From 1a30871fe635d3e92972e6b93e39ff65bb57e52d Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 16 Jan 2012 11:07:16 +0200 Subject: mtd: fix MTD suspend Commits 3fe4bae88460869a8e553397cd9057a4ee7ca341 and 079c985e7a6f4ce60f931cebfdd5ee3c3 broke MTD suspend in 2 ways: 1. When the '->suspend' method is not present, we return -EOPNOTSUPP, but the callers of 'mtd_suspend()' expects 0 instead. 2. Checking of the 'mtd' parameter against NULL has been incorrectly removed in 'mtd_cls_suspend()'. This patch fixes the breakages. This has been found, analyzed, reported and tested by Rafael J. Wysocki . Note, this patch is not needed in the stable tree because it causes a regression introduced during the v3.3 merge window. Reported-by: Rafael J. Wysocki Tested-by: Rafael J. Wysocki Tested-by: Russell King Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/mtd.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 1a81fde8f333..d8c7aad7331c 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -427,9 +427,7 @@ static inline int mtd_is_locked(struct mtd_info *mtd, loff_t ofs, uint64_t len) static inline int mtd_suspend(struct mtd_info *mtd) { - if (!mtd->suspend) - return -EOPNOTSUPP; - return mtd->suspend(mtd); + return mtd->suspend ? mtd->suspend(mtd) : 0; } static inline void mtd_resume(struct mtd_info *mtd) -- cgit v1.2.3 From 3310225dfc71a35a2cc9340c15c0e08b14b3c754 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Mon, 9 Jan 2012 11:53:50 -0600 Subject: lib: proportion: lower PROP_MAX_SHIFT to 32 on 64-bit kernel PROP_MAX_SHIFT should be set to <=32 on 64-bit box. This fixes two bugs in the below lines of bdi_dirty_limit(): bdi_dirty *= numerator; do_div(bdi_dirty, denominator); 1) divide error: do_div() only uses the lower 32 bit of the denominator, which may trimmed to be 0 when PROP_MAX_SHIFT > 32. 2) overflow: (bdi_dirty * numerator) could easily overflow if numerator used up to 48 bits, leaving only 16 bits to bdi_dirty Cc: Cc: Peter Zijlstra Reported-by: Ilya Tumaykin Tested-by: Ilya Tumaykin Signed-off-by: Wu Fengguang --- include/linux/proportions.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/proportions.h b/include/linux/proportions.h index ef35bb73f69b..26a8a4ed9b07 100644 --- a/include/linux/proportions.h +++ b/include/linux/proportions.h @@ -81,7 +81,11 @@ void prop_inc_percpu(struct prop_descriptor *pd, struct prop_local_percpu *pl) * Limit the time part in order to ensure there are some bits left for the * cycle counter and fraction multiply. */ +#if BITS_PER_LONG == 32 #define PROP_MAX_SHIFT (3*BITS_PER_LONG/4) +#else +#define PROP_MAX_SHIFT (BITS_PER_LONG/2) +#endif #define PROP_FRAC_SHIFT (BITS_PER_LONG - PROP_MAX_SHIFT - 1) #define PROP_FRAC_BASE (1UL << PROP_FRAC_SHIFT) -- cgit v1.2.3 From e9c8d7a03e69093e4c33c5056a45c1233a42e8a4 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Wed, 18 Jan 2012 10:14:25 +0100 Subject: dma: sh_dma: not all SH DMAC implementations support MEMCPY Add a flag to allow platforms to specify, whether a DMAC instance supports the MEMCPY operation. To avoid regressions, preserve the current default. Signed-off-by: Guennadi Liakhovetski Acked-by: Paul Mundt Signed-off-by: Vinod Koul --- include/linux/sh_dma.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sh_dma.h b/include/linux/sh_dma.h index 8cd7fe59cf1a..425450b980b8 100644 --- a/include/linux/sh_dma.h +++ b/include/linux/sh_dma.h @@ -70,6 +70,7 @@ struct sh_dmae_pdata { unsigned int needs_tend_set:1; unsigned int no_dmars:1; unsigned int chclr_present:1; + unsigned int slave_only:1; }; /* DMA register */ -- cgit v1.2.3 From b18db3d91234c03ad080d317878c7c77672ba326 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Heiko=20St=C3=BCbner?= Date: Wed, 1 Feb 2012 09:12:24 -0800 Subject: Input: gpio_keys - fix struct device declared inside parameter list A struct device parameter is used in the enable and disable callbacks to distinguish between different gpio_keys devices. Platforms that don't use these callbacks may not include struct device at all, as seen on arch/arm/mach-s3c2410/mach-n30.c Signed-off-by: Heiko Stuebner Signed-off-by: Dmitry Torokhov --- include/linux/gpio_keys.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio_keys.h b/include/linux/gpio_keys.h index b5ca4b2c08ec..004ff33ab38e 100644 --- a/include/linux/gpio_keys.h +++ b/include/linux/gpio_keys.h @@ -1,6 +1,8 @@ #ifndef _GPIO_KEYS_H #define _GPIO_KEYS_H +struct device; + struct gpio_keys_button { /* Configuration parameters */ unsigned int code; /* input event code (KEY_*, SW_*) */ -- cgit v1.2.3 From 504b61630ab65296b6c9113cce834574e8cc01de Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 31 Jan 2012 16:43:50 -0800 Subject: usb: ch9.h: usb_endpoint_maxp() uses __le16_to_cpu() The usb/ch9.h will be installed to /usr/include/linux, and be used from user space. But le16_to_cpu() is only defined for kernel code. Without this patch, user space compile will be broken. Special thanks to Stefan Becker Reported-by: Stefan Becker Signed-off-by: Kuninori Morimoto Cc: stable Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/ch9.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/ch9.h b/include/linux/usb/ch9.h index 61b29057b054..3b6f628880f8 100644 --- a/include/linux/usb/ch9.h +++ b/include/linux/usb/ch9.h @@ -589,7 +589,7 @@ static inline int usb_endpoint_is_isoc_out( */ static inline int usb_endpoint_maxp(const struct usb_endpoint_descriptor *epd) { - return le16_to_cpu(epd->wMaxPacketSize); + return __le16_to_cpu(epd->wMaxPacketSize); } /*-------------------------------------------------------------------------*/ -- cgit v1.2.3 From c31c151b1c4a29da4dc92212aa8648fb4f8557b9 Mon Sep 17 00:00:00 2001 From: Haiyang Zhang Date: Thu, 2 Feb 2012 07:18:00 +0000 Subject: net/hyperv: Fix the page buffer when an RNDIS message goes beyond page boundary There is a possible data corruption if an RNDIS message goes beyond page boundary in the sending code path. This patch fixes the problem. Signed-off-by: Haiyang Zhang Signed-off-by: K. Y. Srinivasan Signed-off-by: David S. Miller --- include/linux/hyperv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 62b908e0e591..0ae065a5fcb2 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -35,7 +35,7 @@ #include -#define MAX_PAGE_BUFFER_COUNT 18 +#define MAX_PAGE_BUFFER_COUNT 19 #define MAX_MULTIPAGE_BUFFER_COUNT 32 /* 128K */ #pragma pack(push, 1) -- cgit v1.2.3 From f8447d6c213273b444c81eaa2449f55510229d4f Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Sat, 14 Jan 2012 20:58:43 +0100 Subject: mfd: Store twl6040-codec mclk configuration Store the last used mclk configuration for the PLL. Signed-off-by: Peter Ujfalusi Signed-off-by: Samuel Ortiz --- include/linux/mfd/twl6040.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/twl6040.h b/include/linux/mfd/twl6040.h index 2463c2619596..9bc9ac651dad 100644 --- a/include/linux/mfd/twl6040.h +++ b/include/linux/mfd/twl6040.h @@ -187,8 +187,10 @@ struct twl6040 { int rev; u8 vibra_ctrl_cache[2]; + /* PLL configuration */ int pll; unsigned int sysclk; + unsigned int mclk; unsigned int irq; unsigned int irq_base; -- cgit v1.2.3 From 331818f1c468a24e581aedcbe52af799366a9dfe Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 3 Feb 2012 18:30:53 -0500 Subject: NFSv4: Fix an Oops in the NFSv4 getacl code Commit bf118a342f10dafe44b14451a1392c3254629a1f (NFSv4: include bitmap in nfsv4 get acl data) introduces the 'acl_scratch' page for the case where we may need to decode multi-page data. However it fails to take into account the fact that the variable may be NULL (for the case where we're not doing multi-page decode), and it also attaches it to the encoding xdr_stream rather than the decoding one. The immediate result is an Oops in nfs4_xdr_enc_getacl due to the call to page_address() with a NULL page pointer. Signed-off-by: Trond Myklebust Cc: Andy Adamson Cc: stable@vger.kernel.org --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index a764cef06b73..d6ba9a12591e 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -614,7 +614,6 @@ struct nfs_getaclargs { size_t acl_len; unsigned int acl_pgbase; struct page ** acl_pages; - struct page * acl_scratch; struct nfs4_sequence_args seq_args; }; @@ -624,6 +623,7 @@ struct nfs_getaclres { size_t acl_len; size_t acl_data_offset; int acl_flags; + struct page * acl_scratch; struct nfs4_sequence_res seq_res; }; -- cgit v1.2.3 From d020283dc694c9ec31b410f522252f7a8397e67d Mon Sep 17 00:00:00 2001 From: Venkatesh Pallipadi Date: Fri, 3 Feb 2012 22:22:25 +0100 Subject: PM / QoS: CPU C-state breakage with PM Qos change Looks like change "PM QoS: Move and rename the implementation files" merged during the 3.2 development cycle made PM QoS depend on CONFIG_PM which depends on (PM_SLEEP || PM_RUNTIME). That breaks CPU C-states with kernels not having these CONFIGs, causing CPUs to spend time in Polling loop idle instead of going into deep C-states, consuming way way more power. This is with either acpi idle or intel idle enabled. Either CONFIG_PM should be enabled with any pm_qos users or the !CONFIG_PM pm_qos_request() should return sane defaults not to break the existing users. Here's is the patch for the latter option. [rjw: Modified the changelog slightly.] Signed-off-by: Venkatesh Pallipadi Signed-off-by: Rafael J. Wysocki Cc: stable@vger.kernel.org --- include/linux/pm_qos.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index e5bbcbaa6f57..4d99e4e6ef83 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -110,7 +110,19 @@ static inline void pm_qos_remove_request(struct pm_qos_request *req) { return; } static inline int pm_qos_request(int pm_qos_class) - { return 0; } +{ + switch (pm_qos_class) { + case PM_QOS_CPU_DMA_LATENCY: + return PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE; + case PM_QOS_NETWORK_LATENCY: + return PM_QOS_NETWORK_LAT_DEFAULT_VALUE; + case PM_QOS_NETWORK_THROUGHPUT: + return PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE; + default: + return PM_QOS_DEFAULT_VALUE; + } +} + static inline int pm_qos_add_notifier(int pm_qos_class, struct notifier_block *notifier) { return 0; } -- cgit v1.2.3 From 96e02d1586782eadf051fa3d6bc4132d2447ac2c Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Sat, 4 Feb 2012 10:47:10 +0100 Subject: exec: fix use-after-free bug in setup_new_exec() Setting the task name is done within setup_new_exec() by accessing bprm->filename. However this happens after flush_old_exec(). This may result in a use after free bug, flush_old_exec() may "complete" vfork_done, which will wake up the parent which in turn may free the passed in filename. To fix this add a new tcomm field in struct linux_binprm which contains the now early generated task name until it is used. Fixes this bug on s390: Unable to handle kernel pointer dereference at virtual kernel address 0000000039768000 Process kworker/u:3 (pid: 245, task: 000000003a3dc840, ksp: 0000000039453818) Krnl PSW : 0704000180000000 0000000000282e94 (setup_new_exec+0xa0/0x374) Call Trace: ([<0000000000282e2c>] setup_new_exec+0x38/0x374) [<00000000002dd12e>] load_elf_binary+0x402/0x1bf4 [<0000000000280a42>] search_binary_handler+0x38e/0x5bc [<0000000000282b6c>] do_execve_common+0x410/0x514 [<0000000000282cb6>] do_execve+0x46/0x58 [<00000000005bce58>] kernel_execve+0x28/0x70 [<000000000014ba2e>] ____call_usermodehelper+0x102/0x140 [<00000000005bc8da>] kernel_thread_starter+0x6/0xc [<00000000005bc8d4>] kernel_thread_starter+0x0/0xc Last Breaking-Event-Address: [<00000000002830f0>] setup_new_exec+0x2fc/0x374 Kernel panic - not syncing: Fatal exception: panic_on_oops Reported-by: Sebastian Ott Signed-off-by: Heiko Carstens Signed-off-by: Linus Torvalds --- include/linux/binfmts.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index fd88a3945aa1..0092102db2de 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -18,7 +18,7 @@ struct pt_regs; #define BINPRM_BUF_SIZE 128 #ifdef __KERNEL__ -#include +#include #define CORENAME_MAX_SIZE 128 @@ -58,6 +58,7 @@ struct linux_binprm { unsigned interp_flags; unsigned interp_data; unsigned long loader, exec; + char tcomm[TASK_COMM_LEN]; }; #define BINPRM_FLAGS_ENFORCE_NONDUMP_BIT 0 -- cgit v1.2.3 From 11a3122f6cf2d988a77eb8883d0fc49cd013a6d5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 7 Feb 2012 07:51:30 +0100 Subject: block: strip out locking optimization in put_io_context() put_io_context() performed a complex trylock dancing to avoid deferring ioc release to workqueue. It was also broken on UP because trylock was always assumed to succeed which resulted in unbalanced preemption count. While there are ways to fix the UP breakage, even the most pathological microbench (forced ioc allocation and tight fork/exit loop) fails to show any appreciable performance benefit of the optimization. Strip it out. If there turns out to be workloads which are affected by this change, simpler optimization from the discussion thread can be applied later. Signed-off-by: Tejun Heo LKML-Reference: <1328514611.21268.66.camel@sli10-conroe> Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 --- include/linux/iocontext.h | 5 ++--- 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6c6a1f008065..606cf339bb56 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -399,9 +399,6 @@ struct request_queue { /* Throttle data */ struct throtl_data *td; #endif -#ifdef CONFIG_LOCKDEP - int ioc_release_depth; -#endif }; #define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */ diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h index 7e1371c4bccf..119773eebe31 100644 --- a/include/linux/iocontext.h +++ b/include/linux/iocontext.h @@ -133,7 +133,7 @@ static inline struct io_context *ioc_task_link(struct io_context *ioc) struct task_struct; #ifdef CONFIG_BLOCK -void put_io_context(struct io_context *ioc, struct request_queue *locked_q); +void put_io_context(struct io_context *ioc); void exit_io_context(struct task_struct *task); struct io_context *get_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node); @@ -141,8 +141,7 @@ void ioc_ioprio_changed(struct io_context *ioc, int ioprio); void ioc_cgroup_changed(struct io_context *ioc); #else struct io_context; -static inline void put_io_context(struct io_context *ioc, - struct request_queue *locked_q) { } +static inline void put_io_context(struct io_context *ioc) { } static inline void exit_io_context(struct task_struct *task) { } #endif -- cgit v1.2.3 From 050c8ea80e3e90019d9e981c6a117ef614e882ed Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 8 Feb 2012 09:19:38 +0100 Subject: block: separate out blk_rq_merge_ok() and blk_try_merge() from elevator functions blk_rq_merge_ok() is the elevator-neutral part of merge eligibility test. blk_try_merge() determines merge direction and expects the caller to have tested elv_rq_merge_ok() previously. elv_rq_merge_ok() now wraps blk_rq_merge_ok() and then calls elv_iosched_allow_merge(). elv_try_merge() is removed and the two callers are updated to call elv_rq_merge_ok() explicitly followed by blk_try_merge(). While at it, make rq_merge_ok() functions return bool. This is to prepare for plug merge update and doesn't introduce any behavior change. This is based on Jens' patch to skip elevator_allow_merge_fn() from plug merge. Signed-off-by: Tejun Heo LKML-Reference: <4F16F3CA.90904@kernel.dk> Original-patch-by: Jens Axboe Signed-off-by: Jens Axboe --- include/linux/elevator.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index c24f3d7fbf1e..d6dfb65c8885 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -122,7 +122,6 @@ extern void elv_dispatch_add_tail(struct request_queue *, struct request *); extern void elv_add_request(struct request_queue *, struct request *, int); extern void __elv_add_request(struct request_queue *, struct request *, int); extern int elv_merge(struct request_queue *, struct request **, struct bio *); -extern int elv_try_merge(struct request *, struct bio *); extern void elv_merge_requests(struct request_queue *, struct request *, struct request *); extern void elv_merged_request(struct request_queue *, struct request *, int); @@ -155,7 +154,7 @@ extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t); extern int elevator_init(struct request_queue *, char *); extern void elevator_exit(struct elevator_queue *); extern int elevator_change(struct request_queue *, const char *); -extern int elv_rq_merge_ok(struct request *, struct bio *); +extern bool elv_rq_merge_ok(struct request *, struct bio *); /* * Helper functions. -- cgit v1.2.3 From 07c2bd37350c9b1af71b35d05f16e300a6602948 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 8 Feb 2012 09:19:42 +0100 Subject: block: don't call elevator callbacks for plug merges Plug merge calls two elevator callbacks outside queue lock - elevator_allow_merge_fn() and elevator_bio_merged_fn(). Although attempt_plug_merge() suggests that elevator is guaranteed to be there through the existing request on the plug list, nothing prevents plug merge from calling into dying or initializing elevator. For regular merges, bypass ensures elvpriv count to reach zero, which in turn prevents merges as all !ELVPRIV requests get REQ_SOFTBARRIER from forced back insertion. Plug merge doesn't check ELVPRIV, and, as the requests haven't gone through elevator insertion yet, it doesn't have SOFTBARRIER set allowing merges on a bypassed queue. This, for example, leads to the following crash during elevator switch. BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 IP: [] cfq_allow_merge+0x49/0xa0 PGD 112cbc067 PUD 115d5c067 PMD 0 Oops: 0000 [#1] PREEMPT SMP CPU 1 Modules linked in: deadline_iosched Pid: 819, comm: dd Not tainted 3.3.0-rc2-work+ #76 Bochs Bochs RIP: 0010:[] [] cfq_allow_merge+0x49/0xa0 RSP: 0018:ffff8801143a38f8 EFLAGS: 00010297 RAX: 0000000000000000 RBX: ffff88011817ce28 RCX: ffff880116eb6cc0 RDX: 0000000000000000 RSI: ffff880118056e20 RDI: ffff8801199512f8 RBP: ffff8801143a3908 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: ffff880118195708 R13: ffff880118052aa0 R14: ffff8801143a3d50 R15: ffff880118195708 FS: 00007f19f82cb700(0000) GS:ffff88011fc80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000008 CR3: 0000000112c6a000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process dd (pid: 819, threadinfo ffff8801143a2000, task ffff880116eb6cc0) Stack: ffff88011817ce28 ffff880118195708 ffff8801143a3928 ffffffff81391bba ffff88011817ce28 ffff880118195708 ffff8801143a3948 ffffffff81391bf1 ffff88011817ce28 0000000000000000 ffff8801143a39a8 ffffffff81398e3e Call Trace: [] elv_rq_merge_ok+0x4a/0x60 [] elv_try_merge+0x21/0x40 [] blk_queue_bio+0x8e/0x390 [] generic_make_request+0xca/0x100 [] submit_bio+0x74/0x100 [] __blockdev_direct_IO+0x1ce2/0x3450 [] blkdev_direct_IO+0x57/0x60 [] generic_file_aio_read+0x6d5/0x760 [] do_sync_read+0xe2/0x120 [] vfs_read+0xc5/0x180 [] sys_read+0x51/0x90 [] system_call_fastpath+0x16/0x1b There are multiple ways to fix this including making plug merge check ELVPRIV; however, * Calling into elevator outside queue lock is confusing and error-prone. * Requests on plug list aren't known to the elevator. They aren't on the elevator yet, so there's no elevator specific state to update. * Given the nature of plug merges - collecting bio's for the same purpose from the same issuer - elevator specific restrictions aren't applicable. So, simply don't call into elevator methods from plug merge by moving elv_bio_merged() from bio_attempt_*_merge() to blk_queue_bio(), and using blk_try_merge() in attempt_plug_merge(). This is based on Jens' patch to skip elevator_allow_merge_fn() from plug merge. Note that this makes per-cgroup merged stats skip plug merging. Signed-off-by: Tejun Heo LKML-Reference: <4F16F3CA.90904@kernel.dk> Original-patch-by: Jens Axboe Signed-off-by: Jens Axboe --- include/linux/elevator.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index d6dfb65c8885..7d4e0356f329 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -42,12 +42,6 @@ struct elevator_ops elevator_merged_fn *elevator_merged_fn; elevator_merge_req_fn *elevator_merge_req_fn; elevator_allow_merge_fn *elevator_allow_merge_fn; - - /* - * Used for both plugged list and elevator merging and in the - * former case called without queue_lock. Read comment on top of - * attempt_plug_merge() for details. - */ elevator_bio_merged_fn *elevator_bio_merged_fn; elevator_dispatch_fn *elevator_dispatch_fn; -- cgit v1.2.3 From cdccaa9467b982d57b139818d15e1e994feca372 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 8 Feb 2012 20:03:14 +0100 Subject: cdrom: move shared static to cdrom_device_info The keeplocked variable in the cdrom driver is shared across multiple drives, but set in per-device ioctls. Move it to the per-device struct, avoiding that the setting on one drive affects the driver's behavior when closing another. [ Impact: limit udev's confusion to one drive when a CD burning program unlocks the CD door at the end of burning. ] Signed-off-by: Paolo Bonzini Signed-off-by: Jens Axboe --- include/linux/cdrom.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 35eae4b67503..7c48029dffe6 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -952,7 +952,8 @@ struct cdrom_device_info { char name[20]; /* name of the device type */ /* per-device flags */ __u8 sanyo_slot : 2; /* Sanyo 3 CD changer support */ - __u8 reserved : 6; /* not used yet */ + __u8 keeplocked : 1; /* CDROM_LOCKDOOR status */ + __u8 reserved : 5; /* not used yet */ int cdda_method; /* see flags */ __u8 last_sense; __u8 media_written; /* dirty flag, DVD+RW bookkeeping */ -- cgit v1.2.3 From d9f5343e35d9138432657202afa8e3ddb2ade360 Mon Sep 17 00:00:00 2001 From: Sarah Sharp Date: Thu, 5 Jan 2012 16:28:54 -0800 Subject: USB: Remove duplicate USB 3.0 hub feature #defines. Somehow we ended up with duplicate hub feature #defines in ch11.h. Tatyana Brokhman first created the USB 3.0 hub feature macros in 2.6.38 with commit 0eadcc09203349b11ca477ec367079b23d32ab91 "usb: USB3.0 ch11 definitions". In 2.6.39, I modified a patch from John Youn that added similar macros in a different place in the same file, and committed dbe79bbe9dcb22cb3651c46f18943477141ca452 "USB 3.0 Hub Changes". Some of the #defines used different names for the same values. Others used exactly the same names with the same values, like these gems: #define USB_PORT_FEAT_BH_PORT_RESET 28 ... #define USB_PORT_FEAT_BH_PORT_RESET 28 According to my very geeky husband (who looked it up in the C99 spec), it is allowed to have object-like macros with duplicate names as long as the replacement list is exactly the same. However, he recalled that some compilers will give warnings when they find duplicate macros. It's probably best to remove the duplicates in the stable tree, so that the code compiles for everyone. The macros are now fixed to move the feature requests that are specific to USB 3.0 hubs into a new section (out of the USB 2.0 hub feature section), and use the most common macro name. This patch should be backported to 2.6.39. Signed-off-by: Sarah Sharp Cc: Tatyana Brokhman Cc: John Youn Cc: Jamey Sharp Cc: stable@vger.kernel.org --- include/linux/usb/ch11.h | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/ch11.h b/include/linux/usb/ch11.h index 31fdb4c6ee3d..0b83acd3360a 100644 --- a/include/linux/usb/ch11.h +++ b/include/linux/usb/ch11.h @@ -61,12 +61,6 @@ #define USB_PORT_FEAT_TEST 21 #define USB_PORT_FEAT_INDICATOR 22 #define USB_PORT_FEAT_C_PORT_L1 23 -#define USB_PORT_FEAT_C_PORT_LINK_STATE 25 -#define USB_PORT_FEAT_C_PORT_CONFIG_ERROR 26 -#define USB_PORT_FEAT_PORT_REMOTE_WAKE_MASK 27 -#define USB_PORT_FEAT_BH_PORT_RESET 28 -#define USB_PORT_FEAT_C_BH_PORT_RESET 29 -#define USB_PORT_FEAT_FORCE_LINKPM_ACCEPT 30 /* * Port feature selectors added by USB 3.0 spec. @@ -75,8 +69,8 @@ #define USB_PORT_FEAT_LINK_STATE 5 #define USB_PORT_FEAT_U1_TIMEOUT 23 #define USB_PORT_FEAT_U2_TIMEOUT 24 -#define USB_PORT_FEAT_C_LINK_STATE 25 -#define USB_PORT_FEAT_C_CONFIG_ERR 26 +#define USB_PORT_FEAT_C_PORT_LINK_STATE 25 +#define USB_PORT_FEAT_C_PORT_CONFIG_ERROR 26 #define USB_PORT_FEAT_REMOTE_WAKE_MASK 27 #define USB_PORT_FEAT_BH_PORT_RESET 28 #define USB_PORT_FEAT_C_BH_PORT_RESET 29 -- cgit v1.2.3 From 2c4967f741e87cdd63de7271b97807041dccbf3b Mon Sep 17 00:00:00 2001 From: Sujit Reddy Thumma Date: Sat, 4 Feb 2012 16:14:50 -0500 Subject: mmc: core: Ensure clocks are always enabled before host interaction Ensure clocks are always enabled before any interaction with the host controller driver. This makes sure that there is no race between host execution and the core layer turning off clocks in different context with clock gating framework. Signed-off-by: Sujit Reddy Thumma Acked-by: Linus Walleij Acked-by: Per Forlin Signed-off-by: Chris Ball --- include/linux/mmc/host.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 0beba1e5e1ed..73e5ee8e9ca2 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -444,4 +444,23 @@ static inline int mmc_boot_partition_access(struct mmc_host *host) return !(host->caps2 & MMC_CAP2_BOOTPART_NOACC); } +#ifdef CONFIG_MMC_CLKGATE +void mmc_host_clk_hold(struct mmc_host *host); +void mmc_host_clk_release(struct mmc_host *host); +unsigned int mmc_host_clk_rate(struct mmc_host *host); + +#else +static inline void mmc_host_clk_hold(struct mmc_host *host) +{ +} + +static inline void mmc_host_clk_release(struct mmc_host *host) +{ +} + +static inline unsigned int mmc_host_clk_rate(struct mmc_host *host) +{ + return host->ios.clock; +} +#endif #endif /* LINUX_MMC_HOST_H */ -- cgit v1.2.3 From 6e8201f57c9359c9c5dc8f9805c15a4392492a10 Mon Sep 17 00:00:00 2001 From: Jaehoon Chung Date: Mon, 16 Jan 2012 17:49:01 +0900 Subject: mmc: core: add the capability for broken voltage There is an understood mismatch between the voltage the host controller is set to and the voltage supplied to the card by a fixed voltage regulator. Teaching the driver to accept the mismatch is overly complicated. Instead just accept the regulator's voltage. This patch adds MMC_CAP2_BROKEN_VOLTAGE. If the voltage didn't satisfy between min_uV and max_uV, try to change the voltage in core.c. When changing the voltage, maybe use regulator_set_voltage(). In regulator_set_voltage(), check the below condition. /* sanity check */ if (!rdev->desc->ops->set_voltage && !rdev->desc->ops->set_voltage_sel) { ret = -EINVAL; goto out; } If some board should use the fixed-regulator, always return -EINVAL. Then, eMMC didn't initialize always. So if use a fixed-regulator, we need to add the MMC_CAP2_BROKEN_VOLTAGE. Signed-off-by: Jaehoon Chung Signed-off-by: Kyungmin Park Acked-by: Adrian Hunter Signed-off-by: Chris Ball --- include/linux/mmc/host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 73e5ee8e9ca2..ee2b0363c040 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -257,6 +257,7 @@ struct mmc_host { #define MMC_CAP2_HS200_1_2V_SDR (1 << 6) /* can support */ #define MMC_CAP2_HS200 (MMC_CAP2_HS200_1_8V_SDR | \ MMC_CAP2_HS200_1_2V_SDR) +#define MMC_CAP2_BROKEN_VOLTAGE (1 << 7) /* Use the broken voltage */ mmc_pm_flag_t pm_caps; /* supported pm features */ unsigned int power_notify_type; -- cgit v1.2.3 From 3e73c36b4dc224529d0b0c0d5d69c0dacd793c42 Mon Sep 17 00:00:00 2001 From: Girish K S Date: Tue, 31 Jan 2012 15:44:03 +0530 Subject: mmc: core: Fix PowerOff Notify suspend/resume Modified the mmc_poweroff to resume before sending the poweroff notification command. In sleep mode only AWAKE and RESET commands are allowed, so before sending the poweroff notification command resume from sleep mode and then send the notification command. PowerOff Notify is tested on a Synopsis Designware Host Controller (eMMC 4.5). The suspend to RAM and resume works fine. Signed-off-by: Girish K S Tested-by: Girish K S Reviewed-by: Saugata Das Signed-off-by: Chris Ball --- include/linux/mmc/card.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 9f22ba572de0..19a41d1737af 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -217,6 +217,7 @@ struct mmc_card { #define MMC_CARD_SDXC (1<<6) /* card is SDXC */ #define MMC_CARD_REMOVED (1<<7) /* card has been removed */ #define MMC_STATE_HIGHSPEED_200 (1<<8) /* card is in HS200 mode */ +#define MMC_STATE_SLEEP (1<<9) /* card is in sleep state */ unsigned int quirks; /* card quirks */ #define MMC_QUIRK_LENIENT_FN0 (1<<0) /* allow SDIO FN0 writes outside of the VS CCCR range */ #define MMC_QUIRK_BLKSZ_FOR_BYTE_MODE (1<<1) /* use func->cur_blksize */ @@ -382,6 +383,7 @@ static inline void __maybe_unused remove_quirk(struct mmc_card *card, int data) #define mmc_sd_card_uhs(c) ((c)->state & MMC_STATE_ULTRAHIGHSPEED) #define mmc_card_ext_capacity(c) ((c)->state & MMC_CARD_SDXC) #define mmc_card_removed(c) ((c) && ((c)->state & MMC_CARD_REMOVED)) +#define mmc_card_is_sleep(c) ((c)->state & MMC_STATE_SLEEP) #define mmc_card_set_present(c) ((c)->state |= MMC_STATE_PRESENT) #define mmc_card_set_readonly(c) ((c)->state |= MMC_STATE_READONLY) @@ -393,7 +395,9 @@ static inline void __maybe_unused remove_quirk(struct mmc_card *card, int data) #define mmc_sd_card_set_uhs(c) ((c)->state |= MMC_STATE_ULTRAHIGHSPEED) #define mmc_card_set_ext_capacity(c) ((c)->state |= MMC_CARD_SDXC) #define mmc_card_set_removed(c) ((c)->state |= MMC_CARD_REMOVED) +#define mmc_card_set_sleep(c) ((c)->state |= MMC_STATE_SLEEP) +#define mmc_card_clr_sleep(c) ((c)->state &= ~MMC_STATE_SLEEP) /* * Quirk add/remove for MMC products. */ -- cgit v1.2.3 From f9c2a0dc42a6938ff2a80e55ca2bbd1d5581c72e Mon Sep 17 00:00:00 2001 From: Seungwon Jeon Date: Thu, 9 Feb 2012 14:32:43 +0900 Subject: mmc: dw_mmc: Fix PIO mode with support of highmem Current PIO mode makes a kernel crash with CONFIG_HIGHMEM. Highmem pages have a NULL from sg_virt(sg). This patch fixes the following problem. Unable to handle kernel NULL pointer dereference at virtual address 00000000 pgd = c0004000 [00000000] *pgd=00000000 Internal error: Oops: 817 [#1] PREEMPT SMP Modules linked in: CPU: 0 Not tainted (3.0.15-01423-gdbf465f #589) PC is at dw_mci_pull_data32+0x4c/0x9c LR is at dw_mci_read_data_pio+0x54/0x1f0 pc : [] lr : [] psr: 20000193 sp : c0619d48 ip : c0619d70 fp : c0619d6c r10: 00000000 r9 : 00000002 r8 : 00001000 r7 : 00000200 r6 : 00000000 r5 : e1dd3100 r4 : 00000000 r3 : 65622023 r2 : 0000007f r1 : eeb96000 r0 : e1dd3100 Flags: nzCv IRQs off FIQs on Mode SVC_32 ISA ARM Segment xkernel Control: 10c5387d Table: 61e2004a DAC: 00000015 Process swapper (pid: 0, stack limit = 0xc06182f0) Stack: (0xc0619d48 to 0xc061a000) 9d40: e1dd3100 e1a4f000 00000000 e1dd3100 e1a4f000 00000200 9d60: c0619da4 c0619d70 c035988c c03587e4 c0619d9c e18158f4 e1dd3100 e1dd3100 9d80: 00000020 00000000 00000000 00000020 c06e8a84 00000000 c0619e04 c0619da8 9da0: c0359b24 c0359844 e18158f4 e1dd3164 e1dd3168 e1dd3150 3d02fc79 e1dd3154 9dc0: e1dd3178 00000000 00000020 00000000 e1dd3150 00000000 c10dd7e8 e1a84900 9de0: c061e7cc 00000000 00000000 0000008d c06e8a84 c061e780 c0619e4c c0619e08 9e00: c00c4738 c0359a34 3d02fc79 00000000 c0619e4c c05a1698 c05a1670 c05a165c 9e20: c04de8b0 c061e780 c061e7cc e1a84900 ffffed68 0000008d c0618000 00000000 9e40: c0619e6c c0619e50 c00c48b4 c00c46c8 c061e780 c00423ac c061e7cc ffffed68 9e60: c0619e8c c0619e70 c00c7358 c00c487c 0000008d ffffee38 c0618000 ffffed68 9e80: c0619ea4 c0619e90 c00c4258 c00c72b0 c00423ac ffffee38 c0619ecc c0619ea8 9ea0: c004241c c00c4234 ffffffff f8810000 0000006d 00000002 00000001 7fffffff 9ec0: c0619f44 c0619ed0 c0048bc0 c00423c4 220ae7a9 00000000 386f0d30 0005d3a4 9ee0: c00423ac c10dd0b8 c06f2cd8 c0618000 c0594778 c003a674 7fffffff c0619f44 9f00: 386f0d30 c0619f18 c00a6f94 c005be3c 80000013 ffffffff 386f0d30 0005d3a4 9f20: 386f0d30 0005d2d1 c10dd0a8 c10dd0b8 c06f2cd8 c0618000 c0619f74 c0619f48 9f40: c0345858 c005be00 c00a2440 c0618000 c0618000 c00410d8 c06c1944 c00410fc 9f60: c0594778 c003a674 c0619f9c c0619f78 c004a7e8 c03457b4 c0618000 c06c18f8 9f80: 00000000 c0039c70 c06c18d4 c003a674 c0619fb4 c0619fa0 c04ceafc c004a714 9fa0: c06287b4 c06c18f8 c0619ff4 c0619fb8 c0008b68 c04cea68 c0008578 00000000 9fc0: 00000000 c003a674 00000000 10c5387d c0628658 c003aa78 c062f1c4 4000406a 9fe0: 413fc090 00000000 00000000 c0619ff8 40008044 c0008858 00000000 00000000 Backtrace: [] (dw_mci_pull_data32+0x0/0x9c) from [] (dw_mci_read_data_pio+0x54/0x1f0) r6:00000200 r5:e1a4f000 r4:e1dd3100 [] (dw_mci_read_data_pio+0x0/0x1f0) from [] (dw_mci_interrupt+0xfc/0x4a4) [] (dw_mci_interrupt+0x0/0x4a4) from [] (handle_irq_event_percpu+0x7c/0x1b4) [] (handle_irq_event_percpu+0x0/0x1b4) from [] (handle_irq_event+0x44/0x64) [] (handle_irq_event+0x0/0x64) from [] (handle_fasteoi_irq+0xb4/0x124) r7:ffffed68 r6:c061e7cc r5:c00423ac r4:c061e780 [] (handle_fasteoi_irq+0x0/0x124) from [] (generic_handle_irq+0x30/0x38) r7:ffffed68 r6:c0618000 r5:ffffee38 r4:0000008d [] (generic_handle_irq+0x0/0x38) from [] (asm_do_IRQ+0x64/0xe0) r5:ffffee38 r4:c00423ac [] (asm_do_IRQ+0x0/0xe0) from [] (__irq_svc+0x80/0x14c) Exception stack(0xc0619ed0 to 0xc0619f18) Signed-off-by: Seungwon Jeon Acked-by: Will Newton Cc: stable Signed-off-by: Chris Ball --- include/linux/mmc/dw_mmc.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h index e8779c6d1759..aae5d1f1bb39 100644 --- a/include/linux/mmc/dw_mmc.h +++ b/include/linux/mmc/dw_mmc.h @@ -14,6 +14,8 @@ #ifndef LINUX_MMC_DW_MMC_H #define LINUX_MMC_DW_MMC_H +#include + #define MAX_MCI_SLOTS 2 enum dw_mci_state { @@ -40,7 +42,7 @@ struct mmc_data; * @lock: Spinlock protecting the queue and associated data. * @regs: Pointer to MMIO registers. * @sg: Scatterlist entry currently being processed by PIO code, if any. - * @pio_offset: Offset into the current scatterlist entry. + * @sg_miter: PIO mapping scatterlist iterator. * @cur_slot: The slot which is currently using the controller. * @mrq: The request currently being processed on @cur_slot, * or NULL if the controller is idle. @@ -115,7 +117,7 @@ struct dw_mci { void __iomem *regs; struct scatterlist *sg; - unsigned int pio_offset; + struct sg_mapping_iter sg_miter; struct dw_mci_slot *cur_slot; struct mmc_request *mrq; -- cgit v1.2.3 From 6b6dc836a195e077e76977b6c020a73de411b46d Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 10 Feb 2012 11:03:00 +0100 Subject: vfs: Provide function to get superblock and wait for it to thaw In quota code we need to find a superblock corresponding to a device and wait for superblock to be unfrozen. However this waiting has to happen without s_umount semaphore because that is required for superblock to thaw. So provide a function in VFS for this to keep dances with s_umount where they belong. [AV: implementation switched to saner variant] Signed-off-by: Jan Kara Signed-off-by: Al Viro --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 386da09f229d..69cd5bb640f5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2496,6 +2496,7 @@ extern void get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern struct super_block *get_super(struct block_device *); +extern struct super_block *get_super_thawed(struct block_device *); extern struct super_block *get_active_super(struct block_device *bdev); extern void drop_super(struct super_block *sb); extern void iterate_supers(void (*)(struct super_block *, void *), void *); -- cgit v1.2.3 From 8b3d1cda4f5ff0d7c2ae910ea8fd03493996912f Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Tue, 7 Feb 2012 21:09:05 -0800 Subject: posix_types: Remove fd_set macros includes a set of macros that operate on file descriptors. Way long ago those were exported to user space, but nowadays they are #ifdef __KERNEL__. However, they are nothing but standard (nonatomic) bit operations, and we already have optimized versions of bit operations in the kernel. We can't include in but we can move the definitions to and define them there in terms of standard kernel bitops. [ v2: folds the following fixes in: a) Stray space in __FD_SET(), reported by Andrew Morton b) #include needed for memset(), reported by Tony Luck ] Signed-off-by: H. Peter Anvin Link: http://lkml.kernel.org/r/1328677745-20121-22-git-send-email-hpa@zytor.com Cc: Arnd Bergmann Cc: Tony Luck Cc: Andrew Morton --- include/linux/time.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index b3061782dec3..93277a0b2293 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -4,8 +4,11 @@ #include #ifdef __KERNEL__ +# include # include +# include # include +# include # include #endif @@ -256,6 +259,27 @@ static __always_inline void timespec_add_ns(struct timespec *a, u64 ns) a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns); a->tv_nsec = ns; } + +static inline void __FD_SET(unsigned long __fd, __kernel_fd_set *__fdsetp) +{ + __set_bit(__fd, __fdsetp->fds_bits); +} + +static inline void __FD_CLR(unsigned long __fd, __kernel_fd_set *__fdsetp) +{ + __clear_bit(__fd, __fdsetp->fds_bits); +} + +static inline int __FD_ISSET(unsigned long __fd, const __kernel_fd_set *__fdsetp) +{ + return test_bit(__fd, __fdsetp->fds_bits); +} + +static inline void __FD_ZERO(__kernel_fd_set *__fdsetp) +{ + memset(__fdsetp->fds_bits, 0, sizeof __fdsetp->fds_bits); +} + #endif /* __KERNEL__ */ #define NFDBITS __NFDBITS -- cgit v1.2.3 From f2ea0f5f04c97b48c88edccba52b0682fbe45087 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Sat, 14 Jan 2012 21:44:49 +0300 Subject: crypto: sha512 - use standard ror64() Use standard ror64() instead of hand-written. There is no standard ror64, so create it. The difference is shift value being "unsigned int" instead of uint64_t (for which there is no reason). gcc starts to emit native ROR instructions which it doesn't do for some reason currently. This should make the code faster. Patch survives in-tree crypto test and ping flood with hmac(sha512) on. Signed-off-by: Alexey Dobriyan Signed-off-by: Herbert Xu --- include/linux/bitops.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index a3ef66a2a083..fc8a3ffce320 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -49,6 +49,26 @@ static inline unsigned long hweight_long(unsigned long w) return sizeof(w) == 4 ? hweight32(w) : hweight64(w); } +/** + * rol64 - rotate a 64-bit value left + * @word: value to rotate + * @shift: bits to roll + */ +static inline __u64 rol64(__u64 word, unsigned int shift) +{ + return (word << shift) | (word >> (64 - shift)); +} + +/** + * ror64 - rotate a 64-bit value right + * @word: value to rotate + * @shift: bits to roll + */ +static inline __u64 ror64(__u64 word, unsigned int shift) +{ + return (word >> shift) | (word << (64 - shift)); +} + /** * rol32 - rotate a 32-bit value left * @word: value to rotate -- cgit v1.2.3 From 1dce27c5aa6770e9d195f2bb7db1db3d4dde5591 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 16 Feb 2012 17:49:42 +0000 Subject: Wrap accesses to the fd_sets in struct fdtable Wrap accesses to the fd_sets in struct fdtable (for recording open files and close-on-exec flags) so that we can move away from using fd_sets since we abuse the fd_set structs by not allocating the full-sized structure under normal circumstances and by non-core code looking at the internals of the fd_sets. The first abuse means that use of FD_ZERO() on these fd_sets is not permitted, since that cannot be told about their abnormal lengths. This introduces six wrapper functions for setting, clearing and testing close-on-exec flags and fd-is-open flags: void __set_close_on_exec(int fd, struct fdtable *fdt); void __clear_close_on_exec(int fd, struct fdtable *fdt); bool close_on_exec(int fd, const struct fdtable *fdt); void __set_open_fd(int fd, struct fdtable *fdt); void __clear_open_fd(int fd, struct fdtable *fdt); bool fd_is_open(int fd, const struct fdtable *fdt); Note that I've prepended '__' to the names of the set/clear functions because they require the caller to hold a lock to use them. Note also that I haven't added wrappers for looking behind the scenes at the the array. Possibly that should exist too. Signed-off-by: David Howells Link: http://lkml.kernel.org/r/20120216174942.23314.1364.stgit@warthog.procyon.org.uk Signed-off-by: H. Peter Anvin Cc: Al Viro --- include/linux/fdtable.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index 82163c4b32c9..7675da2c18f7 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -38,6 +38,36 @@ struct fdtable { struct fdtable *next; }; +static inline void __set_close_on_exec(int fd, struct fdtable *fdt) +{ + FD_SET(fd, fdt->close_on_exec); +} + +static inline void __clear_close_on_exec(int fd, struct fdtable *fdt) +{ + FD_CLR(fd, fdt->close_on_exec); +} + +static inline bool close_on_exec(int fd, const struct fdtable *fdt) +{ + return FD_ISSET(fd, fdt->close_on_exec); +} + +static inline void __set_open_fd(int fd, struct fdtable *fdt) +{ + FD_SET(fd, fdt->open_fds); +} + +static inline void __clear_open_fd(int fd, struct fdtable *fdt) +{ + FD_CLR(fd, fdt->open_fds); +} + +static inline bool fd_is_open(int fd, const struct fdtable *fdt) +{ + return FD_ISSET(fd, fdt->open_fds); +} + /* * Open file table structure */ -- cgit v1.2.3 From 1fd36adcd98c14d2fd97f545293c488775cb2823 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 16 Feb 2012 17:49:54 +0000 Subject: Replace the fd_sets in struct fdtable with an array of unsigned longs Replace the fd_sets in struct fdtable with an array of unsigned longs and then use the standard non-atomic bit operations rather than the FD_* macros. This: (1) Removes the abuses of struct fd_set: (a) Since we don't want to allocate a full fd_set the vast majority of the time, we actually, in effect, just allocate a just-big-enough array of unsigned longs and cast it to an fd_set type - so why bother with the fd_set at all? (b) Some places outside of the core fdtable handling code (such as SELinux) want to look inside the array of unsigned longs hidden inside the fd_set struct for more efficient iteration over the entire set. (2) Eliminates the use of FD_*() macros in the kernel completely. (3) Permits the __FD_*() macros to be deleted entirely where not exposed to userspace. Signed-off-by: David Howells Link: http://lkml.kernel.org/r/20120216174954.23314.48147.stgit@warthog.procyon.org.uk Signed-off-by: H. Peter Anvin Cc: Al Viro --- include/linux/fdtable.h | 28 ++++++++++------------------ 1 file changed, 10 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index 7675da2c18f7..158a41eed314 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -21,51 +21,43 @@ */ #define NR_OPEN_DEFAULT BITS_PER_LONG -/* - * The embedded_fd_set is a small fd_set, - * suitable for most tasks (which open <= BITS_PER_LONG files) - */ -struct embedded_fd_set { - unsigned long fds_bits[1]; -}; - struct fdtable { unsigned int max_fds; struct file __rcu **fd; /* current fd array */ - fd_set *close_on_exec; - fd_set *open_fds; + unsigned long *close_on_exec; + unsigned long *open_fds; struct rcu_head rcu; struct fdtable *next; }; static inline void __set_close_on_exec(int fd, struct fdtable *fdt) { - FD_SET(fd, fdt->close_on_exec); + __set_bit(fd, fdt->close_on_exec); } static inline void __clear_close_on_exec(int fd, struct fdtable *fdt) { - FD_CLR(fd, fdt->close_on_exec); + __clear_bit(fd, fdt->close_on_exec); } static inline bool close_on_exec(int fd, const struct fdtable *fdt) { - return FD_ISSET(fd, fdt->close_on_exec); + return test_bit(fd, fdt->close_on_exec); } static inline void __set_open_fd(int fd, struct fdtable *fdt) { - FD_SET(fd, fdt->open_fds); + __set_bit(fd, fdt->open_fds); } static inline void __clear_open_fd(int fd, struct fdtable *fdt) { - FD_CLR(fd, fdt->open_fds); + __clear_bit(fd, fdt->open_fds); } static inline bool fd_is_open(int fd, const struct fdtable *fdt) { - return FD_ISSET(fd, fdt->open_fds); + return test_bit(fd, fdt->open_fds); } /* @@ -83,8 +75,8 @@ struct files_struct { */ spinlock_t file_lock ____cacheline_aligned_in_smp; int next_fd; - struct embedded_fd_set close_on_exec_init; - struct embedded_fd_set open_fds_init; + unsigned long close_on_exec_init[1]; + unsigned long open_fds_init[1]; struct file __rcu * fd_array[NR_OPEN_DEFAULT]; }; -- cgit v1.2.3 From cf420048b3b2af9ce928d35cc5455c646c9dd2f7 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 16 Feb 2012 17:50:06 +0000 Subject: Delete the __FD_*() funcs for operating on fd_set from linux/time.h Delete the __FD_*() functions for operating on fd_set structs from linux/time.h as they're no longer used within the kernel with the preceding patch and are not exported to userspace. Whilst linux/time.h *does* export the FD_*() equivalents as wrappers around __FD_*(), userspace provides its own definition of __FD_*(). Note that the definition of FD_ZERO() in linux/time.h may not be used with the fd_sets associated with struct fdtable as the fd_set may have been allocated in a truncated fashion. Signed-off-by: David Howells Link: http://lkml.kernel.org/r/20120216175006.23314.18984.stgit@warthog.procyon.org.uk Signed-off-by: H. Peter Anvin Cc: Al Viro --- include/linux/time.h | 23 ----------------------- 1 file changed, 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index 93277a0b2293..9f43487facdf 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -4,11 +4,8 @@ #include #ifdef __KERNEL__ -# include # include -# include # include -# include # include #endif @@ -260,26 +257,6 @@ static __always_inline void timespec_add_ns(struct timespec *a, u64 ns) a->tv_nsec = ns; } -static inline void __FD_SET(unsigned long __fd, __kernel_fd_set *__fdsetp) -{ - __set_bit(__fd, __fdsetp->fds_bits); -} - -static inline void __FD_CLR(unsigned long __fd, __kernel_fd_set *__fdsetp) -{ - __clear_bit(__fd, __fdsetp->fds_bits); -} - -static inline int __FD_ISSET(unsigned long __fd, const __kernel_fd_set *__fdsetp) -{ - return test_bit(__fd, __fdsetp->fds_bits); -} - -static inline void __FD_ZERO(__kernel_fd_set *__fdsetp) -{ - memset(__fdsetp->fds_bits, 0, sizeof __fdsetp->fds_bits); -} - #endif /* __KERNEL__ */ #define NFDBITS __NFDBITS -- cgit v1.2.3 From 59cca653a601372e9b4a430d867377a3e4a36d76 Mon Sep 17 00:00:00 2001 From: Dmitry Kasatkin Date: Thu, 2 Feb 2012 10:46:49 +0200 Subject: digsig: changed type of the timestamp time_t was used in the signature and key packet headers, which is typedef of long and is different on 32 and 64 bit architectures. Signature and key format should be independent of architecture. Similar to GPG, I have changed the type to uint32_t. Signed-off-by: Dmitry Kasatkin Signed-off-by: James Morris --- include/linux/digsig.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/digsig.h b/include/linux/digsig.h index b01558b15814..6f85a070bb45 100644 --- a/include/linux/digsig.h +++ b/include/linux/digsig.h @@ -30,7 +30,7 @@ enum digest_algo { struct pubkey_hdr { uint8_t version; /* key format version */ - time_t timestamp; /* key made, always 0 for now */ + uint32_t timestamp; /* key made, always 0 for now */ uint8_t algo; uint8_t nmpi; char mpi[0]; @@ -38,7 +38,7 @@ struct pubkey_hdr { struct signature_hdr { uint8_t version; /* signature format version */ - time_t timestamp; /* signature made */ + uint32_t timestamp; /* signature made */ uint8_t algo; uint8_t hash; uint8_t keyid[8]; -- cgit v1.2.3 From d8e5ddef21df05bc2a14d8c0e287cbf083da60a3 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Mon, 6 Feb 2012 16:36:48 -0800 Subject: sysinfo: Move struct sysinfo to a separate header file struct sysinfo is just about the only thing exported to userspace from , so move it into a separate header file with a residual #include in . Originally-by: H. J. Lu Signed-off-by: H. Peter Anvin Link: http://lkml.kernel.org/n/tip-4pr1xnnksprt7t0h3w5fw4rv@git.kernel.org --- include/linux/Kbuild | 1 + include/linux/kernel.h | 21 ++------------------- include/linux/sysinfo.h | 22 ++++++++++++++++++++++ 3 files changed, 25 insertions(+), 19 deletions(-) create mode 100644 include/linux/sysinfo.h (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index c94e71781b79..844608677665 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -355,6 +355,7 @@ header-y += suspend_ioctls.h header-y += swab.h header-y += synclink.h header-y += sysctl.h +header-y += sysinfo.h header-y += taskstats.h header-y += tcp.h header-y += telephony.h diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e8343422240a..dc6a50f88ca7 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -1,6 +1,8 @@ #ifndef _LINUX_KERNEL_H #define _LINUX_KERNEL_H +#include + /* * 'kernel.h' contains some often-used function prototypes etc */ @@ -745,27 +747,8 @@ extern int __build_bug_on_failed; # define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD #endif -struct sysinfo; extern int do_sysinfo(struct sysinfo *info); #endif /* __KERNEL__ */ -#define SI_LOAD_SHIFT 16 -struct sysinfo { - long uptime; /* Seconds since boot */ - unsigned long loads[3]; /* 1, 5, and 15 minute load averages */ - unsigned long totalram; /* Total usable main memory size */ - unsigned long freeram; /* Available memory size */ - unsigned long sharedram; /* Amount of shared memory */ - unsigned long bufferram; /* Memory used by buffers */ - unsigned long totalswap; /* Total swap space size */ - unsigned long freeswap; /* swap space still available */ - unsigned short procs; /* Number of current processes */ - unsigned short pad; /* explicit padding for m68k */ - unsigned long totalhigh; /* Total high memory size */ - unsigned long freehigh; /* Available high memory size */ - unsigned int mem_unit; /* Memory unit size in bytes */ - char _f[20-2*sizeof(long)-sizeof(int)]; /* Padding: libc5 uses this.. */ -}; - #endif diff --git a/include/linux/sysinfo.h b/include/linux/sysinfo.h new file mode 100644 index 000000000000..ec4fc228ac0a --- /dev/null +++ b/include/linux/sysinfo.h @@ -0,0 +1,22 @@ +#ifndef _LINUX_SYSINFO_H +#define _LINUX_SYSINFO_H + +#define SI_LOAD_SHIFT 16 +struct sysinfo { + long uptime; /* Seconds since boot */ + unsigned long loads[3]; /* 1, 5, and 15 minute load averages */ + unsigned long totalram; /* Total usable main memory size */ + unsigned long freeram; /* Available memory size */ + unsigned long sharedram; /* Amount of shared memory */ + unsigned long bufferram; /* Memory used by buffers */ + unsigned long totalswap; /* Total swap space size */ + unsigned long freeswap; /* swap space still available */ + unsigned short procs; /* Number of current processes */ + unsigned short pad; /* explicit padding for m68k */ + unsigned long totalhigh; /* Total high memory size */ + unsigned long freehigh; /* Available high memory size */ + unsigned int mem_unit; /* Memory unit size in bytes */ + char _f[20-2*sizeof(long)-sizeof(int)]; /* Padding: libc5 uses this.. */ +}; + +#endif /* _LINUX_SYSINFO_H */ -- cgit v1.2.3 From 109a1f32d0d3e23545f0286f2d6e0a80298f629d Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Fri, 10 Feb 2012 13:58:56 -0800 Subject: sysinfo: Use explicit types in Change to use explicitly sized types. Replace long/unsigned long with __kernel_[u]long_t so that a non-legacy 32-bit ABI running on a 64-bit kernel can export those as 64-bit types. Originally-by: H. J. Lu Signed-off-by: H. Peter Anvin --- include/linux/sysinfo.h | 30 ++++++++++++++++-------------- 1 file changed, 16 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysinfo.h b/include/linux/sysinfo.h index ec4fc228ac0a..934335a22522 100644 --- a/include/linux/sysinfo.h +++ b/include/linux/sysinfo.h @@ -1,22 +1,24 @@ #ifndef _LINUX_SYSINFO_H #define _LINUX_SYSINFO_H +#include + #define SI_LOAD_SHIFT 16 struct sysinfo { - long uptime; /* Seconds since boot */ - unsigned long loads[3]; /* 1, 5, and 15 minute load averages */ - unsigned long totalram; /* Total usable main memory size */ - unsigned long freeram; /* Available memory size */ - unsigned long sharedram; /* Amount of shared memory */ - unsigned long bufferram; /* Memory used by buffers */ - unsigned long totalswap; /* Total swap space size */ - unsigned long freeswap; /* swap space still available */ - unsigned short procs; /* Number of current processes */ - unsigned short pad; /* explicit padding for m68k */ - unsigned long totalhigh; /* Total high memory size */ - unsigned long freehigh; /* Available high memory size */ - unsigned int mem_unit; /* Memory unit size in bytes */ - char _f[20-2*sizeof(long)-sizeof(int)]; /* Padding: libc5 uses this.. */ + __kernel_long_t uptime; /* Seconds since boot */ + __kernel_ulong_t loads[3]; /* 1, 5, and 15 minute load averages */ + __kernel_ulong_t totalram; /* Total usable main memory size */ + __kernel_ulong_t freeram; /* Available memory size */ + __kernel_ulong_t sharedram; /* Amount of shared memory */ + __kernel_ulong_t bufferram; /* Memory used by buffers */ + __kernel_ulong_t totalswap; /* Total swap space size */ + __kernel_ulong_t freeswap; /* swap space still available */ + __u16 procs; /* Number of current processes */ + __u16 pad; /* Explicit padding for m68k */ + __kernel_ulong_t totalhigh; /* Total high memory size */ + __kernel_ulong_t freehigh; /* Available high memory size */ + __u32 mem_unit; /* Memory unit size in bytes */ + char _f[20-2*sizeof(__kernel_ulong_t)-sizeof(__u32)]; /* Padding: libc5 uses this.. */ }; #endif /* _LINUX_SYSINFO_H */ -- cgit v1.2.3 From 45e877812926c69d643d6274347f79513a4ee934 Mon Sep 17 00:00:00 2001 From: "H. J. Lu" Date: Fri, 10 Feb 2012 14:04:27 -0800 Subject: compat: Introduce COMPAT_USE_64BIT_TIME Allow a compatibility ABI to use a 64-bit time_t and 64-bit members in struct timeval and struct timespec to avoid the Y2038 problem. This will be used for the x32 ABI. Signed-off-by: H. Peter Anvin --- include/linux/compat.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 41c9f6515f46..1be91c048249 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -19,6 +19,10 @@ #include #include +#ifndef COMPAT_USE_64BIT_TIME +#define COMPAT_USE_64BIT_TIME 0 +#endif + #define compat_jiffies_to_clock_t(x) \ (((unsigned long)(x) * COMPAT_USER_HZ) / HZ) -- cgit v1.2.3 From 6684ba202b5ab2f36d574c72fe50c207d99b3e35 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Sun, 19 Feb 2012 17:38:00 -0800 Subject: compat: Add helper functions to read/write struct timeval, timespec Add helper functions to read and write struct timeval and struct timespec from userspace. We already had helper functions for reading and writing struct compat_timespec; add a set of functions to do the same with struct timeval, and add a second suite of functions which can be sensitive to COMPAT_USE_64BIT_TIME and access either 32- or 64-bit time structures. This also exports these helper functions to modules. Rename the existing inlines for converting between struct compat_timeval and native struct timespec so we can have a saner naming convention for the exported functions. Suggested-by: Linus Torvalds Signed-off-by: H. Peter Anvin --- include/linux/compat.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 1be91c048249..a82e452bbdb9 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -87,10 +87,26 @@ typedef struct { compat_sigset_word sig[_COMPAT_NSIG_WORDS]; } compat_sigset_t; +/* + * These functions operate strictly on struct compat_time* + */ extern int get_compat_timespec(struct timespec *, const struct compat_timespec __user *); extern int put_compat_timespec(const struct timespec *, struct compat_timespec __user *); +extern int get_compat_timeval(struct timeval *, + const struct compat_timeval __user *); +extern int put_compat_timeval(const struct timeval *, + struct compat_timeval __user *); +/* + * These functions operate on 32- or 64-bit specs depending on + * COMPAT_USE_64BIT_TIME, hence the void user pointer arguments and the + * naming as compat_get/put_ rather than get/put_compat_. + */ +extern int compat_get_timespec(struct timespec *, const void __user *); +extern int compat_put_timespec(const struct timespec *, void __user *); +extern int compat_get_timeval(struct timeval *, const void __user *); +extern int compat_put_timeval(const struct timeval *, void __user *); struct compat_iovec { compat_uptr_t iov_base; -- cgit v1.2.3 From ff88943a1471440cc6be7a11a942a5a8232bee61 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Tue, 14 Feb 2012 12:58:56 -0800 Subject: aio: Use __kernel_ulong_t to define aio_context_t Rather than using "unsigned long" which is ABI-dependent, use __kernel_ulong_t to define the externally visible type aio_context_t. Note: the change in this form will cause unsigned long/unsigned int differences on existing ABIs. If that is unacceptable we may have to define a new type. Signed-off-by: H. Peter Anvin Cc: Benjamin LaHaise --- include/linux/aio_abi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/aio_abi.h b/include/linux/aio_abi.h index 2c8731664180..86fa7a71336a 100644 --- a/include/linux/aio_abi.h +++ b/include/linux/aio_abi.h @@ -30,7 +30,7 @@ #include #include -typedef unsigned long aio_context_t; +typedef __kernel_ulong_t aio_context_t; enum { IOCB_CMD_PREAD = 0, -- cgit v1.2.3 From 88ba136d6635b262f77cc418d536115fb8e4d4ab Mon Sep 17 00:00:00 2001 From: Joerg Willmann Date: Tue, 21 Feb 2012 13:26:14 +0100 Subject: netfilter: ebtables: fix alignment problem in ppc ebt_among extension of ebtables uses __alignof__(_xt_align) while the corresponding kernel module uses __alignof__(ebt_replace) to determine the alignment in EBT_ALIGN(). These are the results of these values on different platforms: x86 x86_64 ppc __alignof__(_xt_align) 4 8 8 __alignof__(ebt_replace) 4 8 4 ebtables fails to add rules which use the among extension. I'm using kernel 2.6.33 and ebtables 2.0.10-4 According to Bart De Schuymer, userspace alignment was changed to _xt_align to fix an alignment issue on a userspace32-kernel64 system (he thinks it was for an ARM device). So userspace must be right. The kernel alignment macro needs to change so it also uses _xt_align instead of ebt_replace. The userspace changes date back from June 29, 2009. Signed-off-by: Joerg Willmann Signed-off by: Bart De Schuymer Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_bridge/ebtables.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index 8797ed16feb2..4dd5bd6994a8 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -285,8 +285,8 @@ struct ebt_table { struct module *me; }; -#define EBT_ALIGN(s) (((s) + (__alignof__(struct ebt_replace)-1)) & \ - ~(__alignof__(struct ebt_replace)-1)) +#define EBT_ALIGN(s) (((s) + (__alignof__(struct _xt_align)-1)) & \ + ~(__alignof__(struct _xt_align)-1)) extern struct ebt_table *ebt_register_table(struct net *net, const struct ebt_table *table); extern void ebt_unregister_table(struct net *net, struct ebt_table *table); -- cgit v1.2.3 From 115c9b81928360d769a76c632bae62d15206a94a Mon Sep 17 00:00:00 2001 From: Greg Rose Date: Tue, 21 Feb 2012 16:54:48 -0500 Subject: rtnetlink: Fix problem with buffer allocation Implement a new netlink attribute type IFLA_EXT_MASK. The mask is a 32 bit value that can be used to indicate to the kernel that certain extended ifinfo values are requested by the user application. At this time the only mask value defined is RTEXT_FILTER_VF to indicate that the user wants the ifinfo dump to send information about the VFs belonging to the interface. This patch fixes a bug in which certain applications do not have large enough buffers to accommodate the extra information returned by the kernel with large numbers of SR-IOV virtual functions. Those applications will not send the new netlink attribute with the interface info dump request netlink messages so they will not get unexpectedly large request buffers returned by the kernel. Modifies the rtnl_calcit function to traverse the list of net devices and compute the minimum buffer size that can hold the info dumps of all matching devices based upon the filter passed in via the new netlink attribute filter mask. If no filter mask is sent then the buffer allocation defaults to NLMSG_GOODSIZE. With this change it is possible to add yet to be defined netlink attributes to the dump request which should make it fairly extensible in the future. Signed-off-by: Greg Rose Signed-off-by: David S. Miller --- include/linux/if_link.h | 1 + include/linux/rtnetlink.h | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_link.h b/include/linux/if_link.h index c52d4b5f872a..4b24ff453aee 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -137,6 +137,7 @@ enum { IFLA_AF_SPEC, IFLA_GROUP, /* Group the device belongs to */ IFLA_NET_NS_FD, + IFLA_EXT_MASK, /* Extended info mask, VFs, etc */ __IFLA_MAX }; diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 8e872ead88b5..577592ea0ea0 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -602,6 +602,9 @@ struct tcamsg { #define TCA_ACT_TAB 1 /* attr type must be >=1 */ #define TCAA_MAX 1 +/* New extended info filters for IFLA_EXT_MASK */ +#define RTEXT_FILTER_VF (1 << 0) + /* End of information exported to user level */ #ifdef __KERNEL__ -- cgit v1.2.3 From faf309009e2e18d30c032b7d9479f29b91677c37 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2012 17:24:20 -0800 Subject: sys_poll: fix incorrect type for 'timeout' parameter The 'poll()' system call timeout parameter is supposed to be 'int', not 'long'. Now, the reason this matters is that right now 32-bit compat mode is broken on at least x86-64, because the 32-bit code just calls 'sys_poll()' directly on x86-64, and the 32-bit argument will have been zero-extended, turning a signed 'int' into a large unsigned 'long' value. We could just introduce a 'compat_sys_poll()' function for this, and that may eventually be what we have to do, but since the actual standard poll() semantics is *supposed* to be 'int', and since at least on x86-64 glibc sign-extends the argument before invocing the system call (so nobody can actually use a 64-bit timeout value in user space _anyway_, even in 64-bit binaries), the simpler solution would seem to be to just fix the definition of the system call to match what it should have been from the very start. If it turns out that somebody somehow circumvents the user-level libc 64-bit sign extension and actually uses a large unsigned 64-bit timeout despite that not being how poll() is supposed to work, we will need to do the compat_sys_poll() approach. Reported-by: Thomas Meyer Acked-by: Eric Dumazet Signed-off-by: Linus Torvalds --- include/linux/syscalls.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 515669fa3c1d..8ec1153ff57b 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -624,7 +624,7 @@ asmlinkage long sys_socketpair(int, int, int, int __user *); asmlinkage long sys_socketcall(int call, unsigned long __user *args); asmlinkage long sys_listen(int, int); asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds, - long timeout); + int timeout); asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp); asmlinkage long sys_old_select(struct sel_arg_struct __user *arg); -- cgit v1.2.3 From 03606895cd98c0a628b17324fd7b5ff15db7e3cd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 23 Feb 2012 10:55:02 +0000 Subject: ipsec: be careful of non existing mac headers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Niccolo Belli reported ipsec crashes in case we handle a frame without mac header (atm in his case) Before copying mac header, better make sure it is present. Bugzilla reference: https://bugzilla.kernel.org/show_bug.cgi?id=42809 Reported-by: Niccolò Belli Tested-by: Niccolò Belli Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 50db9b04a552..ae86adee3746 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1465,6 +1465,16 @@ static inline void skb_set_mac_header(struct sk_buff *skb, const int offset) } #endif /* NET_SKBUFF_DATA_USES_OFFSET */ +static inline void skb_mac_header_rebuild(struct sk_buff *skb) +{ + if (skb_mac_header_was_set(skb)) { + const unsigned char *old_mac = skb_mac_header(skb); + + skb_set_mac_header(skb, -skb->mac_len); + memmove(skb_mac_header(skb), old_mac, skb->mac_len); + } +} + static inline int skb_checksum_start_offset(const struct sk_buff *skb) { return skb->csum_start - skb_headroom(skb); -- cgit v1.2.3 From d80e731ecab420ddcb79ee9d0ac427acbc187b4b Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 24 Feb 2012 20:07:11 +0100 Subject: epoll: introduce POLLFREE to flush ->signalfd_wqh before kfree() This patch is intentionally incomplete to simplify the review. It ignores ep_unregister_pollwait() which plays with the same wqh. See the next change. epoll assumes that the EPOLL_CTL_ADD'ed file controls everything f_op->poll() needs. In particular it assumes that the wait queue can't go away until eventpoll_release(). This is not true in case of signalfd, the task which does EPOLL_CTL_ADD uses its ->sighand which is not connected to the file. This patch adds the special event, POLLFREE, currently only for epoll. It expects that init_poll_funcptr()'ed hook should do the necessary cleanup. Perhaps it should be defined as EPOLLFREE in eventpoll. __cleanup_sighand() is changed to do wake_up_poll(POLLFREE) if ->signalfd_wqh is not empty, we add the new signalfd_cleanup() helper. ep_poll_callback(POLLFREE) simply does list_del_init(task_list). This make this poll entry inconsistent, but we don't care. If you share epoll fd which contains our sigfd with another process you should blame yourself. signalfd is "really special". I simply do not know how we can define the "right" semantics if it used with epoll. The main problem is, epoll calls signalfd_poll() once to establish the connection with the wait queue, after that signalfd_poll(NULL) returns the different/inconsistent results depending on who does EPOLL_CTL_MOD/signalfd_read/etc. IOW: apart from sigmask, signalfd has nothing to do with the file, it works with the current thread. In short: this patch is the hack which tries to fix the symptoms. It also assumes that nobody can take tasklist_lock under epoll locks, this seems to be true. Note: - we do not have wake_up_all_poll() but wake_up_poll() is fine, poll/epoll doesn't use WQ_FLAG_EXCLUSIVE. - signalfd_cleanup() uses POLLHUP along with POLLFREE, we need a couple of simple changes in eventpoll.c to make sure it can't be "lost". Reported-by: Maxime Bizon Cc: Signed-off-by: Oleg Nesterov Signed-off-by: Linus Torvalds --- include/linux/signalfd.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/signalfd.h b/include/linux/signalfd.h index 3ff4961da9b5..247399b2979a 100644 --- a/include/linux/signalfd.h +++ b/include/linux/signalfd.h @@ -61,13 +61,16 @@ static inline void signalfd_notify(struct task_struct *tsk, int sig) wake_up(&tsk->sighand->signalfd_wqh); } +extern void signalfd_cleanup(struct sighand_struct *sighand); + #else /* CONFIG_SIGNALFD */ static inline void signalfd_notify(struct task_struct *tsk, int sig) { } +static inline void signalfd_cleanup(struct sighand_struct *sighand) { } + #endif /* CONFIG_SIGNALFD */ #endif /* __KERNEL__ */ #endif /* _LINUX_SIGNALFD_H */ - -- cgit v1.2.3 From 3c761ea05a8900a907f32b628611873f6bef24b2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 26 Feb 2012 09:44:55 -0800 Subject: Fix autofs compile without CONFIG_COMPAT The autofs compat handling fix caused a compile failure when CONFIG_COMPAT isn't defined. Instead of adding random #ifdef'fery in autofs, let's just make the compat helpers earlier to use: without CONFIG_COMPAT, is_compat_task() just hardcodes to zero. We could probably do something similar for a number of other cases where we have #ifdef's in code, but this is the low-hanging fruit. Reported-and-tested-by: Andreas Schwab Signed-off-by: Linus Torvalds --- include/linux/compat.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 41c9f6515f46..7e05fcee75a1 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -561,5 +561,9 @@ asmlinkage ssize_t compat_sys_process_vm_writev(compat_pid_t pid, unsigned long liovcnt, const struct compat_iovec __user *rvec, unsigned long riovcnt, unsigned long flags); +#else + +#define is_compat_task() (0) + #endif /* CONFIG_COMPAT */ #endif /* _LINUX_COMPAT_H */ -- cgit v1.2.3 From c8e252586f8d5de906385d8cf6385fee289a825e Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Fri, 2 Mar 2012 10:43:48 -0800 Subject: regset: Prevent null pointer reference on readonly regsets The regset common infrastructure assumed that regsets would always have .get and .set methods, but not necessarily .active methods. Unfortunately people have since written regsets without .set methods. Rather than putting in stub functions everywhere, handle regsets with null .get or .set methods explicitly. Signed-off-by: H. Peter Anvin Reviewed-by: Oleg Nesterov Acked-by: Roland McGrath Cc: Signed-off-by: Linus Torvalds --- include/linux/regset.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regset.h b/include/linux/regset.h index 8abee6556223..5150fd16ef93 100644 --- a/include/linux/regset.h +++ b/include/linux/regset.h @@ -335,6 +335,9 @@ static inline int copy_regset_to_user(struct task_struct *target, { const struct user_regset *regset = &view->regsets[setno]; + if (!regset->get) + return -EOPNOTSUPP; + if (!access_ok(VERIFY_WRITE, data, size)) return -EIO; @@ -358,6 +361,9 @@ static inline int copy_regset_from_user(struct task_struct *target, { const struct user_regset *regset = &view->regsets[setno]; + if (!regset->set) + return -EOPNOTSUPP; + if (!access_ok(VERIFY_READ, data, size)) return -EIO; -- cgit v1.2.3 From 5189fa19a4b2b4c3bec37c3a019d446148827717 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Fri, 2 Mar 2012 10:43:49 -0800 Subject: regset: Return -EFAULT, not -EIO, on host-side memory fault There is only one error code to return for a bad user-space buffer pointer passed to a system call in the same address space as the system call is executed, and that is EFAULT. Furthermore, the low-level access routines, which catch most of the faults, return EFAULT already. Signed-off-by: H. Peter Anvin Reviewed-by: Oleg Nesterov Acked-by: Roland McGrath Cc: Signed-off-by: Linus Torvalds --- include/linux/regset.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regset.h b/include/linux/regset.h index 5150fd16ef93..686f37327a49 100644 --- a/include/linux/regset.h +++ b/include/linux/regset.h @@ -339,7 +339,7 @@ static inline int copy_regset_to_user(struct task_struct *target, return -EOPNOTSUPP; if (!access_ok(VERIFY_WRITE, data, size)) - return -EIO; + return -EFAULT; return regset->get(target, regset, offset, size, NULL, data); } @@ -365,7 +365,7 @@ static inline int copy_regset_from_user(struct task_struct *target, return -EOPNOTSUPP; if (!access_ok(VERIFY_READ, data, size)) - return -EIO; + return -EFAULT; return regset->set(target, regset, offset, size, NULL, data); } -- cgit v1.2.3 From 8966be90304b394fd6a2c5af7b6b3abe2df3889c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 2 Mar 2012 14:23:30 -0800 Subject: vfs: trivial __d_lookup_rcu() cleanups These don't change any semantics, but they clean up the code a bit and mark some arguments appropriately 'const'. They came up as I was doing the word-at-a-time dcache name accessor code, and cleaning this up now allows me to send out a smaller relevant interesting patch for the experimental stuff. Signed-off-by: Linus Torvalds --- include/linux/dcache.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index d64a55b23afd..61b24261e07a 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -309,7 +309,8 @@ extern struct dentry *d_ancestor(struct dentry *, struct dentry *); extern struct dentry *d_lookup(struct dentry *, struct qstr *); extern struct dentry *d_hash_and_lookup(struct dentry *, struct qstr *); extern struct dentry *__d_lookup(struct dentry *, struct qstr *); -extern struct dentry *__d_lookup_rcu(struct dentry *parent, struct qstr *name, +extern struct dentry *__d_lookup_rcu(const struct dentry *parent, + const struct qstr *name, unsigned *seq, struct inode **inode); /** -- cgit v1.2.3 From 0145acc202ca613b23b5383e55df3c32a92ad1bf Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 2 Mar 2012 14:32:59 -0800 Subject: vfs: uninline full_name_hash() .. and also use it in lookup_one_len() rather than open-coding it. There aren't any performance-critical users, so inlining it is silly. But it wouldn't matter if it wasn't for the fact that the word-at-a-time dentry name patches want to conditionally replace the function, and uninlining it sets the stage for that. So again, this is a preparatory patch that doesn't change any semantics, and only prepares for a much cleaner and testable word-at-a-time dentry name accessor patch. Signed-off-by: Linus Torvalds --- include/linux/dcache.h | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 61b24261e07a..f1c7eb8461be 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -89,14 +89,7 @@ static inline unsigned long end_name_hash(unsigned long hash) } /* Compute the hash for a name string. */ -static inline unsigned int -full_name_hash(const unsigned char *name, unsigned int len) -{ - unsigned long hash = init_name_hash(); - while (len--) - hash = partial_name_hash(*name++, hash); - return end_name_hash(hash); -} +extern unsigned int full_name_hash(const unsigned char *, unsigned int); /* * Try to keep struct dentry aligned on 64 byte cachelines (this will -- cgit v1.2.3 From 5707c87f20bca9e76969bb4096149de6ef74cbb9 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 2 Mar 2012 14:47:15 -0800 Subject: vfs: clarify and clean up dentry_cmp() It did some odd things for unclear reasons. As this is one of the functions that gets changed when doing word-at-a-time compares, this is yet another of the "don't change any semantics, but clean things up so that subsequent patches don't get obscured by the cleanups". Signed-off-by: Linus Torvalds --- include/linux/dcache.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index f1c7eb8461be..4270bedd2308 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -54,18 +54,17 @@ extern struct dentry_stat_t dentry_stat; static inline int dentry_cmp(const unsigned char *cs, size_t scount, const unsigned char *ct, size_t tcount) { - int ret; if (scount != tcount) return 1; + do { - ret = (*cs != *ct); - if (ret) - break; + if (*cs != *ct) + return 1; cs++; ct++; tcount--; } while (tcount); - return ret; + return 0; } /* Name hashing routines. Initial hash value */ -- cgit v1.2.3