/asm/stackframe.h @@ -152,6 +152,31 @@ .set noreorder bltz k0, 8f move k1, sp +#ifdef CONFIG_EVA + /* + * Flush interAptiv's Return Prediction Stack (RPS) by writing + * EntryHi. Toggling Config7.RPS is slower and less portable. + * + * The RPS isn't automatically flushed when exceptions are + * taken, which can result in kernel mode speculative accesses + * to user addresses if the RPS mispredicts. That's harmless + * when user and kernel share the same address space, but with + * EVA the same user segments may be unmapped to kernel mode, + * even containing sensitive MMIO regions or invalid memory. + * + * This can happen when the kernel sets the return address to + * ret_from_* and jr's to the exception handler, which looks + * more like a tail call than a function call. If nested calls + * don't evict the last user address in the RPS, it will + * mispredict the return and fetch from a user controlled + * address into the icache. + * + * More recent EVA-capable cores with MAAR to restrict + * speculative accesses aren't affected. + */ + MFC0 k0, CP0_ENTRYHI + MTC0 k0, CP0_ENTRYHI +#endif .set reorder /* Called from user mode, new stack. */ get_saved_sp From a4504755e7dc8d43ed2a934397032691cd03adf7 Mon Sep 17 00:00:00 2001 From: James Cowgill Date: Wed, 17 Jun 2015 17:12:50 +0100 Subject: [PATCH 347/428] MIPS: Replace add and sub instructions in relocate_kernel.S with addiu Fixes the assembler errors generated when compiling a MIPS R6 kernel with CONFIG_KEXEC on, by replacing the offending add and sub instructions with addiu instructions. Build errors: arch/mips/kernel/relocate_kernel.S: Assembler messages: arch/mips/kernel/relocate_kernel.S:27: Error: invalid operands `dadd $16,$16,8' arch/mips/kernel/relocate_kernel.S:64: Error: invalid operands `dadd $20,$20,8' arch/mips/kernel/relocate_kernel.S:65: Error: invalid operands `dadd $18,$18,8' arch/mips/kernel/relocate_kernel.S:66: Error: invalid operands `dsub $22,$22,1' scripts/Makefile.build:294: recipe for target 'arch/mips/kernel/relocate_kernel.o' failed Signed-off-by: James Cowgill Cc: # 4.0+ Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/10558/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/relocate_kernel.S | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/mips/kernel/relocate_kernel.S b/arch/mips/kernel/relocate_kernel.S index 74bab9ddd0e1..c6bbf2165051 100644 --- a/arch/mips/kernel/relocate_kernel.S +++ b/arch/mips/kernel/relocate_kernel.S @@ -24,7 +24,7 @@ LEAF(relocate_new_kernel) process_entry: PTR_L s2, (s0) - PTR_ADD s0, s0, SZREG + PTR_ADDIU s0, s0, SZREG /* * In case of a kdump/crash kernel, the indirection page is not @@ -61,9 +61,9 @@ copy_word: /* copy page word by word */ REG_L s5, (s2) REG_S s5, (s4) - PTR_ADD s4, s4, SZREG - PTR_ADD s2, s2, SZREG - LONG_SUB s6, s6, 1 + PTR_ADDIU s4, s4, SZREG + PTR_ADDIU s2, s2, SZREG + LONG_ADDIU s6, s6, -1 beq s6, zero, process_entry b copy_word b process_entry From e13c42ecbe580509451e021ba2586871e5b47640 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Mon, 3 Aug 2015 15:37:24 +0530 Subject: [PATCH 348/428] ARCv2: Fix the peripheral address space detection With HS 2.1 release, the peripheral space register no longer contains the uncached space specifics, causing the kernel to panic early on. So read the newer NON VOLATILE AUX register to get that info. Signed-off-by: Vineet Gupta --- arch/arc/include/asm/arcregs.h | 7 +++---- arch/arc/kernel/setup.c | 8 +++++++- 2 files changed, 10 insertions(+), 5 deletions(-) diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h index 070f58827a5c..c8f57b8449dc 100644 --- a/arch/arc/include/asm/arcregs.h +++ b/arch/arc/include/asm/arcregs.h @@ -89,11 +89,10 @@ #define ECR_C_BIT_DTLB_LD_MISS 8 #define ECR_C_BIT_DTLB_ST_MISS 9 - /* Auxiliary registers */ #define AUX_IDENTITY 4 #define AUX_INTR_VEC_BASE 0x25 - +#define AUX_NON_VOL 0x5e /* * Floating Pt Registers @@ -240,9 +239,9 @@ struct bcr_extn_xymem { struct bcr_perip { #ifdef CONFIG_CPU_BIG_ENDIAN - unsigned int start:8, pad2:8, sz:8, pad:8; + unsigned int start:8, pad2:8, sz:8, ver:8; #else - unsigned int pad:8, sz:8, pad2:8, start:8; + unsigned int ver:8, sz:8, pad2:8, start:8; #endif }; diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index 18cc01591c96..f2f771bd3ede 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -47,6 +47,7 @@ static void read_arc_build_cfg_regs(void) struct bcr_perip uncached_space; struct bcr_generic bcr; struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()]; + unsigned long perip_space; FIX_PTR(cpu); READ_BCR(AUX_IDENTITY, cpu->core); @@ -56,7 +57,12 @@ static void read_arc_build_cfg_regs(void) cpu->vec_base = read_aux_reg(AUX_INTR_VEC_BASE); READ_BCR(ARC_REG_D_UNCACH_BCR, uncached_space); - BUG_ON((uncached_space.start << 24) != ARC_UNCACHED_ADDR_SPACE); + if (uncached_space.ver < 3) + perip_space = uncached_space.start << 24; + else + perip_space = read_aux_reg(AUX_NON_VOL) & 0xF0000000; + + BUG_ON(perip_space != ARC_UNCACHED_ADDR_SPACE); READ_BCR(ARC_REG_MUL_BCR, cpu->extn_mpy); From c93e64e91248becd0edb8f01723dff9da890e2ab Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 16 Jan 2015 11:32:51 -0500 Subject: [PATCH 349/428] usb: udc: core: add device_del() call to error pathway This patch fixes a bug in the error pathway of usb_add_gadget_udc_release() in udc-core.c. If the udc registration fails, the gadget registration is not fully undone; there's a put_device(&gadget->dev) call but no device_del(). CC: Acked-by: Peter Chen Signed-off-by: Alan Stern Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/udc-core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/gadget/udc/udc-core.c b/drivers/usb/gadget/udc/udc-core.c index 362ee8af5fce..89ed5e71a199 100644 --- a/drivers/usb/gadget/udc/udc-core.c +++ b/drivers/usb/gadget/udc/udc-core.c @@ -323,6 +323,7 @@ err4: err3: put_device(&udc->dev); + device_del(&gadget->dev); err2: put_device(&gadget->dev); From 6b5e38dccd2c72b62c57681861ba3594117d993e Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 10 Jul 2015 15:35:00 +0900 Subject: [PATCH 350/428] thermal: Drop owner assignment from platform_driver platform_driver does not need to set an owner because platform_driver_register() will set it. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Zhang Rui --- drivers/thermal/hisi_thermal.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/thermal/hisi_thermal.c b/drivers/thermal/hisi_thermal.c index d5dd357ba57c..b49f97c734d0 100644 --- a/drivers/thermal/hisi_thermal.c +++ b/drivers/thermal/hisi_thermal.c @@ -405,7 +405,6 @@ static SIMPLE_DEV_PM_OPS(hisi_thermal_pm_ops, static struct platform_driver hisi_thermal_driver = { .driver = { .name = "hisi_thermal", - .owner = THIS_MODULE, .pm = &hisi_thermal_pm_ops, .of_match_table = of_hisi_thermal_match, }, From 5413fcdbe9e7ca32ce3f00fd5251dfa560b7484b Mon Sep 17 00:00:00 2001 From: Salvatore Mesoraca Date: Mon, 3 Aug 2015 12:40:51 +0200 Subject: [PATCH 351/428] Adding YAMA hooks also when YAMA is not stacked. Without this patch YAMA will not work at all if it is chosen as the primary LSM instead of being "stacked". Signed-off-by: Salvatore Mesoraca Acked-by: Kees Cook Signed-off-by: James Morris --- security/yama/yama_lsm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c index 9ed32502470e..5ebb89687936 100644 --- a/security/yama/yama_lsm.c +++ b/security/yama/yama_lsm.c @@ -406,6 +406,7 @@ static __init int yama_init(void) */ if (!security_module_enable("yama")) return 0; + yama_add_hooks(); #endif pr_info("Yama: becoming mindful.\n"); From a094935e4ebdf5c22c45b8aeeb2d88e9e8c53dbf Mon Sep 17 00:00:00 2001 From: Bard Liao Date: Mon, 3 Aug 2015 12:17:39 +0800 Subject: [PATCH 352/428] ASoC: rt5645: Fix lost pin setting for DMIC1 I2S2_DAC pin can be used for I2S or GPIO. We should set it as GPIO if we use GPIO5 as DMIC1 data pin. Signed-off-by: Bard Liao Signed-off-by: Mark Brown --- sound/soc/codecs/rt5645.c | 2 ++ sound/soc/codecs/rt5645.h | 4 ++++ 2 files changed, 6 insertions(+) diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index e9cc3aae5366..961bd7e5877e 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -3341,6 +3341,8 @@ static int rt5645_i2c_probe(struct i2c_client *i2c, break; case RT5645_DMIC_DATA_GPIO5: + regmap_update_bits(rt5645->regmap, RT5645_GPIO_CTRL1, + RT5645_I2S2_DAC_PIN_MASK, RT5645_I2S2_DAC_PIN_GPIO); regmap_update_bits(rt5645->regmap, RT5645_DMIC_CTRL1, RT5645_DMIC_1_DP_MASK, RT5645_DMIC_1_DP_GPIO5); regmap_update_bits(rt5645->regmap, RT5645_GPIO_CTRL1, diff --git a/sound/soc/codecs/rt5645.h b/sound/soc/codecs/rt5645.h index 0353a6a273ab..278bb9f464c4 100644 --- a/sound/soc/codecs/rt5645.h +++ b/sound/soc/codecs/rt5645.h @@ -1693,6 +1693,10 @@ #define RT5645_GP6_PIN_SFT 6 #define RT5645_GP6_PIN_GPIO6 (0x0 << 6) #define RT5645_GP6_PIN_DMIC2_SDA (0x1 << 6) +#define RT5645_I2S2_DAC_PIN_MASK (0x1 << 4) +#define RT5645_I2S2_DAC_PIN_SFT 4 +#define RT5645_I2S2_DAC_PIN_I2S (0x0 << 4) +#define RT5645_I2S2_DAC_PIN_GPIO (0x1 << 4) #define RT5645_GP8_PIN_MASK (0x1 << 3) #define RT5645_GP8_PIN_SFT 3 #define RT5645_GP8_PIN_GPIO8 (0x0 << 3) From c20bc5502d151ca731ebc672b95aa77e2bf32c8c Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Thu, 30 Jul 2015 11:01:13 -0700 Subject: [PATCH 353/428] Input: turbografx - fix potential out of bound access Patch 17dd3f0f7aa7: "[PATCH] drivers/input/joystick: convert to dynamic input_dev allocation" from Sep 15, 2005, leads to the following static checker warning: drivers/input/joystick/turbografx.c:235 tgfx_probe() error: buffer overflow 'tgfx_buttons' 5 <= 5 drivers/input/joystick/turbografx.c 195 for (i = 0; i < n_devs; i++) { 196 if (n_buttons[i] < 1) 197 continue; 198 199 if (n_buttons[i] > 6) { ^^^^^^^^^^^^^^^^ Possibly off by one. >= 6. Let's change the upper value to ARRAY_SIZE(tgfx_buttons) to ensure we do not reach past the end of the array. Reported-by: Dan Carpenter Reviewed-by: Dan Carpenter Signed-off-by: Dmitry Torokhov --- drivers/input/joystick/turbografx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/input/joystick/turbografx.c b/drivers/input/joystick/turbografx.c index 27b6a3ce18ca..891797ad76bc 100644 --- a/drivers/input/joystick/turbografx.c +++ b/drivers/input/joystick/turbografx.c @@ -196,7 +196,7 @@ static struct tgfx __init *tgfx_probe(int parport, int *n_buttons, int n_devs) if (n_buttons[i] < 1) continue; - if (n_buttons[i] > 6) { + if (n_buttons[i] > ARRAY_SIZE(tgfx_buttons)) { printk(KERN_ERR "turbografx.c: Invalid number of buttons %d\n", n_buttons[i]); err = -EINVAL; goto err_unreg_devs; From b6e26546cc08e870da5413a3fcccc100eb2192c6 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Mon, 3 Aug 2015 13:29:29 -0700 Subject: [PATCH 354/428] Input: axp20x-pek - add module alias Add a proper module alias so the driver can be autoloaded when the parent axp20x mfd driver registers its cells. Signed-off-by: Chen-Yu Tsai Acked-by: Carlo Caione Signed-off-by: Dmitry Torokhov --- drivers/input/misc/axp20x-pek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/input/misc/axp20x-pek.c b/drivers/input/misc/axp20x-pek.c index 10e140af5aac..1ac898db303a 100644 --- a/drivers/input/misc/axp20x-pek.c +++ b/drivers/input/misc/axp20x-pek.c @@ -292,3 +292,4 @@ module_platform_driver(axp20x_pek_driver); MODULE_DESCRIPTION("axp20x Power Button"); MODULE_AUTHOR("Carlo Caione "); MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:axp20x-pek"); From 073e570d7c2caae9910a993d56f340be4548a4a8 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 3 Aug 2015 14:06:24 -0700 Subject: [PATCH 355/428] Input: alps - only Dell laptops have separate button bits for v2 dualpoint sticks It turns out that only Dell laptops have the separate button bits for v2 dualpoint sticks and that commit 92bac83dd79e ("Input: alps - non interleaved V2 dualpoint has separate stick button bits") causes regressions on Toshiba laptops. This commit adds a check for Dell laptops to the code for handling these extra button bits, fixing this regression. This patch has been tested on a Dell Latitude D620 to make sure that it does not reintroduce the original problem. Reported-and-tested-by: Douglas Christman Cc: stable@vger.kernel.org Signed-off-by: Hans de Goede Signed-off-by: Dmitry Torokhov --- Documentation/input/alps.txt | 6 ++++-- drivers/input/mouse/alps.c | 8 ++++++-- 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/Documentation/input/alps.txt b/Documentation/input/alps.txt index e301887d8523..765d99cdadbb 100644 --- a/Documentation/input/alps.txt +++ b/Documentation/input/alps.txt @@ -119,8 +119,10 @@ ALPS Absolute Mode - Protocol Version 2 byte 5: 0 z6 z5 z4 z3 z2 z1 z0 Protocol Version 2 DualPoint devices send standard PS/2 mouse packets for -the DualPoint Stick. For non interleaved dualpoint devices the pointingstick -buttons get reported separately in the PSM, PSR and PSL bits. +the DualPoint Stick. The M, R and L bits signal the combined status of both +the pointingstick and touchpad buttons, except for Dell dualpoint devices +where the pointingstick buttons get reported separately in the PSM, PSR +and PSL bits. Dualpoint device -- interleaved packet format --------------------------------------------- diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c index 113d6f1516a5..4d246861d692 100644 --- a/drivers/input/mouse/alps.c +++ b/drivers/input/mouse/alps.c @@ -20,6 +20,7 @@ #include #include #include +#include #include "psmouse.h" #include "alps.h" @@ -99,6 +100,7 @@ static const struct alps_nibble_commands alps_v6_nibble_commands[] = { #define ALPS_FOUR_BUTTONS 0x40 /* 4 direction button present */ #define ALPS_PS2_INTERLEAVED 0x80 /* 3-byte PS/2 packet interleaved with 6-byte ALPS packet */ +#define ALPS_DELL 0x100 /* device is a Dell laptop */ #define ALPS_BUTTONPAD 0x200 /* device is a clickpad */ static const struct alps_model_info alps_model_data[] = { @@ -251,9 +253,9 @@ static void alps_process_packet_v1_v2(struct psmouse *psmouse) return; } - /* Non interleaved V2 dualpoint has separate stick button bits */ + /* Dell non interleaved V2 dualpoint has separate stick button bits */ if (priv->proto_version == ALPS_PROTO_V2 && - priv->flags == (ALPS_PASS | ALPS_DUALPOINT)) { + priv->flags == (ALPS_DELL | ALPS_PASS | ALPS_DUALPOINT)) { left |= packet[0] & 1; right |= packet[0] & 2; middle |= packet[0] & 4; @@ -2550,6 +2552,8 @@ static int alps_set_protocol(struct psmouse *psmouse, priv->byte0 = protocol->byte0; priv->mask0 = protocol->mask0; priv->flags = protocol->flags; + if (dmi_name_in_vendors("Dell")) + priv->flags |= ALPS_DELL; priv->x_max = 2000; priv->y_max = 1400; From 7895086afde2a05fa24a0e410d8e6b75ca7c8fdd Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Mon, 3 Aug 2015 16:07:48 +0300 Subject: [PATCH 356/428] xhci: fix off by one error in TRB DMA address boundary check MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We need to check that a TRB is part of the current segment before calculating its DMA address. Previously a ring segment didn't use a full memory page, and every new ring segment got a new memory page, so the off by one error in checking the upper bound was never seen. Now that we use a full memory page, 256 TRBs (4096 bytes), the off by one didn't catch the case when a TRB was the first element of the next segment. This is triggered if the virtual memory pages for a ring segment are next to each in increasing order where the ring buffer wraps around and causes errors like: [ 106.398223] xhci_hcd 0000:00:14.0: ERROR Transfer event TRB DMA ptr not part of current TD ep_index 0 comp_code 1 [ 106.398230] xhci_hcd 0000:00:14.0: Looking for event-dma fffd3000 trb-start fffd4fd0 trb-end fffd5000 seg-start fffd4000 seg-end fffd4ff0 The trb-end address is one outside the end-seg address. Cc: Tested-by: Arkadiusz Miśkiewicz Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-ring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 6a8fc52aed58..32f4d564494a 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -82,7 +82,7 @@ dma_addr_t xhci_trb_virt_to_dma(struct xhci_segment *seg, return 0; /* offset in TRBs */ segment_offset = trb - seg->trbs; - if (segment_offset > TRBS_PER_SEGMENT) + if (segment_offset >= TRBS_PER_SEGMENT) return 0; return seg->dma + (segment_offset * sizeof(*trb)); } From ffe5adcb7661d94e952d6b5ed7f493cb4ef0c7bc Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Mon, 3 Aug 2015 16:07:49 +0300 Subject: [PATCH 357/428] drivers/usb: Delete XHCI command timer if necessary When xhci_mem_cleanup() is called, it's possible that the command timer isn't initialized and scheduled. For those cases, to delete the command timer causes soft-lockup as below stack dump shows. The patch avoids deleting the command timer if it's not scheduled with the help of timer_pending(). NMI watchdog: BUG: soft lockup - CPU#40 stuck for 23s! [kworker/40:1:8140] : NIP [c000000000150b30] lock_timer_base.isra.34+0x90/0xa0 LR [c000000000150c24] try_to_del_timer_sync+0x34/0xa0 Call Trace: [c000000f67c975e0] [c0000000015b84f8] mon_ops+0x0/0x8 (unreliable) [c000000f67c97620] [c000000000150c24] try_to_del_timer_sync+0x34/0xa0 [c000000f67c97660] [c000000000150cf0] del_timer_sync+0x60/0x80 [c000000f67c97690] [c00000000070ac0c] xhci_mem_cleanup+0x5c/0x5e0 [c000000f67c97740] [c00000000070c2e8] xhci_mem_init+0x1158/0x13b0 [c000000f67c97860] [c000000000700978] xhci_init+0x88/0x110 [c000000f67c978e0] [c000000000701644] xhci_gen_setup+0x2b4/0x590 [c000000f67c97970] [c0000000006d4410] xhci_pci_setup+0x40/0x190 [c000000f67c979f0] [c0000000006b1af8] usb_add_hcd+0x418/0xba0 [c000000f67c97ab0] [c0000000006cb15c] usb_hcd_pci_probe+0x1dc/0x5c0 [c000000f67c97b50] [c0000000006d3ba4] xhci_pci_probe+0x64/0x1f0 [c000000f67c97ba0] [c0000000004fe9ac] local_pci_probe+0x6c/0x130 [c000000f67c97c30] [c0000000000e5ce8] work_for_cpu_fn+0x38/0x60 [c000000f67c97c60] [c0000000000eacb8] process_one_work+0x198/0x470 [c000000f67c97cf0] [c0000000000eb6ac] worker_thread+0x37c/0x5a0 [c000000f67c97d80] [c0000000000f2730] kthread+0x110/0x130 [c000000f67c97e30] [c000000000009660] ret_from_kernel_thread+0x5c/0x7c Cc: Reported-by: Priya M. A Signed-off-by: Gavin Shan Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-mem.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 3e442f77a2b9..9a8c936cd42c 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1792,7 +1792,8 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci) int size; int i, j, num_ports; - del_timer_sync(&xhci->cmd_timer); + if (timer_pending(&xhci->cmd_timer)) + del_timer_sync(&xhci->cmd_timer); /* Free the Event Ring Segment Table and the actual Event Ring */ size = sizeof(struct xhci_erst_entry)*(xhci->erst.num_entries); From 1f17124006b65482d9084c01e252b59dbca8db8f Mon Sep 17 00:00:00 2001 From: Malcolm Priestley Date: Sun, 2 Aug 2015 12:34:46 +0100 Subject: [PATCH 358/428] staging: vt6655: vnt_bss_info_changed check conf->beacon_rate is not NULL conf->beacon_rate can be NULL on association. So check conf->beacon_rate BSS_CHANGED_BEACON_INFO needs to flagged in changed as the beacon_rate will appear later. Signed-off-by: Malcolm Priestley Cc: # v3.19+ Signed-off-by: Greg Kroah-Hartman --- drivers/staging/vt6655/device_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c index b0c8e235b982..69bdc8f29b59 100644 --- a/drivers/staging/vt6655/device_main.c +++ b/drivers/staging/vt6655/device_main.c @@ -1483,8 +1483,9 @@ static void vnt_bss_info_changed(struct ieee80211_hw *hw, } } - if (changed & BSS_CHANGED_ASSOC && priv->op_mode != NL80211_IFTYPE_AP) { - if (conf->assoc) { + if (changed & (BSS_CHANGED_ASSOC | BSS_CHANGED_BEACON_INFO) && + priv->op_mode != NL80211_IFTYPE_AP) { + if (conf->assoc && conf->beacon_rate) { CARDbUpdateTSF(priv, conf->beacon_rate->hw_value, conf->sync_tsf); From bd4aaf8f9b85d6b2df3231fd62b219ebb75d3568 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Mon, 3 Aug 2015 09:54:58 -0400 Subject: [PATCH 359/428] dm: fix dm_merge_bvec regression on 32 bit systems A DM regression on 32 bit systems was reported against v4.2-rc3 here: https://lkml.org/lkml/2015/7/29/401 Fix this by reverting both commit 1c220c69 ("dm: fix casting bug in dm_merge_bvec()") and 148e51ba ("dm: improve documentation and code clarity in dm_merge_bvec"). This combined revert is done to eliminate the possibility of a partial revert in stable@ kernels. In hindsight the correct fix, at the time 1c220c69 was applied to fix the regression that 148e51ba introduced, should've been to simply revert 148e51ba. Reported-by: Josh Boyer Tested-by: Adam Williamson Acked-by: Joe Thornber Signed-off-by: Mike Snitzer Cc: stable@vger.kernel.org # 3.19+ --- drivers/md/dm.c | 27 ++++++++++----------------- 1 file changed, 10 insertions(+), 17 deletions(-) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index ab37ae114e94..0d7ab20c58df 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1729,7 +1729,8 @@ static int dm_merge_bvec(struct request_queue *q, struct mapped_device *md = q->queuedata; struct dm_table *map = dm_get_live_table_fast(md); struct dm_target *ti; - sector_t max_sectors, max_size = 0; + sector_t max_sectors; + int max_size = 0; if (unlikely(!map)) goto out; @@ -1742,18 +1743,10 @@ static int dm_merge_bvec(struct request_queue *q, * Find maximum amount of I/O that won't need splitting */ max_sectors = min(max_io_len(bvm->bi_sector, ti), - (sector_t) queue_max_sectors(q)); + (sector_t) BIO_MAX_SECTORS); max_size = (max_sectors << SECTOR_SHIFT) - bvm->bi_size; - - /* - * FIXME: this stop-gap fix _must_ be cleaned up (by passing a sector_t - * to the targets' merge function since it holds sectors not bytes). - * Just doing this as an interim fix for stable@ because the more - * comprehensive cleanup of switching to sector_t will impact every - * DM target that implements a ->merge hook. - */ - if (max_size > INT_MAX) - max_size = INT_MAX; + if (max_size < 0) + max_size = 0; /* * merge_bvec_fn() returns number of bytes @@ -1761,13 +1754,13 @@ static int dm_merge_bvec(struct request_queue *q, * max is precomputed maximal io size */ if (max_size && ti->type->merge) - max_size = ti->type->merge(ti, bvm, biovec, (int) max_size); + max_size = ti->type->merge(ti, bvm, biovec, max_size); /* * If the target doesn't support merge method and some of the devices - * provided their merge_bvec method (we know this by looking for the - * max_hw_sectors that dm_set_device_limits may set), then we can't - * allow bios with multiple vector entries. So always set max_size - * to 0, and the code below allows just one page. + * provided their merge_bvec method (we know this by looking at + * queue_max_hw_sectors), then we can't allow bios with multiple vector + * entries. So always set max_size to 0, and the code below allows + * just one page. */ else if (queue_max_hw_sectors(q) <= PAGE_SIZE >> 9) max_size = 0; From 6de7abfbad1c6a45893a47a17c2ac91b551aa90d Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Mon, 3 Aug 2015 18:27:56 +0530 Subject: [PATCH 360/428] ARCv2: [axs103_smp] Reduce clk for Quad FPGA configs Signed-off-by: Vineet Gupta --- arch/arc/plat-axs10x/axs10x.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/arch/arc/plat-axs10x/axs10x.c b/arch/arc/plat-axs10x/axs10x.c index 99f7da513a48..e7769c3ab5f2 100644 --- a/arch/arc/plat-axs10x/axs10x.c +++ b/arch/arc/plat-axs10x/axs10x.c @@ -389,6 +389,21 @@ axs103_set_freq(unsigned int id, unsigned int fd, unsigned int od) static void __init axs103_early_init(void) { + /* + * AXS103 configurations for SMP/QUAD configurations share device tree + * which defaults to 90 MHz. However recent failures of Quad config + * revealed P&R timing violations so clamp it down to safe 50 MHz + * Instead of duplicating defconfig/DT for SMP/QUAD, add a small hack + * + * This hack is really hacky as of now. Fix it properly by getting the + * number of cores as return value of platform's early SMP callback + */ +#ifdef CONFIG_ARC_MCIP + unsigned int num_cores = (read_aux_reg(ARC_REG_MCIP_BCR) >> 16) & 0x3F; + if (num_cores > 2) + arc_set_core_freq(50 * 1000000); +#endif + switch (arc_get_core_freq()/1000000) { case 33: axs103_set_freq(1, 1, 1); From f5959cb0c34c5c7f9f387e5d8fe1ec831ccb42ac Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Wed, 29 Jul 2015 19:20:58 +0530 Subject: [PATCH 361/428] Revert "ARCv2: STAR 9000837815 workaround hardware exclusive transactions livelock" Extended testing of quad core configuration revealed that this fix was insufficient. Specifically LTP open posix shm_op/23-1 would cause the hardware livelock in llock/scond loop in update_cpu_load_active() So remove this and make way for a proper workaround This reverts commit a5c8b52abe677977883655166796f167ef1e0084. Signed-off-by: Vineet Gupta --- arch/arc/include/asm/atomic.h | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index 03484cb4d16d..20b7dc17979e 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -23,21 +23,13 @@ #define atomic_set(v, i) (((v)->counter) = (i)) -#ifdef CONFIG_ISA_ARCV2 -#define PREFETCHW " prefetchw [%1] \n" -#else -#define PREFETCHW -#endif - #define ATOMIC_OP(op, c_op, asm_op) \ static inline void atomic_##op(int i, atomic_t *v) \ { \ unsigned int temp; \ \ __asm__ __volatile__( \ - "1: \n" \ - PREFETCHW \ - " llock %0, [%1] \n" \ + "1: llock %0, [%1] \n" \ " " #asm_op " %0, %0, %2 \n" \ " scond %0, [%1] \n" \ " bnz 1b \n" \ @@ -58,9 +50,7 @@ static inline int atomic_##op##_return(int i, atomic_t *v) \ smp_mb(); \ \ __asm__ __volatile__( \ - "1: \n" \ - PREFETCHW \ - " llock %0, [%1] \n" \ + "1: llock %0, [%1] \n" \ " " #asm_op " %0, %0, %2 \n" \ " scond %0, [%1] \n" \ " bnz 1b \n" \ From 8ac0665fb6ff125efc4df08772317f7311a95ce5 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Tue, 21 Jul 2015 12:05:42 +0300 Subject: [PATCH 362/428] ARC: refactor atomic inline asm operands with symbolic names This reduces the diff in forth-coming patches and also helps understand better the incremental changes to inline asm. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Vineet Gupta --- arch/arc/include/asm/atomic.h | 32 +++++++++++++++++--------------- 1 file changed, 17 insertions(+), 15 deletions(-) diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index 20b7dc17979e..3dd36c1efee1 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -26,22 +26,23 @@ #define ATOMIC_OP(op, c_op, asm_op) \ static inline void atomic_##op(int i, atomic_t *v) \ { \ - unsigned int temp; \ + unsigned int val; \ \ __asm__ __volatile__( \ - "1: llock %0, [%1] \n" \ - " " #asm_op " %0, %0, %2 \n" \ - " scond %0, [%1] \n" \ - " bnz 1b \n" \ - : "=&r"(temp) /* Early clobber, to prevent reg reuse */ \ - : "r"(&v->counter), "ir"(i) \ + "1: llock %[val], [%[ctr]] \n" \ + " " #asm_op " %[val], %[val], %[i] \n" \ + " scond %[val], [%[ctr]] \n" \ + " bnz 1b \n" \ + : [val] "=&r" (val) /* Early clobber to prevent reg reuse */ \ + : [ctr] "r" (&v->counter), /* Not "m": llock only supports reg direct addr mode */ \ + [i] "ir" (i) \ : "cc"); \ } \ #define ATOMIC_OP_RETURN(op, c_op, asm_op) \ static inline int atomic_##op##_return(int i, atomic_t *v) \ { \ - unsigned int temp; \ + unsigned int val; \ \ /* \ * Explicit full memory barrier needed before/after as \ @@ -50,17 +51,18 @@ static inline int atomic_##op##_return(int i, atomic_t *v) \ smp_mb(); \ \ __asm__ __volatile__( \ - "1: llock %0, [%1] \n" \ - " " #asm_op " %0, %0, %2 \n" \ - " scond %0, [%1] \n" \ - " bnz 1b \n" \ - : "=&r"(temp) \ - : "r"(&v->counter), "ir"(i) \ + "1: llock %[val], [%[ctr]] \n" \ + " " #asm_op " %[val], %[val], %[i] \n" \ + " scond %[val], [%[ctr]] \n" \ + " bnz 1b \n" \ + : [val] "=&r" (val) \ + : [ctr] "r" (&v->counter), \ + [i] "ir" (i) \ : "cc"); \ \ smp_mb(); \ \ - return temp; \ + return val; \ } #else /* !CONFIG_ARC_HAS_LLSC */ From ae7eae9e031206bde8645d038c76ad89e7d3fbcb Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Tue, 14 Jul 2015 17:55:05 +0530 Subject: [PATCH 363/428] ARC: LLOCK/SCOND based spin_lock Current spin_lock uses EXchange instruction to implement the atomic test and set of lock location (reads orig value and ST 1). This however forces the cacheline into exclusive state (because of the ST) and concurrent loops in multiple cores will bounce the line around between cores. Instead, use LLOCK/SCOND to implement the atomic test and set which is better as line is in shared state while lock is spinning on LLOCK The real motivation of this change however is to make way for future changes in atomics to implement delayed retry (with backoff). Initial experiment with delayed retry in atomics combined with orig EX based spinlock was a total disaster (broke even LMBench) as struct sock has a cache line sharing an atomic_t and spinlock. The tight spinning on lock, caused the atomic retry to keep backing off such that it would never finish. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Vineet Gupta --- arch/arc/include/asm/spinlock.h | 76 ++++++++++++++++++++++++++++++--- 1 file changed, 69 insertions(+), 7 deletions(-) diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h index e1651df6a93d..4f6c90a0a68a 100644 --- a/arch/arc/include/asm/spinlock.h +++ b/arch/arc/include/asm/spinlock.h @@ -18,9 +18,68 @@ #define arch_spin_unlock_wait(x) \ do { while (arch_spin_is_locked(x)) cpu_relax(); } while (0) +#ifdef CONFIG_ARC_HAS_LLSC + static inline void arch_spin_lock(arch_spinlock_t *lock) { - unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__; + unsigned int val; + + smp_mb(); + + __asm__ __volatile__( + "1: llock %[val], [%[slock]] \n" + " breq %[val], %[LOCKED], 1b \n" /* spin while LOCKED */ + " scond %[LOCKED], [%[slock]] \n" /* acquire */ + " bnz 1b \n" + " \n" + : [val] "=&r" (val) + : [slock] "r" (&(lock->slock)), + [LOCKED] "r" (__ARCH_SPIN_LOCK_LOCKED__) + : "memory", "cc"); + + smp_mb(); +} + +/* 1 - lock taken successfully */ +static inline int arch_spin_trylock(arch_spinlock_t *lock) +{ + unsigned int val, got_it = 0; + + smp_mb(); + + __asm__ __volatile__( + "1: llock %[val], [%[slock]] \n" + " breq %[val], %[LOCKED], 4f \n" /* already LOCKED, just bail */ + " scond %[LOCKED], [%[slock]] \n" /* acquire */ + " bnz 1b \n" + " mov %[got_it], 1 \n" + "4: \n" + " \n" + : [val] "=&r" (val), + [got_it] "+&r" (got_it) + : [slock] "r" (&(lock->slock)), + [LOCKED] "r" (__ARCH_SPIN_LOCK_LOCKED__) + : "memory", "cc"); + + smp_mb(); + + return got_it; +} + +static inline void arch_spin_unlock(arch_spinlock_t *lock) +{ + smp_mb(); + + lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__; + + smp_mb(); +} + +#else /* !CONFIG_ARC_HAS_LLSC */ + +static inline void arch_spin_lock(arch_spinlock_t *lock) +{ + unsigned int val = __ARCH_SPIN_LOCK_LOCKED__; /* * This smp_mb() is technically superfluous, we only need the one @@ -33,7 +92,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) __asm__ __volatile__( "1: ex %0, [%1] \n" " breq %0, %2, 1b \n" - : "+&r" (tmp) + : "+&r" (val) : "r"(&(lock->slock)), "ir"(__ARCH_SPIN_LOCK_LOCKED__) : "memory"); @@ -48,26 +107,27 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) smp_mb(); } +/* 1 - lock taken successfully */ static inline int arch_spin_trylock(arch_spinlock_t *lock) { - unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__; + unsigned int val = __ARCH_SPIN_LOCK_LOCKED__; smp_mb(); __asm__ __volatile__( "1: ex %0, [%1] \n" - : "+r" (tmp) + : "+r" (val) : "r"(&(lock->slock)) : "memory"); smp_mb(); - return (tmp == __ARCH_SPIN_LOCK_UNLOCKED__); + return (val == __ARCH_SPIN_LOCK_UNLOCKED__); } static inline void arch_spin_unlock(arch_spinlock_t *lock) { - unsigned int tmp = __ARCH_SPIN_LOCK_UNLOCKED__; + unsigned int val = __ARCH_SPIN_LOCK_UNLOCKED__; /* * RELEASE barrier: given the instructions avail on ARCv2, full barrier @@ -77,7 +137,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) __asm__ __volatile__( " ex %0, [%1] \n" - : "+r" (tmp) + : "+r" (val) : "r"(&(lock->slock)) : "memory"); @@ -88,6 +148,8 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) smp_mb(); } +#endif + /* * Read-write spinlocks, allowing multiple readers but only one writer. * From 69cbe630f54ec02efe47fdb9e257e617161da370 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Thu, 16 Jul 2015 10:31:45 +0530 Subject: [PATCH 364/428] ARC: LLOCK/SCOND based rwlock With LLOCK/SCOND, the rwlock counter can be atomically updated w/o need for a guarding spin lock. This in turn elides the EXchange instruction based spinning which causes the cacheline transition to exclusive state and concurrent spinning across cores would cause the line to keep bouncing around. LLOCK/SCOND based implementation is superior as spinning on LLOCK keeps the cacheline in shared state. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Vineet Gupta --- arch/arc/include/asm/spinlock.h | 174 ++++++++++++++++++++++++-- arch/arc/include/asm/spinlock_types.h | 2 + 2 files changed, 166 insertions(+), 10 deletions(-) diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h index 4f6c90a0a68a..9fd5a0221671 100644 --- a/arch/arc/include/asm/spinlock.h +++ b/arch/arc/include/asm/spinlock.h @@ -75,6 +75,164 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) smp_mb(); } +/* + * Read-write spinlocks, allowing multiple readers but only one writer. + * Unfair locking as Writers could be starved indefinitely by Reader(s) + */ + +static inline void arch_read_lock(arch_rwlock_t *rw) +{ + unsigned int val; + + smp_mb(); + + /* + * zero means writer holds the lock exclusively, deny Reader. + * Otherwise grant lock to first/subseq reader + * + * if (rw->counter > 0) { + * rw->counter--; + * ret = 1; + * } + */ + + __asm__ __volatile__( + "1: llock %[val], [%[rwlock]] \n" + " brls %[val], %[WR_LOCKED], 1b\n" /* <= 0: spin while write locked */ + " sub %[val], %[val], 1 \n" /* reader lock */ + " scond %[val], [%[rwlock]] \n" + " bnz 1b \n" + " \n" + : [val] "=&r" (val) + : [rwlock] "r" (&(rw->counter)), + [WR_LOCKED] "ir" (0) + : "memory", "cc"); + + smp_mb(); +} + +/* 1 - lock taken successfully */ +static inline int arch_read_trylock(arch_rwlock_t *rw) +{ + unsigned int val, got_it = 0; + + smp_mb(); + + __asm__ __volatile__( + "1: llock %[val], [%[rwlock]] \n" + " brls %[val], %[WR_LOCKED], 4f\n" /* <= 0: already write locked, bail */ + " sub %[val], %[val], 1 \n" /* counter-- */ + " scond %[val], [%[rwlock]] \n" + " bnz 1b \n" /* retry if collided with someone */ + " mov %[got_it], 1 \n" + " \n" + "4: ; --- done --- \n" + + : [val] "=&r" (val), + [got_it] "+&r" (got_it) + : [rwlock] "r" (&(rw->counter)), + [WR_LOCKED] "ir" (0) + : "memory", "cc"); + + smp_mb(); + + return got_it; +} + +static inline void arch_write_lock(arch_rwlock_t *rw) +{ + unsigned int val; + + smp_mb(); + + /* + * If reader(s) hold lock (lock < __ARCH_RW_LOCK_UNLOCKED__), + * deny writer. Otherwise if unlocked grant to writer + * Hence the claim that Linux rwlocks are unfair to writers. + * (can be starved for an indefinite time by readers). + * + * if (rw->counter == __ARCH_RW_LOCK_UNLOCKED__) { + * rw->counter = 0; + * ret = 1; + * } + */ + + __asm__ __volatile__( + "1: llock %[val], [%[rwlock]] \n" + " brne %[val], %[UNLOCKED], 1b \n" /* while !UNLOCKED spin */ + " mov %[val], %[WR_LOCKED] \n" + " scond %[val], [%[rwlock]] \n" + " bnz 1b \n" + " \n" + : [val] "=&r" (val) + : [rwlock] "r" (&(rw->counter)), + [UNLOCKED] "ir" (__ARCH_RW_LOCK_UNLOCKED__), + [WR_LOCKED] "ir" (0) + : "memory", "cc"); + + smp_mb(); +} + +/* 1 - lock taken successfully */ +static inline int arch_write_trylock(arch_rwlock_t *rw) +{ + unsigned int val, got_it = 0; + + smp_mb(); + + __asm__ __volatile__( + "1: llock %[val], [%[rwlock]] \n" + " brne %[val], %[UNLOCKED], 4f \n" /* !UNLOCKED, bail */ + " mov %[val], %[WR_LOCKED] \n" + " scond %[val], [%[rwlock]] \n" + " bnz 1b \n" /* retry if collided with someone */ + " mov %[got_it], 1 \n" + " \n" + "4: ; --- done --- \n" + + : [val] "=&r" (val), + [got_it] "+&r" (got_it) + : [rwlock] "r" (&(rw->counter)), + [UNLOCKED] "ir" (__ARCH_RW_LOCK_UNLOCKED__), + [WR_LOCKED] "ir" (0) + : "memory", "cc"); + + smp_mb(); + + return got_it; +} + +static inline void arch_read_unlock(arch_rwlock_t *rw) +{ + unsigned int val; + + smp_mb(); + + /* + * rw->counter++; + */ + __asm__ __volatile__( + "1: llock %[val], [%[rwlock]] \n" + " add %[val], %[val], 1 \n" + " scond %[val], [%[rwlock]] \n" + " bnz 1b \n" + " \n" + : [val] "=&r" (val) + : [rwlock] "r" (&(rw->counter)) + : "memory", "cc"); + + smp_mb(); +} + +static inline void arch_write_unlock(arch_rwlock_t *rw) +{ + smp_mb(); + + rw->counter = __ARCH_RW_LOCK_UNLOCKED__; + + smp_mb(); +} + #else /* !CONFIG_ARC_HAS_LLSC */ static inline void arch_spin_lock(arch_spinlock_t *lock) @@ -148,23 +306,14 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) smp_mb(); } -#endif - /* * Read-write spinlocks, allowing multiple readers but only one writer. + * Unfair locking as Writers could be starved indefinitely by Reader(s) * * The spinlock itself is contained in @counter and access to it is * serialized with @lock_mutex. - * - * Unfair locking as Writers could be starved indefinitely by Reader(s) */ -/* Would read_trylock() succeed? */ -#define arch_read_can_lock(x) ((x)->counter > 0) - -/* Would write_trylock() succeed? */ -#define arch_write_can_lock(x) ((x)->counter == __ARCH_RW_LOCK_UNLOCKED__) - /* 1 - lock taken successfully */ static inline int arch_read_trylock(arch_rwlock_t *rw) { @@ -235,6 +384,11 @@ static inline void arch_write_unlock(arch_rwlock_t *rw) arch_spin_unlock(&(rw->lock_mutex)); } +#endif + +#define arch_read_can_lock(x) ((x)->counter > 0) +#define arch_write_can_lock(x) ((x)->counter == __ARCH_RW_LOCK_UNLOCKED__) + #define arch_read_lock_flags(lock, flags) arch_read_lock(lock) #define arch_write_lock_flags(lock, flags) arch_write_lock(lock) diff --git a/arch/arc/include/asm/spinlock_types.h b/arch/arc/include/asm/spinlock_types.h index 662627ced4f2..4e1ef5f650c6 100644 --- a/arch/arc/include/asm/spinlock_types.h +++ b/arch/arc/include/asm/spinlock_types.h @@ -26,7 +26,9 @@ typedef struct { */ typedef struct { volatile unsigned int counter; +#ifndef CONFIG_ARC_HAS_LLSC arch_spinlock_t lock_mutex; +#endif } arch_rwlock_t; #define __ARCH_RW_LOCK_UNLOCKED__ 0x01000000 From e78fdfef84be13a5c2b8276e12203cdf24778596 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Tue, 14 Jul 2015 19:50:18 +0530 Subject: [PATCH 365/428] ARCv2: spinlock/rwlock/atomics: Delayed retry of failed SCOND with exponential backoff This is to workaround the llock/scond livelock HS38x4 could get into a LLOCK/SCOND livelock in case of multiple overlapping coherency transactions in the SCU. The exclusive line state keeps rotating among contenting cores leading to a never ending cycle. So break the cycle by deferring the retry of failed exclusive access (SCOND). The actual delay needed is function of number of contending cores as well as the unrelated coherency traffic from other cores. To keep the code simple, start off with small delay of 1 which would suffice most cases and in case of contention double the delay. Eventually the delay is sufficient such that the coherency pipeline is drained, thus a subsequent exclusive access would succeed. Link: http://lkml.kernel.org/r/1438612568-28265-1-git-send-email-vgupta@synopsys.com Acked-by: Peter Zijlstra (Intel) Signed-off-by: Vineet Gupta --- arch/arc/Kconfig | 5 + arch/arc/include/asm/atomic.h | 49 +++++- arch/arc/include/asm/spinlock.h | 293 ++++++++++++++++++++++++++++++++ arch/arc/kernel/setup.c | 4 + 4 files changed, 347 insertions(+), 4 deletions(-) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index a5fccdfbfc8f..bd4670d1b89b 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -365,6 +365,11 @@ config ARC_HAS_LLSC default y depends on !ARC_CANT_LLSC +config ARC_STAR_9000923308 + bool "Workaround for llock/scond livelock" + default y + depends on ISA_ARCV2 && SMP && ARC_HAS_LLSC + config ARC_HAS_SWAPE bool "Insn: SWAPE (endian-swap)" default y diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index 3dd36c1efee1..629dfd0a0c6b 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -23,17 +23,51 @@ #define atomic_set(v, i) (((v)->counter) = (i)) +#ifdef CONFIG_ARC_STAR_9000923308 + +#define SCOND_FAIL_RETRY_VAR_DEF \ + unsigned int delay = 1, tmp; \ + +#define SCOND_FAIL_RETRY_ASM \ + " bz 4f \n" \ + " ; --- scond fail delay --- \n" \ + " mov %[tmp], %[delay] \n" /* tmp = delay */ \ + "2: brne.d %[tmp], 0, 2b \n" /* while (tmp != 0) */ \ + " sub %[tmp], %[tmp], 1 \n" /* tmp-- */ \ + " asl.f %[delay], %[delay], 1 \n" /* delay *= 2 */ \ + " mov.z %[delay], 1 \n" /* handle overflow */ \ + " b 1b \n" /* start over */ \ + "4: ; --- success --- \n" \ + +#define SCOND_FAIL_RETRY_VARS \ + ,[delay] "+&r" (delay),[tmp] "=&r" (tmp) \ + +#else /* !CONFIG_ARC_STAR_9000923308 */ + +#define SCOND_FAIL_RETRY_VAR_DEF + +#define SCOND_FAIL_RETRY_ASM \ + " bnz 1b \n" \ + +#define SCOND_FAIL_RETRY_VARS + +#endif + #define ATOMIC_OP(op, c_op, asm_op) \ static inline void atomic_##op(int i, atomic_t *v) \ { \ - unsigned int val; \ + unsigned int val; \ + SCOND_FAIL_RETRY_VAR_DEF \ \ __asm__ __volatile__( \ "1: llock %[val], [%[ctr]] \n" \ " " #asm_op " %[val], %[val], %[i] \n" \ " scond %[val], [%[ctr]] \n" \ - " bnz 1b \n" \ + " \n" \ + SCOND_FAIL_RETRY_ASM \ + \ : [val] "=&r" (val) /* Early clobber to prevent reg reuse */ \ + SCOND_FAIL_RETRY_VARS \ : [ctr] "r" (&v->counter), /* Not "m": llock only supports reg direct addr mode */ \ [i] "ir" (i) \ : "cc"); \ @@ -42,7 +76,8 @@ static inline void atomic_##op(int i, atomic_t *v) \ #define ATOMIC_OP_RETURN(op, c_op, asm_op) \ static inline int atomic_##op##_return(int i, atomic_t *v) \ { \ - unsigned int val; \ + unsigned int val; \ + SCOND_FAIL_RETRY_VAR_DEF \ \ /* \ * Explicit full memory barrier needed before/after as \ @@ -54,8 +89,11 @@ static inline int atomic_##op##_return(int i, atomic_t *v) \ "1: llock %[val], [%[ctr]] \n" \ " " #asm_op " %[val], %[val], %[i] \n" \ " scond %[val], [%[ctr]] \n" \ - " bnz 1b \n" \ + " \n" \ + SCOND_FAIL_RETRY_ASM \ + \ : [val] "=&r" (val) \ + SCOND_FAIL_RETRY_VARS \ : [ctr] "r" (&v->counter), \ [i] "ir" (i) \ : "cc"); \ @@ -142,6 +180,9 @@ ATOMIC_OP(and, &=, and) #undef ATOMIC_OPS #undef ATOMIC_OP_RETURN #undef ATOMIC_OP +#undef SCOND_FAIL_RETRY_VAR_DEF +#undef SCOND_FAIL_RETRY_ASM +#undef SCOND_FAIL_RETRY_VARS /** * __atomic_add_unless - add unless the number is a given value diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h index 9fd5a0221671..2a84525b5aa4 100644 --- a/arch/arc/include/asm/spinlock.h +++ b/arch/arc/include/asm/spinlock.h @@ -20,6 +20,11 @@ #ifdef CONFIG_ARC_HAS_LLSC +/* + * A normal LLOCK/SCOND based system, w/o need for livelock workaround + */ +#ifndef CONFIG_ARC_STAR_9000923308 + static inline void arch_spin_lock(arch_spinlock_t *lock) { unsigned int val; @@ -233,6 +238,294 @@ static inline void arch_write_unlock(arch_rwlock_t *rw) smp_mb(); } +#else /* CONFIG_ARC_STAR_9000923308 */ + +/* + * HS38x4 could get into a LLOCK/SCOND livelock in case of multiple overlapping + * coherency transactions in the SCU. The exclusive line state keeps rotating + * among contenting cores leading to a never ending cycle. So break the cycle + * by deferring the retry of failed exclusive access (SCOND). The actual delay + * needed is function of number of contending cores as well as the unrelated + * coherency traffic from other cores. To keep the code simple, start off with + * small delay of 1 which would suffice most cases and in case of contention + * double the delay. Eventually the delay is sufficient such that the coherency + * pipeline is drained, thus a subsequent exclusive access would succeed. + */ + +#define SCOND_FAIL_RETRY_VAR_DEF \ + unsigned int delay, tmp; \ + +#define SCOND_FAIL_RETRY_ASM \ + " ; --- scond fail delay --- \n" \ + " mov %[tmp], %[delay] \n" /* tmp = delay */ \ + "2: brne.d %[tmp], 0, 2b \n" /* while (tmp != 0) */ \ + " sub %[tmp], %[tmp], 1 \n" /* tmp-- */ \ + " asl.f %[delay], %[delay], 1 \n" /* delay *= 2 */ \ + " mov.z %[delay], 1 \n" /* handle overflow */ \ + " b 1b \n" /* start over */ \ + " \n" \ + "4: ; --- done --- \n" \ + +#define SCOND_FAIL_RETRY_VARS \ + ,[delay] "=&r" (delay), [tmp] "=&r" (tmp) \ + +static inline void arch_spin_lock(arch_spinlock_t *lock) +{ + unsigned int val; + SCOND_FAIL_RETRY_VAR_DEF; + + smp_mb(); + + __asm__ __volatile__( + "0: mov %[delay], 1 \n" + "1: llock %[val], [%[slock]] \n" + " breq %[val], %[LOCKED], 1b \n" /* spin while LOCKED */ + " scond %[LOCKED], [%[slock]] \n" /* acquire */ + " bz 4f \n" /* done */ + " \n" + SCOND_FAIL_RETRY_ASM + + : [val] "=&r" (val) + SCOND_FAIL_RETRY_VARS + : [slock] "r" (&(lock->slock)), + [LOCKED] "r" (__ARCH_SPIN_LOCK_LOCKED__) + : "memory", "cc"); + + smp_mb(); +} + +/* 1 - lock taken successfully */ +static inline int arch_spin_trylock(arch_spinlock_t *lock) +{ + unsigned int val, got_it = 0; + SCOND_FAIL_RETRY_VAR_DEF; + + smp_mb(); + + __asm__ __volatile__( + "0: mov %[delay], 1 \n" + "1: llock %[val], [%[slock]] \n" + " breq %[val], %[LOCKED], 4f \n" /* already LOCKED, just bail */ + " scond %[LOCKED], [%[slock]] \n" /* acquire */ + " bz.d 4f \n" + " mov.z %[got_it], 1 \n" /* got it */ + " \n" + SCOND_FAIL_RETRY_ASM + + : [val] "=&r" (val), + [got_it] "+&r" (got_it) + SCOND_FAIL_RETRY_VARS + : [slock] "r" (&(lock->slock)), + [LOCKED] "r" (__ARCH_SPIN_LOCK_LOCKED__) + : "memory", "cc"); + + smp_mb(); + + return got_it; +} + +static inline void arch_spin_unlock(arch_spinlock_t *lock) +{ + smp_mb(); + + lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__; + + smp_mb(); +} + +/* + * Read-write spinlocks, allowing multiple readers but only one writer. + * Unfair locking as Writers could be starved indefinitely by Reader(s) + */ + +static inline void arch_read_lock(arch_rwlock_t *rw) +{ + unsigned int val; + SCOND_FAIL_RETRY_VAR_DEF; + + smp_mb(); + + /* + * zero means writer holds the lock exclusively, deny Reader. + * Otherwise grant lock to first/subseq reader + * + * if (rw->counter > 0) { + * rw->counter--; + * ret = 1; + * } + */ + + __asm__ __volatile__( + "0: mov %[delay], 1 \n" + "1: llock %[val], [%[rwlock]] \n" + " brls %[val], %[WR_LOCKED], 1b\n" /* <= 0: spin while write locked */ + " sub %[val], %[val], 1 \n" /* reader lock */ + " scond %[val], [%[rwlock]] \n" + " bz 4f \n" /* done */ + " \n" + SCOND_FAIL_RETRY_ASM + + : [val] "=&r" (val) + SCOND_FAIL_RETRY_VARS + : [rwlock] "r" (&(rw->counter)), + [WR_LOCKED] "ir" (0) + : "memory", "cc"); + + smp_mb(); +} + +/* 1 - lock taken successfully */ +static inline int arch_read_trylock(arch_rwlock_t *rw) +{ + unsigned int val, got_it = 0; + SCOND_FAIL_RETRY_VAR_DEF; + + smp_mb(); + + __asm__ __volatile__( + "0: mov %[delay], 1 \n" + "1: llock %[val], [%[rwlock]] \n" + " brls %[val], %[WR_LOCKED], 4f\n" /* <= 0: already write locked, bail */ + " sub %[val], %[val], 1 \n" /* counter-- */ + " scond %[val], [%[rwlock]] \n" + " bz.d 4f \n" + " mov.z %[got_it], 1 \n" /* got it */ + " \n" + SCOND_FAIL_RETRY_ASM + + : [val] "=&r" (val), + [got_it] "+&r" (got_it) + SCOND_FAIL_RETRY_VARS + : [rwlock] "r" (&(rw->counter)), + [WR_LOCKED] "ir" (0) + : "memory", "cc"); + + smp_mb(); + + return got_it; +} + +static inline void arch_write_lock(arch_rwlock_t *rw) +{ + unsigned int val; + SCOND_FAIL_RETRY_VAR_DEF; + + smp_mb(); + + /* + * If reader(s) hold lock (lock < __ARCH_RW_LOCK_UNLOCKED__), + * deny writer. Otherwise if unlocked grant to writer + * Hence the claim that Linux rwlocks are unfair to writers. + * (can be starved for an indefinite time by readers). + * + * if (rw->counter == __ARCH_RW_LOCK_UNLOCKED__) { + * rw->counter = 0; + * ret = 1; + * } + */ + + __asm__ __volatile__( + "0: mov %[delay], 1 \n" + "1: llock %[val], [%[rwlock]] \n" + " brne %[val], %[UNLOCKED], 1b \n" /* while !UNLOCKED spin */ + " mov %[val], %[WR_LOCKED] \n" + " scond %[val], [%[rwlock]] \n" + " bz 4f \n" + " \n" + SCOND_FAIL_RETRY_ASM + + : [val] "=&r" (val) + SCOND_FAIL_RETRY_VARS + : [rwlock] "r" (&(rw->counter)), + [UNLOCKED] "ir" (__ARCH_RW_LOCK_UNLOCKED__), + [WR_LOCKED] "ir" (0) + : "memory", "cc"); + + smp_mb(); +} + +/* 1 - lock taken successfully */ +static inline int arch_write_trylock(arch_rwlock_t *rw) +{ + unsigned int val, got_it = 0; + SCOND_FAIL_RETRY_VAR_DEF; + + smp_mb(); + + __asm__ __volatile__( + "0: mov %[delay], 1 \n" + "1: llock %[val], [%[rwlock]] \n" + " brne %[val], %[UNLOCKED], 4f \n" /* !UNLOCKED, bail */ + " mov %[val], %[WR_LOCKED] \n" + " scond %[val], [%[rwlock]] \n" + " bz.d 4f \n" + " mov.z %[got_it], 1 \n" /* got it */ + " \n" + SCOND_FAIL_RETRY_ASM + + : [val] "=&r" (val), + [got_it] "+&r" (got_it) + SCOND_FAIL_RETRY_VARS + : [rwlock] "r" (&(rw->counter)), + [UNLOCKED] "ir" (__ARCH_RW_LOCK_UNLOCKED__), + [WR_LOCKED] "ir" (0) + : "memory", "cc"); + + smp_mb(); + + return got_it; +} + +static inline void arch_read_unlock(arch_rwlock_t *rw) +{ + unsigned int val; + + smp_mb(); + + /* + * rw->counter++; + */ + __asm__ __volatile__( + "1: llock %[val], [%[rwlock]] \n" + " add %[val], %[val], 1 \n" + " scond %[val], [%[rwlock]] \n" + " bnz 1b \n" + " \n" + : [val] "=&r" (val) + : [rwlock] "r" (&(rw->counter)) + : "memory", "cc"); + + smp_mb(); +} + +static inline void arch_write_unlock(arch_rwlock_t *rw) +{ + unsigned int val; + + smp_mb(); + + /* + * rw->counter = __ARCH_RW_LOCK_UNLOCKED__; + */ + __asm__ __volatile__( + "1: llock %[val], [%[rwlock]] \n" + " scond %[UNLOCKED], [%[rwlock]]\n" + " bnz 1b \n" + " \n" + : [val] "=&r" (val) + : [rwlock] "r" (&(rw->counter)), + [UNLOCKED] "r" (__ARCH_RW_LOCK_UNLOCKED__) + : "memory", "cc"); + + smp_mb(); +} + +#undef SCOND_FAIL_RETRY_VAR_DEF +#undef SCOND_FAIL_RETRY_ASM +#undef SCOND_FAIL_RETRY_VARS + +#endif /* CONFIG_ARC_STAR_9000923308 */ + #else /* !CONFIG_ARC_HAS_LLSC */ static inline void arch_spin_lock(arch_spinlock_t *lock) diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index f2f771bd3ede..cabde9dc0696 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -336,6 +336,10 @@ static void arc_chk_core_config(void) pr_warn("CONFIG_ARC_FPU_SAVE_RESTORE needed for working apps\n"); else if (!cpu->extn.fpu_dp && fpu_enabled) panic("FPU non-existent, disable CONFIG_ARC_FPU_SAVE_RESTORE\n"); + + if (is_isa_arcv2() && IS_ENABLED(CONFIG_SMP) && cpu->isa.atomic && + !IS_ENABLED(CONFIG_ARC_STAR_9000923308)) + panic("llock/scond livelock workaround missing\n"); } /* From b89aa12c177477e34caa722818536fb5d0bffd76 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Tue, 21 Jul 2015 18:46:53 +0300 Subject: [PATCH 366/428] ARCv2: spinlock/rwlock: Reset retry delay when starting a new spin-wait cycle The previous commit for delayed retry of SCOND needs some fine tuning for spin locks. The backoff from delayed retry in conjunction with spin looping of lock itself can potentially cause the delay counter to reach high values. So to provide fairness to any lock operation, after a lock "seems" available (i.e. just before first SCOND try0, reset the delay counter back to starting value of 1 Essentially reset delay to 1 for a new spin-wait-loop-acquire cycle. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Vineet Gupta --- arch/arc/include/asm/spinlock.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h index 2a84525b5aa4..7071fc0da56a 100644 --- a/arch/arc/include/asm/spinlock.h +++ b/arch/arc/include/asm/spinlock.h @@ -279,7 +279,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) __asm__ __volatile__( "0: mov %[delay], 1 \n" "1: llock %[val], [%[slock]] \n" - " breq %[val], %[LOCKED], 1b \n" /* spin while LOCKED */ + " breq %[val], %[LOCKED], 0b \n" /* spin while LOCKED */ " scond %[LOCKED], [%[slock]] \n" /* acquire */ " bz 4f \n" /* done */ " \n" @@ -358,7 +358,7 @@ static inline void arch_read_lock(arch_rwlock_t *rw) __asm__ __volatile__( "0: mov %[delay], 1 \n" "1: llock %[val], [%[rwlock]] \n" - " brls %[val], %[WR_LOCKED], 1b\n" /* <= 0: spin while write locked */ + " brls %[val], %[WR_LOCKED], 0b\n" /* <= 0: spin while write locked */ " sub %[val], %[val], 1 \n" /* reader lock */ " scond %[val], [%[rwlock]] \n" " bz 4f \n" /* done */ @@ -427,7 +427,7 @@ static inline void arch_write_lock(arch_rwlock_t *rw) __asm__ __volatile__( "0: mov %[delay], 1 \n" "1: llock %[val], [%[rwlock]] \n" - " brne %[val], %[UNLOCKED], 1b \n" /* while !UNLOCKED spin */ + " brne %[val], %[UNLOCKED], 0b \n" /* while !UNLOCKED spin */ " mov %[val], %[WR_LOCKED] \n" " scond %[val], [%[rwlock]] \n" " bz 4f \n" From 9b06dc939489152b583131f49929ed1c6ae83740 Mon Sep 17 00:00:00 2001 From: Jeeja KP Date: Tue, 4 Aug 2015 09:28:38 +0530 Subject: [PATCH 367/428] ALSA: HDA: Fix stream assignment for host in decoupled mode This fixes issue in assigning host stream in case of decoupled mode. The check to verify if the stream is already in use was wrong so fix that Signed-off-by: Jeeja KP Signed-off-by: Vinod Koul Signed-off-by: Takashi Iwai --- sound/hda/ext/hdac_ext_stream.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/hda/ext/hdac_ext_stream.c b/sound/hda/ext/hdac_ext_stream.c index f8ffbdbb450d..3de47dd1a76d 100644 --- a/sound/hda/ext/hdac_ext_stream.c +++ b/sound/hda/ext/hdac_ext_stream.c @@ -299,7 +299,7 @@ hdac_ext_host_stream_assign(struct hdac_ext_bus *ebus, if (stream->direction != substream->stream) continue; - if (stream->opened) { + if (!stream->opened) { if (!hstream->decoupled) snd_hdac_ext_stream_decouple(ebus, hstream, true); res = hstream; From 5d942ce63c8fd98794a8ba9af559925c8432a052 Mon Sep 17 00:00:00 2001 From: Jeeja KP Date: Tue, 4 Aug 2015 09:28:39 +0530 Subject: [PATCH 368/428] ALSA: HDA: Dont check return for snd_hdac_chip_readl The snd_hdac_chip_readl return can never be less than zeros, so no point in checking for the return value This fixes following static checker warnings in snd_hdac_ext_bus_parse_capabilities sound/hda/ext/hdac_ext_controller.c:47 snd_hdac_ext_bus_parse_capabilities() warn: unsigned 'offset' is never less than zero. sound/hda/ext/hdac_ext_controller.c:54 snd_hdac_ext_bus_parse_capabilities() warn: unsigned 'cur_cap' is never less than zero. Signed-off-by: Jeeja KP Reported-by: Dan Carpenter Signed-off-by: Vinod Koul Signed-off-by: Takashi Iwai --- sound/hda/ext/hdac_ext_controller.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/sound/hda/ext/hdac_ext_controller.c b/sound/hda/ext/hdac_ext_controller.c index b2da19b60f4e..358f16195483 100644 --- a/sound/hda/ext/hdac_ext_controller.c +++ b/sound/hda/ext/hdac_ext_controller.c @@ -44,16 +44,10 @@ int snd_hdac_ext_bus_parse_capabilities(struct hdac_ext_bus *ebus) offset = snd_hdac_chip_readl(bus, LLCH); - if (offset < 0) - return -EIO; - /* Lets walk the linked capabilities list */ do { cur_cap = _snd_hdac_chip_read(l, bus, offset); - if (cur_cap < 0) - return -EIO; - dev_dbg(bus->dev, "Capability version: 0x%x\n", ((cur_cap & AZX_CAP_HDR_VER_MASK) >> AZX_CAP_HDR_VER_OFF)); From 3b8a684bd6cbc13dfd21ca41814c304e9f27ec7f Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 3 Aug 2015 17:24:08 +0200 Subject: [PATCH 369/428] drm/atomic-helper: Add an atomice best_encoder callback With legacy helpers all the routing was already set up when calling best_encoder and so could be inspected. But with atomic it's staged, hence we need a new atomic compliant callback for drivers which need to inspect the requested state and can't just decided the best encoder statically. This is needed to fix up i915 dp mst where we need to pick the right encoder depending upon the requested CRTC for the connector. v2: Don't forget to amend the kerneldoc Cc: Chris Wilson Cc: Linus Torvalds Cc: Theodore Ts'o Acked-by: Thierry Reding Reviewed-by: Ander Conselvan de Oliveira Signed-off-by: Daniel Vetter --- drivers/gpu/drm/drm_atomic_helper.c | 7 ++++++- include/drm/drm_crtc_helper.h | 3 +++ 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index aac212297b49..8694ca9beee3 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -196,7 +196,12 @@ update_connector_routing(struct drm_atomic_state *state, int conn_idx) } funcs = connector->helper_private; - new_encoder = funcs->best_encoder(connector); + + if (funcs->atomic_best_encoder) + new_encoder = funcs->atomic_best_encoder(connector, + connector_state); + else + new_encoder = funcs->best_encoder(connector); if (!new_encoder) { DRM_DEBUG_ATOMIC("No suitable encoder found for [CONNECTOR:%d:%s]\n", diff --git a/include/drm/drm_crtc_helper.h b/include/drm/drm_crtc_helper.h index c8fc187061de..918aa68b5199 100644 --- a/include/drm/drm_crtc_helper.h +++ b/include/drm/drm_crtc_helper.h @@ -168,6 +168,7 @@ struct drm_encoder_helper_funcs { * @get_modes: get mode list for this connector * @mode_valid: is this mode valid on the given connector? (optional) * @best_encoder: return the preferred encoder for this connector + * @atomic_best_encoder: atomic version of @best_encoder * * The helper operations are called by the mid-layer CRTC helper. */ @@ -176,6 +177,8 @@ struct drm_connector_helper_funcs { enum drm_mode_status (*mode_valid)(struct drm_connector *connector, struct drm_display_mode *mode); struct drm_encoder *(*best_encoder)(struct drm_connector *connector); + struct drm_encoder *(*atomic_best_encoder)(struct drm_connector *connector, + struct drm_connector_state *connector_state); }; extern void drm_helper_disable_unused_functions(struct drm_device *dev); From 459485ad3513bce12a3773f801e4647445062d9e Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 3 Aug 2015 17:24:09 +0200 Subject: [PATCH 370/428] drm/i915: Fixup dp mst encoder selection In commit 8c7b5ccb729870e606321b3703e2c2e698c49a95 Author: Ander Conselvan de Oliveira Date: Tue Apr 21 17:13:19 2015 +0300 drm/i915: Use atomic helpers for computing changed flags we've switched over to the atomic version to compute the crtc->encoder->connector routing from the i915 variant. That one relies upon the ->best_encoder callback, but the i915-private version relied upon intel_find_encoder. Which didn't matter except for dp mst, where the encoder depends upon the selected crtc. Fix this functional bug by implemented a correct atomic-state based encoder selector for dp mst. Note that we can't get rid of the legacy best_encoder callback since the fbdev emulation uses that still. That means it's incorrect there still, but that's been the case ever since i915 dp mst support was merged so not a regression. Best to fix that by converting fbdev over to atomic too. Cc: Chris Wilson Cc: Linus Torvalds Cc: Theodore Ts'o Reviewed-by: Ander Conselvan de Oliveira Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/intel_dp_mst.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c index 6e4cc5334f47..600afdbef8c9 100644 --- a/drivers/gpu/drm/i915/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/intel_dp_mst.c @@ -357,6 +357,16 @@ intel_dp_mst_mode_valid(struct drm_connector *connector, return MODE_OK; } +static struct drm_encoder *intel_mst_atomic_best_encoder(struct drm_connector *connector, + struct drm_connector_state *state) +{ + struct intel_connector *intel_connector = to_intel_connector(connector); + struct intel_dp *intel_dp = intel_connector->mst_port; + struct intel_crtc *crtc = to_intel_crtc(state->crtc); + + return &intel_dp->mst_encoders[crtc->pipe]->base.base; +} + static struct drm_encoder *intel_mst_best_encoder(struct drm_connector *connector) { struct intel_connector *intel_connector = to_intel_connector(connector); @@ -367,6 +377,7 @@ static struct drm_encoder *intel_mst_best_encoder(struct drm_connector *connecto static const struct drm_connector_helper_funcs intel_dp_mst_connector_helper_funcs = { .get_modes = intel_dp_mst_get_modes, .mode_valid = intel_dp_mst_mode_valid, + .atomic_best_encoder = intel_mst_atomic_best_encoder, .best_encoder = intel_mst_best_encoder, }; From 42639ba554655c280ae6cb72df0522b1201f2961 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 3 Aug 2015 17:24:10 +0200 Subject: [PATCH 371/428] drm/dp-mst: Remove debug WARN_ON Apparently been in there since forever and fairly easy to hit when hotplugging really fast. I can do that since my mst hub has a manual button to flick the hpd line for reprobing. The resulting WARNING spam isn't pretty. Cc: Dave Airlie Cc: stable@vger.kernel.org Reviewed-by: Thierry Reding Reviewed-by: Ander Conselvan de Oliveira Signed-off-by: Daniel Vetter --- drivers/gpu/drm/drm_dp_mst_topology.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 778bbb6425b8..b0487c9f018c 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -1294,7 +1294,6 @@ retry: goto retry; } DRM_DEBUG_KMS("failed to dpcd write %d %d\n", tosend, ret); - WARN(1, "fail\n"); return -EIO; } From 6ea76f3cade4734e73e3da842005820558b8b828 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 3 Aug 2015 17:24:11 +0200 Subject: [PATCH 372/428] drm/atomic-helpers: Make encoder picking more robust We've had a few issues with atomic where subtle bugs in the encoder picking logic lead to accidental self-stealing of the encoder, resulting in a NULL connector_state->crtc in update_connector_routing and subsequent. Linus applied some duct-tape for an mst regression in commit 27667f4744fc5a0f3e50910e78740bac5670d18b Author: Linus Torvalds Date: Wed Jul 29 22:18:16 2015 -0700 i915: temporary fix for DP MST docking station NULL pointer dereference But that was incomplete (the code will still oops when debuggin is enabled) and mangled the state even further. So instead WARN and bail out as the more future-proof option. Cc: Theodore Ts'o Cc: Linus Torvalds Reviewed-by: Thierry Reding Reviewed-by: Ander Conselvan de Oliveira Signed-off-by: Daniel Vetter --- drivers/gpu/drm/drm_atomic_helper.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 8694ca9beee3..9dcc7280e572 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -234,13 +234,14 @@ update_connector_routing(struct drm_atomic_state *state, int conn_idx) } } - connector_state->best_encoder = new_encoder; - if (connector_state->crtc) { - idx = drm_crtc_index(connector_state->crtc); + if (WARN_ON(!connector_state->crtc)) + return -EINVAL; - crtc_state = state->crtc_states[idx]; - crtc_state->mode_changed = true; - } + connector_state->best_encoder = new_encoder; + idx = drm_crtc_index(connector_state->crtc); + + crtc_state = state->crtc_states[idx]; + crtc_state->mode_changed = true; DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] using [ENCODER:%d:%s] on [CRTC:%d]\n", connector->base.id, From fcdf31a7c162de0c93a2bee51df4688ab0a348f8 Mon Sep 17 00:00:00 2001 From: Ross Lagerwall Date: Fri, 31 Jul 2015 14:30:42 +0100 Subject: [PATCH 373/428] xen/events/fifo: Handle linked events when closing a port An event channel bound to a CPU that was offlined may still be linked on that CPU's queue. If this event channel is closed and reused, subsequent events will be lost because the event channel is never unlinked and thus cannot be linked onto the correct queue. When a channel is closed and the event is still linked into a queue, ensure that it is unlinked before completing. If the CPU to which the event channel bound is online, spin until the event is handled by that CPU. If that CPU is offline, it can't handle the event, so clear the event queue during the close, dropping the events. This fixes the missing interrupts (and subsequent disk stalls etc.) when offlining a CPU. Signed-off-by: Ross Lagerwall Cc: Signed-off-by: David Vrabel --- drivers/xen/events/events_base.c | 10 ++++--- drivers/xen/events/events_fifo.c | 45 ++++++++++++++++++++++++---- drivers/xen/events/events_internal.h | 7 +++++ 3 files changed, 53 insertions(+), 9 deletions(-) diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 96093ae369a5..1495eccb1617 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -452,10 +452,12 @@ static void xen_free_irq(unsigned irq) irq_free_desc(irq); } -static void xen_evtchn_close(unsigned int port) +static void xen_evtchn_close(unsigned int port, unsigned int cpu) { struct evtchn_close close; + xen_evtchn_op_close(port, cpu); + close.port = port; if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0) BUG(); @@ -544,7 +546,7 @@ out: err: pr_err("irq%d: Failed to set port to irq mapping (%d)\n", irq, rc); - xen_evtchn_close(evtchn); + xen_evtchn_close(evtchn, NR_CPUS); return 0; } @@ -565,7 +567,7 @@ static void shutdown_pirq(struct irq_data *data) return; mask_evtchn(evtchn); - xen_evtchn_close(evtchn); + xen_evtchn_close(evtchn, cpu_from_evtchn(evtchn)); xen_irq_info_cleanup(info); } @@ -609,7 +611,7 @@ static void __unbind_from_irq(unsigned int irq) if (VALID_EVTCHN(evtchn)) { unsigned int cpu = cpu_from_irq(irq); - xen_evtchn_close(evtchn); + xen_evtchn_close(evtchn, cpu); switch (type_from_irq(irq)) { case IRQT_VIRQ: diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c index ed673e1acd61..6df8aac966b9 100644 --- a/drivers/xen/events/events_fifo.c +++ b/drivers/xen/events/events_fifo.c @@ -255,6 +255,12 @@ static void evtchn_fifo_unmask(unsigned port) } } +static bool evtchn_fifo_is_linked(unsigned port) +{ + event_word_t *word = event_word_from_port(port); + return sync_test_bit(EVTCHN_FIFO_BIT(LINKED, word), BM(word)); +} + static uint32_t clear_linked(volatile event_word_t *word) { event_word_t new, old, w; @@ -281,7 +287,8 @@ static void handle_irq_for_port(unsigned port) static void consume_one_event(unsigned cpu, struct evtchn_fifo_control_block *control_block, - unsigned priority, unsigned long *ready) + unsigned priority, unsigned long *ready, + bool drop) { struct evtchn_fifo_queue *q = &per_cpu(cpu_queue, cpu); uint32_t head; @@ -313,13 +320,15 @@ static void consume_one_event(unsigned cpu, if (head == 0) clear_bit(priority, ready); - if (evtchn_fifo_is_pending(port) && !evtchn_fifo_is_masked(port)) - handle_irq_for_port(port); + if (evtchn_fifo_is_pending(port) && !evtchn_fifo_is_masked(port)) { + if (likely(!drop)) + handle_irq_for_port(port); + } q->head[priority] = head; } -static void evtchn_fifo_handle_events(unsigned cpu) +static void __evtchn_fifo_handle_events(unsigned cpu, bool drop) { struct evtchn_fifo_control_block *control_block; unsigned long ready; @@ -331,11 +340,16 @@ static void evtchn_fifo_handle_events(unsigned cpu) while (ready) { q = find_first_bit(&ready, EVTCHN_FIFO_MAX_QUEUES); - consume_one_event(cpu, control_block, q, &ready); + consume_one_event(cpu, control_block, q, &ready, drop); ready |= xchg(&control_block->ready, 0); } } +static void evtchn_fifo_handle_events(unsigned cpu) +{ + __evtchn_fifo_handle_events(cpu, false); +} + static void evtchn_fifo_resume(void) { unsigned cpu; @@ -371,6 +385,26 @@ static void evtchn_fifo_resume(void) event_array_pages = 0; } +static void evtchn_fifo_close(unsigned port, unsigned int cpu) +{ + if (cpu == NR_CPUS) + return; + + get_online_cpus(); + if (cpu_online(cpu)) { + if (WARN_ON(irqs_disabled())) + goto out; + + while (evtchn_fifo_is_linked(port)) + cpu_relax(); + } else { + __evtchn_fifo_handle_events(cpu, true); + } + +out: + put_online_cpus(); +} + static const struct evtchn_ops evtchn_ops_fifo = { .max_channels = evtchn_fifo_max_channels, .nr_channels = evtchn_fifo_nr_channels, @@ -384,6 +418,7 @@ static const struct evtchn_ops evtchn_ops_fifo = { .unmask = evtchn_fifo_unmask, .handle_events = evtchn_fifo_handle_events, .resume = evtchn_fifo_resume, + .close = evtchn_fifo_close, }; static int evtchn_fifo_alloc_control_block(unsigned cpu) diff --git a/drivers/xen/events/events_internal.h b/drivers/xen/events/events_internal.h index 50c2050a1e32..d18e12315ec0 100644 --- a/drivers/xen/events/events_internal.h +++ b/drivers/xen/events/events_internal.h @@ -68,6 +68,7 @@ struct evtchn_ops { bool (*test_and_set_mask)(unsigned port); void (*mask)(unsigned port); void (*unmask)(unsigned port); + void (*close)(unsigned port, unsigned cpu); void (*handle_events)(unsigned cpu); void (*resume)(void); @@ -145,6 +146,12 @@ static inline void xen_evtchn_resume(void) evtchn_ops->resume(); } +static inline void xen_evtchn_op_close(unsigned port, unsigned cpu) +{ + if (evtchn_ops->close) + return evtchn_ops->close(port, cpu); +} + void xen_evtchn_2l_init(void); int xen_evtchn_fifo_init(void); From 257d5d9a9f19ee6c6801589c74791d5422c374e9 Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Fri, 17 Jul 2015 16:47:23 +0300 Subject: [PATCH 374/428] ARM: dts: dra7: Add syscon-pllreset syscon to SATA PHY This register is required to be passed to the SATA PHY driver to workaround errata i783 (SATA Lockup After SATA DPLL Unlock/Relock). Signed-off-by: Roger Quadros Acked-by: Tony Lindgren Signed-off-by: Kishon Vijay Abraham I --- arch/arm/boot/dts/dra7.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index 8f1e25bcecbd..4a0718ccf68e 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -1140,6 +1140,7 @@ ctrl-module = <&omap_control_sata>; clocks = <&sys_clkin1>, <&sata_ref_clk>; clock-names = "sysclk", "refclk"; + syscon-pllreset = <&scm_conf 0x3fc>; #phy-cells = <0>; }; From 5406898354ebfb11f49b955fb5e49a62786a542f Mon Sep 17 00:00:00 2001 From: Mengdong Lin Date: Tue, 4 Aug 2015 15:47:35 +0100 Subject: [PATCH 375/428] ASoC: topology: fix typo in soc_tplg_kcontrol_bind_io() Signed-off-by: Mengdong Lin Signed-off-by: Liam Girdwood Signed-off-by: Mark Brown --- sound/soc/soc-topology.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index d0960683c409..6a547c6dd3a1 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -534,7 +534,7 @@ static int soc_tplg_kcontrol_bind_io(struct snd_soc_tplg_ctl_hdr *hdr, k->put = bops[i].put; if (k->get == NULL && bops[i].id == hdr->ops.get) k->get = bops[i].get; - if (k->info == NULL && ops[i].id == hdr->ops.info) + if (k->info == NULL && bops[i].id == hdr->ops.info) k->info = bops[i].info; } From fb1de5a4c825a389f054cc3803e06116d2fbdc7e Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sat, 1 Aug 2015 07:01:24 -0700 Subject: [PATCH 376/428] staging: lustre: Include unaligned.h instead of access_ok.h Including access_ok.h causes the ia64:allmodconfig build (and maybe others) to fail with include/linux/unaligned/le_struct.h:6:19: error: redefinition of 'get_unaligned_le16' include/linux/unaligned/access_ok.h:7:19: note: previous definition of 'get_unaligned_le16' was here include/linux/unaligned/le_struct.h:26:20: error: redefinition of 'put_unaligned_le32' include/linux/unaligned/access_ok.h:42:20: note: previous definition of 'put_unaligned_le32' was here include/linux/unaligned/le_struct.h:31:20: error: redefinition of 'put_unaligned_le64' include/linux/unaligned/access_ok.h:47:20: note: previous definition of 'put_unaligned_le64' was here Include unaligned.h instead and leave it up to the architecture to decide how to implement unaligned accesses. Fixes: 8c4f136497315 ("Staging: lustre: Use put_unaligned_le64") Cc: Vaishali Thakkar Signed-off-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- drivers/staging/lustre/lustre/obdclass/debug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/lustre/lustre/obdclass/debug.c b/drivers/staging/lustre/lustre/obdclass/debug.c index 9c934e6d2ea1..c61add46b426 100644 --- a/drivers/staging/lustre/lustre/obdclass/debug.c +++ b/drivers/staging/lustre/lustre/obdclass/debug.c @@ -40,7 +40,7 @@ #define DEBUG_SUBSYSTEM D_OTHER -#include +#include #include "../include/obd_support.h" #include "../include/lustre_debug.h" From c85523d1d97cc86aadc388221aa83ae9bc1e7cca Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Wed, 5 Aug 2015 09:21:04 +0900 Subject: [PATCH 377/428] Revert "ALSA: fireworks: add support for AudioFire2 quirk" This reverts commit 9c6893e0be38b6ca9a56a854226e51dee0a16a5a. The fix is superseded by the next commit as a better implementation for supporting AudioFire2/AudioFire4/AudioFirePre8 quirks. Signed-off-by: Takashi Sakamoto Signed-off-by: Takashi Iwai --- sound/firewire/fireworks/fireworks.c | 2 -- sound/firewire/fireworks/fireworks.h | 1 - sound/firewire/fireworks/fireworks_stream.c | 3 --- 3 files changed, 6 deletions(-) diff --git a/sound/firewire/fireworks/fireworks.c b/sound/firewire/fireworks/fireworks.c index c670db4eee70..2682e7e3e5c9 100644 --- a/sound/firewire/fireworks/fireworks.c +++ b/sound/firewire/fireworks/fireworks.c @@ -248,8 +248,6 @@ efw_probe(struct fw_unit *unit, err = get_hardware_info(efw); if (err < 0) goto error; - if (entry->model_id == MODEL_ECHO_AUDIOFIRE_2) - efw->is_af2 = true; if (entry->model_id == MODEL_ECHO_AUDIOFIRE_9) efw->is_af9 = true; diff --git a/sound/firewire/fireworks/fireworks.h b/sound/firewire/fireworks/fireworks.h index c33252b7bc84..4f0201a95222 100644 --- a/sound/firewire/fireworks/fireworks.h +++ b/sound/firewire/fireworks/fireworks.h @@ -70,7 +70,6 @@ struct snd_efw { bool resp_addr_changable; /* for quirks */ - bool is_af2; bool is_af9; u32 firmware_version; diff --git a/sound/firewire/fireworks/fireworks_stream.c b/sound/firewire/fireworks/fireworks_stream.c index a0762dd6231e..c55db1bddc80 100644 --- a/sound/firewire/fireworks/fireworks_stream.c +++ b/sound/firewire/fireworks/fireworks_stream.c @@ -172,9 +172,6 @@ int snd_efw_stream_init_duplex(struct snd_efw *efw) efw->tx_stream.flags |= CIP_DBC_IS_END_EVENT; /* Fireworks reset dbc at bus reset. */ efw->tx_stream.flags |= CIP_SKIP_DBC_ZERO_CHECK; - /* AudioFire2 starts packets with non-zero dbc. */ - if (efw->is_af2) - efw->tx_stream.flags |= CIP_SKIP_INIT_DBC_CHECK; /* AudioFire9 always reports wrong dbs. */ if (efw->is_af9) efw->tx_stream.flags |= CIP_WRONG_DBS; From 18f5ed365d3f188a91149d528c853000330a4a58 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Wed, 5 Aug 2015 09:21:05 +0900 Subject: [PATCH 378/428] ALSA: fireworks/firewire-lib: add support for recent firmware quirk Fireworks uses TSB43CB43(IceLynx-Micro) as its IEC 61883-1/6 interface. This chip includes ARM7 core, and loads and runs program. The firmware is stored in on-board memory and loaded every powering-on from it. Echo Audio ships several versions of firmwares for each model. These firmwares have each quirk and the quirk changes a sequence of packets. As long as I investigated, AudioFire2/AudioFire4/AudioFirePre8 have a quirk to transfer a first packet with 0x02 in its dbc field. This causes ALSA Fireworks driver to detect discontinuity. In this case, firmware version 5.7.0, 5.7.3 and 5.8.0 are used. Payload CIP CIP quadlets header1 header2 02 00050002 90ffffff <- 42 0005000a 90013000 42 00050012 90014400 42 0005001a 90015800 02 0005001a 90ffffff 42 00050022 90019000 42 0005002a 9001a400 42 00050032 9001b800 02 00050032 90ffffff 42 0005003a 9001d000 42 00050042 9001e400 42 0005004a 9001f800 02 0005004a 90ffffff (AudioFire2 with firmware version 5.7.) $ dmesg snd-fireworks fw1.0: Detect discontinuity of CIP: 00 02 These models, AudioFire8 (since Jul 2009 ) and Gibson Robot Interface Pack series uses the same ARM binary as their firmware. Thus, this quirk may be observed among them. This commit adds a new member for AMDTP structure. This member represents the value of dbc field in a first AMDTP packet. Drivers can set it with a preferred value according to model's quirk. Tested-by: Johannes Oertei Signed-off-by: Takashi Sakamoto Cc: Signed-off-by: Takashi Iwai --- sound/firewire/amdtp.c | 5 +++-- sound/firewire/amdtp.h | 2 ++ sound/firewire/fireworks/fireworks.c | 8 ++++++++ sound/firewire/fireworks/fireworks.h | 1 + sound/firewire/fireworks/fireworks_stream.c | 9 +++++++++ 5 files changed, 23 insertions(+), 2 deletions(-) diff --git a/sound/firewire/amdtp.c b/sound/firewire/amdtp.c index 7bb988fa6b6d..2a153d260836 100644 --- a/sound/firewire/amdtp.c +++ b/sound/firewire/amdtp.c @@ -740,8 +740,9 @@ static int handle_in_packet(struct amdtp_stream *s, s->data_block_counter != UINT_MAX) data_block_counter = s->data_block_counter; - if (((s->flags & CIP_SKIP_DBC_ZERO_CHECK) && data_block_counter == 0) || - (s->data_block_counter == UINT_MAX)) { + if (((s->flags & CIP_SKIP_DBC_ZERO_CHECK) && + data_block_counter == s->tx_first_dbc) || + s->data_block_counter == UINT_MAX) { lost = false; } else if (!(s->flags & CIP_DBC_IS_END_EVENT)) { lost = data_block_counter != s->data_block_counter; diff --git a/sound/firewire/amdtp.h b/sound/firewire/amdtp.h index 26b909329e54..b2cf9e75693b 100644 --- a/sound/firewire/amdtp.h +++ b/sound/firewire/amdtp.h @@ -157,6 +157,8 @@ struct amdtp_stream { /* quirk: fixed interval of dbc between previos/current packets. */ unsigned int tx_dbc_interval; + /* quirk: indicate the value of dbc field in a first packet. */ + unsigned int tx_first_dbc; bool callbacked; wait_queue_head_t callback_wait; diff --git a/sound/firewire/fireworks/fireworks.c b/sound/firewire/fireworks/fireworks.c index 2682e7e3e5c9..c94a432f7cc6 100644 --- a/sound/firewire/fireworks/fireworks.c +++ b/sound/firewire/fireworks/fireworks.c @@ -248,8 +248,16 @@ efw_probe(struct fw_unit *unit, err = get_hardware_info(efw); if (err < 0) goto error; + /* AudioFire8 (since 2009) and AudioFirePre8 */ if (entry->model_id == MODEL_ECHO_AUDIOFIRE_9) efw->is_af9 = true; + /* These models uses the same firmware. */ + if (entry->model_id == MODEL_ECHO_AUDIOFIRE_2 || + entry->model_id == MODEL_ECHO_AUDIOFIRE_4 || + entry->model_id == MODEL_ECHO_AUDIOFIRE_9 || + entry->model_id == MODEL_GIBSON_RIP || + entry->model_id == MODEL_GIBSON_GOLDTOP) + efw->is_fireworks3 = true; snd_efw_proc_init(efw); diff --git a/sound/firewire/fireworks/fireworks.h b/sound/firewire/fireworks/fireworks.h index 4f0201a95222..084d414b228c 100644 --- a/sound/firewire/fireworks/fireworks.h +++ b/sound/firewire/fireworks/fireworks.h @@ -71,6 +71,7 @@ struct snd_efw { /* for quirks */ bool is_af9; + bool is_fireworks3; u32 firmware_version; unsigned int midi_in_ports; diff --git a/sound/firewire/fireworks/fireworks_stream.c b/sound/firewire/fireworks/fireworks_stream.c index c55db1bddc80..7e353f1f7bff 100644 --- a/sound/firewire/fireworks/fireworks_stream.c +++ b/sound/firewire/fireworks/fireworks_stream.c @@ -172,6 +172,15 @@ int snd_efw_stream_init_duplex(struct snd_efw *efw) efw->tx_stream.flags |= CIP_DBC_IS_END_EVENT; /* Fireworks reset dbc at bus reset. */ efw->tx_stream.flags |= CIP_SKIP_DBC_ZERO_CHECK; + /* + * But Recent firmwares starts packets with non-zero dbc. + * Driver version 5.7.6 installs firmware version 5.7.3. + */ + if (efw->is_fireworks3 && + (efw->firmware_version == 0x5070000 || + efw->firmware_version == 0x5070300 || + efw->firmware_version == 0x5080000)) + efw->tx_stream.tx_first_dbc = 0x02; /* AudioFire9 always reports wrong dbs. */ if (efw->is_af9) efw->tx_stream.flags |= CIP_WRONG_DBS; From 87ce62802f7a3553234ebf1ae7cd52c8bf272fb9 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Wed, 5 Aug 2015 11:12:00 +0530 Subject: [PATCH 379/428] ARC: Make pt_regs regs unsigned KGDB fails to build after f51e2f191112 ("ARC: make sure instruction_pointer() returns unsigned value") The hack to force one specific reg to unsigned backfired. There's no reason to keep the regs signed after all. | CC arch/arc/kernel/kgdb.o |../arch/arc/kernel/kgdb.c: In function 'kgdb_trap': | ../arch/arc/kernel/kgdb.c:180:29: error: lvalue required as left operand of assignment | instruction_pointer(regs) -= BREAK_INSTR_SIZE; Reported-by: Yuriy Kolerov Fixes: f51e2f191112 ("ARC: make sure instruction_pointer() returns unsigned value") Cc: Alexey Brodkin Signed-off-by: Vineet Gupta --- arch/arc/include/asm/ptrace.h | 54 +++++++++++++++--------------- arch/arc/include/uapi/asm/ptrace.h | 20 +++++------ 2 files changed, 37 insertions(+), 37 deletions(-) diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h index 91694ec1ce95..69095da1fcfd 100644 --- a/arch/arc/include/asm/ptrace.h +++ b/arch/arc/include/asm/ptrace.h @@ -20,20 +20,20 @@ struct pt_regs { /* Real registers */ - long bta; /* bta_l1, bta_l2, erbta */ + unsigned long bta; /* bta_l1, bta_l2, erbta */ - long lp_start, lp_end, lp_count; + unsigned long lp_start, lp_end, lp_count; - long status32; /* status32_l1, status32_l2, erstatus */ - long ret; /* ilink1, ilink2 or eret */ - long blink; - long fp; - long r26; /* gp */ + unsigned long status32; /* status32_l1, status32_l2, erstatus */ + unsigned long ret; /* ilink1, ilink2 or eret */ + unsigned long blink; + unsigned long fp; + unsigned long r26; /* gp */ - long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0; + unsigned long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0; - long sp; /* user/kernel sp depending on where we came from */ - long orig_r0; + unsigned long sp; /* User/Kernel depending on where we came from */ + unsigned long orig_r0; /* * To distinguish bet excp, syscall, irq @@ -55,13 +55,13 @@ struct pt_regs { unsigned long event; }; - long user_r25; + unsigned long user_r25; }; #else struct pt_regs { - long orig_r0; + unsigned long orig_r0; union { struct { @@ -76,26 +76,26 @@ struct pt_regs { unsigned long event; }; - long bta; /* bta_l1, bta_l2, erbta */ + unsigned long bta; /* bta_l1, bta_l2, erbta */ - long user_r25; + unsigned long user_r25; - long r26; /* gp */ - long fp; - long sp; /* user/kernel sp depending on where we came from */ + unsigned long r26; /* gp */ + unsigned long fp; + unsigned long sp; /* user/kernel sp depending on where we came from */ - long r12; + unsigned long r12; /*------- Below list auto saved by h/w -----------*/ - long r0, r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11; + unsigned long r0, r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11; - long blink; - long lp_end, lp_start, lp_count; + unsigned long blink; + unsigned long lp_end, lp_start, lp_count; - long ei, ldi, jli; + unsigned long ei, ldi, jli; - long ret; - long status32; + unsigned long ret; + unsigned long status32; }; #endif @@ -103,10 +103,10 @@ struct pt_regs { /* Callee saved registers - need to be saved only when you are scheduled out */ struct callee_regs { - long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13; + unsigned long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13; }; -#define instruction_pointer(regs) (unsigned long)((regs)->ret) +#define instruction_pointer(regs) ((regs)->ret) #define profile_pc(regs) instruction_pointer(regs) /* return 1 if user mode or 0 if kernel mode */ @@ -142,7 +142,7 @@ struct callee_regs { static inline long regs_return_value(struct pt_regs *regs) { - return regs->r0; + return (long)regs->r0; } #endif /* !__ASSEMBLY__ */ diff --git a/arch/arc/include/uapi/asm/ptrace.h b/arch/arc/include/uapi/asm/ptrace.h index 76a7739aab1c..0b3ef63d4a03 100644 --- a/arch/arc/include/uapi/asm/ptrace.h +++ b/arch/arc/include/uapi/asm/ptrace.h @@ -32,20 +32,20 @@ */ struct user_regs_struct { - long pad; + unsigned long pad; struct { - long bta, lp_start, lp_end, lp_count; - long status32, ret, blink, fp, gp; - long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0; - long sp; + unsigned long bta, lp_start, lp_end, lp_count; + unsigned long status32, ret, blink, fp, gp; + unsigned long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0; + unsigned long sp; } scratch; - long pad2; + unsigned long pad2; struct { - long r25, r24, r23, r22, r21, r20; - long r19, r18, r17, r16, r15, r14, r13; + unsigned long r25, r24, r23, r22, r21, r20; + unsigned long r19, r18, r17, r16, r15, r14, r13; } callee; - long efa; /* break pt addr, for break points in delay slots */ - long stop_pc; /* give dbg stop_pc after ensuring brkpt trap */ + unsigned long efa; /* break pt addr, for break points in delay slots */ + unsigned long stop_pc; /* give dbg stop_pc after ensuring brkpt trap */ }; #endif /* !__ASSEMBLY__ */ From ecf5fc6e9654cd7a268c782a523f072b2f1959f9 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 4 Aug 2015 14:36:58 -0700 Subject: [PATCH 380/428] mm, vmscan: Do not wait for page writeback for GFP_NOFS allocations Nikolay has reported a hang when a memcg reclaim got stuck with the following backtrace: PID: 18308 TASK: ffff883d7c9b0a30 CPU: 1 COMMAND: "rsync" #0 __schedule at ffffffff815ab152 #1 schedule at ffffffff815ab76e #2 schedule_timeout at ffffffff815ae5e5 #3 io_schedule_timeout at ffffffff815aad6a #4 bit_wait_io at ffffffff815abfc6 #5 __wait_on_bit at ffffffff815abda5 #6 wait_on_page_bit at ffffffff8111fd4f #7 shrink_page_list at ffffffff81135445 #8 shrink_inactive_list at ffffffff81135845 #9 shrink_lruvec at ffffffff81135ead #10 shrink_zone at ffffffff811360c3 #11 shrink_zones at ffffffff81136eff #12 do_try_to_free_pages at ffffffff8113712f #13 try_to_free_mem_cgroup_pages at ffffffff811372be #14 try_charge at ffffffff81189423 #15 mem_cgroup_try_charge at ffffffff8118c6f5 #16 __add_to_page_cache_locked at ffffffff8112137d #17 add_to_page_cache_lru at ffffffff81121618 #18 pagecache_get_page at ffffffff8112170b #19 grow_dev_page at ffffffff811c8297 #20 __getblk_slow at ffffffff811c91d6 #21 __getblk_gfp at ffffffff811c92c1 #22 ext4_ext_grow_indepth at ffffffff8124565c #23 ext4_ext_create_new_leaf at ffffffff81246ca8 #24 ext4_ext_insert_extent at ffffffff81246f09 #25 ext4_ext_map_blocks at ffffffff8124a848 #26 ext4_map_blocks at ffffffff8121a5b7 #27 mpage_map_one_extent at ffffffff8121b1fa #28 mpage_map_and_submit_extent at ffffffff8121f07b #29 ext4_writepages at ffffffff8121f6d5 #30 do_writepages at ffffffff8112c490 #31 __filemap_fdatawrite_range at ffffffff81120199 #32 filemap_flush at ffffffff8112041c #33 ext4_alloc_da_blocks at ffffffff81219da1 #34 ext4_rename at ffffffff81229b91 #35 ext4_rename2 at ffffffff81229e32 #36 vfs_rename at ffffffff811a08a5 #37 SYSC_renameat2 at ffffffff811a3ffc #38 sys_renameat2 at ffffffff811a408e #39 sys_rename at ffffffff8119e51e #40 system_call_fastpath at ffffffff815afa89 Dave Chinner has properly pointed out that this is a deadlock in the reclaim code because ext4 doesn't submit pages which are marked by PG_writeback right away. The heuristic was introduced by commit e62e384e9da8 ("memcg: prevent OOM with too many dirty pages") and it was applied only when may_enter_fs was specified. The code has been changed by c3b94f44fcb0 ("memcg: further prevent OOM with too many dirty pages") which has removed the __GFP_FS restriction with a reasoning that we do not get into the fs code. But this is not sufficient apparently because the fs doesn't necessarily submit pages marked PG_writeback for IO right away. ext4_bio_write_page calls io_submit_add_bh but that doesn't necessarily submit the bio. Instead it tries to map more pages into the bio and mpage_map_one_extent might trigger memcg charge which might end up waiting on a page which is marked PG_writeback but hasn't been submitted yet so we would end up waiting for something that never finishes. Fix this issue by replacing __GFP_IO by may_enter_fs check (for case 2) before we go to wait on the writeback. The page fault path, which is the only path that triggers memcg oom killer since 3.12, shouldn't require GFP_NOFS and so we shouldn't reintroduce the premature OOM killer issue which was originally addressed by the heuristic. As per David Chinner the xfs is doing similar thing since 2.6.15 already so ext4 is not the only affected filesystem. Moreover he notes: : For example: IO completion might require unwritten extent conversion : which executes filesystem transactions and GFP_NOFS allocations. The : writeback flag on the pages can not be cleared until unwritten : extent conversion completes. Hence memory reclaim cannot wait on : page writeback to complete in GFP_NOFS context because it is not : safe to do so, memcg reclaim or otherwise. Cc: stable@vger.kernel.org # 3.9+ [tytso@mit.edu: corrected the control flow] Fixes: c3b94f44fcb0 ("memcg: further prevent OOM with too many dirty pages") Reported-by: Nikolay Borisov Signed-off-by: Michal Hocko Signed-off-by: Hugh Dickins Signed-off-by: Linus Torvalds --- mm/vmscan.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index e61445dce04e..8286938c70de 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -973,22 +973,18 @@ static unsigned long shrink_page_list(struct list_head *page_list, * caller can stall after page list has been processed. * * 2) Global or new memcg reclaim encounters a page that is - * not marked for immediate reclaim or the caller does not - * have __GFP_IO. In this case mark the page for immediate + * not marked for immediate reclaim, or the caller does not + * have __GFP_FS (or __GFP_IO if it's simply going to swap, + * not to fs). In this case mark the page for immediate * reclaim and continue scanning. * - * __GFP_IO is checked because a loop driver thread might + * Require may_enter_fs because we would wait on fs, which + * may not have submitted IO yet. And the loop driver might * enter reclaim, and deadlock if it waits on a page for * which it is needed to do the write (loop masks off * __GFP_IO|__GFP_FS for this reason); but more thought * would probably show more reasons. * - * Don't require __GFP_FS, since we're not going into the - * FS, just waiting on its writeback completion. Worryingly, - * ext4 gfs2 and xfs allocate pages with - * grab_cache_page_write_begin(,,AOP_FLAG_NOFS), so testing - * may_enter_fs here is liable to OOM on them. - * * 3) Legacy memcg encounters a page that is not already marked * PageReclaim. memcg does not have any dirty pages * throttling so we could easily OOM just because too many @@ -1005,7 +1001,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, /* Case 2 above */ } else if (sane_reclaim(sc) || - !PageReclaim(page) || !(sc->gfp_mask & __GFP_IO)) { + !PageReclaim(page) || !may_enter_fs) { /* * This is slightly racy - end_page_writeback() * might have just cleared PageReclaim, then From 46011e6ea39235e4aca656673c500eac81a07a17 Mon Sep 17 00:00:00 2001 From: David Daney Date: Mon, 3 Aug 2015 17:48:43 -0700 Subject: [PATCH 381/428] MIPS: Make set_pte() SMP safe. On MIPS the GLOBAL bit of the PTE must have the same value in any aligned pair of PTEs. These pairs of PTEs are referred to as "buddies". In a SMP system is is possible for two CPUs to be calling set_pte() on adjacent PTEs at the same time. There is a race between setting the PTE and a different CPU setting the GLOBAL bit in its buddy PTE. This race can be observed when multiple CPUs are executing vmap()/vfree() at the same time. Make setting the buddy PTE's GLOBAL bit an atomic operation to close the race condition. The case of CONFIG_64BIT_PHYS_ADDR && CONFIG_CPU_MIPS32 is *not* handled. Signed-off-by: David Daney Cc: Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/10835/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/pgtable.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 9d8106758142..ae8569475264 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -182,8 +182,39 @@ static inline void set_pte(pte_t *ptep, pte_t pteval) * Make sure the buddy is global too (if it's !none, * it better already be global) */ +#ifdef CONFIG_SMP + /* + * For SMP, multiple CPUs can race, so we need to do + * this atomically. + */ +#ifdef CONFIG_64BIT +#define LL_INSN "lld" +#define SC_INSN "scd" +#else /* CONFIG_32BIT */ +#define LL_INSN "ll" +#define SC_INSN "sc" +#endif + unsigned long page_global = _PAGE_GLOBAL; + unsigned long tmp; + + __asm__ __volatile__ ( + " .set push\n" + " .set noreorder\n" + "1: " LL_INSN " %[tmp], %[buddy]\n" + " bnez %[tmp], 2f\n" + " or %[tmp], %[tmp], %[global]\n" + " " SC_INSN " %[tmp], %[buddy]\n" + " beqz %[tmp], 1b\n" + " nop\n" + "2:\n" + " .set pop" + : [buddy] "+m" (buddy->pte), + [tmp] "=&r" (tmp) + : [global] "r" (page_global)); +#else /* !CONFIG_SMP */ if (pte_none(*buddy)) pte_val(*buddy) = pte_val(*buddy) | _PAGE_GLOBAL; +#endif /* CONFIG_SMP */ } #endif } From 4a6ca1a2c2530af4611024476ba7005bf0336dfe Mon Sep 17 00:00:00 2001 From: Jean-Francois Moine Date: Fri, 17 Jul 2015 13:07:35 +0200 Subject: [PATCH 382/428] drm/i2c: tda998x: fix bad checksum of the HDMI AVI infoframe The commit 8c7a075da9f7980cc95ffcd7e6621d4a87f20f40 "drm/i2c: tda998x: use drm_hdmi_avi_infoframe_from_display_mode()" also uses hdmi_avi_infoframe_pack() to create the AVI infoframe. This function sets the checksum of the frame and this breaks the second calculation of the checksum done in tda998x_write_if(). Fixes: 8c7a075da9f7980c ("drm/i2c: tda998x: use drm_hdmi_avi_infoframe_from_display_mode()") Signed-off-by: Jean-Francois Moine Signed-off-by: Russell King --- drivers/gpu/drm/i2c/tda998x_drv.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c index 290a69d2315a..e7f20009f9c1 100644 --- a/drivers/gpu/drm/i2c/tda998x_drv.c +++ b/drivers/gpu/drm/i2c/tda998x_drv.c @@ -582,8 +582,6 @@ static void tda998x_write_if(struct tda998x_priv *priv, uint8_t bit, uint16_t addr, uint8_t *buf, size_t size) { - buf[PB(0)] = tda998x_cksum(buf, size); - reg_clear(priv, REG_DIP_IF_FLAGS, bit); reg_write_range(priv, addr, buf, size); reg_set(priv, REG_DIP_IF_FLAGS, bit); @@ -603,6 +601,8 @@ tda998x_write_aif(struct tda998x_priv *priv, struct tda998x_encoder_params *p) buf[PB(4)] = p->audio_frame[4]; buf[PB(5)] = p->audio_frame[5] & 0xf8; /* DM_INH + LSV */ + buf[PB(0)] = tda998x_cksum(buf, sizeof(buf)); + tda998x_write_if(priv, DIP_IF_FLAGS_IF4, REG_IF4_HB0, buf, sizeof(buf)); } From fc1a8126bf8095b10f5a79893f2d2b19227f88f2 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Tue, 4 Aug 2015 10:58:26 -0600 Subject: [PATCH 383/428] KVM: MTRR: Use default type for non-MTRR-covered gfn before WARN_ON The patch was munged on commit to re-order these tests resulting in excessive warnings when trying to do device assignment. Return to original ordering: https://lkml.org/lkml/2015/7/15/769 Fixes: 3e5d2fdceda1 ("KVM: MTRR: simplify kvm_mtrr_get_guest_memory_type") Signed-off-by: Alex Williamson Reviewed-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mtrr.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index dc0a84a6f309..9e8bf13572e6 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -672,16 +672,16 @@ u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) if (iter.mtrr_disabled) return mtrr_disabled_type(); + /* not contained in any MTRRs. */ + if (type == -1) + return mtrr_default_type(mtrr_state); + /* * We just check one page, partially covered by MTRRs is * impossible. */ WARN_ON(iter.partial_map); - /* not contained in any MTRRs. */ - if (type == -1) - return mtrr_default_type(mtrr_state); - return type; } EXPORT_SYMBOL_GPL(kvm_mtrr_get_guest_memory_type); From 73851b36fe73819f8c201971e913324d4846a7ea Mon Sep 17 00:00:00 2001 From: Hui Wang Date: Wed, 5 Aug 2015 18:03:34 +0800 Subject: [PATCH 384/428] ALSA: hda - one Dell machine needs the headphone white noise fixup The fixup ALC292_FIXUP_DISABLE_AAMIX can fix the white noise of the headphone on this Dell machine. Cc: Signed-off-by: Hui Wang Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index c456c04e0928..0b9847affbec 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5189,6 +5189,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x06c7, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x06d9, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x06da, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1028, 0x06de, "Dell", ALC292_FIXUP_DISABLE_AAMIX), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), From a4b45b25f18d1e798965efec429ba5fc01b9f0b6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Thu, 30 Jul 2015 20:41:57 +0200 Subject: [PATCH 385/428] hwmon: (dell-smm) Blacklist Dell Studio XPS 8100 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit CPU fan speed going up and down on Dell Studio XPS 8100 for unknown reasons. Without further debugging on the affected machine, it is not possible to find the problem. Link: https://bugzilla.kernel.org/show_bug.cgi?id=100121 Signed-off-by: Pali Rohár Tested-by: Jan C Peters Cc: stable@vger.kernel.org # v4.0+, will need backport [groeck: cleaned up description, comments] Signed-off-by: Guenter Roeck --- drivers/hwmon/dell-smm-hwmon.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c index 37c16afe007a..c8487894b312 100644 --- a/drivers/hwmon/dell-smm-hwmon.c +++ b/drivers/hwmon/dell-smm-hwmon.c @@ -929,6 +929,21 @@ static struct dmi_system_id i8k_dmi_table[] __initdata = { MODULE_DEVICE_TABLE(dmi, i8k_dmi_table); +static struct dmi_system_id i8k_blacklist_dmi_table[] __initdata = { + { + /* + * CPU fan speed going up and down on Dell Studio XPS 8100 + * for unknown reasons. + */ + .ident = "Dell Studio XPS 8100", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Studio XPS 8100"), + }, + }, + { } +}; + /* * Probe for the presence of a supported laptop. */ @@ -940,7 +955,8 @@ static int __init i8k_probe(void) /* * Get DMI information */ - if (!dmi_check_system(i8k_dmi_table)) { + if (!dmi_check_system(i8k_dmi_table) || + dmi_check_system(i8k_blacklist_dmi_table)) { if (!ignore_dmi && !force) return -ENODEV; From 1252be9ce0ab4f622b8692b648894d09c0df71ce Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Thu, 30 Jul 2015 18:18:39 +0200 Subject: [PATCH 386/428] hwmon: (nct7904) Export I2C module alias information The I2C core always reports the MODALIAS uevent as "i2c: Cc: stable@vger.kernel.org # v4.1+ Signed-off-by: Guenter Roeck --- drivers/hwmon/nct7904.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c index 6153df735e82..08ff89d222e5 100644 --- a/drivers/hwmon/nct7904.c +++ b/drivers/hwmon/nct7904.c @@ -575,6 +575,7 @@ static const struct i2c_device_id nct7904_id[] = { {"nct7904", 0}, {} }; +MODULE_DEVICE_TABLE(i2c, nct7904_id); static struct i2c_driver nct7904_driver = { .class = I2C_CLASS_HWMON, From de66b380977eb9daa925aeb21756a9b00f700e45 Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Thu, 30 Jul 2015 18:18:43 +0200 Subject: [PATCH 387/428] hwmon: (g762) Export OF module alias information The I2C core always reports the MODALIAS uevent as "i2c: Signed-off-by: Guenter Roeck --- drivers/hwmon/g762.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hwmon/g762.c b/drivers/hwmon/g762.c index 9b55e673b67c..85d106fe3ce8 100644 --- a/drivers/hwmon/g762.c +++ b/drivers/hwmon/g762.c @@ -582,6 +582,7 @@ static const struct of_device_id g762_dt_match[] = { { .compatible = "gmt,g763" }, { }, }; +MODULE_DEVICE_TABLE(of, g762_dt_match); /* * Grab clock (a required property), enable it, get (fixed) clock frequency From e661d0a04462dd98667f8947141bd8defab5b34a Mon Sep 17 00:00:00 2001 From: Marek Belisko Date: Wed, 29 Jul 2015 14:02:19 -0700 Subject: [PATCH 388/428] Input: twl4030-vibra - fix ERROR: Bad of_node_put() warning Fix following: [ 8.862274] ERROR: Bad of_node_put() on /ocp/i2c@48070000/twl@48/audio [ 8.869293] CPU: 0 PID: 1003 Comm: modprobe Not tainted 4.2.0-rc2-letux+ #1175 [ 8.876922] Hardware name: Generic OMAP36xx (Flattened Device Tree) [ 8.883514] [] (unwind_backtrace) from [] (show_stack+0x10/0x14) [ 8.891693] [] (show_stack) from [] (dump_stack+0x78/0x94) [ 8.899322] [] (dump_stack) from [] (kobject_release+0x68/0x7c) [ 8.907409] [] (kobject_release) from [] (twl4030_vibra_probe+0x74/0x188 [twl4030_vibra]) [ 8.917877] [] (twl4030_vibra_probe [twl4030_vibra]) from [] (platform_drv_probe+0x48/0x90) [ 8.928497] [] (platform_drv_probe) from [] (really_probe+0xd4/0x238) [ 8.937103] [] (really_probe) from [] (driver_probe_device+0x30/0x48) [ 8.945678] [] (driver_probe_device) from [] (__driver_attach+0x68/0x8c) [ 8.954589] [] (__driver_attach) from [] (bus_for_each_dev+0x50/0x84) [ 8.963226] [] (bus_for_each_dev) from [] (bus_add_driver+0xcc/0x1e4) [ 8.971832] [] (bus_add_driver) from [] (driver_register+0x9c/0xe0) [ 8.980255] [] (driver_register) from [] (do_one_initcall+0x100/0x1b8) [ 8.988983] [] (do_one_initcall) from [] (do_init_module+0x58/0x1c0) [ 8.997497] [] (do_init_module) from [] (SyS_init_module+0x54/0x64) [ 9.005950] [] (SyS_init_module) from [] (ret_fast_syscall+0x0/0x54) [ 9.015838] input: twl4030:vibrator as /devices/platform/68000000.ocp/48070000.i2c/i2c-0/0-0048/48070000.i2c:twl@48:audio/input/input2 node passed to of_find_node_by_name is put inside that function and new node is returned if found. Free returned node not already freed node. Signed-off-by: Marek Belisko Signed-off-by: Dmitry Torokhov --- drivers/input/misc/twl4030-vibra.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/input/misc/twl4030-vibra.c b/drivers/input/misc/twl4030-vibra.c index fc17b9592f54..10c4e3d462f1 100644 --- a/drivers/input/misc/twl4030-vibra.c +++ b/drivers/input/misc/twl4030-vibra.c @@ -183,7 +183,8 @@ static bool twl4030_vibra_check_coexist(struct twl4030_vibra_data *pdata, if (pdata && pdata->coexist) return true; - if (of_find_node_by_name(node, "codec")) { + node = of_find_node_by_name(node, "codec"); + if (node) { of_node_put(node); return true; } From a0e2f50bdb588d91a553f2f6bd56be7bedc94b1a Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 8 Jul 2015 22:23:38 -0400 Subject: [PATCH 389/428] drm/amdgpu: fix rb setting for CZ MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Always set num_rbs to 2 for CZ. The 1 RB parts are often harvest configs. The will get sorted out in mesa when we program PA_SC_RASTER_CONFIG[_1]. Acked-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 9e1d4ddbf475..f7538ddf3a9f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -1983,6 +1983,7 @@ static void gfx_v8_0_gpu_init(struct amdgpu_device *adev) adev->gfx.config.max_shader_engines = 1; adev->gfx.config.max_tile_pipes = 2; adev->gfx.config.max_sh_per_se = 1; + adev->gfx.config.max_backends_per_se = 2; switch (adev->pdev->revision) { case 0xc4: @@ -1991,7 +1992,6 @@ static void gfx_v8_0_gpu_init(struct amdgpu_device *adev) case 0xcc: /* B10 */ adev->gfx.config.max_cu_per_sh = 8; - adev->gfx.config.max_backends_per_se = 2; break; case 0xc5: case 0x81: @@ -2000,14 +2000,12 @@ static void gfx_v8_0_gpu_init(struct amdgpu_device *adev) case 0xcd: /* B8 */ adev->gfx.config.max_cu_per_sh = 6; - adev->gfx.config.max_backends_per_se = 2; break; case 0xc6: case 0xca: case 0xce: /* B6 */ adev->gfx.config.max_cu_per_sh = 6; - adev->gfx.config.max_backends_per_se = 2; break; case 0xc7: case 0x87: @@ -2015,7 +2013,6 @@ static void gfx_v8_0_gpu_init(struct amdgpu_device *adev) default: /* B4 */ adev->gfx.config.max_cu_per_sh = 4; - adev->gfx.config.max_backends_per_se = 1; break; } From 0fd64291031d3587753b8adc53123b277855c777 Mon Sep 17 00:00:00 2001 From: Nicolas Iooss Date: Sat, 1 Aug 2015 21:55:38 +0800 Subject: [PATCH 390/428] drm/amdgpu: increment queue when iterating on this variable. gfx_v7_0_print_status contains a for loop on variable queue which does not update this variable between each iteration. This is bug is reported by clang while building allmodconfig LLVMLinux on x86_64: drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c:5126:19: error: variable 'queue' used in loop condition not modified in loop body [-Werror,-Wloop-analysis] for (queue = 0; queue < 8; i++) { ^~~~~ Fix this by incrementing variable queue instead of i in this loop. Signed-off-by: Nicolas Iooss Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index 2db6ab0a543d..5c03420ca5dc 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -5122,7 +5122,7 @@ static void gfx_v7_0_print_status(void *handle) dev_info(adev->dev, " CP_HPD_EOP_CONTROL=0x%08X\n", RREG32(mmCP_HPD_EOP_CONTROL)); - for (queue = 0; queue < 8; i++) { + for (queue = 0; queue < 8; queue++) { cik_srbm_select(adev, me, pipe, queue, 0); dev_info(adev->dev, " queue: %d\n", queue); dev_info(adev->dev, " CP_PQ_WPTR_POLL_CNTL=0x%08X\n", From 351643d7dd8a48b1053aac5fe3a1aebac614c301 Mon Sep 17 00:00:00 2001 From: Jammy Zhou Date: Tue, 4 Aug 2015 10:43:50 +0800 Subject: [PATCH 391/428] drm/amdgpu: add feature version for RLC and MEC v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Expose feature version to user space for RLC/MEC/MEC2 ucode as well v2: fix coding style Signed-off-by: Jammy Zhou Reviewed-by: Christian König --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 3 +++ drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 11 ++++++----- drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 6 ++++++ drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 6 ++++++ 4 files changed, 21 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 31b00f91cfcd..8db642b5abb2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1130,6 +1130,9 @@ struct amdgpu_gfx { uint32_t me_feature_version; uint32_t ce_feature_version; uint32_t pfp_feature_version; + uint32_t rlc_feature_version; + uint32_t mec_feature_version; + uint32_t mec2_feature_version; struct amdgpu_ring gfx_ring[AMDGPU_MAX_GFX_RINGS]; unsigned num_gfx_rings; struct amdgpu_ring compute_ring[AMDGPU_MAX_COMPUTE_RINGS]; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 9736892bcdf9..79eba82defed 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -317,16 +317,17 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file break; case AMDGPU_INFO_FW_GFX_RLC: fw_info.ver = adev->gfx.rlc_fw_version; - fw_info.feature = 0; + fw_info.feature = adev->gfx.rlc_feature_version; break; case AMDGPU_INFO_FW_GFX_MEC: - if (info->query_fw.index == 0) + if (info->query_fw.index == 0) { fw_info.ver = adev->gfx.mec_fw_version; - else if (info->query_fw.index == 1) + fw_info.feature = adev->gfx.mec_feature_version; + } else if (info->query_fw.index == 1) { fw_info.ver = adev->gfx.mec2_fw_version; - else + fw_info.feature = adev->gfx.mec2_feature_version; + } else return -EINVAL; - fw_info.feature = 0; break; case AMDGPU_INFO_FW_SMC: fw_info.ver = adev->pm.fw_version; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index 5c03420ca5dc..0d8bf2cb1956 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -3080,6 +3080,8 @@ static int gfx_v7_0_cp_compute_load_microcode(struct amdgpu_device *adev) mec_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data; amdgpu_ucode_print_gfx_hdr(&mec_hdr->header); adev->gfx.mec_fw_version = le32_to_cpu(mec_hdr->header.ucode_version); + adev->gfx.mec_feature_version = le32_to_cpu( + mec_hdr->ucode_feature_version); gfx_v7_0_cp_compute_enable(adev, false); @@ -3102,6 +3104,8 @@ static int gfx_v7_0_cp_compute_load_microcode(struct amdgpu_device *adev) mec2_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec2_fw->data; amdgpu_ucode_print_gfx_hdr(&mec2_hdr->header); adev->gfx.mec2_fw_version = le32_to_cpu(mec2_hdr->header.ucode_version); + adev->gfx.mec2_feature_version = le32_to_cpu( + mec2_hdr->ucode_feature_version); /* MEC2 */ fw_data = (const __le32 *) @@ -4066,6 +4070,8 @@ static int gfx_v7_0_rlc_resume(struct amdgpu_device *adev) hdr = (const struct rlc_firmware_header_v1_0 *)adev->gfx.rlc_fw->data; amdgpu_ucode_print_rlc_hdr(&hdr->header); adev->gfx.rlc_fw_version = le32_to_cpu(hdr->header.ucode_version); + adev->gfx.rlc_feature_version = le32_to_cpu( + hdr->ucode_feature_version); gfx_v7_0_rlc_stop(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index f7538ddf3a9f..0ac38ee298d1 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -2273,6 +2273,8 @@ static int gfx_v8_0_rlc_load_microcode(struct amdgpu_device *adev) hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data; amdgpu_ucode_print_rlc_hdr(&hdr->header); adev->gfx.rlc_fw_version = le32_to_cpu(hdr->header.ucode_version); + adev->gfx.rlc_feature_version = le32_to_cpu( + hdr->ucode_feature_version); fw_data = (const __le32 *)(adev->gfx.rlc_fw->data + le32_to_cpu(hdr->header.ucode_array_offset_bytes)); @@ -2620,6 +2622,8 @@ static int gfx_v8_0_cp_compute_load_microcode(struct amdgpu_device *adev) mec_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data; amdgpu_ucode_print_gfx_hdr(&mec_hdr->header); adev->gfx.mec_fw_version = le32_to_cpu(mec_hdr->header.ucode_version); + adev->gfx.mec_feature_version = le32_to_cpu( + mec_hdr->ucode_feature_version); fw_data = (const __le32 *) (adev->gfx.mec_fw->data + @@ -2639,6 +2643,8 @@ static int gfx_v8_0_cp_compute_load_microcode(struct amdgpu_device *adev) mec2_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec2_fw->data; amdgpu_ucode_print_gfx_hdr(&mec2_hdr->header); adev->gfx.mec2_fw_version = le32_to_cpu(mec2_hdr->header.ucode_version); + adev->gfx.mec2_feature_version = le32_to_cpu( + mec2_hdr->ucode_feature_version); fw_data = (const __le32 *) (adev->gfx.mec2_fw->data + From cfa2104fbcb87ab0abbdaba608087df1e24fe195 Mon Sep 17 00:00:00 2001 From: Jammy Zhou Date: Tue, 4 Aug 2015 10:50:47 +0800 Subject: [PATCH 392/428] drm/amdgpu: add feature version for SDMA ucode MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Jammy Zhou Reviewed-by: Christian König --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 2 +- drivers/gpu/drm/amd/amdgpu/cik_sdma.c | 1 + drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c | 1 + drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 1 + 5 files changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 8db642b5abb2..f7b49d5ce4b8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1642,6 +1642,7 @@ struct amdgpu_sdma { /* SDMA firmware */ const struct firmware *fw; uint32_t fw_version; + uint32_t feature_version; struct amdgpu_ring ring; }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 79eba82defed..3bfe67de8349 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -337,7 +337,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file if (info->query_fw.index >= 2) return -EINVAL; fw_info.ver = adev->sdma[info->query_fw.index].fw_version; - fw_info.feature = 0; + fw_info.feature = adev->sdma[info->query_fw.index].feature_version; break; default: return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c index ab83cc1ca4cc..15df46c93f0a 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c @@ -500,6 +500,7 @@ static int cik_sdma_load_microcode(struct amdgpu_device *adev) amdgpu_ucode_print_sdma_hdr(&hdr->header); fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4; adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version); + adev->sdma[i].feature_version = le32_to_cpu(hdr->ucode_feature_version); fw_data = (const __le32 *) (adev->sdma[i].fw->data + le32_to_cpu(hdr->header.ucode_array_offset_bytes)); WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], 0); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c index d7895885fe0c..01bd5c903f9b 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c @@ -542,6 +542,7 @@ static int sdma_v2_4_load_microcode(struct amdgpu_device *adev) amdgpu_ucode_print_sdma_hdr(&hdr->header); fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4; adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version); + adev->sdma[i].feature_version = le32_to_cpu(hdr->ucode_feature_version); fw_data = (const __le32 *) (adev->sdma[i].fw->data + diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c index 7bb37b93993f..cf9bc2e126fc 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c @@ -631,6 +631,7 @@ static int sdma_v3_0_load_microcode(struct amdgpu_device *adev) amdgpu_ucode_print_sdma_hdr(&hdr->header); fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4; adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version); + adev->sdma[i].feature_version = le32_to_cpu(hdr->ucode_feature_version); fw_data = (const __le32 *) (adev->sdma[i].fw->data + From 595fd013f795daeed0c7ddda02d8e0c51d8ce76c Mon Sep 17 00:00:00 2001 From: Jammy Zhou Date: Tue, 4 Aug 2015 11:44:19 +0800 Subject: [PATCH 393/428] drm/amdgpu: set fw_version and feature_version for smu fw loading MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The fw_version and feature_verion should be set correctly when the firmwares are loaded by SMU on Tonga/Carrzio/Iceland Signed-off-by: Jammy Zhou Reviewed-by: Christian König --- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 37 +++++++++++++++----------- drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c | 7 ++--- drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 7 ++--- 3 files changed, 30 insertions(+), 21 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 0ac38ee298d1..f5a42ab1f65c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -587,6 +587,7 @@ static int gfx_v8_0_init_microcode(struct amdgpu_device *adev) int err; struct amdgpu_firmware_info *info = NULL; const struct common_firmware_header *header = NULL; + const struct gfx_firmware_header_v1_0 *cp_hdr; DRM_DEBUG("\n"); @@ -611,6 +612,9 @@ static int gfx_v8_0_init_microcode(struct amdgpu_device *adev) err = amdgpu_ucode_validate(adev->gfx.pfp_fw); if (err) goto out; + cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.pfp_fw->data; + adev->gfx.pfp_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); + adev->gfx.pfp_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", chip_name); err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev); @@ -619,6 +623,9 @@ static int gfx_v8_0_init_microcode(struct amdgpu_device *adev) err = amdgpu_ucode_validate(adev->gfx.me_fw); if (err) goto out; + cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.me_fw->data; + adev->gfx.me_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); + adev->gfx.me_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce.bin", chip_name); err = request_firmware(&adev->gfx.ce_fw, fw_name, adev->dev); @@ -627,12 +634,18 @@ static int gfx_v8_0_init_microcode(struct amdgpu_device *adev) err = amdgpu_ucode_validate(adev->gfx.ce_fw); if (err) goto out; + cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.ce_fw->data; + adev->gfx.ce_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); + adev->gfx.ce_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", chip_name); err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev); if (err) goto out; err = amdgpu_ucode_validate(adev->gfx.rlc_fw); + cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.rlc_fw->data; + adev->gfx.rlc_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); + adev->gfx.rlc_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", chip_name); err = request_firmware(&adev->gfx.mec_fw, fw_name, adev->dev); @@ -641,6 +654,9 @@ static int gfx_v8_0_init_microcode(struct amdgpu_device *adev) err = amdgpu_ucode_validate(adev->gfx.mec_fw); if (err) goto out; + cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data; + adev->gfx.mec_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); + adev->gfx.mec_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2.bin", chip_name); err = request_firmware(&adev->gfx.mec2_fw, fw_name, adev->dev); @@ -648,6 +664,12 @@ static int gfx_v8_0_init_microcode(struct amdgpu_device *adev) err = amdgpu_ucode_validate(adev->gfx.mec2_fw); if (err) goto out; + cp_hdr = (const struct gfx_firmware_header_v1_0 *) + adev->gfx.mec2_fw->data; + adev->gfx.mec2_fw_version = le32_to_cpu( + cp_hdr->header.ucode_version); + adev->gfx.mec2_feature_version = le32_to_cpu( + cp_hdr->ucode_feature_version); } else { err = 0; adev->gfx.mec2_fw = NULL; @@ -2272,9 +2294,6 @@ static int gfx_v8_0_rlc_load_microcode(struct amdgpu_device *adev) hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data; amdgpu_ucode_print_rlc_hdr(&hdr->header); - adev->gfx.rlc_fw_version = le32_to_cpu(hdr->header.ucode_version); - adev->gfx.rlc_feature_version = le32_to_cpu( - hdr->ucode_feature_version); fw_data = (const __le32 *)(adev->gfx.rlc_fw->data + le32_to_cpu(hdr->header.ucode_array_offset_bytes)); @@ -2360,12 +2379,6 @@ static int gfx_v8_0_cp_gfx_load_microcode(struct amdgpu_device *adev) amdgpu_ucode_print_gfx_hdr(&pfp_hdr->header); amdgpu_ucode_print_gfx_hdr(&ce_hdr->header); amdgpu_ucode_print_gfx_hdr(&me_hdr->header); - adev->gfx.pfp_fw_version = le32_to_cpu(pfp_hdr->header.ucode_version); - adev->gfx.ce_fw_version = le32_to_cpu(ce_hdr->header.ucode_version); - adev->gfx.me_fw_version = le32_to_cpu(me_hdr->header.ucode_version); - adev->gfx.me_feature_version = le32_to_cpu(me_hdr->ucode_feature_version); - adev->gfx.ce_feature_version = le32_to_cpu(ce_hdr->ucode_feature_version); - adev->gfx.pfp_feature_version = le32_to_cpu(pfp_hdr->ucode_feature_version); gfx_v8_0_cp_gfx_enable(adev, false); @@ -2621,9 +2634,6 @@ static int gfx_v8_0_cp_compute_load_microcode(struct amdgpu_device *adev) mec_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data; amdgpu_ucode_print_gfx_hdr(&mec_hdr->header); - adev->gfx.mec_fw_version = le32_to_cpu(mec_hdr->header.ucode_version); - adev->gfx.mec_feature_version = le32_to_cpu( - mec_hdr->ucode_feature_version); fw_data = (const __le32 *) (adev->gfx.mec_fw->data + @@ -2642,9 +2652,6 @@ static int gfx_v8_0_cp_compute_load_microcode(struct amdgpu_device *adev) mec2_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec2_fw->data; amdgpu_ucode_print_gfx_hdr(&mec2_hdr->header); - adev->gfx.mec2_fw_version = le32_to_cpu(mec2_hdr->header.ucode_version); - adev->gfx.mec2_feature_version = le32_to_cpu( - mec2_hdr->ucode_feature_version); fw_data = (const __le32 *) (adev->gfx.mec2_fw->data + diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c index 01bd5c903f9b..a988dfb1d394 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c @@ -121,6 +121,7 @@ static int sdma_v2_4_init_microcode(struct amdgpu_device *adev) int err, i; struct amdgpu_firmware_info *info = NULL; const struct common_firmware_header *header = NULL; + const struct sdma_firmware_header_v1_0 *hdr; DRM_DEBUG("\n"); @@ -142,6 +143,9 @@ static int sdma_v2_4_init_microcode(struct amdgpu_device *adev) err = amdgpu_ucode_validate(adev->sdma[i].fw); if (err) goto out; + hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data; + adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version); + adev->sdma[i].feature_version = le32_to_cpu(hdr->ucode_feature_version); if (adev->firmware.smu_load) { info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SDMA0 + i]; @@ -541,9 +545,6 @@ static int sdma_v2_4_load_microcode(struct amdgpu_device *adev) hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data; amdgpu_ucode_print_sdma_hdr(&hdr->header); fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4; - adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version); - adev->sdma[i].feature_version = le32_to_cpu(hdr->ucode_feature_version); - fw_data = (const __le32 *) (adev->sdma[i].fw->data + le32_to_cpu(hdr->header.ucode_array_offset_bytes)); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c index cf9bc2e126fc..2b86569b18d3 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c @@ -159,6 +159,7 @@ static int sdma_v3_0_init_microcode(struct amdgpu_device *adev) int err, i; struct amdgpu_firmware_info *info = NULL; const struct common_firmware_header *header = NULL; + const struct sdma_firmware_header_v1_0 *hdr; DRM_DEBUG("\n"); @@ -183,6 +184,9 @@ static int sdma_v3_0_init_microcode(struct amdgpu_device *adev) err = amdgpu_ucode_validate(adev->sdma[i].fw); if (err) goto out; + hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data; + adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version); + adev->sdma[i].feature_version = le32_to_cpu(hdr->ucode_feature_version); if (adev->firmware.smu_load) { info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SDMA0 + i]; @@ -630,9 +634,6 @@ static int sdma_v3_0_load_microcode(struct amdgpu_device *adev) hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data; amdgpu_ucode_print_sdma_hdr(&hdr->header); fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4; - adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version); - adev->sdma[i].feature_version = le32_to_cpu(hdr->ucode_feature_version); - fw_data = (const __le32 *) (adev->sdma[i].fw->data + le32_to_cpu(hdr->header.ucode_array_offset_bytes)); From df4198b1e0c4a7d1adde1e5c2ceb67ac10b391bb Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Thu, 6 Aug 2015 13:54:21 +0800 Subject: [PATCH 394/428] virtio-input: reset device and detach unused during remove Spec requires a device reset during cleanup, so do it and avoid warn in virtio core. And detach unused buffers to avoid memory leak. Signed-off-by: Jason Wang Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_input.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/virtio/virtio_input.c b/drivers/virtio/virtio_input.c index 60e2a1677563..c96944b59856 100644 --- a/drivers/virtio/virtio_input.c +++ b/drivers/virtio/virtio_input.c @@ -313,6 +313,7 @@ err_init_vq: static void virtinput_remove(struct virtio_device *vdev) { struct virtio_input *vi = vdev->priv; + void *buf; unsigned long flags; spin_lock_irqsave(&vi->lock, flags); @@ -320,6 +321,9 @@ static void virtinput_remove(struct virtio_device *vdev) spin_unlock_irqrestore(&vi->lock, flags); input_unregister_device(vi->idev); + vdev->config->reset(vdev); + while ((buf = virtqueue_detach_unused_buf(vi->sts)) != NULL) + kfree(buf); vdev->config->del_vqs(vdev); kfree(vi); } From 6dc6db790a67d28e46abefc44ca1a3bd438b2920 Mon Sep 17 00:00:00 2001 From: "Subhransu S. Prusty" Date: Mon, 29 Jun 2015 17:36:44 +0100 Subject: [PATCH 395/428] ASoC: topology: Add subsequence in topology Some widgets may need sorting within, So add this support in topology. Signed-off-by: Subhransu S. Prusty Signed-off-by: Mark Brown --- include/uapi/sound/asoc.h | 1 + sound/soc/soc-topology.c | 1 + 2 files changed, 2 insertions(+) diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h index 12215205ab8d..7ae13fbc0a3e 100644 --- a/include/uapi/sound/asoc.h +++ b/include/uapi/sound/asoc.h @@ -347,6 +347,7 @@ struct snd_soc_tplg_dapm_widget { __le32 reg; /* negative reg = no direct dapm */ __le32 shift; /* bits to shift */ __le32 mask; /* non-shifted mask */ + __le32 subseq; /* sort within widget type */ __u32 invert; /* invert the power bit */ __u32 ignore_suspend; /* kept enabled over suspend */ __u16 event_flags; diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 6a547c6dd3a1..9f2b048f1071 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -1351,6 +1351,7 @@ static int soc_tplg_dapm_widget_create(struct soc_tplg *tplg, template.reg = w->reg; template.shift = w->shift; template.mask = w->mask; + template.subseq = w->subseq; template.on_val = w->invert ? 0 : 1; template.off_val = w->invert ? 1 : 0; template.ignore_suspend = w->ignore_suspend; From c3879956957b8de9fd6cbad604e668fd00c6506c Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Mon, 29 Jun 2015 17:36:46 +0100 Subject: [PATCH 396/428] ASoC: topology: add private data to manifest The topology file manifest should include a private data field. This allows vendors to specify vendor data in the manifest, like timestamps, hashes, additional information for removing platform configuration out of drivers and making these configurable per platform Signed-off-by: Vinod Koul Signed-off-by: Mark Brown --- include/uapi/sound/asoc.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h index 7ae13fbc0a3e..d550c8d40269 100644 --- a/include/uapi/sound/asoc.h +++ b/include/uapi/sound/asoc.h @@ -238,6 +238,7 @@ struct snd_soc_tplg_manifest { __le32 graph_elems; /* number of graph elements */ __le32 dai_elems; /* number of DAI elements */ __le32 dai_link_elems; /* number of DAI link elements */ + struct snd_soc_tplg_private priv; } __attribute__((packed)); /* From 28a87eebcad40101b1b273cbd4f2a02c104f9367 Mon Sep 17 00:00:00 2001 From: Mengdong Lin Date: Wed, 5 Aug 2015 14:41:13 +0100 Subject: [PATCH 397/428] ASoC: topology: Update TLV support so we can support more TLV types Currently the TLV topology structure is targeted at only supporting the DB scale data. This patch extends support for the other TLV types so they can be easily added at a later stage. TLV structure is moved to common topology control header since it's a common field for controls and can be processed in a general way. Users must set a proper access flag for a control since it's used to decide if the TLV field is valid and if a TLV callback is needed. Removed the following fields from topology TLV struct: - size/count: type can decide the size. - numid: not needed to initialize TLV for kcontrol. - data: replaced by the type specific struct. Added TLV structure to generic control header and removed TLV structure from mixer control. Signed-off-by: Mengdong Lin Signed-off-by: Liam Girdwood Signed-off-by: Mark Brown --- include/uapi/sound/asoc.h | 19 +++++++++---- sound/soc/soc-topology.c | 60 +++++++++++++++++++++++++++------------ 2 files changed, 55 insertions(+), 24 deletions(-) diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h index 2819fc1f8458..aa3a79b42438 100644 --- a/include/uapi/sound/asoc.h +++ b/include/uapi/sound/asoc.h @@ -137,11 +137,19 @@ struct snd_soc_tplg_private { /* * Kcontrol TLV data. */ +struct snd_soc_tplg_tlv_dbscale { + __le32 min; + __le32 step; + __le32 mute; +} __attribute__((packed)); + struct snd_soc_tplg_ctl_tlv { - __le32 size; /* in bytes aligned to 4 */ - __le32 numid; /* control element numeric identification */ - __le32 count; /* number of elem in data array */ - __le32 data[SND_SOC_TPLG_TLV_SIZE]; + __le32 size; /* in bytes of this structure */ + __le32 type; /* SNDRV_CTL_TLVT_*, type of TLV */ + union { + __le32 data[SND_SOC_TPLG_TLV_SIZE]; + struct snd_soc_tplg_tlv_dbscale scale; + }; } __attribute__((packed)); /* @@ -172,7 +180,7 @@ struct snd_soc_tplg_ctl_hdr { char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; __le32 access; struct snd_soc_tplg_kcontrol_ops_id ops; - __le32 tlv_size; /* non zero means control has TLV data */ + struct snd_soc_tplg_ctl_tlv tlv; } __attribute__((packed)); /* @@ -260,7 +268,6 @@ struct snd_soc_tplg_mixer_control { __le32 invert; __le32 num_channels; struct snd_soc_tplg_channel channel[SND_SOC_TPLG_MAX_CHAN]; - struct snd_soc_tplg_ctl_tlv tlv; struct snd_soc_tplg_private priv; } __attribute__((packed)); diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 2c70f30d2d78..31068b8f3db0 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -33,6 +33,7 @@ #include #include #include +#include /* * We make several passes over the data (since it wont necessarily be ordered) @@ -579,28 +580,51 @@ static int soc_tplg_init_kcontrol(struct soc_tplg *tplg, return 0; } -static int soc_tplg_create_tlv(struct soc_tplg *tplg, - struct snd_kcontrol_new *kc, struct snd_soc_tplg_ctl_tlv *tplg_tlv) + +static int soc_tplg_create_tlv_db_scale(struct soc_tplg *tplg, + struct snd_kcontrol_new *kc, struct snd_soc_tplg_tlv_dbscale *scale) { - struct snd_ctl_tlv *tlv; - int size; + unsigned int item_len = 2 * sizeof(unsigned int); + unsigned int *p; - if (tplg_tlv->count == 0) - return 0; - - size = ((tplg_tlv->count + (sizeof(unsigned int) - 1)) & - ~(sizeof(unsigned int) - 1)); - tlv = kzalloc(sizeof(*tlv) + size, GFP_KERNEL); - if (tlv == NULL) + p = kzalloc(item_len + 2 * sizeof(unsigned int), GFP_KERNEL); + if (!p) return -ENOMEM; - dev_dbg(tplg->dev, " created TLV type %d size %d bytes\n", - tplg_tlv->numid, size); + p[0] = SNDRV_CTL_TLVT_DB_SCALE; + p[1] = item_len; + p[2] = scale->min; + p[3] = (scale->step & TLV_DB_SCALE_MASK) + | (scale->mute ? TLV_DB_SCALE_MUTE : 0); - tlv->numid = tplg_tlv->numid; - tlv->length = size; - memcpy(&tlv->tlv[0], tplg_tlv->data, size); - kc->tlv.p = (void *)tlv; + kc->tlv.p = (void *)p; + return 0; +} + +static int soc_tplg_create_tlv(struct soc_tplg *tplg, + struct snd_kcontrol_new *kc, struct snd_soc_tplg_ctl_hdr *tc) +{ + struct snd_soc_tplg_ctl_tlv *tplg_tlv; + + if (!(tc->access & SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE)) + return 0; + + if (tc->access & SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK) { + kc->tlv.c = snd_soc_bytes_tlv_callback; + } else { + tplg_tlv = &tc->tlv; + switch (tplg_tlv->type) { + case SNDRV_CTL_TLVT_DB_SCALE: + return soc_tplg_create_tlv_db_scale(tplg, kc, + &tplg_tlv->scale); + + /* TODO: add support for other TLV types */ + default: + dev_dbg(tplg->dev, "Unsupported TLV type %d\n", + tplg_tlv->type); + return -EINVAL; + } + } return 0; } @@ -772,7 +796,7 @@ static int soc_tplg_dmixer_create(struct soc_tplg *tplg, unsigned int count, } /* create any TLV data */ - soc_tplg_create_tlv(tplg, &kc, &mc->tlv); + soc_tplg_create_tlv(tplg, &kc, &mc->hdr); /* register control here */ err = soc_tplg_add_kcontrol(tplg, &kc, From cb88498b36ab01cbe3a0d95cd097e4afdff4c6fd Mon Sep 17 00:00:00 2001 From: Mengdong Lin Date: Wed, 5 Aug 2015 14:41:14 +0100 Subject: [PATCH 398/428] ASoC: topology: Add ops support to byte controls UAPI Add UAPI support for setting byte control ops. Rename the ops structure to be more generic so it can be sued by other objects too. Signed-off-by: Mengdong Lin Signed-off-by: Liam Girdwood Signed-off-by: Mark Brown --- include/uapi/sound/asoc.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h index aa3a79b42438..d5281ac8e5eb 100644 --- a/include/uapi/sound/asoc.h +++ b/include/uapi/sound/asoc.h @@ -163,9 +163,11 @@ struct snd_soc_tplg_channel { } __attribute__((packed)); /* - * Kcontrol Operations IDs + * Genericl Operations IDs, for binding Kcontrol or Bytes ext ops + * Kcontrol ops need get/put/info. + * Bytes ext ops need get/put. */ -struct snd_soc_tplg_kcontrol_ops_id { +struct snd_soc_tplg_io_ops { __le32 get; __le32 put; __le32 info; @@ -179,7 +181,7 @@ struct snd_soc_tplg_ctl_hdr { __le32 type; char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; __le32 access; - struct snd_soc_tplg_kcontrol_ops_id ops; + struct snd_soc_tplg_io_ops ops; struct snd_soc_tplg_ctl_tlv tlv; } __attribute__((packed)); @@ -311,6 +313,7 @@ struct snd_soc_tplg_bytes_control { __le32 mask; __le32 base; __le32 num_regs; + struct snd_soc_tplg_io_ops ext_ops; struct snd_soc_tplg_private priv; } __attribute__((packed)); From c7bcf8777a539e64dafc7417c00047aee6eb8909 Mon Sep 17 00:00:00 2001 From: Liam Girdwood Date: Wed, 5 Aug 2015 14:41:15 +0100 Subject: [PATCH 399/428] ASoC: topology: Add private data type and bump ABI version to 3 Add ID for standalone private data object types and bump ABI version to 3 in order to userpsace features. Signed-off-by: Liam Girdwood Signed-off-by: Mark Brown --- include/uapi/sound/asoc.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h index d5281ac8e5eb..51b8066a223b 100644 --- a/include/uapi/sound/asoc.h +++ b/include/uapi/sound/asoc.h @@ -77,7 +77,7 @@ #define SND_SOC_TPLG_NUM_TEXTS 16 /* ABI version */ -#define SND_SOC_TPLG_ABI_VERSION 0x2 +#define SND_SOC_TPLG_ABI_VERSION 0x3 /* Max size of TLV data */ #define SND_SOC_TPLG_TLV_SIZE 32 @@ -97,7 +97,8 @@ #define SND_SOC_TPLG_TYPE_PCM 7 #define SND_SOC_TPLG_TYPE_MANIFEST 8 #define SND_SOC_TPLG_TYPE_CODEC_LINK 9 -#define SND_SOC_TPLG_TYPE_MAX SND_SOC_TPLG_TYPE_CODEC_LINK +#define SND_SOC_TPLG_TYPE_PDATA 10 +#define SND_SOC_TPLG_TYPE_MAX SND_SOC_TPLG_TYPE_PDATA /* vendor block IDs - please add new vendor types to end */ #define SND_SOC_TPLG_TYPE_VENDOR_FW 1000 From 047fe6e6db9161e69271f56daaafdaf2add023b1 Mon Sep 17 00:00:00 2001 From: David Weinehall Date: Tue, 4 Aug 2015 16:55:52 +0300 Subject: [PATCH 400/428] drm/i915: Allow parsing of variable size child device entries from VBT MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit VBT version 196 increased the size of common_child_dev_config. The parser code assumed that the size of this structure would not change. The modified code now copies the amount needed based on the VBT version, and emits a debug message if the VBT version is unknown (too new); since the struct config block won't shrink in newer versions it should be harmless to copy the maximum known size in such cases, so that's what we do, but emitting the warning is probably sensible anyway. In the longer run it might make sense to modify the parser code to use a version/feature mapping, rather than hardcoding things like this, but for now the variants are fairly managable. This fixes a regression introduced in commit 90e4f1592bb6e82f6690f0e05a8aadcf04d7bce7 Author: Ville Syrjälä Date: Wed Mar 25 18:45:58 2015 +0200 drm/i915: Fix the VBT child device parsing for BSW since we're hitting a DRM_ERROR on older platforms with this. v2: Stricter size checks Signed-off-by: David Weinehall [danvet: Fixup format string.] Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/intel_bios.c | 27 +++++++++++++++++++++++---- 1 file changed, 23 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index 198fc3c3291b..3dcd59e694db 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -1075,15 +1075,34 @@ parse_device_mapping(struct drm_i915_private *dev_priv, const union child_device_config *p_child; union child_device_config *child_dev_ptr; int i, child_device_num, count; - u16 block_size; + u8 expected_size; + u16 block_size; p_defs = find_section(bdb, BDB_GENERAL_DEFINITIONS); if (!p_defs) { DRM_DEBUG_KMS("No general definition block is found, no devices defined.\n"); return; } - if (p_defs->child_dev_size < sizeof(*p_child)) { - DRM_ERROR("General definiton block child device size is too small.\n"); + if (bdb->version < 195) { + expected_size = 33; + } else if (bdb->version == 195) { + expected_size = 37; + } else if (bdb->version <= 197) { + expected_size = 38; + } else { + expected_size = 38; + DRM_DEBUG_DRIVER("Expected child_device_config size for BDB version %u not known; assuming %u\n", + expected_size, bdb->version); + } + + if (expected_size > sizeof(*p_child)) { + DRM_ERROR("child_device_config cannot fit in p_child\n"); + return; + } + + if (p_defs->child_dev_size != expected_size) { + DRM_ERROR("Size mismatch; child_device_config size=%u (expected %u); bdb->version: %u\n", + p_defs->child_dev_size, expected_size, bdb->version); return; } /* get the block size of general definitions */ @@ -1130,7 +1149,7 @@ parse_device_mapping(struct drm_i915_private *dev_priv, child_dev_ptr = dev_priv->vbt.child_dev + count; count++; - memcpy(child_dev_ptr, p_child, sizeof(*p_child)); + memcpy(child_dev_ptr, p_child, p_defs->child_dev_size); } return; } From c05f9429e12da7c7de2649ef8c8c16bf8c12061f Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Mon, 3 Aug 2015 14:44:29 +0800 Subject: [PATCH 401/428] btrfs: qgroup: Fix a regression in qgroup reserved space. During the change to new btrfs extent-oriented qgroup implement, due to it doesn't use the old __qgroup_excl_accounting() for exclusive extent, it didn't free the reserved bytes. The bug will cause limit function go crazy as the reserved space is never freed, increasing limit will have no effect and still cause EQOUT. The fix is easy, just free reserved bytes for newly created exclusive extent as what it does before. Reported-by: Tsutomu Itoh Signed-off-by: Yang Dongsheng Signed-off-by: Qu Wenruo Signed-off-by: Chris Mason --- fs/btrfs/qgroup.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index e9ace099162c..8a8202956576 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1651,6 +1651,11 @@ static int qgroup_update_counters(struct btrfs_fs_info *fs_info, /* Exclusive -> exclusive, nothing changed */ } } + + /* For exclusive extent, free its reserved bytes too */ + if (nr_old_roots == 0 && nr_new_roots == 1 && + cur_new_count == nr_new_roots) + qg->reserved -= num_bytes; if (dirty) qgroup_dirty(fs_info, qg); } From de54b9ac253787c366bbfb28d901a31954eb3511 Mon Sep 17 00:00:00 2001 From: Marcus Gelderie Date: Thu, 6 Aug 2015 15:46:10 -0700 Subject: [PATCH 402/428] ipc: modify message queue accounting to not take kernel data structures into account A while back, the message queue implementation in the kernel was improved to use btrees to speed up retrieval of messages, in commit d6629859b36d ("ipc/mqueue: improve performance of send/recv"). That patch introducing the improved kernel handling of message queues (using btrees) has, as a by-product, changed the meaning of the QSIZE field in the pseudo-file created for the queue. Before, this field reflected the size of the user-data in the queue. Since, it also takes kernel data structures into account. For example, if 13 bytes of user data are in the queue, on my machine the file reports a size of 61 bytes. There was some discussion on this topic before (for example https://lkml.org/lkml/2014/10/1/115). Commenting on a th lkml, Michael Kerrisk gave the following background (https://lkml.org/lkml/2015/6/16/74): The pseudofiles in the mqueue filesystem (usually mounted at /dev/mqueue) expose fields with metadata describing a message queue. One of these fields, QSIZE, as originally implemented, showed the total number of bytes of user data in all messages in the message queue, and this feature was documented from the beginning in the mq_overview(7) page. In 3.5, some other (useful) work happened to break the user-space API in a couple of places, including the value exposed via QSIZE, which now includes a measure of kernel overhead bytes for the queue, a figure that renders QSIZE useless for its original purpose, since there's no way to deduce the number of overhead bytes consumed by the implementation. (The other user-space breakage was subsequently fixed.) This patch removes the accounting of kernel data structures in the queue. Reporting the size of these data-structures in the QSIZE field was a breaking change (see Michael's comment above). Without the QSIZE field reporting the total size of user-data in the queue, there is no way to deduce this number. It should be noted that the resource limit RLIMIT_MSGQUEUE is counted against the worst-case size of the queue (in both the old and the new implementation). Therefore, the kernel overhead accounting in QSIZE is not necessary to help the user understand the limitations RLIMIT imposes on the processes. Signed-off-by: Marcus Gelderie Acked-by: Doug Ledford Acked-by: Michael Kerrisk Acked-by: Davidlohr Bueso Cc: David Howells Cc: Alexander Viro Cc: John Duffy Cc: Arto Bendiken Cc: Manfred Spraul Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/mqueue.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/ipc/mqueue.c b/ipc/mqueue.c index a24ba9fe5bb8..161a1807e6ef 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -142,7 +142,6 @@ static int msg_insert(struct msg_msg *msg, struct mqueue_inode_info *info) if (!leaf) return -ENOMEM; INIT_LIST_HEAD(&leaf->msg_list); - info->qsize += sizeof(*leaf); } leaf->priority = msg->m_type; rb_link_node(&leaf->rb_node, parent, p); @@ -187,7 +186,6 @@ try_again: "lazy leaf delete!\n"); rb_erase(&leaf->rb_node, &info->msg_tree); if (info->node_cache) { - info->qsize -= sizeof(*leaf); kfree(leaf); } else { info->node_cache = leaf; @@ -200,7 +198,6 @@ try_again: if (list_empty(&leaf->msg_list)) { rb_erase(&leaf->rb_node, &info->msg_tree); if (info->node_cache) { - info->qsize -= sizeof(*leaf); kfree(leaf); } else { info->node_cache = leaf; @@ -1034,7 +1031,6 @@ SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr, /* Save our speculative allocation into the cache */ INIT_LIST_HEAD(&new_leaf->msg_list); info->node_cache = new_leaf; - info->qsize += sizeof(*new_leaf); new_leaf = NULL; } else { kfree(new_leaf); @@ -1142,7 +1138,6 @@ SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr, /* Save our speculative allocation into the cache */ INIT_LIST_HEAD(&new_leaf->msg_list); info->node_cache = new_leaf; - info->qsize += sizeof(*new_leaf); } else { kfree(new_leaf); } From 7ace99170789bc53cbb7e9e352d7a3851208fbcf Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 6 Aug 2015 15:46:13 -0700 Subject: [PATCH 403/428] mm, meminit: allow early_pfn_to_nid to be used during runtime early_pfn_to_nid() historically was inherently not SMP safe but only used during boot which is inherently single threaded or during hotplug which is protected by a giant mutex. With deferred memory initialisation there was a thread-safe version introduced and the early_pfn_to_nid would trigger a BUG_ON if used unsafely. Memory hotplug hit that check. This patch makes early_pfn_to_nid introduces a lock to make it safe to use during hotplug. Signed-off-by: Mel Gorman Reported-by: Alex Ng Tested-by: Alex Ng Acked-by: Peter Zijlstra (Intel) Cc: Nicolai Stange Cc: Dave Hansen Cc: Fengguang Wu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ef19f22b2b7d..ea0e6a6e7a11 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -981,21 +981,21 @@ static void __init __free_pages_boot_core(struct page *page, #if defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) || \ defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) -/* Only safe to use early in boot when initialisation is single-threaded */ + static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata; int __meminit early_pfn_to_nid(unsigned long pfn) { + static DEFINE_SPINLOCK(early_pfn_lock); int nid; - /* The system will behave unpredictably otherwise */ - BUG_ON(system_state != SYSTEM_BOOTING); - + spin_lock(&early_pfn_lock); nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache); - if (nid >= 0) - return nid; - /* just returns 0 */ - return 0; + if (nid < 0) + nid = 0; + spin_unlock(&early_pfn_lock); + + return nid; } #endif From d3cd131d935ab3bab700491edbbd7cad4040ce50 Mon Sep 17 00:00:00 2001 From: Nicolai Stange Date: Thu, 6 Aug 2015 15:46:16 -0700 Subject: [PATCH 404/428] mm, meminit: replace rwsem with completion Commit 0e1cc95b4cc7 ("mm: meminit: finish initialisation of struct pages before basic setup") introduced a rwsem to signal completion of the initialization workers. Lockdep complains about possible recursive locking: ============================================= [ INFO: possible recursive locking detected ] 4.1.0-12802-g1dc51b8 #3 Not tainted --------------------------------------------- swapper/0/1 is trying to acquire lock: (pgdat_init_rwsem){++++.+}, at: [] page_alloc_init_late+0xc7/0xe6 but task is already holding lock: (pgdat_init_rwsem){++++.+}, at: [] page_alloc_init_late+0x3e/0xe6 Replace the rwsem by a completion together with an atomic "outstanding work counter". [peterz@infradead.org: Barrier removal on the grounds of being pointless] [mgorman@suse.de: Applied review feedback] Signed-off-by: Nicolai Stange Signed-off-by: Mel Gorman Acked-by: Peter Zijlstra (Intel) Cc: Dave Hansen Cc: Alex Ng Cc: Fengguang Wu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 22 +++++++++++++++------- 1 file changed, 15 insertions(+), 7 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ea0e6a6e7a11..322628278ae4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include @@ -1060,7 +1059,15 @@ static void __init deferred_free_range(struct page *page, __free_pages_boot_core(page, pfn, 0); } -static __initdata DECLARE_RWSEM(pgdat_init_rwsem); +/* Completion tracking for deferred_init_memmap() threads */ +static atomic_t pgdat_init_n_undone __initdata; +static __initdata DECLARE_COMPLETION(pgdat_init_all_done_comp); + +static inline void __init pgdat_init_report_one_done(void) +{ + if (atomic_dec_and_test(&pgdat_init_n_undone)) + complete(&pgdat_init_all_done_comp); +} /* Initialise remaining memory on a node */ static int __init deferred_init_memmap(void *data) @@ -1077,7 +1084,7 @@ static int __init deferred_init_memmap(void *data) const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); if (first_init_pfn == ULONG_MAX) { - up_read(&pgdat_init_rwsem); + pgdat_init_report_one_done(); return 0; } @@ -1177,7 +1184,8 @@ free_range: pr_info("node %d initialised, %lu pages in %ums\n", nid, nr_pages, jiffies_to_msecs(jiffies - start)); - up_read(&pgdat_init_rwsem); + + pgdat_init_report_one_done(); return 0; } @@ -1185,14 +1193,14 @@ void __init page_alloc_init_late(void) { int nid; + /* There will be num_node_state(N_MEMORY) threads */ + atomic_set(&pgdat_init_n_undone, num_node_state(N_MEMORY)); for_each_node_state(nid, N_MEMORY) { - down_read(&pgdat_init_rwsem); kthread_run(deferred_init_memmap, NODE_DATA(nid), "pgdatinit%d", nid); } /* Block until all are initialised */ - down_write(&pgdat_init_rwsem); - up_write(&pgdat_init_rwsem); + wait_for_completion(&pgdat_init_all_done_comp); } #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ From 4248b0da460839e30eaaad78992b9a1dd3e63e21 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 6 Aug 2015 15:46:20 -0700 Subject: [PATCH 405/428] fs, file table: reinit files_stat.max_files after deferred memory initialisation Dave Hansen reported the following; My laptop has been behaving strangely with 4.2-rc2. Once I log in to my X session, I start getting all kinds of strange errors from applications and see this in my dmesg: VFS: file-max limit 8192 reached The problem is that the file-max is calculated before memory is fully initialised and miscalculates how much memory the kernel is using. This patch recalculates file-max after deferred memory initialisation. Note that using memory hotplug infrastructure would not have avoided this problem as the value is not recalculated after memory hot-add. 4.1: files_stat.max_files = 6582781 4.2-rc2: files_stat.max_files = 8192 4.2-rc2 patched: files_stat.max_files = 6562467 Small differences with the patch applied and 4.1 but not enough to matter. Signed-off-by: Mel Gorman Reported-by: Dave Hansen Cc: Nicolai Stange Cc: Dave Hansen Cc: Alex Ng Cc: Fengguang Wu Cc: Peter Zijlstra (Intel) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/dcache.c | 13 +++---------- fs/file_table.c | 28 +++++++++++++++++----------- include/linux/fs.h | 5 +++-- init/main.c | 2 +- mm/page_alloc.c | 3 +++ 5 files changed, 27 insertions(+), 24 deletions(-) diff --git a/fs/dcache.c b/fs/dcache.c index 5c8ea15e73a5..9b5fe503f6cb 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -3442,22 +3442,15 @@ void __init vfs_caches_init_early(void) inode_init_early(); } -void __init vfs_caches_init(unsigned long mempages) +void __init vfs_caches_init(void) { - unsigned long reserve; - - /* Base hash sizes on available memory, with a reserve equal to - 150% of current kernel size */ - - reserve = min((mempages - nr_free_pages()) * 3/2, mempages - 1); - mempages -= reserve; - names_cachep = kmem_cache_create("names_cache", PATH_MAX, 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); dcache_init(); inode_init(); - files_init(mempages); + files_init(); + files_maxfiles_init(); mnt_init(); bdev_cache_init(); chrdev_init(); diff --git a/fs/file_table.c b/fs/file_table.c index 7f9d407c7595..ad17e05ebf95 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -25,6 +25,7 @@ #include #include #include +#include #include @@ -308,19 +309,24 @@ void put_filp(struct file *file) } } -void __init files_init(unsigned long mempages) +void __init files_init(void) { - unsigned long n; - filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); - - /* - * One file with associated inode and dcache is very roughly 1K. - * Per default don't use more than 10% of our memory for files. - */ - - n = (mempages * (PAGE_SIZE / 1024)) / 10; - files_stat.max_files = max_t(unsigned long, n, NR_FILE); percpu_counter_init(&nr_files, 0, GFP_KERNEL); +} + +/* + * One file with associated inode and dcache is very roughly 1K. Per default + * do not use more than 10% of our memory for files. + */ +void __init files_maxfiles_init(void) +{ + unsigned long n; + unsigned long memreserve = (totalram_pages - nr_free_pages()) * 3/2; + + memreserve = min(memreserve, totalram_pages - 1); + n = ((totalram_pages - memreserve) * (PAGE_SIZE / 1024)) / 10; + + files_stat.max_files = max_t(unsigned long, n, NR_FILE); } diff --git a/include/linux/fs.h b/include/linux/fs.h index cc008c338f5a..84b783f277f7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -55,7 +55,8 @@ struct vm_fault; extern void __init inode_init(void); extern void __init inode_init_early(void); -extern void __init files_init(unsigned long); +extern void __init files_init(void); +extern void __init files_maxfiles_init(void); extern struct files_stat_struct files_stat; extern unsigned long get_max_files(void); @@ -2245,7 +2246,7 @@ extern int ioctl_preallocate(struct file *filp, void __user *argp); /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); -extern void __init vfs_caches_init(unsigned long); +extern void __init vfs_caches_init(void); extern struct kmem_cache *names_cachep; diff --git a/init/main.c b/init/main.c index c5d5626289ce..56506553d4d8 100644 --- a/init/main.c +++ b/init/main.c @@ -656,7 +656,7 @@ asmlinkage __visible void __init start_kernel(void) key_init(); security_init(); dbg_late_init(); - vfs_caches_init(totalram_pages); + vfs_caches_init(); signals_init(); /* rootfs populating might need page-writeback */ page_writeback_init(); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 322628278ae4..cb61f44eb3fc 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1201,6 +1201,9 @@ void __init page_alloc_init_late(void) /* Block until all are initialised */ wait_for_completion(&pgdat_init_all_done_comp); + + /* Reinit limits that are based on free pages after the kernel is up */ + files_maxfiles_init(); } #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ From 209f7512d007980fd111a74a064d70a3656079cf Mon Sep 17 00:00:00 2001 From: Joseph Qi Date: Thu, 6 Aug 2015 15:46:23 -0700 Subject: [PATCH 406/428] ocfs2: fix BUG in ocfs2_downconvert_thread_do_work() The "BUG_ON(list_empty(&osb->blocked_lock_list))" in ocfs2_downconvert_thread_do_work can be triggered in the following case: ocfs2dc has firstly saved osb->blocked_lock_count to local varibale processed, and then processes the dentry lockres. During the dentry put, it calls iput and then deletes rw, inode and open lockres from blocked list in ocfs2_mark_lockres_freeing. And this causes the variable `processed' to not reflect the number of blocked lockres to be processed, which triggers the BUG. Signed-off-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/dlmglue.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 8b23aa2f52dd..23157e40dd74 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -4025,9 +4025,13 @@ static void ocfs2_downconvert_thread_do_work(struct ocfs2_super *osb) osb->dc_work_sequence = osb->dc_wake_sequence; processed = osb->blocked_lock_count; - while (processed) { - BUG_ON(list_empty(&osb->blocked_lock_list)); - + /* + * blocked lock processing in this loop might call iput which can + * remove items off osb->blocked_lock_list. Downconvert up to + * 'processed' number of locks, but stop short if we had some + * removed in ocfs2_mark_lockres_freeing when downconverting. + */ + while (processed && !list_empty(&osb->blocked_lock_list)) { lockres = list_entry(osb->blocked_lock_list.next, struct ocfs2_lock_res, l_blocked_list); list_del_init(&lockres->l_blocked_list); From 3c00cb5e68dc719f2fc73a33b1b230aadfcb1309 Mon Sep 17 00:00:00 2001 From: Amanieu d'Antras Date: Thu, 6 Aug 2015 15:46:26 -0700 Subject: [PATCH 407/428] signal: fix information leak in copy_siginfo_from_user32 This function can leak kernel stack data when the user siginfo_t has a positive si_code value. The top 16 bits of si_code descibe which fields in the siginfo_t union are active, but they are treated inconsistently between copy_siginfo_from_user32, copy_siginfo_to_user32 and copy_siginfo_to_user. copy_siginfo_from_user32 is called from rt_sigqueueinfo and rt_tgsigqueueinfo in which the user has full control overthe top 16 bits of si_code. This fixes the following information leaks: x86: 8 bytes leaked when sending a signal from a 32-bit process to itself. This leak grows to 16 bytes if the process uses x32. (si_code = __SI_CHLD) x86: 100 bytes leaked when sending a signal from a 32-bit process to a 64-bit process. (si_code = -1) sparc: 4 bytes leaked when sending a signal from a 32-bit process to a 64-bit process. (si_code = any) parsic and s390 have similar bugs, but they are not vulnerable because rt_[tg]sigqueueinfo have checks that prevent sending a positive si_code to a different process. These bugs are also fixed for consistency. Signed-off-by: Amanieu d'Antras Cc: Oleg Nesterov Cc: Ingo Molnar Cc: Russell King Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: Chris Metcalf Cc: Paul Mackerras Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/kernel/signal32.c | 2 -- arch/mips/kernel/signal32.c | 2 -- arch/powerpc/kernel/signal_32.c | 2 -- arch/tile/kernel/compat_signal.c | 2 -- kernel/signal.c | 4 ++-- 5 files changed, 2 insertions(+), 10 deletions(-) diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index 1670f15ef69e..81fd38f4fbaa 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -201,8 +201,6 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) { - memset(to, 0, sizeof *to); - if (copy_from_user(to, from, __ARCH_SI_PREAMBLE_SIZE) || copy_from_user(to->_sifields._pad, from->_sifields._pad, SI_PAD_SIZE)) diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c index 19a7705f2a01..5d7f2634996f 100644 --- a/arch/mips/kernel/signal32.c +++ b/arch/mips/kernel/signal32.c @@ -409,8 +409,6 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) { - memset(to, 0, sizeof *to); - if (copy_from_user(to, from, 3*sizeof(int)) || copy_from_user(to->_sifields._pad, from->_sifields._pad, SI_PAD_SIZE32)) diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index d3a831ac0f92..da50e0c9c57e 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -966,8 +966,6 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *d, const siginfo_t *s) int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from) { - memset(to, 0, sizeof *to); - if (copy_from_user(to, from, 3*sizeof(int)) || copy_from_user(to->_sifields._pad, from->_sifields._pad, SI_PAD_SIZE32)) diff --git a/arch/tile/kernel/compat_signal.c b/arch/tile/kernel/compat_signal.c index e8c2c04143cd..c667e104a0c2 100644 --- a/arch/tile/kernel/compat_signal.c +++ b/arch/tile/kernel/compat_signal.c @@ -113,8 +113,6 @@ int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from) if (!access_ok(VERIFY_READ, from, sizeof(struct compat_siginfo))) return -EFAULT; - memset(to, 0, sizeof(*to)); - err = __get_user(to->si_signo, &from->si_signo); err |= __get_user(to->si_errno, &from->si_errno); err |= __get_user(to->si_code, &from->si_code); diff --git a/kernel/signal.c b/kernel/signal.c index 836df8dac6cc..00524cf6c412 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3017,7 +3017,7 @@ COMPAT_SYSCALL_DEFINE3(rt_sigqueueinfo, int, sig, struct compat_siginfo __user *, uinfo) { - siginfo_t info; + siginfo_t info = {}; int ret = copy_siginfo_from_user32(&info, uinfo); if (unlikely(ret)) return ret; @@ -3061,7 +3061,7 @@ COMPAT_SYSCALL_DEFINE4(rt_tgsigqueueinfo, int, sig, struct compat_siginfo __user *, uinfo) { - siginfo_t info; + siginfo_t info = {}; if (copy_siginfo_from_user32(&info, uinfo)) return -EFAULT; From 26135022f85105ad725cda103fa069e29e83bd16 Mon Sep 17 00:00:00 2001 From: Amanieu d'Antras Date: Thu, 6 Aug 2015 15:46:29 -0700 Subject: [PATCH 408/428] signal: fix information leak in copy_siginfo_to_user This function may copy the si_addr_lsb, si_lower and si_upper fields to user mode when they haven't been initialized, which can leak kernel stack data to user mode. Just checking the value of si_code is insufficient because the same si_code value is shared between multiple signals. This is solved by checking the value of si_signo in addition to si_code. Signed-off-by: Amanieu d'Antras Cc: Oleg Nesterov Cc: Ingo Molnar Cc: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/kernel/signal32.c | 3 ++- kernel/signal.c | 9 ++++++--- 2 files changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index 81fd38f4fbaa..948f0ad2de23 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -168,7 +168,8 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) * Other callers might not initialize the si_lsb field, * so check explicitely for the right codes here. */ - if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO) + if (from->si_signo == SIGBUS && + (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)) err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb); #endif break; diff --git a/kernel/signal.c b/kernel/signal.c index 00524cf6c412..0f6bbbe77b46 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2748,12 +2748,15 @@ int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from) * Other callers might not initialize the si_lsb field, * so check explicitly for the right codes here. */ - if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO) + if (from->si_signo == SIGBUS && + (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)) err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb); #endif #ifdef SEGV_BNDERR - err |= __put_user(from->si_lower, &to->si_lower); - err |= __put_user(from->si_upper, &to->si_upper); + if (from->si_signo == SIGSEGV && from->si_code == SEGV_BNDERR) { + err |= __put_user(from->si_lower, &to->si_lower); + err |= __put_user(from->si_upper, &to->si_upper); + } #endif break; case __SI_CHLD: From 3ead7c52bdb0ab44f4bb1feed505a8323cc12ba7 Mon Sep 17 00:00:00 2001 From: Amanieu d'Antras Date: Thu, 6 Aug 2015 15:46:33 -0700 Subject: [PATCH 409/428] signalfd: fix information leak in signalfd_copyinfo This function may copy the si_addr_lsb field to user mode when it hasn't been initialized, which can leak kernel stack data to user mode. Just checking the value of si_code is insufficient because the same si_code value is shared between multiple signals. This is solved by checking the value of si_signo in addition to si_code. Signed-off-by: Amanieu d'Antras Cc: Oleg Nesterov Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/signalfd.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/signalfd.c b/fs/signalfd.c index 7e412ad74836..270221fcef42 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -121,8 +121,9 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, * Other callers might not initialize the si_lsb field, * so check explicitly for the right codes here. */ - if (kinfo->si_code == BUS_MCEERR_AR || - kinfo->si_code == BUS_MCEERR_AO) + if (kinfo->si_signo == SIGBUS && + (kinfo->si_code == BUS_MCEERR_AR || + kinfo->si_code == BUS_MCEERR_AO)) err |= __put_user((short) kinfo->si_addr_lsb, &uinfo->ssi_addr_lsb); #endif From 3e810ae2db76ccde770fd8e5a0de6408ea36e211 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Thu, 6 Aug 2015 15:46:36 -0700 Subject: [PATCH 410/428] mm/slub: allow merging when SLAB_DEBUG_FREE is set This patch fixes creation of new kmem-caches after enabling sanity_checks for existing mergeable kmem-caches in runtime: before that patch creation fails because unique name in sysfs already taken by existing kmem-cache. Unlike other debug options this doesn't change object layout and could be enabled and disabled at any time. Signed-off-by: Konstantin Khlebnikov Acked-by: Christoph Lameter Cc: Pekka Enberg Acked-by: David Rientjes Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slab_common.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/mm/slab_common.c b/mm/slab_common.c index 3e5f8f29c286..86831105a09f 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -37,8 +37,7 @@ struct kmem_cache *kmem_cache; SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE | \ SLAB_FAILSLAB) -#define SLAB_MERGE_SAME (SLAB_DEBUG_FREE | SLAB_RECLAIM_ACCOUNT | \ - SLAB_CACHE_DMA | SLAB_NOTRACK) +#define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | SLAB_NOTRACK) /* * Merge control. If this is set then no merging of slab caches will occur. From 447f6a95a9c80da7faaec3e66e656eab8f262640 Mon Sep 17 00:00:00 2001 From: Sowmini Varadhan Date: Thu, 6 Aug 2015 15:46:39 -0700 Subject: [PATCH 411/428] lib/iommu-common.c: do not use 0xffffffffffffffffl for computing align_mask Using a 64 bit constant generates "warning: integer constant is too large for 'long' type" on 32 bit platforms. Instead use ~0ul and BITS_PER_LONG. Detected by Andrew Morton on ARMD. Signed-off-by: Sowmini Varadhan Cc: Benjamin Herrenschmidt Cc: David S. Miller Cc: Guenter Roeck Cc: Rasmus Villemoes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/iommu-common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/iommu-common.c b/lib/iommu-common.c index df30632f0bef..ff19f66d3f7f 100644 --- a/lib/iommu-common.c +++ b/lib/iommu-common.c @@ -119,7 +119,7 @@ unsigned long iommu_tbl_range_alloc(struct device *dev, unsigned long align_mask = 0; if (align_order > 0) - align_mask = 0xffffffffffffffffl >> (64 - align_order); + align_mask = ~0ul >> (BITS_PER_LONG - align_order); /* Sanity check */ if (unlikely(npages == 0)) { From 8f2f3eb59dff4ec538de55f2e0592fec85966aab Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 6 Aug 2015 15:46:42 -0700 Subject: [PATCH 412/428] fsnotify: fix oops in fsnotify_clear_marks_by_group_flags() fsnotify_clear_marks_by_group_flags() can race with fsnotify_destroy_marks() so that when fsnotify_destroy_mark_locked() drops mark_mutex, a mark from the list iterated by fsnotify_clear_marks_by_group_flags() can be freed and thus the next entry pointer we have cached may become stale and we dereference free memory. Fix the problem by first moving marks to free to a special private list and then always free the first entry in the special list. This method is safe even when entries from the list can disappear once we drop the lock. Signed-off-by: Jan Kara Reported-by: Ashish Sangwan Reviewed-by: Ashish Sangwan Cc: Lino Sanfilippo Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/notify/mark.c | 30 +++++++++++++++++++++++++----- 1 file changed, 25 insertions(+), 5 deletions(-) diff --git a/fs/notify/mark.c b/fs/notify/mark.c index 92e48c70f0f0..39ddcaf0918f 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -412,16 +412,36 @@ void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group, unsigned int flags) { struct fsnotify_mark *lmark, *mark; + LIST_HEAD(to_free); + /* + * We have to be really careful here. Anytime we drop mark_mutex, e.g. + * fsnotify_clear_marks_by_inode() can come and free marks. Even in our + * to_free list so we have to use mark_mutex even when accessing that + * list. And freeing mark requires us to drop mark_mutex. So we can + * reliably free only the first mark in the list. That's why we first + * move marks to free to to_free list in one go and then free marks in + * to_free list one by one. + */ mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING); list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) { - if (mark->flags & flags) { - fsnotify_get_mark(mark); - fsnotify_destroy_mark_locked(mark, group); - fsnotify_put_mark(mark); - } + if (mark->flags & flags) + list_move(&mark->g_list, &to_free); } mutex_unlock(&group->mark_mutex); + + while (1) { + mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING); + if (list_empty(&to_free)) { + mutex_unlock(&group->mark_mutex); + break; + } + mark = list_first_entry(&to_free, struct fsnotify_mark, g_list); + fsnotify_get_mark(mark); + fsnotify_destroy_mark_locked(mark, group); + mutex_unlock(&group->mark_mutex); + fsnotify_put_mark(mark); + } } /* From 18896451eaeee497ef5c397d76902c6376a8787d Mon Sep 17 00:00:00 2001 From: David Kershner Date: Thu, 6 Aug 2015 15:46:45 -0700 Subject: [PATCH 413/428] kthread: export kthread functions The s-Par visornic driver, currently in staging, processes a queue being serviced by the an s-Par service partition. We can get a message that something has happened with the Service Partition, when that happens, we must not access the channel until we get a message that the service partition is back again. The visornic driver has a thread for processing the channel, when we get the message, we need to be able to park the thread and then resume it when the problem clears. We can do this with kthread_park and unpark but they are not exported from the kernel, this patch exports the needed functions. Signed-off-by: David Kershner Acked-by: Ingo Molnar Acked-by: Neil Horman Acked-by: Thomas Gleixner Cc: Richard Weinberger Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/kthread.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/kernel/kthread.c b/kernel/kthread.c index 10e489c448fe..fdea0bee7b5a 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -97,6 +97,7 @@ bool kthread_should_park(void) { return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(current)->flags); } +EXPORT_SYMBOL_GPL(kthread_should_park); /** * kthread_freezable_should_stop - should this freezable kthread return now? @@ -171,6 +172,7 @@ void kthread_parkme(void) { __kthread_parkme(to_kthread(current)); } +EXPORT_SYMBOL_GPL(kthread_parkme); static int kthread(void *_create) { @@ -411,6 +413,7 @@ void kthread_unpark(struct task_struct *k) if (kthread) __kthread_unpark(k, kthread); } +EXPORT_SYMBOL_GPL(kthread_unpark); /** * kthread_park - park a thread created by kthread_create(). @@ -441,6 +444,7 @@ int kthread_park(struct task_struct *k) } return ret; } +EXPORT_SYMBOL_GPL(kthread_park); /** * kthread_stop - stop a thread created by kthread_create(). From 32e5a2a2be6b085febaac36efff495ad65a55e6c Mon Sep 17 00:00:00 2001 From: Joseph Qi Date: Thu, 6 Aug 2015 15:46:48 -0700 Subject: [PATCH 414/428] ocfs2: fix shift left overflow When using a large volume, for example 9T volume with 2T already used, frequent creation of small files with O_DIRECT when the IO is not cluster aligned may clear sectors in the wrong place. This will cause filesystem corruption. This is because p_cpos is a u32. When calculating the corresponding sector it should be converted to u64 first, otherwise it may overflow. Signed-off-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: [4.0+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/aops.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 1a35c6139656..0f5fd9db8194 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -685,7 +685,7 @@ static int ocfs2_direct_IO_zero_extend(struct ocfs2_super *osb, if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) { u64 s = i_size_read(inode); - sector_t sector = (p_cpos << (osb->s_clustersize_bits - 9)) + + sector_t sector = ((u64)p_cpos << (osb->s_clustersize_bits - 9)) + (do_div(s, osb->s_clustersize) >> 9); ret = blkdev_issue_zeroout(osb->sb->s_bdev, sector, @@ -910,7 +910,7 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb, BUG_ON(!p_cpos || (ext_flags & OCFS2_EXT_UNWRITTEN)); ret = blkdev_issue_zeroout(osb->sb->s_bdev, - p_cpos << (osb->s_clustersize_bits - 9), + (u64)p_cpos << (osb->s_clustersize_bits - 9), zero_len_head >> 9, GFP_NOFS, false); if (ret < 0) mlog_errno(ret); From e298ff75f133f2524bb6a9a305b17c5f6ff1a6b2 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 6 Aug 2015 15:46:51 -0700 Subject: [PATCH 415/428] mm: initialize hotplugged pages as reserved Commit 92923ca3aace ("mm: meminit: only set page reserved in the memblock region") broke memory hotplug which expects the memmap for newly added sections to be reserved until onlined by online_pages_range(). This patch marks hotplugged pages as reserved when adding new zones. Signed-off-by: Mel Gorman Reported-by: David Vrabel Tested-by: David Vrabel Cc: Nathan Zimmer Cc: Robin Holt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 26fbba7d888f..003dbe4b060d 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -446,7 +446,7 @@ static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn) int nr_pages = PAGES_PER_SECTION; int nid = pgdat->node_id; int zone_type; - unsigned long flags; + unsigned long flags, pfn; int ret; zone_type = zone - pgdat->node_zones; @@ -461,6 +461,14 @@ static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn) pgdat_resize_unlock(zone->zone_pgdat, &flags); memmap_init_zone(nr_pages, nid, zone_type, phys_start_pfn, MEMMAP_HOTPLUG); + + /* online_page_range is called later and expects pages reserved */ + for (pfn = phys_start_pfn; pfn < phys_start_pfn + nr_pages; pfn++) { + if (!pfn_valid(pfn)) + continue; + + SetPageReserved(pfn_to_page(pfn)); + } return 0; } From e1832f2923ec92d0e590e496c8890675457f8568 Mon Sep 17 00:00:00 2001 From: Stephen Smalley Date: Thu, 6 Aug 2015 15:46:55 -0700 Subject: [PATCH 416/428] ipc: use private shmem or hugetlbfs inodes for shm segments. The shm implementation internally uses shmem or hugetlbfs inodes for shm segments. As these inodes are never directly exposed to userspace and only accessed through the shm operations which are already hooked by security modules, mark the inodes with the S_PRIVATE flag so that inode security initialization and permission checking is skipped. This was motivated by the following lockdep warning: ====================================================== [ INFO: possible circular locking dependency detected ] 4.2.0-0.rc3.git0.1.fc24.x86_64+debug #1 Tainted: G W ------------------------------------------------------- httpd/1597 is trying to acquire lock: (&ids->rwsem){+++++.}, at: shm_close+0x34/0x130 but task is already holding lock: (&mm->mmap_sem){++++++}, at: SyS_shmdt+0x4b/0x180 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #3 (&mm->mmap_sem){++++++}: lock_acquire+0xc7/0x270 __might_fault+0x7a/0xa0 filldir+0x9e/0x130 xfs_dir2_block_getdents.isra.12+0x198/0x1c0 [xfs] xfs_readdir+0x1b4/0x330 [xfs] xfs_file_readdir+0x2b/0x30 [xfs] iterate_dir+0x97/0x130 SyS_getdents+0x91/0x120 entry_SYSCALL_64_fastpath+0x12/0x76 -> #2 (&xfs_dir_ilock_class){++++.+}: lock_acquire+0xc7/0x270 down_read_nested+0x57/0xa0 xfs_ilock+0x167/0x350 [xfs] xfs_ilock_attr_map_shared+0x38/0x50 [xfs] xfs_attr_get+0xbd/0x190 [xfs] xfs_xattr_get+0x3d/0x70 [xfs] generic_getxattr+0x4f/0x70 inode_doinit_with_dentry+0x162/0x670 sb_finish_set_opts+0xd9/0x230 selinux_set_mnt_opts+0x35c/0x660 superblock_doinit+0x77/0xf0 delayed_superblock_init+0x10/0x20 iterate_supers+0xb3/0x110 selinux_complete_init+0x2f/0x40 security_load_policy+0x103/0x600 sel_write_load+0xc1/0x750 __vfs_write+0x37/0x100 vfs_write+0xa9/0x1a0 SyS_write+0x58/0xd0 entry_SYSCALL_64_fastpath+0x12/0x76 ... Signed-off-by: Stephen Smalley Reported-by: Morten Stevens Acked-by: Hugh Dickins Acked-by: Paul Moore Cc: Manfred Spraul Cc: Davidlohr Bueso Cc: Prarit Bhargava Cc: Eric Paris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 2 ++ ipc/shm.c | 2 +- mm/shmem.c | 4 ++-- 3 files changed, 5 insertions(+), 3 deletions(-) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 0cf74df68617..973c24ce59ad 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -1010,6 +1010,8 @@ struct file *hugetlb_file_setup(const char *name, size_t size, inode = hugetlbfs_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0); if (!inode) goto out_dentry; + if (creat_flags == HUGETLB_SHMFS_INODE) + inode->i_flags |= S_PRIVATE; file = ERR_PTR(-ENOMEM); if (hugetlb_reserve_pages(inode, 0, diff --git a/ipc/shm.c b/ipc/shm.c index 06e5cf2fe019..4aef24d91b63 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -545,7 +545,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) if ((shmflg & SHM_NORESERVE) && sysctl_overcommit_memory != OVERCOMMIT_NEVER) acctflag = VM_NORESERVE; - file = shmem_file_setup(name, size, acctflag); + file = shmem_kernel_file_setup(name, size, acctflag); } error = PTR_ERR(file); if (IS_ERR(file)) diff --git a/mm/shmem.c b/mm/shmem.c index 4caf8ed24d65..dbe0c1e8349c 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3363,8 +3363,8 @@ put_path: * shmem_kernel_file_setup - get an unlinked file living in tmpfs which must be * kernel internal. There will be NO LSM permission checks against the * underlying inode. So users of this interface must do LSM checks at a - * higher layer. The one user is the big_key implementation. LSM checks - * are provided at the key level rather than the inode level. + * higher layer. The users are the big_key and shm implementations. LSM + * checks are provided at the key or shm level rather than the inode. * @name: name for dentry (to be seen in /proc//maps * @size: size to be set for the file * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size From a09233f3e1b77dbf50851660533e008056553a2a Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Thu, 6 Aug 2015 15:46:58 -0700 Subject: [PATCH 417/428] mm/memory-failure: unlock_page before put_page Recently I addressed a few of hwpoison race problems and the patches are merged on v4.2-rc1. It made progress, but unfortunately some problems still remain due to less coverage of my testing. So I'm trying to fix or avoid them in this series. One point I'm expecting to discuss is that patch 4/5 changes the page flag set to be checked on free time. In current behavior, __PG_HWPOISON is not supposed to be set when the page is freed. I think that there is no strong reason for this behavior, and it causes a problem hard to fix only in error handler side (because __PG_HWPOISON could be set at arbitrary timing.) So I suggest to change it. With this patchset, hwpoison stress testing in official mce-test testsuite (which previously failed) passes. This patch (of 5): In "just unpoisoned" path, we do put_page and then unlock_page, which is a wrong order and causes "freeing locked page" bug. So let's fix it. Signed-off-by: Naoya Horiguchi Cc: Andi Kleen Cc: Dean Nelson Cc: Tony Luck Cc: "Kirill A. Shutemov" Cc: Hugh Dickins Acked-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index c53543d89282..04d677048af7 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1209,9 +1209,9 @@ int memory_failure(unsigned long pfn, int trapno, int flags) if (!PageHWPoison(p)) { printk(KERN_ERR "MCE %#lx: just unpoisoned\n", pfn); atomic_long_sub(nr_pages, &num_poisoned_pages); + unlock_page(hpage); put_page(hpage); - res = 0; - goto out; + return 0; } if (hwpoison_filter(p)) { if (TestClearPageHWPoison(p)) From a209ef09af0dc921311d0cc4a1d4f926321d91b8 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Thu, 6 Aug 2015 15:47:01 -0700 Subject: [PATCH 418/428] mm/memory-failure: fix race in counting num_poisoned_pages When memory_failure() is called on a page which are just freed after page migration from soft offlining, the counter num_poisoned_pages is raised twi= ce. So let's fix it with using TestSetPageHWPoison. Signed-off-by: Naoya Horiguchi Cc: Andi Kleen Cc: Dean Nelson Cc: Tony Luck Cc: "Kirill A. Shutemov" Cc: Hugh Dickins Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 04d677048af7..f72d2fad0b90 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1671,8 +1671,8 @@ static int __soft_offline_page(struct page *page, int flags) if (ret > 0) ret = -EIO; } else { - SetPageHWPoison(page); - atomic_long_inc(&num_poisoned_pages); + if (!TestSetPageHWPoison(page)) + atomic_long_inc(&num_poisoned_pages); } } else { pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n", From 98ed2b0052e68420f1bad6c81e3f2600d25023e7 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Thu, 6 Aug 2015 15:47:04 -0700 Subject: [PATCH 419/428] mm/memory-failure: give up error handling for non-tail-refcounted thp "non anonymous thp" case is still racy with freeing thp, which causes panic due to put_page() for refcount-0 page. It seems that closing up this race might be hard (and/or not worth doing,) so let's give up the error handling for this case. Signed-off-by: Naoya Horiguchi Cc: Andi Kleen Cc: Dean Nelson Cc: Tony Luck Cc: "Kirill A. Shutemov" Cc: Hugh Dickins Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index f72d2fad0b90..cd985530f102 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -909,6 +909,18 @@ int get_hwpoison_page(struct page *page) * directly for tail pages. */ if (PageTransHuge(head)) { + /* + * Non anonymous thp exists only in allocation/free time. We + * can't handle such a case correctly, so let's give it up. + * This should be better than triggering BUG_ON when kernel + * tries to touch the "partially handled" page. + */ + if (!PageAnon(head)) { + pr_err("MCE: %#lx: non anonymous thp\n", + page_to_pfn(page)); + return 0; + } + if (get_page_unless_zero(head)) { if (PageTail(page)) get_page(page); @@ -1134,15 +1146,6 @@ int memory_failure(unsigned long pfn, int trapno, int flags) } if (!PageHuge(p) && PageTransHuge(hpage)) { - if (!PageAnon(hpage)) { - pr_err("MCE: %#lx: non anonymous thp\n", pfn); - if (TestClearPageHWPoison(p)) - atomic_long_sub(nr_pages, &num_poisoned_pages); - put_page(p); - if (p != hpage) - put_page(hpage); - return -EBUSY; - } if (unlikely(split_huge_page(hpage))) { pr_err("MCE: %#lx: thp split failed\n", pfn); if (TestClearPageHWPoison(p)) From f4c18e6f7b5bbb5b528b3334115806b0d76f50f9 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Thu, 6 Aug 2015 15:47:08 -0700 Subject: [PATCH 420/428] mm: check __PG_HWPOISON separately from PAGE_FLAGS_CHECK_AT_* The race condition addressed in commit add05cecef80 ("mm: soft-offline: don't free target page in successful page migration") was not closed completely, because that can happen not only for soft-offline, but also for hard-offline. Consider that a slab page is about to be freed into buddy pool, and then an uncorrected memory error hits the page just after entering __free_one_page(), then VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP) is triggered, despite the fact that it's not necessary because the data on the affected page is not consumed. To solve it, this patch drops __PG_HWPOISON from page flag checks at allocation/free time. I think it's justified because __PG_HWPOISON flags is defined to prevent the page from being reused, and setting it outside the page's alloc-free cycle is a designed behavior (not a bug.) For recent months, I was annoyed about BUG_ON when soft-offlined page remains on lru cache list for a while, which is avoided by calling put_page() instead of putback_lru_page() in page migration's success path. This means that this patch reverts a major change from commit add05cecef80 about the new refcounting rule of soft-offlined pages, so "reuse window" revives. This will be closed by a subsequent patch. Signed-off-by: Naoya Horiguchi Cc: Andi Kleen Cc: Dean Nelson Cc: Tony Luck Cc: "Kirill A. Shutemov" Cc: Hugh Dickins Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 10 +++++++--- mm/huge_memory.c | 7 +------ mm/migrate.c | 5 ++++- mm/page_alloc.c | 4 ++++ 4 files changed, 16 insertions(+), 10 deletions(-) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index f34e040b34e9..41c93844fb1d 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -631,15 +631,19 @@ static inline void ClearPageSlabPfmemalloc(struct page *page) 1 << PG_private | 1 << PG_private_2 | \ 1 << PG_writeback | 1 << PG_reserved | \ 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \ - 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON | \ + 1 << PG_unevictable | __PG_MLOCKED | \ __PG_COMPOUND_LOCK) /* * Flags checked when a page is prepped for return by the page allocator. - * Pages being prepped should not have any flags set. It they are set, + * Pages being prepped should not have these flags set. It they are set, * there has been a kernel bug or struct page corruption. + * + * __PG_HWPOISON is exceptional because it needs to be kept beyond page's + * alloc-free cycle to prevent from reusing the page. */ -#define PAGE_FLAGS_CHECK_AT_PREP ((1 << NR_PAGEFLAGS) - 1) +#define PAGE_FLAGS_CHECK_AT_PREP \ + (((1 << NR_PAGEFLAGS) - 1) & ~__PG_HWPOISON) #define PAGE_FLAGS_PRIVATE \ (1 << PG_private | 1 << PG_private_2) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index c107094f79ba..097c7a4bfbd9 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1676,12 +1676,7 @@ static void __split_huge_page_refcount(struct page *page, /* after clearing PageTail the gup refcount can be released */ smp_mb__after_atomic(); - /* - * retain hwpoison flag of the poisoned tail page: - * fix for the unsuitable process killed on Guest Machine(KVM) - * by the memory-failure. - */ - page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP | __PG_HWPOISON; + page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; page_tail->flags |= (page->flags & ((1L << PG_referenced) | (1L << PG_swapbacked) | diff --git a/mm/migrate.c b/mm/migrate.c index ee401e4e5ef1..f2415be7d93b 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -950,7 +950,10 @@ out: list_del(&page->lru); dec_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); - if (reason != MR_MEMORY_FAILURE) + /* Soft-offlined page shouldn't go through lru cache list */ + if (reason == MR_MEMORY_FAILURE) + put_page(page); + else putback_lru_page(page); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index cb61f44eb3fc..beda41710802 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1296,6 +1296,10 @@ static inline int check_new_page(struct page *page) bad_reason = "non-NULL mapping"; if (unlikely(atomic_read(&page->_count) != 0)) bad_reason = "nonzero _count"; + if (unlikely(page->flags & __PG_HWPOISON)) { + bad_reason = "HWPoisoned (hardware-corrupted)"; + bad_flags = __PG_HWPOISON; + } if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_PREP)) { bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set"; bad_flags = PAGE_FLAGS_CHECK_AT_PREP; From 4491f7126063ef51081f5662bd4fcae31621a333 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Thu, 6 Aug 2015 15:47:11 -0700 Subject: [PATCH 421/428] mm/memory-failure: set PageHWPoison before migrate_pages() Now page freeing code doesn't consider PageHWPoison as a bad page, so by setting it before completing the page containment, we can prevent the error page from being reused just after successful page migration. I added TTU_IGNORE_HWPOISON for try_to_unmap() to make sure that the page table entry is transformed into migration entry, not to hwpoison entry. Signed-off-by: Naoya Horiguchi Cc: Andi Kleen Cc: Dean Nelson Cc: Tony Luck Cc: "Kirill A. Shutemov" Cc: Hugh Dickins Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 7 ++++--- mm/migrate.c | 3 ++- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index cd985530f102..ea5a93659488 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1659,6 +1659,8 @@ static int __soft_offline_page(struct page *page, int flags) inc_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); list_add(&page->lru, &pagelist); + if (!TestSetPageHWPoison(page)) + atomic_long_inc(&num_poisoned_pages); ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { @@ -1673,9 +1675,8 @@ static int __soft_offline_page(struct page *page, int flags) pfn, ret, page->flags); if (ret > 0) ret = -EIO; - } else { - if (!TestSetPageHWPoison(page)) - atomic_long_inc(&num_poisoned_pages); + if (TestClearPageHWPoison(page)) + atomic_long_dec(&num_poisoned_pages); } } else { pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n", diff --git a/mm/migrate.c b/mm/migrate.c index f2415be7d93b..eb4267107d1f 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -880,7 +880,8 @@ static int __unmap_and_move(struct page *page, struct page *newpage, /* Establish migration ptes or remove ptes */ if (page_mapped(page)) { try_to_unmap(page, - TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS); + TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS| + TTU_IGNORE_HWPOISON); page_was_mapped = 1; } From a50fcb512d9539b5179b1e523641420339086995 Mon Sep 17 00:00:00 2001 From: Rabin Vincent Date: Thu, 6 Aug 2015 15:47:14 -0700 Subject: [PATCH 422/428] writeback: fix initial dirty limit The initial value of global_wb_domain.dirty_limit set by writeback_set_ratelimit() is zeroed out by the memset in wb_domain_init(). Signed-off-by: Rabin Vincent Acked-by: Tejun Heo Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page-writeback.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 22cddd3e5de8..5cccc127ef81 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2063,10 +2063,10 @@ static struct notifier_block ratelimit_nb = { */ void __init page_writeback_init(void) { + BUG_ON(wb_domain_init(&global_wb_domain, GFP_KERNEL)); + writeback_set_ratelimit(); register_cpu_notifier(&ratelimit_nb); - - BUG_ON(wb_domain_init(&global_wb_domain, GFP_KERNEL)); } /** From 44922150d87cef616fd183220d43d8fde4d41390 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 6 Aug 2015 19:13:25 -0700 Subject: [PATCH 423/428] sparc64: Fix userspace FPU register corruptions. If we have a series of events from userpsace, with %fprs=FPRS_FEF, like follows: ETRAP ETRAP VIS_ENTRY(fprs=0x4) VIS_EXIT RTRAP (kernel FPU restore with fpu_saved=0x4) RTRAP We will not restore the user registers that were clobbered by the FPU using kernel code in the inner-most trap. Traps allocate FPU save slots in the thread struct, and FPU using sequences save the "dirty" FPU registers only. This works at the initial trap level because all of the registers get recorded into the top-level FPU save area, and we'll return to userspace with the FPU disabled so that any FPU use by the user will take an FPU disabled trap wherein we'll load the registers back up properly. But this is not how trap returns from kernel to kernel operate. The simplest fix for this bug is to always save all FPU register state for anything other than the top-most FPU save area. Getting rid of the optimized inner-slot FPU saving code ends up making VISEntryHalf degenerate into plain VISEntry. Longer term we need to do something smarter to reinstate the partial save optimizations. Perhaps the fundament error is having trap entry and exit allocate FPU save slots and restore register state. Instead, the VISEntry et al. calls should be doing that work. This bug is about two decades old. Reported-by: James Y Knight Signed-off-by: David S. Miller --- arch/sparc/include/asm/visasm.h | 16 +++----- arch/sparc/lib/NG4memcpy.S | 5 ++- arch/sparc/lib/VISsave.S | 67 +-------------------------------- arch/sparc/lib/ksyms.c | 4 -- 4 files changed, 11 insertions(+), 81 deletions(-) diff --git a/arch/sparc/include/asm/visasm.h b/arch/sparc/include/asm/visasm.h index 1f0aa2024e94..6424249d5f78 100644 --- a/arch/sparc/include/asm/visasm.h +++ b/arch/sparc/include/asm/visasm.h @@ -28,16 +28,10 @@ * Must preserve %o5 between VISEntryHalf and VISExitHalf */ #define VISEntryHalf \ - rd %fprs, %o5; \ - andcc %o5, FPRS_FEF, %g0; \ - be,pt %icc, 297f; \ - sethi %hi(298f), %g7; \ - sethi %hi(VISenterhalf), %g1; \ - jmpl %g1 + %lo(VISenterhalf), %g0; \ - or %g7, %lo(298f), %g7; \ - clr %o5; \ -297: wr %o5, FPRS_FEF, %fprs; \ -298: + VISEntry + +#define VISExitHalf \ + VISExit #define VISEntryHalfFast(fail_label) \ rd %fprs, %o5; \ @@ -47,7 +41,7 @@ ba,a,pt %xcc, fail_label; \ 297: wr %o5, FPRS_FEF, %fprs; -#define VISExitHalf \ +#define VISExitHalfFast \ wr %o5, 0, %fprs; #ifndef __ASSEMBLY__ diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S index 140527a20e7d..83aeeb1dffdb 100644 --- a/arch/sparc/lib/NG4memcpy.S +++ b/arch/sparc/lib/NG4memcpy.S @@ -240,8 +240,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ add %o0, 0x40, %o0 bne,pt %icc, 1b LOAD(prefetch, %g1 + 0x200, #n_reads_strong) +#ifdef NON_USER_COPY + VISExitHalfFast +#else VISExitHalf - +#endif brz,pn %o2, .Lexit cmp %o2, 19 ble,pn %icc, .Lsmall_unaligned diff --git a/arch/sparc/lib/VISsave.S b/arch/sparc/lib/VISsave.S index b320ae9e2e2e..a063d84336d6 100644 --- a/arch/sparc/lib/VISsave.S +++ b/arch/sparc/lib/VISsave.S @@ -44,9 +44,8 @@ vis1: ldub [%g6 + TI_FPSAVED], %g3 stx %g3, [%g6 + TI_GSR] 2: add %g6, %g1, %g3 - cmp %o5, FPRS_DU - be,pn %icc, 6f - sll %g1, 3, %g1 + mov FPRS_DU | FPRS_DL | FPRS_FEF, %o5 + sll %g1, 3, %g1 stb %o5, [%g3 + TI_FPSAVED] rd %gsr, %g2 add %g6, %g1, %g3 @@ -80,65 +79,3 @@ vis1: ldub [%g6 + TI_FPSAVED], %g3 .align 32 80: jmpl %g7 + %g0, %g0 nop - -6: ldub [%g3 + TI_FPSAVED], %o5 - or %o5, FPRS_DU, %o5 - add %g6, TI_FPREGS+0x80, %g2 - stb %o5, [%g3 + TI_FPSAVED] - - sll %g1, 5, %g1 - add %g6, TI_FPREGS+0xc0, %g3 - wr %g0, FPRS_FEF, %fprs - membar #Sync - stda %f32, [%g2 + %g1] ASI_BLK_P - stda %f48, [%g3 + %g1] ASI_BLK_P - membar #Sync - ba,pt %xcc, 80f - nop - - .align 32 -80: jmpl %g7 + %g0, %g0 - nop - - .align 32 -VISenterhalf: - ldub [%g6 + TI_FPDEPTH], %g1 - brnz,a,pn %g1, 1f - cmp %g1, 1 - stb %g0, [%g6 + TI_FPSAVED] - stx %fsr, [%g6 + TI_XFSR] - clr %o5 - jmpl %g7 + %g0, %g0 - wr %g0, FPRS_FEF, %fprs - -1: bne,pn %icc, 2f - srl %g1, 1, %g1 - ba,pt %xcc, vis1 - sub %g7, 8, %g7 -2: addcc %g6, %g1, %g3 - sll %g1, 3, %g1 - andn %o5, FPRS_DU, %g2 - stb %g2, [%g3 + TI_FPSAVED] - - rd %gsr, %g2 - add %g6, %g1, %g3 - stx %g2, [%g3 + TI_GSR] - add %g6, %g1, %g2 - stx %fsr, [%g2 + TI_XFSR] - sll %g1, 5, %g1 -3: andcc %o5, FPRS_DL, %g0 - be,pn %icc, 4f - add %g6, TI_FPREGS, %g2 - - add %g6, TI_FPREGS+0x40, %g3 - membar #Sync - stda %f0, [%g2 + %g1] ASI_BLK_P - stda %f16, [%g3 + %g1] ASI_BLK_P - membar #Sync - ba,pt %xcc, 4f - nop - - .align 32 -4: and %o5, FPRS_DU, %o5 - jmpl %g7 + %g0, %g0 - wr %o5, FPRS_FEF, %fprs diff --git a/arch/sparc/lib/ksyms.c b/arch/sparc/lib/ksyms.c index 1d649a95660c..8069ce12f20b 100644 --- a/arch/sparc/lib/ksyms.c +++ b/arch/sparc/lib/ksyms.c @@ -135,10 +135,6 @@ EXPORT_SYMBOL(copy_user_page); void VISenter(void); EXPORT_SYMBOL(VISenter); -/* CRYPTO code needs this */ -void VISenterhalf(void); -EXPORT_SYMBOL(VISenterhalf); - extern void xor_vis_2(unsigned long, unsigned long *, unsigned long *); extern void xor_vis_3(unsigned long, unsigned long *, unsigned long *, unsigned long *); From 10971638701dedadb58c88ce4d31c9375b224ed6 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Fri, 7 Aug 2015 13:01:39 +0530 Subject: [PATCH 424/428] ARCv2: spinlock/rwlock/atomics: reduce 1 instruction in exponential backoff The increment of delay counter was 2 instructions: Arithmatic Shfit Left (ASL) + set to 1 on overflow This can be done in 1 using ROtate Left (ROL) Suggested-by: Nigel Topham Cc: Peter Zijlstra (Intel) Cc: linux-kernel@vger.kernel.org Signed-off-by: Vineet Gupta --- arch/arc/include/asm/atomic.h | 3 +-- arch/arc/include/asm/spinlock.h | 3 +-- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index 629dfd0a0c6b..87d18ae53115 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -34,8 +34,7 @@ " mov %[tmp], %[delay] \n" /* tmp = delay */ \ "2: brne.d %[tmp], 0, 2b \n" /* while (tmp != 0) */ \ " sub %[tmp], %[tmp], 1 \n" /* tmp-- */ \ - " asl.f %[delay], %[delay], 1 \n" /* delay *= 2 */ \ - " mov.z %[delay], 1 \n" /* handle overflow */ \ + " rol %[delay], %[delay] \n" /* delay *= 2 */ \ " b 1b \n" /* start over */ \ "4: ; --- success --- \n" \ diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h index 7071fc0da56a..db8c59d1eaeb 100644 --- a/arch/arc/include/asm/spinlock.h +++ b/arch/arc/include/asm/spinlock.h @@ -260,8 +260,7 @@ static inline void arch_write_unlock(arch_rwlock_t *rw) " mov %[tmp], %[delay] \n" /* tmp = delay */ \ "2: brne.d %[tmp], 0, 2b \n" /* while (tmp != 0) */ \ " sub %[tmp], %[tmp], 1 \n" /* tmp-- */ \ - " asl.f %[delay], %[delay], 1 \n" /* delay *= 2 */ \ - " mov.z %[delay], 1 \n" /* handle overflow */ \ + " rol %[delay], %[delay] \n" /* delay *= 2 */ \ " b 1b \n" /* start over */ \ " \n" \ "4: ; --- done --- \n" \ From 209e4dbc8dcdb2b1839f18fd1cf07ec7bedadf4d Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 7 Aug 2015 12:31:17 +0200 Subject: [PATCH 425/428] drm/vblank: Use u32 consistently for vblank counters MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In commit 99264a61dfcda41d86d0960cf2d4c0fc2758a773 Author: Daniel Vetter Date: Wed Apr 15 19:34:43 2015 +0200 drm/vblank: Fixup and document timestamp update/read barriers I've switched vblank->count from atomic_t to unsigned long and accidentally created an integer comparison bug in drm_vblank_count_and_time since vblanke->count might overflow the u32 local copy and hence the retry loop never succeed. Fix this by consistently using u32. Cc: Michel Dänzer Reported-by: Michel Dänzer Reviewed-by: Thierry Reding Signed-off-by: Daniel Vetter --- drivers/gpu/drm/drm_irq.c | 2 +- include/drm/drmP.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index f9cc68fbd2a3..b50fa0afd907 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -75,7 +75,7 @@ module_param_named(timestamp_precision_usec, drm_timestamp_precision, int, 0600) module_param_named(timestamp_monotonic, drm_timestamp_monotonic, int, 0600); static void store_vblank(struct drm_device *dev, int crtc, - unsigned vblank_count_inc, + u32 vblank_count_inc, struct timeval *t_vblank) { struct drm_vblank_crtc *vblank = &dev->vblank[crtc]; diff --git a/include/drm/drmP.h b/include/drm/drmP.h index 48db6a56975f..5aa519711e0b 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -691,7 +691,7 @@ struct drm_vblank_crtc { struct timer_list disable_timer; /* delayed disable timer */ /* vblank counter, protected by dev->vblank_time_lock for writes */ - unsigned long count; + u32 count; /* vblank timestamps, protected by dev->vblank_time_lock for writes */ struct timeval time[DRM_VBLANKTIME_RBSIZE]; From aa0cd28d057fd4cb686fbdd2475a6a3f609dd581 Mon Sep 17 00:00:00 2001 From: Joe Thornber Date: Fri, 7 Aug 2015 16:33:01 +0100 Subject: [PATCH 426/428] dm btree remove: fix bug in remove_one() remove_one() was not incrementing the key for the beginning of the range, so not all entries were being removed. This resulted in discards that were not unmapping all blocks. Fixes: 4ec331c3ea ("dm btree: add dm_btree_remove_leaves()") Signed-off-by: Joe Thornber Signed-off-by: Mike Snitzer --- drivers/md/persistent-data/dm-btree-remove.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c index 9836c0ae897c..9ca9eccd512f 100644 --- a/drivers/md/persistent-data/dm-btree-remove.c +++ b/drivers/md/persistent-data/dm-btree-remove.c @@ -689,6 +689,7 @@ static int remove_one(struct dm_btree_info *info, dm_block_t root, value_ptr(n, index)); delete_at(n, index); + keys[last_level] = k + 1ull; } else r = -ENODATA; From 6b30c73e9f37183ad60c7f7050acf8e8edf91e9c Mon Sep 17 00:00:00 2001 From: Duson Lin Date: Fri, 7 Aug 2015 14:37:24 -0700 Subject: [PATCH 427/428] Input: elantech - add special check for fw_version 0x470f01 touchpad It is no need to check the packet[0] for sanity check when doing elantech_packet_check_v4() function for fw_version = 0x470f01 touchpad. Signed-off by: Duson Lin Reviewed-by: Ulrik De Bie Signed-off-by: Dmitry Torokhov --- drivers/input/mouse/elantech.c | 22 ++++++++++++++++++++-- drivers/input/mouse/elantech.h | 1 + 2 files changed, 21 insertions(+), 2 deletions(-) diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index 22b9ca901f4e..2955f1d0ca6c 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -783,19 +783,26 @@ static int elantech_packet_check_v4(struct psmouse *psmouse) struct elantech_data *etd = psmouse->private; unsigned char *packet = psmouse->packet; unsigned char packet_type = packet[3] & 0x03; + unsigned int ic_version; bool sanity_check; if (etd->tp_dev && (packet[3] & 0x0f) == 0x06) return PACKET_TRACKPOINT; + /* This represents the version of IC body. */ + ic_version = (etd->fw_version & 0x0f0000) >> 16; + /* * Sanity check based on the constant bits of a packet. * The constant bits change depending on the value of - * the hardware flag 'crc_enabled' but are the same for - * every packet, regardless of the type. + * the hardware flag 'crc_enabled' and the version of + * the IC body, but are the same for every packet, + * regardless of the type. */ if (etd->crc_enabled) sanity_check = ((packet[3] & 0x08) == 0x00); + else if (ic_version == 7 && etd->samples[1] == 0x2A) + sanity_check = ((packet[3] & 0x1c) == 0x10); else sanity_check = ((packet[0] & 0x0c) == 0x04 && (packet[3] & 0x1c) == 0x10); @@ -1116,6 +1123,7 @@ static int elantech_get_resolution_v4(struct psmouse *psmouse, * Avatar AVIU-145A2 0x361f00 ? clickpad * Fujitsu LIFEBOOK E544 0x470f00 d0, 12, 09 2 hw buttons * Fujitsu LIFEBOOK E554 0x570f01 40, 14, 0c 2 hw buttons + * Fujitsu T725 0x470f01 05, 12, 09 2 hw buttons * Fujitsu H730 0x570f00 c0, 14, 0c 3 hw buttons (**) * Gigabyte U2442 0x450f01 58, 17, 0c 2 hw buttons * Lenovo L430 0x350f02 b9, 15, 0c 2 hw buttons (*) @@ -1651,6 +1659,16 @@ int elantech_init(struct psmouse *psmouse) etd->capabilities[0], etd->capabilities[1], etd->capabilities[2]); + if (etd->hw_version != 1) { + if (etd->send_cmd(psmouse, ETP_SAMPLE_QUERY, etd->samples)) { + psmouse_err(psmouse, "failed to query sample data\n"); + goto init_fail; + } + psmouse_info(psmouse, + "Elan sample query result %02x, %02x, %02x\n", + etd->samples[0], etd->samples[1], etd->samples[2]); + } + if (elantech_set_absolute_mode(psmouse)) { psmouse_err(psmouse, "failed to put touchpad into absolute mode.\n"); diff --git a/drivers/input/mouse/elantech.h b/drivers/input/mouse/elantech.h index f965d1569cc3..e1cbf409d9c8 100644 --- a/drivers/input/mouse/elantech.h +++ b/drivers/input/mouse/elantech.h @@ -129,6 +129,7 @@ struct elantech_data { unsigned char reg_26; unsigned char debug; unsigned char capabilities[3]; + unsigned char samples[3]; bool paritycheck; bool jumpy_cursor; bool reports_pressure; From f7644cbfcdf03528f0f450f3940c4985b2291f49 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 9 Aug 2015 15:54:30 -0400 Subject: [PATCH 428/428] Linux 4.2-rc6 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 15d3201052ae..35b4c196c171 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 2 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Hurr durr I'ma sheep # *DOCUMENTATION*