From 5e3283e2920a0bd8a806964d80274b8756e0dd7f Mon Sep 17 00:00:00 2001 From: Joe Thornber Date: Tue, 8 Apr 2014 11:08:41 +0100 Subject: [PATCH 001/150] dm thin: irqsave must always be used with the pool->lock spinlock Commit c140e1c4e23 ("dm thin: use per thin device deferred bio lists") incorrectly stopped disabling irqs when taking the pool's spinlock. Irqs must be disabled when taking the pool's spinlock otherwise a thread could spin_lock(), then get interrupted to service thin_endio() in interrupt context, which would then deadlock in spin_lock_irqsave(). Signed-off-by: Joe Thornber Signed-off-by: Mike Snitzer --- drivers/md/dm-thin.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 53728be84dee..ae5fd0b9c75c 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -3101,6 +3101,7 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) struct thin_c *tc; struct dm_dev *pool_dev, *origin_dev; struct mapped_device *pool_md; + unsigned long flags; mutex_lock(&dm_thin_pool_table.mutex); @@ -3191,9 +3192,9 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) mutex_unlock(&dm_thin_pool_table.mutex); - spin_lock(&tc->pool->lock); + spin_lock_irqsave(&tc->pool->lock, flags); list_add_tail_rcu(&tc->list, &tc->pool->active_thins); - spin_unlock(&tc->pool->lock); + spin_unlock_irqrestore(&tc->pool->lock, flags); /* * This synchronize_rcu() call is needed here otherwise we risk a * wake_worker() call finding no bios to process (because the newly From b10ebd34cccae1b431caf1be54919aede2be7cbe Mon Sep 17 00:00:00 2001 From: Joe Thornber Date: Tue, 8 Apr 2014 11:29:01 +0100 Subject: [PATCH 002/150] dm thin: fix rcu_read_lock being held in code that can sleep Commit c140e1c4e23 ("dm thin: use per thin device deferred bio lists") introduced the use of an rculist for all active thin devices. The use of rcu_read_lock() in process_deferred_bios() can result in a BUG if a dm_bio_prison_cell must be allocated as a side-effect of bio_detain(): BUG: sleeping function called from invalid context at mm/mempool.c:203 in_atomic(): 1, irqs_disabled(): 0, pid: 6, name: kworker/u8:0 3 locks held by kworker/u8:0/6: #0: ("dm-" "thin"){.+.+..}, at: [] process_one_work+0x192/0x550 #1: ((&pool->worker)){+.+...}, at: [] process_one_work+0x192/0x550 #2: (rcu_read_lock){.+.+..}, at: [] do_worker+0x5/0x4d0 We can't process deferred bios with the rcu lock held, since dm_bio_prison_cell allocation may block if the bio-prison's cell mempool is exhausted. To fix: - Introduce a refcount and completion field to each thin_c - Add thin_get/put methods for adjusting the refcount. If the refcount hits zero then the completion is triggered. - Initialise refcount to 1 when creating thin_c - When iterating the active_thins list we thin_get() whilst the rcu lock is held. - After the rcu lock is dropped we process the deferred bios for that thin. - When destroying a thin_c we thin_put() and then wait for the completion -- to avoid a race between the worker thread iterating from that thin_c and destroying the thin_c. Signed-off-by: Joe Thornber Signed-off-by: Mike Snitzer --- drivers/md/dm-thin.c | 70 ++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 67 insertions(+), 3 deletions(-) diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index ae5fd0b9c75c..28fc282b61b2 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -232,6 +232,13 @@ struct thin_c { struct bio_list deferred_bio_list; struct bio_list retry_on_resume_list; struct rb_root sort_bio_list; /* sorted list of deferred bios */ + + /* + * Ensures the thin is not destroyed until the worker has finished + * iterating the active_thins list. + */ + atomic_t refcount; + struct completion can_destroy; }; /*----------------------------------------------------------------*/ @@ -1486,6 +1493,45 @@ static void process_thin_deferred_bios(struct thin_c *tc) blk_finish_plug(&plug); } +static void thin_get(struct thin_c *tc); +static void thin_put(struct thin_c *tc); + +/* + * We can't hold rcu_read_lock() around code that can block. So we + * find a thin with the rcu lock held; bump a refcount; then drop + * the lock. + */ +static struct thin_c *get_first_thin(struct pool *pool) +{ + struct thin_c *tc = NULL; + + rcu_read_lock(); + if (!list_empty(&pool->active_thins)) { + tc = list_entry_rcu(pool->active_thins.next, struct thin_c, list); + thin_get(tc); + } + rcu_read_unlock(); + + return tc; +} + +static struct thin_c *get_next_thin(struct pool *pool, struct thin_c *tc) +{ + struct thin_c *old_tc = tc; + + rcu_read_lock(); + list_for_each_entry_continue_rcu(tc, &pool->active_thins, list) { + thin_get(tc); + thin_put(old_tc); + rcu_read_unlock(); + return tc; + } + thin_put(old_tc); + rcu_read_unlock(); + + return NULL; +} + static void process_deferred_bios(struct pool *pool) { unsigned long flags; @@ -1493,10 +1539,11 @@ static void process_deferred_bios(struct pool *pool) struct bio_list bios; struct thin_c *tc; - rcu_read_lock(); - list_for_each_entry_rcu(tc, &pool->active_thins, list) + tc = get_first_thin(pool); + while (tc) { process_thin_deferred_bios(tc); - rcu_read_unlock(); + tc = get_next_thin(pool, tc); + } /* * If there are any deferred flush bios, we must commit @@ -3061,11 +3108,25 @@ static struct target_type pool_target = { /*---------------------------------------------------------------- * Thin target methods *--------------------------------------------------------------*/ +static void thin_get(struct thin_c *tc) +{ + atomic_inc(&tc->refcount); +} + +static void thin_put(struct thin_c *tc) +{ + if (atomic_dec_and_test(&tc->refcount)) + complete(&tc->can_destroy); +} + static void thin_dtr(struct dm_target *ti) { struct thin_c *tc = ti->private; unsigned long flags; + thin_put(tc); + wait_for_completion(&tc->can_destroy); + spin_lock_irqsave(&tc->pool->lock, flags); list_del_rcu(&tc->list); spin_unlock_irqrestore(&tc->pool->lock, flags); @@ -3192,6 +3253,9 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) mutex_unlock(&dm_thin_pool_table.mutex); + atomic_set(&tc->refcount, 1); + init_completion(&tc->can_destroy); + spin_lock_irqsave(&tc->pool->lock, flags); list_add_tail_rcu(&tc->list, &tc->pool->active_thins); spin_unlock_irqrestore(&tc->pool->lock, flags); From 79861bbb759053a9b91026becc0915d0f1f8d37d Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Thu, 10 Apr 2014 18:16:33 -0700 Subject: [PATCH 003/150] ASoC: rsnd: fix clock prepare/unprepare As with the previous commit, before a clock can be used it must be prepared for use. Change from clk_enable() and clk_disable() to the versions of the calls which also prepare and un-prepare the clocks. Will fix warnings from the clock code when this is used. Signed-off-by: Ben Dooks Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- sound/soc/sh/rcar/src.c | 4 ++-- sound/soc/sh/rcar/ssi.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/sound/soc/sh/rcar/src.c b/sound/soc/sh/rcar/src.c index 6232b7d307aa..4d0720ed5a90 100644 --- a/sound/soc/sh/rcar/src.c +++ b/sound/soc/sh/rcar/src.c @@ -258,7 +258,7 @@ static int rsnd_src_init(struct rsnd_mod *mod, { struct rsnd_src *src = rsnd_mod_to_src(mod); - clk_enable(src->clk); + clk_prepare_enable(src->clk); return 0; } @@ -269,7 +269,7 @@ static int rsnd_src_quit(struct rsnd_mod *mod, { struct rsnd_src *src = rsnd_mod_to_src(mod); - clk_disable(src->clk); + clk_disable_unprepare(src->clk); return 0; } diff --git a/sound/soc/sh/rcar/ssi.c b/sound/soc/sh/rcar/ssi.c index 4b7e20603dd7..1d8387c25bd8 100644 --- a/sound/soc/sh/rcar/ssi.c +++ b/sound/soc/sh/rcar/ssi.c @@ -171,7 +171,7 @@ static void rsnd_ssi_hw_start(struct rsnd_ssi *ssi, u32 cr; if (0 == ssi->usrcnt) { - clk_enable(ssi->clk); + clk_prepare_enable(ssi->clk); if (rsnd_dai_is_clk_master(rdai)) { if (rsnd_ssi_clk_from_parent(ssi)) @@ -230,7 +230,7 @@ static void rsnd_ssi_hw_stop(struct rsnd_ssi *ssi, rsnd_ssi_master_clk_stop(ssi); } - clk_disable(ssi->clk); + clk_disable_unprepare(ssi->clk); } dev_dbg(dev, "ssi%d hw stopped\n", rsnd_mod_id(&ssi->mod)); From 3b5b24315781c744ab3868edee931ddb2145e6b5 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Sat, 5 Apr 2014 23:35:53 +0200 Subject: [PATCH 004/150] ASoC: tlv320aic3x: fix shared reset pin for DT Currently the second tlv320aic3x instance fails to be probed from DT if the reset pin is shared with the first one. This patch fixes it by moving the list add of the reset pin into the i2c_probe method. Signed-off-by: Sebastian Reichel Signed-off-by: Mark Brown --- sound/soc/codecs/tlv320aic3x.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/sound/soc/codecs/tlv320aic3x.c b/sound/soc/codecs/tlv320aic3x.c index b1835103e9b4..d7349bc89ad3 100644 --- a/sound/soc/codecs/tlv320aic3x.c +++ b/sound/soc/codecs/tlv320aic3x.c @@ -1399,7 +1399,6 @@ static int aic3x_probe(struct snd_soc_codec *codec) } aic3x_add_widgets(codec); - list_add(&aic3x->list, &reset_list); return 0; @@ -1569,7 +1568,13 @@ static int aic3x_i2c_probe(struct i2c_client *i2c, ret = snd_soc_register_codec(&i2c->dev, &soc_codec_dev_aic3x, &aic3x_dai, 1); - return ret; + + if (ret != 0) + goto err_gpio; + + list_add(&aic3x->list, &reset_list); + + return 0; err_gpio: if (gpio_is_valid(aic3x->gpio_reset) && From 8aaa414fadaec2b682168a5c937a3950a77956bf Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Tue, 15 Apr 2014 14:37:05 +0200 Subject: [PATCH 005/150] ASoC: alc5623: Fix regmap endianness Commit 0cd257bf9b9b0cbb4fa1a5c988a232506997867c, "ASoC: alc5623: Convert to direct regmap API usage" broke probing of the codec, because of wrong endinness of the ID and codec version read from the device. Fix this by removing the existing flipping of the endiannes, and extracting the codec type byte from the word from the regmap. Signed-off-by: Andrew Lunn Signed-off-by: Mark Brown --- sound/soc/codecs/alc5623.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/codecs/alc5623.c b/sound/soc/codecs/alc5623.c index f500905e9373..2acf82f4a08a 100644 --- a/sound/soc/codecs/alc5623.c +++ b/sound/soc/codecs/alc5623.c @@ -1018,13 +1018,13 @@ static int alc5623_i2c_probe(struct i2c_client *client, dev_err(&client->dev, "failed to read vendor ID1: %d\n", ret); return ret; } - vid1 = ((vid1 & 0xff) << 8) | (vid1 >> 8); ret = regmap_read(alc5623->regmap, ALC5623_VENDOR_ID2, &vid2); if (ret < 0) { dev_err(&client->dev, "failed to read vendor ID2: %d\n", ret); return ret; } + vid2 >>= 8; if ((vid1 != 0x10ec) || (vid2 != id->driver_data)) { dev_err(&client->dev, "unknown or wrong codec\n"); From 3a7745215e7f73a5c7d9bcdc50661a55b39052a3 Mon Sep 17 00:00:00 2001 From: Milan Broz Date: Mon, 14 Apr 2014 22:02:30 +0200 Subject: [PATCH 006/150] dm verity: fix biovecs hash calculation regression Commit 003b5c5719f159f4f4bf97511c4702a0638313dd ("block: Convert drivers to immutable biovecs") incorrectly converted biovec iteration in dm-verity to always calculate the hash from a full biovec, but the function only needs to calculate the hash from part of the biovec (up to the calculated "todo" value). Fix this issue by limiting hash input to only the requested data size. This problem was identified using the cryptsetup regression test for veritysetup (verity-compat-test). Signed-off-by: Milan Broz Acked-by: Mikulas Patocka Signed-off-by: Mike Snitzer Cc: stable@vger.kernel.org # 3.14+ --- drivers/md/dm-verity.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity.c index 796007a5e0e1..7a7bab8947ae 100644 --- a/drivers/md/dm-verity.c +++ b/drivers/md/dm-verity.c @@ -330,15 +330,17 @@ static int verity_verify_io(struct dm_verity_io *io) return r; } } - todo = 1 << v->data_dev_block_bits; - while (io->iter.bi_size) { + do { u8 *page; + unsigned len; struct bio_vec bv = bio_iter_iovec(bio, io->iter); page = kmap_atomic(bv.bv_page); - r = crypto_shash_update(desc, page + bv.bv_offset, - bv.bv_len); + len = bv.bv_len; + if (likely(len >= todo)) + len = todo; + r = crypto_shash_update(desc, page + bv.bv_offset, len); kunmap_atomic(page); if (r < 0) { @@ -346,8 +348,9 @@ static int verity_verify_io(struct dm_verity_io *io) return r; } - bio_advance_iter(bio, &io->iter, bv.bv_len); - } + bio_advance_iter(bio, &io->iter, len); + todo -= len; + } while (todo); if (!v->version) { r = crypto_shash_update(desc, v->salt, v->salt_size); From e02ba72aabfade4c9cd6e3263e9b57bf890ad25c Mon Sep 17 00:00:00 2001 From: Anatol Pomozov Date: Tue, 15 Apr 2014 11:31:33 -0700 Subject: [PATCH 007/150] aio: block io_destroy() until all context requests are completed deletes aio context and all resources related to. It makes sense that no IO operations connected to the context should be running after the context is destroyed. As we removed io_context we have no chance to get requests status or call io_getevents(). man page for io_destroy says that this function may block until all context's requests are completed. Before kernel 3.11 io_destroy() blocked indeed, but since aio refactoring in 3.11 it is not true anymore. Here is a pseudo-code that shows a testcase for a race condition discovered in 3.11: initialize io_context io_submit(read to buffer) io_destroy() // context is destroyed so we can free the resources free(buffers); // if the buffer is allocated by some other user he'll be surprised // to learn that the buffer still filled by an outstanding operation // from the destroyed io_context The fix is straight-forward - add a completion struct and wait on it in io_destroy, complete() should be called when number of in-fligh requests reaches zero. If two or more io_destroy() called for the same context simultaneously then only the first one waits for IO completion, other calls behaviour is undefined. Tested: ran http://pastebin.com/LrPsQ4RL testcase for several hours and do not see the race condition anymore. Signed-off-by: Anatol Pomozov Signed-off-by: Benjamin LaHaise --- fs/aio.c | 36 ++++++++++++++++++++++++++++++++---- 1 file changed, 32 insertions(+), 4 deletions(-) diff --git a/fs/aio.c b/fs/aio.c index 12a3de0ee6da..2adbb0398ab9 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -112,6 +112,11 @@ struct kioctx { struct work_struct free_work; + /* + * signals when all in-flight requests are done + */ + struct completion *requests_done; + struct { /* * This counts the number of available slots in the ringbuffer, @@ -508,6 +513,10 @@ static void free_ioctx_reqs(struct percpu_ref *ref) { struct kioctx *ctx = container_of(ref, struct kioctx, reqs); + /* At this point we know that there are no any in-flight requests */ + if (ctx->requests_done) + complete(ctx->requests_done); + INIT_WORK(&ctx->free_work, free_ioctx); schedule_work(&ctx->free_work); } @@ -718,7 +727,8 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) * when the processes owning a context have all exited to encourage * the rapid destruction of the kioctx. */ -static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx) +static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx, + struct completion *requests_done) { if (!atomic_xchg(&ctx->dead, 1)) { struct kioctx_table *table; @@ -747,7 +757,11 @@ static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx) if (ctx->mmap_size) vm_munmap(ctx->mmap_base, ctx->mmap_size); + ctx->requests_done = requests_done; percpu_ref_kill(&ctx->users); + } else { + if (requests_done) + complete(requests_done); } } @@ -809,7 +823,7 @@ void exit_aio(struct mm_struct *mm) */ ctx->mmap_size = 0; - kill_ioctx(mm, ctx); + kill_ioctx(mm, ctx, NULL); } } @@ -1185,7 +1199,7 @@ SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp) if (!IS_ERR(ioctx)) { ret = put_user(ioctx->user_id, ctxp); if (ret) - kill_ioctx(current->mm, ioctx); + kill_ioctx(current->mm, ioctx, NULL); percpu_ref_put(&ioctx->users); } @@ -1203,8 +1217,22 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx) { struct kioctx *ioctx = lookup_ioctx(ctx); if (likely(NULL != ioctx)) { - kill_ioctx(current->mm, ioctx); + struct completion requests_done = + COMPLETION_INITIALIZER_ONSTACK(requests_done); + + /* Pass requests_done to kill_ioctx() where it can be set + * in a thread-safe way. If we try to set it here then we have + * a race condition if two io_destroy() called simultaneously. + */ + kill_ioctx(current->mm, ioctx, &requests_done); percpu_ref_put(&ioctx->users); + + /* Wait until all IO for the context are done. Otherwise kernel + * keep using user-space buffers even if user thinks the context + * is destroyed. + */ + wait_for_completion(&requests_done); + return 0; } pr_debug("EINVAL: io_destroy: invalid context id\n"); From 06cd7a874ec6e09d151aeb1fa8600e14f1ff89f6 Mon Sep 17 00:00:00 2001 From: Sebastian Ott Date: Tue, 15 Apr 2014 20:08:01 +0200 Subject: [PATCH 008/150] s390/chsc: fix SEI usage on old FW levels Using a notification type mask for the store event information chsc is unsupported on some firmware levels. Retry SEI with that mask set to zero (which is the old way of requesting only channel subsystem related events). Cc: Reported-and-tested-by: Stefan Haberland Reviewed-by: Peter Oberparleiter Signed-off-by: Sebastian Ott Signed-off-by: Martin Schwidefsky --- drivers/s390/cio/chsc.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c index 9f0ea6cb6922..e3bf885f4a6c 100644 --- a/drivers/s390/cio/chsc.c +++ b/drivers/s390/cio/chsc.c @@ -541,18 +541,27 @@ static void chsc_process_sei_nt0(struct chsc_sei_nt0_area *sei_area) static void chsc_process_event_information(struct chsc_sei *sei, u64 ntsm) { - do { + static int ntsm_unsupported; + + while (true) { memset(sei, 0, sizeof(*sei)); sei->request.length = 0x0010; sei->request.code = 0x000e; - sei->ntsm = ntsm; + if (!ntsm_unsupported) + sei->ntsm = ntsm; if (chsc(sei)) break; if (sei->response.code != 0x0001) { - CIO_CRW_EVENT(2, "chsc: sei failed (rc=%04x)\n", - sei->response.code); + CIO_CRW_EVENT(2, "chsc: sei failed (rc=%04x, ntsm=%llx)\n", + sei->response.code, sei->ntsm); + + if (sei->response.code == 3 && sei->ntsm) { + /* Fallback for old firmware. */ + ntsm_unsupported = 1; + continue; + } break; } @@ -568,7 +577,10 @@ static void chsc_process_event_information(struct chsc_sei *sei, u64 ntsm) CIO_CRW_EVENT(2, "chsc: unhandled nt: %d\n", sei->nt); break; } - } while (sei->u.nt0_area.flags & 0x80); + + if (!(sei->u.nt0_area.flags & 0x80)) + break; + } } /* From 6ae6698276ca36f37afc2ad38054092021519ad4 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Fri, 18 Apr 2014 17:32:08 +0800 Subject: [PATCH 009/150] ASoC: fsl_spdif: Fix wrong OFFSET of STC_SYSCLK_DIV It should use STC_SYSCLK_DIV_OFFSET. Thus fix it. Signed-off-by: Nicolin Chen Signed-off-by: Mark Brown --- sound/soc/fsl/fsl_spdif.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/fsl/fsl_spdif.h b/sound/soc/fsl/fsl_spdif.h index b1266790d117..605a10b2112b 100644 --- a/sound/soc/fsl/fsl_spdif.h +++ b/sound/soc/fsl/fsl_spdif.h @@ -144,8 +144,8 @@ enum spdif_gainsel { /* SPDIF Clock register */ #define STC_SYSCLK_DIV_OFFSET 11 -#define STC_SYSCLK_DIV_MASK (0x1ff << STC_TXCLK_SRC_OFFSET) -#define STC_SYSCLK_DIV(x) ((((x) - 1) << STC_TXCLK_DIV_OFFSET) & STC_SYSCLK_DIV_MASK) +#define STC_SYSCLK_DIV_MASK (0x1ff << STC_SYSCLK_DIV_OFFSET) +#define STC_SYSCLK_DIV(x) ((((x) - 1) << STC_SYSCLK_DIV_OFFSET) & STC_SYSCLK_DIV_MASK) #define STC_TXCLK_SRC_OFFSET 8 #define STC_TXCLK_SRC_MASK (0x7 << STC_TXCLK_SRC_OFFSET) #define STC_TXCLK_SRC_SET(x) ((x << STC_TXCLK_SRC_OFFSET) & STC_TXCLK_SRC_MASK) From eb4dd20c2ac9ad394401694d8762e0a13bc469ef Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Fri, 18 Apr 2014 02:06:30 +0200 Subject: [PATCH 010/150] ASoC: tlv320aic31xx: document that the regulators are mandatory The driver will not probe if regulators are not provided. Move the regulator properties to the required section. Signed-off-by: Alexandre Belloni Signed-off-by: Mark Brown --- Documentation/devicetree/bindings/sound/tlv320aic31xx.txt | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/devicetree/bindings/sound/tlv320aic31xx.txt b/Documentation/devicetree/bindings/sound/tlv320aic31xx.txt index 74c66dee3e14..eff12be5e789 100644 --- a/Documentation/devicetree/bindings/sound/tlv320aic31xx.txt +++ b/Documentation/devicetree/bindings/sound/tlv320aic31xx.txt @@ -13,6 +13,9 @@ Required properties: "ti,tlv320aic3111" - TLV320AIC3111 (stereo speaker amp, MiniDSP) - reg - - I2C slave address +- HPVDD-supply, SPRVDD-supply, SPLVDD-supply, AVDD-supply, IOVDD-supply, + DVDD-supply : power supplies for the device as covered in + Documentation/devicetree/bindings/regulator/regulator.txt Optional properties: @@ -24,9 +27,6 @@ Optional properties: 3 or MICBIAS_AVDD - MICBIAS output is connected to AVDD If this node is not mentioned or if the value is unknown, then micbias is set to 2.0V. -- HPVDD-supply, SPRVDD-supply, SPLVDD-supply, AVDD-supply, IOVDD-supply, - DVDD-supply : power supplies for the device as covered in - Documentation/devicetree/bindings/regulator/regulator.txt CODEC output pins: * HPL From 4e17d2d33abe4b523f79fec037ef66ba93643f65 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Tue, 8 Apr 2014 22:10:33 +0800 Subject: [PATCH 011/150] ASoC: cs42l52: Convert to use devm_gpio_request_one Current code missed a gpio_free() call in cs42l52_i2c_remove(). Convert to use devm_gpio_request_one() to fix it. Signed-off-by: Axel Lin Signed-off-by: Mark Brown --- sound/soc/codecs/cs42l52.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/sound/soc/codecs/cs42l52.c b/sound/soc/codecs/cs42l52.c index 460d35547a68..2213a037c893 100644 --- a/sound/soc/codecs/cs42l52.c +++ b/sound/soc/codecs/cs42l52.c @@ -1229,8 +1229,10 @@ static int cs42l52_i2c_probe(struct i2c_client *i2c_client, } if (cs42l52->pdata.reset_gpio) { - ret = gpio_request_one(cs42l52->pdata.reset_gpio, - GPIOF_OUT_INIT_HIGH, "CS42L52 /RST"); + ret = devm_gpio_request_one(&i2c_client->dev, + cs42l52->pdata.reset_gpio, + GPIOF_OUT_INIT_HIGH, + "CS42L52 /RST"); if (ret < 0) { dev_err(&i2c_client->dev, "Failed to request /RST %d: %d\n", cs42l52->pdata.reset_gpio, ret); From 2b21694f153a0df88dca7fb4ce04614ea7ff9dc2 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Tue, 8 Apr 2014 22:11:40 +0800 Subject: [PATCH 012/150] ASoC: cs42l73: Convert to use devm_gpio_request_one Current code missed a gpio_free() call in cs42l73_i2c_remove(). Convert to use devm_gpio_request_one() to fix it. Signed-off-by: Axel Lin Signed-off-by: Mark Brown --- sound/soc/codecs/cs42l73.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/sound/soc/codecs/cs42l73.c b/sound/soc/codecs/cs42l73.c index 0ee60a19a263..ae3717992d56 100644 --- a/sound/soc/codecs/cs42l73.c +++ b/sound/soc/codecs/cs42l73.c @@ -1443,8 +1443,10 @@ static int cs42l73_i2c_probe(struct i2c_client *i2c_client, i2c_set_clientdata(i2c_client, cs42l73); if (cs42l73->pdata.reset_gpio) { - ret = gpio_request_one(cs42l73->pdata.reset_gpio, - GPIOF_OUT_INIT_HIGH, "CS42L73 /RST"); + ret = devm_gpio_request_one(&i2c_client->dev, + cs42l73->pdata.reset_gpio, + GPIOF_OUT_INIT_HIGH, + "CS42L73 /RST"); if (ret < 0) { dev_err(&i2c_client->dev, "Failed to request /RST %d: %d\n", cs42l73->pdata.reset_gpio, ret); From 7897ab78f64008a81344af9fecec6527dbab7a31 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 16 Apr 2014 18:38:11 +0300 Subject: [PATCH 013/150] ASoC: Intel: some incorrect sizeof() usages The intent was to say "sizeof(*pos)" and not "sizeof(pos)". The sizeof(*pos) is 8 bytes so the bug won't show up on 64 bit systems. The sizeof(*dx) is 172 bytes so that will be a bugfix. Signed-off-by: Dan Carpenter Signed-off-by: Mark Brown --- sound/soc/intel/sst-haswell-ipc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/intel/sst-haswell-ipc.c b/sound/soc/intel/sst-haswell-ipc.c index f46bb4ddde6f..4ed2d1706a83 100644 --- a/sound/soc/intel/sst-haswell-ipc.c +++ b/sound/soc/intel/sst-haswell-ipc.c @@ -617,7 +617,7 @@ static void hsw_notification_work(struct work_struct *work) case IPC_POSITION_CHANGED: trace_ipc_notification("DSP stream position changed for", stream->reply.stream_hw_id); - sst_dsp_inbox_read(hsw->dsp, pos, sizeof(pos)); + sst_dsp_inbox_read(hsw->dsp, pos, sizeof(*pos)); if (stream->notify_position) stream->notify_position(stream, stream->pdata); @@ -1609,7 +1609,7 @@ int sst_hsw_dx_set_state(struct sst_hsw *hsw, trace_ipc_request("PM enter Dx state", state); ret = ipc_tx_message_wait(hsw, header, &state_, sizeof(state_), - dx, sizeof(dx)); + dx, sizeof(*dx)); if (ret < 0) { dev_err(hsw->dev, "ipc: error set dx state %d failed\n", state); return ret; From bf657d2479d179a03668cd7ab8aec96415592f02 Mon Sep 17 00:00:00 2001 From: Christian Engelmayer Date: Sun, 13 Apr 2014 19:56:36 +0200 Subject: [PATCH 014/150] ASoC: Intel: Fix incorrect sizeof() in sst_hsw_stream_get_volume() Fix an incorrect sizeof() usage in sst_hsw_stream_get_volume(). sst_dsp_read() is called to read into a variable of type u32, but is passed sizeof(u32 *) for argument 'size_t bytes'. Detected by Coverity: CID 1195260. Signed-off-by: Christian Engelmayer Signed-off-by: Mark Brown --- sound/soc/intel/sst-haswell-ipc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/sound/soc/intel/sst-haswell-ipc.c b/sound/soc/intel/sst-haswell-ipc.c index 4ed2d1706a83..50e4246d4b57 100644 --- a/sound/soc/intel/sst-haswell-ipc.c +++ b/sound/soc/intel/sst-haswell-ipc.c @@ -991,7 +991,8 @@ int sst_hsw_stream_get_volume(struct sst_hsw *hsw, struct sst_hsw_stream *stream return -EINVAL; sst_dsp_read(hsw->dsp, volume, - stream->reply.volume_register_address[channel], sizeof(volume)); + stream->reply.volume_register_address[channel], + sizeof(*volume)); return 0; } From da343fc776e0bcb238b65d9d24610819b95d0ef4 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Fri, 18 Apr 2014 14:19:47 +0200 Subject: [PATCH 015/150] irqchip: armada-370-xp: fix invalid cast of signed value into unsigned variable The armada_370_xp_alloc_msi() function returns a signed int, which is negative on error. However, we store the return value into an irq_hw_number_t, which is unsigned. Therefore, we actually never test if armada_370_xp_alloc_msi() returns an error or not, which may lead us to use hwirq numbers of as 0xffffffe4 (when armada_370_xp_alloc_msi() returns -ENOSPC). This commit fixes that by storing the return value of armada_370_xp_alloc_msi() in a signed variable. Fixes: 31f614edb726fcc4d5aa0f2895fbdec9b04a3ca4 ('irqchip: armada-370-xp: implement MSI support') Cc: # v3.13+ Signed-off-by: Thomas Petazzoni Link: https://lkml.kernel.org/r/1397823593-1932-2-git-send-email-thomas.petazzoni@free-electrons.com Tested-by: Neil Greatorex Signed-off-by: Jason Cooper --- drivers/irqchip/irq-armada-370-xp.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c index 41be897df8d5..3c8d89b62a21 100644 --- a/drivers/irqchip/irq-armada-370-xp.c +++ b/drivers/irqchip/irq-armada-370-xp.c @@ -132,8 +132,7 @@ static int armada_370_xp_setup_msi_irq(struct msi_chip *chip, struct msi_desc *desc) { struct msi_msg msg; - irq_hw_number_t hwirq; - int virq; + int virq, hwirq; hwirq = armada_370_xp_alloc_msi(); if (hwirq < 0) From 830cbe4b7a918613276aa3d3b28d24410623f92c Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Fri, 18 Apr 2014 14:19:48 +0200 Subject: [PATCH 016/150] irqchip: armada-370-xp: implement the ->check_device() msi_chip operation Until now, we were leaving the ->check_device() msi_chip operation empty, which leads the PCI core to believe that we support both MSI and MSI-X. In fact, we do not support MSI-X, so we have to tell this to the PCI core by providing an implementation of this operation. Fixes: 31f614edb726fcc4d5aa0f2895fbdec9b04a3ca4 ('irqchip: armada-370-xp: implement MSI support') Cc: # v3.13+ Signed-off-by: Thomas Petazzoni Link: https://lkml.kernel.org/r/1397823593-1932-3-git-send-email-thomas.petazzoni@free-electrons.com Tested-by: Neil Greatorex Signed-off-by: Jason Cooper --- drivers/irqchip/irq-armada-370-xp.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c index 3c8d89b62a21..78b0ac9129d7 100644 --- a/drivers/irqchip/irq-armada-370-xp.c +++ b/drivers/irqchip/irq-armada-370-xp.c @@ -162,6 +162,15 @@ static void armada_370_xp_teardown_msi_irq(struct msi_chip *chip, armada_370_xp_free_msi(d->hwirq); } +static int armada_370_xp_check_msi_device(struct msi_chip *chip, struct pci_dev *dev, + int nvec, int type) +{ + /* We support MSI, but not MSI-X */ + if (type == PCI_CAP_ID_MSI) + return 0; + return -EINVAL; +} + static struct irq_chip armada_370_xp_msi_irq_chip = { .name = "armada_370_xp_msi_irq", .irq_enable = unmask_msi_irq, @@ -200,6 +209,7 @@ static int armada_370_xp_msi_init(struct device_node *node, msi_chip->setup_irq = armada_370_xp_setup_msi_irq; msi_chip->teardown_irq = armada_370_xp_teardown_msi_irq; + msi_chip->check_device = armada_370_xp_check_msi_device; msi_chip->of_node = node; armada_370_xp_msi_domain = From ff3c664505bf8a8334bca5045e87b85cfe4d2277 Mon Sep 17 00:00:00 2001 From: Neil Greatorex Date: Fri, 18 Apr 2014 14:19:49 +0200 Subject: [PATCH 017/150] irqchip: armada-370-xp: Fix releasing of MSIs Store the value of d->hwirq in a local variable as the real value is wiped out by calling irq_dispose_mapping. Without this patch, the armada_370_xp_free_msi function would always free MSI#0, no matter what was passed to it. Fixes: 31f614edb726fcc4d5aa0f2895fbdec9b04a3ca4 ('irqchip: armada-370-xp: implement MSI support') Cc: # v3.13+ Signed-off-by: Neil Greatorex Link: https://lkml.kernel.org/r/1397823593-1932-4-git-send-email-thomas.petazzoni@free-electrons.com Signed-off-by: Thomas Petazzoni Link: https://lkml.kernel.org/r/1397823593-1932-4-git-send-email-thomas.petazzoni@free-electrons.com Signed-off-by: Jason Cooper --- drivers/irqchip/irq-armada-370-xp.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c index 78b0ac9129d7..868d11bc00d2 100644 --- a/drivers/irqchip/irq-armada-370-xp.c +++ b/drivers/irqchip/irq-armada-370-xp.c @@ -158,8 +158,10 @@ static void armada_370_xp_teardown_msi_irq(struct msi_chip *chip, unsigned int irq) { struct irq_data *d = irq_get_irq_data(irq); + unsigned long hwirq = d->hwirq; + irq_dispose_mapping(irq); - armada_370_xp_free_msi(d->hwirq); + armada_370_xp_free_msi(hwirq); } static int armada_370_xp_check_msi_device(struct msi_chip *chip, struct pci_dev *dev, From 2697e4fb9209dfe1d1b24c92d254158f63d4bc8e Mon Sep 17 00:00:00 2001 From: Jarkko Nikula Date: Tue, 15 Apr 2014 16:58:09 +0300 Subject: [PATCH 018/150] ASoC: dapm: Fix widget double free with auto-disable DAPM kcontrol Commit 9e1fda4ae158 ("ASoC: dapm: Implement mixer input auto-disable") is trying to free the widget it allocated by snd_soc_dapm_new_control() call in dapm_kcontrol_data_alloc() by adding kfree(data->widget) to dapm_kcontrol_free(). This is causing a widget double free with auto-disabled DAPM kcontrols in sound card unregistration because widgets are already freed before dapm_kcontrol_free() is called. Reason for that is all widgets are added into dapm->card->widgets list in snd_soc_dapm_new_control() and freed in dapm_free_widgets() during execution of snd_soc_dapm_free(). Now snd_soc_dapm_free() calls for different DAPM contexts happens before snd_card_free() call from where the call chain to dapm_kcontrol_free() begins: soc_cleanup_card_resources() soc_remove_dai_links() soc_remove_link_dais() snd_soc_dapm_free(&cpu_dai->dapm) soc_remove_link_components() soc_remove_platform() snd_soc_dapm_free(&platform->dapm) soc_remove_codec() snd_soc_dapm_free(&codec->dapm) snd_soc_dapm_free(&card->dapm) snd_card_free() snd_card_do_free() snd_device_free_all() snd_device_free() snd_ctl_dev_free() snd_ctl_remove() snd_ctl_free_one() dapm_kcontrol_free() This wasn't making harm with ordinary DAPM kcontrols since data->widget is NULL for them. Fixes: 9e1fda4ae158 (ASoC: dapm: Implement mixer input auto-disable) Signed-off-by: Jarkko Nikula Acked-by: Lars-Peter Clausen Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- sound/soc/soc-dapm.c | 1 - 1 file changed, 1 deletion(-) diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index c8a780d0d057..7769b0a2bc5a 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -254,7 +254,6 @@ static int dapm_kcontrol_data_alloc(struct snd_soc_dapm_widget *widget, static void dapm_kcontrol_free(struct snd_kcontrol *kctl) { struct dapm_kcontrol_data *data = snd_kcontrol_chip(kctl); - kfree(data->widget); kfree(data->wlist); kfree(data); } From 8f2dd677bec68fb55904799a82674c9e64b23be3 Mon Sep 17 00:00:00 2001 From: Behan Webster Date: Mon, 21 Apr 2014 22:40:27 -0700 Subject: [PATCH 019/150] x86: LLVMLinux: Wrap -mno-80387 with cc-option Wrap -mno-80387 gcc options with cc-option so they don't break clang. Signed-off-by: Behan Webster Cc: torvalds@linux-foundation.org Cc: dwmw2@infradead.org Cc: pageexec@freemail.hu Link: http://lkml.kernel.org/r/1398145227-25053-1-git-send-email-behanw@converseincode.com Signed-off-by: Ingo Molnar --- arch/x86/Makefile | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/x86/Makefile b/arch/x86/Makefile index d1b7c377a234..ce6ad7e6a7d7 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -83,7 +83,9 @@ else KBUILD_CFLAGS += -m64 # Don't autogenerate traditional x87, MMX or SSE instructions - KBUILD_CFLAGS += -mno-mmx -mno-sse -mno-80387 -mno-fp-ret-in-387 + KBUILD_CFLAGS += -mno-mmx -mno-sse + KBUILD_CFLAGS += $(call cc-option,-mno-80387) + KBUILD_CFLAGS += $(call cc-option,-mno-fp-ret-in-387) # Use -mpreferred-stack-boundary=3 if supported. KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3) From 40478455fefdc0bde24ae872c3f88d58a1b0e435 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Thu, 27 Mar 2014 11:08:45 +0200 Subject: [PATCH 020/150] drm/i915: Allow user modes to exceed DVI 165MHz limit MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In commit commit 6375b768a9850b6154478993e5fb566fa4614a9c Author: Ville Syrjälä Date: Mon Mar 3 11:33:36 2014 +0200 drm/i915: Reject >165MHz modes w/ DVI monitors the driver started to filter out display modes which exceed the single-link DVI 165Mz dotclock limits when the monitor doesn't report itself as being HDMI compliant. The intent was to filter out all EDID derived modes that require dual-link DVI to operate since we don't support dual-link. However the patch went a bit too far and also causes the driver to reject such modes even when specified by the user. Normally we don't check the sink limitations when setting a mode from the user. This allows the user to specify any mode whether the sink reports to support it or not. This can be useful since often the sinks support more modes than they report in the EDID. So relax the checks a bit, and apply the single-link DVI dotclock limit only when filtering the mode list, and ignore the limit when setting a user specified mode. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=72961 Tested-by: Nicholas Vinson Cc: stable@vger.kernel.org [3.14] Reviewed-by: Daniel Vetter Signed-off-by: Ville Syrjälä Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_hdmi.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index b0413e190625..157267aa3561 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -821,11 +821,11 @@ static void intel_disable_hdmi(struct intel_encoder *encoder) } } -static int hdmi_portclock_limit(struct intel_hdmi *hdmi) +static int hdmi_portclock_limit(struct intel_hdmi *hdmi, bool respect_dvi_limit) { struct drm_device *dev = intel_hdmi_to_dev(hdmi); - if (!hdmi->has_hdmi_sink || IS_G4X(dev)) + if ((respect_dvi_limit && !hdmi->has_hdmi_sink) || IS_G4X(dev)) return 165000; else if (IS_HASWELL(dev) || INTEL_INFO(dev)->gen >= 8) return 300000; @@ -837,7 +837,8 @@ static enum drm_mode_status intel_hdmi_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { - if (mode->clock > hdmi_portclock_limit(intel_attached_hdmi(connector))) + if (mode->clock > hdmi_portclock_limit(intel_attached_hdmi(connector), + true)) return MODE_CLOCK_HIGH; if (mode->clock < 20000) return MODE_CLOCK_LOW; @@ -879,7 +880,7 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder, struct drm_device *dev = encoder->base.dev; struct drm_display_mode *adjusted_mode = &pipe_config->adjusted_mode; int clock_12bpc = pipe_config->adjusted_mode.crtc_clock * 3 / 2; - int portclock_limit = hdmi_portclock_limit(intel_hdmi); + int portclock_limit = hdmi_portclock_limit(intel_hdmi, false); int desired_bpp; if (intel_hdmi->color_range_auto) { From 4c5fba3d4ae3a7aae2c4a56d4a234aa556b7caca Mon Sep 17 00:00:00 2001 From: Christian Ruppert Date: Fri, 11 Apr 2014 16:46:04 +0200 Subject: [PATCH 021/150] pinctrl/TB10x: Fix signedness bug In the TB10x pin database, a port index of -1 is used to indicate unmuxed GPIO pin groups. This bug fixes a 'cast to unsigned' bug of this value. Thanks to Dan Carpenter for highlighting this. CC: Dan Carpenter Signed-off-by: Christian Ruppert Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-tb10x.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/pinctrl/pinctrl-tb10x.c b/drivers/pinctrl/pinctrl-tb10x.c index c5e0f6973a3b..26ca6855f478 100644 --- a/drivers/pinctrl/pinctrl-tb10x.c +++ b/drivers/pinctrl/pinctrl-tb10x.c @@ -629,9 +629,8 @@ static int tb10x_gpio_request_enable(struct pinctrl_dev *pctl, */ for (i = 0; i < state->pinfuncgrpcnt; i++) { const struct tb10x_pinfuncgrp *pfg = &state->pingroups[i]; - unsigned int port = pfg->port; unsigned int mode = pfg->mode; - int j; + int j, port = pfg->port; /* * Skip pin groups which are always mapped and don't need From a73d2e30b46787d478275db36c19222020e29dc5 Mon Sep 17 00:00:00 2001 From: Andrew Bresticker Date: Wed, 16 Apr 2014 13:40:17 -0700 Subject: [PATCH 022/150] pinctrl: as3722: fix handling of GPIO invert bit The AS3722_GPIO_INV bit will always be blindly overwritten by as3722_pinctrl_gpio_set_direction() and will be ignored when setting the value of the GPIO in as3722_gpio_set() since the enable_gpio_invert flag is never set. This will cause an initially inverted GPIO to toggle when requested as an output, which could be problematic if, for example, the GPIO controls a critical regulator. Instead of setting up the enable_gpio_invert flag, just leave the invert bit alone and check it before setting the GPIO value. Cc: # v3.14+ Signed-off-by: Andrew Bresticker Reviewed-by: Stephen Warren Tested-by: Stephen Warren Acked-by: Laxman Dewangan Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-as3722.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/drivers/pinctrl/pinctrl-as3722.c b/drivers/pinctrl/pinctrl-as3722.c index 92ed4b2e3c07..c862f9c0e9ce 100644 --- a/drivers/pinctrl/pinctrl-as3722.c +++ b/drivers/pinctrl/pinctrl-as3722.c @@ -64,7 +64,6 @@ struct as3722_pin_function { }; struct as3722_gpio_pin_control { - bool enable_gpio_invert; unsigned mode_prop; int io_function; }; @@ -320,10 +319,8 @@ static int as3722_pinctrl_gpio_set_direction(struct pinctrl_dev *pctldev, return mode; } - if (as_pci->gpio_control[offset].enable_gpio_invert) - mode |= AS3722_GPIO_INV; - - return as3722_write(as3722, AS3722_GPIOn_CONTROL_REG(offset), mode); + return as3722_update_bits(as3722, AS3722_GPIOn_CONTROL_REG(offset), + AS3722_GPIO_MODE_MASK, mode); } static const struct pinmux_ops as3722_pinmux_ops = { @@ -496,10 +493,18 @@ static void as3722_gpio_set(struct gpio_chip *chip, unsigned offset, { struct as3722_pctrl_info *as_pci = to_as_pci(chip); struct as3722 *as3722 = as_pci->as3722; - int en_invert = as_pci->gpio_control[offset].enable_gpio_invert; + int en_invert; u32 val; int ret; + ret = as3722_read(as3722, AS3722_GPIOn_CONTROL_REG(offset), &val); + if (ret < 0) { + dev_err(as_pci->dev, + "GPIO_CONTROL%d_REG read failed: %d\n", offset, ret); + return; + } + en_invert = !!(val & AS3722_GPIO_INV); + if (value) val = (en_invert) ? 0 : AS3722_GPIOn_SIGNAL(offset); else From 95e9ee92e20162681e9f65c25962e0606db9d149 Mon Sep 17 00:00:00 2001 From: Wenkai Du Date: Tue, 22 Apr 2014 16:38:54 +0300 Subject: [PATCH 023/150] ASoC: Intel: Fix audio crash due to negative address offset There were occasional ADSP crash during reboot testing: [ 11.883364] BUG: unable to handle kernel paging request at ffffc90121700000 [ 11.883380] IP: [] sst_module_insert_fixed_block+0x24f/0x26d [snd_soc_sst_dsp] [ 11.883397] PGD 7800b067 PUD 0 [ 11.883405] Oops: 0002 [#1] SMP [ 11.886418] gsmi: Log Shutdown Reason 0x03 The virtual address, ffffc90121700000, was out of range. The virtual address is calculated by adding LPE base address with an offset: sst_memcpy32(dsp->addr.lpe + data->offset, data->data, data->size); The offset is calculated in sst_byt_parse_module, by subtraction of two virtual addresses dsp->addr.fw_ext and dsp->addr.lpe: block_data.offset = block->ram_offset + (dsp->addr.fw_ext - dsp->addr.lpe); These virtual addresses are assigned by kernel from ioremap: sst->addr.lpe = ioremap(pdata->lpe_base, pdata->lpe_size); sst->addr.fw_ext = ioremap(pdata->fw_base, pdata->fw_size); In current driver code, offset is defined as unsigned int32: struct sst_module_data { ... u32 offset; /* offset in FW file */ }; Most of the time kernel assigned virtual addresses with addr.fw_ext greater than addr.lpe. But sometimes it was the other way round. Fix the problem by declaring offset as signed int32_t. Signed-off-by: Wenkai Du Signed-off-by: Jarkko Nikula Signed-off-by: Mark Brown --- sound/soc/intel/sst-dsp-priv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/intel/sst-dsp-priv.h b/sound/soc/intel/sst-dsp-priv.h index fe8e81aad646..30ca14a6a835 100644 --- a/sound/soc/intel/sst-dsp-priv.h +++ b/sound/soc/intel/sst-dsp-priv.h @@ -136,7 +136,7 @@ struct sst_module_data { enum sst_data_type data_type; /* type of module data */ u32 size; /* size in bytes */ - u32 offset; /* offset in FW file */ + int32_t offset; /* offset in FW file */ u32 data_offset; /* offset in ADSP memory space */ void *data; /* module data */ }; From eebdec044e82a4c694b7c1f4996e3ab82d64482c Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Tue, 22 Apr 2014 22:46:31 +0200 Subject: [PATCH 024/150] ASoC: jz4740: Remove Makefile entry for removed file Commit 0406a40a0 ("ASoC: jz4740: Use the generic dmaengine PCM driver") jz4740-pcm.c file, but neglected to remove the Makefile entries. Fixes: 0406a40a0 ("ASoC: jz4740: Use the generic dmaengine PCM driver") Reported-by: kbuild test robot Reported-by: Ralf Baechle Signed-off-by: Lars-Peter Clausen Signed-off-by: Mark Brown --- sound/soc/jz4740/Makefile | 2 -- 1 file changed, 2 deletions(-) diff --git a/sound/soc/jz4740/Makefile b/sound/soc/jz4740/Makefile index be873c1b0c20..d32c540555c4 100644 --- a/sound/soc/jz4740/Makefile +++ b/sound/soc/jz4740/Makefile @@ -1,10 +1,8 @@ # # Jz4740 Platform Support # -snd-soc-jz4740-objs := jz4740-pcm.o snd-soc-jz4740-i2s-objs := jz4740-i2s.o -obj-$(CONFIG_SND_JZ4740_SOC) += snd-soc-jz4740.o obj-$(CONFIG_SND_JZ4740_SOC_I2S) += snd-soc-jz4740-i2s.o # Jz4740 Machine Support From 132e9a68a5794ad2e4a3d0c07dfb7133a70b1651 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Tue, 15 Apr 2014 11:05:16 -0400 Subject: [PATCH 025/150] Fix: tracing: use 'E' instead of 'X' for unsigned module tain flag In the following commit: commit 57673c2b0baa900dddae3b9eb3d7748ebf550eb3 Author: Rusty Russell Date: Mon Mar 31 14:39:57 2014 +1030 Use 'E' instead of 'X' for unsigned module taint flag. One site has been forgotten in trace events module.h. Signed-off-by: Mathieu Desnoyers CC: Steven Rostedt CC: Rusty Russell Signed-off-by: Rusty Russell --- include/trace/events/module.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/trace/events/module.h b/include/trace/events/module.h index 11fd51b413de..ed0b2c599a64 100644 --- a/include/trace/events/module.h +++ b/include/trace/events/module.h @@ -25,7 +25,7 @@ struct module; { (1UL << TAINT_OOT_MODULE), "O" }, \ { (1UL << TAINT_FORCED_MODULE), "F" }, \ { (1UL << TAINT_CRAP), "C" }, \ - { (1UL << TAINT_UNSIGNED_MODULE), "X" }) + { (1UL << TAINT_UNSIGNED_MODULE), "E" }) TRACE_EVENT(module_load, From 9953599bc02dbc1d3330e6a0bfc6c50e9dffcac6 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Sun, 13 Apr 2014 12:00:33 +0200 Subject: [PATCH 026/150] drm/i915: Don't check gmch state on inherited configs ... our current modeset code isn't good enough yet to handle this. The scenario is: 1. BIOS sets up a cloned config with lvds+external screen on the same pipe, e.g. pipe B. 2. We read out that state for pipe B and assign the gmch_pfit state to it. 3. The initial modeset switches the lvds to pipe A but due to lack of atomic modeset we don't recompute the config of pipe B. -> both pipes now claim (in the sw pipe config structure) to use the gmch_pfit, which just won't work. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=74081 Tested-by: max Cc: Alan Stern Cc: stable@vger.kernel.org Signed-off-by: Daniel Vetter Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_display.c | 23 ++++++++++++++++++----- drivers/gpu/drm/i915/intel_drv.h | 3 ++- 2 files changed, 20 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index dae976f51d83..69bcc42a0e44 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -9654,11 +9654,22 @@ intel_pipe_config_compare(struct drm_device *dev, PIPE_CONF_CHECK_I(pipe_src_w); PIPE_CONF_CHECK_I(pipe_src_h); - PIPE_CONF_CHECK_I(gmch_pfit.control); - /* pfit ratios are autocomputed by the hw on gen4+ */ - if (INTEL_INFO(dev)->gen < 4) - PIPE_CONF_CHECK_I(gmch_pfit.pgm_ratios); - PIPE_CONF_CHECK_I(gmch_pfit.lvds_border_bits); + /* + * FIXME: BIOS likes to set up a cloned config with lvds+external + * screen. Since we don't yet re-compute the pipe config when moving + * just the lvds port away to another pipe the sw tracking won't match. + * + * Proper atomic modesets with recomputed global state will fix this. + * Until then just don't check gmch state for inherited modes. + */ + if (!PIPE_CONF_QUIRK(PIPE_CONFIG_QUIRK_INHERITED_MODE)) { + PIPE_CONF_CHECK_I(gmch_pfit.control); + /* pfit ratios are autocomputed by the hw on gen4+ */ + if (INTEL_INFO(dev)->gen < 4) + PIPE_CONF_CHECK_I(gmch_pfit.pgm_ratios); + PIPE_CONF_CHECK_I(gmch_pfit.lvds_border_bits); + } + PIPE_CONF_CHECK_I(pch_pfit.enabled); if (current_config->pch_pfit.enabled) { PIPE_CONF_CHECK_I(pch_pfit.pos); @@ -11616,6 +11627,8 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) base.head) { memset(&crtc->config, 0, sizeof(crtc->config)); + crtc->config.quirks |= PIPE_CONFIG_QUIRK_INHERITED_MODE; + crtc->active = dev_priv->display.get_pipe_config(crtc, &crtc->config); diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 0542de982260..328b1a70264b 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -236,7 +236,8 @@ struct intel_crtc_config { * tracked with quirk flags so that fastboot and state checker can act * accordingly. */ -#define PIPE_CONFIG_QUIRK_MODE_SYNC_FLAGS (1<<0) /* unreliable sync mode.flags */ +#define PIPE_CONFIG_QUIRK_MODE_SYNC_FLAGS (1<<0) /* unreliable sync mode.flags */ +#define PIPE_CONFIG_QUIRK_INHERITED_MODE (1<<1) /* mode inherited from firmware */ unsigned long quirks; /* User requested mode, only valid as a starting point to From 636352173a0dd127636fe331c97b117a8004bf50 Mon Sep 17 00:00:00 2001 From: Paulo Zanoni Date: Tue, 22 Apr 2014 19:55:42 -0300 Subject: [PATCH 027/150] drm/i915: get power domain in case the BIOS enabled eDP VDD If I unplug the eDP monitor, the BIOS of my machine will enable the VDD bit, then when the driver loads it will think VDD is enabled. It will detect that the eDP is not enabled and return false from intel_edp_init_connector. This will trigger a call to edp_panel_vdd_off_sync(), which trigger a WARN saying that the refcount of the power domain is less than zero. The problem happens because the driver gets a refcount whenever it enables the VDD bit, and puts the refcount whenever it disables the VDD bit. But on this case, the BIOS enabled VDD, so all we do is to call put() without calling get() first, so the code added is there to make sure we always have the get() in case the BIOS enabled the bit. This regression was introduced in commit e9cb81a22841908b1c075156b409a538d09c8466 Author: Paulo Zanoni Date: Thu Nov 21 13:47:23 2013 -0200 drm/i915: get a runtime PM reference when the panel VDD is on v2: - Rebase Tested-by: Chris Wilson (v1) Reviewed-by: Daniel Vetter Cc: stable@vger.kernel.org (v3.13+) Signed-off-by: Paulo Zanoni Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_dp.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index d2a55884ad52..dfa85289f28f 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -3619,7 +3619,8 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp, { struct drm_connector *connector = &intel_connector->base; struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); - struct drm_device *dev = intel_dig_port->base.base.dev; + struct intel_encoder *intel_encoder = &intel_dig_port->base; + struct drm_device *dev = intel_encoder->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; struct drm_display_mode *fixed_mode = NULL; bool has_dpcd; @@ -3629,6 +3630,14 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp, if (!is_edp(intel_dp)) return true; + /* The VDD bit needs a power domain reference, so if the bit is already + * enabled when we boot, grab this reference. */ + if (edp_have_panel_vdd(intel_dp)) { + enum intel_display_power_domain power_domain; + power_domain = intel_display_port_power_domain(intel_encoder); + intel_display_power_get(dev_priv, power_domain); + } + /* Cache DPCD and EDID for edp. */ intel_edp_panel_vdd_on(intel_dp); has_dpcd = intel_dp_get_dpcd(intel_dp); From 763d7f5f2718f085bab5a9e63308349728f3ad12 Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Sun, 20 Apr 2014 00:16:41 +0900 Subject: [PATCH 028/150] perf tests x86: Fix memory leak in sample_ustack() The buf is not freed, when kernel failed to get stack map and return. Signed-off-by: Masanari Iida Link: http://lkml.kernel.org/r/1398091024-7901-1-git-send-email-standby24x7@gmail.com Signed-off-by: Jiri Olsa --- tools/perf/arch/x86/tests/dwarf-unwind.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c index b602ad93ce63..b8c0102c70c8 100644 --- a/tools/perf/arch/x86/tests/dwarf-unwind.c +++ b/tools/perf/arch/x86/tests/dwarf-unwind.c @@ -26,6 +26,7 @@ static int sample_ustack(struct perf_sample *sample, map = map_groups__find(&thread->mg, MAP__FUNCTION, (u64) sp); if (!map) { pr_debug("failed to get stack map\n"); + free(buf); return -1; } From 4dc549e58b6ebf63554cd466d5ceb0e9c70ab859 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sun, 20 Apr 2014 10:50:00 +0200 Subject: [PATCH 029/150] perf tools: Disable libdw unwind for all but x86 arch So far there's only x86 libdw unwind support merged in perf. Disable it on all other architectures in case libdw unwind support is detected in system. Cc: Arnaldo Carvalho de Melo Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jean Pihet Cc: Josh Boyer Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1397988006-14158-1-git-send-email-jolsa@redhat.com Signed-off-by: Jiri Olsa --- tools/perf/config/Makefile | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index ee21fa95ebcf..a71fb395e38f 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -34,6 +34,14 @@ ifeq ($(ARCH),arm) LIBUNWIND_LIBS = -lunwind -lunwind-arm endif +# So far there's only x86 libdw unwind support merged in perf. +# Disable it on all other architectures in case libdw unwind +# support is detected in system. Add supported architectures +# to the check. +ifneq ($(ARCH),x86) + NO_LIBDW_DWARF_UNWIND := 1 +endif + ifeq ($(LIBUNWIND_LIBS),) NO_LIBUNWIND := 1 else From 4508793541140723ab862d83095f6b5141d24e49 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 21 Apr 2014 22:23:46 -0400 Subject: [PATCH 030/150] tools lib traceevent: Fix backward compatibility macros for pevent filter enums The return value for pevent_filter_match() is suppose to return FILTER_NONE if the event doesn't have a filter, and FILTER_NOEXIST if there is no filter at all. But the change 41e12e580a7 "tools lib traceevent: Refactor pevent_filter_match() to get rid of die()" replaced the return value with PEVENT_ERRNO__* values and added "backward compatibility" macros that used the old names. Unfortunately, the NOEXIST and NONE macros were swapped, and this broke users that use the old return names. Signed-off-by: Steven Rostedt Link: http://lkml.kernel.org/r/20140421222346.0351ced4@gandalf.local.home Signed-off-by: Jiri Olsa --- tools/lib/traceevent/event-parse.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h index 791c539374c7..feab94281634 100644 --- a/tools/lib/traceevent/event-parse.h +++ b/tools/lib/traceevent/event-parse.h @@ -876,8 +876,8 @@ struct event_filter { struct event_filter *pevent_filter_alloc(struct pevent *pevent); /* for backward compatibility */ -#define FILTER_NONE PEVENT_ERRNO__FILTER_NOT_FOUND -#define FILTER_NOEXIST PEVENT_ERRNO__NO_FILTER +#define FILTER_NONE PEVENT_ERRNO__NO_FILTER +#define FILTER_NOEXIST PEVENT_ERRNO__FILTER_NOT_FOUND #define FILTER_MISS PEVENT_ERRNO__FILTER_MISS #define FILTER_MATCH PEVENT_ERRNO__FILTER_MATCH From de04f8657de9d3351a2d5880f1f7080b23b798cf Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 22 Apr 2014 19:23:30 -0400 Subject: [PATCH 031/150] tools lib traceevent: Fix memory leak in pretty_print() Commit 12e55569a244 "tools lib traceevent: Use helper trace-seq in print functions like kernel does" added a extra trace_seq helper to process string arguments like the kernel does it. But the difference between the kernel and the userspace library is that the kernel's trace_seq structure has a static allocated buffer. The userspace one has a dynamically allocated one. It requires a trace_seq_destroy(), otherwise it produces a nasty memory leak. Cc: stable@vger.kernel.org # 3.14+ Signed-off-by: Steven Rostedt Link: http://lkml.kernel.org/r/20140422192330.6bb09bf8@gandalf.local.home Signed-off-by: Jiri Olsa --- tools/lib/traceevent/event-parse.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index baec7d887da4..b83184f2d484 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -4344,6 +4344,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event format, len_arg, arg); trace_seq_terminate(&p); trace_seq_puts(s, p.buffer); + trace_seq_destroy(&p); arg = arg->next; break; default: From ae107d06137ce210ea21d1423443d3638599f297 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 22 Apr 2014 20:40:25 +0200 Subject: [PATCH 032/150] dt: Fix binding typos in clock-names and interrupt-names s/interrupts-names/interrupt-names/g s/clocks-names/clock-names/g Some of the binding files and device tree files get this wrong and the kernel won't be able to pick it up. Fix them up now so that they don't get widely used. Signed-off-by: Geert Uytterhoeven Acked-by : Patrice Chotard Signed-off-by: Grant Likely --- .../devicetree/bindings/net/socfpga-dwmac.txt | 2 +- Documentation/devicetree/bindings/net/stmmac.txt | 2 +- .../devicetree/bindings/pinctrl/pinctrl-st.txt | 4 ++-- .../devicetree/bindings/sound/davinci-mcasp-audio.txt | 2 +- arch/arm/boot/dts/am33xx.dtsi | 4 ++-- arch/arm/boot/dts/am4372.dtsi | 4 ++-- arch/arm/boot/dts/stih415-pinctrl.dtsi | 10 +++++----- arch/arm/boot/dts/stih416-pinctrl.dtsi | 10 +++++----- drivers/of/irq.c | 2 +- 9 files changed, 20 insertions(+), 20 deletions(-) diff --git a/Documentation/devicetree/bindings/net/socfpga-dwmac.txt b/Documentation/devicetree/bindings/net/socfpga-dwmac.txt index 636f0ac4e223..2a60cd3e8d5d 100644 --- a/Documentation/devicetree/bindings/net/socfpga-dwmac.txt +++ b/Documentation/devicetree/bindings/net/socfpga-dwmac.txt @@ -23,5 +23,5 @@ gmac0: ethernet@ff700000 { interrupt-names = "macirq"; mac-address = [00 00 00 00 00 00];/* Filled in by U-Boot */ clocks = <&emac_0_clk>; - clocks-names = "stmmaceth"; + clock-names = "stmmaceth"; }; diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt index 80c1fb8bfbb8..a2acd2b26baf 100644 --- a/Documentation/devicetree/bindings/net/stmmac.txt +++ b/Documentation/devicetree/bindings/net/stmmac.txt @@ -33,7 +33,7 @@ Optional properties: - max-frame-size: See ethernet.txt file in the same directory - clocks: If present, the first clock should be the GMAC main clock, further clocks may be specified in derived bindings. -- clocks-names: One name for each entry in the clocks property, the +- clock-names: One name for each entry in the clocks property, the first one should be "stmmaceth". Examples: diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-st.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-st.txt index 4bd5be0e5e7d..26bcb18f4e60 100644 --- a/Documentation/devicetree/bindings/pinctrl/pinctrl-st.txt +++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-st.txt @@ -83,7 +83,7 @@ Example: reg = <0xfe61f080 0x4>; reg-names = "irqmux"; interrupts = ; - interrupts-names = "irqmux"; + interrupt-names = "irqmux"; ranges = <0 0xfe610000 0x5000>; PIO0: gpio@fe610000 { @@ -165,7 +165,7 @@ sdhci0:sdhci@fe810000{ interrupt-parent = <&PIO3>; #interrupt-cells = <2>; interrupts = <3 IRQ_TYPE_LEVEL_HIGH>; /* Interrupt line via PIO3-3 */ - interrupts-names = "card-detect"; + interrupt-names = "card-detect"; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_mmc>; }; diff --git a/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.txt b/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.txt index 569b26c4a81e..60ca07996458 100644 --- a/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.txt +++ b/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.txt @@ -47,7 +47,7 @@ mcasp0: mcasp0@1d00000 { reg = <0x100000 0x3000>; reg-names "mpu"; interrupts = <82>, <83>; - interrupts-names = "tx", "rx"; + interrupt-names = "tx", "rx"; op-mode = <0>; /* MCASP_IIS_MODE */ tdm-slots = <2>; serial-dir = < diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi index 9770e35f2536..3bce3c9dbd24 100644 --- a/arch/arm/boot/dts/am33xx.dtsi +++ b/arch/arm/boot/dts/am33xx.dtsi @@ -802,7 +802,7 @@ mcasp0: mcasp@48038000 { <0x46000000 0x400000>; reg-names = "mpu", "dat"; interrupts = <80>, <81>; - interrupts-names = "tx", "rx"; + interrupt-names = "tx", "rx"; status = "disabled"; dmas = <&edma 8>, <&edma 9>; @@ -816,7 +816,7 @@ mcasp1: mcasp@4803C000 { <0x46400000 0x400000>; reg-names = "mpu", "dat"; interrupts = <82>, <83>; - interrupts-names = "tx", "rx"; + interrupt-names = "tx", "rx"; status = "disabled"; dmas = <&edma 10>, <&edma 11>; diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi index 36d523a26831..d1f8707ff1df 100644 --- a/arch/arm/boot/dts/am4372.dtsi +++ b/arch/arm/boot/dts/am4372.dtsi @@ -691,7 +691,7 @@ mcasp0: mcasp@48038000 { <0x46000000 0x400000>; reg-names = "mpu", "dat"; interrupts = <80>, <81>; - interrupts-names = "tx", "rx"; + interrupt-names = "tx", "rx"; status = "disabled"; dmas = <&edma 8>, <&edma 9>; @@ -705,7 +705,7 @@ mcasp1: mcasp@4803C000 { <0x46400000 0x400000>; reg-names = "mpu", "dat"; interrupts = <82>, <83>; - interrupts-names = "tx", "rx"; + interrupt-names = "tx", "rx"; status = "disabled"; dmas = <&edma 10>, <&edma 11>; diff --git a/arch/arm/boot/dts/stih415-pinctrl.dtsi b/arch/arm/boot/dts/stih415-pinctrl.dtsi index f09fb10a3791..81df870e5ee6 100644 --- a/arch/arm/boot/dts/stih415-pinctrl.dtsi +++ b/arch/arm/boot/dts/stih415-pinctrl.dtsi @@ -49,7 +49,7 @@ pin-controller-sbc { reg = <0xfe61f080 0x4>; reg-names = "irqmux"; interrupts = ; - interrupts-names = "irqmux"; + interrupt-names = "irqmux"; ranges = <0 0xfe610000 0x5000>; PIO0: gpio@fe610000 { @@ -187,7 +187,7 @@ pin-controller-front { reg = <0xfee0f080 0x4>; reg-names = "irqmux"; interrupts = ; - interrupts-names = "irqmux"; + interrupt-names = "irqmux"; ranges = <0 0xfee00000 0x8000>; PIO5: gpio@fee00000 { @@ -282,7 +282,7 @@ pin-controller-rear { reg = <0xfe82f080 0x4>; reg-names = "irqmux"; interrupts = ; - interrupts-names = "irqmux"; + interrupt-names = "irqmux"; ranges = <0 0xfe820000 0x8000>; PIO13: gpio@fe820000 { @@ -423,7 +423,7 @@ pin-controller-left { reg = <0xfd6bf080 0x4>; reg-names = "irqmux"; interrupts = ; - interrupts-names = "irqmux"; + interrupt-names = "irqmux"; ranges = <0 0xfd6b0000 0x3000>; PIO100: gpio@fd6b0000 { @@ -460,7 +460,7 @@ pin-controller-right { reg = <0xfd33f080 0x4>; reg-names = "irqmux"; interrupts = ; - interrupts-names = "irqmux"; + interrupt-names = "irqmux"; ranges = <0 0xfd330000 0x5000>; PIO103: gpio@fd330000 { diff --git a/arch/arm/boot/dts/stih416-pinctrl.dtsi b/arch/arm/boot/dts/stih416-pinctrl.dtsi index aeea304086eb..250d5ecc951e 100644 --- a/arch/arm/boot/dts/stih416-pinctrl.dtsi +++ b/arch/arm/boot/dts/stih416-pinctrl.dtsi @@ -53,7 +53,7 @@ pin-controller-sbc { reg = <0xfe61f080 0x4>; reg-names = "irqmux"; interrupts = ; - interrupts-names = "irqmux"; + interrupt-names = "irqmux"; ranges = <0 0xfe610000 0x6000>; PIO0: gpio@fe610000 { @@ -201,7 +201,7 @@ pin-controller-front { reg = <0xfee0f080 0x4>; reg-names = "irqmux"; interrupts = ; - interrupts-names = "irqmux"; + interrupt-names = "irqmux"; ranges = <0 0xfee00000 0x10000>; PIO5: gpio@fee00000 { @@ -333,7 +333,7 @@ pin-controller-rear { reg = <0xfe82f080 0x4>; reg-names = "irqmux"; interrupts = ; - interrupts-names = "irqmux"; + interrupt-names = "irqmux"; ranges = <0 0xfe820000 0x6000>; PIO13: gpio@fe820000 { @@ -461,7 +461,7 @@ pin-controller-fvdp-fe { reg = <0xfd6bf080 0x4>; reg-names = "irqmux"; interrupts = ; - interrupts-names = "irqmux"; + interrupt-names = "irqmux"; ranges = <0 0xfd6b0000 0x3000>; PIO100: gpio@fd6b0000 { @@ -498,7 +498,7 @@ pin-controller-fvdp-lite { reg = <0xfd33f080 0x4>; reg-names = "irqmux"; interrupts = ; - interrupts-names = "irqmux"; + interrupt-names = "irqmux"; ranges = <0 0xfd330000 0x5000>; PIO103: gpio@fd330000 { diff --git a/drivers/of/irq.c b/drivers/of/irq.c index 9bcf2cf19357..e2e4c548a42f 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -364,7 +364,7 @@ int of_irq_to_resource(struct device_node *dev, int index, struct resource *r) memset(r, 0, sizeof(*r)); /* - * Get optional "interrupts-names" property to add a name + * Get optional "interrupt-names" property to add a name * to the resource. */ of_property_read_string_index(dev, "interrupt-names", index, From 58968625c496c2e39545781915dbb848b38bd249 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Thu, 10 Apr 2014 16:47:19 -0700 Subject: [PATCH 033/150] pinctrl: single: Clear pin interrupts enabled by bootloader Since we set up device wake-up interrupts as pinctrl-single interrupts, we now must use the standard request_irq and related functions to manage them. If the pin interrupts are enabled for some pins at boot, the wake-up events can show up as constantly pending at least on omaps and will hang the system unless the related device driver clears the event at the device. To fix this, let's clear the interrupt flags during init, and print out a warning so the board maintainers can update their drivers to do proper request_irq for the driver specific wake-up events. Cc: Haojian Zhuang Cc: Linus Walleij Signed-off-by: Tony Lindgren Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-single.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c index 81075f2a1d3f..2960557bfed9 100644 --- a/drivers/pinctrl/pinctrl-single.c +++ b/drivers/pinctrl/pinctrl-single.c @@ -810,6 +810,7 @@ static const struct pinconf_ops pcs_pinconf_ops = { static int pcs_add_pin(struct pcs_device *pcs, unsigned offset, unsigned pin_pos) { + struct pcs_soc_data *pcs_soc = &pcs->socdata; struct pinctrl_pin_desc *pin; struct pcs_name *pn; int i; @@ -821,6 +822,18 @@ static int pcs_add_pin(struct pcs_device *pcs, unsigned offset, return -ENOMEM; } + if (pcs_soc->irq_enable_mask) { + unsigned val; + + val = pcs->read(pcs->base + offset); + if (val & pcs_soc->irq_enable_mask) { + dev_dbg(pcs->dev, "irq enabled at boot for pin at %lx (%x), clearing\n", + (unsigned long)pcs->res->start + offset, val); + val &= ~pcs_soc->irq_enable_mask; + pcs->write(val, pcs->base + offset); + } + } + pin = &pcs->pins.pa[i]; pn = &pcs->names[i]; sprintf(pn->name, "%lx.%d", From 34ce57e9df7d14b52c7613bb2c190e411ca99186 Mon Sep 17 00:00:00 2001 From: Guido Piasenza Date: Tue, 22 Apr 2014 16:28:03 +0100 Subject: [PATCH 034/150] sh-pfc: r8a7790: Fix definition of IPSR5 The extra entry in the table makes SCIFA0_B, and all peripherals after it, fail. Signed-off-by: Phil Edworthy Acked-by: Laurent Pinchart Signed-off-by: Linus Walleij --- drivers/pinctrl/sh-pfc/pfc-r8a7790.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7790.c b/drivers/pinctrl/sh-pfc/pfc-r8a7790.c index 48093719167a..f5cd3f961808 100644 --- a/drivers/pinctrl/sh-pfc/pfc-r8a7790.c +++ b/drivers/pinctrl/sh-pfc/pfc-r8a7790.c @@ -4794,8 +4794,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { FN_MSIOF0_SCK_B, 0, /* IP5_23_21 [3] */ FN_WE1_N, FN_IERX, FN_CAN1_RX, FN_VI1_G4, - FN_VI1_G4_B, FN_VI2_R6, FN_SCIFA0_CTS_N_B, - FN_IERX_C, 0, + FN_VI1_G4_B, FN_VI2_R6, FN_SCIFA0_CTS_N_B, FN_IERX_C, /* IP5_20_18 [3] */ FN_WE0_N, FN_IECLK, FN_CAN_CLK, FN_VI2_VSYNC_N, FN_SCIFA0_TXD_B, FN_VI2_VSYNC_N_B, 0, 0, From 0c66c5628bbb5e96360032440f53a6cb6f8973d0 Mon Sep 17 00:00:00 2001 From: Phil Edworthy Date: Tue, 22 Apr 2014 17:38:05 +0100 Subject: [PATCH 035/150] sh-pfc: r8a7791: Fix definition of MOD_SEL3 There is a missing 0 entry from the MOD_SEL3 table. Signed-off-by: Phil Edworthy Acked-by: Laurent Pinchart Signed-off-by: Linus Walleij --- drivers/pinctrl/sh-pfc/pfc-r8a7791.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c index 5186d70c49d4..7868bf3a0f91 100644 --- a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c +++ b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c @@ -5288,7 +5288,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { /* SEL_SCIF3 [2] */ FN_SEL_SCIF3_0, FN_SEL_SCIF3_1, FN_SEL_SCIF3_2, FN_SEL_SCIF3_3, /* SEL_IEB [2] */ - FN_SEL_IEB_0, FN_SEL_IEB_1, FN_SEL_IEB_2, + FN_SEL_IEB_0, FN_SEL_IEB_1, FN_SEL_IEB_2, 0, /* SEL_MMC [1] */ FN_SEL_MMC_0, FN_SEL_MMC_1, /* SEL_SCIF5 [1] */ From 9f7ff8931e3c5ddc8535476971ec9501e9555c05 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Wed, 23 Apr 2014 19:04:19 +0200 Subject: [PATCH 036/150] perf/x86: Fix RAPL rdmsrl_safe() usage This patch fixes a bug introduced by: 24223657806a ("perf/x86/intel: Use rdmsrl_safe() when initializing RAPL PMU") The rdmsrl_safe() function returns 0 on success. The current code was failing to detect the RAPL PMU on real hardware (missing /sys/devices/power) because the return value of rdmsrl_safe() was misinterpreted. Signed-off-by: Stephane Eranian Acked-by: Borislav Petkov Acked-by: Venkatesh Srinivas Cc: peterz@infradead.org Cc: zheng.z.yan@intel.com Link: http://lkml.kernel.org/r/20140423170418.GA12767@quad Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_intel_rapl.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c index 7c87424d4140..619f7699487a 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -543,7 +543,8 @@ static int rapl_cpu_prepare(int cpu) if (phys_id < 0) return -1; - if (!rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits)) + /* protect rdmsrl() to handle virtualization */ + if (rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits)) return -1; pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); From cbd75e97a525e3819c02dc18bc2d67aa544c9e45 Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Tue, 15 Apr 2014 18:25:48 +0200 Subject: [PATCH 037/150] drm/vmwgfx: Make sure user-space can't DMA across buffer object boundaries v2 We already check that the buffer object we're accessing is registered with the file. Now also make sure that we can't DMA across buffer object boundaries. v2: Code commenting update. Cc: stable@vger.kernel.org Signed-off-by: Thomas Hellstrom Reviewed-by: Jakob Bornecrantz --- drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 931490b9cfed..87df0b3674fd 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -1214,14 +1214,36 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv, SVGA3dCmdSurfaceDMA dma; } *cmd; int ret; + SVGA3dCmdSurfaceDMASuffix *suffix; + uint32_t bo_size; cmd = container_of(header, struct vmw_dma_cmd, header); + suffix = (SVGA3dCmdSurfaceDMASuffix *)((unsigned long) &cmd->dma + + header->size - sizeof(*suffix)); + + /* Make sure device and verifier stays in sync. */ + if (unlikely(suffix->suffixSize != sizeof(*suffix))) { + DRM_ERROR("Invalid DMA suffix size.\n"); + return -EINVAL; + } + ret = vmw_translate_guest_ptr(dev_priv, sw_context, &cmd->dma.guest.ptr, &vmw_bo); if (unlikely(ret != 0)) return ret; + /* Make sure DMA doesn't cross BO boundaries. */ + bo_size = vmw_bo->base.num_pages * PAGE_SIZE; + if (unlikely(cmd->dma.guest.ptr.offset > bo_size)) { + DRM_ERROR("Invalid DMA offset.\n"); + return -EINVAL; + } + + bo_size -= cmd->dma.guest.ptr.offset; + if (unlikely(suffix->maximumOffset > bo_size)) + suffix->maximumOffset = bo_size; + ret = vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface, user_surface_converter, &cmd->dma.host.sid, NULL); From edd586fe705e819bc711b5ed7194a0b6f9f1a7e1 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 23 Apr 2014 08:54:31 +0100 Subject: [PATCH 038/150] drm/i915: Discard BIOS framebuffers too small to accommodate chosen mode MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If the inherited BIOS framebuffer is smaller than the mode selected for fbdev, then if we continue to use it then we cause display corruption as we do not setup the panel fitter to upscale. Regression from commit d978ef14456a38034f6c0e94a794129501f89200 Author: Jesse Barnes Date: Fri Mar 7 08:57:51 2014 -0800 drm/i915: Wrap the preallocated BIOS framebuffer and preserve for KMS fbcon v12 v2: Add a debug message to track the discard of the BIOS fb. v3: Ville pointed out the difference between ref/unref Reported-by: Knut Petersen Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=77767 Signed-off-by: Chris Wilson Cc: Jesse Barnes Reviewed-by: Daniel Vetter Reviewed-by: Ville Syrjälä Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_fbdev.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index b4d44e62f0c7..fce4a0d93c0b 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -132,6 +132,16 @@ static int intelfb_create(struct drm_fb_helper *helper, mutex_lock(&dev->struct_mutex); + if (intel_fb && + (sizes->fb_width > intel_fb->base.width || + sizes->fb_height > intel_fb->base.height)) { + DRM_DEBUG_KMS("BIOS fb too small (%dx%d), we require (%dx%d)," + " releasing it\n", + intel_fb->base.width, intel_fb->base.height, + sizes->fb_width, sizes->fb_height); + drm_framebuffer_unreference(&intel_fb->base); + intel_fb = ifbdev->fb = NULL; + } if (!intel_fb || WARN_ON(!intel_fb->obj)) { DRM_DEBUG_KMS("no BIOS fb, allocating a new one\n"); ret = intelfb_alloc(helper, sizes); From 0f9dc59db6abc475dc23afc077fabbc606b8830f Mon Sep 17 00:00:00 2001 From: Ben Widawsky Date: Mon, 24 Mar 2014 18:06:00 -0700 Subject: [PATCH 039/150] drm/i915: Allow full PPGTT with param override When PPGTT was disabled by default, the patch also prevented the user from overriding this behavior via module parameter. Being able to test this on arbitrary kernels is extremely beneficial to track down the remaining bugs. The patch that prevented this was: commit 93a25a9e2d67765c3092bfaac9b855d95e39df97 Author: Daniel Vetter Date: Thu Mar 6 09:40:43 2014 +0100 drm/i915: Disable full ppgtt by default By default PPGTT is set to -1. 0 means off, 1 means aliasing only, 2 means full, all other values are reserved. Signed-off-by: Ben Widawsky Signed-off-by: Daniel Vetter Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_gem_gtt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index ab5e93c30aa2..62a5c3627b90 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -50,7 +50,7 @@ bool intel_enable_ppgtt(struct drm_device *dev, bool full) /* Full ppgtt disabled by default for now due to issues. */ if (full) - return false; /* HAS_PPGTT(dev) */ + return HAS_PPGTT(dev) && (i915.enable_ppgtt == 2); else return HAS_ALIASING_PPGTT(dev); } From 2b4c36612efac173397756398000921a7771fdda Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 23 Apr 2014 15:15:32 +0200 Subject: [PATCH 040/150] drm/tegra: restrict plane loops to legacy planes In Matt Ropers primary plane series a set of prep patches like commit af2b653bfb4ef40931b4d101ca842ce0c5da57ef Author: Matt Roper Date: Tue Apr 1 15:22:32 2014 -0700 drm/i915: Restrict plane loops to only operate on overlay planes (v2) ensured that all exisiting users of the mode_config->plane_list wouldn't change behaviour. Unfortunately tegra seems to have fallen through the cracks. Fix it. This regression was introduced in commit e13161af80c185ecd8dc4641d0f5df58f9e3e0af Author: Matt Roper Date: Tue Apr 1 15:22:38 2014 -0700 drm: Add drm_crtc_init_with_planes() (v2) The result was that we've unref'ed the fb for the primary plane twice, leading to a use-after free bug. This is because the drm core will already set crtc->primary->fb to NULL and do the unref for us, and the crtc disable hook is called by the drm crtc helpers for exactly this case. Aside: Now that the fbdev helpers clean up planes there's no longer a need to do this in drivers. So this could probably be nuked entirely in linux-next. Signed-off-by: Daniel Vetter Reviewed-by: Matt Roper Tested-by: Stephen Warren Signed-off-by: Thierry Reding --- drivers/gpu/drm/tegra/dc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c index 36c717af6cf9..edb871d7d395 100644 --- a/drivers/gpu/drm/tegra/dc.c +++ b/drivers/gpu/drm/tegra/dc.c @@ -312,7 +312,7 @@ static void tegra_crtc_disable(struct drm_crtc *crtc) struct drm_device *drm = crtc->dev; struct drm_plane *plane; - list_for_each_entry(plane, &drm->mode_config.plane_list, head) { + drm_for_each_legacy_plane(plane, &drm->mode_config.plane_list) { if (plane->crtc == crtc) { tegra_plane_disable(plane); plane->crtc = NULL; From 82c0f5897a8708dbf7abe08e49efd9a4a8d8cd3a Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 23 Apr 2014 17:57:40 -0500 Subject: [PATCH 041/150] of: selftest: add deferred probe interrupt test Signed-off-by: Rob Herring [grant.likely: fixed failure when root node specifies the interrupt parent] Signed-off-by: Grant Likely --- drivers/of/selftest.c | 32 +++++++++++++++++++ .../of/testcase-data/tests-interrupts.dtsi | 13 ++++++++ 2 files changed, 45 insertions(+) diff --git a/drivers/of/selftest.c b/drivers/of/selftest.c index ae4450070503..fe70b86bcffb 100644 --- a/drivers/of/selftest.c +++ b/drivers/of/selftest.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -427,6 +428,36 @@ static void __init of_selftest_match_node(void) } } +static void __init of_selftest_platform_populate(void) +{ + int irq; + struct device_node *np; + struct platform_device *pdev; + + np = of_find_node_by_path("/testcase-data"); + of_platform_populate(np, of_default_bus_match_table, NULL, NULL); + + /* Test that a missing irq domain returns -EPROBE_DEFER */ + np = of_find_node_by_path("/testcase-data/testcase-device1"); + pdev = of_find_device_by_node(np); + if (!pdev) + selftest(0, "device 1 creation failed\n"); + irq = platform_get_irq(pdev, 0); + if (irq != -EPROBE_DEFER) + selftest(0, "device deferred probe failed - %d\n", irq); + + /* Test that a parsing failure does not return -EPROBE_DEFER */ + np = of_find_node_by_path("/testcase-data/testcase-device2"); + pdev = of_find_device_by_node(np); + if (!pdev) + selftest(0, "device 2 creation failed\n"); + irq = platform_get_irq(pdev, 0); + if (irq >= 0 || irq == -EPROBE_DEFER) + selftest(0, "device parsing error failed - %d\n", irq); + + selftest(1, "passed"); +} + static int __init of_selftest(void) { struct device_node *np; @@ -445,6 +476,7 @@ static int __init of_selftest(void) of_selftest_parse_interrupts(); of_selftest_parse_interrupts_extended(); of_selftest_match_node(); + of_selftest_platform_populate(); pr_info("end of selftest - %i passed, %i failed\n", selftest_results.passed, selftest_results.failed); return 0; diff --git a/drivers/of/testcase-data/tests-interrupts.dtsi b/drivers/of/testcase-data/tests-interrupts.dtsi index c843720bd3e5..da4695f60351 100644 --- a/drivers/of/testcase-data/tests-interrupts.dtsi +++ b/drivers/of/testcase-data/tests-interrupts.dtsi @@ -54,5 +54,18 @@ interrupts-extended0 { <&test_intmap1 1 2>; }; }; + + testcase-device1 { + compatible = "testcase-device"; + interrupt-parent = <&test_intc0>; + interrupts = <1>; + }; + + testcase-device2 { + compatible = "testcase-device"; + interrupt-parent = <&test_intc2>; + interrupts = <1>; /* invalid specifier - too short */ + }; }; + }; From 9ec36cafe43bf835f8f29273597a5b0cbc8267ef Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 23 Apr 2014 17:57:41 -0500 Subject: [PATCH 042/150] of/irq: do irq resolution in platform_get_irq Currently we get the following kind of errors if we try to use interrupt phandles to irqchips that have not yet initialized: irq: no irq domain found for /ocp/pinmux@48002030 ! ------------[ cut here ]------------ WARNING: CPU: 0 PID: 1 at drivers/of/platform.c:171 of_device_alloc+0x144/0x184() Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.12.0-00038-g42a9708 #1012 (show_stack+0x14/0x1c) (dump_stack+0x6c/0xa0) (warn_slowpath_common+0x64/0x84) (warn_slowpath_null+0x1c/0x24) (of_device_alloc+0x144/0x184) (of_platform_device_create_pdata+0x44/0x9c) (of_platform_bus_create+0xd0/0x170) (of_platform_bus_create+0x12c/0x170) (of_platform_populate+0x60/0x98) This is because we're wrongly trying to populate resources that are not yet available. It's perfectly valid to create irqchips dynamically, so let's fix up the issue by resolving the interrupt resources when platform_get_irq is called. And then we also need to accept the fact that some irqdomains do not exist that early on, and only get initialized later on. So we can make the current WARN_ON into just into a pr_debug(). We still attempt to populate irq resources when we create the devices. This allows current drivers which don't use platform_get_irq to continue to function. Once all drivers are fixed, this code can be removed. Suggested-by: Russell King Signed-off-by: Rob Herring Signed-off-by: Tony Lindgren Tested-by: Tony Lindgren Cc: stable@vger.kernel.org # v3.10+ Signed-off-by: Grant Likely --- drivers/base/platform.c | 7 ++++++- drivers/of/irq.c | 26 ++++++++++++++++++++++++++ drivers/of/platform.c | 4 +++- include/linux/of_irq.h | 5 +++++ 4 files changed, 40 insertions(+), 2 deletions(-) diff --git a/drivers/base/platform.c b/drivers/base/platform.c index e714709704e4..5b47210889e0 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -87,7 +88,11 @@ int platform_get_irq(struct platform_device *dev, unsigned int num) return -ENXIO; return dev->archdata.irqs[num]; #else - struct resource *r = platform_get_resource(dev, IORESOURCE_IRQ, num); + struct resource *r; + if (IS_ENABLED(CONFIG_OF_IRQ) && dev->dev.of_node) + return of_irq_get(dev->dev.of_node, num); + + r = platform_get_resource(dev, IORESOURCE_IRQ, num); return r ? r->start : -ENXIO; #endif diff --git a/drivers/of/irq.c b/drivers/of/irq.c index e2e4c548a42f..5aeb89411350 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -379,6 +379,32 @@ int of_irq_to_resource(struct device_node *dev, int index, struct resource *r) } EXPORT_SYMBOL_GPL(of_irq_to_resource); +/** + * of_irq_get - Decode a node's IRQ and return it as a Linux irq number + * @dev: pointer to device tree node + * @index: zero-based index of the irq + * + * Returns Linux irq number on success, or -EPROBE_DEFER if the irq domain + * is not yet created. + * + */ +int of_irq_get(struct device_node *dev, int index) +{ + int rc; + struct of_phandle_args oirq; + struct irq_domain *domain; + + rc = of_irq_parse_one(dev, index, &oirq); + if (rc) + return rc; + + domain = irq_find_host(oirq.np); + if (!domain) + return -EPROBE_DEFER; + + return irq_create_of_mapping(&oirq); +} + /** * of_irq_count - Count the number of IRQs a node uses * @dev: pointer to device tree node diff --git a/drivers/of/platform.c b/drivers/of/platform.c index 404d1daebefa..bd47fbc53dc9 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -168,7 +168,9 @@ struct platform_device *of_device_alloc(struct device_node *np, rc = of_address_to_resource(np, i, res); WARN_ON(rc); } - WARN_ON(of_irq_to_resource_table(np, res, num_irq) != num_irq); + if (of_irq_to_resource_table(np, res, num_irq) != num_irq) + pr_debug("not all legacy IRQ resources mapped for %s\n", + np->name); } dev->dev.of_node = of_node_get(np); diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index 3f23b4472c31..6404253d810d 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -44,11 +44,16 @@ extern void of_irq_init(const struct of_device_id *matches); #ifdef CONFIG_OF_IRQ extern int of_irq_count(struct device_node *dev); +extern int of_irq_get(struct device_node *dev, int index); #else static inline int of_irq_count(struct device_node *dev) { return 0; } +static inline int of_irq_get(struct device_node *dev, int index) +{ + return 0; +} #endif #if defined(CONFIG_OF) From 6e0de817594c61f3b392a9245deeb09609ec707d Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Fri, 25 Apr 2014 10:53:44 +0200 Subject: [PATCH 043/150] s390/bpf,jit: initialize A register if 1st insn is BPF_S_LDX_B_MSH The A register needs to be initialized to zero in the prolog if the first instruction of the BPF program is BPF_S_LDX_B_MSH to prevent leaking the content of %r5 to user space. Cc: Signed-off-by: Martin Schwidefsky --- arch/s390/net/bpf_jit_comp.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 9c36dc398f90..452d3ebd9d0f 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -276,7 +276,6 @@ static void bpf_jit_noleaks(struct bpf_jit *jit, struct sock_filter *filter) case BPF_S_LD_W_IND: case BPF_S_LD_H_IND: case BPF_S_LD_B_IND: - case BPF_S_LDX_B_MSH: case BPF_S_LD_IMM: case BPF_S_LD_MEM: case BPF_S_MISC_TXA: From 1ffa2425bf7cc70f87d5cdbe12175fd4c661dd19 Mon Sep 17 00:00:00 2001 From: Micah Richert Date: Wed, 9 Apr 2014 14:11:31 -0700 Subject: [PATCH 044/150] drm/msm: fix memory leak Signed-off-by: Micah Richert Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/msm_gem.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 3da8264d3039..bb8026daebc9 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -118,8 +118,10 @@ static void put_pages(struct drm_gem_object *obj) if (iommu_present(&platform_bus_type)) drm_gem_put_pages(obj, msm_obj->pages, true, false); - else + else { drm_mm_remove_node(msm_obj->vram_node); + drm_free_large(msm_obj->pages); + } msm_obj->pages = NULL; } From 96673ecbd7f638c0865045377a44f53cd8606850 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Fri, 25 Apr 2014 08:50:08 -0400 Subject: [PATCH 045/150] drm/msm: default to XR24 rather than AR24 Since X11 is going to create an XR24 fb, if the pixel formats do not match then crtc helpers will think it is a full modeset even if mode is the same, which prevents smooth/flickerless handover from fbcon/plymouth to X11. Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/msm_fbdev.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c index 6c6d7d4c9b4e..a752ab83b810 100644 --- a/drivers/gpu/drm/msm/msm_fbdev.c +++ b/drivers/gpu/drm/msm/msm_fbdev.c @@ -62,11 +62,8 @@ static int msm_fbdev_create(struct drm_fb_helper *helper, dma_addr_t paddr; int ret, size; - /* only doing ARGB32 since this is what is needed to alpha-blend - * with video overlays: - */ sizes->surface_bpp = 32; - sizes->surface_depth = 32; + sizes->surface_depth = 24; DBG("create fbdev: %dx%d@%d (%dx%d)", sizes->surface_width, sizes->surface_height, sizes->surface_bpp, From 7d8d9f670513593377cd1442f987ce03a64ba55d Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Tue, 22 Apr 2014 12:27:28 -0400 Subject: [PATCH 046/150] drm/msm/mdp4: cure for the cursor blues (v2) The hw cursor is relatively adept at triggering underflows, which manifest as a "blue flash" (since blue is configured as the underflow color). Juggle a few things around to tighten up the timing for setting cursor registers in DONE irq. And most importantly, don't ever disable the hw cursor. Instead flip it to a blank/empty cursor. This seems far more reliable, as even simply clearing the cursor-enable bit (with no other updates in previous/ following frames) can in some cases cause underflow. v1: original v2: add missing locking spotted by Micah Cc: Micah Richert Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c | 9 +++------ drivers/gpu/drm/msm/mdp/mdp4/mdp4_irq.c | 4 ++-- drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.c | 21 +++++++++++++++++++++ drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h | 4 ++++ drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c | 4 ++-- 5 files changed, 32 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c index 3e6c0f3ed592..ef9957dbac94 100644 --- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c +++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c @@ -510,9 +510,8 @@ static void update_cursor(struct drm_crtc *crtc) MDP4_DMA_CURSOR_BLEND_CONFIG_CURSOR_EN); } else { /* disable cursor: */ - mdp4_write(mdp4_kms, REG_MDP4_DMA_CURSOR_BASE(dma), 0); - mdp4_write(mdp4_kms, REG_MDP4_DMA_CURSOR_BLEND_CONFIG(dma), - MDP4_DMA_CURSOR_BLEND_CONFIG_FORMAT(CURSOR_ARGB)); + mdp4_write(mdp4_kms, REG_MDP4_DMA_CURSOR_BASE(dma), + mdp4_kms->blank_cursor_iova); } /* and drop the iova ref + obj rev when done scanning out: */ @@ -574,11 +573,9 @@ static int mdp4_crtc_cursor_set(struct drm_crtc *crtc, if (old_bo) { /* drop our previous reference: */ - msm_gem_put_iova(old_bo, mdp4_kms->id); - drm_gem_object_unreference_unlocked(old_bo); + drm_flip_work_queue(&mdp4_crtc->unref_cursor_work, old_bo); } - crtc_flush(crtc); request_pending(crtc, PENDING_CURSOR); return 0; diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_irq.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_irq.c index c740ccd1cc67..8edd531cb621 100644 --- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_irq.c +++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_irq.c @@ -70,12 +70,12 @@ irqreturn_t mdp4_irq(struct msm_kms *kms) VERB("status=%08x", status); + mdp_dispatch_irqs(mdp_kms, status); + for (id = 0; id < priv->num_crtcs; id++) if (status & mdp4_crtc_vblank(priv->crtcs[id])) drm_handle_vblank(dev, id); - mdp_dispatch_irqs(mdp_kms, status); - return IRQ_HANDLED; } diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.c index 272e707c9487..0bb4faa17523 100644 --- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.c +++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.c @@ -144,6 +144,10 @@ static void mdp4_preclose(struct msm_kms *kms, struct drm_file *file) static void mdp4_destroy(struct msm_kms *kms) { struct mdp4_kms *mdp4_kms = to_mdp4_kms(to_mdp_kms(kms)); + if (mdp4_kms->blank_cursor_iova) + msm_gem_put_iova(mdp4_kms->blank_cursor_bo, mdp4_kms->id); + if (mdp4_kms->blank_cursor_bo) + drm_gem_object_unreference(mdp4_kms->blank_cursor_bo); kfree(mdp4_kms); } @@ -372,6 +376,23 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev) goto fail; } + mutex_lock(&dev->struct_mutex); + mdp4_kms->blank_cursor_bo = msm_gem_new(dev, SZ_16K, MSM_BO_WC); + mutex_unlock(&dev->struct_mutex); + if (IS_ERR(mdp4_kms->blank_cursor_bo)) { + ret = PTR_ERR(mdp4_kms->blank_cursor_bo); + dev_err(dev->dev, "could not allocate blank-cursor bo: %d\n", ret); + mdp4_kms->blank_cursor_bo = NULL; + goto fail; + } + + ret = msm_gem_get_iova(mdp4_kms->blank_cursor_bo, mdp4_kms->id, + &mdp4_kms->blank_cursor_iova); + if (ret) { + dev_err(dev->dev, "could not pin blank-cursor bo: %d\n", ret); + goto fail; + } + return kms; fail: diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h index 66a4d31aec80..715520c54cde 100644 --- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h +++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h @@ -44,6 +44,10 @@ struct mdp4_kms { struct clk *lut_clk; struct mdp_irq error_handler; + + /* empty/blank cursor bo to use when cursor is "disabled" */ + struct drm_gem_object *blank_cursor_bo; + uint32_t blank_cursor_iova; }; #define to_mdp4_kms(x) container_of(x, struct mdp4_kms, base) diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c index 353d494a497f..f2b985bc2adf 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c @@ -71,11 +71,11 @@ static void mdp5_irq_mdp(struct mdp_kms *mdp_kms) VERB("status=%08x", status); + mdp_dispatch_irqs(mdp_kms, status); + for (id = 0; id < priv->num_crtcs; id++) if (status & mdp5_crtc_vblank(priv->crtcs[id])) drm_handle_vblank(dev, id); - - mdp_dispatch_irqs(mdp_kms, status); } irqreturn_t mdp5_irq(struct msm_kms *kms) From 3ff04a160a891e56cdcee5c198d4c764d1c8c78b Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 24 Apr 2014 12:03:17 +0200 Subject: [PATCH 047/150] drm/i915: Don't WARN nor handle unexpected hpd interrupts on gmch platforms The status bits are unconditionally set, the control bits only enable the actual interrupt generation. Which means if we get some random other interrupts we'll bogusly complain about them. So restrict the WARN to platforms with a sane hotplug interrupt handling scheme. And even more important also don't attempt to process the hpd bit since we've detected a storm already. Instead just clear the bit silently. This WARN has been introduced in commit b8f102e8bf71cacf33326360fdf9dcfd1a63925b Author: Egbert Eich Date: Fri Jul 26 14:14:24 2013 +0200 drm/i915: Add messages useful for HPD storm detection debugging (v2) before that we silently handled the hpd event and so partially defeated the storm detection. v2: Pimp commit message (Jani) Cc: Jani Nikula Cc: Egbert Eich Cc: bitlord Reported-by: bitlord Cc: stable@vger.kernel.org Signed-off-by: Daniel Vetter Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_irq.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 7753249b3a95..f98ba4e6e70b 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -1362,10 +1362,20 @@ static inline void intel_hpd_irq_handler(struct drm_device *dev, spin_lock(&dev_priv->irq_lock); for (i = 1; i < HPD_NUM_PINS; i++) { - WARN_ONCE(hpd[i] & hotplug_trigger && - dev_priv->hpd_stats[i].hpd_mark == HPD_DISABLED, - "Received HPD interrupt (0x%08x) on pin %d (0x%08x) although disabled\n", - hotplug_trigger, i, hpd[i]); + if (hpd[i] & hotplug_trigger && + dev_priv->hpd_stats[i].hpd_mark == HPD_DISABLED) { + /* + * On GMCH platforms the interrupt mask bits only + * prevent irq generation, not the setting of the + * hotplug bits itself. So only WARN about unexpected + * interrupts on saner platforms. + */ + WARN_ONCE(INTEL_INFO(dev)->gen >= 5 && !IS_VALLEYVIEW(dev), + "Received HPD interrupt (0x%08x) on pin %d (0x%08x) although disabled\n", + hotplug_trigger, i, hpd[i]); + + continue; + } if (!(hpd[i] & hotplug_trigger) || dev_priv->hpd_stats[i].hpd_mark != HPD_ENABLED) From 78f2975eec9faff353a6194e854d3d39907bab68 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 2 Apr 2014 16:36:07 +0100 Subject: [PATCH 048/150] drm/i915: Move all ring resets before setting the HWS page In commit a51435a3137ad8ae75c288c39bd2d8b2696bae8f Author: Naresh Kumar Kachhi Date: Wed Mar 12 16:39:40 2014 +0530 drm/i915: disable rings before HW status page setup we reordered stopping the rings to do so before we set the HWS register. However, there is an extra workaround for g45 to reset the rings twice, and for consistency we should apply that workaround before setting the HWS to be sure that the rings are truly stopped. Reference: http://lkml.kernel.org/r/20140423202248.GA3621@amd.pavel.ucw.cz Tested-by: Pavel Machek Cc: Naresh Kumar Kachhi Signed-off-by: Chris Wilson Reviewed-by: Jesse Barnes Signed-off-by: Daniel Vetter Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_reg.h | 1 + drivers/gpu/drm/i915/intel_ringbuffer.c | 54 ++++++++++++++++--------- drivers/gpu/drm/i915/intel_ringbuffer.h | 1 + 3 files changed, 36 insertions(+), 20 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 9f5b18d9d885..c77af69c2d8f 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -827,6 +827,7 @@ enum punit_power_well { # define MI_FLUSH_ENABLE (1 << 12) # define ASYNC_FLIP_PERF_DISABLE (1 << 14) # define MODE_IDLE (1 << 9) +# define STOP_RING (1 << 8) #define GEN6_GT_MODE 0x20d0 #define GEN7_GT_MODE 0x7008 diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 6bc68bdcf433..79fb4cc2137c 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -437,32 +437,41 @@ static void ring_setup_phys_status_page(struct intel_ring_buffer *ring) I915_WRITE(HWS_PGA, addr); } +static bool stop_ring(struct intel_ring_buffer *ring) +{ + struct drm_i915_private *dev_priv = to_i915(ring->dev); + + if (!IS_GEN2(ring->dev)) { + I915_WRITE_MODE(ring, _MASKED_BIT_ENABLE(STOP_RING)); + if (wait_for_atomic((I915_READ_MODE(ring) & MODE_IDLE) != 0, 1000)) { + DRM_ERROR("%s :timed out trying to stop ring\n", ring->name); + return false; + } + } + + I915_WRITE_CTL(ring, 0); + I915_WRITE_HEAD(ring, 0); + ring->write_tail(ring, 0); + + if (!IS_GEN2(ring->dev)) { + (void)I915_READ_CTL(ring); + I915_WRITE_MODE(ring, _MASKED_BIT_DISABLE(STOP_RING)); + } + + return (I915_READ_HEAD(ring) & HEAD_ADDR) == 0; +} + static int init_ring_common(struct intel_ring_buffer *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_gem_object *obj = ring->obj; int ret = 0; - u32 head; gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL); - /* Stop the ring if it's running. */ - I915_WRITE_CTL(ring, 0); - I915_WRITE_HEAD(ring, 0); - ring->write_tail(ring, 0); - if (wait_for_atomic((I915_READ_MODE(ring) & MODE_IDLE) != 0, 1000)) - DRM_ERROR("%s :timed out trying to stop ring\n", ring->name); - - if (I915_NEED_GFX_HWS(dev)) - intel_ring_setup_status_page(ring); - else - ring_setup_phys_status_page(ring); - - head = I915_READ_HEAD(ring) & HEAD_ADDR; - - /* G45 ring initialization fails to reset head to zero */ - if (head != 0) { + if (!stop_ring(ring)) { + /* G45 ring initialization often fails to reset head to zero */ DRM_DEBUG_KMS("%s head not reset to zero " "ctl %08x head %08x tail %08x start %08x\n", ring->name, @@ -471,9 +480,7 @@ static int init_ring_common(struct intel_ring_buffer *ring) I915_READ_TAIL(ring), I915_READ_START(ring)); - I915_WRITE_HEAD(ring, 0); - - if (I915_READ_HEAD(ring) & HEAD_ADDR) { + if (!stop_ring(ring)) { DRM_ERROR("failed to set %s head to zero " "ctl %08x head %08x tail %08x start %08x\n", ring->name, @@ -481,9 +488,16 @@ static int init_ring_common(struct intel_ring_buffer *ring) I915_READ_HEAD(ring), I915_READ_TAIL(ring), I915_READ_START(ring)); + ret = -EIO; + goto out; } } + if (I915_NEED_GFX_HWS(dev)) + intel_ring_setup_status_page(ring); + else + ring_setup_phys_status_page(ring); + /* Initialize the ring. This must happen _after_ we've cleared the ring * registers with the above sequence (the readback of the HEAD registers * also enforces ordering), otherwise the hw might lose the new ring diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 270a6a973438..2b91c4b4d34b 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -34,6 +34,7 @@ struct intel_hw_status_page { #define I915_WRITE_IMR(ring, val) I915_WRITE(RING_IMR((ring)->mmio_base), val) #define I915_READ_MODE(ring) I915_READ(RING_MI_MODE((ring)->mmio_base)) +#define I915_WRITE_MODE(ring, val) I915_WRITE(RING_MI_MODE((ring)->mmio_base), val) enum intel_ring_hangcheck_action { HANGCHECK_IDLE = 0, From 4e4468fac4381b92eb333d94256e7fb8350f3de3 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 25 Apr 2014 11:46:04 +0100 Subject: [PATCH 049/150] ARM: KVM: disable KVM in Kconfig on big-endian systems KVM currently crashes and burns on big-endian hosts, so don't allow it to be selected until we've got that fixed. Cc: Marc Zyngier Signed-off-by: Will Deacon Signed-off-by: Christoffer Dall --- arch/arm/kvm/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig index 466bd299b1a8..4be5bb150bdd 100644 --- a/arch/arm/kvm/Kconfig +++ b/arch/arm/kvm/Kconfig @@ -23,7 +23,7 @@ config KVM select HAVE_KVM_CPU_RELAX_INTERCEPT select KVM_MMIO select KVM_ARM_HOST - depends on ARM_VIRT_EXT && ARM_LPAE + depends on ARM_VIRT_EXT && ARM_LPAE && !CPU_BIG_ENDIAN ---help--- Support hosting virtualized guest machines. You will also need to select one or more of the processor modules below. From 79465d2fd48e68940c2bdecddbdecd45bbba06fe Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Mon, 28 Apr 2014 11:05:43 +0930 Subject: [PATCH 050/150] module: remove warning about waiting module removal. We remove the waiting module removal in commit 3f2b9c9cdf38 (September 2013), but it turns out that modprobe in kmod (< version 16) was asking for waiting module removal. No one noticed since modprobe would check for 0 usage immediately before trying to remove the module, and the race is unlikely. However, it means that anyone running old (but not ancient) kmod versions is hitting the printk designed to see if anyone was running "rmmod -w". All reports so far have been false positives, so remove the warning. Fixes: 3f2b9c9cdf389e303b2273679af08aab5f153517 Reported-by: Valerio Vanni Cc: Elliott, Robert (Server Storage) Cc: stable@kernel.org Acked-by: Lucas De Marchi Signed-off-by: Rusty Russell --- kernel/module.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/kernel/module.c b/kernel/module.c index 11869408f79b..ae7821898bf2 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -815,9 +815,6 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, return -EFAULT; name[MODULE_NAME_LEN-1] = '\0'; - if (!(flags & O_NONBLOCK)) - pr_warn("waiting module removal not supported: please upgrade\n"); - if (mutex_lock_interruptible(&module_mutex) != 0) return -EINTR; From 28ea3c7529388c1e4177336a0e655c6c7272fd1c Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Sun, 27 Apr 2014 18:10:43 -0400 Subject: [PATCH 051/150] powerpc: Export flush_icache_range Commit aac416fc38c (lkdtm: flush icache and report actions) calls flush_icache_range from a module. It's exported on most architectures that implement it, but not on powerpc. This patch exports it to fix the module link failure. Signed-off-by: Jeff Mahoney Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/ppc_ksyms.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index 3bd77edd7610..450850a49dce 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -120,6 +120,7 @@ EXPORT_SYMBOL(giveup_spe); EXPORT_SYMBOL(flush_instruction_cache); #endif EXPORT_SYMBOL(flush_dcache_range); +EXPORT_SYMBOL(flush_icache_range); #ifdef CONFIG_SMP #ifdef CONFIG_PPC32 From 4fb8d027dca0236c811272d342cf185569d91311 Mon Sep 17 00:00:00 2001 From: Li Zhong Date: Mon, 28 Apr 2014 08:29:51 +0800 Subject: [PATCH 052/150] powerpc: Fix Oops in rtas_stop_self() commit 41dd03a9 may cause Oops in rtas_stop_self(). The reason is that the rtas_args was moved into stack space. For a box with more that 4GB RAM, the stack could easily be outside 32bit range, but RTAS is 32bit. So the patch moves rtas_args away from stack by adding static before it. Signed-off-by: Li Zhong Signed-off-by: Anton Blanchard Cc: stable@vger.kernel.org # 3.14+ Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/hotplug-cpu.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 9b8e05078a63..20d62975856f 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -88,13 +88,14 @@ void set_default_offline_state(int cpu) static void rtas_stop_self(void) { - struct rtas_args args = { - .token = cpu_to_be32(rtas_stop_self_token), + static struct rtas_args args = { .nargs = 0, .nret = 1, .rets = &args.args[0], }; + args.token = cpu_to_be32(rtas_stop_self_token); + local_irq_disable(); BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE); From ba9a32b176c31ec4d3d7314bb2e529a85423f7a4 Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Thu, 24 Apr 2014 16:55:33 +0930 Subject: [PATCH 053/150] powerpc/powernv: Fix sysparam sysfs error handling When a sysparam query in OPAL returned a negative value (error code), sysfs would spew out a decent chunk of memory; almost 64K more than expected. This was traced to a sign/unsigned mix up in the OPAL sysparam sysfs code at sys_param_show. The return value of sys_param_show is a ssize_t, calculated using return ret ? ret : attr->param_size; Alan Modra explains: "attr->param_size" is an unsigned int, "ret" an int, so the overall expression has type unsigned int. Result is that ret is cast to unsigned int before being cast to ssize_t. Instead of using the ternary operator, set ret to the param_size if an error is not detected. The same bug exists in the sysfs write callback; this patch fixes it in the same way. A note on debugging this next time: on my system gcc will warn about this if compiled with -Wsign-compare, which is not enabled by -Wall, only -Wextra. Signed-off-by: Joel Stanley Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/opal-sysparam.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c index 6b614726baf2..a51ea189aec3 100644 --- a/arch/powerpc/platforms/powernv/opal-sysparam.c +++ b/arch/powerpc/platforms/powernv/opal-sysparam.c @@ -121,9 +121,10 @@ static ssize_t sys_param_show(struct kobject *kobj, memcpy(buf, param_data_buf, attr->param_size); + ret = attr->param_size; out: mutex_unlock(&opal_sysparam_mutex); - return ret ? ret : attr->param_size; + return ret; } static ssize_t sys_param_store(struct kobject *kobj, @@ -138,7 +139,9 @@ static ssize_t sys_param_store(struct kobject *kobj, ret = opal_set_sys_param(attr->param_id, attr->param_size, param_data_buf); mutex_unlock(&opal_sysparam_mutex); - return ret ? ret : count; + if (!ret) + ret = count; + return ret; } void __init opal_sys_param_init(void) From b8569d230416c490065098684adf13c1751cb830 Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Thu, 24 Apr 2014 16:55:34 +0930 Subject: [PATCH 054/150] powerpc/powernv: Use ssize_t for sysparam return values The OPAL calls are returning int64_t values, which the sysparam code stores in an int, and the sysfs callback returns ssize_t. Make code a easier to read by consistently using ssize_t. Signed-off-by: Joel Stanley Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/opal-sysparam.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c index a51ea189aec3..0675e1a90b40 100644 --- a/arch/powerpc/platforms/powernv/opal-sysparam.c +++ b/arch/powerpc/platforms/powernv/opal-sysparam.c @@ -39,10 +39,11 @@ struct param_attr { struct kobj_attribute kobj_attr; }; -static int opal_get_sys_param(u32 param_id, u32 length, void *buffer) +static ssize_t opal_get_sys_param(u32 param_id, u32 length, void *buffer) { struct opal_msg msg; - int ret, token; + ssize_t ret; + int token; token = opal_async_get_token_interruptible(); if (token < 0) { @@ -59,7 +60,7 @@ static int opal_get_sys_param(u32 param_id, u32 length, void *buffer) ret = opal_async_wait_response(token, &msg); if (ret) { - pr_err("%s: Failed to wait for the async response, %d\n", + pr_err("%s: Failed to wait for the async response, %zd\n", __func__, ret); goto out_token; } @@ -111,7 +112,7 @@ static ssize_t sys_param_show(struct kobject *kobj, { struct param_attr *attr = container_of(kobj_attr, struct param_attr, kobj_attr); - int ret; + ssize_t ret; mutex_lock(&opal_sysparam_mutex); ret = opal_get_sys_param(attr->param_id, attr->param_size, @@ -132,7 +133,7 @@ static ssize_t sys_param_store(struct kobject *kobj, { struct param_attr *attr = container_of(kobj_attr, struct param_attr, kobj_attr); - int ret; + ssize_t ret; mutex_lock(&opal_sysparam_mutex); memcpy(param_data_buf, buf, count); From 85390378f0a6abf3bdb10c3d504d77862a2d0ec9 Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Thu, 24 Apr 2014 16:55:35 +0930 Subject: [PATCH 055/150] powerpc/powernv: Check sysfs size before copying The sysparam code currently uses the userspace supplied number of bytes when memcpy()ing in to a local 64-byte buffer. Limit the maximum number of bytes by the size of the buffer. Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/opal-sysparam.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c index 0675e1a90b40..83f5f2a1c563 100644 --- a/arch/powerpc/platforms/powernv/opal-sysparam.c +++ b/arch/powerpc/platforms/powernv/opal-sysparam.c @@ -135,6 +135,10 @@ static ssize_t sys_param_store(struct kobject *kobj, kobj_attr); ssize_t ret; + /* MAX_PARAM_DATA_LEN is sizeof(param_data_buf) */ + if (count > MAX_PARAM_DATA_LEN) + count = MAX_PARAM_DATA_LEN; + mutex_lock(&opal_sysparam_mutex); memcpy(param_data_buf, buf, count); ret = opal_set_sys_param(attr->param_id, attr->param_size, From 16003d235bdb4d1ebcecfe4915c6e6d8c95f4a0c Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Thu, 24 Apr 2014 16:55:36 +0930 Subject: [PATCH 056/150] powerpc/powernv: Fix typos in sysparam code Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/opal-sysparam.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c index 83f5f2a1c563..c59e77a84721 100644 --- a/arch/powerpc/platforms/powernv/opal-sysparam.c +++ b/arch/powerpc/platforms/powernv/opal-sysparam.c @@ -222,13 +222,13 @@ void __init opal_sys_param_init(void) } if (of_property_read_u32_array(sysparam, "param-len", size, count)) { - pr_err("SYSPARAM: Missing propery param-len in the DT\n"); + pr_err("SYSPARAM: Missing property param-len in the DT\n"); goto out_free_perm; } if (of_property_read_u8_array(sysparam, "param-perm", perm, count)) { - pr_err("SYSPARAM: Missing propery param-perm in the DT\n"); + pr_err("SYSPARAM: Missing property param-perm in the DT\n"); goto out_free_perm; } From 63aecfb20a6629f1ca91d7a052f87988ceb6dd53 Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Thu, 24 Apr 2014 16:55:37 +0930 Subject: [PATCH 057/150] powerpc/powernv: Check sysparam size before creation The size of the sysparam sysfs files is determined from the device tree at boot. However the buffer is hard coded to 64 bytes. If we encounter a parameter that is larger than 64, or miss-parse the device tree, the buffer will overflow when reading or writing to the parameter. Check it at discovery time, and if the parameter is too large, do not create a sysfs entry for it. Signed-off-by: Joel Stanley Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/opal-sysparam.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c index c59e77a84721..d202f9bc3683 100644 --- a/arch/powerpc/platforms/powernv/opal-sysparam.c +++ b/arch/powerpc/platforms/powernv/opal-sysparam.c @@ -241,6 +241,12 @@ void __init opal_sys_param_init(void) /* For each of the parameters, populate the parameter attributes */ for (i = 0; i < count; i++) { + if (size[i] > MAX_PARAM_DATA_LEN) { + pr_warn("SYSPARAM: Not creating parameter %d as size " + "exceeds buffer length\n", i); + continue; + } + sysfs_attr_init(&attr[i].kobj_attr.attr); attr[i].param_id = id[i]; attr[i].param_size = size[i]; From 298b34d7d578c3b4325248b823f3d83a8ea1541c Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 24 Apr 2014 16:14:25 +1000 Subject: [PATCH 058/150] powerpc/powernv: Fix kexec races going back to OPAL We have a subtle race when sending CPUs back to OPAL on kexec. We mark them as "in real mode" right before we send them down. Once we've booted the new kernel, it might try to call opal_reinit_cpus() to change endianness, and that requires all CPUs to be spinning inside OPAL. However there is no synchronization here and we've observed cases where the returning CPUs hadn't established their new state inside OPAL before opal_reinit_cpus() is called, causing it to fail. The proper fix is to actually wait for them to go down all the way from the kexec'ing kernel. Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/setup.c | 48 ++++++++++++++++++++++++-- 1 file changed, 46 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 61cf8fa9c61b..8723d32632f5 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -162,18 +162,62 @@ static void pnv_shutdown(void) } #ifdef CONFIG_KEXEC +static void pnv_kexec_wait_secondaries_down(void) +{ + int my_cpu, i, notified = -1; + + my_cpu = get_cpu(); + + for_each_online_cpu(i) { + uint8_t status; + int64_t rc; + + if (i == my_cpu) + continue; + + for (;;) { + rc = opal_query_cpu_status(get_hard_smp_processor_id(i), + &status); + if (rc != OPAL_SUCCESS || status != OPAL_THREAD_STARTED) + break; + barrier(); + if (i != notified) { + printk(KERN_INFO "kexec: waiting for cpu %d " + "(physical %d) to enter OPAL\n", + i, paca[i].hw_cpu_id); + notified = i; + } + } + } +} + static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) { xics_kexec_teardown_cpu(secondary); - /* Return secondary CPUs to firmware on OPAL v3 */ - if (firmware_has_feature(FW_FEATURE_OPALv3) && secondary) { + /* On OPAL v3, we return all CPUs to firmware */ + + if (!firmware_has_feature(FW_FEATURE_OPALv3)) + return; + + if (secondary) { + /* Return secondary CPUs to firmware on OPAL v3 */ mb(); get_paca()->kexec_state = KEXEC_STATE_REAL_MODE; mb(); /* Return the CPU to OPAL */ opal_return_cpu(); + } else if (crash_shutdown) { + /* + * On crash, we don't wait for secondaries to go + * down as they might be unreachable or hung, so + * instead we just wait a bit and move on. + */ + mdelay(1); + } else { + /* Primary waits for the secondaries to have reached OPAL */ + pnv_kexec_wait_secondaries_down(); } } #endif /* CONFIG_KEXEC */ From cc146d1db0673396429ce4f906350d684ef4ca2a Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Thu, 24 Apr 2014 07:25:34 +1000 Subject: [PATCH 059/150] powerpc/powernv: Fix little endian issues in OPAL flash code With this patch I was able to update firmware on an LE kernel. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/opal-flash.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c index 714ef972406b..a968fd1888b3 100644 --- a/arch/powerpc/platforms/powernv/opal-flash.c +++ b/arch/powerpc/platforms/powernv/opal-flash.c @@ -131,11 +131,15 @@ static DEFINE_MUTEX(image_data_mutex); */ static inline void opal_flash_validate(void) { - struct validate_flash_t *args_buf = &validate_flash_data; + long ret; + void *buf = validate_flash_data.buf; + __be32 size, result; - args_buf->status = opal_validate_flash(__pa(args_buf->buf), - &(args_buf->buf_size), - &(args_buf->result)); + ret = opal_validate_flash(__pa(buf), &size, &result); + + validate_flash_data.status = ret; + validate_flash_data.buf_size = be32_to_cpu(size); + validate_flash_data.result = be32_to_cpu(result); } /* From 3f28c5af3964c11e61e9a58df77cae5ebdb8209e Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Wed, 23 Apr 2014 10:26:32 +0800 Subject: [PATCH 060/150] powerpc/powernv: Reduce multi-hit of iommu_add_device() During the EEH hotplug event, iommu_add_device() will be invoked three times and two of them will trigger warning or error. The three times to invoke the iommu_add_device() are: pci_device_add ... set_iommu_table_base_and_group <- 1st time, fail device_add ... tce_iommu_bus_notifier <- 2nd time, succees pcibios_add_pci_devices ... pcibios_setup_bus_devices <- 3rd time, re-attach The first time fails, since the dev->kobj->sd is not initialized. The dev->kobj->sd is initialized in device_add(). The third time's warning is triggered by the re-attach of the iommu_group. After applying this patch, the error iommu_tce: 0003:05:00.0 has not been added, ret=-14 and the warning [ 204.123609] ------------[ cut here ]------------ [ 204.123645] WARNING: at arch/powerpc/kernel/iommu.c:1125 [ 204.123680] Modules linked in: xt_CHECKSUM nf_conntrack_netbios_ns nf_conntrack_broadcast ipt_MASQUERADE ip6t_REJECT bnep bluetooth 6lowpan_iphc rfkill xt_conntrack ebtable_nat ebtable_broute bridge stp llc mlx4_ib ib_sa ib_mad ib_core ib_addr ebtable_filter ebtables ip6table_nat nf_conntrack_ipv6 nf_defrag_ipv6 nf_nat_ipv6 ip6table_mangle ip6table_security ip6table_raw ip6table_filter ip6_tables iptable_nat nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_nat nf_conntrack iptable_mangle iptable_security iptable_raw bnx2x tg3 mlx4_core nfsd ptp mdio ses libcrc32c nfs_acl enclosure be2net pps_core shpchp lockd kvm uinput sunrpc binfmt_misc lpfc scsi_transport_fc ipr scsi_tgt [ 204.124356] CPU: 18 PID: 650 Comm: eehd Not tainted 3.14.0-rc5yw+ #102 [ 204.124400] task: c0000027ed485670 ti: c0000027ed50c000 task.ti: c0000027ed50c000 [ 204.124453] NIP: c00000000003cf80 LR: c00000000006c648 CTR: c00000000006c5c0 [ 204.124506] REGS: c0000027ed50f440 TRAP: 0700 Not tainted (3.14.0-rc5yw+) [ 204.124558] MSR: 9000000000029032 CR: 88008084 XER: 20000000 [ 204.124682] CFAR: c00000000006c644 SOFTE: 1 GPR00: c00000000006c648 c0000027ed50f6c0 c000000001398380 c0000027ec260300 GPR04: c0000027ea92c000 c00000000006ad00 c0000000016e41b0 0000000000000110 GPR08: c0000000012cd4c0 0000000000000001 c0000027ec2602ff 0000000000000062 GPR12: 0000000028008084 c00000000fdca200 c0000000000d1d90 c0000027ec281a80 GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR20: 0000000000000000 0000000000000000 0000000000000000 0000000000000001 GPR24: 000000005342697b 0000000000002906 c000001fe6ac9800 c000001fe6ac9800 GPR28: 0000000000000000 c0000000016e3a80 c0000027ea92c090 c0000027ea92c000 [ 204.125353] NIP [c00000000003cf80] .iommu_add_device+0x30/0x1f0 [ 204.125399] LR [c00000000006c648] .pnv_pci_ioda_dma_dev_setup+0x88/0xb0 [ 204.125443] Call Trace: [ 204.125464] [c0000027ed50f6c0] [c0000027ed50f750] 0xc0000027ed50f750 (unreliable) [ 204.125526] [c0000027ed50f750] [c00000000006c648] .pnv_pci_ioda_dma_dev_setup+0x88/0xb0 [ 204.125588] [c0000027ed50f7d0] [c000000000069cc8] .pnv_pci_dma_dev_setup+0x78/0x340 [ 204.125650] [c0000027ed50f870] [c000000000044408] .pcibios_setup_device+0x88/0x2f0 [ 204.125712] [c0000027ed50f940] [c000000000046040] .pcibios_setup_bus_devices+0x60/0xd0 [ 204.125774] [c0000027ed50f9c0] [c000000000043acc] .pcibios_add_pci_devices+0xdc/0x1c0 [ 204.125837] [c0000027ed50fa50] [c00000000086f970] .eeh_reset_device+0x36c/0x4f0 [ 204.125939] [c0000027ed50fb20] [c00000000003a2d8] .eeh_handle_normal_event+0x448/0x480 [ 204.126068] [c0000027ed50fbc0] [c00000000003a35c] .eeh_handle_event+0x4c/0x340 [ 204.126192] [c0000027ed50fc80] [c00000000003a74c] .eeh_event_handler+0xfc/0x1b0 [ 204.126319] [c0000027ed50fd30] [c0000000000d1ea0] .kthread+0x110/0x130 [ 204.126430] [c0000027ed50fe30] [c00000000000a460] .ret_from_kernel_thread+0x5c/0x7c [ 204.126556] Instruction dump: [ 204.126610] 7c0802a6 fba1ffe8 fbc1fff0 fbe1fff8 f8010010 f821ff71 7c7e1b78 60000000 [ 204.126787] 60000000 e87e0298 3143ffff 7d2a1910 <0b090000> 2fa90000 40de00c8 ebfe0218 [ 204.126966] ---[ end trace 6e7aefd80add2973 ]--- are cleared. This patch removes iommu_add_device() in pnv_pci_ioda_dma_dev_setup(), which revert part of the change in commit d905c5df(PPC: POWERNV: move iommu_add_device earlier). Signed-off-by: Wei Yang Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/pci-ioda.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 3b2b4fb3585b..1d992f137c48 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -462,7 +462,7 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev pe = &phb->ioda.pe_array[pdn->pe_number]; WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops); - set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table); + set_iommu_table_base(&pdev->dev, &pe->tce32_table); } static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb, From 4966bfa1b3347ee75e6d93859a2e8ce9a662390c Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Wed, 23 Apr 2014 10:26:33 +0800 Subject: [PATCH 061/150] powerpc/powernv: Release the refcount for pci_dev On PowerNV platform, we are holding an unnecessary refcount on a pci_dev, which leads to the pci_dev is not destroyed when hotplugging a pci device. This patch release the unnecessary refcount. Signed-off-by: Wei Yang Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/pci-ioda.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 1d992f137c48..98824aa99173 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -343,7 +343,6 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe) pci_name(dev)); continue; } - pci_dev_get(dev); pdn->pcidev = dev; pdn->pe_number = pe->pe_number; pe->dma_weight += pnv_ioda_dma_weight(dev); From 2bad742388d23c15f2cb355bb992046e30065a11 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 22 Apr 2014 15:01:22 +1000 Subject: [PATCH 062/150] powerpc/powernv: Use uint64_t instead of size_t in OPAL APIs Using size_t in our APIs is asking for trouble, especially when some OPAL calls use size_t pointers. Signed-off-by: Anton Blanchard Reviewed-by: Stewart Smith Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/opal.h | 12 ++++++------ arch/powerpc/platforms/powernv/opal-elog.c | 2 +- 2 files changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index a2efdaa020b0..2a34485f7e0a 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -858,8 +858,8 @@ int64_t opal_lpc_write(uint32_t chip_id, enum OpalLPCAddressType addr_type, int64_t opal_lpc_read(uint32_t chip_id, enum OpalLPCAddressType addr_type, uint32_t addr, __be32 *data, uint32_t sz); -int64_t opal_read_elog(uint64_t buffer, size_t size, uint64_t log_id); -int64_t opal_get_elog_size(uint64_t *log_id, size_t *size, uint64_t *elog_type); +int64_t opal_read_elog(uint64_t buffer, uint64_t size, uint64_t log_id); +int64_t opal_get_elog_size(uint64_t *log_id, uint64_t *size, uint64_t *elog_type); int64_t opal_write_elog(uint64_t buffer, uint64_t size, uint64_t offset); int64_t opal_send_ack_elog(uint64_t log_id); void opal_resend_pending_logs(void); @@ -874,13 +874,13 @@ int64_t opal_dump_read(uint32_t dump_id, uint64_t buffer); int64_t opal_dump_ack(uint32_t dump_id); int64_t opal_dump_resend_notification(void); -int64_t opal_get_msg(uint64_t buffer, size_t size); -int64_t opal_check_completion(uint64_t buffer, size_t size, uint64_t token); +int64_t opal_get_msg(uint64_t buffer, uint64_t size); +int64_t opal_check_completion(uint64_t buffer, uint64_t size, uint64_t token); int64_t opal_sync_host_reboot(void); int64_t opal_get_param(uint64_t token, uint32_t param_id, uint64_t buffer, - size_t length); + uint64_t length); int64_t opal_set_param(uint64_t token, uint32_t param_id, uint64_t buffer, - size_t length); + uint64_t length); int64_t opal_sensor_read(uint32_t sensor_hndl, int token, __be32 *sensor_data); /* Internal functions */ diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c index ef7bc2a97862..7e3821e611a8 100644 --- a/arch/powerpc/platforms/powernv/opal-elog.c +++ b/arch/powerpc/platforms/powernv/opal-elog.c @@ -238,7 +238,7 @@ static struct elog_obj *create_elog_obj(uint64_t id, size_t size, uint64_t type) static void elog_work_fn(struct work_struct *work) { - size_t elog_size; + uint64_t elog_size; uint64_t log_id; uint64_t elog_type; int rc; From e2c8b93e65935498d9bd419cec900221ace70c5b Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 22 Apr 2014 15:01:23 +1000 Subject: [PATCH 063/150] powerpc/powernv: Remove some OPAL function declaration duplication We had some duplication of the internal OPAL functions. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/opal.h | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 2a34485f7e0a..cb7d52ed86d2 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -884,7 +884,8 @@ int64_t opal_set_param(uint64_t token, uint32_t param_id, uint64_t buffer, int64_t opal_sensor_read(uint32_t sensor_hndl, int token, __be32 *sensor_data); /* Internal functions */ -extern int early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data); +extern int early_init_dt_scan_opal(unsigned long node, const char *uname, + int depth, void *data); extern int early_init_dt_scan_recoverable_ranges(unsigned long node, const char *uname, int depth, void *data); @@ -893,10 +894,6 @@ extern int opal_put_chars(uint32_t vtermno, const char *buf, int total_len); extern void hvc_opal_init_early(void); -/* Internal functions */ -extern int early_init_dt_scan_opal(unsigned long node, const char *uname, - int depth, void *data); - extern int opal_notifier_register(struct notifier_block *nb); extern int opal_notifier_unregister(struct notifier_block *nb); @@ -906,9 +903,6 @@ extern void opal_notifier_enable(void); extern void opal_notifier_disable(void); extern void opal_notifier_update_evt(uint64_t evt_mask, uint64_t evt_val); -extern int opal_get_chars(uint32_t vtermno, char *buf, int count); -extern int opal_put_chars(uint32_t vtermno, const char *buf, int total_len); - extern int __opal_async_get_token(void); extern int opal_async_get_token_interruptible(void); extern int __opal_async_release_token(int token); @@ -916,8 +910,6 @@ extern int opal_async_release_token(int token); extern int opal_async_wait_response(uint64_t token, struct opal_msg *msg); extern int opal_get_sensor_data(u32 sensor_hndl, u32 *sensor_data); -extern void hvc_opal_init_early(void); - struct rtc_time; extern int opal_set_rtc_time(struct rtc_time *tm); extern void opal_get_rtc_time(struct rtc_time *tm); From 56b4c993124d15f3b198cc757ba49a0022b5d695 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 22 Apr 2014 15:01:24 +1000 Subject: [PATCH 064/150] powerpc/powernv: Fix little endian issues with opal_do_notifier calls The bitmap in opal_poll_events and opal_handle_interrupt is big endian, so we need to byteswap it on little endian builds. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/opal.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 49d2f00019e5..17cfc70082aa 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -242,14 +242,14 @@ void opal_notifier_update_evt(uint64_t evt_mask, void opal_notifier_enable(void) { int64_t rc; - uint64_t evt = 0; + __be64 evt = 0; atomic_set(&opal_notifier_hold, 0); /* Process pending events */ rc = opal_poll_events(&evt); if (rc == OPAL_SUCCESS && evt) - opal_do_notifier(evt); + opal_do_notifier(be64_to_cpu(evt)); } void opal_notifier_disable(void) @@ -529,7 +529,7 @@ static irqreturn_t opal_interrupt(int irq, void *data) opal_handle_interrupt(virq_to_hw(irq), &events); - opal_do_notifier(events); + opal_do_notifier(be64_to_cpu(events)); return IRQ_HANDLED; } From 14ad0c58d5df6e5911a5413abdc2a9be6a8acb51 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 22 Apr 2014 15:01:25 +1000 Subject: [PATCH 065/150] powerpc/powernv: Fix little endian issues in OPAL error log code Fix little endian issues with the OPAL error log code. Signed-off-by: Anton Blanchard Reviewed-by: Stewart Smith Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/opal.h | 2 +- arch/powerpc/platforms/powernv/opal-elog.c | 9 ++++++++- 2 files changed, 9 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index cb7d52ed86d2..1a752ac8c0ba 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -859,7 +859,7 @@ int64_t opal_lpc_read(uint32_t chip_id, enum OpalLPCAddressType addr_type, uint32_t addr, __be32 *data, uint32_t sz); int64_t opal_read_elog(uint64_t buffer, uint64_t size, uint64_t log_id); -int64_t opal_get_elog_size(uint64_t *log_id, uint64_t *size, uint64_t *elog_type); +int64_t opal_get_elog_size(__be64 *log_id, __be64 *size, __be64 *elog_type); int64_t opal_write_elog(uint64_t buffer, uint64_t size, uint64_t offset); int64_t opal_send_ack_elog(uint64_t log_id); void opal_resend_pending_logs(void); diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c index 7e3821e611a8..10268c41d830 100644 --- a/arch/powerpc/platforms/powernv/opal-elog.c +++ b/arch/powerpc/platforms/powernv/opal-elog.c @@ -238,18 +238,25 @@ static struct elog_obj *create_elog_obj(uint64_t id, size_t size, uint64_t type) static void elog_work_fn(struct work_struct *work) { + __be64 size; + __be64 id; + __be64 type; uint64_t elog_size; uint64_t log_id; uint64_t elog_type; int rc; char name[2+16+1]; - rc = opal_get_elog_size(&log_id, &elog_size, &elog_type); + rc = opal_get_elog_size(&id, &size, &type); if (rc != OPAL_SUCCESS) { pr_err("ELOG: Opal log read failed\n"); return; } + elog_size = be64_to_cpu(size); + log_id = be64_to_cpu(id); + elog_type = be64_to_cpu(type); + BUG_ON(elog_size > OPAL_MAX_ERRLOG_SIZE); if (elog_size >= OPAL_MAX_ERRLOG_SIZE) From 3441f04b4b62758a798f9fbbf2047dfedf0329a5 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 22 Apr 2014 15:01:26 +1000 Subject: [PATCH 066/150] powerpc/powernv: Create OPAL sglist helper functions and fix endian issues We have two copies of code that creates an OPAL sg list. Consolidate these into a common set of helpers and fix the endian issues. The flash interface embedded a version number in the num_entries field, whereas the dump interface did did not. Since versioning wasn't added to the flash interface and it is impossible to add this in a backwards compatible way, just remove it. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/opal.h | 14 ++- arch/powerpc/platforms/powernv/opal-dump.c | 81 +-------------- arch/powerpc/platforms/powernv/opal-flash.c | 106 +------------------- arch/powerpc/platforms/powernv/opal.c | 63 ++++++++++++ 4 files changed, 76 insertions(+), 188 deletions(-) diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 1a752ac8c0ba..afb0fedd1214 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -41,14 +41,14 @@ struct opal_takeover_args { * size except the last one in the list to be as well. */ struct opal_sg_entry { - void *data; - long length; + __be64 data; + __be64 length; }; -/* sg list */ +/* SG list */ struct opal_sg_list { - unsigned long num_entries; - struct opal_sg_list *next; + __be64 length; + __be64 next; struct opal_sg_entry entry[]; }; @@ -929,6 +929,10 @@ extern int opal_resync_timebase(void); extern void opal_lpc_init(void); +struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr, + unsigned long vmalloc_size); +void opal_free_sg_list(struct opal_sg_list *sg); + #endif /* __ASSEMBLY__ */ #endif /* __OPAL_H */ diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c index b9827b0d87e4..f0b472427c57 100644 --- a/arch/powerpc/platforms/powernv/opal-dump.c +++ b/arch/powerpc/platforms/powernv/opal-dump.c @@ -209,80 +209,6 @@ static struct kobj_type dump_ktype = { .default_attrs = dump_default_attrs, }; -static void free_dump_sg_list(struct opal_sg_list *list) -{ - struct opal_sg_list *sg1; - while (list) { - sg1 = list->next; - kfree(list); - list = sg1; - } - list = NULL; -} - -static struct opal_sg_list *dump_data_to_sglist(struct dump_obj *dump) -{ - struct opal_sg_list *sg1, *list = NULL; - void *addr; - int64_t size; - - addr = dump->buffer; - size = dump->size; - - sg1 = kzalloc(PAGE_SIZE, GFP_KERNEL); - if (!sg1) - goto nomem; - - list = sg1; - sg1->num_entries = 0; - while (size > 0) { - /* Translate virtual address to physical address */ - sg1->entry[sg1->num_entries].data = - (void *)(vmalloc_to_pfn(addr) << PAGE_SHIFT); - - if (size > PAGE_SIZE) - sg1->entry[sg1->num_entries].length = PAGE_SIZE; - else - sg1->entry[sg1->num_entries].length = size; - - sg1->num_entries++; - if (sg1->num_entries >= SG_ENTRIES_PER_NODE) { - sg1->next = kzalloc(PAGE_SIZE, GFP_KERNEL); - if (!sg1->next) - goto nomem; - - sg1 = sg1->next; - sg1->num_entries = 0; - } - addr += PAGE_SIZE; - size -= PAGE_SIZE; - } - return list; - -nomem: - pr_err("%s : Failed to allocate memory\n", __func__); - free_dump_sg_list(list); - return NULL; -} - -static void sglist_to_phy_addr(struct opal_sg_list *list) -{ - struct opal_sg_list *sg, *next; - - for (sg = list; sg; sg = next) { - next = sg->next; - /* Don't translate NULL pointer for last entry */ - if (sg->next) - sg->next = (struct opal_sg_list *)__pa(sg->next); - else - sg->next = NULL; - - /* Convert num_entries to length */ - sg->num_entries = - sg->num_entries * sizeof(struct opal_sg_entry) + 16; - } -} - static int64_t dump_read_info(uint32_t *id, uint32_t *size, uint32_t *type) { int rc; @@ -314,15 +240,12 @@ static int64_t dump_read_data(struct dump_obj *dump) } /* Generate SG list */ - list = dump_data_to_sglist(dump); + list = opal_vmalloc_to_sg_list(dump->buffer, dump->size); if (!list) { rc = -ENOMEM; goto out; } - /* Translate sg list addr to real address */ - sglist_to_phy_addr(list); - /* First entry address */ addr = __pa(list); @@ -341,7 +264,7 @@ static int64_t dump_read_data(struct dump_obj *dump) __func__, dump->id); /* Free SG list */ - free_dump_sg_list(list); + opal_free_sg_list(list); out: return rc; diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c index a968fd1888b3..dc487ff04704 100644 --- a/arch/powerpc/platforms/powernv/opal-flash.c +++ b/arch/powerpc/platforms/powernv/opal-flash.c @@ -79,9 +79,6 @@ /* XXX: Assume candidate image size is <= 1GB */ #define MAX_IMAGE_SIZE 0x40000000 -/* Flash sg list version */ -#define SG_LIST_VERSION (1UL) - /* Image status */ enum { IMAGE_INVALID, @@ -271,94 +268,12 @@ static ssize_t manage_store(struct kobject *kobj, return count; } -/* - * Free sg list - */ -static void free_sg_list(struct opal_sg_list *list) -{ - struct opal_sg_list *sg1; - while (list) { - sg1 = list->next; - kfree(list); - list = sg1; - } - list = NULL; -} - -/* - * Build candidate image scatter gather list - * - * list format: - * ----------------------------------- - * | VER (8) | Entry length in bytes | - * ----------------------------------- - * | Pointer to next entry | - * ----------------------------------- - * | Address of memory area 1 | - * ----------------------------------- - * | Length of memory area 1 | - * ----------------------------------- - * | ......... | - * ----------------------------------- - * | ......... | - * ----------------------------------- - * | Address of memory area N | - * ----------------------------------- - * | Length of memory area N | - * ----------------------------------- - */ -static struct opal_sg_list *image_data_to_sglist(void) -{ - struct opal_sg_list *sg1, *list = NULL; - void *addr; - int size; - - addr = image_data.data; - size = image_data.size; - - sg1 = kzalloc(PAGE_SIZE, GFP_KERNEL); - if (!sg1) - return NULL; - - list = sg1; - sg1->num_entries = 0; - while (size > 0) { - /* Translate virtual address to physical address */ - sg1->entry[sg1->num_entries].data = - (void *)(vmalloc_to_pfn(addr) << PAGE_SHIFT); - - if (size > PAGE_SIZE) - sg1->entry[sg1->num_entries].length = PAGE_SIZE; - else - sg1->entry[sg1->num_entries].length = size; - - sg1->num_entries++; - if (sg1->num_entries >= SG_ENTRIES_PER_NODE) { - sg1->next = kzalloc(PAGE_SIZE, GFP_KERNEL); - if (!sg1->next) { - pr_err("%s : Failed to allocate memory\n", - __func__); - goto nomem; - } - - sg1 = sg1->next; - sg1->num_entries = 0; - } - addr += PAGE_SIZE; - size -= PAGE_SIZE; - } - return list; -nomem: - free_sg_list(list); - return NULL; -} - /* * OPAL update flash */ static int opal_flash_update(int op) { - struct opal_sg_list *sg, *list, *next; + struct opal_sg_list *list; unsigned long addr; int64_t rc = OPAL_PARAMETER; @@ -368,30 +283,13 @@ static int opal_flash_update(int op) goto flash; } - list = image_data_to_sglist(); + list = opal_vmalloc_to_sg_list(image_data.data, image_data.size); if (!list) goto invalid_img; /* First entry address */ addr = __pa(list); - /* Translate sg list address to absolute */ - for (sg = list; sg; sg = next) { - next = sg->next; - /* Don't translate NULL pointer for last entry */ - if (sg->next) - sg->next = (struct opal_sg_list *)__pa(sg->next); - else - sg->next = NULL; - - /* - * Convert num_entries to version/length format - * to satisfy OPAL. - */ - sg->num_entries = (SG_LIST_VERSION << 56) | - (sg->num_entries * sizeof(struct opal_sg_entry) + 16); - } - pr_alert("FLASH: Image is %u bytes\n", image_data.size); pr_alert("FLASH: Image update requested\n"); pr_alert("FLASH: Image will be updated during system reboot\n"); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 17cfc70082aa..360ad80c754c 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -638,3 +638,66 @@ void opal_shutdown(void) /* Export this so that test modules can use it */ EXPORT_SYMBOL_GPL(opal_invalid_call); + +/* Convert a region of vmalloc memory to an opal sg list */ +struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr, + unsigned long vmalloc_size) +{ + struct opal_sg_list *sg, *first = NULL; + unsigned long i = 0; + + sg = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!sg) + goto nomem; + + first = sg; + + while (vmalloc_size > 0) { + uint64_t data = vmalloc_to_pfn(vmalloc_addr) << PAGE_SHIFT; + uint64_t length = min(vmalloc_size, PAGE_SIZE); + + sg->entry[i].data = cpu_to_be64(data); + sg->entry[i].length = cpu_to_be64(length); + i++; + + if (i >= SG_ENTRIES_PER_NODE) { + struct opal_sg_list *next; + + next = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!next) + goto nomem; + + sg->length = cpu_to_be64( + i * sizeof(struct opal_sg_entry) + 16); + i = 0; + sg->next = cpu_to_be64(__pa(next)); + sg = next; + } + + vmalloc_addr += length; + vmalloc_size -= length; + } + + sg->length = cpu_to_be64(i * sizeof(struct opal_sg_entry) + 16); + + return first; + +nomem: + pr_err("%s : Failed to allocate memory\n", __func__); + opal_free_sg_list(first); + return NULL; +} + +void opal_free_sg_list(struct opal_sg_list *sg) +{ + while (sg) { + uint64_t next = be64_to_cpu(sg->next); + + kfree(sg); + + if (next) + sg = __va(next); + else + sg = NULL; + } +} From 2d6b63bbdd7a649ea17fae19f8bab07d4b292a09 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 22 Apr 2014 15:01:27 +1000 Subject: [PATCH 067/150] powerpc/powernv: Fix little endian issues in OPAL dump code Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/opal.h | 4 ++-- arch/powerpc/platforms/powernv/opal-dump.c | 13 +++++++++---- 2 files changed, 11 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index afb0fedd1214..66ad7a74116f 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -868,8 +868,8 @@ int64_t opal_validate_flash(uint64_t buffer, uint32_t *size, uint32_t *result); int64_t opal_manage_flash(uint8_t op); int64_t opal_update_flash(uint64_t blk_list); int64_t opal_dump_init(uint8_t dump_type); -int64_t opal_dump_info(uint32_t *dump_id, uint32_t *dump_size); -int64_t opal_dump_info2(uint32_t *dump_id, uint32_t *dump_size, uint32_t *dump_type); +int64_t opal_dump_info(__be32 *dump_id, __be32 *dump_size); +int64_t opal_dump_info2(__be32 *dump_id, __be32 *dump_size, __be32 *dump_type); int64_t opal_dump_read(uint32_t dump_id, uint64_t buffer); int64_t opal_dump_ack(uint32_t dump_id); int64_t opal_dump_resend_notification(void); diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c index f0b472427c57..788a1977b9a5 100644 --- a/arch/powerpc/platforms/powernv/opal-dump.c +++ b/arch/powerpc/platforms/powernv/opal-dump.c @@ -209,15 +209,20 @@ static struct kobj_type dump_ktype = { .default_attrs = dump_default_attrs, }; -static int64_t dump_read_info(uint32_t *id, uint32_t *size, uint32_t *type) +static int64_t dump_read_info(uint32_t *dump_id, uint32_t *dump_size, uint32_t *dump_type) { + __be32 id, size, type; int rc; - *type = 0xffffffff; - rc = opal_dump_info2(id, size, type); + type = cpu_to_be32(0xffffffff); + rc = opal_dump_info2(&id, &size, &type); if (rc == OPAL_PARAMETER) - rc = opal_dump_info(id, size); + rc = opal_dump_info(&id, &size); + + *dump_id = be32_to_cpu(id); + *dump_size = be32_to_cpu(size); + *dump_type = be32_to_cpu(type); if (rc) pr_warn("%s: Failed to get dump info (%d)\n", From 29ef7a3e26283606f181000b11e5fd37d73ab98f Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 21 Apr 2014 10:37:36 +0530 Subject: [PATCH 068/150] powerpc/mm: Fix tlbie to add AVAL fields for 64K pages The if condition check was based on a draft ISA doc. Remove the same. Signed-off-by: Aneesh Kumar K.V Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/mm/hash_native_64.c | 38 ++++++++++++++------------------ 1 file changed, 16 insertions(+), 22 deletions(-) diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index 3ea26c25590b..cf1d325eae8b 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -82,17 +82,14 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize) va &= ~((1ul << mmu_psize_defs[apsize].shift) - 1); va |= penc << 12; va |= ssize << 8; - /* Add AVAL part */ - if (psize != apsize) { - /* - * MPSS, 64K base page size and 16MB parge page size - * We don't need all the bits, but rest of the bits - * must be ignored by the processor. - * vpn cover upto 65 bits of va. (0...65) and we need - * 58..64 bits of va. - */ - va |= (vpn & 0xfe); - } + /* + * AVAL bits: + * We don't need all the bits, but rest of the bits + * must be ignored by the processor. + * vpn cover upto 65 bits of va. (0...65) and we need + * 58..64 bits of va. + */ + va |= (vpn & 0xfe); /* AVAL */ va |= 1; /* L */ asm volatile(ASM_FTR_IFCLR("tlbie %0,1", PPC_TLBIE(%1,%0), %2) : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206) @@ -133,17 +130,14 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize) va &= ~((1ul << mmu_psize_defs[apsize].shift) - 1); va |= penc << 12; va |= ssize << 8; - /* Add AVAL part */ - if (psize != apsize) { - /* - * MPSS, 64K base page size and 16MB parge page size - * We don't need all the bits, but rest of the bits - * must be ignored by the processor. - * vpn cover upto 65 bits of va. (0...65) and we need - * 58..64 bits of va. - */ - va |= (vpn & 0xfe); - } + /* + * AVAL bits: + * We don't need all the bits, but rest of the bits + * must be ignored by the processor. + * vpn cover upto 65 bits of va. (0...65) and we need + * 58..64 bits of va. + */ + va |= (vpn & 0xfe); va |= 1; /* L */ asm volatile(".long 0x7c000224 | (%0 << 11) | (1 << 21)" : : "r"(va) : "memory"); From e98bf005d5feafb3a089868420c1f3743d304e14 Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Tue, 15 Apr 2014 10:10:50 -0700 Subject: [PATCH 069/150] powerpc/perf/hv_24x7: Probe errors changed to pr_debug(), padding fixed fixup for "powerpc/perf: Add support for the hv 24x7 interface" Makes the "not enabled" message less awful (and hides it in most cases). Signed-off-by: Cody P Schafer Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/perf/hv-24x7.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index 297c91051413..f5bca73d92b8 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -485,13 +485,13 @@ static int hv_24x7_init(void) struct hv_perf_caps caps; if (!firmware_has_feature(FW_FEATURE_LPAR)) { - pr_info("not a virtualized system, not enabling\n"); + pr_debug("not a virtualized system, not enabling\n"); return -ENODEV; } hret = hv_perf_caps_get(&caps); if (hret) { - pr_info("could not obtain capabilities, error 0x%80lx, not enabling\n", + pr_debug("could not obtain capabilities, not enabling, rc=%ld\n", hret); return -ENODEV; } From 0a8cf9e28c094cd934deaedfd3ec07830f2a63cf Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Tue, 15 Apr 2014 10:10:51 -0700 Subject: [PATCH 070/150] powerpc/perf/hv_gpci: Probe failures use pr_debug(), and padding reduced fixup for "powerpc/perf: Add support for the hv gpci (get performance counter info) interface". Makes the "not enabled" message less awful (and hidden unless debugging). Signed-off-by: Cody P Schafer Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/perf/hv-gpci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c index 278ba7b9c2b5..8fee1dccaaec 100644 --- a/arch/powerpc/perf/hv-gpci.c +++ b/arch/powerpc/perf/hv-gpci.c @@ -273,13 +273,13 @@ static int hv_gpci_init(void) struct hv_perf_caps caps; if (!firmware_has_feature(FW_FEATURE_LPAR)) { - pr_info("not a virtualized system, not enabling\n"); + pr_debug("not a virtualized system, not enabling\n"); return -ENODEV; } hret = hv_perf_caps_get(&caps); if (hret) { - pr_info("could not obtain capabilities, error 0x%80lx, not enabling\n", + pr_debug("could not obtain capabilities, not enabling, rc=%ld\n", hret); return -ENODEV; } From 58a685c2d8f0616b5c6cfa0f7a9f2d081af3c6fd Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Tue, 15 Apr 2014 10:10:52 -0700 Subject: [PATCH 071/150] powerpc/perf/hv-gpci: Make device attr static Signed-off-by: Cody P Schafer Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/perf/hv-gpci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c index 8fee1dccaaec..c9d399a2df82 100644 --- a/arch/powerpc/perf/hv-gpci.c +++ b/arch/powerpc/perf/hv-gpci.c @@ -78,7 +78,7 @@ static ssize_t kernel_version_show(struct device *dev, return sprintf(page, "0x%x\n", COUNTER_INFO_VERSION_CURRENT); } -DEVICE_ATTR_RO(kernel_version); +static DEVICE_ATTR_RO(kernel_version); HV_CAPS_ATTR(version, "0x%x\n"); HV_CAPS_ATTR(ga, "%d\n"); HV_CAPS_ATTR(expanded, "%d\n"); From 78d13166b189ff1741327d748a7f8d73e65d70bd Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Tue, 15 Apr 2014 10:10:53 -0700 Subject: [PATCH 072/150] powerpc/perf/hv-24x7: Use (unsigned long) not (u32) values when calling plpar_hcall_norets() Signed-off-by: Cody P Schafer Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/perf/hv-24x7.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index f5bca73d92b8..3e8f60a1d53f 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -155,14 +155,26 @@ static ssize_t read_offset_data(void *dest, size_t dest_len, return copy_len; } +static unsigned long h_get_24x7_catalog_page_(unsigned long phys_4096, + unsigned long version, + unsigned long index) +{ + pr_devel("h_get_24x7_catalog_page(0x%lx, %lu, %lu)", + phys_4096, + version, + index); + WARN_ON(!IS_ALIGNED(phys_4096, 4096)); + return plpar_hcall_norets(H_GET_24X7_CATALOG_PAGE, + phys_4096, + version, + index); +} + static unsigned long h_get_24x7_catalog_page(char page[static 4096], u32 version, u32 index) { - WARN_ON(!IS_ALIGNED((unsigned long)page, 4096)); - return plpar_hcall_norets(H_GET_24X7_CATALOG_PAGE, - virt_to_phys(page), - version, - index); + return h_get_24x7_catalog_page_(virt_to_phys(page), + version, index); } static ssize_t catalog_read(struct file *filp, struct kobject *kobj, From 1ee9fcc1a021e54454a23b107a47d10fb603508c Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Tue, 15 Apr 2014 10:10:54 -0700 Subject: [PATCH 073/150] powerpc/perf/hv-24x7: Remove [static 4096], sparse chokes on it Signed-off-by: Cody P Schafer Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/perf/hv-24x7.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index 3e8f60a1d53f..95a67f81f22a 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -170,7 +170,7 @@ static unsigned long h_get_24x7_catalog_page_(unsigned long phys_4096, index); } -static unsigned long h_get_24x7_catalog_page(char page[static 4096], +static unsigned long h_get_24x7_catalog_page(char page[], u32 version, u32 index) { return h_get_24x7_catalog_page_(virt_to_phys(page), From bbad3e50e8ed2d48294c141e687d411430cacbcf Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Tue, 15 Apr 2014 10:10:55 -0700 Subject: [PATCH 074/150] powerpc/perf/hv-24x7: Catalog version number is be64, not be32 The catalog version number was changed from a be32 (with proceeding 32bits of padding) to a be64, update the code to treat it as a be64 Signed-off-by: Cody P Schafer Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/perf/hv-24x7.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index 95a67f81f22a..e0766b82e165 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -171,7 +171,7 @@ static unsigned long h_get_24x7_catalog_page_(unsigned long phys_4096, } static unsigned long h_get_24x7_catalog_page(char page[], - u32 version, u32 index) + u64 version, u32 index) { return h_get_24x7_catalog_page_(virt_to_phys(page), version, index); @@ -185,7 +185,7 @@ static ssize_t catalog_read(struct file *filp, struct kobject *kobj, ssize_t ret = 0; size_t catalog_len = 0, catalog_page_len = 0, page_count = 0; loff_t page_offset = 0; - uint32_t catalog_version_num = 0; + uint64_t catalog_version_num = 0; void *page = kmem_cache_alloc(hv_page_cache, GFP_USER); struct hv_24x7_catalog_page_0 *page_0 = page; if (!page) @@ -197,7 +197,7 @@ static ssize_t catalog_read(struct file *filp, struct kobject *kobj, goto e_free; } - catalog_version_num = be32_to_cpu(page_0->version); + catalog_version_num = be64_to_cpu(page_0->version); catalog_page_len = be32_to_cpu(page_0->length); catalog_len = catalog_page_len * 4096; @@ -220,8 +220,9 @@ static ssize_t catalog_read(struct file *filp, struct kobject *kobj, page, 4096, page_offset * 4096); e_free: if (hret) - pr_err("h_get_24x7_catalog_page(ver=%d, page=%lld) failed: rc=%ld\n", - catalog_version_num, page_offset, hret); + pr_err("h_get_24x7_catalog_page(ver=%lld, page=%lld) failed:" + " rc=%ld\n", + catalog_version_num, page_offset, hret); kfree(page); pr_devel("catalog_read: offset=%lld(%lld) count=%zu(%zu) catalog_len=%zu(%zu) => %zd\n", @@ -255,7 +256,7 @@ e_free: \ static DEVICE_ATTR_RO(_name) PAGE_0_ATTR(catalog_version, "%lld\n", - (unsigned long long)be32_to_cpu(page_0->version)); + (unsigned long long)be64_to_cpu(page_0->version)); PAGE_0_ATTR(catalog_len, "%lld\n", (unsigned long long)be32_to_cpu(page_0->length) * 4096); static BIN_ATTR_RO(catalog, 0/* real length varies */); From a2dd5da77f2cc9fc9ff11ea6b699556254e94a6c Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 14 Apr 2014 21:54:05 +1000 Subject: [PATCH 075/150] powerpc: Rename duplicate COMMAND_LINE_SIZE define We have two definitions of COMMAND_LINE_SIZE, one for the kernel and one for the boot wrapper. I assume this is so the boot wrapper can be self sufficient and not rely on kernel headers. Having two defines with the same name is confusing, I just updated the wrong one when trying to bump it. Make the boot wrapper define unique by calling it BOOT_COMMAND_LINE_SIZE. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/boot/main.c | 8 ++++---- arch/powerpc/boot/ops.h | 2 +- arch/powerpc/boot/ps3.c | 4 ++-- 3 files changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/boot/main.c b/arch/powerpc/boot/main.c index a28f02165e97..d367a0aece2a 100644 --- a/arch/powerpc/boot/main.c +++ b/arch/powerpc/boot/main.c @@ -139,18 +139,18 @@ static struct addr_range prep_initrd(struct addr_range vmlinux, void *chosen, * edit the command line passed to vmlinux (by setting /chosen/bootargs). * The buffer is put in it's own section so that tools may locate it easier. */ -static char cmdline[COMMAND_LINE_SIZE] +static char cmdline[BOOT_COMMAND_LINE_SIZE] __attribute__((__section__("__builtin_cmdline"))); static void prep_cmdline(void *chosen) { if (cmdline[0] == '\0') - getprop(chosen, "bootargs", cmdline, COMMAND_LINE_SIZE-1); + getprop(chosen, "bootargs", cmdline, BOOT_COMMAND_LINE_SIZE-1); printf("\n\rLinux/PowerPC load: %s", cmdline); /* If possible, edit the command line */ if (console_ops.edit_cmdline) - console_ops.edit_cmdline(cmdline, COMMAND_LINE_SIZE); + console_ops.edit_cmdline(cmdline, BOOT_COMMAND_LINE_SIZE); printf("\n\r"); /* Put the command line back into the devtree for the kernel */ @@ -174,7 +174,7 @@ void start(void) * built-in command line wasn't set by an external tool */ if ((loader_info.cmdline_len > 0) && (cmdline[0] == '\0')) memmove(cmdline, loader_info.cmdline, - min(loader_info.cmdline_len, COMMAND_LINE_SIZE-1)); + min(loader_info.cmdline_len, BOOT_COMMAND_LINE_SIZE-1)); if (console_ops.open && (console_ops.open() < 0)) exit(); diff --git a/arch/powerpc/boot/ops.h b/arch/powerpc/boot/ops.h index b3218ce451bb..339e041e8dda 100644 --- a/arch/powerpc/boot/ops.h +++ b/arch/powerpc/boot/ops.h @@ -15,7 +15,7 @@ #include "types.h" #include "string.h" -#define COMMAND_LINE_SIZE 512 +#define BOOT_COMMAND_LINE_SIZE 512 #define MAX_PATH_LEN 256 #define MAX_PROP_LEN 256 /* What should this be? */ diff --git a/arch/powerpc/boot/ps3.c b/arch/powerpc/boot/ps3.c index 9954d98871d0..4ec2d86d3c50 100644 --- a/arch/powerpc/boot/ps3.c +++ b/arch/powerpc/boot/ps3.c @@ -47,13 +47,13 @@ BSS_STACK(4096); * The buffer is put in it's own section so that tools may locate it easier. */ -static char cmdline[COMMAND_LINE_SIZE] +static char cmdline[BOOT_COMMAND_LINE_SIZE] __attribute__((__section__("__builtin_cmdline"))); static void prep_cmdline(void *chosen) { if (cmdline[0] == '\0') - getprop(chosen, "bootargs", cmdline, COMMAND_LINE_SIZE-1); + getprop(chosen, "bootargs", cmdline, BOOT_COMMAND_LINE_SIZE-1); else setprop_str(chosen, "bootargs", cmdline); From a5980d064fe292584da73ddd180f4f140f9ab97d Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 14 Apr 2014 21:54:52 +1000 Subject: [PATCH 076/150] powerpc: Bump COMMAND_LINE_SIZE to 2048 I've had a report that the current limit is too small for an automated network based installer. Bump it. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/uapi/asm/setup.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/include/uapi/asm/setup.h b/arch/powerpc/include/uapi/asm/setup.h index 552df83f1a49..ae3fb68cb28e 100644 --- a/arch/powerpc/include/uapi/asm/setup.h +++ b/arch/powerpc/include/uapi/asm/setup.h @@ -1 +1,6 @@ -#include +#ifndef _UAPI_ASM_POWERPC_SETUP_H +#define _UAPI_ASM_POWERPC_SETUP_H + +#define COMMAND_LINE_SIZE 2048 + +#endif /* _UAPI_ASM_POWERPC_SETUP_H */ From 579a53cafdd641f2d67ba4f4fbd9cc4180b8717d Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 14 Apr 2014 21:55:25 +1000 Subject: [PATCH 077/150] powerpc: Bump BOOT_COMMAND_LINE_SIZE to 2048 Bump the boot wrapper BOOT_COMMAND_LINE_SIZE to match the kernel. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/boot/ops.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/boot/ops.h b/arch/powerpc/boot/ops.h index 339e041e8dda..8aad3c55aeda 100644 --- a/arch/powerpc/boot/ops.h +++ b/arch/powerpc/boot/ops.h @@ -15,7 +15,7 @@ #include "types.h" #include "string.h" -#define BOOT_COMMAND_LINE_SIZE 512 +#define BOOT_COMMAND_LINE_SIZE 2048 #define MAX_PATH_LEN 256 #define MAX_PROP_LEN 256 /* What should this be? */ From 0c930692107be4b91c3eeecfd9c9d600039f966f Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 14 Apr 2014 21:23:32 +1000 Subject: [PATCH 078/150] powerpc: Fix error return in rtas_flash module init module_init should return 0 or a negative errno. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/rtas_flash.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index 2f3cdb01506d..658e89d2025b 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -705,7 +705,7 @@ static int __init rtas_flash_init(void) if (rtas_token("ibm,update-flash-64-and-reboot") == RTAS_UNKNOWN_SERVICE) { pr_info("rtas_flash: no firmware flash support\n"); - return 1; + return -EINVAL; } rtas_validate_flash_data.buf = kzalloc(VALIDATE_BUF_SIZE, GFP_KERNEL); From 42dbfc8649737cb622b2a7e02045401c4c09561c Mon Sep 17 00:00:00 2001 From: Li Zhong Date: Thu, 10 Apr 2014 16:25:31 +0800 Subject: [PATCH 079/150] powerpc/pseries: Protect remove_memory() with device hotplug lock While testing memory hot-remove, I found following dead lock: Process #1141 is drmgr, trying to remove some memory, i.e. memory499. It holds the memory_hotplug_mutex, and blocks when trying to remove file "online" under dir memory499, in kernfs_drain(), at wait_event(root->deactivate_waitq, atomic_read(&kn->active) == KN_DEACTIVATED_BIAS); Process #1120 is trying to online memory499 by echo 1 > memory499/online In .kernfs_fop_write, it uses kernfs_get_active() to increase &kn->active, thus blocking process #1141. While itself is blocked later when trying to acquire memory_hotplug_mutex, which is held by process The backtrace of both processes are shown below: [] 0xc000000001b18600 [] .__switch_to+0x144/0x200 [] .online_pages+0x74/0x7b0 [] .memory_subsys_online+0x9c/0x150 [] .device_online+0xb8/0x120 [] .online_store+0xb4/0xc0 [] .dev_attr_store+0x64/0xa0 [] .sysfs_kf_write+0x7c/0xb0 [] .kernfs_fop_write+0x154/0x1e0 [] .vfs_write+0xe0/0x260 [] .SyS_write+0x64/0x110 [] syscall_exit+0x0/0x7c [] 0xc000000001b18600 [] .__switch_to+0x144/0x200 [] .__kernfs_remove+0x204/0x300 [] .kernfs_remove_by_name_ns+0x68/0xf0 [] .sysfs_remove_file_ns+0x38/0x60 [] .device_remove_attrs+0x54/0xc0 [] .device_del+0x158/0x250 [] .device_unregister+0x34/0xa0 [] .unregister_memory_section+0x164/0x170 [] .__remove_pages+0x108/0x4c0 [] .arch_remove_memory+0x60/0xc0 [] .remove_memory+0x8c/0xe0 [] .pseries_remove_memblock+0xd4/0x160 [] .pseries_memory_notifier+0x27c/0x290 [] .notifier_call_chain+0x8c/0x100 [] .__blocking_notifier_call_chain+0x6c/0xe0 [] .of_property_notify+0x7c/0xc0 [] .of_update_property+0x3c/0x1b0 [] .ofdt_write+0x3dc/0x740 [] .proc_reg_write+0xac/0x110 [] .vfs_write+0xe0/0x260 [] .SyS_write+0x64/0x110 [] syscall_exit+0x0/0x7c This patch uses lock_device_hotplug() to protect remove_memory() called in pseries_remove_memblock(), which is also stated before function remove_memory(): * NOTE: The caller must call lock_device_hotplug() to serialize hotplug * and online/offline operations before this call, as required by * try_offline_node(). */ void __ref remove_memory(int nid, u64 start, u64 size) With this lock held, the other process(#1120 above) trying to online the memory block will retry the system call when calling lock_device_hotplug_sysfs(), and finally find No such device error. Signed-off-by: Li Zhong Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/hotplug-memory.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 573b488fc48b..7f75c94af822 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -100,10 +100,10 @@ static int pseries_remove_memblock(unsigned long base, unsigned int memblock_siz start_pfn = base >> PAGE_SHIFT; - if (!pfn_valid(start_pfn)) { - memblock_remove(base, memblock_size); - return 0; - } + lock_device_hotplug(); + + if (!pfn_valid(start_pfn)) + goto out; block_sz = memory_block_size_bytes(); sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE; @@ -114,8 +114,10 @@ static int pseries_remove_memblock(unsigned long base, unsigned int memblock_siz base += MIN_MEMORY_BLOCK_SIZE; } +out: /* Update memory regions for memory remove */ memblock_remove(base, memblock_size); + unlock_device_hotplug(); return 0; } From f203891117323dd31c11adcbba60452c933d604e Mon Sep 17 00:00:00 2001 From: Preeti U Murthy Date: Fri, 11 Apr 2014 16:01:48 +0530 Subject: [PATCH 080/150] ppc/powernv: Set the runlatch bits correctly for offline cpus Up until now we have been setting the runlatch bits for a busy CPU and clearing it when a CPU enters idle state. The runlatch bit has thus been consistent with the utilization of a CPU as long as the CPU is online. However when a CPU is hotplugged out the runlatch bit is not cleared. It needs to be cleared to indicate an unused CPU. Hence this patch has the runlatch bit cleared for an offline CPU just before entering an idle state and sets it immediately after it exits the idle state. Signed-off-by: Preeti U Murthy Acked-by: Paul Mackerras Reviewed-by: Srivatsa S. Bhat Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/smp.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 908672bdcea6..bf5fcd452168 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -30,6 +30,7 @@ #include #include #include +#include #include "powernv.h" @@ -156,7 +157,9 @@ static void pnv_smp_cpu_kill_self(void) */ mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1); while (!generic_check_cpu_restart(cpu)) { + ppc64_runlatch_off(); power7_nap(); + ppc64_runlatch_on(); if (!generic_check_cpu_restart(cpu)) { DBG("CPU%d Unexpected exit while offline !\n", cpu); /* We may be getting an IPI, so we re-enable From fd17dc7b9a8d57150ee0121c4c83edbb7e26eece Mon Sep 17 00:00:00 2001 From: Preeti U Murthy Date: Fri, 11 Apr 2014 16:01:58 +0530 Subject: [PATCH 081/150] ppc/kvm: Set the runlatch bit of a CPU just before starting guest The secondary threads in the core are kept offline before launching guests in kvm on powerpc: "371fefd6f2dc4666:KVM: PPC: Allow book3s_hv guests to use SMT processor modes." Hence their runlatch bits are cleared. When the secondary threads are called in to start a guest, their runlatch bits need to be set to indicate that they are busy. The primary thread has its runlatch bit set though, but there is no harm in setting this bit once again. Hence set the runlatch bit for all threads before they start guest. Signed-off-by: Preeti U Murthy Acked-by: Paul Mackerras Reviewed-by: Srivatsa S. Bhat Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index ffbb871c2bd8..b25407533618 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -242,6 +242,12 @@ kvm_novcpu_exit: */ .globl kvm_start_guest kvm_start_guest: + + /* Set runlatch bit the minute you wake up from nap */ + mfspr r1, SPRN_CTRLF + ori r1, r1, 1 + mtspr SPRN_CTRLT, r1 + ld r2,PACATOC(r13) li r0,KVM_HWTHREAD_IN_KVM From 582b910edafd283dfab78f41f437a92a65ee5103 Mon Sep 17 00:00:00 2001 From: Preeti U Murthy Date: Fri, 11 Apr 2014 16:02:08 +0530 Subject: [PATCH 082/150] ppc/kvm: Clear the runlatch bit of a vcpu before napping When the guest cedes the vcpu or the vcpu has no guest to run it naps. Clear the runlatch bit of the vcpu before napping to indicate an idle cpu. Signed-off-by: Preeti U Murthy Acked-by: Paul Mackerras Reviewed-by: Srivatsa S. Bhat Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index b25407533618..b031f932c0cc 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -315,6 +315,11 @@ kvm_no_guest: li r0, KVM_HWTHREAD_IN_NAP stb r0, HSTATE_HWTHREAD_STATE(r13) kvm_do_nap: + /* Clear the runlatch bit before napping */ + mfspr r2, SPRN_CTRLF + clrrdi r2, r2, 1 + mtspr SPRN_CTRLT, r2 + li r3, LPCR_PECE0 mfspr r4, SPRN_LPCR rlwimi r4, r3, 0, LPCR_PECE0 | LPCR_PECE1 @@ -2005,8 +2010,13 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) /* * Take a nap until a decrementer or external or doobell interrupt - * occurs, with PECE1, PECE0 and PECEDP set in LPCR + * occurs, with PECE1, PECE0 and PECEDP set in LPCR. Also clear the + * runlatch bit before napping. */ + mfspr r2, SPRN_CTRLF + clrrdi r2, r2, 1 + mtspr SPRN_CTRLT, r2 + li r0,1 stb r0,HSTATE_HWTHREAD_REQ(r13) mfspr r5,SPRN_LPCR From e4565362c7adc31201135c4b6d649fc1bdc3bf20 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Tue, 8 Apr 2014 14:20:19 +1000 Subject: [PATCH 083/150] powerpc/4xx: Fix section mismatch in ppc4xx_pci.c This patch fixes this section mismatch: WARNING: vmlinux.o(.text+0x1efc4): Section mismatch in reference from the function apm821xx_pciex_init_port_hw() to the function .init.text:ppc4xx_pciex_wait_on_sdr.isra.9() The function apm821xx_pciex_init_port_hw() references the function __init ppc4xx_pciex_wait_on_sdr.isra.9(). This is often because apm821xx_pciex_init_port_hw lacks a __init annotation or the annotation of ppc4xx_pciex_wait_on_sdr.isra.9 is wrong. apm821xx_pciex_init_port_hw is only referenced by a struct in __initdata, so it should be safe to add __init to apm821xx_pciex_init_port_hw. Signed-off-by: Alistair Popple Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/sysdev/ppc4xx_pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/sysdev/ppc4xx_pci.c b/arch/powerpc/sysdev/ppc4xx_pci.c index 64603a10b863..4914fd3f41ec 100644 --- a/arch/powerpc/sysdev/ppc4xx_pci.c +++ b/arch/powerpc/sysdev/ppc4xx_pci.c @@ -1058,7 +1058,7 @@ static int __init apm821xx_pciex_core_init(struct device_node *np) return 1; } -static int apm821xx_pciex_init_port_hw(struct ppc4xx_pciex_port *port) +static int __init apm821xx_pciex_init_port_hw(struct ppc4xx_pciex_port *port) { u32 val; From 39025ba38278f3003ee538409f7c98970620ef49 Mon Sep 17 00:00:00 2001 From: Oren Twaig Date: Mon, 28 Apr 2014 10:21:37 +0300 Subject: [PATCH 084/150] x86/vsmp: Fix irq routing Correct IRQ routing in case a vSMP box is detected but the Interrupt Routing Comply (IRC) value is set to "comply", which leads to incorrect IRQ routing. Before the patch: When a vSMP box was detected and IRC was set to "comply", users (and the kernel) couldn't effectively set the destination of the IRQs. This is because the hook inside vsmp_64.c always setup all CPUs as the IRQ destination using cpumask_setall() as the return value for IRQ allocation mask. Later, this "overrided" mask caused the kernel to set the IRQ destination to the lowest online CPU in the mask (CPU0 usually). After the patch: When the IRC is set to "comply", users (and the kernel) can control the destination of the IRQs as we will not be changing the default "apic->vector_allocation_domain". Signed-off-by: Oren Twaig Acked-by: Shai Fultheim Link: http://lkml.kernel.org/r/1398669697-2123-1-git-send-email-oren@scalemp.com [ Minor readability edits. ] Signed-off-by: Ingo Molnar --- arch/x86/kernel/vsmp_64.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index f6584a90aba3..5edc34b5b951 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -26,6 +26,9 @@ #define TOPOLOGY_REGISTER_OFFSET 0x10 +/* Flag below is initialized once during vSMP PCI initialization. */ +static int irq_routing_comply = 1; + #if defined CONFIG_PCI && defined CONFIG_PARAVIRT /* * Interrupt control on vSMPowered systems: @@ -101,6 +104,10 @@ static void __init set_vsmp_pv_ops(void) #ifdef CONFIG_SMP if (cap & ctl & BIT(8)) { ctl &= ~BIT(8); + + /* Interrupt routing set to ignore */ + irq_routing_comply = 0; + #ifdef CONFIG_PROC_FS /* Don't let users change irq affinity via procfs */ no_irq_affinity = 1; @@ -218,7 +225,9 @@ static void vsmp_apic_post_init(void) { /* need to update phys_pkg_id */ apic->phys_pkg_id = apicid_phys_pkg_id; - apic->vector_allocation_domain = fill_vector_allocation_domain; + + if (!irq_routing_comply) + apic->vector_allocation_domain = fill_vector_allocation_domain; } void __init vsmp_init(void) From e8e249d78e0600cb892c87992b6c8c9ea3b301ae Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Fri, 21 Feb 2014 18:05:05 +0100 Subject: [PATCH 085/150] kvm: Use pci_enable_msix_exact() instead of pci_enable_msix() As result of deprecation of MSI-X/MSI enablement functions pci_enable_msix() and pci_enable_msi_block() all drivers using these two interfaces need to be updated to use the new pci_enable_msi_range() or pci_enable_msi_exact() and pci_enable_msix_range() or pci_enable_msix_exact() interfaces. Signed-off-by: Alexander Gordeev Cc: Gleb Natapov Cc: Paolo Bonzini Cc: kvm@vger.kernel.org Cc: linux-pci@vger.kernel.org Signed-off-by: Paolo Bonzini --- virt/kvm/assigned-dev.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c index 8db43701016f..bf06577fea51 100644 --- a/virt/kvm/assigned-dev.c +++ b/virt/kvm/assigned-dev.c @@ -395,7 +395,8 @@ static int assigned_device_enable_host_msix(struct kvm *kvm, if (dev->entries_nr == 0) return r; - r = pci_enable_msix(dev->dev, dev->host_msix_entries, dev->entries_nr); + r = pci_enable_msix_exact(dev->dev, + dev->host_msix_entries, dev->entries_nr); if (r) return r; From fe2b201b3be91575857227da7ef21f661bc460b1 Mon Sep 17 00:00:00 2001 From: Bandan Das Date: Mon, 21 Apr 2014 15:20:14 -0400 Subject: [PATCH 086/150] KVM: x86: Check for host supported fields in shadow vmcs We track shadow vmcs fields through two static lists, one for read only and another for r/w fields. However, with addition of new vmcs fields, not all fields may be supported on all hosts. If so, copy_vmcs12_to_shadow() trying to vmwrite on unsupported hosts will result in a vmwrite error. For example, commit 36be0b9deb23161 introduced GUEST_BNDCFGS, which is not supported by all processors. Filter out host unsupported fields before letting guests use shadow vmcs Signed-off-by: Bandan Das Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx.c | 53 +++++++++++++++++++++++++++++++++++----------- 1 file changed, 41 insertions(+), 12 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 1f68c5831924..33e8c028842f 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -503,7 +503,7 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) [number##_HIGH] = VMCS12_OFFSET(name)+4 -static const unsigned long shadow_read_only_fields[] = { +static unsigned long shadow_read_only_fields[] = { /* * We do NOT shadow fields that are modified when L0 * traps and emulates any vmx instruction (e.g. VMPTRLD, @@ -526,10 +526,10 @@ static const unsigned long shadow_read_only_fields[] = { GUEST_LINEAR_ADDRESS, GUEST_PHYSICAL_ADDRESS }; -static const int max_shadow_read_only_fields = +static int max_shadow_read_only_fields = ARRAY_SIZE(shadow_read_only_fields); -static const unsigned long shadow_read_write_fields[] = { +static unsigned long shadow_read_write_fields[] = { GUEST_RIP, GUEST_RSP, GUEST_CR0, @@ -558,7 +558,7 @@ static const unsigned long shadow_read_write_fields[] = { HOST_FS_SELECTOR, HOST_GS_SELECTOR }; -static const int max_shadow_read_write_fields = +static int max_shadow_read_write_fields = ARRAY_SIZE(shadow_read_write_fields); static const unsigned short vmcs_field_to_offset_table[] = { @@ -3009,6 +3009,41 @@ static void free_kvm_area(void) } } +static void init_vmcs_shadow_fields(void) +{ + int i, j; + + /* No checks for read only fields yet */ + + for (i = j = 0; i < max_shadow_read_write_fields; i++) { + switch (shadow_read_write_fields[i]) { + case GUEST_BNDCFGS: + if (!vmx_mpx_supported()) + continue; + break; + default: + break; + } + + if (j < i) + shadow_read_write_fields[j] = + shadow_read_write_fields[i]; + j++; + } + max_shadow_read_write_fields = j; + + /* shadowed fields guest access without vmexit */ + for (i = 0; i < max_shadow_read_write_fields; i++) { + clear_bit(shadow_read_write_fields[i], + vmx_vmwrite_bitmap); + clear_bit(shadow_read_write_fields[i], + vmx_vmread_bitmap); + } + for (i = 0; i < max_shadow_read_only_fields; i++) + clear_bit(shadow_read_only_fields[i], + vmx_vmread_bitmap); +} + static __init int alloc_kvm_area(void) { int cpu; @@ -3039,6 +3074,8 @@ static __init int hardware_setup(void) enable_vpid = 0; if (!cpu_has_vmx_shadow_vmcs()) enable_shadow_vmcs = 0; + if (enable_shadow_vmcs) + init_vmcs_shadow_fields(); if (!cpu_has_vmx_ept() || !cpu_has_vmx_ept_4levels()) { @@ -8803,14 +8840,6 @@ static int __init vmx_init(void) memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE); memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE); - /* shadowed read/write fields */ - for (i = 0; i < max_shadow_read_write_fields; i++) { - clear_bit(shadow_read_write_fields[i], vmx_vmwrite_bitmap); - clear_bit(shadow_read_write_fields[i], vmx_vmread_bitmap); - } - /* shadowed read only fields */ - for (i = 0; i < max_shadow_read_only_fields; i++) - clear_bit(shadow_read_only_fields[i], vmx_vmread_bitmap); /* * Allow direct access to the PC debug port (it is often used for I/O From e32dfbed8cc06aac72528e2bb53067ce02262413 Mon Sep 17 00:00:00 2001 From: Hui Wang Date: Mon, 28 Apr 2014 14:45:00 +0800 Subject: [PATCH 087/150] ALSA: hda - add headset mic detect quirk for a Dell laptop When we plug a 3-ring headset on the Dell machine (VID: 0x10ec0255, SID: 0x10280674), the headset mic can't be detected, after apply this patch, the headset mic can work well. BugLink: https://bugs.launchpad.net/bugs/1297581 Cc: David Henningsson Cc: stable@vger.kernel.org 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 c643dfc0a826..c1952c910339 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4621,6 +4621,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0667, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0668, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0669, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1028, 0x0674, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x067f, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x15cc, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x15cd, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE), From def5f1273c5f18abf8fcaee03a115d3e907ad407 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 27 Apr 2014 21:03:09 -0700 Subject: [PATCH 088/150] linux/interrupt.h: fix new kernel-doc warnings Fix new kernel-doc warnings in : Warning(include/linux/interrupt.h:219): No description found for parameter 'cpumask' Warning(include/linux/interrupt.h:219): Excess function parameter 'mask' description in 'irq_set_affinity' Warning(include/linux/interrupt.h:236): No description found for parameter 'cpumask' Warning(include/linux/interrupt.h:236): Excess function parameter 'mask' description in 'irq_force_affinity' Signed-off-by: Randy Dunlap Link: http://lkml.kernel.org/r/535DD2FD.7030804@infradead.org Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 8834a7e5b944..97ac926c78a7 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -210,7 +210,7 @@ extern int __irq_set_affinity(unsigned int irq, const struct cpumask *cpumask, /** * irq_set_affinity - Set the irq affinity of a given irq * @irq: Interrupt to set affinity - * @mask: cpumask + * @cpumask: cpumask * * Fails if cpumask does not contain an online CPU */ @@ -223,7 +223,7 @@ irq_set_affinity(unsigned int irq, const struct cpumask *cpumask) /** * irq_force_affinity - Force the irq affinity of a given irq * @irq: Interrupt to set affinity - * @mask: cpumask + * @cpumask: cpumask * * Same as irq_set_affinity, but without checking the mask against * online cpus. From 62a08ae2a5763aabeee98264605236b001503e0c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 24 Apr 2014 09:50:53 +0200 Subject: [PATCH 089/150] genirq: x86: Ensure that dynamic irq allocation does not conflict On x86 the allocation of irq descriptors may allocate interrupts which are in the range of the GSI interrupts. That's wrong as those interrupts are hardwired and we don't have the irq domain translation like PPC. So one of these interrupts can be hooked up later to one of the devices which are hard wired to it and the io_apic init code for that particular interrupt line happily reuses that descriptor with a completely different configuration so hell breaks lose. Inside x86 we allocate dynamic interrupts from above nr_gsi_irqs, except for a few usage sites which have not yet blown up in our face for whatever reason. But for drivers which need an irq range, like the GPIO drivers, we have no limit in place and we don't want to expose such a detail to a driver. To cure this introduce a function which an architecture can implement to impose a lower bound on the dynamic interrupt allocations. Implement it for x86 and set the lower bound to nr_gsi_irqs, which is the end of the hardwired interrupt space, so all dynamic allocations happen above. That not only allows the GPIO driver to work sanely, it also protects the bogus callsites of create_irq_nr() in hpet, uv, irq_remapping and htirq code. They need to be cleaned up as well, but that's a separate issue. Reported-by: Jin Yao Signed-off-by: Thomas Gleixner Tested-by: Mika Westerberg Cc: Mathias Nyman Cc: Linus Torvalds Cc: Grant Likely Cc: H. Peter Anvin Cc: Rafael J. Wysocki Cc: Andy Shevchenko Cc: Krogerus Heikki Cc: Linus Walleij Link: http://lkml.kernel.org/r/alpine.DEB.2.02.1404241617360.28206@ionos.tec.linutronix.de Signed-off-by: Thomas Gleixner --- arch/x86/kernel/apic/io_apic.c | 5 +++++ include/linux/irq.h | 2 ++ kernel/irq/irqdesc.c | 7 +++++++ kernel/softirq.c | 5 +++++ 4 files changed, 19 insertions(+) diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 6ad4658de705..d23aa82e7a7b 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -3425,6 +3425,11 @@ int get_nr_irqs_gsi(void) return nr_irqs_gsi; } +unsigned int arch_dynirq_lower_bound(unsigned int from) +{ + return from < nr_irqs_gsi ? nr_irqs_gsi : from; +} + int __init arch_probe_nr_irqs(void) { int nr; diff --git a/include/linux/irq.h b/include/linux/irq.h index 10a0b1ac4ea0..5c57efb863d0 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -603,6 +603,8 @@ static inline u32 irq_get_trigger_type(unsigned int irq) return d ? irqd_get_trigger_type(d) : 0; } +unsigned int arch_dynirq_lower_bound(unsigned int from); + int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, struct module *owner); diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index a7174617616b..bb07f2928f4b 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -363,6 +363,13 @@ __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, if (from > irq) return -EINVAL; from = irq; + } else { + /* + * For interrupts which are freely allocated the + * architecture can force a lower bound to the @from + * argument. x86 uses this to exclude the GSI space. + */ + from = arch_dynirq_lower_bound(from); } mutex_lock(&sparse_irq_lock); diff --git a/kernel/softirq.c b/kernel/softirq.c index b50990a5bea0..33e4648ae0e7 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -779,3 +779,8 @@ int __init __weak arch_early_irq_init(void) { return 0; } + +unsigned int __weak arch_dynirq_lower_bound(unsigned int from) +{ + return from; +} From 5d4e08c45a6cf8f1ab3c7fa375007635ac569165 Mon Sep 17 00:00:00 2001 From: Mark Salter Date: Fri, 28 Mar 2014 14:25:19 +0000 Subject: [PATCH 090/150] arm: KVM: fix possible misalignment of PGDs and bounce page The kvm/mmu code shared by arm and arm64 uses kalloc() to allocate a bounce page (if hypervisor init code crosses page boundary) and hypervisor PGDs. The problem is that kalloc() does not guarantee the proper alignment. In the case of the bounce page, the page sized buffer allocated may also cross a page boundary negating the purpose and leading to a hang during kvm initialization. Likewise the PGDs allocated may not meet the minimum alignment requirements of the underlying MMU. This patch uses __get_free_page() to guarantee the worst case alignment needs of the bounce page and PGDs on both arm and arm64. Cc: # 3.10+ Signed-off-by: Mark Salter Acked-by: Marc Zyngier Signed-off-by: Christoffer Dall --- arch/arm/kvm/mmu.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 80bb1e6c2c29..16f804938b8f 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -42,6 +42,8 @@ static unsigned long hyp_idmap_start; static unsigned long hyp_idmap_end; static phys_addr_t hyp_idmap_vector; +#define pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t)) + #define kvm_pmd_huge(_x) (pmd_huge(_x) || pmd_trans_huge(_x)) static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) @@ -293,14 +295,14 @@ void free_boot_hyp_pgd(void) if (boot_hyp_pgd) { unmap_range(NULL, boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE); unmap_range(NULL, boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE); - kfree(boot_hyp_pgd); + free_pages((unsigned long)boot_hyp_pgd, pgd_order); boot_hyp_pgd = NULL; } if (hyp_pgd) unmap_range(NULL, hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE); - kfree(init_bounce_page); + free_page((unsigned long)init_bounce_page); init_bounce_page = NULL; mutex_unlock(&kvm_hyp_pgd_mutex); @@ -330,7 +332,7 @@ void free_hyp_pgds(void) for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE) unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE); - kfree(hyp_pgd); + free_pages((unsigned long)hyp_pgd, pgd_order); hyp_pgd = NULL; } @@ -1024,7 +1026,7 @@ int kvm_mmu_init(void) size_t len = __hyp_idmap_text_end - __hyp_idmap_text_start; phys_addr_t phys_base; - init_bounce_page = kmalloc(PAGE_SIZE, GFP_KERNEL); + init_bounce_page = (void *)__get_free_page(GFP_KERNEL); if (!init_bounce_page) { kvm_err("Couldn't allocate HYP init bounce page\n"); err = -ENOMEM; @@ -1050,8 +1052,9 @@ int kvm_mmu_init(void) (unsigned long)phys_base); } - hyp_pgd = kzalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL); - boot_hyp_pgd = kzalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL); + hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order); + boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order); + if (!hyp_pgd || !boot_hyp_pgd) { kvm_err("Hyp mode PGD not allocated\n"); err = -ENOMEM; From 5c8818b46e067120d33bbb2f610313240d76ba02 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sat, 26 Apr 2014 03:43:01 -0700 Subject: [PATCH 091/150] MAINTAINERS: co-maintainance of KVM/{arm,arm64} The KVM/{arm,arm64} ports are sharing a lot of code, and are effectively co-maintained (and have been for quite a while). Make the situation official and list the two maintainers for both ports. Cc: Catalin Marinas Cc: Russell King Cc: Paolo Bonzini Cc: Gleb Natapov Signed-off-by: Marc Zyngier Signed-off-by: Christoffer Dall Acked-by: Catalin Marinas Signed-off-by: Paolo Bonzini --- MAINTAINERS | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 6dc67b1fdb50..24815e784905 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5108,14 +5108,19 @@ F: drivers/s390/kvm/ KERNEL VIRTUAL MACHINE (KVM) FOR ARM M: Christoffer Dall +M: Marc Zyngier +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: kvmarm@lists.cs.columbia.edu W: http://systems.cs.columbia.edu/projects/kvm-arm S: Supported F: arch/arm/include/uapi/asm/kvm* F: arch/arm/include/asm/kvm* F: arch/arm/kvm/ +F: virt/kvm/arm/ +F: include/kvm/arm_* KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64) +M: Christoffer Dall M: Marc Zyngier L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: kvmarm@lists.cs.columbia.edu From 91021a6c8ffdc55804dab5acdfc7de4f278b9ac3 Mon Sep 17 00:00:00 2001 From: Haibin Wang Date: Thu, 10 Apr 2014 13:14:32 +0100 Subject: [PATCH 092/150] KVM: ARM: vgic: Fix sgi dispatch problem When dispatch SGI(mode == 0), that is the vcpu of VM should send sgi to the cpu which the target_cpus list. So, there must add the "break" to branch of case 0. Cc: # 3.10+ Signed-off-by: Haibin Wang Acked-by: Marc Zyngier Signed-off-by: Christoffer Dall --- virt/kvm/arm/vgic.c | 1 + 1 file changed, 1 insertion(+) diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index 47b29834a6b6..7e8b44efb739 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -916,6 +916,7 @@ static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg) case 0: if (!target_cpus) return; + break; case 1: target_cpus = ((1 << nrcpus) - 1) & ~(1 << vcpu_id) & 0xff; From 41c22f626254b9dc0376928cae009e73d1b6a49a Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 21 Apr 2014 15:26:01 +0200 Subject: [PATCH 093/150] KVM: async_pf: mm->mm_users can not pin apf->mm get_user_pages(mm) is simply wrong if mm->mm_users == 0 and exit_mmap/etc was already called (or is in progress), mm->mm_count can only pin mm->pgd and mm_struct itself. Change kvm_setup_async_pf/async_pf_execute to inc/dec mm->mm_users. kvm_create_vm/kvm_destroy_vm play with ->mm_count too but this case looks fine at first glance, it seems that this ->mm is only used to verify that current->mm == kvm->mm. Signed-off-by: Oleg Nesterov Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- virt/kvm/async_pf.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 10df100c4514..06e6401d6ef4 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -101,7 +101,7 @@ static void async_pf_execute(struct work_struct *work) if (waitqueue_active(&vcpu->wq)) wake_up_interruptible(&vcpu->wq); - mmdrop(mm); + mmput(mm); kvm_put_kvm(vcpu->kvm); } @@ -118,7 +118,7 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) flush_work(&work->work); #else if (cancel_work_sync(&work->work)) { - mmdrop(work->mm); + mmput(work->mm); kvm_put_kvm(vcpu->kvm); /* == work->vcpu->kvm */ kmem_cache_free(async_pf_cache, work); } @@ -183,7 +183,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva, work->addr = hva; work->arch = *arch; work->mm = current->mm; - atomic_inc(&work->mm->mm_count); + atomic_inc(&work->mm->mm_users); kvm_get_kvm(work->vcpu->kvm); /* this can't really happen otherwise gfn_to_pfn_async @@ -201,7 +201,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva, return 1; retry_sync: kvm_put_kvm(work->vcpu->kvm); - mmdrop(work->mm); + mmput(work->mm); kmem_cache_free(async_pf_cache, work); return 0; } From f2ae85b2ab3776b9e4e42e5b6fa090f40d396794 Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Fri, 11 Apr 2014 00:07:18 +0200 Subject: [PATCH 094/150] KVM: arm/arm64: vgic: fix GICD_ICFGR register accesses Since KVM internally represents the ICFGR registers by stuffing two of them into one word, the offset for accessing the internal representation and the one for the MMIO based access are different. So keep the original offset around, but adjust the internal array offset by one bit. Reported-by: Haibin Wang Signed-off-by: Andre Przywara Signed-off-by: Marc Zyngier Signed-off-by: Christoffer Dall --- virt/kvm/arm/vgic.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index 7e8b44efb739..f9af48c9eb37 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -548,11 +548,10 @@ static bool handle_mmio_cfg_reg(struct kvm_vcpu *vcpu, u32 val; u32 *reg; - offset >>= 1; reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg, - vcpu->vcpu_id, offset); + vcpu->vcpu_id, offset >> 1); - if (offset & 2) + if (offset & 4) val = *reg >> 16; else val = *reg & 0xffff; @@ -561,13 +560,13 @@ static bool handle_mmio_cfg_reg(struct kvm_vcpu *vcpu, vgic_reg_access(mmio, &val, offset, ACCESS_READ_VALUE | ACCESS_WRITE_VALUE); if (mmio->is_write) { - if (offset < 4) { + if (offset < 8) { *reg = ~0U; /* Force PPIs/SGIs to 1 */ return false; } val = vgic_cfg_compress(val); - if (offset & 2) { + if (offset & 4) { *reg &= 0xffff; *reg |= val << 16; } else { From a949ae560a511fe4e3adf48fa44fefded93e5c2b Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Thu, 24 Apr 2014 10:40:12 -0400 Subject: [PATCH 095/150] ftrace/module: Hardcode ftrace_module_init() call into load_module() A race exists between module loading and enabling of function tracer. CPU 1 CPU 2 ----- ----- load_module() module->state = MODULE_STATE_COMING register_ftrace_function() mutex_lock(&ftrace_lock); ftrace_startup() update_ftrace_function(); ftrace_arch_code_modify_prepare() set_all_module_text_rw(); ftrace_arch_code_modify_post_process() set_all_module_text_ro(); [ here all module text is set to RO, including the module that is loading!! ] blocking_notifier_call_chain(MODULE_STATE_COMING); ftrace_init_module() [ tries to modify code, but it's RO, and fails! ftrace_bug() is called] When this race happens, ftrace_bug() will produces a nasty warning and all of the function tracing features will be disabled until reboot. The simple solution is to treate module load the same way the core kernel is treated at boot. To hardcode the ftrace function modification of converting calls to mcount into nops. This is done in init/main.c there's no reason it could not be done in load_module(). This gives a better control of the changes and doesn't tie the state of the module to its notifiers as much. Ftrace is special, it needs to be treated as such. The reason this would work, is that the ftrace_module_init() would be called while the module is in MODULE_STATE_UNFORMED, which is ignored by the set_all_module_text_ro() call. Link: http://lkml.kernel.org/r/1395637826-3312-1-git-send-email-indou.takao@jp.fujitsu.com Reported-by: Takao Indoh Acked-by: Rusty Russell Cc: stable@vger.kernel.org # 2.6.38+ Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 2 ++ kernel/module.c | 3 +++ kernel/trace/ftrace.c | 27 ++++----------------------- 3 files changed, 9 insertions(+), 23 deletions(-) diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 9212b017bc72..ae9504b4b67d 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -535,6 +535,7 @@ static inline int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_a extern int ftrace_arch_read_dyn_info(char *buf, int size); extern int skip_trace(unsigned long ip); +extern void ftrace_module_init(struct module *mod); extern void ftrace_disable_daemon(void); extern void ftrace_enable_daemon(void); @@ -544,6 +545,7 @@ static inline int ftrace_force_update(void) { return 0; } static inline void ftrace_disable_daemon(void) { } static inline void ftrace_enable_daemon(void) { } static inline void ftrace_release_mod(struct module *mod) {} +static inline void ftrace_module_init(struct module *mod) {} static inline __init int register_ftrace_command(struct ftrace_func_command *cmd) { return -EINVAL; diff --git a/kernel/module.c b/kernel/module.c index 11869408f79b..5f14fec9f825 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3271,6 +3271,9 @@ static int load_module(struct load_info *info, const char __user *uargs, dynamic_debug_setup(info->debug, info->num_debug); + /* Ftrace init must be called in the MODULE_STATE_UNFORMED state */ + ftrace_module_init(mod); + /* Finally it's fully formed, ready to start executing. */ err = complete_formation(mod, info); if (err) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 1fd4b9479210..4a54a25afa2f 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4330,16 +4330,11 @@ static void ftrace_init_module(struct module *mod, ftrace_process_locs(mod, start, end); } -static int ftrace_module_notify_enter(struct notifier_block *self, - unsigned long val, void *data) +void ftrace_module_init(struct module *mod) { - struct module *mod = data; - - if (val == MODULE_STATE_COMING) - ftrace_init_module(mod, mod->ftrace_callsites, - mod->ftrace_callsites + - mod->num_ftrace_callsites); - return 0; + ftrace_init_module(mod, mod->ftrace_callsites, + mod->ftrace_callsites + + mod->num_ftrace_callsites); } static int ftrace_module_notify_exit(struct notifier_block *self, @@ -4353,11 +4348,6 @@ static int ftrace_module_notify_exit(struct notifier_block *self, return 0; } #else -static int ftrace_module_notify_enter(struct notifier_block *self, - unsigned long val, void *data) -{ - return 0; -} static int ftrace_module_notify_exit(struct notifier_block *self, unsigned long val, void *data) { @@ -4365,11 +4355,6 @@ static int ftrace_module_notify_exit(struct notifier_block *self, } #endif /* CONFIG_MODULES */ -struct notifier_block ftrace_module_enter_nb = { - .notifier_call = ftrace_module_notify_enter, - .priority = INT_MAX, /* Run before anything that can use kprobes */ -}; - struct notifier_block ftrace_module_exit_nb = { .notifier_call = ftrace_module_notify_exit, .priority = INT_MIN, /* Run after anything that can remove kprobes */ @@ -4403,10 +4388,6 @@ void __init ftrace_init(void) __start_mcount_loc, __stop_mcount_loc); - ret = register_module_notifier(&ftrace_module_enter_nb); - if (ret) - pr_warning("Failed to register trace ftrace module enter notifier\n"); - ret = register_module_notifier(&ftrace_module_exit_nb); if (ret) pr_warning("Failed to register trace ftrace module exit notifier\n"); From af61e27c3f77c7623b5335590ae24b6a5c323e22 Mon Sep 17 00:00:00 2001 From: Tyler Stachecki Date: Fri, 25 Apr 2014 16:41:04 -0400 Subject: [PATCH 096/150] [SCSI] mpt2sas: Don't disable device twice at suspend. On suspend, _scsih_suspend calls mpt2sas_base_free_resources, which in turn calls pci_disable_device if the device is enabled prior to suspending. However, _scsih_suspend also calls pci_disable_device itself. Thus, in the event that the device is enabled prior to suspending, pci_disable_device will be called twice. This patch removes the duplicate call to pci_disable_device in _scsi_suspend as it is both unnecessary and results in a kernel oops. Signed-off-by: Tyler Stachecki Cc: stable@vger.kernel.org Signed-off-by: James Bottomley --- drivers/scsi/mpt2sas/mpt2sas_scsih.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c index 7f0af4fcc001..6fd7d40b2c4d 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c +++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c @@ -8293,7 +8293,6 @@ _scsih_suspend(struct pci_dev *pdev, pm_message_t state) mpt2sas_base_free_resources(ioc); pci_save_state(pdev); - pci_disable_device(pdev); pci_set_power_state(pdev, device_state); return 0; } From 8cc3cfc5ccf1680b7c88f874912b6bec2797b76b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 4 Mar 2014 20:43:41 +0000 Subject: [PATCH 097/150] irqchip: armanda: Sanitize set_irq_affinity() The set_irq_affinity() function has two issues: 1) It has no protection against selecting an offline cpu from the given mask. 2) It pointlessly restricts the affinity masks to have a single cpu set. This collides with the irq migration code of arm. irq affinity is set to core 3 core 3 goes offline migration code sets mask to cpu_online_mask and calls the irq_set_affinity() callback of the irq_chip which fails due to bit 0,1,2 set. So instead of doing silly for_each_cpu() loops just pick any bit of the mask which intersects with the online mask. Get rid of fiddling with the default_irq_affinity as well. [ Gregory: Fixed the access to the routing register ] Signed-off-by: Thomas Gleixner Acked-by: Gregory CLEMENT Tested-by: Gregory CLEMENT Cc: Jason Cooper Cc: Peter Zijlstra Cc: Ingo Molnar Link: http://lkml.kernel.org/r/20140304203101.088889302@linutronix.de Signed-off-by: Thomas Gleixner --- drivers/irqchip/irq-armada-370-xp.c | 37 +++++------------------------ 1 file changed, 6 insertions(+), 31 deletions(-) diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c index 41be897df8d5..304a20d0ad15 100644 --- a/drivers/irqchip/irq-armada-370-xp.c +++ b/drivers/irqchip/irq-armada-370-xp.c @@ -41,6 +41,7 @@ #define ARMADA_370_XP_INT_SET_ENABLE_OFFS (0x30) #define ARMADA_370_XP_INT_CLEAR_ENABLE_OFFS (0x34) #define ARMADA_370_XP_INT_SOURCE_CTL(irq) (0x100 + irq*4) +#define ARMADA_370_XP_INT_SOURCE_CPU_MASK 0xF #define ARMADA_370_XP_CPU_INTACK_OFFS (0x44) #define ARMADA_375_PPI_CAUSE (0x10) @@ -244,35 +245,18 @@ static DEFINE_RAW_SPINLOCK(irq_controller_lock); static int armada_xp_set_affinity(struct irq_data *d, const struct cpumask *mask_val, bool force) { - unsigned long reg; - unsigned long new_mask = 0; - unsigned long online_mask = 0; - unsigned long count = 0; irq_hw_number_t hwirq = irqd_to_hwirq(d); + unsigned long reg, mask; int cpu; - for_each_cpu(cpu, mask_val) { - new_mask |= 1 << cpu_logical_map(cpu); - count++; - } - - /* - * Forbid mutlicore interrupt affinity - * This is required since the MPIC HW doesn't limit - * several CPUs from acknowledging the same interrupt. - */ - if (count > 1) - return -EINVAL; - - for_each_cpu(cpu, cpu_online_mask) - online_mask |= 1 << cpu_logical_map(cpu); + /* Select a single core from the affinity mask which is online */ + cpu = cpumask_any_and(mask_val, cpu_online_mask); + mask = 1UL << cpu_logical_map(cpu); raw_spin_lock(&irq_controller_lock); - reg = readl(main_int_base + ARMADA_370_XP_INT_SOURCE_CTL(hwirq)); - reg = (reg & (~online_mask)) | new_mask; + reg = (reg & (~ARMADA_370_XP_INT_SOURCE_CPU_MASK)) | mask; writel(reg, main_int_base + ARMADA_370_XP_INT_SOURCE_CTL(hwirq)); - raw_spin_unlock(&irq_controller_lock); return 0; @@ -494,15 +478,6 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node, #ifdef CONFIG_SMP armada_xp_mpic_smp_cpu_init(); - - /* - * Set the default affinity from all CPUs to the boot cpu. - * This is required since the MPIC doesn't limit several CPUs - * from acknowledging the same interrupt. - */ - cpumask_clear(irq_default_affinity); - cpumask_set_cpu(smp_processor_id(), irq_default_affinity); - #endif armada_370_xp_msi_init(node, main_int_res.start); From 3894e9e82dfdc87fa35dc7976e0472d220228826 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 3 Apr 2014 10:21:34 +0300 Subject: [PATCH 098/150] irqchip: irq-crossbar: Not allocating enough memory We are allocating the size of a pointer and not the size of the data. This will lead to memory corruption. There isn't actually a "cb_device" struct, btw. The code is only able to compile because GCC knows that all pointers are the same size. Fixes: 96ca848ef7ea ('DRIVERS: IRQCHIP: CROSSBAR: Add support for Crossbar IP') Signed-off-by: Dan Carpenter Acked-by: Sricharan R Cc: Grant Likely Cc: Rob Herring Link: http://lkml.kernel.org/r/20140403072134.GA14286@mwanda Signed-off-by: Thomas Gleixner --- drivers/irqchip/irq-crossbar.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/irqchip/irq-crossbar.c b/drivers/irqchip/irq-crossbar.c index fc817d28d1fe..3d15d16a7088 100644 --- a/drivers/irqchip/irq-crossbar.c +++ b/drivers/irqchip/irq-crossbar.c @@ -107,7 +107,7 @@ static int __init crossbar_of_init(struct device_node *node) int i, size, max, reserved = 0, entry; const __be32 *irqsr; - cb = kzalloc(sizeof(struct cb_device *), GFP_KERNEL); + cb = kzalloc(sizeof(*cb), GFP_KERNEL); if (!cb) return -ENOMEM; From 50f5aa8a9b248fa4262cf379863ec9a531b49737 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 28 Apr 2014 14:24:09 -0700 Subject: [PATCH 099/150] mm: don't pointlessly use BUG_ON() for sanity check BUG_ON() is a big hammer, and should be used _only_ if there is some major corruption that you cannot possibly recover from, making it imperative that the current process (and possibly the whole machine) be terminated with extreme prejudice. The trivial sanity check in the vmacache code is *not* such a fatal error. Recovering from it is absolutely trivial, and using BUG_ON() just makes it harder to debug for no actual advantage. To make matters worse, the placement of the BUG_ON() (only if the range check matched) actually makes it harder to hit the sanity check to begin with, so _if_ there is a bug (and we just got a report from Srivatsa Bhat that this can indeed trigger), it is harder to debug not just because the machine is possibly dead, but because we don't have better coverage. BUG_ON() must *die*. Maybe we should add a checkpatch warning for it, because it is simply just about the worst thing you can ever do if you hit some "this cannot happen" situation. Reported-by: Srivatsa S. Bhat Cc: Davidlohr Bueso Cc: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmacache.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/mm/vmacache.c b/mm/vmacache.c index d4224b397c0e..1037a3bab505 100644 --- a/mm/vmacache.c +++ b/mm/vmacache.c @@ -81,10 +81,12 @@ struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr) for (i = 0; i < VMACACHE_SIZE; i++) { struct vm_area_struct *vma = current->vmacache[i]; - if (vma && vma->vm_start <= addr && vma->vm_end > addr) { - BUG_ON(vma->vm_mm != mm); + if (!vma) + continue; + if (WARN_ON_ONCE(vma->vm_mm != mm)) + break; + if (vma->vm_start <= addr && vma->vm_end > addr) return vma; - } } return NULL; From 0c8482ac92db5ac15792caf23b7f7df9e4f48ae1 Mon Sep 17 00:00:00 2001 From: Fam Zheng Date: Mon, 14 Apr 2014 10:16:09 +0800 Subject: [PATCH 100/150] [SCSI] virtio-scsi: Skip setting affinity on uninitialized vq virtscsi_init calls virtscsi_remove_vqs on err, even before initializing the vqs. The latter calls virtscsi_set_affinity, so let's check the pointer there before setting affinity on it. This fixes a panic when setting device's num_queues=2 on RHEL 6.5: qemu-system-x86_64 ... \ -device virtio-scsi-pci,id=scsi0,addr=0x13,...,num_queues=2 \ -drive file=/stor/vm/dummy.raw,id=drive-scsi-disk,... \ -device scsi-hd,drive=drive-scsi-disk,... [ 0.354734] scsi0 : Virtio SCSI HBA [ 0.379504] BUG: unable to handle kernel NULL pointer dereference at 0000000000000020 [ 0.380141] IP: [] __virtscsi_set_affinity+0x4f/0x120 [ 0.380141] PGD 0 [ 0.380141] Oops: 0000 [#1] SMP [ 0.380141] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.14.0+ #5 [ 0.380141] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2007 [ 0.380141] task: ffff88003c9f0000 ti: ffff88003c9f8000 task.ti: ffff88003c9f8000 [ 0.380141] RIP: 0010:[] [] __virtscsi_set_affinity+0x4f/0x120 [ 0.380141] RSP: 0000:ffff88003c9f9c08 EFLAGS: 00010256 [ 0.380141] RAX: 0000000000000000 RBX: ffff88003c3a9d40 RCX: 0000000000001070 [ 0.380141] RDX: 0000000000000002 RSI: 0000000000000000 RDI: 0000000000000000 [ 0.380141] RBP: ffff88003c9f9c28 R08: 00000000000136c0 R09: ffff88003c801c00 [ 0.380141] R10: ffffffff81475229 R11: 0000000000000008 R12: 0000000000000000 [ 0.380141] R13: ffffffff81cc7ca8 R14: ffff88003cac3d40 R15: ffff88003cac37a0 [ 0.380141] FS: 0000000000000000(0000) GS:ffff88003e400000(0000) knlGS:0000000000000000 [ 0.380141] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 0.380141] CR2: 0000000000000020 CR3: 0000000001c0e000 CR4: 00000000000006f0 [ 0.380141] Stack: [ 0.380141] ffff88003c3a9d40 0000000000000000 ffff88003cac3d80 ffff88003cac3d40 [ 0.380141] ffff88003c9f9c48 ffffffff814742e8 ffff88003c26d000 ffff88003c26d000 [ 0.380141] ffff88003c9f9c68 ffffffff81474321 ffff88003c26d000 ffff88003c3a9d40 [ 0.380141] Call Trace: [ 0.380141] [] virtscsi_set_affinity+0x28/0x40 [ 0.380141] [] virtscsi_remove_vqs+0x21/0x50 [ 0.380141] [] virtscsi_init+0x91/0x240 [ 0.380141] [] ? vp_get+0x50/0x70 [ 0.380141] [] virtscsi_probe+0xf4/0x280 [ 0.380141] [] virtio_dev_probe+0xe5/0x140 [ 0.380141] [] driver_probe_device+0x89/0x230 [ 0.380141] [] __driver_attach+0x9b/0xa0 [ 0.380141] [] ? driver_probe_device+0x230/0x230 [ 0.380141] [] ? driver_probe_device+0x230/0x230 [ 0.380141] [] bus_for_each_dev+0x8c/0xb0 [ 0.380141] [] driver_attach+0x19/0x20 [ 0.380141] [] bus_add_driver+0x198/0x220 [ 0.380141] [] driver_register+0x5f/0xf0 [ 0.380141] [] ? spi_transport_init+0x79/0x79 [ 0.380141] [] register_virtio_driver+0x1b/0x30 [ 0.380141] [] init+0x88/0xd6 [ 0.380141] [] ? scsi_init_procfs+0x5b/0x5b [ 0.380141] [] do_one_initcall+0x7f/0x10a [ 0.380141] [] kernel_init_freeable+0x14a/0x1de [ 0.380141] [] ? kernel_init_freeable+0x1de/0x1de [ 0.380141] [] ? rest_init+0x80/0x80 [ 0.380141] [] kernel_init+0x9/0xf0 [ 0.380141] [] ret_from_fork+0x7c/0xb0 [ 0.380141] [] ? rest_init+0x80/0x80 [ 0.380141] RIP [] __virtscsi_set_affinity+0x4f/0x120 [ 0.380141] RSP [ 0.380141] CR2: 0000000000000020 [ 0.380141] ---[ end trace 8074b70c3d5e1d73 ]--- [ 0.475018] Kernel panic - not syncing: Attempted to kill init! exitcode=0x00000009 [ 0.475018] [ 0.475068] Kernel Offset: 0x0 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffff9fffffff) [ 0.475068] ---[ end Kernel panic - not syncing: Attempted to kill init! exitcode=0x00000009 [jejb: checkpatch fixes] Signed-off-by: Fam Zheng Acked-by: Paolo Bonzini Cc: stable@vger.kernel.org Signed-off-by: James Bottomley --- drivers/scsi/virtio_scsi.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 16bfd50cd3fe..db3b494e5926 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -750,8 +750,12 @@ static void __virtscsi_set_affinity(struct virtio_scsi *vscsi, bool affinity) vscsi->affinity_hint_set = true; } else { - for (i = 0; i < vscsi->num_queues; i++) + for (i = 0; i < vscsi->num_queues; i++) { + if (!vscsi->req_vqs[i].vq) + continue; + virtqueue_set_affinity(vscsi->req_vqs[i].vq, -1); + } vscsi->affinity_hint_set = false; } From 7aa0557fae5ce26dddc877869c7ad934e71f30db Mon Sep 17 00:00:00 2001 From: "Srivatsa S. Bhat" Date: Tue, 29 Apr 2014 00:24:09 +0530 Subject: [PATCH 101/150] cpufreq: longhaul: Fix double invocation of cpufreq_freq_transition_begin/end During frequency transitions, the cpufreq core takes the responsibility of invoking cpufreq_freq_transition_begin() and cpufreq_freq_transition_end() for those cpufreq drivers that define the ->target_index callback but don't set the ASYNC_NOTIFICATION flag. The longhaul cpufreq driver falls under this category, but this driver was invoking the _begin() and _end() APIs itself around frequency transitions, which led to double invocation of the _begin() API. The _begin API makes contending callers wait until the previous invocation is complete. Hence, the longhaul driver ended up waiting on itself, leading to system hangs during boot. Fix this by removing the calls to the _begin() and _end() APIs from the longhaul driver, since they rightly belong to the cpufreq core. (Note that during module_exit(), the longhaul driver sets the frequency without any help from the cpufreq core. So add explicit calls to the _begin() and _end() APIs around that frequency transition alone, to take care of that special case.) Fixes: 12478cf0c55e (cpufreq: Make sure frequency transitions are serialized) Reported-and-tested-by: Meelis Roos Signed-off-by: Srivatsa S. Bhat Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/longhaul.c | 36 ++++++++++++++++++++++++------------ 1 file changed, 24 insertions(+), 12 deletions(-) diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c index d00e5d1abd25..5c4369b5d834 100644 --- a/drivers/cpufreq/longhaul.c +++ b/drivers/cpufreq/longhaul.c @@ -242,7 +242,7 @@ static void do_powersaver(int cx_address, unsigned int mults_index, * Sets a new clock ratio. */ -static void longhaul_setstate(struct cpufreq_policy *policy, +static int longhaul_setstate(struct cpufreq_policy *policy, unsigned int table_index) { unsigned int mults_index; @@ -258,10 +258,12 @@ static void longhaul_setstate(struct cpufreq_policy *policy, /* Safety precautions */ mult = mults[mults_index & 0x1f]; if (mult == -1) - return; + return -EINVAL; + speed = calc_speed(mult); if ((speed > highest_speed) || (speed < lowest_speed)) - return; + return -EINVAL; + /* Voltage transition before frequency transition? */ if (can_scale_voltage && longhaul_index < table_index) dir = 1; @@ -269,8 +271,6 @@ static void longhaul_setstate(struct cpufreq_policy *policy, freqs.old = calc_speed(longhaul_get_cpu_mult()); freqs.new = speed; - cpufreq_freq_transition_begin(policy, &freqs); - pr_debug("Setting to FSB:%dMHz Mult:%d.%dx (%s)\n", fsb, mult/10, mult%10, print_speed(speed/1000)); retry_loop: @@ -385,12 +385,14 @@ static void longhaul_setstate(struct cpufreq_policy *policy, goto retry_loop; } } - /* Report true CPU frequency */ - cpufreq_freq_transition_end(policy, &freqs, 0); - if (!bm_timeout) + if (!bm_timeout) { printk(KERN_INFO PFX "Warning: Timeout while waiting for " "idle PCI bus.\n"); + return -EBUSY; + } + + return 0; } /* @@ -631,9 +633,10 @@ static int longhaul_target(struct cpufreq_policy *policy, unsigned int i; unsigned int dir = 0; u8 vid, current_vid; + int retval = 0; if (!can_scale_voltage) - longhaul_setstate(policy, table_index); + retval = longhaul_setstate(policy, table_index); else { /* On test system voltage transitions exceeding single * step up or down were turning motherboard off. Both @@ -648,7 +651,7 @@ static int longhaul_target(struct cpufreq_policy *policy, while (i != table_index) { vid = (longhaul_table[i].driver_data >> 8) & 0x1f; if (vid != current_vid) { - longhaul_setstate(policy, i); + retval = longhaul_setstate(policy, i); current_vid = vid; msleep(200); } @@ -657,10 +660,11 @@ static int longhaul_target(struct cpufreq_policy *policy, else i--; } - longhaul_setstate(policy, table_index); + retval = longhaul_setstate(policy, table_index); } + longhaul_index = table_index; - return 0; + return retval; } @@ -968,7 +972,15 @@ static void __exit longhaul_exit(void) for (i = 0; i < numscales; i++) { if (mults[i] == maxmult) { + struct cpufreq_freqs freqs; + + freqs.old = policy->cur; + freqs.new = longhaul_table[i].frequency; + freqs.flags = 0; + + cpufreq_freq_transition_begin(policy, &freqs); longhaul_setstate(policy, i); + cpufreq_freq_transition_end(policy, &freqs, 0); break; } } From 237ede16ba5bcd4d6c612ea280518c48ca31986c Mon Sep 17 00:00:00 2001 From: "Srivatsa S. Bhat" Date: Tue, 29 Apr 2014 00:24:27 +0530 Subject: [PATCH 102/150] cpufreq: powernow-k6: Fix incorrect comparison with max_multipler The value of 'max_multiplier' is meant to be used for comparison with clock_ratio[index].driver_data, not the index itself! Fix the code in powernow_k6_cpu_exit() that has this bug. Also, while at it, make the for-loop condition look for CPUFREQ_TABLE_END, instead of hard-coding the loop count to 8. Reported-by: Viresh Kumar Signed-off-by: Srivatsa S. Bhat Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/powernow-k6.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/cpufreq/powernow-k6.c b/drivers/cpufreq/powernow-k6.c index 49f120e1bc7b..695a68cfdcd4 100644 --- a/drivers/cpufreq/powernow-k6.c +++ b/drivers/cpufreq/powernow-k6.c @@ -227,8 +227,9 @@ static int powernow_k6_cpu_init(struct cpufreq_policy *policy) static int powernow_k6_cpu_exit(struct cpufreq_policy *policy) { unsigned int i; - for (i = 0; i < 8; i++) { - if (i == max_multiplier) + + for (i = 0; (clock_ratio[i].frequency != CPUFREQ_TABLE_END); i++) { + if (clock_ratio[i].driver_data == max_multiplier) powernow_k6_target(policy, i); } return 0; From 3221e55b72359c44ed75afbcf707710af5bc2d59 Mon Sep 17 00:00:00 2001 From: "Srivatsa S. Bhat" Date: Tue, 29 Apr 2014 00:24:42 +0530 Subject: [PATCH 103/150] cpufreq: powernow-k6: Fix double invocation of cpufreq_freq_transition_begin/end During frequency transitions, the cpufreq core takes the responsibility of invoking cpufreq_freq_transition_begin() and cpufreq_freq_transition_end() for those cpufreq drivers that define the ->target_index callback but don't set the ASYNC_NOTIFICATION flag. The powernow-k6 cpufreq driver falls under this category, but this driver was invoking the _begin() and _end() APIs itself around frequency transitions, which led to double invocation of the _begin() API. The _begin API makes contending callers wait until the previous invocation is complete. Hence, the powernow-k6 driver ended up waiting on itself, leading to system hangs during boot. Fix this by removing the calls to the _begin() and _end() APIs from the powernow-k6 driver, since they rightly belong to the cpufreq core. (Note that during ->exit(), the powernow-k6 driver sets the frequency without any help from the cpufreq core. So add explicit calls to the _begin() and _end() APIs around that frequency transition alone, to take care of that special case. Also, add a missing 'break' statement there.) Fixes: 12478cf0c55e (cpufreq: Make sure frequency transitions are serialized) Signed-off-by: Srivatsa S. Bhat Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/powernow-k6.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/drivers/cpufreq/powernow-k6.c b/drivers/cpufreq/powernow-k6.c index 695a68cfdcd4..78904e6ca4a0 100644 --- a/drivers/cpufreq/powernow-k6.c +++ b/drivers/cpufreq/powernow-k6.c @@ -138,22 +138,14 @@ static void powernow_k6_set_cpu_multiplier(unsigned int best_i) static int powernow_k6_target(struct cpufreq_policy *policy, unsigned int best_i) { - struct cpufreq_freqs freqs; if (clock_ratio[best_i].driver_data > max_multiplier) { printk(KERN_ERR PFX "invalid target frequency\n"); return -EINVAL; } - freqs.old = busfreq * powernow_k6_get_cpu_multiplier(); - freqs.new = busfreq * clock_ratio[best_i].driver_data; - - cpufreq_freq_transition_begin(policy, &freqs); - powernow_k6_set_cpu_multiplier(best_i); - cpufreq_freq_transition_end(policy, &freqs, 0); - return 0; } @@ -229,8 +221,18 @@ static int powernow_k6_cpu_exit(struct cpufreq_policy *policy) unsigned int i; for (i = 0; (clock_ratio[i].frequency != CPUFREQ_TABLE_END); i++) { - if (clock_ratio[i].driver_data == max_multiplier) + if (clock_ratio[i].driver_data == max_multiplier) { + struct cpufreq_freqs freqs; + + freqs.old = policy->cur; + freqs.new = clock_ratio[i].frequency; + freqs.flags = 0; + + cpufreq_freq_transition_begin(policy, &freqs); powernow_k6_target(policy, i); + cpufreq_freq_transition_end(policy, &freqs, 0); + break; + } } return 0; } From 8997b185119966c62c6e95e7b010b4060407e358 Mon Sep 17 00:00:00 2001 From: "Srivatsa S. Bhat" Date: Tue, 29 Apr 2014 00:24:58 +0530 Subject: [PATCH 104/150] cpufreq: powernow-k7: Fix double invocation of cpufreq_freq_transition_begin/end During frequency transitions, the cpufreq core takes the responsibility of invoking cpufreq_freq_transition_begin() and cpufreq_freq_transition_end() for those cpufreq drivers that define the ->target_index callback but don't set the ASYNC_NOTIFICATION flag. The powernow-k7 cpufreq driver falls under this category, but this driver was invoking the _begin() and _end() APIs itself around frequency transitions, which led to double invocation of the _begin() API. The _begin API makes contending callers wait until the previous invocation is complete. Hence, the powernow-k7 driver ended up waiting on itself, leading to system hangs during boot. Fix this by removing the calls to the _begin() and _end() APIs from the powernow-k7 driver, since they rightly belong to the cpufreq core. Fixes: 12478cf0c55e (cpufreq: Make sure frequency transitions are serialized) Signed-off-by: Srivatsa S. Bhat Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/powernow-k7.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/cpufreq/powernow-k7.c b/drivers/cpufreq/powernow-k7.c index f911645c3f6d..e61e224475ad 100644 --- a/drivers/cpufreq/powernow-k7.c +++ b/drivers/cpufreq/powernow-k7.c @@ -269,8 +269,6 @@ static int powernow_target(struct cpufreq_policy *policy, unsigned int index) freqs.new = powernow_table[index].frequency; - cpufreq_freq_transition_begin(policy, &freqs); - /* Now do the magic poking into the MSRs. */ if (have_a0 == 1) /* A0 errata 5 */ @@ -290,8 +288,6 @@ static int powernow_target(struct cpufreq_policy *policy, unsigned int index) if (have_a0 == 1) local_irq_enable(); - cpufreq_freq_transition_end(policy, &freqs, 0); - return 0; } From 6712d2931933ada259b82f06c03a855b19937074 Mon Sep 17 00:00:00 2001 From: Tim Gardner Date: Mon, 28 Apr 2014 10:18:18 -0600 Subject: [PATCH 105/150] cpufreq: ppc-corenet-cpufreq: Fix __udivdi3 modpost error bfa709bc823fc32ee8dd5220d1711b46078235d8 (cpufreq: powerpc: add cpufreq transition latency for FSL e500mc SoCs) introduced a modpost error: ERROR: "__udivdi3" [drivers/cpufreq/ppc-corenet-cpufreq.ko] undefined! make[1]: *** [__modpost] Error 1 Fix this by avoiding 64 bit integer division. gcc version 4.8.2 Fixes: bfa709bc823f (cpufreq: powerpc: add cpufreq transition latency for FSL e500mc SoCs) Signed-off-by: Tim Gardner Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/ppc-corenet-cpufreq.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/cpufreq/ppc-corenet-cpufreq.c b/drivers/cpufreq/ppc-corenet-cpufreq.c index a1ca3dd04a8e..0af618abebaf 100644 --- a/drivers/cpufreq/ppc-corenet-cpufreq.c +++ b/drivers/cpufreq/ppc-corenet-cpufreq.c @@ -138,6 +138,7 @@ static int corenet_cpufreq_cpu_init(struct cpufreq_policy *policy) struct cpufreq_frequency_table *table; struct cpu_data *data; unsigned int cpu = policy->cpu; + u64 transition_latency_hz; np = of_get_cpu_node(cpu, NULL); if (!np) @@ -205,8 +206,10 @@ static int corenet_cpufreq_cpu_init(struct cpufreq_policy *policy) for_each_cpu(i, per_cpu(cpu_mask, cpu)) per_cpu(cpu_data, i) = data; + transition_latency_hz = 12ULL * NSEC_PER_SEC; policy->cpuinfo.transition_latency = - (12ULL * NSEC_PER_SEC) / fsl_get_sys_freq(); + do_div(transition_latency_hz, fsl_get_sys_freq()); + of_node_put(np); return 0; From cc18b939e1efbc2a47f62dbd2b1df53d974df6b7 Mon Sep 17 00:00:00 2001 From: Steve Wise Date: Thu, 24 Apr 2014 14:31:53 -0500 Subject: [PATCH 106/150] RDMA/cxgb4: Fix endpoint mutex deadlocks In cases where the cm calls c4iw_modify_rc_qp() with the endpoint mutex held, they must be called with internal == 1. rx_data() and process_mpa_reply() are not doing this. This causes a deadlock because c4iw_modify_rc_qp() might call c4iw_ep_disconnect() in some !internal cases, and c4iw_ep_disconnect() acquires the endpoint mutex. The design was intended to only do the disconnect for !internal calls. Change rx_data(), FPDU_MODE case, to call c4iw_modify_rc_qp() with internal == 1, and then disconnect only after releasing the mutex. Change process_mpa_reply() to call c4iw_modify_rc_qp(TERMINATE) with internal == 1 and set a new attr flag telling it to send a TERMINATE message. Previously this was implied by !internal. Change process_mpa_reply() to return whether the caller should disconnect after releasing the endpoint mutex. Now rx_data() will do the disconnect in the cases where process_mpa_reply() wants to disconnect after the TERMINATE is sent. Change c4iw_modify_rc_qp() RTS->TERM to only disconnect if !internal, and to send a TERMINATE message if attrs->send_term is 1. Change abort_connection() to not aquire the ep mutex for setting the state, and make all calls to abort_connection() do so with the mutex held. Signed-off-by: Steve Wise Signed-off-by: Roland Dreier --- drivers/infiniband/hw/cxgb4/cm.c | 31 +++++++++++++++++--------- drivers/infiniband/hw/cxgb4/iw_cxgb4.h | 1 + drivers/infiniband/hw/cxgb4/qp.c | 9 ++++---- 3 files changed, 26 insertions(+), 15 deletions(-) diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index 185452abf32c..f9b04bc7e602 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -996,7 +996,7 @@ static void close_complete_upcall(struct c4iw_ep *ep, int status) static int abort_connection(struct c4iw_ep *ep, struct sk_buff *skb, gfp_t gfp) { PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid); - state_set(&ep->com, ABORTING); + __state_set(&ep->com, ABORTING); set_bit(ABORT_CONN, &ep->com.history); return send_abort(ep, skb, gfp); } @@ -1154,7 +1154,7 @@ static int update_rx_credits(struct c4iw_ep *ep, u32 credits) return credits; } -static void process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb) +static int process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb) { struct mpa_message *mpa; struct mpa_v2_conn_params *mpa_v2_params; @@ -1164,6 +1164,7 @@ static void process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb) struct c4iw_qp_attributes attrs; enum c4iw_qp_attr_mask mask; int err; + int disconnect = 0; PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid); @@ -1173,7 +1174,7 @@ static void process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb) * will abort the connection. */ if (stop_ep_timer(ep)) - return; + return 0; /* * If we get more than the supported amount of private data @@ -1195,7 +1196,7 @@ static void process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb) * if we don't even have the mpa message, then bail. */ if (ep->mpa_pkt_len < sizeof(*mpa)) - return; + return 0; mpa = (struct mpa_message *) ep->mpa_pkt; /* Validate MPA header. */ @@ -1235,7 +1236,7 @@ static void process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb) * We'll continue process when more data arrives. */ if (ep->mpa_pkt_len < (sizeof(*mpa) + plen)) - return; + return 0; if (mpa->flags & MPA_REJECT) { err = -ECONNREFUSED; @@ -1337,9 +1338,11 @@ static void process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb) attrs.layer_etype = LAYER_MPA | DDP_LLP; attrs.ecode = MPA_NOMATCH_RTR; attrs.next_state = C4IW_QP_STATE_TERMINATE; + attrs.send_term = 1; err = c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp, - C4IW_QP_ATTR_NEXT_STATE, &attrs, 0); + C4IW_QP_ATTR_NEXT_STATE, &attrs, 1); err = -ENOMEM; + disconnect = 1; goto out; } @@ -1355,9 +1358,11 @@ static void process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb) attrs.layer_etype = LAYER_MPA | DDP_LLP; attrs.ecode = MPA_INSUFF_IRD; attrs.next_state = C4IW_QP_STATE_TERMINATE; + attrs.send_term = 1; err = c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp, - C4IW_QP_ATTR_NEXT_STATE, &attrs, 0); + C4IW_QP_ATTR_NEXT_STATE, &attrs, 1); err = -ENOMEM; + disconnect = 1; goto out; } goto out; @@ -1366,7 +1371,7 @@ static void process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb) send_abort(ep, skb, GFP_KERNEL); out: connect_reply_upcall(ep, err); - return; + return disconnect; } static void process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb) @@ -1524,6 +1529,7 @@ static int rx_data(struct c4iw_dev *dev, struct sk_buff *skb) unsigned int tid = GET_TID(hdr); struct tid_info *t = dev->rdev.lldi.tids; __u8 status = hdr->status; + int disconnect = 0; ep = lookup_tid(t, tid); if (!ep) @@ -1539,7 +1545,7 @@ static int rx_data(struct c4iw_dev *dev, struct sk_buff *skb) switch (ep->com.state) { case MPA_REQ_SENT: ep->rcv_seq += dlen; - process_mpa_reply(ep, skb); + disconnect = process_mpa_reply(ep, skb); break; case MPA_REQ_WAIT: ep->rcv_seq += dlen; @@ -1555,13 +1561,16 @@ static int rx_data(struct c4iw_dev *dev, struct sk_buff *skb) ep->com.state, ep->hwtid, status); attrs.next_state = C4IW_QP_STATE_TERMINATE; c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp, - C4IW_QP_ATTR_NEXT_STATE, &attrs, 0); + C4IW_QP_ATTR_NEXT_STATE, &attrs, 1); + disconnect = 1; break; } default: break; } mutex_unlock(&ep->com.mutex); + if (disconnect) + c4iw_ep_disconnect(ep, 0, GFP_KERNEL); return 0; } @@ -3482,9 +3491,9 @@ static void process_timeout(struct c4iw_ep *ep) __func__, ep, ep->hwtid, ep->com.state); abort = 0; } - mutex_unlock(&ep->com.mutex); if (abort) abort_connection(ep, NULL, GFP_KERNEL); + mutex_unlock(&ep->com.mutex); c4iw_put_ep(&ep->com); } diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h index 7b8c5806a09d..7474b490760a 100644 --- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h +++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h @@ -435,6 +435,7 @@ struct c4iw_qp_attributes { u8 ecode; u16 sq_db_inc; u16 rq_db_inc; + u8 send_term; }; struct c4iw_qp { diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index 7b5114cb486f..f18ef34e8184 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -1388,11 +1388,12 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp, qhp->attr.layer_etype = attrs->layer_etype; qhp->attr.ecode = attrs->ecode; ep = qhp->ep; - disconnect = 1; - c4iw_get_ep(&qhp->ep->com); - if (!internal) + if (!internal) { + c4iw_get_ep(&qhp->ep->com); terminate = 1; - else { + disconnect = 1; + } else { + terminate = qhp->attr.send_term; ret = rdma_fini(rhp, qhp, ep); if (ret) goto err; From 92e5011ab0e073ab8fbb726c11529021e5e63973 Mon Sep 17 00:00:00 2001 From: Steve Wise Date: Thu, 24 Apr 2014 14:31:59 -0500 Subject: [PATCH 107/150] RDMA/cxgb4: Force T5 connections to use TAHOE congestion control This is required to work around a T5 HW issue. Signed-off-by: Steve Wise Signed-off-by: Roland Dreier --- drivers/infiniband/hw/cxgb4/cm.c | 8 ++++++++ drivers/infiniband/hw/cxgb4/t4fw_ri_api.h | 14 ++++++++++++++ 2 files changed, 22 insertions(+) diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index f9b04bc7e602..1f863a96a480 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -587,6 +587,10 @@ static int send_connect(struct c4iw_ep *ep) opt2 |= SACK_EN(1); if (wscale && enable_tcp_window_scaling) opt2 |= WND_SCALE_EN(1); + if (is_t5(ep->com.dev->rdev.lldi.adapter_type)) { + opt2 |= T5_OPT_2_VALID; + opt2 |= V_CONG_CNTRL(CONG_ALG_TAHOE); + } t4_set_arp_err_handler(skb, NULL, act_open_req_arp_failure); if (is_t4(ep->com.dev->rdev.lldi.adapter_type)) { @@ -2018,6 +2022,10 @@ static void accept_cr(struct c4iw_ep *ep, struct sk_buff *skb, if (tcph->ece && tcph->cwr) opt2 |= CCTRL_ECN(1); } + if (is_t5(ep->com.dev->rdev.lldi.adapter_type)) { + opt2 |= T5_OPT_2_VALID; + opt2 |= V_CONG_CNTRL(CONG_ALG_TAHOE); + } rpl = cplhdr(skb); INIT_TP_WR(rpl, ep->hwtid); diff --git a/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h b/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h index dc193c292671..6121ca08fe58 100644 --- a/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h +++ b/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h @@ -836,4 +836,18 @@ struct ulptx_idata { #define V_RX_DACK_CHANGE(x) ((x) << S_RX_DACK_CHANGE) #define F_RX_DACK_CHANGE V_RX_DACK_CHANGE(1U) +enum { /* TCP congestion control algorithms */ + CONG_ALG_RENO, + CONG_ALG_TAHOE, + CONG_ALG_NEWRENO, + CONG_ALG_HIGHSPEED +}; + +#define S_CONG_CNTRL 14 +#define M_CONG_CNTRL 0x3 +#define V_CONG_CNTRL(x) ((x) << S_CONG_CNTRL) +#define G_CONG_CNTRL(x) (((x) >> S_CONG_CNTRL) & M_CONG_CNTRL) + +#define T5_OPT_2_VALID (1 << 31) + #endif /* _T4FW_RI_API_H_ */ From c2f9da92f2fd6dbf8f40ef4d5e00db688cc0416a Mon Sep 17 00:00:00 2001 From: Steve Wise Date: Thu, 24 Apr 2014 14:32:04 -0500 Subject: [PATCH 108/150] RDMA/cxgb4: Only allow kernel db ringing for T4 devs The whole db drop avoidance stuff is for T4 only. So we cannot allow that to be enabled for T5 devices. Signed-off-by: Steve Wise Signed-off-by: Roland Dreier --- drivers/infiniband/hw/cxgb4/qp.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index f18ef34e8184..086f62f5dc9e 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -1777,11 +1777,15 @@ int c4iw_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, /* * Use SQ_PSN and RQ_PSN to pass in IDX_INC values for * ringing the queue db when we're in DB_FULL mode. + * Only allow this on T4 devices. */ attrs.sq_db_inc = attr->sq_psn; attrs.rq_db_inc = attr->rq_psn; mask |= (attr_mask & IB_QP_SQ_PSN) ? C4IW_QP_ATTR_SQ_DB : 0; mask |= (attr_mask & IB_QP_RQ_PSN) ? C4IW_QP_ATTR_RQ_DB : 0; + if (is_t5(to_c4iw_qp(ibqp)->rhp->rdev.lldi.adapter_type) && + (mask & (C4IW_QP_ATTR_SQ_DB|C4IW_QP_ATTR_RQ_DB))) + return -EINVAL; return c4iw_modify_qp(rhp, qhp, mask, &attrs, 0); } From 7d0a73a40c5ceb7524aa6a43f108de0dd8dbe3f0 Mon Sep 17 00:00:00 2001 From: Hariprasad S Date: Sat, 26 Apr 2014 00:51:18 +0530 Subject: [PATCH 109/150] RDMA/cxgb4: Update Kconfig to include Chelsio T5 adapter Signed-off-by: Hariprasad Shenai Signed-off-by: Roland Dreier --- drivers/infiniband/hw/cxgb4/Kconfig | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/hw/cxgb4/Kconfig b/drivers/infiniband/hw/cxgb4/Kconfig index d4e8983fba53..23f38cf2c5cd 100644 --- a/drivers/infiniband/hw/cxgb4/Kconfig +++ b/drivers/infiniband/hw/cxgb4/Kconfig @@ -1,10 +1,10 @@ config INFINIBAND_CXGB4 - tristate "Chelsio T4 RDMA Driver" + tristate "Chelsio T4/T5 RDMA Driver" depends on CHELSIO_T4 && INET && (IPV6 || IPV6=n) select GENERIC_ALLOCATOR ---help--- - This is an iWARP/RDMA driver for the Chelsio T4 1GbE and - 10GbE adapters. + This is an iWARP/RDMA driver for the Chelsio T4 and T5 + 1GbE, 10GbE adapters and T5 40GbE adapter. For general information about Chelsio and our products, visit our website at . From 30c2117085bc4e05d091cee6eba79f069b41a9cd Mon Sep 17 00:00:00 2001 From: Haibin Wang Date: Tue, 29 Apr 2014 14:49:17 +0800 Subject: [PATCH 110/150] KVM: ARM: vgic: Fix the overlap check action about setting the GICD & GICC base address. Currently below check in vgic_ioaddr_overlap will always succeed, because the vgic dist base and vgic cpu base are still kept UNDEF after initialization. The code as follows will be return forever. if (IS_VGIC_ADDR_UNDEF(dist) || IS_VGIC_ADDR_UNDEF(cpu)) return 0; So, before invoking the vgic_ioaddr_overlap, it needs to set the corresponding base address firstly. Signed-off-by: Haibin Wang Acked-by: Marc Zyngier Signed-off-by: Christoffer Dall --- virt/kvm/arm/vgic.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index f9af48c9eb37..56ff9bebb577 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -1667,10 +1667,11 @@ static int vgic_ioaddr_assign(struct kvm *kvm, phys_addr_t *ioaddr, if (addr + size < addr) return -EINVAL; + *ioaddr = addr; ret = vgic_ioaddr_overlap(kvm); if (ret) - return ret; - *ioaddr = addr; + *ioaddr = VGIC_ADDR_UNDEF; + return ret; } From 82a5619410d4c4df65c04272db198eca5a867c18 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Tue, 8 Apr 2014 10:04:32 +0100 Subject: [PATCH 111/150] clocksource: arch_arm_timer: Fix age-old arch timer C3STOP detection issue ARM arch timers are tightly coupled with the CPU logic and lose context on platform implementing HW power management when cores are powered down at run-time. Marking the arch timers as C3STOP regardless of power management capabilities causes issues on platforms with no power management, since in that case the arch timers cannot possibly enter states where the timer loses context at runtime and therefore can always be used as a high resolution clockevent device. In order to fix the C3STOP issue in a way compliant with how real HW works, this patch adds a boolean property to the arch timer bindings to define if the arch timer is managed by an always-on power domain. This power domain is present on all ARM platforms to date, and manages HW that must not be turned off, whatever the state of other HW components (eg power controller). On platforms with no power management capabilities, it is the only power domain present, which encompasses and manages power supply for all HW components in the system. If the timer is powered by the always-on power domain, the always-on property must be present in the bindings which means that the timer cannot be shutdown at runtime, so it is not a C3STOP clockevent device. If the timer binding does not contain the always-on property, the timer is assumed to be power-gateable, hence it must be defined as a C3STOP clockevent device. Cc: Daniel Lezcano Cc: Magnus Damm Cc: Marc Carino Cc: Mark Rutland Acked-by: Marc Zyngier Acked-by: Rob Herring Signed-off-by: Lorenzo Pieralisi Signed-off-by: Daniel Lezcano --- Documentation/devicetree/bindings/arm/arch_timer.txt | 3 +++ drivers/clocksource/arm_arch_timer.c | 6 +++++- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/arm/arch_timer.txt b/Documentation/devicetree/bindings/arm/arch_timer.txt index 06fc7602593a..37b2cafa4e52 100644 --- a/Documentation/devicetree/bindings/arm/arch_timer.txt +++ b/Documentation/devicetree/bindings/arm/arch_timer.txt @@ -19,6 +19,9 @@ to deliver its interrupts via SPIs. - clock-frequency : The frequency of the main counter, in Hz. Optional. +- always-on : a boolean property. If present, the timer is powered through an + always-on power domain, therefore it never loses context. + Example: timer { diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index 57e823c44d2a..5163ec13429d 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -66,6 +66,7 @@ static int arch_timer_ppi[MAX_TIMER_PPI]; static struct clock_event_device __percpu *arch_timer_evt; static bool arch_timer_use_virtual = true; +static bool arch_timer_c3stop; static bool arch_timer_mem_use_virtual; /* @@ -263,7 +264,8 @@ static void __arch_timer_setup(unsigned type, clk->features = CLOCK_EVT_FEAT_ONESHOT; if (type == ARCH_CP15_TIMER) { - clk->features |= CLOCK_EVT_FEAT_C3STOP; + if (arch_timer_c3stop) + clk->features |= CLOCK_EVT_FEAT_C3STOP; clk->name = "arch_sys_timer"; clk->rating = 450; clk->cpumask = cpumask_of(smp_processor_id()); @@ -665,6 +667,8 @@ static void __init arch_timer_init(struct device_node *np) } } + arch_timer_c3stop = !of_property_read_bool(np, "always-on"); + arch_timer_register(); arch_timer_common_init(); } From 9afa27ce9414c92e271b0d7eec937bd9f5565da5 Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Sat, 26 Apr 2014 09:32:16 +0400 Subject: [PATCH 112/150] clocksource: nspire: Fix compiler warning CC drivers/clocksource/zevio-timer.o drivers/clocksource/zevio-timer.c:215:1: warning: comparison of distinct pointer types lacks a cast [enabled by default] Signed-off-by: Alexander Shiyan Signed-off-by: Daniel Lezcano --- drivers/clocksource/zevio-timer.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/clocksource/zevio-timer.c b/drivers/clocksource/zevio-timer.c index ca81809d159d..7ce442148c3f 100644 --- a/drivers/clocksource/zevio-timer.c +++ b/drivers/clocksource/zevio-timer.c @@ -212,4 +212,9 @@ static int __init zevio_timer_add(struct device_node *node) return ret; } -CLOCKSOURCE_OF_DECLARE(zevio_timer, "lsi,zevio-timer", zevio_timer_add); +static void __init zevio_timer_init(struct device_node *node) +{ + BUG_ON(zevio_timer_add(node)); +} + +CLOCKSOURCE_OF_DECLARE(zevio_timer, "lsi,zevio-timer", zevio_timer_init); From 58b116bce13612e5aa6fcd49ecbd4cf8bb59e835 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 29 Apr 2014 12:05:22 +0100 Subject: [PATCH 113/150] drivercore: deferral race condition fix When the kernel is built with CONFIG_PREEMPT it is possible to reach a state when all modules loaded but some driver still stuck in the deferred list and there is a need for external event to kick the deferred queue to probe these drivers. The issue has been observed on embedded systems with CONFIG_PREEMPT enabled, audio support built as modules and using nfsroot for root filesystem. The following log fragment shows such sequence when all audio modules were loaded but the sound card is not present since the machine driver has failed to probe due to missing dependency during it's probe. The board is am335x-evmsk (McASP<->tlv320aic3106 codec) with davinci-evm machine driver: ... [ 12.615118] davinci-mcasp 4803c000.mcasp: davinci_mcasp_probe: ENTER [ 12.719969] davinci_evm sound.3: davinci_evm_probe: ENTER [ 12.725753] davinci_evm sound.3: davinci_evm_probe: snd_soc_register_card [ 12.753846] davinci-mcasp 4803c000.mcasp: davinci_mcasp_probe: snd_soc_register_component [ 12.922051] davinci-mcasp 4803c000.mcasp: davinci_mcasp_probe: snd_soc_register_component DONE [ 12.950839] davinci_evm sound.3: ASoC: platform (null) not registered [ 12.957898] davinci_evm sound.3: davinci_evm_probe: snd_soc_register_card DONE (-517) [ 13.099026] davinci-mcasp 4803c000.mcasp: Kicking the deferred list [ 13.177838] davinci-mcasp 4803c000.mcasp: really_probe: probe_count = 2 [ 13.194130] davinci_evm sound.3: snd_soc_register_card failed (-517) [ 13.346755] davinci_mcasp_driver_init: LEAVE [ 13.377446] platform sound.3: Driver davinci_evm requests probe deferral [ 13.592527] platform sound.3: really_probe: probe_count = 0 In the log the machine driver enters it's probe at 12.719969 (this point it has been removed from the deferred lists). McASP driver already executing it's probing (since 12.615118). The machine driver tries to construct the sound card (12.950839) but did not found one of the components so it fails. After this McASP driver registers all the ASoC components (the machine driver still in it's probe function after it failed to construct the card) and the deferred work is prepared at 13.099026 (note that this time the machine driver is not in the lists so it is not going to be handled when the work is executing). Lastly the machine driver exit from it's probe and the core places it to the deferred list but there will be no other driver going to load and the deferred queue is not going to be kicked again - till we have external event like connecting USB stick, etc. The proposed solution is to try the deferred queue once more when the last driver is asking for deferring and we had drivers loaded while this last driver was probing. This way we can avoid drivers stuck in the deferred queue. Signed-off-by: Grant Likely Reviewed-by: Peter Ujfalusi Tested-by: Peter Ujfalusi Acked-by: Greg Kroah-Hartman Cc: Mark Brown Cc: Stable # v3.4+ --- drivers/base/dd.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 8986b9f22781..62ec61e8f84a 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -52,6 +52,7 @@ static DEFINE_MUTEX(deferred_probe_mutex); static LIST_HEAD(deferred_probe_pending_list); static LIST_HEAD(deferred_probe_active_list); static struct workqueue_struct *deferred_wq; +static atomic_t deferred_trigger_count = ATOMIC_INIT(0); /** * deferred_probe_work_func() - Retry probing devices in the active list. @@ -135,6 +136,17 @@ static bool driver_deferred_probe_enable = false; * This functions moves all devices from the pending list to the active * list and schedules the deferred probe workqueue to process them. It * should be called anytime a driver is successfully bound to a device. + * + * Note, there is a race condition in multi-threaded probe. In the case where + * more than one device is probing at the same time, it is possible for one + * probe to complete successfully while another is about to defer. If the second + * depends on the first, then it will get put on the pending list after the + * trigger event has already occured and will be stuck there. + * + * The atomic 'deferred_trigger_count' is used to determine if a successful + * trigger has occurred in the midst of probing a driver. If the trigger count + * changes in the midst of a probe, then deferred processing should be triggered + * again. */ static void driver_deferred_probe_trigger(void) { @@ -147,6 +159,7 @@ static void driver_deferred_probe_trigger(void) * into the active list so they can be retried by the workqueue */ mutex_lock(&deferred_probe_mutex); + atomic_inc(&deferred_trigger_count); list_splice_tail_init(&deferred_probe_pending_list, &deferred_probe_active_list); mutex_unlock(&deferred_probe_mutex); @@ -265,6 +278,7 @@ static DECLARE_WAIT_QUEUE_HEAD(probe_waitqueue); static int really_probe(struct device *dev, struct device_driver *drv) { int ret = 0; + int local_trigger_count = atomic_read(&deferred_trigger_count); atomic_inc(&probe_count); pr_debug("bus: '%s': %s: probing driver %s with device %s\n", @@ -310,6 +324,9 @@ static int really_probe(struct device *dev, struct device_driver *drv) /* Driver requested deferred probing */ dev_info(dev, "Driver %s requests probe deferral\n", drv->name); driver_deferred_probe_add(dev); + /* Did a trigger occur while probing? Need to re-trigger if yes */ + if (local_trigger_count != atomic_read(&deferred_trigger_count)) + driver_deferred_probe_trigger(); } else if (ret != -ENODEV && ret != -ENXIO) { /* driver matched but the probe failed */ printk(KERN_WARNING From fbcde3d8b9c2d97704b8ca299e5266147b24c8ee Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Tue, 29 Apr 2014 11:22:04 -0400 Subject: [PATCH 114/150] dm thin: use INIT_WORK_ONSTACK in noflush_work to avoid ODEBUG warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use INIT_WORK_ONSTACK to silence "ODEBUG: object is on stack, but not annotated". Reported-by: Zdeněk Kabeláč Signed-off-by: Mike Snitzer Acked-by: Joe Thornber --- drivers/md/dm-thin.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 28fc282b61b2..13abade76ad9 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -1625,7 +1625,7 @@ static void noflush_work(struct thin_c *tc, void (*fn)(struct work_struct *)) { struct noflush_work w; - INIT_WORK(&w.worker, fn); + INIT_WORK_ONSTACK(&w.worker, fn); w.tc = tc; atomic_set(&w.complete, 0); init_waitqueue_head(&w.wait); From 6ba736dd02e7b3658c344efeb2f4a096a6785d83 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 29 Apr 2014 18:38:21 +0200 Subject: [PATCH 115/150] ALSA: hda - Suppress CORBRP clear on Nvidia controller chips The recent commit (ca460f86521) changed the CORB RP reset procedure to follow the specification with a couple of sanity checks. Unfortunately, Nvidia controller chips seem not following this way, and spew the warning messages like: snd_hda_intel 0000:00:10.1: CORB reset timeout#1, CORBRP = 0 This patch adds the workaround for such chips. It just skips the new reset procedure for the known broken chips. Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_controller.c | 34 ++++++++++++++++++---------------- sound/pci/hda/hda_intel.c | 3 ++- sound/pci/hda/hda_priv.h | 1 + 3 files changed, 21 insertions(+), 17 deletions(-) diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c index 248b90abb882..480bbddbd801 100644 --- a/sound/pci/hda/hda_controller.c +++ b/sound/pci/hda/hda_controller.c @@ -1059,24 +1059,26 @@ static void azx_init_cmd_io(struct azx *chip) /* reset the corb hw read pointer */ azx_writew(chip, CORBRP, ICH6_CORBRP_RST); - for (timeout = 1000; timeout > 0; timeout--) { - if ((azx_readw(chip, CORBRP) & ICH6_CORBRP_RST) == ICH6_CORBRP_RST) - break; - udelay(1); - } - if (timeout <= 0) - dev_err(chip->card->dev, "CORB reset timeout#1, CORBRP = %d\n", - azx_readw(chip, CORBRP)); + if (!(chip->driver_caps & AZX_DCAPS_CORBRP_SELF_CLEAR)) { + for (timeout = 1000; timeout > 0; timeout--) { + if ((azx_readw(chip, CORBRP) & ICH6_CORBRP_RST) == ICH6_CORBRP_RST) + break; + udelay(1); + } + if (timeout <= 0) + dev_err(chip->card->dev, "CORB reset timeout#1, CORBRP = %d\n", + azx_readw(chip, CORBRP)); - azx_writew(chip, CORBRP, 0); - for (timeout = 1000; timeout > 0; timeout--) { - if (azx_readw(chip, CORBRP) == 0) - break; - udelay(1); + azx_writew(chip, CORBRP, 0); + for (timeout = 1000; timeout > 0; timeout--) { + if (azx_readw(chip, CORBRP) == 0) + break; + udelay(1); + } + if (timeout <= 0) + dev_err(chip->card->dev, "CORB reset timeout#2, CORBRP = %d\n", + azx_readw(chip, CORBRP)); } - if (timeout <= 0) - dev_err(chip->card->dev, "CORB reset timeout#2, CORBRP = %d\n", - azx_readw(chip, CORBRP)); /* enable corb dma */ azx_writeb(chip, CORBCTL, ICH6_CORBCTL_RUN); diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index d6bca62ef387..b540ad71eb0d 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -249,7 +249,8 @@ enum { /* quirks for Nvidia */ #define AZX_DCAPS_PRESET_NVIDIA \ (AZX_DCAPS_NVIDIA_SNOOP | AZX_DCAPS_RIRB_DELAY | AZX_DCAPS_NO_MSI |\ - AZX_DCAPS_ALIGN_BUFSIZE | AZX_DCAPS_NO_64BIT) + AZX_DCAPS_ALIGN_BUFSIZE | AZX_DCAPS_NO_64BIT |\ + AZX_DCAPS_CORBRP_SELF_CLEAR) #define AZX_DCAPS_PRESET_CTHDA \ (AZX_DCAPS_NO_MSI | AZX_DCAPS_POSFIX_LPIB | AZX_DCAPS_4K_BDLE_BOUNDARY) diff --git a/sound/pci/hda/hda_priv.h b/sound/pci/hda/hda_priv.h index ba38b819f984..4a7cb01fa912 100644 --- a/sound/pci/hda/hda_priv.h +++ b/sound/pci/hda/hda_priv.h @@ -189,6 +189,7 @@ enum { SDI0, SDI1, SDI2, SDI3, SDO0, SDO1, SDO2, SDO3 }; #define AZX_DCAPS_COUNT_LPIB_DELAY (1 << 25) /* Take LPIB as delay */ #define AZX_DCAPS_PM_RUNTIME (1 << 26) /* runtime PM support */ #define AZX_DCAPS_I915_POWERWELL (1 << 27) /* HSW i915 powerwell support */ +#define AZX_DCAPS_CORBRP_SELF_CLEAR (1 << 28) /* CORBRP clears itself after reset */ /* position fix mode */ enum { From 3eba563e280101209bad27d40bfc83ddf1489234 Mon Sep 17 00:00:00 2001 From: Kieran Clancy Date: Wed, 30 Apr 2014 00:21:20 +0930 Subject: [PATCH 116/150] ACPI / EC: Process rather than discard events in acpi_ec_clear Address a regression caused by commit ad332c8a4533: (ACPI / EC: Clear stale EC events on Samsung systems) After the earlier patch, there was found to be a race condition on some earlier Samsung systems (N150/N210/N220). The function acpi_ec_clear was sometimes discarding a new EC event before its GPE was triggered by the system. In the case of these systems, this meant that the "lid open" event was not registered on resume if that was the cause of the wake, leading to problems when attempting to close the lid to suspend again. After testing on a number of Samsung systems, both those affected by the previous EC bug and those affected by the race condition, it seemed that the best course of action was to process rather than discard the events. On Samsung systems which accumulate stale EC events, there does not seem to be any adverse side-effects of running the associated _Q methods. This patch adds an argument to the static function acpi_ec_sync_query so that it may be used within the acpi_ec_clear loop in place of acpi_ec_query_unlocked which was used previously. With thanks to Stefan Biereigel for reporting the issue, and for all the people who helped test the new patch on affected systems. Fixes: ad332c8a4533 (ACPI / EC: Clear stale EC events on Samsung systems) References: https://lkml.kernel.org/r/532FE3B2.9060808@biereigel-wb.de References: https://bugzilla.kernel.org/show_bug.cgi?id=44161#c173 Reported-by: Stefan Biereigel Signed-off-by: Kieran Clancy Tested-by: Stefan Biereigel Tested-by: Dennis Jansen Tested-by: Nicolas Porcel Tested-by: Maurizio D'Addona Tested-by: Juan Manuel Cabo Tested-by: Giannis Koutsou Tested-by: Kieran Clancy Cc: 3.14+ # 3.14+ Signed-off-by: Rafael J. Wysocki --- drivers/acpi/ec.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index d7d32c28829b..ad11ba4a412d 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -206,13 +206,13 @@ static void advance_transaction(struct acpi_ec *ec, u8 status) spin_unlock_irqrestore(&ec->lock, flags); } -static int acpi_ec_sync_query(struct acpi_ec *ec); +static int acpi_ec_sync_query(struct acpi_ec *ec, u8 *data); static int ec_check_sci_sync(struct acpi_ec *ec, u8 state) { if (state & ACPI_EC_FLAG_SCI) { if (!test_and_set_bit(EC_FLAGS_QUERY_PENDING, &ec->flags)) - return acpi_ec_sync_query(ec); + return acpi_ec_sync_query(ec, NULL); } return 0; } @@ -443,10 +443,8 @@ acpi_handle ec_get_handle(void) EXPORT_SYMBOL(ec_get_handle); -static int acpi_ec_query_unlocked(struct acpi_ec *ec, u8 *data); - /* - * Clears stale _Q events that might have accumulated in the EC. + * Process _Q events that might have accumulated in the EC. * Run with locked ec mutex. */ static void acpi_ec_clear(struct acpi_ec *ec) @@ -455,7 +453,7 @@ static void acpi_ec_clear(struct acpi_ec *ec) u8 value = 0; for (i = 0; i < ACPI_EC_CLEAR_MAX; i++) { - status = acpi_ec_query_unlocked(ec, &value); + status = acpi_ec_sync_query(ec, &value); if (status || !value) break; } @@ -582,13 +580,18 @@ static void acpi_ec_run(void *cxt) kfree(handler); } -static int acpi_ec_sync_query(struct acpi_ec *ec) +static int acpi_ec_sync_query(struct acpi_ec *ec, u8 *data) { u8 value = 0; int status; struct acpi_ec_query_handler *handler, *copy; - if ((status = acpi_ec_query_unlocked(ec, &value))) + + status = acpi_ec_query_unlocked(ec, &value); + if (data) + *data = value; + if (status) return status; + list_for_each_entry(handler, &ec->list, node) { if (value == handler->query_bit) { /* have custom handler for this bit */ @@ -612,7 +615,7 @@ static void acpi_ec_gpe_query(void *ec_cxt) if (!ec) return; mutex_lock(&ec->mutex); - acpi_ec_sync_query(ec); + acpi_ec_sync_query(ec, NULL); mutex_unlock(&ec->mutex); } From b3413afb4a8995a67f5df6218c6d0ff3a53a6978 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 29 Apr 2014 00:20:34 +0200 Subject: [PATCH 117/150] PNP: Fix compile error in quirks.c Fix the compile error: drivers/pnp/quirks.c:393:2: error: implicit declaration of function 'pcibios_bus_to_resource' that occurs when building with CONFIG_PCI unset. The quirk is only relevent to Intel devices, so we could use "#if defined(CONFIG_X86) && defined(CONFIG_PCI)" instead, but testing CONFIG_X86 is not strictly necessary. Fixes: cb171f7abb9a (PNP: Work around BIOS defects in Intel MCH area reporting) Reported-by: Randy Dunlap Signed-off-by: Bjorn Helgaas Signed-off-by: Rafael J. Wysocki --- drivers/pnp/quirks.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/pnp/quirks.c b/drivers/pnp/quirks.c index 3736bc408adb..ebf0d6710b5a 100644 --- a/drivers/pnp/quirks.c +++ b/drivers/pnp/quirks.c @@ -335,7 +335,7 @@ static void quirk_amd_mmconfig_area(struct pnp_dev *dev) } #endif -#ifdef CONFIG_X86 +#ifdef CONFIG_PCI /* Device IDs of parts that have 32KB MCH space */ static const unsigned int mch_quirk_devices[] = { 0x0154, /* Ivy Bridge */ @@ -440,7 +440,7 @@ static struct pnp_fixup pnp_fixups[] = { #ifdef CONFIG_AMD_NB {"PNP0c01", quirk_amd_mmconfig_area}, #endif -#ifdef CONFIG_X86 +#ifdef CONFIG_PCI {"PNP0c02", quirk_intel_mch}, #endif {""} From 25c8b5c3048cb6c98d402ca8d4735ccf910f727c Mon Sep 17 00:00:00 2001 From: Andrzej Hajda Date: Tue, 15 Apr 2014 15:33:01 +0200 Subject: [PATCH 118/150] drm/exynos: balance framebuffer refcount exynos_drm_crtc_mode_set assigns primary framebuffer to plane without taking reference. Then during framebuffer removal it is dereferenced twice, causing oops. The patch fixes it. Signed-off-by: Andrzej Hajda Signed-off-by: Inki Dae Signed-off-by: Dave Airlie --- drivers/gpu/drm/exynos/exynos_drm_crtc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c index e930d4fe29c7..1ef5ab9c9d51 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c @@ -145,6 +145,7 @@ exynos_drm_crtc_mode_set(struct drm_crtc *crtc, struct drm_display_mode *mode, plane->crtc = crtc; plane->fb = crtc->primary->fb; + drm_framebuffer_reference(plane->fb); return 0; } From e2a75c446e38ddf32ccdeb6e8cf2baa61fd8510f Mon Sep 17 00:00:00 2001 From: Jingoo Han Date: Thu, 10 Apr 2014 20:24:03 +0900 Subject: [PATCH 119/150] MAINTAINERS: update maintainer entry for Exynos DP driver Recently, Exynos DP driver was moved from drivers/video/exynos/ directory to drivers/gpu/drm/exynos/ directory. So, I update and add maintainer entry for Exynos DP driver. Signed-off-by: Jingoo Han Signed-off-by: Inki Dae Signed-off-by: Dave Airlie --- MAINTAINERS | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index e67ea2442041..ea44a57f790e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3485,6 +3485,12 @@ S: Maintained F: drivers/extcon/ F: Documentation/extcon/ +EXYNOS DP DRIVER +M: Jingoo Han +L: dri-devel@lists.freedesktop.org +S: Maintained +F: drivers/gpu/drm/exynos/exynos_dp* + EXYNOS MIPI DISPLAY DRIVERS M: Inki Dae M: Donghwa Lee From 293d3f6a70704691c3539bc3630ba1acbabc5c43 Mon Sep 17 00:00:00 2001 From: Jingoo Han Date: Thu, 17 Apr 2014 19:08:40 +0900 Subject: [PATCH 120/150] drm/exynos: dsi: use IS_ERR() to check devm_ioremap_resource() results devm_ioremap_resource() returns an error pointer, not NULL. Thus, the result should be checked with IS_ERR(). Signed-off-by: Jingoo Han Signed-off-by: Inki Dae Signed-off-by: Dave Airlie --- drivers/gpu/drm/exynos/exynos_drm_dsi.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c index eb73e3bf2a0c..4ac438187568 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c @@ -1426,9 +1426,9 @@ static int exynos_dsi_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); dsi->reg_base = devm_ioremap_resource(&pdev->dev, res); - if (!dsi->reg_base) { + if (IS_ERR(dsi->reg_base)) { dev_err(&pdev->dev, "failed to remap io region\n"); - return -EADDRNOTAVAIL; + return PTR_ERR(dsi->reg_base); } dsi->phy = devm_phy_get(&pdev->dev, "dsim"); From b8eade24c9891b8f153c40cf310ef4696c873af9 Mon Sep 17 00:00:00 2001 From: Jingoo Han Date: Tue, 22 Apr 2014 14:45:32 +0900 Subject: [PATCH 121/150] drm/exynos: use %pad for dma_addr_t Use %pad for dma_addr_t, because a dma_addr_t type can vary based on build options. So, it prevents possible build warnings in printks. Signed-off-by: Jingoo Han Reviewed-by: Daniel Kurtz Signed-off-by: Inki Dae Signed-off-by: Dave Airlie --- drivers/gpu/drm/exynos/exynos_drm_dmabuf.c | 2 +- drivers/gpu/drm/exynos/exynos_drm_vidi.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c index c786cd4f457b..2a3ad24276f8 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c @@ -263,7 +263,7 @@ struct drm_gem_object *exynos_dmabuf_prime_import(struct drm_device *drm_dev, buffer->sgt = sgt; exynos_gem_obj->base.import_attach = attach; - DRM_DEBUG_PRIME("dma_addr = 0x%x, size = 0x%lx\n", buffer->dma_addr, + DRM_DEBUG_PRIME("dma_addr = %pad, size = 0x%lx\n", &buffer->dma_addr, buffer->size); return &exynos_gem_obj->base; diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c index 7afead9c3f30..852f2dadaebd 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c @@ -220,7 +220,7 @@ static void vidi_win_commit(struct exynos_drm_manager *mgr, int zpos) win_data->enabled = true; - DRM_DEBUG_KMS("dma_addr = 0x%x\n", win_data->dma_addr); + DRM_DEBUG_KMS("dma_addr = %pad\n", &win_data->dma_addr); if (ctx->vblank_on) schedule_work(&ctx->work); From 6c6c0d5a1c949d2e084706f9e5fb1fccc175b265 Mon Sep 17 00:00:00 2001 From: Stuart Hayes Date: Tue, 29 Apr 2014 17:55:02 -0500 Subject: [PATCH 122/150] hrtimer: Prevent all reprogramming if hang detected If the last hrtimer interrupt detected a hang it sets hang_detected=1 and programs the clock event device with a delay to let the system make progress. If hang_detected == 1, we prevent reprogramming of the clock event device in hrtimer_reprogram() but not in hrtimer_force_reprogram(). This can lead to the following situation: hrtimer_interrupt() hang_detected = 1; program ce device to Xms from now (hang delay) We have two timers pending: T1 expires 50ms from now T2 expires 5s from now Now T1 gets canceled, which causes hrtimer_force_reprogram() to be invoked, which in turn programs the clock event device to T2 (5 seconds from now). Any hrtimer_start after that will not reprogram the hardware due to hang_detected still being set. So we effectivly block all timers until the T2 event fires and cleans up the hang situation. Add a check for hang_detected to hrtimer_force_reprogram() which prevents the reprogramming of the hang delay in the hardware timer. The subsequent hrtimer_interrupt will resolve all outstanding issues. [ tglx: Rewrote subject and changelog and fixed up the comment in hrtimer_force_reprogram() ] Signed-off-by: Stuart Hayes Link: http://lkml.kernel.org/r/53602DC6.2060101@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Thomas Gleixner --- kernel/hrtimer.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index d55092ceee29..e3724fdac2da 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -569,6 +569,23 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal) cpu_base->expires_next.tv64 = expires_next.tv64; + /* + * If a hang was detected in the last timer interrupt then we + * leave the hang delay active in the hardware. We want the + * system to make progress. That also prevents the following + * scenario: + * T1 expires 50ms from now + * T2 expires 5s from now + * + * T1 is removed, so this code is called and would reprogram + * the hardware to 5s from now. Any hrtimer_start after that + * will not reprogram the hardware due to hang_detected being + * set. So we'd effectivly block all timers until the T2 event + * fires. + */ + if (cpu_base->hang_detected) + return; + if (cpu_base->expires_next.tv64 != KTIME_MAX) tick_program_event(cpu_base->expires_next, 1); } From 012a45e3f4af68e86d85cce060c6c2fed56498b2 Mon Sep 17 00:00:00 2001 From: Leon Ma Date: Wed, 30 Apr 2014 16:43:10 +0800 Subject: [PATCH 123/150] hrtimer: Prevent remote enqueue of leftmost timers If a cpu is idle and starts an hrtimer which is not pinned on that same cpu, the nohz code might target the timer to a different cpu. In the case that we switch the cpu base of the timer we already have a sanity check in place, which determines whether the timer is earlier than the current leftmost timer on the target cpu. In that case we enqueue the timer on the current cpu because we cannot reprogram the clock event device on the target. If the timers base is already the target CPU we do not have this sanity check in place so we enqueue the timer as the leftmost timer in the target cpus rb tree, but we cannot reprogram the clock event device on the target cpu. So the timer expires late and subsequently prevents the reprogramming of the target cpu clock event device until the previously programmed event fires or a timer with an earlier expiry time gets enqueued on the target cpu itself. Add the same target check as we have for the switch base case and start the timer on the current cpu if it would become the leftmost timer on the target. [ tglx: Rewrote subject and changelog ] Signed-off-by: Leon Ma Link: http://lkml.kernel.org/r/1398847391-5994-1-git-send-email-xindong.ma@intel.com Cc: stable@vger.kernel.org Signed-off-by: Thomas Gleixner --- kernel/hrtimer.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index e3724fdac2da..6b715c0af1b1 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -234,6 +234,11 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base, goto again; } timer->base = new_base; + } else { + if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) { + cpu = this_cpu; + goto again; + } } return new_base; } From 98a01e779f3c66b0b11cd7e64d531c0e41c95762 Mon Sep 17 00:00:00 2001 From: Jiri Bohac Date: Fri, 18 Apr 2014 17:23:11 +0200 Subject: [PATCH 124/150] timer: Prevent overflow in apply_slack On architectures with sizeof(int) < sizeof (long), the computation of mask inside apply_slack() can be undefined if the computed bit is > 32. E.g. with: expires = 0xffffe6f5 and slack = 25, we get: expires_limit = 0x20000000e bit = 33 mask = (1 << 33) - 1 /* undefined */ On x86, mask becomes 1 and and the slack is not applied properly. On s390, mask is -1, expires is set to 0 and the timer fires immediately. Use 1UL << bit to solve that issue. Suggested-by: Deborah Townsend Signed-off-by: Jiri Bohac Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/20140418152310.GA13654@midget.suse.cz Signed-off-by: Thomas Gleixner --- kernel/timer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/timer.c b/kernel/timer.c index 87bd529879c2..3bb01a323b2a 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -838,7 +838,7 @@ unsigned long apply_slack(struct timer_list *timer, unsigned long expires) bit = find_last_bit(&mask, BITS_PER_LONG); - mask = (1 << bit) - 1; + mask = (1UL << bit) - 1; expires_limit = expires_limit & ~(mask); From e27a08f53d081b33c988db954008d879b2ab8b39 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sun, 27 Apr 2014 11:12:21 +0200 Subject: [PATCH 125/150] perf tools: Use LDFLAGS instead of ALL_LDFLAGS We no longer use ALL_LDFLAGS, Replacing with LDFLAGS. Acked-by: Namhyung Kim Cc: Arnaldo Carvalho de Melo Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1398675770-3109-1-git-send-email-jolsa@kernel.org Signed-off-by: Jiri Olsa --- tools/perf/Makefile.perf | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index e96923310d57..895edd32930c 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -589,7 +589,7 @@ $(GTK_OBJS): $(OUTPUT)%.o: %.c $(LIB_H) $(QUIET_CC)$(CC) -o $@ -c -fPIC $(CFLAGS) $(GTK_CFLAGS) $< $(OUTPUT)libperf-gtk.so: $(GTK_OBJS) $(PERFLIBS) - $(QUIET_LINK)$(CC) -o $@ -shared $(ALL_LDFLAGS) $(filter %.o,$^) $(GTK_LIBS) + $(QUIET_LINK)$(CC) -o $@ -shared $(LDFLAGS) $(filter %.o,$^) $(GTK_LIBS) $(OUTPUT)builtin-help.o: builtin-help.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \ From 2cf9040714f3e63f94935c9f1ed4e5bc54265ddb Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 23 Apr 2014 16:53:25 +0200 Subject: [PATCH 126/150] perf tools: Fix bfd dependency libraries detection There's false assumption in the library detection code assuming -liberty and -lz are always present once bfd is detected. The fails on Ubuntu (14.04) as reported by Ingo. Forcing the bdf dependency libraries detection any time bfd library is detected. Reported-by: Ingo Molnar Tested-by: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1398676935-6615-1-git-send-email-jolsa@kernel.org Signed-off-by: Jiri Olsa --- tools/perf/config/Makefile | 34 +++++++++++++++++++++++----------- 1 file changed, 23 insertions(+), 11 deletions(-) diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index a71fb395e38f..a57d59e7fe4b 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -194,7 +194,10 @@ VF_FEATURE_TESTS = \ stackprotector-all \ timerfd \ libunwind-debug-frame \ - bionic + bionic \ + liberty \ + liberty-z \ + cplus-demangle # Set FEATURE_CHECK_(C|LD)FLAGS-all for all CORE_FEATURE_TESTS features. # If in the future we need per-feature checks/flags for features not @@ -512,7 +515,21 @@ else endif ifeq ($(feature-libbfd), 1) - EXTLIBS += -lbfd -lz -liberty + EXTLIBS += -lbfd + + # call all detections now so we get correct + # status in VF output + $(call feature_check,liberty) + $(call feature_check,liberty-z) + $(call feature_check,cplus-demangle) + + ifeq ($(feature-liberty), 1) + EXTLIBS += -liberty + else + ifeq ($(feature-liberty-z), 1) + EXTLIBS += -liberty -lz + endif + endif endif ifdef NO_DEMANGLE @@ -523,15 +540,10 @@ else CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT else ifneq ($(feature-libbfd), 1) - $(call feature_check,liberty) - ifeq ($(feature-liberty), 1) - EXTLIBS += -lbfd -liberty - else - $(call feature_check,liberty-z) - ifeq ($(feature-liberty-z), 1) - EXTLIBS += -lbfd -liberty -lz - else - $(call feature_check,cplus-demangle) + ifneq ($(feature-liberty), 1) + ifneq ($(feature-liberty-z), 1) + # we dont have neither HAVE_CPLUS_DEMANGLE_SUPPORT + # or any of 'bfd iberty z' trinity ifeq ($(feature-cplus-demangle), 1) EXTLIBS += -liberty CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT From 611ec127165b572f02823e152d6774e2145305a3 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 29 Apr 2014 09:53:40 +0200 Subject: [PATCH 127/150] perf tests: Add static build make test Adding test for building static perf build into the automated suite. Also available via following commands: $ make -f tests/make make_static - make_static: cd . && make -f Makefile DESTDIR=/tmp/tmp.7u5MlB4njo LDFLAGS=-static $ make -f tests/make make_static_O - make_static_O: cd . && make -f Makefile O=/tmp/tmp.Ay6r3wEmtX DESTDIR=/tmp/tmp.vK0KQwO0Vi LDFLAGS=-static Acked-by: David Ahern Cc: Arnaldo Carvalho de Melo Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1398760413-7574-1-git-send-email-jolsa@kernel.org Signed-off-by: Jiri Olsa --- tools/perf/tests/make | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/tests/make b/tools/perf/tests/make index 5daeae1cb4c0..2f92d6e7ee00 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -46,6 +46,7 @@ make_install_man := install-man make_install_html := install-html make_install_info := install-info make_install_pdf := install-pdf +make_static := LDFLAGS=-static # all the NO_* variable combined make_minimal := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1 @@ -87,6 +88,7 @@ run += make_install_bin # run += make_install_info # run += make_install_pdf run += make_minimal +run += make_static ifneq ($(call has,ctags),) run += make_tags From 61d4290cc1f10588147b76b385875f06827d47ff Mon Sep 17 00:00:00 2001 From: Richard Yao Date: Sat, 26 Apr 2014 13:17:55 -0400 Subject: [PATCH 128/150] perf machine: Search for modules in %s/lib/modules/%s Modules installed outside of the kernel's build system should go into "%s/lib/modules/%s/extra", but at present, perf will only look at them when they are in "%s/lib/modules/%s/kernel". Lets encourage good citizenship by relaxing this requirement to "%s/lib/modules/%s". This way open source modules that are out-of-tree have no incentive to start populating a directory reserved for in-kernel modules and I can stop hex-editing my system's perf binary when profiling OSS out-of-tree modules. Feedback from Namhyung Kim correctly revealed that the hex-edits that I had been doing meant that perf was also traversing the build and source symlinks in %s/lib/modules/%s. That is undesireable, so we explicitly exclude them from traversal with a minor tweak to the traversal routine. Signed-off-by: Richard Yao Acked-by: Namhyung kim Link: http://lkml.kernel.org/r/1398532675-13684-1-git-send-email-ryao@gentoo.org Signed-off-by: Jiri Olsa --- tools/perf/util/machine.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index a53cd0b8c151..27c2a5efe450 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -717,7 +717,7 @@ static char *get_kernel_version(const char *root_dir) } static int map_groups__set_modules_path_dir(struct map_groups *mg, - const char *dir_name) + const char *dir_name, int depth) { struct dirent *dent; DIR *dir = opendir(dir_name); @@ -742,7 +742,15 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg, !strcmp(dent->d_name, "..")) continue; - ret = map_groups__set_modules_path_dir(mg, path); + /* Do not follow top-level source and build symlinks */ + if (depth == 0) { + if (!strcmp(dent->d_name, "source") || + !strcmp(dent->d_name, "build")) + continue; + } + + ret = map_groups__set_modules_path_dir(mg, path, + depth + 1); if (ret < 0) goto out; } else { @@ -786,11 +794,11 @@ static int machine__set_modules_path(struct machine *machine) if (!version) return -1; - snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s/kernel", + snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s", machine->root_dir, version); free(version); - return map_groups__set_modules_path_dir(&machine->kmaps, modules_path); + return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0); } static int machine__create_module(void *arg, const char *name, u64 start) From 603940b6b8b1347ec13a628165c00194ebc17ed2 Mon Sep 17 00:00:00 2001 From: Xia Kaixu Date: Sat, 26 Apr 2014 15:55:12 +0800 Subject: [PATCH 129/150] perf tools: Remove extra '/' character in events file path The array debugfs_known_mountpoints[] will cause extra '/' character output. Remove it. pre: $ perf probe -l /sys/kernel/debug//tracing/uprobe_events file does not exist - please rebuild kernel with CONFIG_UPROBE_EVENTS. post: $ perf probe -l /sys/kernel/debug/tracing/uprobe_events file does not exist - please rebuild kernel with CONFIG_UPROBE_EVENTS. Signed-off-by: Xia Kaixu Acked-by: Namhyung Kim Link: http://lkml.kernel.org/r/535B6660.2060001@huawei.com Signed-off-by: Jiri Olsa --- tools/lib/api/fs/debugfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/lib/api/fs/debugfs.c b/tools/lib/api/fs/debugfs.c index 7c4347962353..a74fba6d7743 100644 --- a/tools/lib/api/fs/debugfs.c +++ b/tools/lib/api/fs/debugfs.c @@ -12,8 +12,8 @@ char debugfs_mountpoint[PATH_MAX + 1] = "/sys/kernel/debug"; static const char * const debugfs_known_mountpoints[] = { - "/sys/kernel/debug/", - "/debug/", + "/sys/kernel/debug", + "/debug", 0, }; From 6392b4ebdc1acfbed605d68c437ff5597d0a8d95 Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Sun, 27 Apr 2014 18:51:05 +0200 Subject: [PATCH 130/150] perf x86: Fix perf to use non-executable stack, again arch/x86/tests/regs_load.S is missing the linker note about the stack requirements, therefore making the linker fall back to an executable stack. As this object gets linked against the final perf binary, it'll needlessly end up with an executable stack. Fix this by adding the appropriate linker note. Also add a global linker flag to prevent future regressions, as suggested by Jiri. This way perf won't get an executable stack even if we fail to add the .GNU-stack linker note to future assembler files. Though, doing so might create regressions the other way around, when (statically) linking against libraries needing an executable stack. But, apparently, regressing in that direction is wanted as it is an indicator of poor code quality -- or just missing linker notes. Fixes: 3c8b06f981 ("perf tests x86: Introduce perf_regs_load function") Signed-off-by: Mathias Krause Acked-by: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1398617466-22749-1-git-send-email-minipli@googlemail.com Signed-off-by: Jiri Olsa --- tools/perf/arch/x86/tests/regs_load.S | 8 +++++++- tools/perf/config/Makefile | 4 ++++ 2 files changed, 11 insertions(+), 1 deletion(-) diff --git a/tools/perf/arch/x86/tests/regs_load.S b/tools/perf/arch/x86/tests/regs_load.S index 99167bf644ea..60875d5c556c 100644 --- a/tools/perf/arch/x86/tests/regs_load.S +++ b/tools/perf/arch/x86/tests/regs_load.S @@ -1,4 +1,3 @@ - #include #define AX 0 @@ -90,3 +89,10 @@ ENTRY(perf_regs_load) ret ENDPROC(perf_regs_load) #endif + +/* + * We need to provide note.GNU-stack section, saying that we want + * NOT executable stack. Otherwise the final linking will assume that + * the ELF stack should not be restricted at all and set it RWX. + */ +.section .note.GNU-stack,"",@progbits diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index a57d59e7fe4b..802cf544202b 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -117,6 +117,10 @@ CFLAGS += -Wall CFLAGS += -Wextra CFLAGS += -std=gnu99 +# Enforce a non-executable stack, as we may regress (again) in the future by +# adding assembler files missing the .GNU-stack linker note. +LDFLAGS += -Wl,-z,noexecstack + EXTLIBS = -lelf -lpthread -lrt -lm -ldl ifneq ($(OUTPUT),) From 9a126728165eef9b1e9349fe57b9747ac6c6f7e3 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 30 Apr 2014 16:39:44 +0200 Subject: [PATCH 131/150] perf tests x86: Fix stack map lookup in dwarf unwind test Previous commit 'perf x86: Fix perf to use non-executable stack, again' moved stack map into MAP__VARIABLE map type again. Fixing the dwarf unwind test stack map lookup appropriately. Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Jean Pihet Link: http://lkml.kernel.org/n/tip-ttzyhbe4zls24z7ednkmhvxl@git.kernel.org Signed-off-by: Jiri Olsa --- tools/perf/arch/x86/tests/dwarf-unwind.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c index b8c0102c70c8..83bc2385e6d3 100644 --- a/tools/perf/arch/x86/tests/dwarf-unwind.c +++ b/tools/perf/arch/x86/tests/dwarf-unwind.c @@ -23,7 +23,7 @@ static int sample_ustack(struct perf_sample *sample, sp = (unsigned long) regs[PERF_REG_X86_SP]; - map = map_groups__find(&thread->mg, MAP__FUNCTION, (u64) sp); + map = map_groups__find(&thread->mg, MAP__VARIABLE, (u64) sp); if (!map) { pr_debug("failed to get stack map\n"); free(buf); From 8aa9e85adac609588eeec356e5a85059b3b819ba Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Wed, 30 Apr 2014 15:26:45 +0530 Subject: [PATCH 132/150] ARC: !PREEMPT: Ensure Return to kernel mode is IRQ safe There was a very small race window where resume to kernel mode from a Exception Path (or pure kernel mode which is true for most of ARC exceptions anyways), was not disabling interrupts in restore_regs, clobbering the exception regs Anton found the culprit call flow (after many sleepless nights) | 1. we got a Trap from user land | 2. started to service it. | 3. While doing some stuff on user-land memory (I think it is padzero()), | we got a DataTlbMiss | 4. On return from it we are taking "resume_kernel_mode" path | 5. NEED_RESHED is not set, so we go to "return from exception" path in | restore regs. | 6. there seems to be IRQ happening Signed-off-by: Vineet Gupta Cc: #3.10, 3.12, 3.13, 3.14 Cc: Anton Kolesov Cc: Francois Bedard Signed-off-by: Linus Torvalds --- arch/arc/kernel/entry.S | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index 819dd5f7eb05..29b82adbf0b4 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -614,11 +614,13 @@ resume_user_mode_begin: resume_kernel_mode: -#ifdef CONFIG_PREEMPT - - ; This is a must for preempt_schedule_irq() + ; Disable Interrupts from this point on + ; CONFIG_PREEMPT: This is a must for preempt_schedule_irq() + ; !CONFIG_PREEMPT: To ensure restore_regs is intr safe IRQ_DISABLE r9 +#ifdef CONFIG_PREEMPT + ; Can't preempt if preemption disabled GET_CURR_THR_INFO_FROM_SP r10 ld r8, [r10, THREAD_INFO_PREEMPT_COUNT] From 8c836fa85bebfea26ceff024b5d1c518bf63f3d8 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 30 Apr 2014 13:28:17 -0400 Subject: [PATCH 133/150] MAINTAINERS: email address change for Jeff Layton jlayton@redhat.com -> jlayton@poochiereds.net Signed-off-by: Jeff Layton --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index ea44a57f790e..37a36aa94177 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3556,7 +3556,7 @@ F: include/scsi/libfcoe.h F: include/uapi/scsi/fc/ FILE LOCKING (flock() and fcntl()/lockf()) -M: Jeff Layton +M: Jeff Layton M: J. Bruce Fields L: linux-fsdevel@vger.kernel.org S: Maintained From a8d22396302b7e4e5f0a594c1c1594388c29edaf Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 30 Apr 2014 22:36:33 +0200 Subject: [PATCH 134/150] PNP / ACPI: Do not return errors if _DIS or _SRS are not present The ACPI PNP subsystem returns errors from pnpacpi_set_resources() and pnpacpi_disable_resources() if the _SRS or _DIS methods are not present, respectively, but it should not do that, because those methods are optional. For this reason, modify pnpacpi_set_resources() and pnpacpi_disable_resources(), respectively, to ignore missing _SRS or _DIS. This problem has been uncovered by commit 202317a573b2 (ACPI / scan: Add acpi_device objects for all device nodes in the namespace) and manifested itself by causing serial port suspend to fail on some systems. Fixes: 202317a573b2 (ACPI / scan: Add acpi_device objects for all device nodes in the namespace) References: https://bugzilla.kernel.org/show_bug.cgi?id=74371 Reported-by: wxg4net Reported-and-tested-by: Cc: 3.14+ # 3.14+ Signed-off-by: Rafael J. Wysocki --- drivers/pnp/pnpacpi/core.c | 44 ++++++++++++++++++++++---------------- 1 file changed, 26 insertions(+), 18 deletions(-) diff --git a/drivers/pnp/pnpacpi/core.c b/drivers/pnp/pnpacpi/core.c index 9f611cbbc294..c31aa07b3ba5 100644 --- a/drivers/pnp/pnpacpi/core.c +++ b/drivers/pnp/pnpacpi/core.c @@ -83,8 +83,7 @@ static int pnpacpi_set_resources(struct pnp_dev *dev) { struct acpi_device *acpi_dev; acpi_handle handle; - struct acpi_buffer buffer; - int ret; + int ret = 0; pnp_dbg(&dev->dev, "set resources\n"); @@ -97,19 +96,26 @@ static int pnpacpi_set_resources(struct pnp_dev *dev) if (WARN_ON_ONCE(acpi_dev != dev->data)) dev->data = acpi_dev; - ret = pnpacpi_build_resource_template(dev, &buffer); - if (ret) - return ret; - ret = pnpacpi_encode_resources(dev, &buffer); - if (ret) { + if (acpi_has_method(handle, METHOD_NAME__SRS)) { + struct acpi_buffer buffer; + + ret = pnpacpi_build_resource_template(dev, &buffer); + if (ret) + return ret; + + ret = pnpacpi_encode_resources(dev, &buffer); + if (!ret) { + acpi_status status; + + status = acpi_set_current_resources(handle, &buffer); + if (ACPI_FAILURE(status)) + ret = -EIO; + } kfree(buffer.pointer); - return ret; } - if (ACPI_FAILURE(acpi_set_current_resources(handle, &buffer))) - ret = -EINVAL; - else if (acpi_bus_power_manageable(handle)) + if (!ret && acpi_bus_power_manageable(handle)) ret = acpi_bus_set_power(handle, ACPI_STATE_D0); - kfree(buffer.pointer); + return ret; } @@ -117,7 +123,7 @@ static int pnpacpi_disable_resources(struct pnp_dev *dev) { struct acpi_device *acpi_dev; acpi_handle handle; - int ret; + acpi_status status; dev_dbg(&dev->dev, "disable resources\n"); @@ -128,13 +134,15 @@ static int pnpacpi_disable_resources(struct pnp_dev *dev) } /* acpi_unregister_gsi(pnp_irq(dev, 0)); */ - ret = 0; if (acpi_bus_power_manageable(handle)) acpi_bus_set_power(handle, ACPI_STATE_D3_COLD); - /* continue even if acpi_bus_set_power() fails */ - if (ACPI_FAILURE(acpi_evaluate_object(handle, "_DIS", NULL, NULL))) - ret = -ENODEV; - return ret; + + /* continue even if acpi_bus_set_power() fails */ + status = acpi_evaluate_object(handle, "_DIS", NULL, NULL); + if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) + return -ENODEV; + + return 0; } #ifdef CONFIG_ACPI_SLEEP From 4985c32ee4241d1aba1beeac72294faa46aaff10 Mon Sep 17 00:00:00 2001 From: Lan Tianyu Date: Wed, 30 Apr 2014 15:46:33 +0800 Subject: [PATCH 135/150] ACPI / processor: Fix failure of loading acpi-cpufreq driver According commit d640113fe (ACPI: processor: fix acpi_get_cpuid for UP processor), BIOS may not provide _MAT or MADT tables and acpi_get_apicid() always returns -1. For these cases, original code will pass apic_id with vaule of -1 to acpi_map_cpuid() and it will check the acpi_id. If acpi_id is equal to zero, ignores apic_id and return zero for CPU0. Commit b981513 (ACPI / scan: bail out early if failed to parse APIC ID for CPU) changed the behavior. Return ENODEV when find apic_id is less than zero after calling acpi_get_apicid(). This causes acpi-cpufreq driver fails to be loaded on some machines. This patch is to fix it. Fixes: b981513f806d (ACPI / scan: bail out early if failed to parse APIC ID for CPU) References: https://bugzilla.kernel.org/show_bug.cgi?id=73781 Cc: 3.14+ # 3.14+ Reported-and-tested-by: KATO Hiroshi Reported-and-tested-by: Stuart Foster Signed-off-by: Lan Tianyu Signed-off-by: Rafael J. Wysocki --- drivers/acpi/acpi_processor.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c index c29c2c3ec0ad..b06f5f55ada9 100644 --- a/drivers/acpi/acpi_processor.c +++ b/drivers/acpi/acpi_processor.c @@ -170,6 +170,9 @@ static int acpi_processor_hotadd_init(struct acpi_processor *pr) acpi_status status; int ret; + if (pr->apic_id == -1) + return -ENODEV; + status = acpi_evaluate_integer(pr->handle, "_STA", NULL, &sta); if (ACPI_FAILURE(status) || !(sta & ACPI_STA_DEVICE_PRESENT)) return -ENODEV; @@ -260,10 +263,8 @@ static int acpi_processor_get_info(struct acpi_device *device) } apic_id = acpi_get_apicid(pr->handle, device_declaration, pr->acpi_id); - if (apic_id < 0) { + if (apic_id < 0) acpi_handle_debug(pr->handle, "failed to get CPU APIC ID.\n"); - return -ENODEV; - } pr->apic_id = apic_id; cpu_index = acpi_map_cpuid(pr->apic_id, pr->acpi_id); From c0940e95f7a78be0525c8d31df0b1f71e149e57e Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Wed, 30 Apr 2014 14:08:14 -0700 Subject: [PATCH 136/150] Revert "hwmon: (coretemp) Refine TjMax detection" This reverts commit 9fb6c9c73b11bef65ba80a362547fd116c1e1c9d. Tjmax on some Intel CPUs is below 85 degrees C. One known example is L5630 with Tjmax of 71 degrees C. There are other Xeon processors with Tjmax of 70 or 80 degrees C. Also, the Intel IA32 System Programming document states that the temperature target is in bits 23:16 of MSR 0x1a2 (MSR_TEMPERATURE_TARGET), which is 8 bits, not 7. So even if turbostat uses similar checks to validate Tjmax, there is no evidence that the checks are actually required. On the contrary, the checks are known to cause problems and therefore need to be removed. This fixes https://bugzilla.kernel.org/show_bug.cgi?id=75071. Fixes: 9fb6c9c hwmon: (coretemp) Refine TjMax detection Reviewed-by: Jean Delvare Cc: stable@vger.kernel.org # 3.14+ Signed-off-by: Guenter Roeck --- drivers/hwmon/coretemp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index 6d02e3b06375..d76f0b70c6e0 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -365,12 +365,12 @@ static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev) if (cpu_has_tjmax(c)) dev_warn(dev, "Unable to read TjMax from CPU %u\n", id); } else { - val = (eax >> 16) & 0x7f; + val = (eax >> 16) & 0xff; /* * If the TjMax is not plausible, an assumption * will be used */ - if (val >= 85) { + if (val) { dev_dbg(dev, "TjMax is %d degrees C\n", val); return val * 1000; } From 754320d6e166d3a12cb4810a452bde00afbd4e9a Mon Sep 17 00:00:00 2001 From: Leon Yu Date: Thu, 1 May 2014 03:31:28 +0000 Subject: [PATCH 137/150] aio: fix potential leak in aio_run_iocb(). iovec should be reclaimed whenever caller of rw_copy_check_uvector() returns, but it doesn't hold when failure happens right after aio_setup_vectored_rw(). Fix that in a such way to avoid hairy goto. Signed-off-by: Leon Yu Signed-off-by: Benjamin LaHaise Cc: stable@vger.kernel.org --- fs/aio.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/aio.c b/fs/aio.c index 2adbb0398ab9..a0ed6c7d2cd2 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -1327,10 +1327,8 @@ static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode, &iovec, compat) : aio_setup_single_vector(req, rw, buf, &nr_segs, iovec); - if (ret) - return ret; - - ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes); + if (!ret) + ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes); if (ret < 0) { if (iovec != &inline_vec) kfree(iovec); From 789ce9dca8007ab5d7c72b9a174a29243817ac32 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Wed, 30 Apr 2014 14:22:19 -0700 Subject: [PATCH 138/150] word-at-a-time: simplify big-endian zero_bytemask macro This is simpler and cleaner. Depending on architecture, a smart compiler may or may not generate the same code. Acked-by: Will Deacon Signed-off-by: Linus Torvalds --- include/asm-generic/word-at-a-time.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/asm-generic/word-at-a-time.h b/include/asm-generic/word-at-a-time.h index d96deb443f18..94f9ea8abcae 100644 --- a/include/asm-generic/word-at-a-time.h +++ b/include/asm-generic/word-at-a-time.h @@ -50,7 +50,7 @@ static inline bool has_zero(unsigned long val, unsigned long *data, const struct } #ifndef zero_bytemask -#define zero_bytemask(mask) (~0ul << __fls(mask) << 1) +#define zero_bytemask(mask) (~1ul << __fls(mask)) #endif #endif /* _ASM_WORD_AT_A_TIME_H */ From b7e1bd964812808710b48a5f9a58f7ddfb1d4e59 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Fri, 18 Apr 2014 13:38:35 +0530 Subject: [PATCH 139/150] Hexagon: Delete stale barrier.h Commit 93ea02bb8435 ("arch: Clean up asm/barrier.h implementations") wired generic barrier.h for hexagon, but failed to delete the existing file. Cc: Richard Kuo Cc: Peter Zijlstra Signed-off-by: Vineet Gupta Compile-tested-by: Guenter Roeck Signed-off-by: Linus Torvalds --- arch/hexagon/include/asm/barrier.h | 37 ------------------------------ 1 file changed, 37 deletions(-) delete mode 100644 arch/hexagon/include/asm/barrier.h diff --git a/arch/hexagon/include/asm/barrier.h b/arch/hexagon/include/asm/barrier.h deleted file mode 100644 index 4e863daea25b..000000000000 --- a/arch/hexagon/include/asm/barrier.h +++ /dev/null @@ -1,37 +0,0 @@ -/* - * Memory barrier definitions for the Hexagon architecture - * - * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 and - * only version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA. - */ - -#ifndef _ASM_BARRIER_H -#define _ASM_BARRIER_H - -#define rmb() barrier() -#define read_barrier_depends() barrier() -#define wmb() barrier() -#define mb() barrier() -#define smp_rmb() barrier() -#define smp_read_barrier_depends() barrier() -#define smp_wmb() barrier() -#define smp_mb() barrier() - -/* Set a value and use a memory barrier. Used by the scheduler somewhere. */ -#define set_mb(var, value) \ - do { var = value; mb(); } while (0) - -#endif /* _ASM_BARRIER_H */ From e0d8898d76a785453bfaf6cd08b830a7d5189f78 Mon Sep 17 00:00:00 2001 From: John David Anglin Date: Sun, 27 Apr 2014 16:20:47 -0400 Subject: [PATCH 140/150] parisc: remove _STK_LIM_MAX override There are only a couple of architectures that override _STK_LIM_MAX to a non-infinity value. This changes the stack allocation semantics in subtle ways. For example, GNU make changes its stack allocation to the hard maximum defined by _STK_LIM_MAX. As a results, threads executed by processes running under make are allocated a stack size of _STK_LIM_MAX rather than a sensible default value. This causes various thread stress tests to fail when they can't muster more than about 50 threads. The attached change implements the default behavior used by the majority of architectures. Signed-off-by: John David Anglin Reviewed-by: Carlos O'Donell Cc: stable@vger.kernel.org # 3.14 Signed-off-by: Helge Deller --- arch/parisc/include/uapi/asm/resource.h | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/parisc/include/uapi/asm/resource.h b/arch/parisc/include/uapi/asm/resource.h index 8b06343b62ed..090483c47dbb 100644 --- a/arch/parisc/include/uapi/asm/resource.h +++ b/arch/parisc/include/uapi/asm/resource.h @@ -1,7 +1,6 @@ #ifndef _ASM_PARISC_RESOURCE_H #define _ASM_PARISC_RESOURCE_H -#define _STK_LIM_MAX 10 * _STK_LIM #include #endif From 8a415e534dbda905b829320f90c9ce5f7359debf Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Tue, 29 Apr 2014 16:13:22 +0200 Subject: [PATCH 141/150] parisc: Use generic uapi/asm/resource.h file Signed-off-by: Helge Deller --- arch/parisc/include/uapi/asm/Kbuild | 3 ++- arch/parisc/include/uapi/asm/resource.h | 6 ------ 2 files changed, 2 insertions(+), 7 deletions(-) delete mode 100644 arch/parisc/include/uapi/asm/resource.h diff --git a/arch/parisc/include/uapi/asm/Kbuild b/arch/parisc/include/uapi/asm/Kbuild index a580642555b6..348356c99514 100644 --- a/arch/parisc/include/uapi/asm/Kbuild +++ b/arch/parisc/include/uapi/asm/Kbuild @@ -1,6 +1,8 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += resource.h + header-y += bitsperlong.h header-y += byteorder.h header-y += errno.h @@ -13,7 +15,6 @@ header-y += msgbuf.h header-y += pdc.h header-y += posix_types.h header-y += ptrace.h -header-y += resource.h header-y += sembuf.h header-y += setup.h header-y += shmbuf.h diff --git a/arch/parisc/include/uapi/asm/resource.h b/arch/parisc/include/uapi/asm/resource.h deleted file mode 100644 index 090483c47dbb..000000000000 --- a/arch/parisc/include/uapi/asm/resource.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ASM_PARISC_RESOURCE_H -#define _ASM_PARISC_RESOURCE_H - -#include - -#endif From 131cd131a9ff63d4b84f3fe15073a2984ac30066 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 1 May 2014 16:14:24 -0400 Subject: [PATCH 142/150] dm cache: fix writethrough mode quiescing in cache_map Commit 2ee57d58735 ("dm cache: add passthrough mode") inadvertently removed the deferred set reference that was taken in cache_map()'s writethrough mode support. Restore taking this reference. This issue was found with code inspection. Signed-off-by: Mike Snitzer Acked-by: Joe Thornber Cc: stable@vger.kernel.org # 3.13+ --- 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 1bf4a71919ec..9380be7b1895 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -2488,6 +2488,7 @@ static int cache_map(struct dm_target *ti, struct bio *bio) } else { inc_hit_counter(cache, bio); + pb->all_io_entry = dm_deferred_entry_inc(cache->all_io_ds); if (bio_data_dir(bio) == WRITE && writethrough_mode(&cache->features) && !is_dirty(cache, lookup_result.cblock)) From 561a4fe851ccab9dd0d14989ab566f9392d9f8b5 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 2 May 2014 13:30:04 -0400 Subject: [PATCH 143/150] tracing: Use rcu_dereference_sched() for trace event triggers As trace event triggers are now part of the mainline kernel, I added my trace event trigger tests to my test suite I run on all my kernels. Now these tests get run under different config options, and one of those options is CONFIG_PROVE_RCU, which checks under lockdep that the rcu locking primitives are being used correctly. This triggered the following splat: =============================== [ INFO: suspicious RCU usage. ] 3.15.0-rc2-test+ #11 Not tainted ------------------------------- kernel/trace/trace_events_trigger.c:80 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 1, debug_locks = 0 4 locks held by swapper/1/0: #0: ((&(&j_cdbs->work)->timer)){..-...}, at: [] call_timer_fn+0x5/0x1be #1: (&(&pool->lock)->rlock){-.-...}, at: [] __queue_work+0x140/0x283 #2: (&p->pi_lock){-.-.-.}, at: [] try_to_wake_up+0x2e/0x1e8 #3: (&rq->lock){-.-.-.}, at: [] try_to_wake_up+0x1a0/0x1e8 stack backtrace: CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.15.0-rc2-test+ #11 Hardware name: /DG965MQ, BIOS MQ96510J.86A.0372.2006.0605.1717 06/05/2006 0000000000000001 ffff88007e083b98 ffffffff819f53a5 0000000000000006 ffff88007b0942c0 ffff88007e083bc8 ffffffff81081307 ffff88007ad96d20 0000000000000000 ffff88007af2d840 ffff88007b2e701c ffff88007e083c18 Call Trace: [] dump_stack+0x4f/0x7c [] lockdep_rcu_suspicious+0x107/0x110 [] event_triggers_call+0x99/0x108 [] ftrace_event_buffer_commit+0x42/0xa4 [] ftrace_raw_event_sched_wakeup_template+0x71/0x7c [] ttwu_do_wakeup+0x7f/0xff [] ttwu_do_activate.constprop.126+0x5c/0x61 [] try_to_wake_up+0x1ac/0x1e8 [] wake_up_process+0x36/0x3b [] wake_up_worker+0x24/0x26 [] insert_work+0x5c/0x65 [] __queue_work+0x26c/0x283 [] ? __queue_work+0x283/0x283 [] delayed_work_timer_fn+0x1e/0x20 [] call_timer_fn+0xdf/0x1be^M [] ? call_timer_fn+0x5/0x1be [] ? __queue_work+0x283/0x283 [] run_timer_softirq+0x1a4/0x22f^M [] __do_softirq+0x17b/0x31b^M [] irq_exit+0x42/0x97 [] smp_apic_timer_interrupt+0x37/0x44 [] apic_timer_interrupt+0x6f/0x80 [] ? default_idle+0x21/0x32 [] ? default_idle+0x1f/0x32 [] arch_cpu_idle+0xf/0x11 [] cpu_startup_entry+0x1a3/0x213 [] start_secondary+0x212/0x219 The cause is that the triggers are protected by rcu_read_lock_sched() but the data is dereferenced with rcu_dereference() which expects it to be protected with rcu_read_lock(). The proper reference should be rcu_dereference_sched(). Cc: Tom Zanussi Cc: stable@vger.kernel.org # 3.14+ Signed-off-by: Steven Rostedt --- kernel/trace/trace_events_trigger.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 925f537f07d1..4747b476a030 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -77,7 +77,7 @@ event_triggers_call(struct ftrace_event_file *file, void *rec) data->ops->func(data); continue; } - filter = rcu_dereference(data->filter); + filter = rcu_dereference_sched(data->filter); if (filter && !filter_match_preds(filter, rec)) continue; if (data->cmd_ops->post_trigger) { From da6e4cb67c6dd1f72257c0a4a97c26dc4e80d3a7 Mon Sep 17 00:00:00 2001 From: Dave Anderson Date: Tue, 15 Apr 2014 18:53:24 +0100 Subject: [PATCH 144/150] arm64: Fix for the arm64 kern_addr_valid() function Fix for the arm64 kern_addr_valid() function to recognize virtual addresses in the kernel logical memory map. The function fails as written because it does not check whether the addresses in that region are mapped at the pmd level to 2MB or 512MB pages, continues the page table walk to the pte level, and issues a garbage value to pfn_valid(). Tested on 4K-page and 64K-page kernels. Signed-off-by: Dave Anderson Signed-off-by: Catalin Marinas --- arch/arm64/mm/mmu.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 6b7e89569a3a..0a472c41a67f 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -374,6 +374,9 @@ int kern_addr_valid(unsigned long addr) if (pmd_none(*pmd)) return 0; + if (pmd_sect(*pmd)) + return pfn_valid(pmd_pfn(*pmd)); + pte = pte_offset_kernel(pmd, addr); if (pte_none(*pte)) return 0; From f774b7d10e2155e52b92dfce2f8cb099a6d6d0e6 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 28 Apr 2014 19:50:06 +0100 Subject: [PATCH 145/150] arm64: fixmap: fix missing sub-page offset for earlyprintk Commit d57c33c5daa4 (add generic fixmap.h) added (among other similar things) set_fixmap_io to deal with early ioremap of devices. More recently, commit bf4b558eba92 (arm64: add early_ioremap support) converted the arm64 earlyprintk to use set_fixmap_io. A side effect of this conversion is that my virtual machines have stopped booting when I pass "earlyprintk=uart8250-8bit,0x3f8" to the guest kernel. Turns out that the new earlyprintk code doesn't care at all about sub-page offsets, and just assumes that the earlyprintk device will be page-aligned. Obviously, that doesn't play well with the above example. Further investigation shows that set_fixmap_io uses __set_fixmap instead of __set_fixmap_offset. A fix is to introduce a set_fixmap_offset_io that uses the latter, and to remove the superflous call to fix_to_virt (which only returns the value that set_fixmap_io has already given us). With this applied, my VMs are back in business. Tested on a Cortex-A57 platform with kvmtool as platform emulation. Cc: Will Deacon Acked-by: Mark Salter Acked-by: Arnd Bergmann Signed-off-by: Marc Zyngier Signed-off-by: Catalin Marinas --- arch/arm64/kernel/early_printk.c | 6 ++---- include/asm-generic/fixmap.h | 3 +++ 2 files changed, 5 insertions(+), 4 deletions(-) diff --git a/arch/arm64/kernel/early_printk.c b/arch/arm64/kernel/early_printk.c index ffbbdde7aba1..2dc36d00addf 100644 --- a/arch/arm64/kernel/early_printk.c +++ b/arch/arm64/kernel/early_printk.c @@ -143,10 +143,8 @@ static int __init setup_early_printk(char *buf) } /* no options parsing yet */ - if (paddr) { - set_fixmap_io(FIX_EARLYCON_MEM_BASE, paddr); - early_base = (void __iomem *)fix_to_virt(FIX_EARLYCON_MEM_BASE); - } + if (paddr) + early_base = (void __iomem *)set_fixmap_offset_io(FIX_EARLYCON_MEM_BASE, paddr); printch = match->printch; early_console = &early_console_dev; diff --git a/include/asm-generic/fixmap.h b/include/asm-generic/fixmap.h index 5a64ca4621f3..f23174fb9ec4 100644 --- a/include/asm-generic/fixmap.h +++ b/include/asm-generic/fixmap.h @@ -93,5 +93,8 @@ static inline unsigned long virt_to_fix(const unsigned long vaddr) #define set_fixmap_io(idx, phys) \ __set_fixmap(idx, phys, FIXMAP_PAGE_IO) +#define set_fixmap_offset_io(idx, phys) \ + __set_fixmap_offset(idx, phys, FIXMAP_PAGE_IO) + #endif /* __ASSEMBLY__ */ #endif /* __ASM_GENERIC_FIXMAP_H */ From c7a4a7658d689f664050c45493d79adf053f226e Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Wed, 23 Apr 2014 06:29:46 +0100 Subject: [PATCH 146/150] arm64: Make default dma_ops to be noncoherent Currently arm64 dma_ops is by default made coherent which makes it opposite in default policy from arm. Make default dma_ops to be noncoherent (same as arm), as currently there aren't any dma-capable drivers which assumes coherent ops Signed-off-by: Ritesh Harjani Acked-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/mm/dma-mapping.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 0ba347e59f06..1f65963a9c04 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -311,7 +311,7 @@ static int __init swiotlb_late_init(void) { size_t swiotlb_size = min(SZ_64M, MAX_ORDER_NR_PAGES << PAGE_SHIFT); - dma_ops = &coherent_swiotlb_dma_ops; + dma_ops = &noncoherent_swiotlb_dma_ops; return swiotlb_late_init_with_default_size(swiotlb_size); } From 6ecba8eb51b7d23fda66388a5420be7d8688b186 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Fri, 25 Apr 2014 15:31:45 +0100 Subject: [PATCH 147/150] arm64: Use bus notifiers to set per-device coherent DMA ops Recently, the default DMA ops have been changed to non-coherent for alignment with 32-bit ARM platforms (and DT files). This patch adds bus notifiers to be able to set the coherent DMA ops (with no cache maintenance) for devices explicitly marked as coherent via the "dma-coherent" DT property. Signed-off-by: Catalin Marinas --- arch/arm64/kernel/setup.c | 2 +- arch/arm64/mm/dma-mapping.c | 33 ++++++++++++++++++++++++++++++++- 2 files changed, 33 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 93e7df8968fe..7ec784653b29 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -396,7 +396,7 @@ static int __init arm64_device_init(void) of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL); return 0; } -arch_initcall(arm64_device_init); +arch_initcall_sync(arm64_device_init); static DEFINE_PER_CPU(struct cpu, cpu_data); diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 1f65963a9c04..c851eb44dc50 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -22,8 +22,11 @@ #include #include #include +#include +#include #include #include +#include #include @@ -305,17 +308,45 @@ struct dma_map_ops coherent_swiotlb_dma_ops = { }; EXPORT_SYMBOL(coherent_swiotlb_dma_ops); +static int dma_bus_notifier(struct notifier_block *nb, + unsigned long event, void *_dev) +{ + struct device *dev = _dev; + + if (event != BUS_NOTIFY_ADD_DEVICE) + return NOTIFY_DONE; + + if (of_property_read_bool(dev->of_node, "dma-coherent")) + set_dma_ops(dev, &coherent_swiotlb_dma_ops); + + return NOTIFY_OK; +} + +static struct notifier_block platform_bus_nb = { + .notifier_call = dma_bus_notifier, +}; + +static struct notifier_block amba_bus_nb = { + .notifier_call = dma_bus_notifier, +}; + extern int swiotlb_late_init_with_default_size(size_t default_size); static int __init swiotlb_late_init(void) { size_t swiotlb_size = min(SZ_64M, MAX_ORDER_NR_PAGES << PAGE_SHIFT); + /* + * These must be registered before of_platform_populate(). + */ + bus_register_notifier(&platform_bus_type, &platform_bus_nb); + bus_register_notifier(&amba_bustype, &amba_bus_nb); + dma_ops = &noncoherent_swiotlb_dma_ops; return swiotlb_late_init_with_default_size(swiotlb_size); } -subsys_initcall(swiotlb_late_init); +arch_initcall(swiotlb_late_init); #define PREALLOC_DMA_DEBUG_ENTRIES 4096 From 7a8d1ec16dfbb7785e82ccc97b0076cc34911701 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Fri, 25 Apr 2014 16:39:49 +0100 Subject: [PATCH 148/150] arm64: Mark the Applied Micro X-Gene SATA controller as DMA coherent Since the default DMA ops for arm64 are non-coherent, mark the X-Gene controller explicitly as dma-coherent to avoid additional cache maintenance. Signed-off-by: Catalin Marinas Cc: Loc Ho --- Documentation/devicetree/bindings/ata/apm-xgene.txt | 3 +++ arch/arm64/boot/dts/apm-storm.dtsi | 3 +++ 2 files changed, 6 insertions(+) diff --git a/Documentation/devicetree/bindings/ata/apm-xgene.txt b/Documentation/devicetree/bindings/ata/apm-xgene.txt index 7bcfbf59810e..a668f0e7d001 100644 --- a/Documentation/devicetree/bindings/ata/apm-xgene.txt +++ b/Documentation/devicetree/bindings/ata/apm-xgene.txt @@ -24,6 +24,7 @@ Required properties: * "sata-phy" for the SATA 6.0Gbps PHY Optional properties: +- dma-coherent : Present if dma operations are coherent - status : Shall be "ok" if enabled or "disabled" if disabled. Default is "ok". @@ -55,6 +56,7 @@ Example: <0x0 0x1f22e000 0x0 0x1000>, <0x0 0x1f227000 0x0 0x1000>; interrupts = <0x0 0x87 0x4>; + dma-coherent; status = "ok"; clocks = <&sataclk 0>; phys = <&phy2 0>; @@ -69,6 +71,7 @@ Example: <0x0 0x1f23e000 0x0 0x1000>, <0x0 0x1f237000 0x0 0x1000>; interrupts = <0x0 0x88 0x4>; + dma-coherent; status = "ok"; clocks = <&sataclk 0>; phys = <&phy3 0>; diff --git a/arch/arm64/boot/dts/apm-storm.dtsi b/arch/arm64/boot/dts/apm-storm.dtsi index 93f4b2dd9248..f8c40a66e65d 100644 --- a/arch/arm64/boot/dts/apm-storm.dtsi +++ b/arch/arm64/boot/dts/apm-storm.dtsi @@ -307,6 +307,7 @@ sata1: sata@1a000000 { <0x0 0x1f21e000 0x0 0x1000>, <0x0 0x1f217000 0x0 0x1000>; interrupts = <0x0 0x86 0x4>; + dma-coherent; status = "disabled"; clocks = <&sata01clk 0>; phys = <&phy1 0>; @@ -321,6 +322,7 @@ sata2: sata@1a400000 { <0x0 0x1f22e000 0x0 0x1000>, <0x0 0x1f227000 0x0 0x1000>; interrupts = <0x0 0x87 0x4>; + dma-coherent; status = "ok"; clocks = <&sata23clk 0>; phys = <&phy2 0>; @@ -334,6 +336,7 @@ sata3: sata@1a800000 { <0x0 0x1f23d000 0x0 0x1000>, <0x0 0x1f23e000 0x0 0x1000>; interrupts = <0x0 0x88 0x4>; + dma-coherent; status = "ok"; clocks = <&sata45clk 0>; phys = <&phy3 0>; From e715eb2e73918f4cefbba0b717ff8902e8030b39 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Mon, 28 Apr 2014 17:08:37 +0100 Subject: [PATCH 149/150] vexpress: Initialise the sysregs before setting up the clocks Following arm64 commit bc3ee18a7a57 (arm64: init: Move of_clk_init to time_init()), vexpress_osc_of_setup() is called via of_clk_init() long before initcalls are issued. Initialising the vexpress oscillators requires the vespress sysregs to be already initialised, so this patch adds an explicit call to vexpress_sysreg_of_early_init() in vexpress oscillator setup function. Signed-off-by: Catalin Marinas Tested-by: Will Deacon Acked-by: Will Deacon Tested-by: Pawel Moll Acked-by: Pawel Moll Cc: Mike Turquette --- drivers/clk/versatile/clk-vexpress-osc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/clk/versatile/clk-vexpress-osc.c b/drivers/clk/versatile/clk-vexpress-osc.c index a535c7bf8574..422391242b39 100644 --- a/drivers/clk/versatile/clk-vexpress-osc.c +++ b/drivers/clk/versatile/clk-vexpress-osc.c @@ -100,6 +100,8 @@ void __init vexpress_osc_of_setup(struct device_node *node) struct clk *clk; u32 range[2]; + vexpress_sysreg_of_early_init(); + osc = kzalloc(sizeof(*osc), GFP_KERNEL); if (!osc) return; From 89ca3b881987f5a4be4c5dbaa7f0df12bbdde2fd Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 4 May 2014 18:14:42 -0700 Subject: [PATCH 150/150] Linux 3.15-rc4 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 041c685e11ea..28a7259e0f3b 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 3 PATCHLEVEL = 15 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Shuffling Zombie Juror # *DOCUMENTATION*