From ec51b7f538c440bfa5a4d538133c659071c02155 Mon Sep 17 00:00:00 2001 From: Michael Hennerich Date: Tue, 19 Jan 2010 00:27:58 -0800 Subject: Input: ad7879 - support auxiliary GPIOs via gpiolib Drop the simple fancy sysfs hooks for the aux GPIOs and expose these via the gpiolib interface so that other drivers can use them. Signed-off-by: Michael Hennerich Signed-off-by: Mike Frysinger Signed-off-by: Dmitry Torokhov --- include/linux/spi/ad7879.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/ad7879.h b/include/linux/spi/ad7879.h index 4231104c9afa..6334cee1a3be 100644 --- a/include/linux/spi/ad7879.h +++ b/include/linux/spi/ad7879.h @@ -28,8 +28,12 @@ struct ad7879_platform_data { * 1 = 4, 2 = 8, 3 = 16 (median > averaging) */ u8 median; - /* 1 = AUX/VBAT/GPIO set to GPIO Output */ - u8 gpio_output; - /* Initial GPIO pin state (valid if gpio_output = 1) */ - u8 gpio_default; + /* 1 = AUX/VBAT/GPIO export GPIO to gpiolib + * requires CONFIG_GPIOLIB + */ + bool gpio_export; + /* identifies the first GPIO number handled by this chip; + * or, if negative, requests dynamic ID allocation. + */ + s32 gpio_base; }; -- cgit v1.2.3 From 4f9c85a1b03bfa5c0a0d8488a3a7766f3c9fb756 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Mon, 18 Jan 2010 05:37:16 +0000 Subject: phylib: Move workqueue initialization to a proper place commit 541cd3ee00a4fe975b22fac6a3bc846bacef37f7 ("phylib: Fix deadlock on resume") caused TI DaVinci EMAC ethernet driver to oops upon resume: PM: resume of devices complete after 237.098 msecs Restarting tasks ... done. kernel BUG at kernel/workqueue.c:354! Unable to handle kernel NULL pointer dereference at virtual address 00000000 [...] Backtrace: [] (__bug+0x0/0x2c) from [] (queue_delayed_work_on+0x74/0xf8) [] (queue_delayed_work_on+0x0/0xf8) from [] (queue_delayed_work+0x2c/0x30) The oops pops up because TI DaVinci EMAC driver detaches PHY on suspend and attaches it back on resume. Attaching makes phylib call phy_start_machine() that initializes a workqueue. On the other hand, PHY's resume routine will call phy_start_machine() again, and that will cause the oops since we just destroyed the already scheduled workqueue. This patch fixes the issue by moving workqueue initialization to phy_device_create(). p.s. We don't see this oops with ucc_geth and gianfar drivers because they perform a fine-grained suspend, i.e. they just stop the PHYs without detaching. Reported-by: Sekhar Nori Signed-off-by: Anton Vorontsov Tested-by: Sekhar Nori Signed-off-by: David S. Miller --- drivers/net/phy/phy.c | 4 +--- drivers/net/phy/phy_device.c | 1 + include/linux/phy.h | 1 + 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index b0e9f9c51721..0295097d6c44 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -410,7 +410,6 @@ EXPORT_SYMBOL(phy_start_aneg); static void phy_change(struct work_struct *work); -static void phy_state_machine(struct work_struct *work); /** * phy_start_machine - start PHY state machine tracking @@ -430,7 +429,6 @@ void phy_start_machine(struct phy_device *phydev, { phydev->adjust_state = handler; - INIT_DELAYED_WORK(&phydev->state_queue, phy_state_machine); schedule_delayed_work(&phydev->state_queue, HZ); } @@ -761,7 +759,7 @@ EXPORT_SYMBOL(phy_start); * phy_state_machine - Handle the state machine * @work: work_struct that describes the work to be done */ -static void phy_state_machine(struct work_struct *work) +void phy_state_machine(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); struct phy_device *phydev = diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 8212b2b93422..adbc0fded130 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -177,6 +177,7 @@ struct phy_device* phy_device_create(struct mii_bus *bus, int addr, int phy_id) dev->state = PHY_DOWN; mutex_init(&dev->lock); + INIT_DELAYED_WORK(&dev->state_queue, phy_state_machine); return dev; } diff --git a/include/linux/phy.h b/include/linux/phy.h index 7968defd2fa7..6a7eb402165d 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -485,6 +485,7 @@ void phy_driver_unregister(struct phy_driver *drv); int phy_driver_register(struct phy_driver *new_driver); void phy_prepare_link(struct phy_device *phydev, void (*adjust_link)(struct net_device *)); +void phy_state_machine(struct work_struct *work); void phy_start_machine(struct phy_device *phydev, void (*handler)(struct net_device *)); void phy_stop_machine(struct phy_device *phydev); -- cgit v1.2.3 From cb289d6244a37cf932c571d6deb0daa8030f931b Mon Sep 17 00:00:00 2001 From: Davide Libenzi Date: Wed, 13 Jan 2010 09:34:36 -0800 Subject: eventfd - allow atomic read and waitqueue remove KVM needs a wait to atomically remove themselves from the eventfd ->poll() wait queue head, in order to handle correctly their IRQfd deassign operation. This patch introduces such API, plus a way to read an eventfd from its context. Signed-off-by: Davide Libenzi Signed-off-by: Avi Kivity --- fs/eventfd.c | 89 ++++++++++++++++++++++++++++++++++++++++--------- include/linux/eventfd.h | 16 +++++++++ 2 files changed, 90 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/fs/eventfd.c b/fs/eventfd.c index d26402ff06ea..7758cc382ef0 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -135,26 +135,71 @@ static unsigned int eventfd_poll(struct file *file, poll_table *wait) return events; } -static ssize_t eventfd_read(struct file *file, char __user *buf, size_t count, - loff_t *ppos) +static void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt) +{ + *cnt = (ctx->flags & EFD_SEMAPHORE) ? 1 : ctx->count; + ctx->count -= *cnt; +} + +/** + * eventfd_ctx_remove_wait_queue - Read the current counter and removes wait queue. + * @ctx: [in] Pointer to eventfd context. + * @wait: [in] Wait queue to be removed. + * @cnt: [out] Pointer to the 64bit conter value. + * + * Returns zero if successful, or the following error codes: + * + * -EAGAIN : The operation would have blocked. + * + * This is used to atomically remove a wait queue entry from the eventfd wait + * queue head, and read/reset the counter value. + */ +int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_t *wait, + __u64 *cnt) +{ + unsigned long flags; + + spin_lock_irqsave(&ctx->wqh.lock, flags); + eventfd_ctx_do_read(ctx, cnt); + __remove_wait_queue(&ctx->wqh, wait); + if (*cnt != 0 && waitqueue_active(&ctx->wqh)) + wake_up_locked_poll(&ctx->wqh, POLLOUT); + spin_unlock_irqrestore(&ctx->wqh.lock, flags); + + return *cnt != 0 ? 0 : -EAGAIN; +} +EXPORT_SYMBOL_GPL(eventfd_ctx_remove_wait_queue); + +/** + * eventfd_ctx_read - Reads the eventfd counter or wait if it is zero. + * @ctx: [in] Pointer to eventfd context. + * @no_wait: [in] Different from zero if the operation should not block. + * @cnt: [out] Pointer to the 64bit conter value. + * + * Returns zero if successful, or the following error codes: + * + * -EAGAIN : The operation would have blocked but @no_wait was nonzero. + * -ERESTARTSYS : A signal interrupted the wait operation. + * + * If @no_wait is zero, the function might sleep until the eventfd internal + * counter becomes greater than zero. + */ +ssize_t eventfd_ctx_read(struct eventfd_ctx *ctx, int no_wait, __u64 *cnt) { - struct eventfd_ctx *ctx = file->private_data; ssize_t res; - __u64 ucnt = 0; DECLARE_WAITQUEUE(wait, current); - if (count < sizeof(ucnt)) - return -EINVAL; spin_lock_irq(&ctx->wqh.lock); + *cnt = 0; res = -EAGAIN; if (ctx->count > 0) - res = sizeof(ucnt); - else if (!(file->f_flags & O_NONBLOCK)) { + res = 0; + else if (!no_wait) { __add_wait_queue(&ctx->wqh, &wait); - for (res = 0;;) { + for (;;) { set_current_state(TASK_INTERRUPTIBLE); if (ctx->count > 0) { - res = sizeof(ucnt); + res = 0; break; } if (signal_pending(current)) { @@ -168,18 +213,32 @@ static ssize_t eventfd_read(struct file *file, char __user *buf, size_t count, __remove_wait_queue(&ctx->wqh, &wait); __set_current_state(TASK_RUNNING); } - if (likely(res > 0)) { - ucnt = (ctx->flags & EFD_SEMAPHORE) ? 1 : ctx->count; - ctx->count -= ucnt; + if (likely(res == 0)) { + eventfd_ctx_do_read(ctx, cnt); if (waitqueue_active(&ctx->wqh)) wake_up_locked_poll(&ctx->wqh, POLLOUT); } spin_unlock_irq(&ctx->wqh.lock); - if (res > 0 && put_user(ucnt, (__u64 __user *) buf)) - return -EFAULT; return res; } +EXPORT_SYMBOL_GPL(eventfd_ctx_read); + +static ssize_t eventfd_read(struct file *file, char __user *buf, size_t count, + loff_t *ppos) +{ + struct eventfd_ctx *ctx = file->private_data; + ssize_t res; + __u64 cnt; + + if (count < sizeof(cnt)) + return -EINVAL; + res = eventfd_ctx_read(ctx, file->f_flags & O_NONBLOCK, &cnt); + if (res < 0) + return res; + + return put_user(cnt, (__u64 __user *) buf) ? -EFAULT : sizeof(cnt); +} static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index 94dd10366a78..91bb4f27238c 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -10,6 +10,7 @@ #include #include +#include /* * CAREFUL: Check include/asm-generic/fcntl.h when defining @@ -34,6 +35,9 @@ struct file *eventfd_fget(int fd); struct eventfd_ctx *eventfd_ctx_fdget(int fd); struct eventfd_ctx *eventfd_ctx_fileget(struct file *file); int eventfd_signal(struct eventfd_ctx *ctx, int n); +ssize_t eventfd_ctx_read(struct eventfd_ctx *ctx, int no_wait, __u64 *cnt); +int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_t *wait, + __u64 *cnt); #else /* CONFIG_EVENTFD */ @@ -61,6 +65,18 @@ static inline void eventfd_ctx_put(struct eventfd_ctx *ctx) } +static inline ssize_t eventfd_ctx_read(struct eventfd_ctx *ctx, int no_wait, + __u64 *cnt) +{ + return -ENOSYS; +} + +static inline int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, + wait_queue_t *wait, __u64 *cnt) +{ + return -ENOSYS; +} + #endif #endif /* _LINUX_EVENTFD_H */ -- cgit v1.2.3 From 6d3faf6f431bafb25f4b9926c50a7e5c267738c6 Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Sun, 24 Jan 2010 14:48:00 +0100 Subject: firewire: cdev: add_descriptor documentation fix struct fw_cdev_add_descriptor.length is in quadlets, not in bytes. Also remove any doubts about the endianess of descriptor data. Signed-off-by: Stefan Richter --- include/linux/firewire-cdev.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index 1f716d9f714b..520ecf86cbb3 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -380,7 +380,7 @@ struct fw_cdev_initiate_bus_reset { * @immediate: If non-zero, immediate key to insert before pointer * @key: Upper 8 bits of root directory pointer * @data: Userspace pointer to contents of descriptor block - * @length: Length of descriptor block data, in bytes + * @length: Length of descriptor block data, in quadlets * @handle: Handle to the descriptor, written by the kernel * * Add a descriptor block and optionally a preceding immediate key to the local @@ -394,6 +394,8 @@ struct fw_cdev_initiate_bus_reset { * If not 0, the @immediate field specifies an immediate key which will be * inserted before the root directory pointer. * + * @immediate, @key, and @data array elements are CPU-endian quadlets. + * * If successful, the kernel adds the descriptor and writes back a handle to the * kernel-side object to be used for later removal of the descriptor block and * immediate key. -- cgit v1.2.3 From 0531b2aac59c2296570ac52bfc032ef2ace7d5e1 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 27 Jan 2010 09:20:03 -0800 Subject: mm: add new 'read_cache_page_gfp()' helper function It's a simplified 'read_cache_page()' which takes a page allocation flag, so that different paths can control how aggressive the memory allocations are that populate a address space. In particular, the intel GPU object mapping code wants to be able to do a certain amount of own internal memory management by automatically shrinking the address space when memory starts getting tight. This allows it to dynamically use different memory allocation policies on a per-allocation basis, rather than depend on the (static) address space gfp policy. The actual new function is a one-liner, but re-organizing the helper functions to the point where you can do this with a single line of code is what most of the patch is all about. Tested-by: Chris Wilson Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 2 + mm/filemap.c | 100 ++++++++++++++++++++++++++++++++---------------- 2 files changed, 70 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ed5d7501e181..3c62ed408492 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -253,6 +253,8 @@ extern struct page * read_cache_page_async(struct address_space *mapping, extern struct page * read_cache_page(struct address_space *mapping, pgoff_t index, filler_t *filler, void *data); +extern struct page * read_cache_page_gfp(struct address_space *mapping, + pgoff_t index, gfp_t gfp_mask); extern int read_cache_pages(struct address_space *mapping, struct list_head *pages, filler_t *filler, void *data); diff --git a/mm/filemap.c b/mm/filemap.c index 96ac6b0eb6cb..e3736923220e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1634,14 +1634,15 @@ EXPORT_SYMBOL(generic_file_readonly_mmap); static struct page *__read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *,struct page*), - void *data) + void *data, + gfp_t gfp) { struct page *page; int err; repeat: page = find_get_page(mapping, index); if (!page) { - page = page_cache_alloc_cold(mapping); + page = __page_cache_alloc(gfp | __GFP_COLD); if (!page) return ERR_PTR(-ENOMEM); err = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL); @@ -1661,31 +1662,18 @@ repeat: return page; } -/** - * read_cache_page_async - read into page cache, fill it if needed - * @mapping: the page's address_space - * @index: the page index - * @filler: function to perform the read - * @data: destination for read data - * - * Same as read_cache_page, but don't wait for page to become unlocked - * after submitting it to the filler. - * - * Read into the page cache. If a page already exists, and PageUptodate() is - * not set, try to fill the page but don't wait for it to become unlocked. - * - * If the page does not get brought uptodate, return -EIO. - */ -struct page *read_cache_page_async(struct address_space *mapping, +static struct page *do_read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *,struct page*), - void *data) + void *data, + gfp_t gfp) + { struct page *page; int err; retry: - page = __read_cache_page(mapping, index, filler, data); + page = __read_cache_page(mapping, index, filler, data, gfp); if (IS_ERR(page)) return page; if (PageUptodate(page)) @@ -1710,8 +1698,67 @@ out: mark_page_accessed(page); return page; } + +/** + * read_cache_page_async - read into page cache, fill it if needed + * @mapping: the page's address_space + * @index: the page index + * @filler: function to perform the read + * @data: destination for read data + * + * Same as read_cache_page, but don't wait for page to become unlocked + * after submitting it to the filler. + * + * Read into the page cache. If a page already exists, and PageUptodate() is + * not set, try to fill the page but don't wait for it to become unlocked. + * + * If the page does not get brought uptodate, return -EIO. + */ +struct page *read_cache_page_async(struct address_space *mapping, + pgoff_t index, + int (*filler)(void *,struct page*), + void *data) +{ + return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping)); +} EXPORT_SYMBOL(read_cache_page_async); +static struct page *wait_on_page_read(struct page *page) +{ + if (!IS_ERR(page)) { + wait_on_page_locked(page); + if (!PageUptodate(page)) { + page_cache_release(page); + page = ERR_PTR(-EIO); + } + } + return page; +} + +/** + * read_cache_page_gfp - read into page cache, using specified page allocation flags. + * @mapping: the page's address_space + * @index: the page index + * @gfp: the page allocator flags to use if allocating + * + * This is the same as "read_mapping_page(mapping, index, NULL)", but with + * any new page allocations done using the specified allocation flags. Note + * that the Radix tree operations will still use GFP_KERNEL, so you can't + * expect to do this atomically or anything like that - but you can pass in + * other page requirements. + * + * If the page does not get brought uptodate, return -EIO. + */ +struct page *read_cache_page_gfp(struct address_space *mapping, + pgoff_t index, + gfp_t gfp) +{ + filler_t *filler = (filler_t *)mapping->a_ops->readpage; + + return wait_on_page_read(do_read_cache_page(mapping, index, filler, NULL, gfp)); +} +EXPORT_SYMBOL(read_cache_page_gfp); + /** * read_cache_page - read into page cache, fill it if needed * @mapping: the page's address_space @@ -1729,18 +1776,7 @@ struct page *read_cache_page(struct address_space *mapping, int (*filler)(void *,struct page*), void *data) { - struct page *page; - - page = read_cache_page_async(mapping, index, filler, data); - if (IS_ERR(page)) - goto out; - wait_on_page_locked(page); - if (!PageUptodate(page)) { - page_cache_release(page); - page = ERR_PTR(-EIO); - } - out: - return page; + return wait_on_page_read(read_cache_page_async(mapping, index, filler, data)); } EXPORT_SYMBOL(read_cache_page); -- cgit v1.2.3 From bb209c8287d2d55ec4a67e3933346e0a3ee0da76 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Tue, 26 Jan 2010 17:10:03 +0000 Subject: powerpc/pci: Add calls to set_pcie_port_type() and set_pcie_hotplug_bridge() We are missing these when building the pci_dev from scratch off the Open Firmware device-tree Signed-off-by: Benjamin Herrenschmidt Acked-by: Jesse Barnes --- arch/powerpc/kernel/pci_of_scan.c | 2 ++ drivers/pci/probe.c | 4 ++-- include/linux/pci.h | 4 ++++ 3 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 7311fdfb9bf8..693eb9a25bfa 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -140,6 +140,7 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, dev->devfn = devfn; dev->multifunction = 0; /* maybe a lie? */ dev->needs_freset = 0; /* pcie fundamental reset required */ + set_pcie_port_type(dev); dev->vendor = get_int_prop(node, "vendor-id", 0xffff); dev->device = get_int_prop(node, "device-id", 0xffff); @@ -164,6 +165,7 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, /* a PCI-PCI bridge */ dev->hdr_type = PCI_HEADER_TYPE_BRIDGE; dev->rom_base_reg = PCI_ROM_ADDRESS1; + set_pcie_hotplug_bridge(dev); } else if (!strcmp(type, "cardbus")) { dev->hdr_type = PCI_HEADER_TYPE_CARDBUS; } else { diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 98ffb2de22e9..446e4a94d7d3 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -681,7 +681,7 @@ static void pci_read_irq(struct pci_dev *dev) dev->irq = irq; } -static void set_pcie_port_type(struct pci_dev *pdev) +void set_pcie_port_type(struct pci_dev *pdev) { int pos; u16 reg16; @@ -695,7 +695,7 @@ static void set_pcie_port_type(struct pci_dev *pdev) pdev->pcie_type = (reg16 & PCI_EXP_FLAGS_TYPE) >> 4; } -static void set_pcie_hotplug_bridge(struct pci_dev *pdev) +void set_pcie_hotplug_bridge(struct pci_dev *pdev) { int pos; u16 reg16; diff --git a/include/linux/pci.h b/include/linux/pci.h index 174e5392e51e..c1968f464c38 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -756,6 +756,10 @@ pci_power_t pci_target_state(struct pci_dev *dev); int pci_prepare_to_sleep(struct pci_dev *dev); int pci_back_from_sleep(struct pci_dev *dev); +/* For use by arch with custom probe code */ +void set_pcie_port_type(struct pci_dev *pdev); +void set_pcie_hotplug_bridge(struct pci_dev *pdev); + /* Functions for PCI Hotplug drivers to use */ int pci_bus_find_capability(struct pci_bus *bus, unsigned int devfn, int cap); #ifdef CONFIG_HOTPLUG -- cgit v1.2.3 From cb6ecf6f7afece066265e243657b0ac28150a7b2 Mon Sep 17 00:00:00 2001 From: Henrik Rydberg Date: Thu, 28 Jan 2010 22:28:27 -0800 Subject: Input: add the ABS_MT_PRESSURE event For pressure-based multi-touch devices, a direct way to send sensor intensity data per finger is needed. This patch adds the ABS_MT_PRESSURE event to the MT protocol. Requested-by: Yoonyoung Shim Requested-by: Mika Kuoppala Requested-by: Peter Hutterer Signed-off-by: Henrik Rydberg Signed-off-by: Dmitry Torokhov --- drivers/input/input.c | 1 + include/linux/input.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/drivers/input/input.c b/drivers/input/input.c index 30b503b8d67b..86cb2d2196ff 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -46,6 +46,7 @@ static unsigned int input_abs_bypass_init_data[] __initdata = { ABS_MT_TOOL_TYPE, ABS_MT_BLOB_ID, ABS_MT_TRACKING_ID, + ABS_MT_PRESSURE, 0 }; static unsigned long input_abs_bypass[BITS_TO_LONGS(ABS_CNT)]; diff --git a/include/linux/input.h b/include/linux/input.h index 7be8a6537b57..735ceaf1bc2d 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -660,6 +660,7 @@ struct input_absinfo { #define ABS_MT_TOOL_TYPE 0x37 /* Type of touching device */ #define ABS_MT_BLOB_ID 0x38 /* Group a set of packets as a blob */ #define ABS_MT_TRACKING_ID 0x39 /* Unique ID of initiated contact */ +#define ABS_MT_PRESSURE 0x3a /* Pressure on contact area */ #define ABS_MAX 0x3f #define ABS_CNT (ABS_MAX+1) -- cgit v1.2.3 From 221af7f87b97431e3ee21ce4b0e77d5411cf1549 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 28 Jan 2010 22:14:42 -0800 Subject: Split 'flush_old_exec' into two functions 'flush_old_exec()' is the point of no return when doing an execve(), and it is pretty badly misnamed. It doesn't just flush the old executable environment, it also starts up the new one. Which is very inconvenient for things like setting up the new personality, because we want the new personality to affect the starting of the new environment, but at the same time we do _not_ want the new personality to take effect if flushing the old one fails. As a result, the x86-64 '32-bit' personality is actually done using this insane "I'm going to change the ABI, but I haven't done it yet" bit (TIF_ABI_PENDING), with SET_PERSONALITY() not actually setting the personality, but just the "pending" bit, so that "flush_thread()" can do the actual personality magic. This patch in no way changes any of that insanity, but it does split the 'flush_old_exec()' function up into a preparatory part that can fail (still called flush_old_exec()), and a new part that will actually set up the new exec environment (setup_new_exec()). All callers are changed to trivially comply with the new world order. Signed-off-by: H. Peter Anvin Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- arch/sh/kernel/process_64.c | 2 +- arch/x86/ia32/ia32_aout.c | 10 ++++++---- fs/binfmt_aout.c | 1 + fs/binfmt_elf.c | 27 ++------------------------- fs/binfmt_elf_fdpic.c | 3 +++ fs/binfmt_flat.c | 1 + fs/binfmt_som.c | 1 + fs/exec.c | 26 ++++++++++++++++---------- include/linux/binfmts.h | 1 + include/linux/sched.h | 2 +- 10 files changed, 33 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/arch/sh/kernel/process_64.c b/arch/sh/kernel/process_64.c index 31f80c61b031..ec79faf6f021 100644 --- a/arch/sh/kernel/process_64.c +++ b/arch/sh/kernel/process_64.c @@ -368,7 +368,7 @@ void exit_thread(void) void flush_thread(void) { - /* Called by fs/exec.c (flush_old_exec) to remove traces of a + /* Called by fs/exec.c (setup_new_exec) to remove traces of a * previously running executable. */ #ifdef CONFIG_SH_FPU if (last_task_used_math == current) { diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 2a4d073d2cf1..435d2a5323da 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -308,15 +308,17 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs) if (retval) return retval; - regs->cs = __USER32_CS; - regs->r8 = regs->r9 = regs->r10 = regs->r11 = regs->r12 = - regs->r13 = regs->r14 = regs->r15 = 0; - /* OK, This is the point of no return */ set_personality(PER_LINUX); set_thread_flag(TIF_IA32); clear_thread_flag(TIF_ABI_PENDING); + setup_new_exec(bprm); + + regs->cs = __USER32_CS; + regs->r8 = regs->r9 = regs->r10 = regs->r11 = regs->r12 = + regs->r13 = regs->r14 = regs->r15 = 0; + current->mm->end_code = ex.a_text + (current->mm->start_code = N_TXTADDR(ex)); current->mm->end_data = ex.a_data + diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index 346b69405363..fdd397099172 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -264,6 +264,7 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs) #else set_personality(PER_LINUX); #endif + setup_new_exec(bprm); current->mm->end_code = ex.a_text + (current->mm->start_code = N_TXTADDR(ex)); diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index edd90c49003c..fd5b2ea5d299 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -662,27 +662,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) if (elf_interpreter[elf_ppnt->p_filesz - 1] != '\0') goto out_free_interp; - /* - * The early SET_PERSONALITY here is so that the lookup - * for the interpreter happens in the namespace of the - * to-be-execed image. SET_PERSONALITY can select an - * alternate root. - * - * However, SET_PERSONALITY is NOT allowed to switch - * this task into the new images's memory mapping - * policy - that is, TASK_SIZE must still evaluate to - * that which is appropriate to the execing application. - * This is because exit_mmap() needs to have TASK_SIZE - * evaluate to the size of the old image. - * - * So if (say) a 64-bit application is execing a 32-bit - * application it is the architecture's responsibility - * to defer changing the value of TASK_SIZE until the - * switch really is going to happen - do this in - * flush_thread(). - akpm - */ - SET_PERSONALITY(loc->elf_ex); - interpreter = open_exec(elf_interpreter); retval = PTR_ERR(interpreter); if (IS_ERR(interpreter)) @@ -730,9 +709,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) /* Verify the interpreter has a valid arch */ if (!elf_check_arch(&loc->interp_elf_ex)) goto out_free_dentry; - } else { - /* Executables without an interpreter also need a personality */ - SET_PERSONALITY(loc->elf_ex); } /* Flush all traces of the currently running executable */ @@ -752,7 +728,8 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space) current->flags |= PF_RANDOMIZE; - arch_pick_mmap_layout(current->mm); + + setup_new_exec(bprm); /* Do this so that we can load the interpreter, if need be. We will change some of these later */ diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index c57d9ce5ff7e..18d77297ccc8 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -321,6 +321,9 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm, set_personality(PER_LINUX_FDPIC); if (elf_read_implies_exec(&exec_params.hdr, executable_stack)) current->personality |= READ_IMPLIES_EXEC; + + setup_new_exec(bprm); + set_binfmt(&elf_fdpic_format); current->mm->start_code = 0; diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index d4a00ea1054c..42c6b4a54445 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -519,6 +519,7 @@ static int load_flat_file(struct linux_binprm * bprm, /* OK, This is the point of no return */ set_personality(PER_LINUX_32BIT); + setup_new_exec(bprm); } /* diff --git a/fs/binfmt_som.c b/fs/binfmt_som.c index 2a9b5330cc5e..cc8560f6c9b0 100644 --- a/fs/binfmt_som.c +++ b/fs/binfmt_som.c @@ -227,6 +227,7 @@ load_som_binary(struct linux_binprm * bprm, struct pt_regs * regs) /* OK, This is the point of no return */ current->flags &= ~PF_FORKNOEXEC; current->personality = PER_HPUX; + setup_new_exec(bprm); /* Set the task size for HP-UX processes such that * the gateway page is outside the address space. diff --git a/fs/exec.c b/fs/exec.c index 632b02e34ec7..675c3f44c2ea 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -941,9 +941,7 @@ void set_task_comm(struct task_struct *tsk, char *buf) int flush_old_exec(struct linux_binprm * bprm) { - char * name; - int i, ch, retval; - char tcomm[sizeof(current->comm)]; + int retval; /* * Make sure we have a private signal table and that @@ -963,6 +961,20 @@ int flush_old_exec(struct linux_binprm * bprm) goto out; bprm->mm = NULL; /* We're using it now */ + return 0; + +out: + return retval; +} +EXPORT_SYMBOL(flush_old_exec); + +void setup_new_exec(struct linux_binprm * bprm) +{ + int i, ch; + char * name; + char tcomm[sizeof(current->comm)]; + + arch_pick_mmap_layout(current->mm); /* This is the point of no return */ current->sas_ss_sp = current->sas_ss_size = 0; @@ -1019,14 +1031,8 @@ int flush_old_exec(struct linux_binprm * bprm) flush_signal_handlers(current, 0); flush_old_files(current->files); - - return 0; - -out: - return retval; } - -EXPORT_SYMBOL(flush_old_exec); +EXPORT_SYMBOL(setup_new_exec); /* * Prepare credentials and lock ->cred_guard_mutex. diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index cd4349bdc34e..89c6249fc561 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -109,6 +109,7 @@ extern int prepare_binprm(struct linux_binprm *); extern int __must_check remove_arg_zero(struct linux_binprm *); extern int search_binary_handler(struct linux_binprm *,struct pt_regs *); extern int flush_old_exec(struct linux_binprm * bprm); +extern void setup_new_exec(struct linux_binprm * bprm); extern int suid_dumpable; #define SUID_DUMP_DISABLE 0 /* No setuid dumping */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 6f7bba93929b..abdfacc58653 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1369,7 +1369,7 @@ struct task_struct { char comm[TASK_COMM_LEN]; /* executable name excluding path - access with [gs]et_task_comm (which lock it with task_lock()) - - initialized normally by flush_old_exec */ + - initialized normally by setup_new_exec */ /* file system info */ int link_count, total_link_count; #ifdef CONFIG_SYSVIPC -- cgit v1.2.3 From 5352ae638e2d7d5c9b2e4d528676bbf2af6fd6f3 Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Thu, 28 Jan 2010 17:04:43 -0600 Subject: perf, hw_breakpoint, kgdb: Do not take mutex for kernel debugger This patch fixes the regression in functionality where the kernel debugger and the perf API do not nicely share hw breakpoint reservations. The kernel debugger cannot use any mutex_lock() calls because it can start the kernel running from an invalid context. A mutex free version of the reservation API needed to get created for the kernel debugger to safely update hw breakpoint reservations. The possibility for a breakpoint reservation to be concurrently processed at the time that kgdb interrupts the system is improbable. Should this corner case occur the end user is warned, and the kernel debugger will prohibit updating the hardware breakpoint reservations. Any time the kernel debugger reserves a hardware breakpoint it will be a system wide reservation. Signed-off-by: Jason Wessel Acked-by: Frederic Weisbecker Cc: kgdb-bugreport@lists.sourceforge.net Cc: K.Prasad Cc: Peter Zijlstra Cc: Alan Stern Cc: torvalds@linux-foundation.org LKML-Reference: <1264719883-7285-3-git-send-email-jason.wessel@windriver.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/kgdb.c | 51 ++++++++++++++++++++++++++++++++++++++++++ include/linux/hw_breakpoint.h | 2 ++ kernel/hw_breakpoint.c | 52 ++++++++++++++++++++++++++++++++++--------- 3 files changed, 95 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 62bea7307eaa..bfba6019d762 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -239,6 +239,49 @@ static void kgdb_correct_hw_break(void) hw_breakpoint_restore(); } +static int hw_break_reserve_slot(int breakno) +{ + int cpu; + int cnt = 0; + struct perf_event **pevent; + + for_each_online_cpu(cpu) { + cnt++; + pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu); + if (dbg_reserve_bp_slot(*pevent)) + goto fail; + } + + return 0; + +fail: + for_each_online_cpu(cpu) { + cnt--; + if (!cnt) + break; + pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu); + dbg_release_bp_slot(*pevent); + } + return -1; +} + +static int hw_break_release_slot(int breakno) +{ + struct perf_event **pevent; + int cpu; + + for_each_online_cpu(cpu) { + pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu); + if (dbg_release_bp_slot(*pevent)) + /* + * The debugger is responisble for handing the retry on + * remove failure. + */ + return -1; + } + return 0; +} + static int kgdb_remove_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype) { @@ -250,6 +293,10 @@ kgdb_remove_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype) if (i == 4) return -1; + if (hw_break_release_slot(i)) { + printk(KERN_ERR "Cannot remove hw breakpoint at %lx\n", addr); + return -1; + } breakinfo[i].enabled = 0; return 0; @@ -316,6 +363,10 @@ kgdb_set_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype) return -1; } breakinfo[i].addr = addr; + if (hw_break_reserve_slot(i)) { + breakinfo[i].addr = 0; + return -1; + } breakinfo[i].enabled = 1; return 0; diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h index 41235c93e4e9..070ba0621738 100644 --- a/include/linux/hw_breakpoint.h +++ b/include/linux/hw_breakpoint.h @@ -75,6 +75,8 @@ extern int __register_perf_hw_breakpoint(struct perf_event *bp); extern void unregister_hw_breakpoint(struct perf_event *bp); extern void unregister_wide_hw_breakpoint(struct perf_event **cpu_events); +extern int dbg_reserve_bp_slot(struct perf_event *bp); +extern int dbg_release_bp_slot(struct perf_event *bp); extern int reserve_bp_slot(struct perf_event *bp); extern void release_bp_slot(struct perf_event *bp); diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c index c030ae657f20..8a5c7d55ac9f 100644 --- a/kernel/hw_breakpoint.c +++ b/kernel/hw_breakpoint.c @@ -243,38 +243,70 @@ static void toggle_bp_slot(struct perf_event *bp, bool enable) * ((per_cpu(nr_bp_flexible, *) > 1) + max(per_cpu(nr_cpu_bp_pinned, *)) * + max(per_cpu(nr_task_bp_pinned, *))) < HBP_NUM */ -int reserve_bp_slot(struct perf_event *bp) +static int __reserve_bp_slot(struct perf_event *bp) { struct bp_busy_slots slots = {0}; - int ret = 0; - - mutex_lock(&nr_bp_mutex); fetch_bp_busy_slots(&slots, bp); /* Flexible counters need to keep at least one slot */ - if (slots.pinned + (!!slots.flexible) == HBP_NUM) { - ret = -ENOSPC; - goto end; - } + if (slots.pinned + (!!slots.flexible) == HBP_NUM) + return -ENOSPC; toggle_bp_slot(bp, true); -end: + return 0; +} + +int reserve_bp_slot(struct perf_event *bp) +{ + int ret; + + mutex_lock(&nr_bp_mutex); + + ret = __reserve_bp_slot(bp); + mutex_unlock(&nr_bp_mutex); return ret; } +static void __release_bp_slot(struct perf_event *bp) +{ + toggle_bp_slot(bp, false); +} + void release_bp_slot(struct perf_event *bp) { mutex_lock(&nr_bp_mutex); - toggle_bp_slot(bp, false); + __release_bp_slot(bp); mutex_unlock(&nr_bp_mutex); } +/* + * Allow the kernel debugger to reserve breakpoint slots without + * taking a lock using the dbg_* variant of for the reserve and + * release breakpoint slots. + */ +int dbg_reserve_bp_slot(struct perf_event *bp) +{ + if (mutex_is_locked(&nr_bp_mutex)) + return -1; + + return __reserve_bp_slot(bp); +} + +int dbg_release_bp_slot(struct perf_event *bp) +{ + if (mutex_is_locked(&nr_bp_mutex)) + return -1; + + __release_bp_slot(bp); + + return 0; +} int register_perf_hw_breakpoint(struct perf_event *bp) { -- cgit v1.2.3 From d6ad3e286d2c075a60b9f11075a2c55aeeeca2ad Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Wed, 27 Jan 2010 16:25:22 -0600 Subject: softlockup: Add sched_clock_tick() to avoid kernel warning on kgdb resume When CONFIG_HAVE_UNSTABLE_SCHED_CLOCK is set, sched_clock() gets the time from hardware such as the TSC on x86. In this configuration kgdb will report a softlock warning message on resuming or detaching from a debug session. Sequence of events in the problem case: 1) "cpu sched clock" and "hardware time" are at 100 sec prior to a call to kgdb_handle_exception() 2) Debugger waits in kgdb_handle_exception() for 80 sec and on exit the following is called ... touch_softlockup_watchdog() --> __raw_get_cpu_var(touch_timestamp) = 0; 3) "cpu sched clock" = 100s (it was not updated, because the interrupt was disabled in kgdb) but the "hardware time" = 180 sec 4) The first timer interrupt after resuming from kgdb_handle_exception updates the watchdog from the "cpu sched clock" update_process_times() { ... run_local_timers() --> softlockup_tick() --> check (touch_timestamp == 0) (it is "YES" here, we have set "touch_timestamp = 0" at kgdb) --> __touch_softlockup_watchdog() ***(A)--> reset "touch_timestamp" to "get_timestamp()" (Here, the "touch_timestamp" will still be set to 100s.) ... scheduler_tick() ***(B)--> sched_clock_tick() (update "cpu sched clock" to "hardware time" = 180s) ... } 5) The Second timer interrupt handler appears to have a large jump and trips the softlockup warning. update_process_times() { ... run_local_timers() --> softlockup_tick() --> "cpu sched clock" - "touch_timestamp" = 180s-100s > 60s --> printk "soft lockup error messages" ... } note: ***(A) reset "touch_timestamp" to "get_timestamp(this_cpu)" Why is "touch_timestamp" 100 sec, instead of 180 sec? When CONFIG_HAVE_UNSTABLE_SCHED_CLOCK is set, the call trace of get_timestamp() is: get_timestamp(this_cpu) -->cpu_clock(this_cpu) -->sched_clock_cpu(this_cpu) -->__update_sched_clock(sched_clock_data, now) The __update_sched_clock() function uses the GTOD tick value to create a window to normalize the "now" values. So if "now" value is too big for sched_clock_data, it will be ignored. The fix is to invoke sched_clock_tick() to update "cpu sched clock" in order to recover from this state. This is done by introducing the function touch_softlockup_watchdog_sync(). This allows kgdb to request that the sched clock is updated when the watchdog thread runs the first time after a resume from kgdb. [yong.zhang0@gmail.com: Use per cpu instead of an array] Signed-off-by: Jason Wessel Signed-off-by: Dongdong Deng Cc: kgdb-bugreport@lists.sourceforge.net Cc: peterz@infradead.org LKML-Reference: <1264631124-4837-2-git-send-email-jason.wessel@windriver.com> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++++ kernel/kgdb.c | 6 +++--- kernel/softlockup.c | 15 +++++++++++++++ 3 files changed, 22 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 6f7bba93929b..89232151a9d0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -310,6 +310,7 @@ extern void sched_show_task(struct task_struct *p); #ifdef CONFIG_DETECT_SOFTLOCKUP extern void softlockup_tick(void); extern void touch_softlockup_watchdog(void); +extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); extern int proc_dosoftlockup_thresh(struct ctl_table *table, int write, void __user *buffer, @@ -323,6 +324,9 @@ static inline void softlockup_tick(void) static inline void touch_softlockup_watchdog(void) { } +static inline void touch_softlockup_watchdog_sync(void) +{ +} static inline void touch_all_softlockup_watchdogs(void) { } diff --git a/kernel/kgdb.c b/kernel/kgdb.c index 2eb517e23514..87f2cc557553 100644 --- a/kernel/kgdb.c +++ b/kernel/kgdb.c @@ -596,7 +596,7 @@ static void kgdb_wait(struct pt_regs *regs) /* Signal the primary CPU that we are done: */ atomic_set(&cpu_in_kgdb[cpu], 0); - touch_softlockup_watchdog(); + touch_softlockup_watchdog_sync(); clocksource_touch_watchdog(); local_irq_restore(flags); } @@ -1450,7 +1450,7 @@ acquirelock: (kgdb_info[cpu].task && kgdb_info[cpu].task->pid != kgdb_sstep_pid) && --sstep_tries) { atomic_set(&kgdb_active, -1); - touch_softlockup_watchdog(); + touch_softlockup_watchdog_sync(); clocksource_touch_watchdog(); local_irq_restore(flags); @@ -1550,7 +1550,7 @@ kgdb_restore: } /* Free kgdb_active */ atomic_set(&kgdb_active, -1); - touch_softlockup_watchdog(); + touch_softlockup_watchdog_sync(); clocksource_touch_watchdog(); local_irq_restore(flags); diff --git a/kernel/softlockup.c b/kernel/softlockup.c index d22579087e27..0d4c7898ab80 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -25,6 +25,7 @@ static DEFINE_SPINLOCK(print_lock); static DEFINE_PER_CPU(unsigned long, softlockup_touch_ts); /* touch timestamp */ static DEFINE_PER_CPU(unsigned long, softlockup_print_ts); /* print timestamp */ static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog); +static DEFINE_PER_CPU(bool, softlock_touch_sync); static int __read_mostly did_panic; int __read_mostly softlockup_thresh = 60; @@ -79,6 +80,12 @@ void touch_softlockup_watchdog(void) } EXPORT_SYMBOL(touch_softlockup_watchdog); +void touch_softlockup_watchdog_sync(void) +{ + __raw_get_cpu_var(softlock_touch_sync) = true; + __raw_get_cpu_var(softlockup_touch_ts) = 0; +} + void touch_all_softlockup_watchdogs(void) { int cpu; @@ -118,6 +125,14 @@ void softlockup_tick(void) } if (touch_ts == 0) { + if (unlikely(per_cpu(softlock_touch_sync, this_cpu))) { + /* + * If the time stamp was touched atomically + * make sure the scheduler tick is up to date. + */ + per_cpu(softlock_touch_sync, this_cpu) = false; + sched_clock_tick(); + } __touch_softlockup_watchdog(); return; } -- cgit v1.2.3 From f98bfbd78c37c5946cc53089da32a5f741efdeb7 Mon Sep 17 00:00:00 2001 From: Evgeniy Polyakov Date: Tue, 2 Feb 2010 15:58:48 -0800 Subject: connector: Delete buggy notification code. On Tue, Feb 02, 2010 at 02:57:14PM -0800, Greg KH (gregkh@suse.de) wrote: > > There are at least two ways to fix it: using a big cannon and a small > > one. The former way is to disable notification registration, since it is > > not used by anyone at all. Second way is to check whether calling > > process is root and its destination group is -1 (kind of priveledged > > one) before command is dispatched to workqueue. > > Well if no one is using it, removing it makes the most sense, right? > > No objection from me, care to make up a patch either way for this? Getting it is not used, let's drop support for notifications about (un)registered events from connector. Another option was to check credentials on receiving, but we can always restore it without bugs if needed, but genetlink has a wider code base and none complained, that userspace can not get notification when some other clients were (un)registered. Kudos for Sebastian Krahmer , who found a bug in the code. Signed-off-by: Evgeniy Polyakov Acked-by: Greg Kroah-Hartman Signed-off-by: David S. Miller --- drivers/connector/connector.c | 175 ------------------------------------------ include/linux/connector.h | 32 -------- 2 files changed, 207 deletions(-) (limited to 'include/linux') diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c index f06024668f99..537c29ac4487 100644 --- a/drivers/connector/connector.c +++ b/drivers/connector/connector.c @@ -36,17 +36,6 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Evgeniy Polyakov "); MODULE_DESCRIPTION("Generic userspace <-> kernelspace connector."); -static u32 cn_idx = CN_IDX_CONNECTOR; -static u32 cn_val = CN_VAL_CONNECTOR; - -module_param(cn_idx, uint, 0); -module_param(cn_val, uint, 0); -MODULE_PARM_DESC(cn_idx, "Connector's main device idx."); -MODULE_PARM_DESC(cn_val, "Connector's main device val."); - -static DEFINE_MUTEX(notify_lock); -static LIST_HEAD(notify_list); - static struct cn_dev cdev; static int cn_already_initialized; @@ -209,54 +198,6 @@ static void cn_rx_skb(struct sk_buff *__skb) } } -/* - * Notification routing. - * - * Gets id and checks if there are notification request for it's idx - * and val. If there are such requests notify the listeners with the - * given notify event. - * - */ -static void cn_notify(struct cb_id *id, u32 notify_event) -{ - struct cn_ctl_entry *ent; - - mutex_lock(¬ify_lock); - list_for_each_entry(ent, ¬ify_list, notify_entry) { - int i; - struct cn_notify_req *req; - struct cn_ctl_msg *ctl = ent->msg; - int idx_found, val_found; - - idx_found = val_found = 0; - - req = (struct cn_notify_req *)ctl->data; - for (i = 0; i < ctl->idx_notify_num; ++i, ++req) { - if (id->idx >= req->first && - id->idx < req->first + req->range) { - idx_found = 1; - break; - } - } - - for (i = 0; i < ctl->val_notify_num; ++i, ++req) { - if (id->val >= req->first && - id->val < req->first + req->range) { - val_found = 1; - break; - } - } - - if (idx_found && val_found) { - struct cn_msg m = { .ack = notify_event, }; - - memcpy(&m.id, id, sizeof(m.id)); - cn_netlink_send(&m, ctl->group, GFP_KERNEL); - } - } - mutex_unlock(¬ify_lock); -} - /* * Callback add routing - adds callback with given ID and name. * If there is registered callback with the same ID it will not be added. @@ -276,8 +217,6 @@ int cn_add_callback(struct cb_id *id, char *name, if (err) return err; - cn_notify(id, 0); - return 0; } EXPORT_SYMBOL_GPL(cn_add_callback); @@ -295,111 +234,9 @@ void cn_del_callback(struct cb_id *id) struct cn_dev *dev = &cdev; cn_queue_del_callback(dev->cbdev, id); - cn_notify(id, 1); } EXPORT_SYMBOL_GPL(cn_del_callback); -/* - * Checks two connector's control messages to be the same. - * Returns 1 if they are the same or if the first one is corrupted. - */ -static int cn_ctl_msg_equals(struct cn_ctl_msg *m1, struct cn_ctl_msg *m2) -{ - int i; - struct cn_notify_req *req1, *req2; - - if (m1->idx_notify_num != m2->idx_notify_num) - return 0; - - if (m1->val_notify_num != m2->val_notify_num) - return 0; - - if (m1->len != m2->len) - return 0; - - if ((m1->idx_notify_num + m1->val_notify_num) * sizeof(*req1) != - m1->len) - return 1; - - req1 = (struct cn_notify_req *)m1->data; - req2 = (struct cn_notify_req *)m2->data; - - for (i = 0; i < m1->idx_notify_num; ++i) { - if (req1->first != req2->first || req1->range != req2->range) - return 0; - req1++; - req2++; - } - - for (i = 0; i < m1->val_notify_num; ++i) { - if (req1->first != req2->first || req1->range != req2->range) - return 0; - req1++; - req2++; - } - - return 1; -} - -/* - * Main connector device's callback. - * - * Used for notification of a request's processing. - */ -static void cn_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp) -{ - struct cn_ctl_msg *ctl; - struct cn_ctl_entry *ent; - u32 size; - - if (msg->len < sizeof(*ctl)) - return; - - ctl = (struct cn_ctl_msg *)msg->data; - - size = (sizeof(*ctl) + ((ctl->idx_notify_num + - ctl->val_notify_num) * - sizeof(struct cn_notify_req))); - - if (msg->len != size) - return; - - if (ctl->len + sizeof(*ctl) != msg->len) - return; - - /* - * Remove notification. - */ - if (ctl->group == 0) { - struct cn_ctl_entry *n; - - mutex_lock(¬ify_lock); - list_for_each_entry_safe(ent, n, ¬ify_list, notify_entry) { - if (cn_ctl_msg_equals(ent->msg, ctl)) { - list_del(&ent->notify_entry); - kfree(ent); - } - } - mutex_unlock(¬ify_lock); - - return; - } - - size += sizeof(*ent); - - ent = kzalloc(size, GFP_KERNEL); - if (!ent) - return; - - ent->msg = (struct cn_ctl_msg *)(ent + 1); - - memcpy(ent->msg, ctl, size - sizeof(*ent)); - - mutex_lock(¬ify_lock); - list_add(&ent->notify_entry, ¬ify_list); - mutex_unlock(¬ify_lock); -} - static int cn_proc_show(struct seq_file *m, void *v) { struct cn_queue_dev *dev = cdev.cbdev; @@ -437,11 +274,8 @@ static const struct file_operations cn_file_ops = { static int __devinit cn_init(void) { struct cn_dev *dev = &cdev; - int err; dev->input = cn_rx_skb; - dev->id.idx = cn_idx; - dev->id.val = cn_val; dev->nls = netlink_kernel_create(&init_net, NETLINK_CONNECTOR, CN_NETLINK_USERS + 0xf, @@ -457,14 +291,6 @@ static int __devinit cn_init(void) cn_already_initialized = 1; - err = cn_add_callback(&dev->id, "connector", &cn_callback); - if (err) { - cn_already_initialized = 0; - cn_queue_free_dev(dev->cbdev); - netlink_kernel_release(dev->nls); - return -EINVAL; - } - proc_net_fops_create(&init_net, "connector", S_IRUGO, &cn_file_ops); return 0; @@ -478,7 +304,6 @@ static void __devexit cn_fini(void) proc_net_remove(&init_net, "connector"); - cn_del_callback(&dev->id); cn_queue_free_dev(dev->cbdev); netlink_kernel_release(dev->nls); } diff --git a/include/linux/connector.h b/include/linux/connector.h index 72ba63eb83c5..3a779ffba60b 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -24,9 +24,6 @@ #include -#define CN_IDX_CONNECTOR 0xffffffff -#define CN_VAL_CONNECTOR 0xffffffff - /* * Process Events connector unique ids -- used for message routing */ @@ -75,30 +72,6 @@ struct cn_msg { __u8 data[0]; }; -/* - * Notify structure - requests notification about - * registering/unregistering idx/val in range [first, first+range]. - */ -struct cn_notify_req { - __u32 first; - __u32 range; -}; - -/* - * Main notification control message - * *_notify_num - number of appropriate cn_notify_req structures after - * this struct. - * group - notification receiver's idx. - * len - total length of the attached data. - */ -struct cn_ctl_msg { - __u32 idx_notify_num; - __u32 val_notify_num; - __u32 group; - __u32 len; - __u8 data[0]; -}; - #ifdef __KERNEL__ #include @@ -151,11 +124,6 @@ struct cn_callback_entry { u32 seq, group; }; -struct cn_ctl_entry { - struct list_head notify_entry; - struct cn_ctl_msg *msg; -}; - struct cn_dev { struct cb_id id; -- cgit v1.2.3 From f7acede65d6b65919aee5b6a360a17cedb11f2f7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 Jan 2010 13:30:11 +0100 Subject: libata: fix ata_id_logical_per_physical_sectors The value we get from the low byte of the ATA_ID_SECTOR_SIZE word is not not a plain multiple, but the log of it, so fix the helper to give the correct answer. Without this we'll get an incorrect minimal I/O size in the block limits VPD page for 4k sector drives. Also change the return value of ata_id_logical_per_physical_sectors to u16 for the unlikely case of very large logical sectors. Signed-off-by: Christoph Hellwig Signed-off-by: Jeff Garzik --- include/linux/ata.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index 38a6948ce0c2..20f31567ccee 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -647,9 +647,9 @@ static inline int ata_id_has_large_logical_sectors(const u16 *id) return id[ATA_ID_SECTOR_SIZE] & (1 << 13); } -static inline u8 ata_id_logical_per_physical_sectors(const u16 *id) +static inline u16 ata_id_logical_per_physical_sectors(const u16 *id) { - return id[ATA_ID_SECTOR_SIZE] & 0xf; + return 1 << (id[ATA_ID_SECTOR_SIZE] & 0xf); } static inline int ata_id_has_lba48(const u16 *id) -- cgit v1.2.3 From 2938429501b73f6aeb312236eac7ed0416a07cd5 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Fri, 5 Feb 2010 16:09:11 +1100 Subject: percpu: add __percpu for sparse This is to make the annotation of percpu variables during the next merge window less painfull. Extracted from a patch by Rusty Russell. Signed-off-by: Stephen Rothwell Acked-by: Tejun Heo Signed-off-by: Linus Torvalds --- include/linux/compiler.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 5be3dab4a695..188fcae10a99 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -15,6 +15,7 @@ # define __acquire(x) __context__(x,1) # define __release(x) __context__(x,-1) # define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) +# define __percpu __attribute__((noderef, address_space(3))) extern void __chk_user_ptr(const volatile void __user *); extern void __chk_io_ptr(const volatile void __iomem *); #else @@ -32,6 +33,7 @@ extern void __chk_io_ptr(const volatile void __iomem *); # define __acquire(x) (void)0 # define __release(x) (void)0 # define __cond_lock(x,c) (c) +# define __percpu #endif #ifdef __KERNEL__ -- cgit v1.2.3