diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2014-08-05 05:34:04 +0400 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-08-05 05:34:04 +0400 |
| commit | 29b88e23a9212136d39b0161a39afe587d0170a5 (patch) | |
| tree | 48d9f857b137222e35f853004973e12a515314f5 /drivers | |
| parent | 2521129a6d2fd8a81f99cf95055eddea3df914ff (diff) | |
| parent | 4e3a25b0274b8474f5ad46215a270785dd18265e (diff) | |
| download | linux-29b88e23a9212136d39b0161a39afe587d0170a5.tar.xz | |
Merge tag 'driver-core-3.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core
Pull driver core updates from Greg KH:
"Here's the big driver-core pull request for 3.17-rc1.
Largest thing in here is the dma-buf rework and fence code, that
touched many different subsystems so it was agreed it should go
through this tree to handle merge issues. There's also some firmware
loading updates, as well as tests added, and a few other tiny changes,
the changelog has the details.
All have been in linux-next for a long time"
* tag 'driver-core-3.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core: (32 commits)
ARM: imx: Remove references to platform_bus in mxc code
firmware loader: Fix _request_firmware_load() return val for fw load abort
platform: Remove most references to platform_bus device
test: add firmware_class loader test
doc: fix minor typos in firmware_class README
staging: android: Cleanup style issues
Documentation: devres: Sort managed interfaces
Documentation: devres: Add devm_kmalloc() et al
fs: debugfs: remove trailing whitespace
kernfs: kernel-doc warning fix
debugfs: Fix corrupted loop in debugfs_remove_recursive
stable_kernel_rules: Add pointer to netdev-FAQ for network patches
driver core: platform: add device binding path 'driver_override'
driver core/platform: remove unused implicit padding in platform_object
firmware loader: inform direct failure when udev loader is disabled
firmware: replace ALIGN(PAGE_SIZE) by PAGE_ALIGN
firmware: read firmware size using i_size_read()
firmware loader: allow disabling of udev as firmware loader
reservation: add suppport for read-only access using rcu
reservation: update api and add some helpers
...
Conflicts:
drivers/base/platform.c
Diffstat (limited to 'drivers')
35 files changed, 2050 insertions, 774 deletions
diff --git a/drivers/Makefile b/drivers/Makefile index 54bfae1f09a4..ebee55537a05 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -61,6 +61,7 @@ obj-$(CONFIG_FB_INTEL) += video/fbdev/intelfb/ obj-$(CONFIG_PARPORT) += parport/ obj-y += base/ block/ misc/ mfd/ nfc/ +obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf/ obj-$(CONFIG_NUBUS) += nubus/ obj-y += macintosh/ obj-$(CONFIG_IDE) += ide/ diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig index 23b8726962af..88500fed3c7a 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -149,15 +149,21 @@ config EXTRA_FIRMWARE_DIR some other directory containing the firmware files. config FW_LOADER_USER_HELPER + bool + +config FW_LOADER_USER_HELPER_FALLBACK bool "Fallback user-helper invocation for firmware loading" depends on FW_LOADER - default y + select FW_LOADER_USER_HELPER help This option enables / disables the invocation of user-helper (e.g. udev) for loading firmware files as a fallback after the direct file loading in kernel fails. The user-mode helper is no longer required unless you have a special firmware file that - resides in a non-standard path. + resides in a non-standard path. Moreover, the udev support has + been deprecated upstream. + + If you are unsure about this, say N here. config DEBUG_DRIVER bool "Driver Core verbose debug messages" @@ -208,6 +214,15 @@ config DMA_SHARED_BUFFER APIs extension; the file's descriptor can then be passed on to other driver. +config FENCE_TRACE + bool "Enable verbose FENCE_TRACE messages" + depends on DMA_SHARED_BUFFER + help + Enable the FENCE_TRACE printks. This will add extra + spam to the console log, but will make it easier to diagnose + lockup related problems for dma-buffers shared across multiple + devices. + config DMA_CMA bool "DMA Contiguous Memory Allocator" depends on HAVE_DMA_CONTIGUOUS && CMA diff --git a/drivers/base/Makefile b/drivers/base/Makefile index 04b314e0fa51..4aab26ec0292 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -10,7 +10,6 @@ obj-$(CONFIG_DMA_CMA) += dma-contiguous.o obj-y += power/ obj-$(CONFIG_HAS_DMA) += dma-mapping.o obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o -obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf.o reservation.o obj-$(CONFIG_ISA) += isa.o obj-$(CONFIG_FW_LOADER) += firmware_class.o obj-$(CONFIG_NUMA) += node.o diff --git a/drivers/base/component.c b/drivers/base/component.c index c4778995cd72..f748430bb654 100644 --- a/drivers/base/component.c +++ b/drivers/base/component.c @@ -18,6 +18,15 @@ #include <linux/mutex.h> #include <linux/slab.h> +struct component_match { + size_t alloc; + size_t num; + struct { + void *data; + int (*fn)(struct device *, void *); + } compare[0]; +}; + struct master { struct list_head node; struct list_head components; @@ -25,6 +34,7 @@ struct master { const struct component_master_ops *ops; struct device *dev; + struct component_match *match; }; struct component { @@ -69,6 +79,11 @@ static void component_detach_master(struct master *master, struct component *c) c->master = NULL; } +/* + * Add a component to a master, finding the component via the compare + * function and compare data. This is safe to call for duplicate matches + * and will not result in the same component being added multiple times. + */ int component_master_add_child(struct master *master, int (*compare)(struct device *, void *), void *compare_data) { @@ -76,11 +91,12 @@ int component_master_add_child(struct master *master, int ret = -ENXIO; list_for_each_entry(c, &component_list, node) { - if (c->master) + if (c->master && c->master != master) continue; if (compare(c->dev, compare_data)) { - component_attach_master(master, c); + if (!c->master) + component_attach_master(master, c); ret = 0; break; } @@ -90,6 +106,34 @@ int component_master_add_child(struct master *master, } EXPORT_SYMBOL_GPL(component_master_add_child); +static int find_components(struct master *master) +{ + struct component_match *match = master->match; + size_t i; + int ret = 0; + + if (!match) { + /* + * Search the list of components, looking for components that + * belong to this master, and attach them to the master. + */ + return master->ops->add_components(master->dev, master); + } + + /* + * Scan the array of match functions and attach + * any components which are found to this master. + */ + for (i = 0; i < match->num; i++) { + ret = component_master_add_child(master, + match->compare[i].fn, + match->compare[i].data); + if (ret) + break; + } + return ret; +} + /* Detach all attached components from this master */ static void master_remove_components(struct master *master) { @@ -113,44 +157,44 @@ static void master_remove_components(struct master *master) static int try_to_bring_up_master(struct master *master, struct component *component) { - int ret = 0; + int ret; - if (!master->bound) { - /* - * Search the list of components, looking for components that - * belong to this master, and attach them to the master. - */ - if (master->ops->add_components(master->dev, master)) { - /* Failed to find all components */ - master_remove_components(master); - ret = 0; - goto out; - } + if (master->bound) + return 0; - if (component && component->master != master) { - master_remove_components(master); - ret = 0; - goto out; - } + /* + * Search the list of components, looking for components that + * belong to this master, and attach them to the master. + */ + if (find_components(master)) { + /* Failed to find all components */ + ret = 0; + goto out; + } - if (!devres_open_group(master->dev, NULL, GFP_KERNEL)) { - ret = -ENOMEM; - goto out; - } + if (component && component->master != master) { + ret = 0; + goto out; + } - /* Found all components */ - ret = master->ops->bind(master->dev); - if (ret < 0) { - devres_release_group(master->dev, NULL); - dev_info(master->dev, "master bind failed: %d\n", ret); - master_remove_components(master); - goto out; - } + if (!devres_open_group(master->dev, NULL, GFP_KERNEL)) { + ret = -ENOMEM; + goto out; + } - master->bound = true; - ret = 1; + /* Found all components */ + ret = master->ops->bind(master->dev); + if (ret < 0) { + devres_release_group(master->dev, NULL); + dev_info(master->dev, "master bind failed: %d\n", ret); + goto out; } + + master->bound = true; + return 1; + out: + master_remove_components(master); return ret; } @@ -180,18 +224,89 @@ static void take_down_master(struct master *master) master_remove_components(master); } -int component_master_add(struct device *dev, - const struct component_master_ops *ops) +static size_t component_match_size(size_t num) +{ + return offsetof(struct component_match, compare[num]); +} + +static struct component_match *component_match_realloc(struct device *dev, + struct component_match *match, size_t num) +{ + struct component_match *new; + + if (match && match->alloc == num) + return match; + + new = devm_kmalloc(dev, component_match_size(num), GFP_KERNEL); + if (!new) + return ERR_PTR(-ENOMEM); + + if (match) { + memcpy(new, match, component_match_size(min(match->num, num))); + devm_kfree(dev, match); + } else { + new->num = 0; + } + + new->alloc = num; + + return new; +} + +/* + * Add a component to be matched. + * + * The match array is first created or extended if necessary. + */ +void component_match_add(struct device *dev, struct component_match **matchptr, + int (*compare)(struct device *, void *), void *compare_data) +{ + struct component_match *match = *matchptr; + + if (IS_ERR(match)) + return; + + if (!match || match->num == match->alloc) { + size_t new_size = match ? match->alloc + 16 : 15; + + match = component_match_realloc(dev, match, new_size); + + *matchptr = match; + + if (IS_ERR(match)) + return; + } + + match->compare[match->num].fn = compare; + match->compare[match->num].data = compare_data; + match->num++; +} +EXPORT_SYMBOL(component_match_add); + +int component_master_add_with_match(struct device *dev, + const struct component_master_ops *ops, + struct component_match *match) { struct master *master; int ret; + if (ops->add_components && match) + return -EINVAL; + + if (match) { + /* Reallocate the match array for its true size */ + match = component_match_realloc(dev, match, match->num); + if (IS_ERR(match)) + return PTR_ERR(match); + } + master = kzalloc(sizeof(*master), GFP_KERNEL); if (!master) return -ENOMEM; master->dev = dev; master->ops = ops; + master->match = match; INIT_LIST_HEAD(&master->components); /* Add to the list of available masters. */ @@ -209,6 +324,13 @@ int component_master_add(struct device *dev, return ret < 0 ? ret : 0; } +EXPORT_SYMBOL_GPL(component_master_add_with_match); + +int component_master_add(struct device *dev, + const struct component_master_ops *ops) +{ + return component_master_add_with_match(dev, ops, NULL); +} EXPORT_SYMBOL_GPL(component_master_add); void component_master_del(struct device *dev, diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c index d276e33880be..da77791793f1 100644 --- a/drivers/base/firmware_class.c +++ b/drivers/base/firmware_class.c @@ -100,10 +100,16 @@ static inline long firmware_loading_timeout(void) #define FW_OPT_UEVENT (1U << 0) #define FW_OPT_NOWAIT (1U << 1) #ifdef CONFIG_FW_LOADER_USER_HELPER -#define FW_OPT_FALLBACK (1U << 2) +#define FW_OPT_USERHELPER (1U << 2) #else -#define FW_OPT_FALLBACK 0 +#define FW_OPT_USERHELPER 0 #endif +#ifdef CONFIG_FW_LOADER_USER_HELPER_FALLBACK +#define FW_OPT_FALLBACK FW_OPT_USERHELPER +#else +#define FW_OPT_FALLBACK 0 +#endif +#define FW_OPT_NO_WARN (1U << 3) struct firmware_cache { /* firmware_buf instance will be added into the below list */ @@ -279,26 +285,15 @@ static const char * const fw_path[] = { module_param_string(path, fw_path_para, sizeof(fw_path_para), 0644); MODULE_PARM_DESC(path, "customized firmware image search path with a higher priority than default path"); -/* Don't inline this: 'struct kstat' is biggish */ -static noinline_for_stack int fw_file_size(struct file *file) -{ - struct kstat st; - if (vfs_getattr(&file->f_path, &st)) - return -1; - if (!S_ISREG(st.mode)) - return -1; - if (st.size != (int)st.size) - return -1; - return st.size; -} - static int fw_read_file_contents(struct file *file, struct firmware_buf *fw_buf) { int size; char *buf; int rc; - size = fw_file_size(file); + if (!S_ISREG(file_inode(file)->i_mode)) + return -EINVAL; + size = i_size_read(file_inode(file)); if (size <= 0) return -EINVAL; buf = vmalloc(size); @@ -718,7 +713,7 @@ out: static int fw_realloc_buffer(struct firmware_priv *fw_priv, int min_size) { struct firmware_buf *buf = fw_priv->buf; - int pages_needed = ALIGN(min_size, PAGE_SIZE) >> PAGE_SHIFT; + int pages_needed = PAGE_ALIGN(min_size) >> PAGE_SHIFT; /* If the array of pages is too small, grow it... */ if (buf->page_array_size < pages_needed) { @@ -911,7 +906,9 @@ static int _request_firmware_load(struct firmware_priv *fw_priv, wait_for_completion(&buf->completion); cancel_delayed_work_sync(&fw_priv->timeout_work); - if (!buf->data) + if (is_fw_load_aborted(buf)) + retval = -EAGAIN; + else if (!buf->data) retval = -ENOMEM; device_remove_file(f_dev, &dev_attr_loading); @@ -1111,10 +1108,11 @@ _request_firmware(const struct firmware **firmware_p, const char *name, ret = fw_get_filesystem_firmware(device, fw->priv); if (ret) { - if (opt_flags & FW_OPT_FALLBACK) { + if (!(opt_flags & FW_OPT_NO_WARN)) dev_warn(device, - "Direct firmware load failed with error %d\n", - ret); + "Direct firmware load for %s failed with error %d\n", + name, ret); + if (opt_flags & FW_OPT_USERHELPER) { dev_warn(device, "Falling back to user helper\n"); ret = fw_load_from_user_helper(fw, name, device, opt_flags, timeout); @@ -1171,7 +1169,6 @@ request_firmware(const struct firmware **firmware_p, const char *name, } EXPORT_SYMBOL(request_firmware); -#ifdef CONFIG_FW_LOADER_USER_HELPER /** * request_firmware: - load firmware directly without usermode helper * @firmware_p: pointer to firmware image @@ -1188,12 +1185,12 @@ int request_firmware_direct(const struct firmware **firmware_p, { int ret; __module_get(THIS_MODULE); - ret = _request_firmware(firmware_p, name, device, FW_OPT_UEVENT); + ret = _request_firmware(firmware_p, name, device, + FW_OPT_UEVENT | FW_OPT_NO_WARN); module_put(THIS_MODULE); return ret; } EXPORT_SYMBOL_GPL(request_firmware_direct); -#endif /** * release_firmware: - release the resource associated with a firmware image @@ -1277,7 +1274,7 @@ request_firmware_nowait( fw_work->context = context; fw_work->cont = cont; fw_work->opt_flags = FW_OPT_NOWAIT | FW_OPT_FALLBACK | - (uevent ? FW_OPT_UEVENT : 0); + (uevent ? FW_OPT_UEVENT : FW_OPT_USERHELPER); if (!try_module_get(module)) { kfree(fw_work); diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 00f2208949d1..ab4f4ce02722 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -24,6 +24,7 @@ #include <linux/idr.h> #include <linux/acpi.h> #include <linux/clk/clk-conf.h> +#include <linux/limits.h> #include "base.h" #include "power/power.h" @@ -176,7 +177,7 @@ EXPORT_SYMBOL_GPL(platform_add_devices); struct platform_object { struct platform_device pdev; - char name[1]; + char name[]; }; /** @@ -202,6 +203,7 @@ static void platform_device_release(struct device *dev) kfree(pa->pdev.dev.platform_data); kfree(pa->pdev.mfd_cell); kfree(pa->pdev.resource); + kfree(pa->pdev.driver_override); kfree(pa); } @@ -217,7 +219,7 @@ struct platform_device *platform_device_alloc(const char *name, int id) { struct platform_object *pa; - pa = kzalloc(sizeof(struct platform_object) + strlen(name), GFP_KERNEL); + pa = kzalloc(sizeof(*pa) + strlen(name) + 1, GFP_KERNEL); if (pa) { strcpy(pa->name, name); pa->pdev.name = pa->name; @@ -713,8 +715,49 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *a, } static DEVICE_ATTR_RO(modalias); +static ssize_t driver_override_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct platform_device *pdev = to_platform_device(dev); + char *driver_override, *old = pdev->driver_override, *cp; + + if (count > PATH_MAX) + return -EINVAL; + + driver_override = kstrndup(buf, count, GFP_KERNEL); + if (!driver_override) + return -ENOMEM; + + cp = strchr(driver_override, '\n'); + if (cp) + *cp = '\0'; + + if (strlen(driver_override)) { + pdev->driver_override = driver_override; + } else { + kfree(driver_override); + pdev->driver_override = NULL; + } + + kfree(old); + + return count; +} + +static ssize_t driver_override_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct platform_device *pdev = to_platform_device(dev); + + return sprintf(buf, "%s\n", pdev->driver_override); +} +static DEVICE_ATTR_RW(driver_override); + + static struct attribute *platform_dev_attrs[] = { &dev_attr_modalias.attr, + &dev_attr_driver_override.attr, NULL, }; ATTRIBUTE_GROUPS(platform_dev); @@ -770,6 +813,10 @@ static int platform_match(struct device *dev, struct device_driver *drv) struct platform_device *pdev = to_platform_device(dev); struct platform_driver *pdrv = to_platform_driver(drv); + /* When driver_override is set, only bind to the matching driver */ + if (pdev->driver_override) + return !strcmp(pdev->driver_override, drv->name); + /* Attempt an OF style match first */ if (of_driver_match_device(dev, drv)) return 1; diff --git a/drivers/base/reservation.c b/drivers/base/reservation.c deleted file mode 100644 index a73fbf3b8e56..000000000000 --- a/drivers/base/reservation.c +++ /dev/null @@ -1,39 +0,0 @@ -/* - * Copyright (C) 2012-2013 Canonical Ltd - * - * Based on bo.c which bears the following copyright notice, - * but is dual licensed: - * - * Copyright (c) 2006-2009 VMware, Inc., Palo Alto, CA., USA - * All Rights Reserved. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the - * "Software"), to deal in the Software without restriction, including - * without limitation the rights to use, copy, modify, merge, publish, - * distribute, sub license, and/or sell copies of the Software, and to - * permit persons to whom the Software is furnished to do so, subject to - * the following conditions: - * - * The above copyright notice and this permission notice (including the - * next paragraph) shall be included in all copies or substantial portions - * of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, - * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR - * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE - * USE OR OTHER DEALINGS IN THE SOFTWARE. - * - **************************************************************************/ -/* - * Authors: Thomas Hellstrom <thellstrom-at-vmware-dot-com> - */ - -#include <linux/reservation.h> -#include <linux/export.h> - -DEFINE_WW_CLASS(reservation_ww_class); -EXPORT_SYMBOL(reservation_ww_class); diff --git a/drivers/bus/brcmstb_gisb.c b/drivers/bus/brcmstb_gisb.c index 6159b7752a64..f2cd6a2d40b4 100644 --- a/drivers/bus/brcmstb_gisb.c +++ b/drivers/bus/brcmstb_gisb.c @@ -212,9 +212,9 @@ static int brcmstb_gisb_arb_probe(struct platform_device *pdev) mutex_init(&gdev->lock); INIT_LIST_HEAD(&gdev->next); - gdev->base = devm_request_and_ioremap(&pdev->dev, r); - if (!gdev->base) - return -ENOMEM; + gdev->base = devm_ioremap_resource(&pdev->dev, r); + if (IS_ERR(gdev->base)) + return PTR_ERR(gdev->base); err = devm_request_irq(&pdev->dev, timeout_irq, brcmstb_gisb_timeout_handler, 0, pdev->name, diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile new file mode 100644 index 000000000000..57a675f90cd0 --- /dev/null +++ b/drivers/dma-buf/Makefile @@ -0,0 +1 @@ +obj-y := dma-buf.o fence.o reservation.o seqno-fence.o diff --git a/drivers/base/dma-buf.c b/drivers/dma-buf/dma-buf.c index 840c7fa80983..f3014c448e1e 100644 --- a/drivers/base/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -25,10 +25,13 @@ #include <linux/fs.h> #include <linux/slab.h> #include <linux/dma-buf.h> +#include <linux/fence.h> #include <linux/anon_inodes.h> #include <linux/export.h> #include <linux/debugfs.h> #include <linux/seq_file.h> +#include <linux/poll.h> +#include <linux/reservation.h> static inline int is_dma_buf_file(struct file *); @@ -50,12 +53,25 @@ static int dma_buf_release(struct inode *inode, struct file *file) BUG_ON(dmabuf->vmapping_counter); + /* + * Any fences that a dma-buf poll can wait on should be signaled + * before releasing dma-buf. This is the responsibility of each + * driver that uses the reservation objects. + * + * If you hit this BUG() it means someone dropped their ref to the + * dma-buf while still having pending operation to the buffer. + */ + BUG_ON(dmabuf->cb_shared.active || dmabuf->cb_excl.active); + dmabuf->ops->release(dmabuf); mutex_lock(&db_list.lock); list_del(&dmabuf->list_node); mutex_unlock(&db_list.lock); + if (dmabuf->resv == (struct reservation_object *)&dmabuf[1]) + reservation_object_fini(dmabuf->resv); + kfree(dmabuf); return 0; } @@ -103,10 +119,141 @@ static loff_t dma_buf_llseek(struct file *file, loff_t offset, int whence) return base + offset; } +static void dma_buf_poll_cb(struct fence *fence, struct fence_cb *cb) +{ + struct dma_buf_poll_cb_t *dcb = (struct dma_buf_poll_cb_t *)cb; + unsigned long flags; + + spin_lock_irqsave(&dcb->poll->lock, flags); + wake_up_locked_poll(dcb->poll, dcb->active); + dcb->active = 0; + spin_unlock_irqrestore(&dcb->poll->lock, flags); +} + +static unsigned int dma_buf_poll(struct file *file, poll_table *poll) +{ + struct dma_buf *dmabuf; + struct reservation_object *resv; + struct reservation_object_list *fobj; + struct fence *fence_excl; + unsigned long events; + unsigned shared_count, seq; + + dmabuf = file->private_data; + if (!dmabuf || !dmabuf->resv) + return POLLERR; + + resv = dmabuf->resv; + + poll_wait(file, &dmabuf->poll, poll); + + events = poll_requested_events(poll) & (POLLIN | POLLOUT); + if (!events) + return 0; + +retry: + seq = read_seqcount_begin(&resv->seq); + rcu_read_lock(); + + fobj = rcu_dereference(resv->fence); + if (fobj) + shared_count = fobj->shared_count; + else + shared_count = 0; + fence_excl = rcu_dereference(resv->fence_excl); + if (read_seqcount_retry(&resv->seq, seq)) { + rcu_read_unlock(); + goto retry; + } + + if (fence_excl && (!(events & POLLOUT) || shared_count == 0)) { + struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_excl; + unsigned long pevents = POLLIN; + + if (shared_count == 0) + pevents |= POLLOUT; + + spin_lock_irq(&dmabuf->poll.lock); + if (dcb->active) { + dcb->active |= pevents; + events &= ~pevents; + } else + dcb->active = pevents; + spin_unlock_irq(&dmabuf->poll.lock); + + if (events & pevents) { + if (!fence_get_rcu(fence_excl)) { + /* force a recheck */ + events &= ~pevents; + dma_buf_poll_cb(NULL, &dcb->cb); + } else if (!fence_add_callback(fence_excl, &dcb->cb, + dma_buf_poll_cb)) { + events &= ~pevents; + fence_put(fence_excl); + } else { + /* + * No callback queued, wake up any additional + * waiters. + */ + fence_put(fence_excl); + dma_buf_poll_cb(NULL, &dcb->cb); + } + } + } + + if ((events & POLLOUT) && shared_count > 0) { + struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_shared; + int i; + + /* Only queue a new callback if no event has fired yet */ + spin_lock_irq(&dmabuf->poll.lock); + if (dcb->active) + events &= ~POLLOUT; + else + dcb->active = POLLOUT; + spin_unlock_irq(&dmabuf->poll.lock); + + if (!(events & POLLOUT)) + goto out; + + for (i = 0; i < shared_count; ++i) { + struct fence *fence = rcu_dereference(fobj->shared[i]); + + if (!fence_get_rcu(fence)) { + /* + * fence refcount dropped to zero, this means + * that fobj has been freed + * + * call dma_buf_poll_cb and force a recheck! + */ + events &= ~POLLOUT; + dma_buf_poll_cb(NULL, &dcb->cb); + break; + } + if (!fence_add_callback(fence, &dcb->cb, + dma_buf_poll_cb)) { + fence_put(fence); + events &= ~POLLOUT; + break; + } + fence_put(fence); + } + + /* No callback queued, wake up any additional waiters. */ + if (i == shared_count) + dma_buf_poll_cb(NULL, &dcb->cb); + } + +out: + rcu_read_unlock(); + return events; +} + static const struct file_operations dma_buf_fops = { .release = dma_buf_release, .mmap = dma_buf_mmap_internal, .llseek = dma_buf_llseek, + .poll = dma_buf_poll, }; /* @@ -128,6 +275,7 @@ static inline int is_dma_buf_file(struct file *file) * @size: [in] Size of the buffer * @flags: [in] mode flags for the file. * @exp_name: [in] name of the exporting module - useful for debugging. + * @resv: [in] reservation-object, NULL to allocate default one. * * Returns, on success, a newly created dma_buf object, which wraps the * supplied private data and operations for dma_buf_ops. On either missing @@ -135,10 +283,17 @@ static inline int is_dma_buf_file(struct file *file) * */ struct dma_buf *dma_buf_export_named(void *priv, const struct dma_buf_ops *ops, - size_t size, int flags, const char *exp_name) + size_t size, int flags, const char *exp_name, + struct reservation_object *resv) { struct dma_buf *dmabuf; struct file *file; + size_t alloc_size = sizeof(struct dma_buf); + if (!resv) + alloc_size += sizeof(struct reservation_object); + else + /* prevent &dma_buf[1] == dma_buf->resv */ + alloc_size += 1; if (WARN_ON(!priv || !ops || !ops->map_dma_buf @@ -150,7 +305,7 @@ struct dma_buf *dma_buf_export_named(void *priv, const struct dma_buf_ops *ops, return ERR_PTR(-EINVAL); } - dmabuf = kzalloc(sizeof(struct dma_buf), GFP_KERNEL); + dmabuf = kzalloc(alloc_size, GFP_KERNEL); if (dmabuf == NULL) return ERR_PTR(-ENOMEM); @@ -158,6 +313,15 @@ struct dma_buf *dma_buf_export_named(void *priv, const struct dma_buf_ops *ops, dmabuf->ops = ops; dmabuf->size = size; dmabuf->exp_name = exp_name; + init_waitqueue_head(&dmabuf->poll); + dmabuf->cb_excl.poll = dmabuf->cb_shared.poll = &dmabuf->poll; + dmabuf->cb_excl.active = dmabuf->cb_shared.active = 0; + + if (!resv) { + resv = (struct reservation_object *)&dmabuf[1]; + reservation_object_init(resv); + } + dmabuf->resv = resv; file = anon_inode_getfile("dmabuf", &dma_buf_fops, dmabuf, flags); if (IS_ERR(file)) { diff --git a/drivers/dma-buf/fence.c b/drivers/dma-buf/fence.c new file mode 100644 index 000000000000..4222cb2aa96a --- /dev/null +++ b/drivers/dma-buf/fence.c @@ -0,0 +1,431 @@ +/* + * Fence mechanism for dma-buf and to allow for asynchronous dma access + * + * Copyright (C) 2012 Canonical Ltd + * Copyright (C) 2012 Texas Instruments + * + * Authors: + * Rob Clark <robdclark@gmail.com> + * Maarten Lankhorst <maarten.lankhorst@canonical.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License 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. + */ + +#include <linux/slab.h> +#include <linux/export.h> +#include <linux/atomic.h> +#include <linux/fence.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/fence.h> + +EXPORT_TRACEPOINT_SYMBOL(fence_annotate_wait_on); +EXPORT_TRACEPOINT_SYMBOL(fence_emit); + +/** + * fence context counter: each execution context should have its own + * fence context, this allows checking if fences belong to the same + * context or not. One device can have multiple separate contexts, + * and they're used if some engine can run independently of another. + */ +static atomic_t fence_context_counter = ATOMIC_INIT(0); + +/** + * fence_context_alloc - allocate an array of fence contexts + * @num: [in] amount of contexts to allocate + * + * This function will return the first index of the number of fences allocated. + * The fence context is used for setting fence->context to a unique number. + */ +unsigned fence_context_alloc(unsigned num) +{ + BUG_ON(!num); + return atomic_add_return(num, &fence_context_counter) - num; +} +EXPORT_SYMBOL(fence_context_alloc); + +/** + * fence_signal_locked - signal completion of a fence + * @fence: the fence to signal + * + * Signal completion for software callbacks on a fence, this will unblock + * fence_wait() calls and run all the callbacks added with + * fence_add_callback(). Can be called multiple times, but since a fence + * can only go from unsignaled to signaled state, it will only be effective + * the first time. + * + * Unlike fence_signal, this function must be called with fence->lock held. + */ +int fence_signal_locked(struct fence *fence) +{ + struct fence_cb *cur, *tmp; + int ret = 0; + + if (WARN_ON(!fence)) + return -EINVAL; + + if (!ktime_to_ns(fence->timestamp)) { + fence->timestamp = ktime_get(); + smp_mb__before_atomic(); + } + + if (test_and_set_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags)) { + ret = -EINVAL; + + /* + * we might have raced with the unlocked fence_signal, + * still run through all callbacks + */ + } else + trace_fence_signaled(fence); + + list_for_each_entry_safe(cur, tmp, &fence->cb_list, node) { + list_del_init(&cur->node); + cur->func(fence, cur); + } + return ret; +} +EXPORT_SYMBOL(fence_signal_locked); + +/** + * fence_signal - signal completion of a fence + * @fence: the fence to signal + * + * Signal completion for software callbacks on a fence, this will unblock + * fence_wait() calls and run all the callbacks added with + * fence_add_callback(). Can be called multiple times, but since a fence + * can only go from unsignaled to signaled state, it will only be effective + * the first time. + */ +int fence_signal(struct fence *fence) +{ + unsigned long flags; + + if (!fence) + return -EINVAL; + + if (!ktime_to_ns(fence->timestamp)) { + fence->timestamp = ktime_get(); + smp_mb__before_atomic(); + } + + if (test_and_set_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + return -EINVAL; + + trace_fence_signaled(fence); + + if (test_bit(FENCE_FLAG_ENABLE_SIGNAL_BIT, &fence->flags)) { + struct fence_cb *cur, *tmp; + + spin_lock_irqsave(fence->lock, flags); + list_for_each_entry_safe(cur, tmp, &fence->cb_list, node) { + list_del_init(&cur->node); + cur->func(fence, cur); + } + spin_unlock_irqrestore(fence->lock, flags); + } + return 0; +} +EXPORT_SYMBOL(fence_signal); + +/** + * fence_wait_timeout - sleep until the fence gets signaled + * or until timeout elapses + * @fence: [in] the fence to wait on + * @intr: [in] if true, do an interruptible wait + * @timeout: [in] timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT + * + * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or the + * remaining timeout in jiffies on success. Other error values may be + * returned on custom implementations. + * + * Performs a synchronous wait on this fence. It is assumed the caller + * directly or indirectly (buf-mgr between reservation and committing) + * holds a reference to the fence, otherwise the fence might be + * freed before return, resulting in undefined behavior. + */ +signed long +fence_wait_timeout(struct fence *fence, bool intr, signed long timeout) +{ + signed long ret; + + if (WARN_ON(timeout < 0)) + return -EINVAL; + + trace_fence_wait_start(fence); + ret = fence->ops->wait(fence, intr, timeout); + trace_fence_wait_end(fence); + return ret; +} +EXPORT_SYMBOL(fence_wait_timeout); + +void fence_release(struct kref *kref) +{ + struct fence *fence = + container_of(kref, struct fence, refcount); + + trace_fence_destroy(fence); + + BUG_ON(!list_empty(&fence->cb_list)); + + if (fence->ops->release) + fence->ops->release(fence); + else + fence_free(fence); +} +EXPORT_SYMBOL(fence_release); + +void fence_free(struct fence *fence) +{ + kfree_rcu(fence, rcu); +} +EXPORT_SYMBOL(fence_free); + +/** + * fence_enable_sw_signaling - enable signaling on fence + * @fence: [in] the fence to enable + * + * this will request for sw signaling to be enabled, to make the fence + * complete as soon as possible + */ +void fence_enable_sw_signaling(struct fence *fence) +{ + unsigned long flags; + + if (!test_and_set_bit(FENCE_FLAG_ENABLE_SIGNAL_BIT, &fence->flags) && + !test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags)) { + trace_fence_enable_signal(fence); + + spin_lock_irqsave(fence->lock, flags); + + if (!fence->ops->enable_signaling(fence)) + fence_signal_locked(fence); + + spin_unlock_irqrestore(fence->lock, flags); + } +} +EXPORT_SYMBOL(fence_enable_sw_signaling); + +/** + * fence_add_callback - add a callback to be called when the fence + * is signaled + * @fence: [in] the fence to wait on + * @cb: [in] the callback to register + * @func: [in] the function to call + * + * cb will be initialized by fence_add_callback, no initialization + * by the caller is required. Any number of callbacks can be registered + * to a fence, but a callback can only be registered to one fence at a time. + * + * Note that the callback can be called from an atomic context. If + * fence is already signaled, this function will return -ENOENT (and + * *not* call the callback) + * + * Add a software callback to the fence. Same restrictions apply to + * refcount as it does to fence_wait, however the caller doesn't need to + * keep a refcount to fence afterwards: when software access is enabled, + * the creator of the fence is required to keep the fence alive until + * after it signals with fence_signal. The callback itself can be called + * from irq context. + * + */ +int fence_add_callback(struct fence *fence, struct fence_cb *cb, + fence_func_t func) +{ + unsigned long flags; + int ret = 0; + bool was_set; + + if (WARN_ON(!fence || !func)) + return -EINVAL; + + if (test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags)) { + INIT_LIST_HEAD(&cb->node); + return -ENOENT; + } + + spin_lock_irqsave(fence->lock, flags); + + was_set = test_and_set_bit(FENCE_FLAG_ENABLE_SIGNAL_BIT, &fence->flags); + + if (test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + ret = -ENOENT; + else if (!was_set) { + trace_fence_enable_signal(fence); + + if (!fence->ops->enable_signaling(fence)) { + fence_signal_locked(fence); + ret = -ENOENT; + } + } + + if (!ret) { + cb->func = func; + list_add_tail(&cb->node, &fence->cb_list); + } else + INIT_LIST_HEAD(&cb->node); + spin_unlock_irqrestore(fence->lock, flags); + + return ret; +} +EXPORT_SYMBOL(fence_add_callback); + +/** + * fence_remove_callback - remove a callback from the signaling list + * @fence: [in] the fence to wait on + * @cb: [in] the callback to remove + * + * Remove a previously queued callback from the fence. This function returns + * true if the callback is succesfully removed, or false if the fence has + * already been signaled. + * + * *WARNING*: + * Cancelling a callback should only be done if you really know what you're + * doing, since deadlocks and race conditions could occur all too easily. For + * this reason, it should only ever be done on hardware lockup recovery, + * with a reference held to the fence. + */ +bool +fence_remove_callback(struct fence *fence, struct fence_cb *cb) +{ + unsigned long flags; + bool ret; + + spin_lock_irqsave(fence->lock, flags); + + ret = !list_empty(&cb->node); + if (ret) + list_del_init(&cb->node); + + spin_unlock_irqrestore(fence->lock, flags); + + return ret; +} +EXPORT_SYMBOL(fence_remove_callback); + +struct default_wait_cb { + struct fence_cb base; + struct task_struct *task; +}; + +static void +fence_default_wait_cb(struct fence *fence, struct fence_cb *cb) +{ + struct default_wait_cb *wait = + container_of(cb, struct default_wait_cb, base); + + wake_up_state(wait->task, TASK_NORMAL); +} + +/** + * fence_default_wait - default sleep until the fence gets signaled + * or until timeout elapses + * @fence: [in] the fence to wait on + * @intr: [in] if true, do an interruptible wait + * @timeout: [in] timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT + * + * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or the + * remaining timeout in jiffies on success. + */ +signed long +fence_default_wait(struct fence *fence, bool intr, signed long timeout) +{ + struct default_wait_cb cb; + unsigned long flags; + signed long ret = timeout; + bool was_set; + + if (test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + return timeout; + + spin_lock_irqsave(fence->lock, flags); + + if (intr && signal_pending(current)) { + ret = -ERESTARTSYS; + goto out; + } + + was_set = test_and_set_bit(FENCE_FLAG_ENABLE_SIGNAL_BIT, &fence->flags); + + if (test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + goto out; + + if (!was_set) { + trace_fence_enable_signal(fence); + + if (!fence->ops->enable_signaling(fence)) { + fence_signal_locked(fence); + goto out; + } + } + + cb.base.func = fence_default_wait_cb; + cb.task = current; + list_add(&cb.base.node, &fence->cb_list); + + while (!test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->flags) && ret > 0) { + if (intr) + __set_current_state(TASK_INTERRUPTIBLE); + else + __set_current_state(TASK_UNINTERRUPTIBLE); + spin_unlock_irqrestore(fence->lock, flags); + + ret = schedule_timeout(ret); + + spin_lock_irqsave(fence->lock, flags); + if (ret > 0 && intr && signal_pending(current)) + ret = -ERESTARTSYS; + } + + if (!list_empty(&cb.base.node)) + list_del(&cb.base.node); + __set_current_state(TASK_RUNNING); + +out: + spin_unlock_irqrestore(fence->lock, flags); + return ret; +} +EXPORT_SYMBOL(fence_default_wait); + +/** + * fence_init - Initialize a custom fence. + * @fence: [in] the fence to initialize + * @ops: [in] the fence_ops for operations on this fence + * @lock: [in] the irqsafe spinlock to use for locking this fence + * @context: [in] the execution context this fence is run on + * @seqno: [in] a linear increasing sequence number for this context + * + * Initializes an allocated fence, the caller doesn't have to keep its + * refcount after committing with this fence, but it will need to hold a + * refcount again if fence_ops.enable_signaling gets called. This can + * be used for other implementing other types of fence. + * + * context and seqno are used for easy comparison between fences, allowing + * to check which fence is later by simply using fence_later. + */ +void +fence_init(struct fence *fence, const struct fence_ops *ops, + spinlock_t *lock, unsigned context, unsigned seqno) +{ + BUG_ON(!lock); + BUG_ON(!ops || !ops->wait || !ops->enable_signaling || + !ops->get_driver_name || !ops->get_timeline_name); + + kref_init(&fence->refcount); + fence->ops = ops; + INIT_LIST_HEAD(&fence->cb_list); + fence->lock = lock; + fence->context = context; + fence->seqno = seqno; + fence->flags = 0UL; + + trace_fence_init(fence); +} +EXPORT_SYMBOL(fence_init); diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c new file mode 100644 index 000000000000..3c97c8fa8d02 --- /dev/null +++ b/drivers/dma-buf/reservation.c @@ -0,0 +1,477 @@ +/* + * Copyright (C) 2012-2014 Canonical Ltd (Maarten Lankhorst) + * + * Based on bo.c which bears the following copyright notice, + * but is dual licensed: + * + * Copyright (c) 2006-2009 VMware, Inc., Palo Alto, CA., USA + * All Rights Reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sub license, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, + * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + * USE OR OTHER DEALINGS IN THE SOFTWARE. + * + **************************************************************************/ +/* + * Authors: Thomas Hellstrom <thellstrom-at-vmware-dot-com> + */ + +#include <linux/reservation.h> +#include <linux/export.h> + +DEFINE_WW_CLASS(reservation_ww_class); +EXPORT_SYMBOL(reservation_ww_class); + +struct lock_class_key reservation_seqcount_class; +EXPORT_SYMBOL(reservation_seqcount_class); + +const char reservation_seqcount_string[] = "reservation_seqcount"; +EXPORT_SYMBOL(reservation_seqcount_string); +/* + * Reserve space to add a shared fence to a reservation_object, + * must be called with obj->lock held. + */ +int reservation_object_reserve_shared(struct reservation_object *obj) +{ + struct reservation_object_list *fobj, *old; + u32 max; + + old = reservation_object_get_list(obj); + + if (old && old->shared_max) { + if (old->shared_count < old->shared_max) { + /* perform an in-place update */ + kfree(obj->staged); + obj->staged = NULL; + return 0; + } else + max = old->shared_max * 2; + } else + max = 4; + + /* + * resize obj->staged or allocate if it doesn't exist, + * noop if already correct size + */ + fobj = krealloc(obj->staged, offsetof(typeof(*fobj), shared[max]), + GFP_KERNEL); + if (!fobj) + return -ENOMEM; + + obj->staged = fobj; + fobj->shared_max = max; + return 0; +} +EXPORT_SYMBOL(reservation_object_reserve_shared); + +static void +reservation_object_add_shared_inplace(struct reservation_object *obj, + struct reservation_object_list *fobj, + struct fence *fence) +{ + u32 i; + + fence_get(fence); + + preempt_disable(); + write_seqcount_begin(&obj->seq); + + for (i = 0; i < fobj->shared_count; ++i) { + struct fence *old_fence; + + old_fence = rcu_dereference_protected(fobj->shared[i], + reservation_object_held(obj)); + + if (old_fence->context == fence->context) { + /* memory barrier is added by write_seqcount_begin */ + RCU_INIT_POINTER(fobj->shared[i], fence); + write_seqcount_end(&obj->seq); + preempt_enable(); + + fence_put(old_fence); + return; + } + } + + /* + * memory barrier is added by write_seqcount_begin, + * fobj->shared_count is protected by this lock too + */ + RCU_INIT_POINTER(fobj->shared[fobj->shared_count], fence); + fobj->shared_count++; + + write_seqcount_end(&obj->seq); + preempt_enable(); +} + +static void +reservation_object_add_shared_replace(struct reservation_object *obj, + struct reservation_object_list *old, + struct reservation_object_list *fobj, + struct fence *fence) +{ + unsigned i; + struct fence *old_fence = NULL; + + fence_get(fence); + + if (!old) { + RCU_INIT_POINTER(fobj->shared[0], fence); + fobj->shared_count = 1; + goto done; + } + + /* + * no need to bump fence refcounts, rcu_read access + * requires the use of kref_get_unless_zero, and the + * references from the old struct are carried over to + * the new. + */ + fobj->shared_count = old->shared_count; + + for (i = 0; i < old->shared_count; ++i) { + struct fence *check; + + check = rcu_dereference_protected(old->shared[i], + reservation_object_held(obj)); + + if (!old_fence && check->context == fence->context) { + old_fence = check; + RCU_INIT_POINTER(fobj->shared[i], fence); + } else + RCU_INIT_POINTER(fobj->shared[i], check); + } + if (!old_fence) { + RCU_INIT_POINTER(fobj->shared[fobj->shared_count], fence); + fobj->shared_count++; + } + +done: + preempt_disable(); + write_seqcount_begin(&obj->seq); + /* + * RCU_INIT_POINTER can be used here, + * seqcount provides the necessary barriers + */ + RCU_INIT_POINTER(obj->fence, fobj); + write_seqcount_end(&obj->seq); + preempt_enable(); + + if (old) + kfree_rcu(old, rcu); + + if (old_fence) + fence_put(old_fence); +} + +/* + * Add a fence to a shared slot, obj->lock must be held, and + * reservation_object_reserve_shared_fence has been called. + */ +void reservation_object_add_shared_fence(struct reservation_object *obj, + struct fence *fence) +{ + struct reservation_object_list *old, *fobj = obj->staged; + + old = reservation_object_get_list(obj); + obj->staged = NULL; + + if (!fobj) { + BUG_ON(old->shared_count >= old->shared_max); + reservation_object_add_shared_inplace(obj, old, fence); + } else + reservation_object_add_shared_replace(obj, old, fobj, fence); +} +EXPORT_SYMBOL(reservation_object_add_shared_fence); + +void reservation_object_add_excl_fence(struct reservation_object *obj, + struct fence *fence) +{ + struct fence *old_fence = reservation_object_get_excl(obj); + struct reservation_object_list *old; + u32 i = 0; + + old = reservation_object_get_list(obj); + if (old) + i = old->shared_count; + + if (fence) + fence_get(fence); + + preempt_disable(); + write_seqcount_begin(&obj->seq); + /* write_seqcount_begin provides the necessary memory barrier */ + RCU_INIT_POINTER(obj->fence_excl, fence); + if (old) + old->shared_count = 0; + write_seqcount_end(&obj->seq); + preempt_enable(); + + /* inplace update, no shared fences */ + while (i--) + fence_put(rcu_dereference_protected(old->shared[i], + reservation_object_held(obj))); + + if (old_fence) + fence_put(old_fence); +} +EXPORT_SYMBOL(reservation_object_add_excl_fence); + +int reservation_object_get_fences_rcu(struct reservation_object *obj, + struct fence **pfence_excl, + unsigned *pshared_count, + struct fence ***pshared) +{ + unsigned shared_count = 0; + unsigned retry = 1; + struct fence **shared = NULL, *fence_excl = NULL; + int ret = 0; + + while (retry) { + struct reservation_object_list *fobj; + unsigned seq; + + seq = read_seqcount_begin(&obj->seq); + + rcu_read_lock(); + + fobj = rcu_dereference(obj->fence); + if (fobj) { + struct fence **nshared; + size_t sz = sizeof(*shared) * fobj->shared_max; + + nshared = krealloc(shared, sz, + GFP_NOWAIT | __GFP_NOWARN); + if (!nshared) { + rcu_read_unlock(); + nshared = krealloc(shared, sz, GFP_KERNEL); + if (nshared) { + shared = nshared; + continue; + } + + ret = -ENOMEM; + shared_count = 0; + break; + } + shared = nshared; + memcpy(shared, fobj->shared, sz); + shared_count = fobj->shared_count; + } else + shared_count = 0; + fence_excl = rcu_dereference(obj->fence_excl); + + retry = read_seqcount_retry(&obj->seq, seq); + if (retry) + goto unlock; + + if (!fence_excl || fence_get_rcu(fence_excl)) { + unsigned i; + + for (i = 0; i < shared_count; ++i) { + if (fence_get_rcu(shared[i])) + continue; + + /* uh oh, refcount failed, abort and retry */ + while (i--) + fence_put(shared[i]); + + if (fence_excl) { + fence_put(fence_excl); + fence_excl = NULL; + } + + retry = 1; + break; + } + } else + retry = 1; + +unlock: + rcu_read_unlock(); + } + *pshared_count = shared_count; + if (shared_count) + *pshared = shared; + else { + *pshared = NULL; + kfree(shared); + } + *pfence_excl = fence_excl; + + return ret; +} +EXPORT_SYMBOL_GPL(reservation_object_get_fences_rcu); + +long reservation_object_wait_timeout_rcu(struct reservation_object *obj, + bool wait_all, bool intr, + unsigned long timeout) +{ + struct fence *fence; + unsigned seq, shared_count, i = 0; + long ret = timeout; + +retry: + fence = NULL; + shared_count = 0; + seq = read_seqcount_begin(&obj->seq); + rcu_read_lock(); + + if (wait_all) { + struct reservation_object_list *fobj = rcu_dereference(obj->fence); + + if (fobj) + shared_count = fobj->shared_count; + + if (read_seqcount_retry(&obj->seq, seq)) + goto unlock_retry; + + for (i = 0; i < shared_count; ++i) { + struct fence *lfence = rcu_dereference(fobj->shared[i]); + + if (test_bit(FENCE_FLAG_SIGNALED_BIT, &lfence->flags)) + continue; + + if (!fence_get_rcu(lfence)) + goto unlock_retry; + + if (fence_is_signaled(lfence)) { + fence_put(lfence); + continue; + } + + fence = lfence; + break; + } + } + + if (!shared_count) { + struct fence *fence_excl = rcu_dereference(obj->fence_excl); + + if (read_seqcount_retry(&obj->seq, seq)) + goto unlock_retry; + + if (fence_excl && + !test_bit(FENCE_FLAG_SIGNALED_BIT, &fence_excl->flags)) { + if (!fence_get_rcu(fence_excl)) + goto unlock_retry; + + if (fence_is_signaled(fence_excl)) + fence_put(fence_excl); + else + fence = fence_excl; + } + } + + rcu_read_unlock(); + if (fence) { + ret = fence_wait_timeout(fence, intr, ret); + fence_put(fence); + if (ret > 0 && wait_all && (i + 1 < shared_count)) + goto retry; + } + return ret; + +unlock_retry: + rcu_read_unlock(); + goto retry; +} +EXPORT_SYMBOL_GPL(reservation_object_wait_timeout_rcu); + + +static inline int +reservation_object_test_signaled_single(struct fence *passed_fence) +{ + struct fence *fence, *lfence = passed_fence; + int ret = 1; + + if (!test_bit(FENCE_FLAG_SIGNALED_BIT, &lfence->flags)) { + int ret; + + fence = fence_get_rcu(lfence); + if (!fence) + return -1; + + ret = !!fence_is_signaled(fence); + fence_put(fence); + } + return ret; +} + +bool reservation_object_test_signaled_rcu(struct reservation_object *obj, + bool test_all) +{ + unsigned seq, shared_count; + int ret = true; + +retry: + shared_count = 0; + seq = read_seqcount_begin(&obj->seq); + rcu_read_lock(); + + if (test_all) { + unsigned i; + + struct reservation_object_list *fobj = rcu_dereference(obj->fence); + + if (fobj) + shared_count = fobj->shared_count; + + if (read_seqcount_retry(&obj->seq, seq)) + goto unlock_retry; + + for (i = 0; i < shared_count; ++i) { + struct fence *fence = rcu_dereference(fobj->shared[i]); + + ret = reservation_object_test_signaled_single(fence); + if (ret < 0) + goto unlock_retry; + else if (!ret) + break; + } + + /* + * There could be a read_seqcount_retry here, but nothing cares + * about whether it's the old or newer fence pointers that are + * signaled. That race could still have happened after checking + * read_seqcount_retry. If you care, use ww_mutex_lock. + */ + } + + if (!shared_count) { + struct fence *fence_excl = rcu_dereference(obj->fence_excl); + + if (read_seqcount_retry(&obj->seq, seq)) + goto unlock_retry; + + if (fence_excl) { + ret = reservation_object_test_signaled_single(fence_excl); + if (ret < 0) + goto unlock_retry; + } + } + + rcu_read_unlock(); + return ret; + +unlock_retry: + rcu_read_unlock(); + goto retry; +} +EXPORT_SYMBOL_GPL(reservation_object_test_signaled_rcu); diff --git a/drivers/dma-buf/seqno-fence.c b/drivers/dma-buf/seqno-fence.c new file mode 100644 index 000000000000..7d12a39a4b57 --- /dev/null +++ b/drivers/dma-buf/seqno-fence.c @@ -0,0 +1,73 @@ +/* + * seqno-fence, using a dma-buf to synchronize fencing + * + * Copyright (C) 2012 Texas Instruments + * Copyright (C) 2012-2014 Canonical Ltd + * Authors: + * Rob Clark <robdclark@gmail.com> + * Maarten Lankhorst <maarten.lankhorst@canonical.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License 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. + */ + +#include <linux/slab.h> +#include <linux/export.h> +#include <linux/seqno-fence.h> + +static const char *seqno_fence_get_driver_name(struct fence *fence) +{ + struct seqno_fence *seqno_fence = to_seqno_fence(fence); + return seqno_fence->ops->get_driver_name(fence); +} + +static const char *seqno_fence_get_timeline_name(struct fence *fence) +{ + struct seqno_fence *seqno_fence = to_seqno_fence(fence); + return seqno_fence->ops->get_timeline_name(fence); +} + +static bool seqno_enable_signaling(struct fence *fence) +{ + struct seqno_fence *seqno_fence = to_seqno_fence(fence); + return seqno_fence->ops->enable_signaling(fence); +} + +static bool seqno_signaled(struct fence *fence) +{ + struct seqno_fence *seqno_fence = to_seqno_fence(fence); + return seqno_fence->ops->signaled && seqno_fence->ops->signaled(fence); +} + +static void seqno_release(struct fence *fence) +{ + struct seqno_fence *f = to_seqno_fence(fence); + + dma_buf_put(f->sync_buf); + if (f->ops->release) + f->ops->release(fence); + else + fence_free(&f->base); +} + +static signed long seqno_wait(struct fence *fence, bool intr, signed long timeout) +{ + struct seqno_fence *f = to_seqno_fence(fence); + return f->ops->wait(fence, intr, timeout); +} + +const struct fence_ops seqno_fence_ops = { + .get_driver_name = seqno_fence_get_driver_name, + .get_timeline_name = seqno_fence_get_timeline_name, + .enable_signaling = seqno_enable_signaling, + .signaled = seqno_signaled, + .wait = seqno_wait, + .release = seqno_release, +}; +EXPORT_SYMBOL(seqno_fence_ops); diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c index 81c34f949dfc..3aedf9e993e6 100644 --- a/drivers/gpu/drm/armada/armada_crtc.c +++ b/drivers/gpu/drm/armada/armada_crtc.c @@ -1039,11 +1039,9 @@ int armada_drm_crtc_create(struct drm_device *dev, unsigned num, if (ret) return ret; - base = devm_request_and_ioremap(dev->dev, res); - if (!base) { - DRM_ERROR("failed to ioremap register\n"); - return -ENOMEM; - } + base = devm_ioremap_resource(dev->dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); dcrtc = kzalloc(sizeof(*dcrtc), GFP_KERNEL); if (!dcrtc) { diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c index bb9b642d8485..7496f55611a5 100644 --- a/drivers/gpu/drm/armada/armada_gem.c +++ b/drivers/gpu/drm/armada/armada_gem.c @@ -539,7 +539,7 @@ armada_gem_prime_export(struct drm_device *dev, struct drm_gem_object *obj, int flags) { return dma_buf_export(obj, &armada_gem_prime_dmabuf_ops, obj->size, - O_RDWR); + O_RDWR, NULL); } struct drm_gem_object * diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 304ca8cacbc4..99d578bad17e 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -336,7 +336,13 @@ static const struct dma_buf_ops drm_gem_prime_dmabuf_ops = { struct dma_buf *drm_gem_prime_export(struct drm_device *dev, struct drm_gem_object *obj, int flags) { - return dma_buf_export(obj, &drm_gem_prime_dmabuf_ops, obj->size, flags); + struct reservation_object *robj = NULL; + + if (dev->driver->gem_prime_res_obj) + robj = dev->driver->gem_prime_res_obj(obj); + + return dma_buf_export(obj, &drm_gem_prime_dmabuf_ops, obj->size, + flags, robj); } EXPORT_SYMBOL(drm_gem_prime_export); diff --git a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c index 2a3ad24276f8..60192ed544f0 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c @@ -187,7 +187,7 @@ struct dma_buf *exynos_dmabuf_prime_export(struct drm_device *drm_dev, struct exynos_drm_gem_obj *exynos_gem_obj = to_exynos_gem_obj(obj); return dma_buf_export(obj, &exynos_dmabuf_ops, - exynos_gem_obj->base.size, flags); + exynos_gem_obj->base.size, flags, NULL); } struct drm_gem_object *exynos_dmabuf_prime_import(struct drm_device *drm_dev, diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c index 580aa42443ed..82a1f4b57778 100644 --- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c @@ -237,7 +237,8 @@ struct dma_buf *i915_gem_prime_export(struct drm_device *dev, return ERR_PTR(ret); } - return dma_buf_export(gem_obj, &i915_dmabuf_ops, gem_obj->size, flags); + return dma_buf_export(gem_obj, &i915_dmabuf_ops, gem_obj->size, flags, + NULL); } static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj) diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 5425ffe3931d..c9428c943afb 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -845,6 +845,7 @@ driver = { .gem_prime_export = drm_gem_prime_export, .gem_prime_import = drm_gem_prime_import, .gem_prime_pin = nouveau_gem_prime_pin, + .gem_prime_res_obj = nouveau_gem_prime_res_obj, .gem_prime_unpin = nouveau_gem_prime_unpin, .gem_prime_get_sg_table = nouveau_gem_prime_get_sg_table, .gem_prime_import_sg_table = nouveau_gem_prime_import_sg_table, diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.h b/drivers/gpu/drm/nouveau/nouveau_gem.h index 7caca057bc38..ddab762d81fe 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.h +++ b/drivers/gpu/drm/nouveau/nouveau_gem.h @@ -35,6 +35,7 @@ extern int nouveau_gem_ioctl_info(struct drm_device *, void *, struct drm_file *); extern int nouveau_gem_prime_pin(struct drm_gem_object *); +struct reservation_object *nouveau_gem_prime_res_obj(struct drm_gem_object *); extern void nouveau_gem_prime_unpin(struct drm_gem_object *); extern struct sg_table *nouveau_gem_prime_get_sg_table(struct drm_gem_object *); extern struct drm_gem_object *nouveau_gem_prime_import_sg_table( diff --git a/drivers/gpu/drm/nouveau/nouveau_prime.c b/drivers/gpu/drm/nouveau/nouveau_prime.c index 51a2cb102b44..1f51008e4d26 100644 --- a/drivers/gpu/drm/nouveau/nouveau_prime.c +++ b/drivers/gpu/drm/nouveau/nouveau_prime.c @@ -102,3 +102,10 @@ void nouveau_gem_prime_unpin(struct drm_gem_object *obj) nouveau_bo_unpin(nvbo); } + +struct reservation_object *nouveau_gem_prime_res_obj(struct drm_gem_object *obj) +{ + struct nouveau_bo *nvbo = nouveau_gem_object(obj); + + return nvbo->bo.resv; +} diff --git a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c index 4fcca8d42796..a2dbfb1737b4 100644 --- a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c +++ b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c @@ -171,7 +171,7 @@ static struct dma_buf_ops omap_dmabuf_ops = { struct dma_buf *omap_gem_prime_export(struct drm_device *dev, struct drm_gem_object *obj, int flags) { - return dma_buf_export(obj, &omap_dmabuf_ops, obj->size, flags); + return dma_buf_export(obj, &omap_dmabuf_ops, obj->size, flags, NULL); } struct drm_gem_object *omap_gem_prime_import(struct drm_device *dev, diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index e9e361084249..959f0866d993 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -132,6 +132,7 @@ struct drm_gem_object *radeon_gem_prime_import_sg_table(struct drm_device *dev, struct sg_table *sg); int radeon_gem_prime_pin(struct drm_gem_object *obj); void radeon_gem_prime_unpin(struct drm_gem_object *obj); +struct reservation_object *radeon_gem_prime_res_obj(struct drm_gem_object *); void *radeon_gem_prime_vmap(struct drm_gem_object *obj); void radeon_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr); extern long radeon_kms_compat_ioctl(struct file *filp, unsigned int cmd, @@ -566,6 +567,7 @@ static struct drm_driver kms_driver = { .gem_prime_import = drm_gem_prime_import, .gem_prime_pin = radeon_gem_prime_pin, .gem_prime_unpin = radeon_gem_prime_unpin, + .gem_prime_res_obj = radeon_gem_prime_res_obj, .gem_prime_get_sg_table = radeon_gem_prime_get_sg_table, .gem_prime_import_sg_table = radeon_gem_prime_import_sg_table, .gem_prime_vmap = radeon_gem_prime_vmap, diff --git a/drivers/gpu/drm/radeon/radeon_prime.c b/drivers/gpu/drm/radeon/radeon_prime.c index 20074560fc25..28d71070c389 100644 --- a/drivers/gpu/drm/radeon/radeon_prime.c +++ b/drivers/gpu/drm/radeon/radeon_prime.c @@ -103,3 +103,11 @@ void radeon_gem_prime_unpin(struct drm_gem_object *obj) radeon_bo_unpin(bo); radeon_bo_unreserve(bo); } + + +struct reservation_object *radeon_gem_prime_res_obj(struct drm_gem_object *obj) +{ + struct radeon_bo *bo = gem_to_radeon_bo(obj); + + return bo->tbo.resv; +} diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c index aa85b7b26f10..78cc8143760a 100644 --- a/drivers/gpu/drm/tegra/gem.c +++ b/drivers/gpu/drm/tegra/gem.c @@ -420,7 +420,7 @@ struct dma_buf *tegra_gem_prime_export(struct drm_device *drm, int flags) { return dma_buf_export(gem, &tegra_gem_prime_dmabuf_ops, gem->size, - flags); + flags, NULL); } struct drm_gem_object *tegra_gem_prime_import(struct drm_device *drm, diff --git a/drivers/gpu/drm/ttm/ttm_object.c b/drivers/gpu/drm/ttm/ttm_object.c index d2a053352789..12c87110db3a 100644 --- a/drivers/gpu/drm/ttm/ttm_object.c +++ b/drivers/gpu/drm/ttm/ttm_object.c @@ -695,7 +695,7 @@ int ttm_prime_handle_to_fd(struct ttm_object_file *tfile, } dma_buf = dma_buf_export(prime, &tdev->ops, - prime->size, flags); + prime->size, flags, NULL); if (IS_ERR(dma_buf)) { ret = PTR_ERR(dma_buf); ttm_mem_global_free(tdev->mem_glob, diff --git a/drivers/media/v4l2-core/videobuf2-dma-contig.c b/drivers/media/v4l2-core/videobuf2-dma-contig.c index 880be0782dd9..c4e4dfa8123a 100644 --- a/drivers/media/v4l2-core/videobuf2-dma-contig.c +++ b/drivers/media/v4l2-core/videobuf2-dma-contig.c @@ -404,7 +404,7 @@ static struct dma_buf *vb2_dc_get_dmabuf(void *buf_priv, unsigned long flags) if (WARN_ON(!buf->sgt_base)) return NULL; - dbuf = dma_buf_export(buf, &vb2_dc_dmabuf_ops, buf->size, flags); + dbuf = dma_buf_export(buf, &vb2_dc_dmabuf_ops, buf->size, flags, NULL); if (IS_ERR(dbuf)) return NULL; diff --git a/drivers/staging/android/Kconfig b/drivers/staging/android/Kconfig index 99e484f845f2..51607e9aa049 100644 --- a/drivers/staging/android/Kconfig +++ b/drivers/staging/android/Kconfig @@ -88,6 +88,7 @@ config SYNC bool "Synchronization framework" default n select ANON_INODES + select DMA_SHARED_BUFFER ---help--- This option enables the framework for synchronization between multiple drivers. Sync implementations can take advantage of hardware diff --git a/drivers/staging/android/Makefile b/drivers/staging/android/Makefile index 0a01e1914905..517ad5ffa429 100644 --- a/drivers/staging/android/Makefile +++ b/drivers/staging/android/Makefile @@ -9,5 +9,5 @@ obj-$(CONFIG_ANDROID_TIMED_OUTPUT) += timed_output.o obj-$(CONFIG_ANDROID_TIMED_GPIO) += timed_gpio.o obj-$(CONFIG_ANDROID_LOW_MEMORY_KILLER) += lowmemorykiller.o obj-$(CONFIG_ANDROID_INTF_ALARM_DEV) += alarm-dev.o -obj-$(CONFIG_SYNC) += sync.o +obj-$(CONFIG_SYNC) += sync.o sync_debug.o obj-$(CONFIG_SW_SYNC) += sw_sync.o diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c index 389b8f67a2ec..270360912b2c 100644 --- a/drivers/staging/android/ion/ion.c +++ b/drivers/staging/android/ion/ion.c @@ -1120,7 +1120,8 @@ struct dma_buf *ion_share_dma_buf(struct ion_client *client, ion_buffer_get(buffer); mutex_unlock(&client->lock); - dmabuf = dma_buf_export(buffer, &dma_buf_ops, buffer->size, O_RDWR); + dmabuf = dma_buf_export(buffer, &dma_buf_ops, buffer->size, O_RDWR, + NULL); if (IS_ERR(dmabuf)) { ion_buffer_put(buffer); return dmabuf; diff --git a/drivers/staging/android/sw_sync.c b/drivers/staging/android/sw_sync.c index 12a136ec1cec..a76db3ff87cb 100644 --- a/drivers/staging/android/sw_sync.c +++ b/drivers/staging/android/sw_sync.c @@ -50,7 +50,7 @@ static struct sync_pt *sw_sync_pt_dup(struct sync_pt *sync_pt) { struct sw_sync_pt *pt = (struct sw_sync_pt *) sync_pt; struct sw_sync_timeline *obj = - (struct sw_sync_timeline *)sync_pt->parent; + (struct sw_sync_timeline *)sync_pt_parent(sync_pt); return (struct sync_pt *) sw_sync_pt_create(obj, pt->value); } @@ -59,7 +59,7 @@ static int sw_sync_pt_has_signaled(struct sync_pt *sync_pt) { struct sw_sync_pt *pt = (struct sw_sync_pt *)sync_pt; struct sw_sync_timeline *obj = - (struct sw_sync_timeline *)sync_pt->parent; + (struct sw_sync_timeline *)sync_pt_parent(sync_pt); return sw_sync_cmp(obj->value, pt->value) >= 0; } @@ -97,7 +97,6 @@ static void sw_sync_pt_value_str(struct sync_pt *sync_pt, char *str, int size) { struct sw_sync_pt *pt = (struct sw_sync_pt *)sync_pt; - snprintf(str, size, "%d", pt->value); } @@ -157,7 +156,6 @@ static int sw_sync_open(struct inode *inode, struct file *file) static int sw_sync_release(struct inode *inode, struct file *file) { struct sw_sync_timeline *obj = file->private_data; - sync_timeline_destroy(&obj->obj); return 0; } diff --git a/drivers/staging/android/sync.c b/drivers/staging/android/sync.c index 18174f7c871c..c9a0c2cdc81a 100644 --- a/drivers/staging/android/sync.c +++ b/drivers/staging/android/sync.c @@ -31,22 +31,13 @@ #define CREATE_TRACE_POINTS #include "trace/sync.h" -static void sync_fence_signal_pt(struct sync_pt *pt); -static int _sync_pt_has_signaled(struct sync_pt *pt); -static void sync_fence_free(struct kref *kref); -static void sync_dump(void); - -static LIST_HEAD(sync_timeline_list_head); -static DEFINE_SPINLOCK(sync_timeline_list_lock); - -static LIST_HEAD(sync_fence_list_head); -static DEFINE_SPINLOCK(sync_fence_list_lock); +static const struct fence_ops android_fence_ops; +static const struct file_operations sync_fence_fops; struct sync_timeline *sync_timeline_create(const struct sync_timeline_ops *ops, int size, const char *name) { struct sync_timeline *obj; - unsigned long flags; if (size < sizeof(struct sync_timeline)) return NULL; @@ -57,17 +48,14 @@ struct sync_timeline *sync_timeline_create(const struct sync_timeline_ops *ops, kref_init(&obj->kref); obj->ops = ops; + obj->context = fence_context_alloc(1); strlcpy(obj->name, name, sizeof(obj->name)); INIT_LIST_HEAD(&obj->child_list_head); - spin_lock_init(&obj->child_list_lock); - INIT_LIST_HEAD(&obj->active_list_head); - spin_lock_init(&obj->active_list_lock); + spin_lock_init(&obj->child_list_lock); - spin_lock_irqsave(&sync_timeline_list_lock, flags); - list_add_tail(&obj->sync_timeline_list, &sync_timeline_list_head); - spin_unlock_irqrestore(&sync_timeline_list_lock, flags); + sync_timeline_debug_add(obj); return obj; } @@ -77,11 +65,8 @@ static void sync_timeline_free(struct kref *kref) { struct sync_timeline *obj = container_of(kref, struct sync_timeline, kref); - unsigned long flags; - spin_lock_irqsave(&sync_timeline_list_lock, flags); - list_del(&obj->sync_timeline_list); - spin_unlock_irqrestore(&sync_timeline_list_lock, flags); + sync_timeline_debug_remove(obj); if (obj->ops->release_obj) obj->ops->release_obj(obj); @@ -89,6 +74,16 @@ static void sync_timeline_free(struct kref *kref) kfree(obj); } +static void sync_timeline_get(struct sync_timeline *obj) +{ + kref_get(&obj->kref); +} + +static void sync_timeline_put(struct sync_timeline *obj) +{ + kref_put(&obj->kref, sync_timeline_free); +} + void sync_timeline_destroy(struct sync_timeline *obj) { obj->destroyed = true; @@ -102,75 +97,33 @@ void sync_timeline_destroy(struct sync_timeline *obj) * signal any children that their parent is going away. */ sync_timeline_signal(obj); - - kref_put(&obj->kref, sync_timeline_free); + sync_timeline_put(obj); } EXPORT_SYMBOL(sync_timeline_destroy); -static void sync_timeline_add_pt(struct sync_timeline *obj, struct sync_pt *pt) -{ - unsigned long flags; - - pt->parent = obj; - - spin_lock_irqsave(&obj->child_list_lock, flags); - list_add_tail(&pt->child_list, &obj->child_list_head); - spin_unlock_irqrestore(&obj->child_list_lock, flags); -} - -static void sync_timeline_remove_pt(struct sync_pt *pt) -{ - struct sync_timeline *obj = pt->parent; - unsigned long flags; - - spin_lock_irqsave(&obj->active_list_lock, flags); - if (!list_empty(&pt->active_list)) - list_del_init(&pt->active_list); - spin_unlock_irqrestore(&obj->active_list_lock, flags); - - spin_lock_irqsave(&obj->child_list_lock, flags); - if (!list_empty(&pt->child_list)) - list_del_init(&pt->child_list); - - spin_unlock_irqrestore(&obj->child_list_lock, flags); -} - void sync_timeline_signal(struct sync_timeline *obj) { unsigned long flags; LIST_HEAD(signaled_pts); - struct list_head *pos, *n; + struct sync_pt *pt, *next; trace_sync_timeline(obj); - spin_lock_irqsave(&obj->active_list_lock, flags); - - list_for_each_safe(pos, n, &obj->active_list_head) { - struct sync_pt *pt = - container_of(pos, struct sync_pt, active_list); + spin_lock_irqsave(&obj->child_list_lock, flags); - if (_sync_pt_has_signaled(pt)) { - list_del_init(pos); - list_add(&pt->signaled_list, &signaled_pts); - kref_get(&pt->fence->kref); - } + list_for_each_entry_safe(pt, next, &obj->active_list_head, + active_list) { + if (fence_is_signaled_locked(&pt->base)) + list_del(&pt->active_list); } - spin_unlock_irqrestore(&obj->active_list_lock, flags); - - list_for_each_safe(pos, n, &signaled_pts) { - struct sync_pt *pt = - container_of(pos, struct sync_pt, signaled_list); - - list_del_init(pos); - sync_fence_signal_pt(pt); - kref_put(&pt->fence->kref, sync_fence_free); - } + spin_unlock_irqrestore(&obj->child_list_lock, flags); } EXPORT_SYMBOL(sync_timeline_signal); -struct sync_pt *sync_pt_create(struct sync_timeline *parent, int size) +struct sync_pt *sync_pt_create(struct sync_timeline *obj, int size) { + unsigned long flags; struct sync_pt *pt; if (size < sizeof(struct sync_pt)) @@ -180,87 +133,28 @@ struct sync_pt *sync_pt_create(struct sync_timeline *parent, int size) if (pt == NULL) return NULL; + spin_lock_irqsave(&obj->child_list_lock, flags); + sync_timeline_get(obj); + fence_init(&pt->base, &android_fence_ops, &obj->child_list_lock, + obj->context, ++obj->value); + list_add_tail(&pt->child_list, &obj->child_list_head); INIT_LIST_HEAD(&pt->active_list); - kref_get(&parent->kref); - sync_timeline_add_pt(parent, pt); - + spin_unlock_irqrestore(&obj->child_list_lock, flags); return pt; } EXPORT_SYMBOL(sync_pt_create); void sync_pt_free(struct sync_pt *pt) { - if (pt->parent->ops->free_pt) - pt->parent->ops->free_pt(pt); - - sync_timeline_remove_pt(pt); - - kref_put(&pt->parent->kref, sync_timeline_free); - - kfree(pt); + fence_put(&pt->base); } EXPORT_SYMBOL(sync_pt_free); -/* call with pt->parent->active_list_lock held */ -static int _sync_pt_has_signaled(struct sync_pt *pt) -{ - int old_status = pt->status; - - if (!pt->status) - pt->status = pt->parent->ops->has_signaled(pt); - - if (!pt->status && pt->parent->destroyed) - pt->status = -ENOENT; - - if (pt->status != old_status) - pt->timestamp = ktime_get(); - - return pt->status; -} - -static struct sync_pt *sync_pt_dup(struct sync_pt *pt) -{ - return pt->parent->ops->dup(pt); -} - -/* Adds a sync pt to the active queue. Called when added to a fence */ -static void sync_pt_activate(struct sync_pt *pt) -{ - struct sync_timeline *obj = pt->parent; - unsigned long flags; - int err; - - spin_lock_irqsave(&obj->active_list_lock, flags); - - err = _sync_pt_has_signaled(pt); - if (err != 0) - goto out; - - list_add_tail(&pt->active_list, &obj->active_list_head); - -out: - spin_unlock_irqrestore(&obj->active_list_lock, flags); -} - -static int sync_fence_release(struct inode *inode, struct file *file); -static unsigned int sync_fence_poll(struct file *file, poll_table *wait); -static long sync_fence_ioctl(struct file *file, unsigned int cmd, - unsigned long arg); - - -static const struct file_operations sync_fence_fops = { - .release = sync_fence_release, - .poll = sync_fence_poll, - .unlocked_ioctl = sync_fence_ioctl, - .compat_ioctl = sync_fence_ioctl, -}; - -static struct sync_fence *sync_fence_alloc(const char *name) +static struct sync_fence *sync_fence_alloc(int size, const char *name) { struct sync_fence *fence; - unsigned long flags; - fence = kzalloc(sizeof(struct sync_fence), GFP_KERNEL); + fence = kzalloc(size, GFP_KERNEL); if (fence == NULL) return NULL; @@ -272,16 +166,8 @@ static struct sync_fence *sync_fence_alloc(const char *name) kref_init(&fence->kref); strlcpy(fence->name, name, sizeof(fence->name)); - INIT_LIST_HEAD(&fence->pt_list_head); - INIT_LIST_HEAD(&fence->waiter_list_head); - spin_lock_init(&fence->waiter_list_lock); - init_waitqueue_head(&fence->wq); - spin_lock_irqsave(&sync_fence_list_lock, flags); - list_add_tail(&fence->sync_fence_list, &sync_fence_list_head); - spin_unlock_irqrestore(&sync_fence_list_lock, flags); - return fence; err: @@ -289,120 +175,42 @@ err: return NULL; } -/* TODO: implement a create which takes more that one sync_pt */ -struct sync_fence *sync_fence_create(const char *name, struct sync_pt *pt) +static void fence_check_cb_func(struct fence *f, struct fence_cb *cb) { + struct sync_fence_cb *check; struct sync_fence *fence; - if (pt->fence) - return NULL; - - fence = sync_fence_alloc(name); - if (fence == NULL) - return NULL; + check = container_of(cb, struct sync_fence_cb, cb); + fence = check->fence; - pt->fence = fence; - list_add(&pt->pt_list, &fence->pt_list_head); - sync_pt_activate(pt); - - /* - * signal the fence in case pt was activated before - * sync_pt_activate(pt) was called - */ - sync_fence_signal_pt(pt); - - return fence; -} -EXPORT_SYMBOL(sync_fence_create); - -static int sync_fence_copy_pts(struct sync_fence *dst, struct sync_fence *src) -{ - struct list_head *pos; - - list_for_each(pos, &src->pt_list_head) { - struct sync_pt *orig_pt = - container_of(pos, struct sync_pt, pt_list); - struct sync_pt *new_pt = sync_pt_dup(orig_pt); - - if (new_pt == NULL) - return -ENOMEM; - - new_pt->fence = dst; - list_add(&new_pt->pt_list, &dst->pt_list_head); - } - - return 0; + if (atomic_dec_and_test(&fence->status)) + wake_up_all(&fence->wq); } -static int sync_fence_merge_pts(struct sync_fence *dst, struct sync_fence *src) -{ - struct list_head *src_pos, *dst_pos, *n; - - list_for_each(src_pos, &src->pt_list_head) { - struct sync_pt *src_pt = - container_of(src_pos, struct sync_pt, pt_list); - bool collapsed = false; - - list_for_each_safe(dst_pos, n, &dst->pt_list_head) { - struct sync_pt *dst_pt = - container_of(dst_pos, struct sync_pt, pt_list); - /* collapse two sync_pts on the same timeline - * to a single sync_pt that will signal at - * the later of the two - */ - if (dst_pt->parent == src_pt->parent) { - if (dst_pt->parent->ops->compare(dst_pt, src_pt) - == -1) { - struct sync_pt *new_pt = - sync_pt_dup(src_pt); - if (new_pt == NULL) - return -ENOMEM; - - new_pt->fence = dst; - list_replace(&dst_pt->pt_list, - &new_pt->pt_list); - sync_pt_free(dst_pt); - } - collapsed = true; - break; - } - } - - if (!collapsed) { - struct sync_pt *new_pt = sync_pt_dup(src_pt); - - if (new_pt == NULL) - return -ENOMEM; - - new_pt->fence = dst; - list_add(&new_pt->pt_list, &dst->pt_list_head); - } - } - - return 0; -} - -static void sync_fence_detach_pts(struct sync_fence *fence) +/* TODO: implement a create which takes more that one sync_pt */ +struct sync_fence *sync_fence_create(const char *name, struct sync_pt *pt) { - struct list_head *pos, *n; + struct sync_fence *fence; - list_for_each_safe(pos, n, &fence->pt_list_head) { - struct sync_pt *pt = container_of(pos, struct sync_pt, pt_list); + fence = sync_fence_alloc(offsetof(struct sync_fence, cbs[1]), name); + if (fence == NULL) + return NULL; - sync_timeline_remove_pt(pt); - } -} + fence->num_fences = 1; + atomic_set(&fence->status, 1); -static void sync_fence_free_pts(struct sync_fence *fence) -{ - struct list_head *pos, *n; + fence_get(&pt->base); + fence->cbs[0].sync_pt = &pt->base; + fence->cbs[0].fence = fence; + if (fence_add_callback(&pt->base, &fence->cbs[0].cb, + fence_check_cb_func)) + atomic_dec(&fence->status); - list_for_each_safe(pos, n, &fence->pt_list_head) { - struct sync_pt *pt = container_of(pos, struct sync_pt, pt_list); + sync_fence_debug_add(fence); - sync_pt_free(pt); - } + return fence; } +EXPORT_SYMBOL(sync_fence_create); struct sync_fence *sync_fence_fdget(int fd) { @@ -434,197 +242,155 @@ void sync_fence_install(struct sync_fence *fence, int fd) } EXPORT_SYMBOL(sync_fence_install); -static int sync_fence_get_status(struct sync_fence *fence) +static void sync_fence_add_pt(struct sync_fence *fence, + int *i, struct fence *pt) { - struct list_head *pos; - int status = 1; - - list_for_each(pos, &fence->pt_list_head) { - struct sync_pt *pt = container_of(pos, struct sync_pt, pt_list); - int pt_status = pt->status; - - if (pt_status < 0) { - status = pt_status; - break; - } else if (status == 1) { - status = pt_status; - } - } + fence->cbs[*i].sync_pt = pt; + fence->cbs[*i].fence = fence; - return status; + if (!fence_add_callback(pt, &fence->cbs[*i].cb, fence_check_cb_func)) { + fence_get(pt); + (*i)++; + } } struct sync_fence *sync_fence_merge(const char *name, struct sync_fence *a, struct sync_fence *b) { + int num_fences = a->num_fences + b->num_fences; struct sync_fence *fence; - struct list_head *pos; - int err; + int i, i_a, i_b; + unsigned long size = offsetof(struct sync_fence, cbs[num_fences]); - fence = sync_fence_alloc(name); + fence = sync_fence_alloc(size, name); if (fence == NULL) return NULL; - err = sync_fence_copy_pts(fence, a); - if (err < 0) - goto err; + atomic_set(&fence->status, num_fences); - err = sync_fence_merge_pts(fence, b); - if (err < 0) - goto err; + /* + * Assume sync_fence a and b are both ordered and have no + * duplicates with the same context. + * + * If a sync_fence can only be created with sync_fence_merge + * and sync_fence_create, this is a reasonable assumption. + */ + for (i = i_a = i_b = 0; i_a < a->num_fences && i_b < b->num_fences; ) { + struct fence *pt_a = a->cbs[i_a].sync_pt; + struct fence *pt_b = b->cbs[i_b].sync_pt; + + if (pt_a->context < pt_b->context) { + sync_fence_add_pt(fence, &i, pt_a); + + i_a++; + } else if (pt_a->context > pt_b->context) { + sync_fence_add_pt(fence, &i, pt_b); - list_for_each(pos, &fence->pt_list_head) { - struct sync_pt *pt = - container_of(pos, struct sync_pt, pt_list); - sync_pt_activate(pt); + i_b++; + } else { + if (pt_a->seqno - pt_b->seqno <= INT_MAX) + sync_fence_add_pt(fence, &i, pt_a); + else + sync_fence_add_pt(fence, &i, pt_b); + + i_a++; + i_b++; + } } - /* - * signal the fence in case one of it's pts were activated before - * they were activated - */ - sync_fence_signal_pt(list_first_entry(&fence->pt_list_head, - struct sync_pt, - pt_list)); + for (; i_a < a->num_fences; i_a++) + sync_fence_add_pt(fence, &i, a->cbs[i_a].sync_pt); + for (; i_b < b->num_fences; i_b++) + sync_fence_add_pt(fence, &i, b->cbs[i_b].sync_pt); + + if (num_fences > i) + atomic_sub(num_fences - i, &fence->status); + fence->num_fences = i; + + sync_fence_debug_add(fence); return fence; -err: - sync_fence_free_pts(fence); - kfree(fence); - return NULL; } EXPORT_SYMBOL(sync_fence_merge); -static void sync_fence_signal_pt(struct sync_pt *pt) +int sync_fence_wake_up_wq(wait_queue_t *curr, unsigned mode, + int wake_flags, void *key) { - LIST_HEAD(signaled_waiters); - struct sync_fence *fence = pt->fence; - struct list_head *pos; - struct list_head *n; - unsigned long flags; - int status; - - status = sync_fence_get_status(fence); - - spin_lock_irqsave(&fence->waiter_list_lock, flags); - /* - * this should protect against two threads racing on the signaled - * false -> true transition - */ - if (status && !fence->status) { - list_for_each_safe(pos, n, &fence->waiter_list_head) - list_move(pos, &signaled_waiters); - - fence->status = status; - } else { - status = 0; - } - spin_unlock_irqrestore(&fence->waiter_list_lock, flags); + struct sync_fence_waiter *wait; - if (status) { - list_for_each_safe(pos, n, &signaled_waiters) { - struct sync_fence_waiter *waiter = - container_of(pos, struct sync_fence_waiter, - waiter_list); + wait = container_of(curr, struct sync_fence_waiter, work); + list_del_init(&wait->work.task_list); - list_del(pos); - waiter->callback(fence, waiter); - } - wake_up(&fence->wq); - } + wait->callback(wait->work.private, wait); + return 1; } int sync_fence_wait_async(struct sync_fence *fence, struct sync_fence_waiter *waiter) { + int err = atomic_read(&fence->status); unsigned long flags; - int err = 0; - spin_lock_irqsave(&fence->waiter_list_lock, flags); + if (err < 0) + return err; - if (fence->status) { - err = fence->status; - goto out; - } + if (!err) + return 1; - list_add_tail(&waiter->waiter_list, &fence->waiter_list_head); -out: - spin_unlock_irqrestore(&fence->waiter_list_lock, flags); + init_waitqueue_func_entry(&waiter->work, sync_fence_wake_up_wq); + waiter->work.private = fence; - return err; + spin_lock_irqsave(&fence->wq.lock, flags); + err = atomic_read(&fence->status); + if (err > 0) + __add_wait_queue_tail(&fence->wq, &waiter->work); + spin_unlock_irqrestore(&fence->wq.lock, flags); + + if (err < 0) + return err; + + return !err; } EXPORT_SYMBOL(sync_fence_wait_async); int sync_fence_cancel_async(struct sync_fence *fence, struct sync_fence_waiter *waiter) { - struct list_head *pos; - struct list_head *n; unsigned long flags; - int ret = -ENOENT; + int ret = 0; - spin_lock_irqsave(&fence->waiter_list_lock, flags); - /* - * Make sure waiter is still in waiter_list because it is possible for - * the waiter to be removed from the list while the callback is still - * pending. - */ - list_for_each_safe(pos, n, &fence->waiter_list_head) { - struct sync_fence_waiter *list_waiter = - container_of(pos, struct sync_fence_waiter, - waiter_list); - if (list_waiter == waiter) { - list_del(pos); - ret = 0; - break; - } - } - spin_unlock_irqrestore(&fence->waiter_list_lock, flags); + spin_lock_irqsave(&fence->wq.lock, flags); + if (!list_empty(&waiter->work.task_list)) + list_del_init(&waiter->work.task_list); + else + ret = -ENOENT; + spin_unlock_irqrestore(&fence->wq.lock, flags); return ret; } EXPORT_SYMBOL(sync_fence_cancel_async); -static bool sync_fence_check(struct sync_fence *fence) -{ - /* - * Make sure that reads to fence->status are ordered with the - * wait queue event triggering - */ - smp_rmb(); - return fence->status != 0; -} - int sync_fence_wait(struct sync_fence *fence, long timeout) { - int err = 0; - struct sync_pt *pt; - - trace_sync_wait(fence, 1); - list_for_each_entry(pt, &fence->pt_list_head, pt_list) - trace_sync_pt(pt); + long ret; + int i; - if (timeout > 0) { + if (timeout < 0) + timeout = MAX_SCHEDULE_TIMEOUT; + else timeout = msecs_to_jiffies(timeout); - err = wait_event_interruptible_timeout(fence->wq, - sync_fence_check(fence), - timeout); - } else if (timeout < 0) { - err = wait_event_interruptible(fence->wq, - sync_fence_check(fence)); - } - trace_sync_wait(fence, 0); - if (err < 0) - return err; - - if (fence->status < 0) { - pr_info("fence error %d on [%p]\n", fence->status, fence); - sync_dump(); - return fence->status; - } + trace_sync_wait(fence, 1); + for (i = 0; i < fence->num_fences; ++i) + trace_sync_pt(fence->cbs[i].sync_pt); + ret = wait_event_interruptible_timeout(fence->wq, + atomic_read(&fence->status) <= 0, + timeout); + trace_sync_wait(fence, 0); - if (fence->status == 0) { - if (timeout > 0) { + if (ret < 0) + return ret; + else if (ret == 0) { + if (timeout) { pr_info("fence timeout on [%p] after %dms\n", fence, jiffies_to_msecs(timeout)); sync_dump(); @@ -632,15 +398,136 @@ int sync_fence_wait(struct sync_fence *fence, long timeout) return -ETIME; } - return 0; + ret = atomic_read(&fence->status); + if (ret) { + pr_info("fence error %ld on [%p]\n", ret, fence); + sync_dump(); + } + return ret; } EXPORT_SYMBOL(sync_fence_wait); +static const char *android_fence_get_driver_name(struct fence *fence) +{ + struct sync_pt *pt = container_of(fence, struct sync_pt, base); + struct sync_timeline *parent = sync_pt_parent(pt); + + return parent->ops->driver_name; +} + +static const char *android_fence_get_timeline_name(struct fence *fence) +{ + struct sync_pt *pt = container_of(fence, struct sync_pt, base); + struct sync_timeline *parent = sync_pt_parent(pt); + + return parent->name; +} + +static void android_fence_release(struct fence *fence) +{ + struct sync_pt *pt = container_of(fence, struct sync_pt, base); + struct sync_timeline *parent = sync_pt_parent(pt); + unsigned long flags; + + spin_lock_irqsave(fence->lock, flags); + list_del(&pt->child_list); + if (WARN_ON_ONCE(!list_empty(&pt->active_list))) + list_del(&pt->active_list); + spin_unlock_irqrestore(fence->lock, flags); + + if (parent->ops->free_pt) + parent->ops->free_pt(pt); + + sync_timeline_put(parent); + fence_free(&pt->base); +} + +static bool android_fence_signaled(struct fence *fence) +{ + struct sync_pt *pt = container_of(fence, struct sync_pt, base); + struct sync_timeline *parent = sync_pt_parent(pt); + int ret; + + ret = parent->ops->has_signaled(pt); + if (ret < 0) + fence->status = ret; + return ret; +} + +static bool android_fence_enable_signaling(struct fence *fence) +{ + struct sync_pt *pt = container_of(fence, struct sync_pt, base); + struct sync_timeline *parent = sync_pt_parent(pt); + + if (android_fence_signaled(fence)) + return false; + + list_add_tail(&pt->active_list, &parent->active_list_head); + return true; +} + +static int android_fence_fill_driver_data(struct fence *fence, + void *data, int size) +{ + struct sync_pt *pt = container_of(fence, struct sync_pt, base); + struct sync_timeline *parent = sync_pt_parent(pt); + + if (!parent->ops->fill_driver_data) + return 0; + return parent->ops->fill_driver_data(pt, data, size); +} + +static void android_fence_value_str(struct fence *fence, + char *str, int size) +{ + struct sync_pt *pt = container_of(fence, struct sync_pt, base); + struct sync_timeline *parent = sync_pt_parent(pt); + + if (!parent->ops->pt_value_str) { + if (size) + *str = 0; + return; + } + parent->ops->pt_value_str(pt, str, size); +} + +static void android_fence_timeline_value_str(struct fence *fence, + char *str, int size) +{ + struct sync_pt *pt = container_of(fence, struct sync_pt, base); + struct sync_timeline *parent = sync_pt_parent(pt); + + if (!parent->ops->timeline_value_str) { + if (size) + *str = 0; + return; + } + parent->ops->timeline_value_str(parent, str, size); +} + +static const struct fence_ops android_fence_ops = { + .get_driver_name = android_fence_get_driver_name, + .get_timeline_name = android_fence_get_timeline_name, + .enable_signaling = android_fence_enable_signaling, + .signaled = android_fence_signaled, + .wait = fence_default_wait, + .release = android_fence_release, + .fill_driver_data = android_fence_fill_driver_data, + .fence_value_str = android_fence_value_str, + .timeline_value_str = android_fence_timeline_value_str, +}; + static void sync_fence_free(struct kref *kref) { struct sync_fence *fence = container_of(kref, struct sync_fence, kref); + int i, status = atomic_read(&fence->status); - sync_fence_free_pts(fence); + for (i = 0; i < fence->num_fences; ++i) { + if (status) + fence_remove_callback(fence->cbs[i].sync_pt, + &fence->cbs[i].cb); + fence_put(fence->cbs[i].sync_pt); + } kfree(fence); } @@ -648,44 +535,25 @@ static void sync_fence_free(struct kref *kref) static int sync_fence_release(struct inode *inode, struct file *file) { struct sync_fence *fence = file->private_data; - unsigned long flags; - - /* - * We need to remove all ways to access this fence before droping - * our ref. - * - * start with its membership in the global fence list - */ - spin_lock_irqsave(&sync_fence_list_lock, flags); - list_del(&fence->sync_fence_list); - spin_unlock_irqrestore(&sync_fence_list_lock, flags); - /* - * remove its pts from their parents so that sync_timeline_signal() - * can't reference the fence. - */ - sync_fence_detach_pts(fence); + sync_fence_debug_remove(fence); kref_put(&fence->kref, sync_fence_free); - return 0; } static unsigned int sync_fence_poll(struct file *file, poll_table *wait) { struct sync_fence *fence = file->private_data; + int status; poll_wait(file, &fence->wq, wait); - /* - * Make sure that reads to fence->status are ordered with the - * wait queue event triggering - */ - smp_rmb(); + status = atomic_read(&fence->status); - if (fence->status == 1) + if (!status) return POLLIN; - else if (fence->status < 0) + else if (status < 0) return POLLERR; else return 0; @@ -750,7 +618,7 @@ err_put_fd: return err; } -static int sync_fill_pt_info(struct sync_pt *pt, void *data, int size) +static int sync_fill_pt_info(struct fence *fence, void *data, int size) { struct sync_pt_info *info = data; int ret; @@ -760,20 +628,24 @@ static int sync_fill_pt_info(struct sync_pt *pt, void *data, int size) info->len = sizeof(struct sync_pt_info); - if (pt->parent->ops->fill_driver_data) { - ret = pt->parent->ops->fill_driver_data(pt, info->driver_data, - size - sizeof(*info)); + if (fence->ops->fill_driver_data) { + ret = fence->ops->fill_driver_data(fence, info->driver_data, + size - sizeof(*info)); if (ret < 0) return ret; info->len += ret; } - strlcpy(info->obj_name, pt->parent->name, sizeof(info->obj_name)); - strlcpy(info->driver_name, pt->parent->ops->driver_name, + strlcpy(info->obj_name, fence->ops->get_timeline_name(fence), + sizeof(info->obj_name)); + strlcpy(info->driver_name, fence->ops->get_driver_name(fence), sizeof(info->driver_name)); - info->status = pt->status; - info->timestamp_ns = ktime_to_ns(pt->timestamp); + if (fence_is_signaled(fence)) + info->status = fence->status >= 0 ? 1 : fence->status; + else + info->status = 0; + info->timestamp_ns = ktime_to_ns(fence->timestamp); return info->len; } @@ -782,10 +654,9 @@ static long sync_fence_ioctl_fence_info(struct sync_fence *fence, unsigned long arg) { struct sync_fence_info_data *data; - struct list_head *pos; __u32 size; __u32 len = 0; - int ret; + int ret, i; if (copy_from_user(&size, (void __user *)arg, sizeof(size))) return -EFAULT; @@ -801,12 +672,14 @@ static long sync_fence_ioctl_fence_info(struct sync_fence *fence, return -ENOMEM; strlcpy(data->name, fence->name, sizeof(data->name)); - data->status = fence->status; + data->status = atomic_read(&fence->status); + if (data->status >= 0) + data->status = !data->status; + len = sizeof(struct sync_fence_info_data); - list_for_each(pos, &fence->pt_list_head) { - struct sync_pt *pt = - container_of(pos, struct sync_pt, pt_list); + for (i = 0; i < fence->num_fences; ++i) { + struct fence *pt = fence->cbs[i].sync_pt; ret = sync_fill_pt_info(pt, (u8 *)data + len, size - len); @@ -833,7 +706,6 @@ static long sync_fence_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct sync_fence *fence = file->private_data; - switch (cmd) { case SYNC_IOC_WAIT: return sync_fence_ioctl_wait(fence, arg); @@ -849,181 +721,10 @@ static long sync_fence_ioctl(struct file *file, unsigned int cmd, } } -#ifdef CONFIG_DEBUG_FS -static const char *sync_status_str(int status) -{ - if (status > 0) - return "signaled"; - else if (status == 0) - return "active"; - else - return "error"; -} - -static void sync_print_pt(struct seq_file *s, struct sync_pt *pt, bool fence) -{ - int status = pt->status; - - seq_printf(s, " %s%spt %s", - fence ? pt->parent->name : "", - fence ? "_" : "", - sync_status_str(status)); - if (pt->status) { - struct timeval tv = ktime_to_timeval(pt->timestamp); - - seq_printf(s, "@%ld.%06ld", tv.tv_sec, tv.tv_usec); - } - - if (pt->parent->ops->timeline_value_str && - pt->parent->ops->pt_value_str) { - char value[64]; - - pt->parent->ops->pt_value_str(pt, value, sizeof(value)); - seq_printf(s, ": %s", value); - if (fence) { - pt->parent->ops->timeline_value_str(pt->parent, value, - sizeof(value)); - seq_printf(s, " / %s", value); - } - } else if (pt->parent->ops->print_pt) { - seq_puts(s, ": "); - pt->parent->ops->print_pt(s, pt); - } - - seq_puts(s, "\n"); -} - -static void sync_print_obj(struct seq_file *s, struct sync_timeline *obj) -{ - struct list_head *pos; - unsigned long flags; - - seq_printf(s, "%s %s", obj->name, obj->ops->driver_name); - - if (obj->ops->timeline_value_str) { - char value[64]; - - obj->ops->timeline_value_str(obj, value, sizeof(value)); - seq_printf(s, ": %s", value); - } else if (obj->ops->print_obj) { - seq_puts(s, ": "); - obj->ops->print_obj(s, obj); - } - - seq_puts(s, "\n"); - - spin_lock_irqsave(&obj->child_list_lock, flags); - list_for_each(pos, &obj->child_list_head) { - struct sync_pt *pt = - container_of(pos, struct sync_pt, child_list); - sync_print_pt(s, pt, false); - } - spin_unlock_irqrestore(&obj->child_list_lock, flags); -} - -static void sync_print_fence(struct seq_file *s, struct sync_fence *fence) -{ - struct list_head *pos; - unsigned long flags; - - seq_printf(s, "[%p] %s: %s\n", fence, fence->name, - sync_status_str(fence->status)); - - list_for_each(pos, &fence->pt_list_head) { - struct sync_pt *pt = - container_of(pos, struct sync_pt, pt_list); - sync_print_pt(s, pt, true); - } - - spin_lock_irqsave(&fence->waiter_list_lock, flags); - list_for_each(pos, &fence->waiter_list_head) { - struct sync_fence_waiter *waiter = - container_of(pos, struct sync_fence_waiter, - waiter_list); - - seq_printf(s, "waiter %pF\n", waiter->callback); - } - spin_unlock_irqrestore(&fence->waiter_list_lock, flags); -} - -static int sync_debugfs_show(struct seq_file *s, void *unused) -{ - unsigned long flags; - struct list_head *pos; - - seq_puts(s, "objs:\n--------------\n"); - - spin_lock_irqsave(&sync_timeline_list_lock, flags); - list_for_each(pos, &sync_timeline_list_head) { - struct sync_timeline *obj = - container_of(pos, struct sync_timeline, - sync_timeline_list); - - sync_print_obj(s, obj); - seq_puts(s, "\n"); - } - spin_unlock_irqrestore(&sync_timeline_list_lock, flags); - - seq_puts(s, "fences:\n--------------\n"); - - spin_lock_irqsave(&sync_fence_list_lock, flags); - list_for_each(pos, &sync_fence_list_head) { - struct sync_fence *fence = - container_of(pos, struct sync_fence, sync_fence_list); - - sync_print_fence(s, fence); - seq_puts(s, "\n"); - } - spin_unlock_irqrestore(&sync_fence_list_lock, flags); - return 0; -} - -static int sync_debugfs_open(struct inode *inode, struct file *file) -{ - return single_open(file, sync_debugfs_show, inode->i_private); -} - -static const struct file_operations sync_debugfs_fops = { - .open = sync_debugfs_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, +static const struct file_operations sync_fence_fops = { + .release = sync_fence_release, + .poll = sync_fence_poll, + .unlocked_ioctl = sync_fence_ioctl, + .compat_ioctl = sync_fence_ioctl, }; -static __init int sync_debugfs_init(void) -{ - debugfs_create_file("sync", S_IRUGO, NULL, NULL, &sync_debugfs_fops); - return 0; -} -late_initcall(sync_debugfs_init); - -#define DUMP_CHUNK 256 -static char sync_dump_buf[64 * 1024]; -static void sync_dump(void) -{ - struct seq_file s = { - .buf = sync_dump_buf, - .size = sizeof(sync_dump_buf) - 1, - }; - int i; - - sync_debugfs_show(&s, NULL); - - for (i = 0; i < s.count; i += DUMP_CHUNK) { - if ((s.count - i) > DUMP_CHUNK) { - char c = s.buf[i + DUMP_CHUNK]; - - s.buf[i + DUMP_CHUNK] = 0; - pr_cont("%s", s.buf + i); - s.buf[i + DUMP_CHUNK] = c; - } else { - s.buf[s.count] = 0; - pr_cont("%s", s.buf + i); - } - } -} -#else -static void sync_dump(void) -{ -} -#endif diff --git a/drivers/staging/android/sync.h b/drivers/staging/android/sync.h index eaf57cccf626..66b0f431f63e 100644 --- a/drivers/staging/android/sync.h +++ b/drivers/staging/android/sync.h @@ -19,6 +19,7 @@ #include <linux/list.h> #include <linux/spinlock.h> #include <linux/wait.h> +#include <linux/fence.h> #include "uapi/sync.h" @@ -40,8 +41,6 @@ struct sync_fence; * -1 if a will signal before b * @free_pt: called before sync_pt is freed * @release_obj: called before sync_timeline is freed - * @print_obj: deprecated - * @print_pt: deprecated * @fill_driver_data: write implementation specific driver data to data. * should return an error if there is not enough room * as specified by size. This information is returned @@ -67,13 +66,6 @@ struct sync_timeline_ops { /* optional */ void (*release_obj)(struct sync_timeline *sync_timeline); - /* deprecated */ - void (*print_obj)(struct seq_file *s, - struct sync_timeline *sync_timeline); - - /* deprecated */ - void (*print_pt)(struct seq_file *s, struct sync_pt *sync_pt); - /* optional */ int (*fill_driver_data)(struct sync_pt *syncpt, void *data, int size); @@ -104,19 +96,21 @@ struct sync_timeline { /* protected by child_list_lock */ bool destroyed; + int context, value; struct list_head child_list_head; spinlock_t child_list_lock; struct list_head active_list_head; - spinlock_t active_list_lock; +#ifdef CONFIG_DEBUG_FS struct list_head sync_timeline_list; +#endif }; /** * struct sync_pt - sync point - * @parent: sync_timeline to which this sync_pt belongs + * @fence: base fence class * @child_list: membership in sync_timeline.child_list_head * @active_list: membership in sync_timeline.active_list_head * @signaled_list: membership in temporary signaled_list on stack @@ -127,19 +121,22 @@ struct sync_timeline { * signaled or error. */ struct sync_pt { - struct sync_timeline *parent; - struct list_head child_list; + struct fence base; + struct list_head child_list; struct list_head active_list; - struct list_head signaled_list; - - struct sync_fence *fence; - struct list_head pt_list; +}; - /* protected by parent->active_list_lock */ - int status; +static inline struct sync_timeline *sync_pt_parent(struct sync_pt *pt) +{ + return container_of(pt->base.lock, struct sync_timeline, + child_list_lock); +} - ktime_t timestamp; +struct sync_fence_cb { + struct fence_cb cb; + struct fence *sync_pt; + struct sync_fence *fence; }; /** @@ -149,9 +146,7 @@ struct sync_pt { * @name: name of sync_fence. Useful for debugging * @pt_list_head: list of sync_pts in the fence. immutable once fence * is created - * @waiter_list_head: list of asynchronous waiters on this fence - * @waiter_list_lock: lock protecting @waiter_list_head and @status - * @status: 1: signaled, 0:active, <0: error + * @status: 0: signaled, >0:active, <0: error * * @wq: wait queue for fence signaling * @sync_fence_list: membership in global fence list @@ -160,17 +155,15 @@ struct sync_fence { struct file *file; struct kref kref; char name[32]; - - /* this list is immutable once the fence is created */ - struct list_head pt_list_head; - - struct list_head waiter_list_head; - spinlock_t waiter_list_lock; /* also protects status */ - int status; +#ifdef CONFIG_DEBUG_FS + struct list_head sync_fence_list; +#endif + int num_fences; wait_queue_head_t wq; + atomic_t status; - struct list_head sync_fence_list; + struct sync_fence_cb cbs[]; }; struct sync_fence_waiter; @@ -184,14 +177,14 @@ typedef void (*sync_callback_t)(struct sync_fence *fence, * @callback_data: pointer to pass to @callback */ struct sync_fence_waiter { - struct list_head waiter_list; - - sync_callback_t callback; + wait_queue_t work; + sync_callback_t callback; }; static inline void sync_fence_waiter_init(struct sync_fence_waiter *waiter, sync_callback_t callback) { + INIT_LIST_HEAD(&waiter->work.task_list); waiter->callback = callback; } @@ -341,4 +334,22 @@ int sync_fence_cancel_async(struct sync_fence *fence, */ int sync_fence_wait(struct sync_fence *fence, long timeout); +#ifdef CONFIG_DEBUG_FS + +extern void sync_timeline_debug_add(struct sync_timeline *obj); +extern void sync_timeline_debug_remove(struct sync_timeline *obj); +extern void sync_fence_debug_add(struct sync_fence *fence); +extern void sync_fence_debug_remove(struct sync_fence *fence); +extern void sync_dump(void); + +#else +# define sync_timeline_debug_add(obj) +# define sync_timeline_debug_remove(obj) +# define sync_fence_debug_add(fence) +# define sync_fence_debug_remove(fence) +# define sync_dump() +#endif +int sync_fence_wake_up_wq(wait_queue_t *curr, unsigned mode, + int wake_flags, void *key); + #endif /* _LINUX_SYNC_H */ diff --git a/drivers/staging/android/sync_debug.c b/drivers/staging/android/sync_debug.c new file mode 100644 index 000000000000..257fc91bf02b --- /dev/null +++ b/drivers/staging/android/sync_debug.c @@ -0,0 +1,252 @@ +/* + * drivers/base/sync.c + * + * Copyright (C) 2012 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * 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. + * + */ + +#include <linux/debugfs.h> +#include <linux/export.h> +#include <linux/file.h> +#include <linux/fs.h> +#include <linux/kernel.h> +#include <linux/poll.h> +#include <linux/sched.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#include <linux/anon_inodes.h> +#include "sync.h" + +#ifdef CONFIG_DEBUG_FS + +static LIST_HEAD(sync_timeline_list_head); +static DEFINE_SPINLOCK(sync_timeline_list_lock); +static LIST_HEAD(sync_fence_list_head); +static DEFINE_SPINLOCK(sync_fence_list_lock); + +void sync_timeline_debug_add(struct sync_timeline *obj) +{ + unsigned long flags; + + spin_lock_irqsave(&sync_timeline_list_lock, flags); + list_add_tail(&obj->sync_timeline_list, &sync_timeline_list_head); + spin_unlock_irqrestore(&sync_timeline_list_lock, flags); +} + +void sync_timeline_debug_remove(struct sync_timeline *obj) +{ + unsigned long flags; + + spin_lock_irqsave(&sync_timeline_list_lock, flags); + list_del(&obj->sync_timeline_list); + spin_unlock_irqrestore(&sync_timeline_list_lock, flags); +} + +void sync_fence_debug_add(struct sync_fence *fence) +{ + unsigned long flags; + + spin_lock_irqsave(&sync_fence_list_lock, flags); + list_add_tail(&fence->sync_fence_list, &sync_fence_list_head); + spin_unlock_irqrestore(&sync_fence_list_lock, flags); +} + +void sync_fence_debug_remove(struct sync_fence *fence) +{ + unsigned long flags; + + spin_lock_irqsave(&sync_fence_list_lock, flags); + list_del(&fence->sync_fence_list); + spin_unlock_irqrestore(&sync_fence_list_lock, flags); +} + +static const char *sync_status_str(int status) +{ + if (status == 0) + return "signaled"; + + if (status > 0) + return "active"; + + return "error"; +} + +static void sync_print_pt(struct seq_file *s, struct sync_pt *pt, bool fence) +{ + int status = 1; + struct sync_timeline *parent = sync_pt_parent(pt); + + if (fence_is_signaled_locked(&pt->base)) + status = pt->base.status; + + seq_printf(s, " %s%spt %s", + fence ? parent->name : "", + fence ? "_" : "", + sync_status_str(status)); + + if (status <= 0) { + struct timeval tv = ktime_to_timeval(pt->base.timestamp); + + seq_printf(s, "@%ld.%06ld", tv.tv_sec, tv.tv_usec); + } + + if (parent->ops->timeline_value_str && + parent->ops->pt_value_str) { + char value[64]; + + parent->ops->pt_value_str(pt, value, sizeof(value)); + seq_printf(s, ": %s", value); + if (fence) { + parent->ops->timeline_value_str(parent, value, + sizeof(value)); + seq_printf(s, " / %s", value); + } + } + + seq_puts(s, "\n"); +} + +static void sync_print_obj(struct seq_file *s, struct sync_timeline *obj) +{ + struct list_head *pos; + unsigned long flags; + + seq_printf(s, "%s %s", obj->name, obj->ops->driver_name); + + if (obj->ops->timeline_value_str) { + char value[64]; + + obj->ops->timeline_value_str(obj, value, sizeof(value)); + seq_printf(s, ": %s", value); + } + + seq_puts(s, "\n"); + + spin_lock_irqsave(&obj->child_list_lock, flags); + list_for_each(pos, &obj->child_list_head) { + struct sync_pt *pt = + container_of(pos, struct sync_pt, child_list); + sync_print_pt(s, pt, false); + } + spin_unlock_irqrestore(&obj->child_list_lock, flags); +} + +static void sync_print_fence(struct seq_file *s, struct sync_fence *fence) +{ + wait_queue_t *pos; + unsigned long flags; + int i; + + seq_printf(s, "[%p] %s: %s\n", fence, fence->name, + sync_status_str(atomic_read(&fence->status))); + + for (i = 0; i < fence->num_fences; ++i) { + struct sync_pt *pt = + container_of(fence->cbs[i].sync_pt, + struct sync_pt, base); + + sync_print_pt(s, pt, true); + } + + spin_lock_irqsave(&fence->wq.lock, flags); + list_for_each_entry(pos, &fence->wq.task_list, task_list) { + struct sync_fence_waiter *waiter; + + if (pos->func != &sync_fence_wake_up_wq) + continue; + + waiter = container_of(pos, struct sync_fence_waiter, work); + + seq_printf(s, "waiter %pF\n", waiter->callback); + } + spin_unlock_irqrestore(&fence->wq.lock, flags); +} + +static int sync_debugfs_show(struct seq_file *s, void *unused) +{ + unsigned long flags; + struct list_head *pos; + + seq_puts(s, "objs:\n--------------\n"); + + spin_lock_irqsave(&sync_timeline_list_lock, flags); + list_for_each(pos, &sync_timeline_list_head) { + struct sync_timeline *obj = + container_of(pos, struct sync_timeline, + sync_timeline_list); + + sync_print_obj(s, obj); + seq_puts(s, "\n"); + } + spin_unlock_irqrestore(&sync_timeline_list_lock, flags); + + seq_puts(s, "fences:\n--------------\n"); + + spin_lock_irqsave(&sync_fence_list_lock, flags); + list_for_each(pos, &sync_fence_list_head) { + struct sync_fence *fence = + container_of(pos, struct sync_fence, sync_fence_list); + + sync_print_fence(s, fence); + seq_puts(s, "\n"); + } + spin_unlock_irqrestore(&sync_fence_list_lock, flags); + return 0; +} + +static int sync_debugfs_open(struct inode *inode, struct file *file) +{ + return single_open(file, sync_debugfs_show, inode->i_private); +} + +static const struct file_operations sync_debugfs_fops = { + .open = sync_debugfs_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static __init int sync_debugfs_init(void) +{ + debugfs_create_file("sync", S_IRUGO, NULL, NULL, &sync_debugfs_fops); + return 0; +} +late_initcall(sync_debugfs_init); + +#define DUMP_CHUNK 256 +static char sync_dump_buf[64 * 1024]; +void sync_dump(void) +{ + struct seq_file s = { + .buf = sync_dump_buf, + .size = sizeof(sync_dump_buf) - 1, + }; + int i; + + sync_debugfs_show(&s, NULL); + + for (i = 0; i < s.count; i += DUMP_CHUNK) { + if ((s.count - i) > DUMP_CHUNK) { + char c = s.buf[i + DUMP_CHUNK]; + + s.buf[i + DUMP_CHUNK] = 0; + pr_cont("%s", s.buf + i); + s.buf[i + DUMP_CHUNK] = c; + } else { + s.buf[s.count] = 0; + pr_cont("%s", s.buf + i); + } + } +} + +#endif diff --git a/drivers/staging/android/trace/sync.h b/drivers/staging/android/trace/sync.h index 95462359ba57..77edb977a7bf 100644 --- a/drivers/staging/android/trace/sync.h +++ b/drivers/staging/android/trace/sync.h @@ -45,7 +45,7 @@ TRACE_EVENT(sync_wait, TP_fast_assign( __assign_str(name, fence->name); - __entry->status = fence->status; + __entry->status = atomic_read(&fence->status); __entry->begin = begin; ), @@ -54,19 +54,19 @@ TRACE_EVENT(sync_wait, ); TRACE_EVENT(sync_pt, - TP_PROTO(struct sync_pt *pt), + TP_PROTO(struct fence *pt), TP_ARGS(pt), TP_STRUCT__entry( - __string(timeline, pt->parent->name) + __string(timeline, pt->ops->get_timeline_name(pt)) __array(char, value, 32) ), TP_fast_assign( - __assign_str(timeline, pt->parent->name); - if (pt->parent->ops->pt_value_str) { - pt->parent->ops->pt_value_str(pt, __entry->value, + __assign_str(timeline, pt->ops->get_timeline_name(pt)); + if (pt->ops->fence_value_str) { + pt->ops->fence_value_str(pt, __entry->value, sizeof(__entry->value)); } else { __entry->value[0] = '\0'; |