From 2e1c9b2867656ff9a469d23e1dfe90cf77ec0c72 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 8 Mar 2013 12:43:30 -0800 Subject: idr: remove WARN_ON_ONCE() on negative IDs idr_find(), idr_remove() and idr_replace() used to silently ignore the sign bit and perform lookup with the rest of the bits. The weird behavior has been changed such that negative IDs are treated as invalid. As the behavior change was subtle, WARN_ON_ONCE() was added in the hope of determining who's calling idr functions with negative IDs so that they can be examined for problems. Up until now, all two reported cases are ID number coming directly from userland and getting fed into idr_find() and the warnings seem to cause more problems than being helpful. Drop the WARN_ON_ONCE()s. Signed-off-by: Tejun Heo Reported-by: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/idr.c | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) (limited to 'lib') diff --git a/lib/idr.c b/lib/idr.c index 73f4d53c02f..00739aaf95a 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -569,8 +569,7 @@ void idr_remove(struct idr *idp, int id) struct idr_layer *p; struct idr_layer *to_free; - /* see comment in idr_find_slowpath() */ - if (WARN_ON_ONCE(id < 0)) + if (id < 0) return; sub_remove(idp, (idp->layers - 1) * IDR_BITS, id); @@ -667,15 +666,7 @@ void *idr_find_slowpath(struct idr *idp, int id) int n; struct idr_layer *p; - /* - * If @id is negative, idr_find() used to ignore the sign bit and - * performed lookup with the rest of bits, which is weird and can - * lead to very obscure bugs. We're now returning NULL for all - * negative IDs but just in case somebody was depending on the sign - * bit being ignored, let's trigger WARN_ON_ONCE() so that they can - * be detected and fixed. WARN_ON_ONCE() can later be removed. - */ - if (WARN_ON_ONCE(id < 0)) + if (id < 0) return NULL; p = rcu_dereference_raw(idp->top); @@ -824,8 +815,7 @@ void *idr_replace(struct idr *idp, void *ptr, int id) int n; struct idr_layer *p, *old_p; - /* see comment in idr_find_slowpath() */ - if (WARN_ON_ONCE(id < 0)) + if (id < 0) return ERR_PTR(-EINVAL); p = idp->top; -- cgit v1.2.3-70-g09d2 From 5857f70c8a62377c2304d8ad27e579881728fc5a Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 4 Mar 2013 14:32:54 -0800 Subject: idr: fix new kernel-doc warnings Fix new kernel-doc warnings in idr: Warning(include/linux/idr.h:113): No description found for parameter 'idr' Warning(include/linux/idr.h:113): Excess function parameter 'idp' description in 'idr_find' Warning(lib/idr.c:232): Excess function parameter 'id' description in 'sub_alloc' Warning(lib/idr.c:232): Excess function parameter 'id' description in 'sub_alloc' Signed-off-by: Randy Dunlap Acked-by: Tejun Heo Signed-off-by: Linus Torvalds --- include/linux/idr.h | 2 +- lib/idr.c | 1 - 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'lib') diff --git a/include/linux/idr.h b/include/linux/idr.h index a6f38b5c34e..8c1f81f823c 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -99,7 +99,7 @@ static inline void idr_preload_end(void) /** * idr_find - return pointer for given id - * @idp: idr handle + * @idr: idr handle * @id: lookup key * * Return the pointer given the id it has been registered with. A %NULL diff --git a/lib/idr.c b/lib/idr.c index 00739aaf95a..4f82a284c6a 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -214,7 +214,6 @@ EXPORT_SYMBOL(idr_pre_get); * sub_alloc - try to allocate an id without growing the tree depth * @idp: idr handle * @starting_id: id to start search at - * @id: pointer to the allocated handle * @pa: idr_layer[MAX_IDR_LEVEL] used as backtrack buffer * @gfp_mask: allocation mask for idr_layer_alloc() * @layer_idr: optional idr passed to idr_layer_alloc() -- cgit v1.2.3-70-g09d2 From c8615d3716fe327c2540cf514a34b227dc9b39e8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 13 Mar 2013 14:59:42 -0700 Subject: idr: deprecate idr_pre_get() and idr_get_new[_above]() Now that all in-kernel users are converted to ues the new alloc interface, mark the old interface deprecated. We should be able to remove these in a few releases. Signed-off-by: Tejun Heo Cc: Rusty Russell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 66 ++++++++++++++++++++++++++++++++++++++++------------- lib/idr.c | 41 ++++----------------------------- 2 files changed, 55 insertions(+), 52 deletions(-) (limited to 'lib') diff --git a/include/linux/idr.h b/include/linux/idr.h index 8c1f81f823c..2640c7e99e5 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -73,8 +73,6 @@ struct idr { */ void *idr_find_slowpath(struct idr *idp, int id); -int idr_pre_get(struct idr *idp, gfp_t gfp_mask); -int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id); void idr_preload(gfp_t gfp_mask); int idr_alloc(struct idr *idp, void *ptr, int start, int end, gfp_t gfp_mask); int idr_for_each(struct idr *idp, @@ -119,19 +117,6 @@ static inline void *idr_find(struct idr *idr, int id) return idr_find_slowpath(idr, id); } -/** - * idr_get_new - allocate new idr entry - * @idp: idr handle - * @ptr: pointer you want associated with the id - * @id: pointer to the allocated handle - * - * Simple wrapper around idr_get_new_above() w/ @starting_id of zero. - */ -static inline int idr_get_new(struct idr *idp, void *ptr, int *id) -{ - return idr_get_new_above(idp, ptr, 0, id); -} - /** * idr_for_each_entry - iterate over an idr's elements of a given type * @idp: idr handle @@ -143,7 +128,56 @@ static inline int idr_get_new(struct idr *idp, void *ptr, int *id) entry != NULL; \ ++id, entry = (typeof(entry))idr_get_next((idp), &(id))) -void __idr_remove_all(struct idr *idp); /* don't use */ +/* + * Don't use the following functions. These exist only to suppress + * deprecated warnings on EXPORT_SYMBOL()s. + */ +int __idr_pre_get(struct idr *idp, gfp_t gfp_mask); +int __idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id); +void __idr_remove_all(struct idr *idp); + +/** + * idr_pre_get - reserve resources for idr allocation + * @idp: idr handle + * @gfp_mask: memory allocation flags + * + * Part of old alloc interface. This is going away. Use + * idr_preload[_end]() and idr_alloc() instead. + */ +static inline int __deprecated idr_pre_get(struct idr *idp, gfp_t gfp_mask) +{ + return __idr_pre_get(idp, gfp_mask); +} + +/** + * idr_get_new_above - allocate new idr entry above or equal to a start id + * @idp: idr handle + * @ptr: pointer you want associated with the id + * @starting_id: id to start search at + * @id: pointer to the allocated handle + * + * Part of old alloc interface. This is going away. Use + * idr_preload[_end]() and idr_alloc() instead. + */ +static inline int __deprecated idr_get_new_above(struct idr *idp, void *ptr, + int starting_id, int *id) +{ + return __idr_get_new_above(idp, ptr, starting_id, id); +} + +/** + * idr_get_new - allocate new idr entry + * @idp: idr handle + * @ptr: pointer you want associated with the id + * @id: pointer to the allocated handle + * + * Part of old alloc interface. This is going away. Use + * idr_preload[_end]() and idr_alloc() instead. + */ +static inline int __deprecated idr_get_new(struct idr *idp, void *ptr, int *id) +{ + return __idr_get_new_above(idp, ptr, 0, id); +} /** * idr_remove_all - remove all ids from the given idr tree diff --git a/lib/idr.c b/lib/idr.c index 4f82a284c6a..c6fb8295507 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -184,20 +184,7 @@ static void idr_mark_full(struct idr_layer **pa, int id) } } -/** - * idr_pre_get - reserve resources for idr allocation - * @idp: idr handle - * @gfp_mask: memory allocation flags - * - * This function should be called prior to calling the idr_get_new* functions. - * It preallocates enough memory to satisfy the worst possible allocation. The - * caller should pass in GFP_KERNEL if possible. This of course requires that - * no spinning locks be held. - * - * If the system is REALLY out of memory this function returns %0, - * otherwise %1. - */ -int idr_pre_get(struct idr *idp, gfp_t gfp_mask) +int __idr_pre_get(struct idr *idp, gfp_t gfp_mask) { while (idp->id_free_cnt < MAX_IDR_FREE) { struct idr_layer *new; @@ -208,7 +195,7 @@ int idr_pre_get(struct idr *idp, gfp_t gfp_mask) } return 1; } -EXPORT_SYMBOL(idr_pre_get); +EXPORT_SYMBOL(__idr_pre_get); /** * sub_alloc - try to allocate an id without growing the tree depth @@ -375,25 +362,7 @@ static void idr_fill_slot(struct idr *idr, void *ptr, int id, idr_mark_full(pa, id); } -/** - * idr_get_new_above - allocate new idr entry above or equal to a start id - * @idp: idr handle - * @ptr: pointer you want associated with the id - * @starting_id: id to start search at - * @id: pointer to the allocated handle - * - * This is the allocate id function. It should be called with any - * required locks. - * - * If allocation from IDR's private freelist fails, idr_get_new_above() will - * return %-EAGAIN. The caller should retry the idr_pre_get() call to refill - * IDR's preallocation and then retry the idr_get_new_above() call. - * - * If the idr is full idr_get_new_above() will return %-ENOSPC. - * - * @id returns a value in the range @starting_id ... %0x7fffffff - */ -int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id) +int __idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id) { struct idr_layer *pa[MAX_IDR_LEVEL + 1]; int rv; @@ -406,7 +375,7 @@ int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id) *id = rv; return 0; } -EXPORT_SYMBOL(idr_get_new_above); +EXPORT_SYMBOL(__idr_get_new_above); /** * idr_preload - preload for idr_alloc() @@ -907,7 +876,7 @@ static void free_bitmap(struct ida *ida, struct ida_bitmap *bitmap) int ida_pre_get(struct ida *ida, gfp_t gfp_mask) { /* allocate idr_layers */ - if (!idr_pre_get(&ida->idr, gfp_mask)) + if (!__idr_pre_get(&ida->idr, gfp_mask)) return 0; /* allocate free_bitmap */ -- cgit v1.2.3-70-g09d2 From 97da55fcec6e3898f50010a6847dfa64f7c085e6 Mon Sep 17 00:00:00 2001 From: Paul Bolle Date: Wed, 13 Mar 2013 14:59:44 -0700 Subject: decompressors: fix typo "POWERPC" Commit 5dc49c75a26b ("decompressors: make the default XZ_DEC_* config match the selected architecture") added default y if POWERPC to lib/xz/Kconfig. But there is no Kconfig symbol POWERPC. The most general Kconfig symbol for the powerpc architecture is PPC. So let's use that. Signed-off-by: Paul Bolle Cc: Florian Fainelli Cc: Lasse Collin Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/xz/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/xz/Kconfig b/lib/xz/Kconfig index 82a04d7ba99..08837db52d9 100644 --- a/lib/xz/Kconfig +++ b/lib/xz/Kconfig @@ -15,7 +15,7 @@ config XZ_DEC_X86 config XZ_DEC_POWERPC bool "PowerPC BCJ filter decoder" - default y if POWERPC + default y if PPC select XZ_DEC_BCJ config XZ_DEC_IA64 -- cgit v1.2.3-70-g09d2 From 59bfbcf01967d4d3370a2b8294673dd709e732cc Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 13 Mar 2013 14:59:49 -0700 Subject: idr: idr_alloc() shouldn't trigger lowmem warning when preloaded GFP_NOIO is often used for idr_alloc() inside preloaded section as the allocation mask doesn't really matter. If the idr tree needs to be expanded, idr_alloc() first tries to allocate using the specified allocation mask and if it fails falls back to the preloaded buffer. This order prevent non-preloading idr_alloc() users from taking advantage of preloading ones by using preload buffer without filling it shifting the burden of allocation to the preload users. Unfortunately, this allowed/expected-to-fail kmem_cache allocation ends up generating spurious slab lowmem warning before succeeding the request from the preload buffer. This patch makes idr_layer_alloc() add __GFP_NOWARN to the first kmem_cache attempt and try kmem_cache again w/o __GFP_NOWARN after allocation from preload_buffer fails so that lowmem warning is generated if not suppressed by the original @gfp_mask. Signed-off-by: Tejun Heo Reported-by: David Teigland Tested-by: David Teigland Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/idr.c | 38 +++++++++++++++++++++++++------------- 1 file changed, 25 insertions(+), 13 deletions(-) (limited to 'lib') diff --git a/lib/idr.c b/lib/idr.c index c6fb8295507..322e2816f2f 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -106,8 +106,14 @@ static struct idr_layer *idr_layer_alloc(gfp_t gfp_mask, struct idr *layer_idr) if (layer_idr) return get_from_free_list(layer_idr); - /* try to allocate directly from kmem_cache */ - new = kmem_cache_zalloc(idr_layer_cache, gfp_mask); + /* + * Try to allocate directly from kmem_cache. We want to try this + * before preload buffer; otherwise, non-preloading idr_alloc() + * users will end up taking advantage of preloading ones. As the + * following is allowed to fail for preloaded cases, suppress + * warning this time. + */ + new = kmem_cache_zalloc(idr_layer_cache, gfp_mask | __GFP_NOWARN); if (new) return new; @@ -115,18 +121,24 @@ static struct idr_layer *idr_layer_alloc(gfp_t gfp_mask, struct idr *layer_idr) * Try to fetch one from the per-cpu preload buffer if in process * context. See idr_preload() for details. */ - if (in_interrupt()) - return NULL; - - preempt_disable(); - new = __this_cpu_read(idr_preload_head); - if (new) { - __this_cpu_write(idr_preload_head, new->ary[0]); - __this_cpu_dec(idr_preload_cnt); - new->ary[0] = NULL; + if (!in_interrupt()) { + preempt_disable(); + new = __this_cpu_read(idr_preload_head); + if (new) { + __this_cpu_write(idr_preload_head, new->ary[0]); + __this_cpu_dec(idr_preload_cnt); + new->ary[0] = NULL; + } + preempt_enable(); + if (new) + return new; } - preempt_enable(); - return new; + + /* + * Both failed. Try kmem_cache again w/o adding __GFP_NOWARN so + * that memory allocation failure warning is printed as intended. + */ + return kmem_cache_zalloc(idr_layer_cache, gfp_mask); } static void idr_layer_rcu_free(struct rcu_head *head) -- cgit v1.2.3-70-g09d2 From dc72c32e1fd872a9a4fdfe645283c9dcd68e556d Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 22 Mar 2013 15:04:39 -0700 Subject: printk: Provide a wake_up_klogd() off-case wake_up_klogd() is useless when CONFIG_PRINTK=n because neither printk() nor printk_sched() are in use and there are actually no waiter on log_wait waitqueue. It should be a stub in this case for users like bust_spinlocks(). Otherwise this results in this warning when CONFIG_PRINTK=n and CONFIG_IRQ_WORK=n: kernel/built-in.o In function `wake_up_klogd': (.text.wake_up_klogd+0xb4): undefined reference to `irq_work_queue' To fix this, provide an off-case for wake_up_klogd() when CONFIG_PRINTK=n. There is much more from console_unlock() and other console related code in printk.c that should be moved under CONFIG_PRINTK. But for now, focus on a minimal fix as we passed the merged window already. [akpm@linux-foundation.org: include printk.h in bust_spinlocks.c] Signed-off-by: Frederic Weisbecker Reported-by: James Hogan Cc: James Hogan Cc: Steven Rostedt Cc: Peter Zijlstra Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 1 - include/linux/printk.h | 6 ++++ kernel/printk.c | 80 ++++++++++++++++++++++++-------------------------- lib/bust_spinlocks.c | 3 +- 4 files changed, 46 insertions(+), 44 deletions(-) (limited to 'lib') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 80d36874689..79fdd80a42d 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -390,7 +390,6 @@ extern struct pid *session_of_pgrp(struct pid *pgrp); unsigned long int_sqrt(unsigned long); extern void bust_spinlocks(int yes); -extern void wake_up_klogd(void); extern int oops_in_progress; /* If set, an oops, panic(), BUG() or die() is in progress */ extern int panic_timeout; extern int panic_on_oops; diff --git a/include/linux/printk.h b/include/linux/printk.h index 1249a54d17e..822171fcb1c 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -134,6 +134,8 @@ extern int printk_delay_msec; extern int dmesg_restrict; extern int kptr_restrict; +extern void wake_up_klogd(void); + void log_buf_kexec_setup(void); void __init setup_log_buf(int early); #else @@ -162,6 +164,10 @@ static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies, return false; } +static inline void wake_up_klogd(void) +{ +} + static inline void log_buf_kexec_setup(void) { } diff --git a/kernel/printk.c b/kernel/printk.c index 0b31715f335..abbdd9e2ac8 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -63,8 +63,6 @@ void asmlinkage __attribute__((weak)) early_printk(const char *fmt, ...) #define MINIMUM_CONSOLE_LOGLEVEL 1 /* Minimum loglevel we let people use */ #define DEFAULT_CONSOLE_LOGLEVEL 7 /* anything MORE serious than KERN_DEBUG */ -DECLARE_WAIT_QUEUE_HEAD(log_wait); - int console_printk[4] = { DEFAULT_CONSOLE_LOGLEVEL, /* console_loglevel */ DEFAULT_MESSAGE_LOGLEVEL, /* default_message_loglevel */ @@ -224,6 +222,7 @@ struct log { static DEFINE_RAW_SPINLOCK(logbuf_lock); #ifdef CONFIG_PRINTK +DECLARE_WAIT_QUEUE_HEAD(log_wait); /* the next printk record to read by syslog(READ) or /proc/kmsg */ static u64 syslog_seq; static u32 syslog_idx; @@ -1957,45 +1956,6 @@ int is_console_locked(void) return console_locked; } -/* - * Delayed printk version, for scheduler-internal messages: - */ -#define PRINTK_BUF_SIZE 512 - -#define PRINTK_PENDING_WAKEUP 0x01 -#define PRINTK_PENDING_SCHED 0x02 - -static DEFINE_PER_CPU(int, printk_pending); -static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_sched_buf); - -static void wake_up_klogd_work_func(struct irq_work *irq_work) -{ - int pending = __this_cpu_xchg(printk_pending, 0); - - if (pending & PRINTK_PENDING_SCHED) { - char *buf = __get_cpu_var(printk_sched_buf); - printk(KERN_WARNING "[sched_delayed] %s", buf); - } - - if (pending & PRINTK_PENDING_WAKEUP) - wake_up_interruptible(&log_wait); -} - -static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = { - .func = wake_up_klogd_work_func, - .flags = IRQ_WORK_LAZY, -}; - -void wake_up_klogd(void) -{ - preempt_disable(); - if (waitqueue_active(&log_wait)) { - this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP); - irq_work_queue(&__get_cpu_var(wake_up_klogd_work)); - } - preempt_enable(); -} - static void console_cont_flush(char *text, size_t size) { unsigned long flags; @@ -2458,6 +2418,44 @@ static int __init printk_late_init(void) late_initcall(printk_late_init); #if defined CONFIG_PRINTK +/* + * Delayed printk version, for scheduler-internal messages: + */ +#define PRINTK_BUF_SIZE 512 + +#define PRINTK_PENDING_WAKEUP 0x01 +#define PRINTK_PENDING_SCHED 0x02 + +static DEFINE_PER_CPU(int, printk_pending); +static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_sched_buf); + +static void wake_up_klogd_work_func(struct irq_work *irq_work) +{ + int pending = __this_cpu_xchg(printk_pending, 0); + + if (pending & PRINTK_PENDING_SCHED) { + char *buf = __get_cpu_var(printk_sched_buf); + printk(KERN_WARNING "[sched_delayed] %s", buf); + } + + if (pending & PRINTK_PENDING_WAKEUP) + wake_up_interruptible(&log_wait); +} + +static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = { + .func = wake_up_klogd_work_func, + .flags = IRQ_WORK_LAZY, +}; + +void wake_up_klogd(void) +{ + preempt_disable(); + if (waitqueue_active(&log_wait)) { + this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP); + irq_work_queue(&__get_cpu_var(wake_up_klogd_work)); + } + preempt_enable(); +} int printk_sched(const char *fmt, ...) { diff --git a/lib/bust_spinlocks.c b/lib/bust_spinlocks.c index 9681d54b95d..f8e0e536739 100644 --- a/lib/bust_spinlocks.c +++ b/lib/bust_spinlocks.c @@ -8,6 +8,7 @@ */ #include +#include #include #include #include @@ -28,5 +29,3 @@ void __attribute__((weak)) bust_spinlocks(int yes) wake_up_klogd(); } } - - -- cgit v1.2.3-70-g09d2 From 8d640a51ec9e9cdefa680b67ad55f933eefc5923 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 22 Mar 2013 15:04:48 -0700 Subject: dma-debug: fix locking bug in check_unmap() In check_unmap() it is possible to get into a dead-locked state if dma_mapping_error is called. The problem is that the bucket is locked in check_unmap, and locked again by debug_dma_mapping_error which is called by dma_mapping_error. To resolve that we must release the lock on the bucket before making the call to dma_mapping_error. [akpm@linux-foundation.org: restore 80-col trickery to be consistent with the rest of the file] Signed-off-by: Alexander Duyck Cc: Joerg Roedel Reviewed-by: Shuah Khan Tested-by: Shuah Khan Cc: Jakub Kicinski Cc: Konrad Rzeszutek Wilk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/dma-debug.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) (limited to 'lib') diff --git a/lib/dma-debug.c b/lib/dma-debug.c index 5e396accd3d..d3e06a5e981 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -862,17 +862,21 @@ static void check_unmap(struct dma_debug_entry *ref) entry = bucket_find_exact(bucket, ref); if (!entry) { + /* must drop lock before calling dma_mapping_error */ + put_hash_bucket(bucket, &flags); + if (dma_mapping_error(ref->dev, ref->dev_addr)) { err_printk(ref->dev, NULL, - "DMA-API: device driver tries " - "to free an invalid DMA memory address\n"); - return; + "DMA-API: device driver tries to free an " + "invalid DMA memory address\n"); + } else { + err_printk(ref->dev, NULL, + "DMA-API: device driver tries to free DMA " + "memory it has not allocated [device " + "address=0x%016llx] [size=%llu bytes]\n", + ref->dev_addr, ref->size); } - err_printk(ref->dev, NULL, "DMA-API: device driver tries " - "to free DMA memory it has not allocated " - "[device address=0x%016llx] [size=%llu bytes]\n", - ref->dev_addr, ref->size); - goto out; + return; } if (ref->size != entry->size) { @@ -936,7 +940,6 @@ static void check_unmap(struct dma_debug_entry *ref) hash_bucket_del(entry); dma_entry_free(entry); -out: put_hash_bucket(bucket, &flags); } -- cgit v1.2.3-70-g09d2 From 96e7d7a1e0fc7780b4c1981c787e42473aa91a95 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 22 Mar 2013 15:04:49 -0700 Subject: dma-debug: update DMA debug API to better handle multiple mappings of a buffer There were reports of the igb driver unmapping buffers without calling dma_mapping_error. On closer inspection issues were found in the DMA debug API and how it handled multiple mappings of the same buffer. The issue I found is the fact that the debug_dma_mapping_error would only set the map_err_type to MAP_ERR_CHECKED in the case that the was only one match for device and device address. However in the case of non-IOMMU, multiple addresses existed and as a result it was not setting this field once a second mapping was instantiated. I have resolved this by changing the search so that it instead will now set MAP_ERR_CHECKED on the first buffer that matches the device and DMA address that is currently in the state MAP_ERR_NOT_CHECKED. A secondary side effect of this patch is that in the case of multiple buffers using the same address only the last mapping will have a valid map_err_type. The previous mappings will all end up with map_err_type set to MAP_ERR_CHECKED because of the dma_mapping_error call in debug_dma_map_page. However this behavior may be preferable as it means you will likely only see one real error per multi-mapped buffer, versus the current behavior of multiple false errors mer multi-mapped buffer. Signed-off-by: Alexander Duyck Cc: Joerg Roedel Reviewed-by: Shuah Khan Tested-by: Shuah Khan Cc: Jakub Kicinski Cc: Konrad Rzeszutek Wilk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/dma-debug.c | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-) (limited to 'lib') diff --git a/lib/dma-debug.c b/lib/dma-debug.c index d3e06a5e981..d87a17a819d 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -1085,13 +1085,27 @@ void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) ref.dev = dev; ref.dev_addr = dma_addr; bucket = get_hash_bucket(&ref, &flags); - entry = bucket_find_exact(bucket, &ref); - if (!entry) - goto out; + list_for_each_entry(entry, &bucket->list, list) { + if (!exact_match(&ref, entry)) + continue; + + /* + * The same physical address can be mapped multiple + * times. Without a hardware IOMMU this results in the + * same device addresses being put into the dma-debug + * hash multiple times too. This can result in false + * positives being reported. Therefore we implement a + * best-fit algorithm here which updates the first entry + * from the hash which fits the reference value and is + * not currently listed as being checked. + */ + if (entry->map_err_type == MAP_ERR_NOT_CHECKED) { + entry->map_err_type = MAP_ERR_CHECKED; + break; + } + } - entry->map_err_type = MAP_ERR_CHECKED; -out: put_hash_bucket(bucket, &flags); } EXPORT_SYMBOL(debug_dma_mapping_error); -- cgit v1.2.3-70-g09d2 From a49b7e82cab0f9b41f483359be83f44fbb6b4979 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 13 Apr 2013 15:15:30 -0700 Subject: kobject: fix kset_find_obj() race with concurrent last kobject_put() Anatol Pomozov identified a race condition that hits module unloading and re-loading. To quote Anatol: "This is a race codition that exists between kset_find_obj() and kobject_put(). kset_find_obj() might return kobject that has refcount equal to 0 if this kobject is freeing by kobject_put() in other thread. Here is timeline for the crash in case if kset_find_obj() searches for an object tht nobody holds and other thread is doing kobject_put() on the same kobject: THREAD A (calls kset_find_obj()) THREAD B (calls kobject_put()) splin_lock() atomic_dec_return(kobj->kref), counter gets zero here ... starts kobject cleanup .... spin_lock() // WAIT thread A in kobj_kset_leave() iterate over kset->list atomic_inc(kobj->kref) (counter becomes 1) spin_unlock() spin_lock() // taken // it does not know that thread A increased counter so it remove obj from list spin_unlock() vfree(module) // frees module object with containing kobj // kobj points to freed memory area!! kobject_put(kobj) // OOPS!!!! The race above happens because module.c tries to use kset_find_obj() when somebody unloads module. The module.c code was introduced in commit 6494a93d55fa" Anatol supplied a patch specific for module.c that worked around the problem by simply not using kset_find_obj() at all, but rather than make a local band-aid, this just fixes kset_find_obj() to be thread-safe using the proper model of refusing the get a new reference if the refcount has already dropped to zero. See examples of this proper refcount handling not only in the kref documentation, but in various other equivalent uses of this pattern by grepping for atomic_inc_not_zero(). [ Side note: the module race does indicate that module loading and unloading is not properly serialized wrt sysfs information using the module mutex. That may require further thought, but this is the correct fix at the kobject layer regardless. ] Reported-analyzed-and-tested-by: Anatol Pomozov Cc: Greg Kroah-Hartman Cc: Al Viro Cc: stable@vger.kernel.org Signed-off-by: Linus Torvalds --- lib/kobject.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/kobject.c b/lib/kobject.c index e07ee1fcd6f..a65486613d7 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -529,6 +529,13 @@ struct kobject *kobject_get(struct kobject *kobj) return kobj; } +static struct kobject *kobject_get_unless_zero(struct kobject *kobj) +{ + if (!kref_get_unless_zero(&kobj->kref)) + kobj = NULL; + return kobj; +} + /* * kobject_cleanup - free kobject resources. * @kobj: object to cleanup @@ -751,7 +758,7 @@ struct kobject *kset_find_obj(struct kset *kset, const char *name) list_for_each_entry(k, &kset->list, entry) { if (kobject_name(k) && !strcmp(kobject_name(k), name)) { - ret = kobject_get(k); + ret = kobject_get_unless_zero(k); break; } } -- cgit v1.2.3-70-g09d2 From 0635eb8a54cf0fea64b174bb68bc36b9c3d622db Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Mon, 15 Apr 2013 13:09:45 -0700 Subject: Move utf16 functions to kernel core and rename We want to be able to use the utf16 functions that are currently present in the EFI variables code in platform-specific code as well. Move them to the kernel core, and in the process rename them to accurately describe what they do - they don't handle UTF16, only UCS2. Signed-off-by: Matthew Garrett Signed-off-by: Matt Fleming --- drivers/firmware/Kconfig | 1 + drivers/firmware/efivars.c | 80 ++++++++++----------------------------------- include/linux/ucs2_string.h | 14 ++++++++ lib/Kconfig | 3 ++ lib/Makefile | 2 ++ lib/ucs2_string.c | 51 +++++++++++++++++++++++++++++ 6 files changed, 89 insertions(+), 62 deletions(-) create mode 100644 include/linux/ucs2_string.h create mode 100644 lib/ucs2_string.c (limited to 'lib') diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig index 42c759a4d04..3e532002e4d 100644 --- a/drivers/firmware/Kconfig +++ b/drivers/firmware/Kconfig @@ -39,6 +39,7 @@ config FIRMWARE_MEMMAP config EFI_VARS tristate "EFI Variable Support via sysfs" depends on EFI + select UCS2_STRING default n help If you say Y here, you are able to get EFI (Extensible Firmware diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c index bf15d81d74e..182ce947117 100644 --- a/drivers/firmware/efivars.c +++ b/drivers/firmware/efivars.c @@ -80,6 +80,7 @@ #include #include #include +#include #include #include @@ -172,51 +173,6 @@ static void efivar_update_sysfs_entries(struct work_struct *); static DECLARE_WORK(efivar_work, efivar_update_sysfs_entries); static bool efivar_wq_enabled = true; -/* Return the number of unicode characters in data */ -static unsigned long -utf16_strnlen(efi_char16_t *s, size_t maxlength) -{ - unsigned long length = 0; - - while (*s++ != 0 && length < maxlength) - length++; - return length; -} - -static inline unsigned long -utf16_strlen(efi_char16_t *s) -{ - return utf16_strnlen(s, ~0UL); -} - -/* - * Return the number of bytes is the length of this string - * Note: this is NOT the same as the number of unicode characters - */ -static inline unsigned long -utf16_strsize(efi_char16_t *data, unsigned long maxlength) -{ - return utf16_strnlen(data, maxlength/sizeof(efi_char16_t)) * sizeof(efi_char16_t); -} - -static inline int -utf16_strncmp(const efi_char16_t *a, const efi_char16_t *b, size_t len) -{ - while (1) { - if (len == 0) - return 0; - if (*a < *b) - return -1; - if (*a > *b) - return 1; - if (*a == 0) /* implies *b == 0 */ - return 0; - a++; - b++; - len--; - } -} - static bool validate_device_path(struct efi_variable *var, int match, u8 *buffer, unsigned long len) @@ -268,7 +224,7 @@ validate_load_option(struct efi_variable *var, int match, u8 *buffer, u16 filepathlength; int i, desclength = 0, namelen; - namelen = utf16_strnlen(var->VariableName, sizeof(var->VariableName)); + namelen = ucs2_strnlen(var->VariableName, sizeof(var->VariableName)); /* Either "Boot" or "Driver" followed by four digits of hex */ for (i = match; i < match+4; i++) { @@ -291,7 +247,7 @@ validate_load_option(struct efi_variable *var, int match, u8 *buffer, * There's no stored length for the description, so it has to be * found by hand */ - desclength = utf16_strsize((efi_char16_t *)(buffer + 6), len - 6) + 2; + desclength = ucs2_strsize((efi_char16_t *)(buffer + 6), len - 6) + 2; /* Each boot entry must have a descriptor */ if (!desclength) @@ -581,7 +537,7 @@ efivar_store_raw(struct efivar_entry *entry, const char *buf, size_t count) spin_lock_irq(&efivars->lock); status = check_var_size_locked(efivars, new_var->Attributes, - new_var->DataSize + utf16_strsize(new_var->VariableName, 1024)); + new_var->DataSize + ucs2_strsize(new_var->VariableName, 1024)); if (status == EFI_SUCCESS || status == EFI_UNSUPPORTED) status = efivars->ops->set_variable(new_var->VariableName, @@ -759,7 +715,7 @@ static ssize_t efivarfs_file_write(struct file *file, * QueryVariableInfo() isn't supported by the firmware. */ - varsize = datasize + utf16_strsize(var->var.VariableName, 1024); + varsize = datasize + ucs2_strsize(var->var.VariableName, 1024); status = check_var_size(efivars, attributes, varsize); if (status != EFI_SUCCESS) { @@ -1211,7 +1167,7 @@ static int efivarfs_fill_super(struct super_block *sb, void *data, int silent) inode = NULL; - len = utf16_strlen(entry->var.VariableName); + len = ucs2_strlen(entry->var.VariableName); /* name, plus '-', plus GUID, plus NUL*/ name = kmalloc(len + 1 + GUID_LEN + 1, GFP_ATOMIC); @@ -1469,8 +1425,8 @@ static int efi_pstore_erase(enum pstore_type_id type, u64 id, int count, if (efi_guidcmp(entry->var.VendorGuid, vendor)) continue; - if (utf16_strncmp(entry->var.VariableName, efi_name, - utf16_strlen(efi_name))) { + if (ucs2_strncmp(entry->var.VariableName, efi_name, + ucs2_strlen(efi_name))) { /* * Check if an old format, * which doesn't support holding @@ -1482,8 +1438,8 @@ static int efi_pstore_erase(enum pstore_type_id type, u64 id, int count, for (i = 0; i < DUMP_NAME_LEN; i++) efi_name_old[i] = name_old[i]; - if (utf16_strncmp(entry->var.VariableName, efi_name_old, - utf16_strlen(efi_name_old))) + if (ucs2_strncmp(entry->var.VariableName, efi_name_old, + ucs2_strlen(efi_name_old))) continue; } @@ -1561,8 +1517,8 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj, * Does this variable already exist? */ list_for_each_entry_safe(search_efivar, n, &efivars->list, list) { - strsize1 = utf16_strsize(search_efivar->var.VariableName, 1024); - strsize2 = utf16_strsize(new_var->VariableName, 1024); + strsize1 = ucs2_strsize(search_efivar->var.VariableName, 1024); + strsize2 = ucs2_strsize(new_var->VariableName, 1024); if (strsize1 == strsize2 && !memcmp(&(search_efivar->var.VariableName), new_var->VariableName, strsize1) && @@ -1578,7 +1534,7 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj, } status = check_var_size_locked(efivars, new_var->Attributes, - new_var->DataSize + utf16_strsize(new_var->VariableName, 1024)); + new_var->DataSize + ucs2_strsize(new_var->VariableName, 1024)); if (status && status != EFI_UNSUPPORTED) { spin_unlock_irq(&efivars->lock); @@ -1602,7 +1558,7 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj, /* Create the entry in sysfs. Locking is not required here */ status = efivar_create_sysfs_entry(efivars, - utf16_strsize(new_var->VariableName, + ucs2_strsize(new_var->VariableName, 1024), new_var->VariableName, &new_var->VendorGuid); @@ -1632,8 +1588,8 @@ static ssize_t efivar_delete(struct file *filp, struct kobject *kobj, * Does this variable already exist? */ list_for_each_entry_safe(search_efivar, n, &efivars->list, list) { - strsize1 = utf16_strsize(search_efivar->var.VariableName, 1024); - strsize2 = utf16_strsize(del_var->VariableName, 1024); + strsize1 = ucs2_strsize(search_efivar->var.VariableName, 1024); + strsize2 = ucs2_strsize(del_var->VariableName, 1024); if (strsize1 == strsize2 && !memcmp(&(search_efivar->var.VariableName), del_var->VariableName, strsize1) && @@ -1679,9 +1635,9 @@ static bool variable_is_present(efi_char16_t *variable_name, efi_guid_t *vendor) unsigned long strsize1, strsize2; bool found = false; - strsize1 = utf16_strsize(variable_name, 1024); + strsize1 = ucs2_strsize(variable_name, 1024); list_for_each_entry_safe(entry, n, &efivars->list, list) { - strsize2 = utf16_strsize(entry->var.VariableName, 1024); + strsize2 = ucs2_strsize(entry->var.VariableName, 1024); if (strsize1 == strsize2 && !memcmp(variable_name, &(entry->var.VariableName), strsize2) && diff --git a/include/linux/ucs2_string.h b/include/linux/ucs2_string.h new file mode 100644 index 00000000000..cbb20afdbc0 --- /dev/null +++ b/include/linux/ucs2_string.h @@ -0,0 +1,14 @@ +#ifndef _LINUX_UCS2_STRING_H_ +#define _LINUX_UCS2_STRING_H_ + +#include /* for size_t */ +#include /* for NULL */ + +typedef u16 ucs2_char_t; + +unsigned long ucs2_strnlen(const ucs2_char_t *s, size_t maxlength); +unsigned long ucs2_strlen(const ucs2_char_t *s); +unsigned long ucs2_strsize(const ucs2_char_t *data, unsigned long maxlength); +int ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len); + +#endif /* _LINUX_UCS2_STRING_H_ */ diff --git a/lib/Kconfig b/lib/Kconfig index 3958dc4389f..fe01d418b09 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -404,4 +404,7 @@ config OID_REGISTRY help Enable fast lookup object identifier registry. +config UCS2_STRING + tristate + endmenu diff --git a/lib/Makefile b/lib/Makefile index d7946ff75b2..6e2cc561f76 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -174,3 +174,5 @@ quiet_cmd_build_OID_registry = GEN $@ cmd_build_OID_registry = perl $(srctree)/$(src)/build_OID_registry $< $@ clean-files += oid_registry_data.c + +obj-$(CONFIG_UCS2_STRING) += ucs2_string.o diff --git a/lib/ucs2_string.c b/lib/ucs2_string.c new file mode 100644 index 00000000000..6f500ef2301 --- /dev/null +++ b/lib/ucs2_string.c @@ -0,0 +1,51 @@ +#include +#include + +/* Return the number of unicode characters in data */ +unsigned long +ucs2_strnlen(const ucs2_char_t *s, size_t maxlength) +{ + unsigned long length = 0; + + while (*s++ != 0 && length < maxlength) + length++; + return length; +} +EXPORT_SYMBOL(ucs2_strnlen); + +unsigned long +ucs2_strlen(const ucs2_char_t *s) +{ + return ucs2_strnlen(s, ~0UL); +} +EXPORT_SYMBOL(ucs2_strlen); + +/* + * Return the number of bytes is the length of this string + * Note: this is NOT the same as the number of unicode characters + */ +unsigned long +ucs2_strsize(const ucs2_char_t *data, unsigned long maxlength) +{ + return ucs2_strnlen(data, maxlength/sizeof(ucs2_char_t)) * sizeof(ucs2_char_t); +} +EXPORT_SYMBOL(ucs2_strsize); + +int +ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len) +{ + while (1) { + if (len == 0) + return 0; + if (*a < *b) + return -1; + if (*a > *b) + return 1; + if (*a == 0) /* implies *b == 0 */ + return 0; + a++; + b++; + len--; + } +} +EXPORT_SYMBOL(ucs2_strncmp); -- cgit v1.2.3-70-g09d2 From c729de8fcea37a1c444e81857eace12494c804a9 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 15 Apr 2013 22:23:45 -0700 Subject: x86, kdump: Set crashkernel_low automatically Chao said that kdump does does work well on his system on 3.8 without extra parameter, even iommu does not work with kdump. And now have to append crashkernel_low=Y in first kernel to make kdump work. We have now modified crashkernel=X to allocate memory beyong 4G (if available) and do not allocate low range for crashkernel if the user does not specify that with crashkernel_low=Y. This causes regression if iommu is not enabled. Without iommu, swiotlb needs to be setup in first 4G and there is no low memory available to second kernel. Set crashkernel_low automatically if the user does not specify that. For system that does support IOMMU with kdump properly, user could specify crashkernel_low=0 to save that 72M low ram. -v3: add swiotlb_size() according to Konrad. -v4: add comments what 8M is for according to hpa. also update more crashkernel_low= in kernel-parameters.txt -v5: update changelog according to Vivek. -v6: Change description about swiotlb referring according to HATAYAMA. Reported-by: WANG Chao Tested-by: WANG Chao Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1366089828-19692-2-git-send-email-yinghai@kernel.org Acked-by: Vivek Goyal Signed-off-by: H. Peter Anvin --- Documentation/kernel-parameters.txt | 14 +++++++++++--- arch/x86/kernel/setup.c | 21 ++++++++++++++++++--- include/linux/swiotlb.h | 1 + lib/swiotlb.c | 19 +++++++++++++++---- 4 files changed, 45 insertions(+), 10 deletions(-) (limited to 'lib') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 4609e81dbc3..cff672da248 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -596,9 +596,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted. is selected automatically. Check Documentation/kdump/kdump.txt for further details. - crashkernel_low=size[KMG] - [KNL, x86] parts under 4G. - crashkernel=range1:size1[,range2:size2,...][@offset] [KNL] Same as above, but depends on the memory in the running system. The syntax of range is @@ -606,6 +603,17 @@ bytes respectively. Such letter suffixes can also be entirely omitted. a memory unit (amount[KMG]). See also Documentation/kdump/kdump.txt for an example. + crashkernel_low=size[KMG] + [KNL, x86_64] range under 4G. When crashkernel= is + passed, kernel allocate physical memory region + above 4G, that cause second kernel crash on system + that require some amount of low memory, e.g. swiotlb + requires at least 64M+32K low memory. Kernel would + try to allocate 72M below 4G automatically. + This one let user to specify own low range under 4G + for second kernel instead. + 0: to disable low allocation. + cs89x0_dma= [HW,NET] Format: diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 90d8cc930f5..12349202cae 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -521,19 +521,34 @@ static void __init reserve_crashkernel_low(void) unsigned long long low_base = 0, low_size = 0; unsigned long total_low_mem; unsigned long long base; + bool auto_set = false; int ret; total_low_mem = memblock_mem_size(1UL<<(32-PAGE_SHIFT)); ret = parse_crashkernel_low(boot_command_line, total_low_mem, &low_size, &base); - if (ret != 0 || low_size <= 0) - return; + if (ret != 0) { + /* + * two parts from lib/swiotlb.c: + * swiotlb size: user specified with swiotlb= or default. + * swiotlb overflow buffer: now is hardcoded to 32k. + * We round it to 8M for other buffers that + * may need to stay low too. + */ + low_size = swiotlb_size_or_default() + (8UL<<20); + auto_set = true; + } else { + /* passed with crashkernel_low=0 ? */ + if (!low_size) + return; + } low_base = memblock_find_in_range(low_size, (1ULL<<32), low_size, alignment); if (!low_base) { - pr_info("crashkernel low reservation failed - No suitable area found.\n"); + if (!auto_set) + pr_info("crashkernel low reservation failed - No suitable area found.\n"); return; } diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 2de42f9401d..a5ffd32642f 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -25,6 +25,7 @@ extern int swiotlb_force; extern void swiotlb_init(int verbose); int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose); extern unsigned long swiotlb_nr_tbl(void); +unsigned long swiotlb_size_or_default(void); extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); /* diff --git a/lib/swiotlb.c b/lib/swiotlb.c index bfe02b8fc55..d23762e6652 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -105,9 +105,9 @@ setup_io_tlb_npages(char *str) if (!strcmp(str, "force")) swiotlb_force = 1; - return 1; + return 0; } -__setup("swiotlb=", setup_io_tlb_npages); +early_param("swiotlb", setup_io_tlb_npages); /* make io_tlb_overflow tunable too? */ unsigned long swiotlb_nr_tbl(void) @@ -115,6 +115,18 @@ unsigned long swiotlb_nr_tbl(void) return io_tlb_nslabs; } EXPORT_SYMBOL_GPL(swiotlb_nr_tbl); + +/* default to 64MB */ +#define IO_TLB_DEFAULT_SIZE (64UL<<20) +unsigned long swiotlb_size_or_default(void) +{ + unsigned long size; + + size = io_tlb_nslabs << IO_TLB_SHIFT; + + return size ? size : (IO_TLB_DEFAULT_SIZE); +} + /* Note that this doesn't work with highmem page */ static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev, volatile void *address) @@ -188,8 +200,7 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) void __init swiotlb_init(int verbose) { - /* default to 64MB */ - size_t default_size = 64UL<<20; + size_t default_size = IO_TLB_DEFAULT_SIZE; unsigned char *vstart; unsigned long bytes; -- cgit v1.2.3-70-g09d2 From 4b59e6c4730978679b414a8da61514a2518da512 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 29 Apr 2013 15:06:11 -0700 Subject: mm, show_mem: suppress page counts in non-blockable contexts On large systems with a lot of memory, walking all RAM to determine page types may take a half second or even more. In non-blockable contexts, the page allocator will emit a page allocation failure warning unless __GFP_NOWARN is specified. In such contexts, irqs are typically disabled and such a lengthy delay may even result in NMI watchdog timeouts. To fix this, suppress the page walk in such contexts when printing the page allocation failure warning. Signed-off-by: David Rientjes Cc: Mel Gorman Acked-by: Michal Hocko Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/mm/init.c | 3 +++ arch/ia64/mm/contig.c | 2 ++ arch/ia64/mm/discontig.c | 2 ++ arch/parisc/mm/init.c | 2 ++ arch/unicore32/mm/init.c | 3 +++ include/linux/mm.h | 3 ++- lib/show_mem.c | 3 +++ mm/page_alloc.c | 7 +++++++ 8 files changed, 24 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index ad722f1208a..ad9a9f3f032 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -99,6 +99,9 @@ void show_mem(unsigned int filter) printk("Mem-info:\n"); show_free_areas(filter); + if (filter & SHOW_MEM_FILTER_PAGE_COUNT) + return; + for_each_bank (i, mi) { struct membank *bank = &mi->bank[i]; unsigned int pfn1, pfn2; diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c index 80dab509dfb..67c59ebec89 100644 --- a/arch/ia64/mm/contig.c +++ b/arch/ia64/mm/contig.c @@ -47,6 +47,8 @@ void show_mem(unsigned int filter) printk(KERN_INFO "Mem-info:\n"); show_free_areas(filter); printk(KERN_INFO "Node memory in pages:\n"); + if (filter & SHOW_MEM_FILTER_PAGE_COUNT) + return; for_each_online_pgdat(pgdat) { unsigned long present; unsigned long flags; diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index c2e955ee79a..a57436e5d40 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -623,6 +623,8 @@ void show_mem(unsigned int filter) printk(KERN_INFO "Mem-info:\n"); show_free_areas(filter); + if (filter & SHOW_MEM_FILTER_PAGE_COUNT) + return; printk(KERN_INFO "Node memory in pages:\n"); for_each_online_pgdat(pgdat) { unsigned long present; diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 3ac462de53a..cf2da13c41e 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -697,6 +697,8 @@ void show_mem(unsigned int filter) printk(KERN_INFO "Mem-info:\n"); show_free_areas(filter); + if (filter & SHOW_MEM_FILTER_PAGE_COUNT) + return; #ifndef CONFIG_DISCONTIGMEM i = max_mapnr; while (i-- > 0) { diff --git a/arch/unicore32/mm/init.c b/arch/unicore32/mm/init.c index de186bde897..644482882ba 100644 --- a/arch/unicore32/mm/init.c +++ b/arch/unicore32/mm/init.c @@ -66,6 +66,9 @@ void show_mem(unsigned int filter) printk(KERN_DEFAULT "Mem-info:\n"); show_free_areas(filter); + if (filter & SHOW_MEM_FILTER_PAGE_COUNT) + return; + for_each_bank(i, mi) { struct membank *bank = &mi->bank[i]; unsigned int pfn1, pfn2; diff --git a/include/linux/mm.h b/include/linux/mm.h index e2091b88d24..f3c7b1f9d1d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -899,7 +899,8 @@ extern void pagefault_out_of_memory(void); * Flags passed to show_mem() and show_free_areas() to suppress output in * various contexts. */ -#define SHOW_MEM_FILTER_NODES (0x0001u) /* filter disallowed nodes */ +#define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */ +#define SHOW_MEM_FILTER_PAGE_COUNT (0x0002u) /* page type count */ extern void show_free_areas(unsigned int flags); extern bool skip_free_areas_node(unsigned int flags, int nid); diff --git a/lib/show_mem.c b/lib/show_mem.c index 4407f8c9b1f..b7c72311ad0 100644 --- a/lib/show_mem.c +++ b/lib/show_mem.c @@ -18,6 +18,9 @@ void show_mem(unsigned int filter) printk("Mem-Info:\n"); show_free_areas(filter); + if (filter & SHOW_MEM_FILTER_PAGE_COUNT) + return; + for_each_online_pgdat(pgdat) { unsigned long i, flags; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7ff1536f01b..da7a2fe7332 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2002,6 +2002,13 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...) debug_guardpage_minorder() > 0) return; + /* + * Walking all memory to count page types is very expensive and should + * be inhibited in non-blockable contexts. + */ + if (!(gfp_mask & __GFP_WAIT)) + filter |= SHOW_MEM_FILTER_PAGE_COUNT; + /* * This documents exceptions given to allocations in certain * contexts that are allowed to allocate outside current's set -- cgit v1.2.3-70-g09d2 From 9375db07adeaeea5f5ea7ca0463a8b371d71ddbb Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Mon, 29 Apr 2013 16:17:10 -0700 Subject: genalloc: add devres support, allow to find a managed pool by device This patch adds three exported functions to lib/genalloc.c: devm_gen_pool_create, dev_get_gen_pool, and of_get_named_gen_pool. devm_gen_pool_create is a managed version of gen_pool_create that keeps track of the pool via devres and allows the management code to automatically destroy it after device removal. dev_get_gen_pool retrieves the gen_pool for a given device, if it was created with devm_gen_pool_create, using devres_find. of_get_named_gen_pool retrieves the gen_pool for a given device node and property name, where the property must contain a phandle pointing to a platform device node. The corresponding platform device is then fed into dev_get_gen_pool and the resulting gen_pool is returned. [akpm@linux-foundation.org: make the of_get_named_gen_pool() stub static, fixing a zillion link errors] [akpm@linux-foundation.org: squish "struct device declared inside parameter list" warning] Signed-off-by: Philipp Zabel Acked-by: Grant Likely Tested-by: Michal Simek Cc: Fabio Estevam Cc: Matt Porter Cc: Dong Aisheng Cc: Greg Kroah-Hartman Cc: Rob Herring Cc: Paul Gortmaker Cc: Javier Martin Cc: Huang Shijie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/genalloc.h | 18 +++++++++++ lib/genalloc.c | 81 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 99 insertions(+) (limited to 'lib') diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index dd7c569aaca..661d374aeb2 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -29,6 +29,10 @@ #ifndef __GENALLOC_H__ #define __GENALLOC_H__ + +struct device; +struct device_node; + /** * Allocation callback function type definition * @map: Pointer to bitmap @@ -105,4 +109,18 @@ extern unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size, extern unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, void *data); +extern struct gen_pool *devm_gen_pool_create(struct device *dev, + int min_alloc_order, int nid); +extern struct gen_pool *dev_get_gen_pool(struct device *dev); + +#ifdef CONFIG_OF +extern struct gen_pool *of_get_named_gen_pool(struct device_node *np, + const char *propname, int index); +#else +static inline struct gen_pool *of_get_named_gen_pool(struct device_node *np, + const char *propname, int index) +{ + return NULL; +} +#endif #endif /* __GENALLOC_H__ */ diff --git a/lib/genalloc.c b/lib/genalloc.c index 54920433705..b35cfa9bc3d 100644 --- a/lib/genalloc.c +++ b/lib/genalloc.c @@ -34,6 +34,8 @@ #include #include #include +#include +#include static int set_bits_ll(unsigned long *addr, unsigned long mask_to_set) { @@ -480,3 +482,82 @@ unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size, return start_bit; } EXPORT_SYMBOL(gen_pool_best_fit); + +static void devm_gen_pool_release(struct device *dev, void *res) +{ + gen_pool_destroy(*(struct gen_pool **)res); +} + +/** + * devm_gen_pool_create - managed gen_pool_create + * @dev: device that provides the gen_pool + * @min_alloc_order: log base 2 of number of bytes each bitmap bit represents + * @nid: node id of the node the pool structure should be allocated on, or -1 + * + * Create a new special memory pool that can be used to manage special purpose + * memory not managed by the regular kmalloc/kfree interface. The pool will be + * automatically destroyed by the device management code. + */ +struct gen_pool *devm_gen_pool_create(struct device *dev, int min_alloc_order, + int nid) +{ + struct gen_pool **ptr, *pool; + + ptr = devres_alloc(devm_gen_pool_release, sizeof(*ptr), GFP_KERNEL); + + pool = gen_pool_create(min_alloc_order, nid); + if (pool) { + *ptr = pool; + devres_add(dev, ptr); + } else { + devres_free(ptr); + } + + return pool; +} + +/** + * dev_get_gen_pool - Obtain the gen_pool (if any) for a device + * @dev: device to retrieve the gen_pool from + * @name: Optional name for the gen_pool, usually NULL + * + * Returns the gen_pool for the device if one is present, or NULL. + */ +struct gen_pool *dev_get_gen_pool(struct device *dev) +{ + struct gen_pool **p = devres_find(dev, devm_gen_pool_release, NULL, + NULL); + + if (!p) + return NULL; + return *p; +} +EXPORT_SYMBOL_GPL(dev_get_gen_pool); + +#ifdef CONFIG_OF +/** + * of_get_named_gen_pool - find a pool by phandle property + * @np: device node + * @propname: property name containing phandle(s) + * @index: index into the phandle array + * + * Returns the pool that contains the chunk starting at the physical + * address of the device tree node pointed at by the phandle property, + * or NULL if not found. + */ +struct gen_pool *of_get_named_gen_pool(struct device_node *np, + const char *propname, int index) +{ + struct platform_device *pdev; + struct device_node *np_pool; + + np_pool = of_parse_phandle(np, propname, index); + if (!np_pool) + return NULL; + pdev = of_find_device_by_node(np_pool); + if (!pdev) + return NULL; + return dev_get_gen_pool(&pdev->dev); +} +EXPORT_SYMBOL_GPL(of_get_named_gen_pool); +#endif /* CONFIG_OF */ -- cgit v1.2.3-70-g09d2 From 30493cc9dddb68066dcc4878015660fdaa8e0965 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Mon, 29 Apr 2013 16:18:09 -0700 Subject: lib/int_sqrt.c: optimize square root algorithm Optimize the current version of the shift-and-subtract (hardware) algorithm, described by John von Newmann[1] and Guy L Steele. Iterating 1,000,000 times, perf shows for the current version: Performance counter stats for './sqrt-curr' (10 runs): 27.170996 task-clock # 0.979 CPUs utilized ( +- 3.19% ) 3 context-switches # 0.103 K/sec ( +- 4.76% ) 0 cpu-migrations # 0.004 K/sec ( +-100.00% ) 104 page-faults # 0.004 M/sec ( +- 0.16% ) 64,921,199 cycles # 2.389 GHz ( +- 0.03% ) 28,967,789 stalled-cycles-frontend # 44.62% frontend cycles idle ( +- 0.18% ) stalled-cycles-backend 104,502,623 instructions # 1.61 insns per cycle # 0.28 stalled cycles per insn ( +- 0.00% ) 34,088,368 branches # 1254.587 M/sec ( +- 0.00% ) 4,901 branch-misses # 0.01% of all branches ( +- 1.32% ) 0.027763015 seconds time elapsed ( +- 3.22% ) And for the new version: Performance counter stats for './sqrt-new' (10 runs): 0.496869 task-clock # 0.519 CPUs utilized ( +- 2.38% ) 0 context-switches # 0.000 K/sec 0 cpu-migrations # 0.403 K/sec ( +-100.00% ) 104 page-faults # 0.209 M/sec ( +- 0.15% ) 590,760 cycles # 1.189 GHz ( +- 2.35% ) 395,053 stalled-cycles-frontend # 66.87% frontend cycles idle ( +- 3.67% ) stalled-cycles-backend 398,963 instructions # 0.68 insns per cycle # 0.99 stalled cycles per insn ( +- 0.39% ) 70,228 branches # 141.341 M/sec ( +- 0.36% ) 3,364 branch-misses # 4.79% of all branches ( +- 5.45% ) 0.000957440 seconds time elapsed ( +- 2.42% ) Furthermore, this saves space in instruction text: text data bss dec hex filename 111 0 0 111 6f lib/int_sqrt-baseline.o 89 0 0 89 59 lib/int_sqrt.o [1] http://en.wikipedia.org/wiki/First_Draft_of_a_Report_on_the_EDVAC Signed-off-by: Davidlohr Bueso Reviewed-by: Jonathan Gonzalez Tested-by: Jonathan Gonzalez Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/int_sqrt.c | 32 +++++++++++++++++++------------- 1 file changed, 19 insertions(+), 13 deletions(-) (limited to 'lib') diff --git a/lib/int_sqrt.c b/lib/int_sqrt.c index fc2eeb7cb2e..1ef4cc34497 100644 --- a/lib/int_sqrt.c +++ b/lib/int_sqrt.c @@ -1,3 +1,9 @@ +/* + * Copyright (C) 2013 Davidlohr Bueso + * + * Based on the shift-and-subtract algorithm for computing integer + * square root from Guy L. Steele. + */ #include #include @@ -10,23 +16,23 @@ */ unsigned long int_sqrt(unsigned long x) { - unsigned long op, res, one; + unsigned long b, m, y = 0; - op = x; - res = 0; + if (x <= 1) + return x; - one = 1UL << (BITS_PER_LONG - 2); - while (one > op) - one >>= 2; + m = 1UL << (BITS_PER_LONG - 2); + while (m != 0) { + b = y + m; + y >>= 1; - while (one != 0) { - if (op >= res + one) { - op = op - (res + one); - res = res + 2 * one; + if (x >= b) { + x -= b; + y += m; } - res /= 2; - one /= 4; + m >>= 2; } - return res; + + return y; } EXPORT_SYMBOL(int_sqrt); -- cgit v1.2.3-70-g09d2 From 095d141b2e40665289d44a42d387ffac2841ef82 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 29 Apr 2013 16:18:10 -0700 Subject: argv_split(): teach it to handle mutable strings argv_split() allocates argv[count_argc(str)] array and assumes that it will find the same number of arguments later. This is obviously wrong if this string can be changed, say, by sysctl. With this patch argv_split() kstrndup's the whole string and does not split it, we simply replace the spaces with zeroes and keep the allocated memory in argv[-1] for argv_free(arg). We do not use argv[0] because: - str can be all-spaces or empty. In fact this case is fine, we could kfree() it before return, but: - str can have a space at the start, and we can not rely on kstrndup(skip_spaces(str)) because it can equally race if this string is mutable. Also, simplify count_argc() and kill the no longer used skip_arg(). Signed-off-by: Oleg Nesterov Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/argv_split.c | 87 ++++++++++++++++++++++++++------------------------------ 1 file changed, 40 insertions(+), 47 deletions(-) (limited to 'lib') diff --git a/lib/argv_split.c b/lib/argv_split.c index 1e9a6cbc368..e927ed0e18a 100644 --- a/lib/argv_split.c +++ b/lib/argv_split.c @@ -8,23 +8,17 @@ #include #include -static const char *skip_arg(const char *cp) -{ - while (*cp && !isspace(*cp)) - cp++; - - return cp; -} - static int count_argc(const char *str) { int count = 0; + bool was_space; - while (*str) { - str = skip_spaces(str); - if (*str) { + for (was_space = true; *str; str++) { + if (isspace(*str)) { + was_space = true; + } else if (was_space) { + was_space = false; count++; - str = skip_arg(str); } } @@ -39,10 +33,8 @@ static int count_argc(const char *str) */ void argv_free(char **argv) { - char **p; - for (p = argv; *p; p++) - kfree(*p); - + argv--; + kfree(argv[0]); kfree(argv); } EXPORT_SYMBOL(argv_free); @@ -59,43 +51,44 @@ EXPORT_SYMBOL(argv_free); * considered to be a single argument separator. The returned array * is always NULL-terminated. Returns NULL on memory allocation * failure. + * + * The source string at `str' may be undergoing concurrent alteration via + * userspace sysctl activity (at least). The argv_split() implementation + * attempts to handle this gracefully by taking a local copy to work on. */ char **argv_split(gfp_t gfp, const char *str, int *argcp) { - int argc = count_argc(str); - char **argv = kzalloc(sizeof(*argv) * (argc+1), gfp); - char **argvp; - - if (argv == NULL) - goto out; - - if (argcp) - *argcp = argc; - - argvp = argv; - - while (*str) { - str = skip_spaces(str); - - if (*str) { - const char *p = str; - char *t; - - str = skip_arg(str); + char *argv_str; + bool was_space; + char **argv, **argv_ret; + int argc; + + argv_str = kstrndup(str, KMALLOC_MAX_SIZE - 1, gfp); + if (!argv_str) + return NULL; + + argc = count_argc(argv_str); + argv = kmalloc(sizeof(*argv) * (argc + 2), gfp); + if (!argv) { + kfree(argv_str); + return NULL; + } - t = kstrndup(p, str-p, gfp); - if (t == NULL) - goto fail; - *argvp++ = t; + *argv = argv_str; + argv_ret = ++argv; + for (was_space = true; *argv_str; argv_str++) { + if (isspace(*argv_str)) { + was_space = true; + *argv_str = 0; + } else if (was_space) { + was_space = false; + *argv++ = argv_str; } } - *argvp = NULL; - - out: - return argv; + *argv = NULL; - fail: - argv_free(argv); - return NULL; + if (argcp) + *argcp = argc; + return argv_ret; } EXPORT_SYMBOL(argv_split); -- cgit v1.2.3-70-g09d2 From 2e0fb404c86d6c86dc33e284310eb5d28d192dcf Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 29 Apr 2013 16:18:11 -0700 Subject: lib, net: make isodigit() public and use it There are at least two users of isodigit(). Let's make it a public function of ctype.h. Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ctype.h | 6 ++++++ lib/dynamic_debug.c | 1 - net/sunrpc/cache.c | 1 - 3 files changed, 6 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/include/linux/ctype.h b/include/linux/ctype.h index 8acfe312f94..653589e3e30 100644 --- a/include/linux/ctype.h +++ b/include/linux/ctype.h @@ -61,4 +61,10 @@ static inline char _tolower(const char c) return c | 0x20; } +/* Fast check for octal digit */ +static inline int isodigit(const char c) +{ + return c >= '0' && c <= '7'; +} + #endif diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c index 5276b99ca65..46032453abd 100644 --- a/lib/dynamic_debug.c +++ b/lib/dynamic_debug.c @@ -281,7 +281,6 @@ static inline int parse_lineno(const char *str, unsigned int *val) * allow the user to express a query which matches a format * containing embedded spaces. */ -#define isodigit(c) ((c) >= '0' && (c) <= '7') static char *unescape(char *str) { char *in = str; diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 25d58e76601..ce2d180d05a 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1208,7 +1208,6 @@ EXPORT_SYMBOL_GPL(sunrpc_cache_pipe_upcall); * key and content are both parsed by cache */ -#define isodigit(c) (isdigit(c) && c <= '7') int qword_get(char **bpp, char *dest, int bufsize) { /* return bytes copied, or -1 on error */ -- cgit v1.2.3-70-g09d2 From 3e6628c4b347a558965041290c5a92791dd4c741 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 29 Apr 2013 16:21:16 -0700 Subject: idr: introduce idr_alloc_cyclic() As Tejun points out, there are several users of the IDR facility that attempt to use it in a cyclic fashion. These users are likely to see -ENOSPC errors after the counter wraps one or more times however. This patchset adds a new idr_alloc_cyclic routine and converts several of these users to it. Many of these users are in obscure parts of the kernel, and I don't have a good way to test some of them. The change is pretty straightforward though, so hopefully it won't be an issue. There is one other cyclic user of idr_alloc that I didn't touch in ipc/util.c. That one is doing some strange stuff that I didn't quite understand, but it looks like it should probably be converted later somehow. This patch: Thus spake Tejun Heo: Ooh, BTW, the cyclic allocation is broken. It's prone to -ENOSPC after the first wraparound. There are several cyclic users in the kernel and I think it probably would be best to implement cyclic support in idr. This patch does that by adding new idr_alloc_cyclic function that such users in the kernel can use. With this, there's no need for a caller to keep track of the last value used as that's now tracked internally. This should prevent the ENOSPC problems that can hit when the "last allocated" counter exceeds INT_MAX. Later patches will convert existing cyclic users to the new interface. Signed-off-by: Jeff Layton Reviewed-by: Tejun Heo Cc: "David S. Miller" Cc: "J. Bruce Fields" Cc: Eric Paris Cc: Jack Morgenstein Cc: John McCutchan Cc: Neil Horman Cc: Or Gerlitz Cc: Robert Love Cc: Roland Dreier Cc: Sridhar Samudrala Cc: Steve Wise Cc: Tom Tucker Cc: Vlad Yasevich Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 2 ++ lib/idr.c | 27 +++++++++++++++++++++++++++ 2 files changed, 29 insertions(+) (limited to 'lib') diff --git a/include/linux/idr.h b/include/linux/idr.h index 2640c7e99e5..a470ac3ef49 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -42,6 +42,7 @@ struct idr { struct idr_layer *id_free; int layers; /* only valid w/o concurrent changes */ int id_free_cnt; + int cur; /* current pos for cyclic allocation */ spinlock_t lock; }; @@ -75,6 +76,7 @@ struct idr { void *idr_find_slowpath(struct idr *idp, int id); void idr_preload(gfp_t gfp_mask); int idr_alloc(struct idr *idp, void *ptr, int start, int end, gfp_t gfp_mask); +int idr_alloc_cyclic(struct idr *idr, void *ptr, int start, int end, gfp_t gfp_mask); int idr_for_each(struct idr *idp, int (*fn)(int id, void *p, void *data), void *data); void *idr_get_next(struct idr *idp, int *nextid); diff --git a/lib/idr.c b/lib/idr.c index 322e2816f2f..cca4b9302a7 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -495,6 +495,33 @@ int idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp_mask) } EXPORT_SYMBOL_GPL(idr_alloc); +/** + * idr_alloc_cyclic - allocate new idr entry in a cyclical fashion + * @idr: the (initialized) idr + * @ptr: pointer to be associated with the new id + * @start: the minimum id (inclusive) + * @end: the maximum id (exclusive, <= 0 for max) + * @gfp_mask: memory allocation flags + * + * Essentially the same as idr_alloc, but prefers to allocate progressively + * higher ids if it can. If the "cur" counter wraps, then it will start again + * at the "start" end of the range and allocate one that has already been used. + */ +int idr_alloc_cyclic(struct idr *idr, void *ptr, int start, int end, + gfp_t gfp_mask) +{ + int id; + + id = idr_alloc(idr, ptr, max(start, idr->cur), end, gfp_mask); + if (id == -ENOSPC) + id = idr_alloc(idr, ptr, start, end, gfp_mask); + + if (likely(id >= 0)) + idr->cur = id + 1; + return id; +} +EXPORT_SYMBOL(idr_alloc_cyclic); + static void idr_remove_warning(int id) { printk(KERN_WARNING -- cgit v1.2.3-70-g09d2 From cedddb00023b1321f2bb2739739aa8c9927fc063 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Mon, 29 Apr 2013 16:21:25 -0700 Subject: uuid: use prandom_bytes() Use prandom_bytes() to generate 16 bytes of pseudo-random bytes. Signed-off-by: Akinobu Mita Cc: "Theodore Ts'o" Cc: Huang Ying Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/uuid.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'lib') diff --git a/lib/uuid.c b/lib/uuid.c index 52a6fe6387d..398821e4dce 100644 --- a/lib/uuid.c +++ b/lib/uuid.c @@ -25,13 +25,7 @@ static void __uuid_gen_common(__u8 b[16]) { - int i; - u32 r; - - for (i = 0; i < 4; i++) { - r = random32(); - memcpy(b + i * 4, &r, 4); - } + prandom_bytes(b, 16); /* reversion 0b10 */ b[8] = (b[8] & 0x3F) | 0x80; } -- cgit v1.2.3-70-g09d2 From f39fee5f11f7adfcf5c9643f87718b80450be18a Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Mon, 29 Apr 2013 16:21:28 -0700 Subject: lib/: rename random32() to prandom_u32() Use preferable function name which implies using a pseudo-random number generator. Signed-off-by: Akinobu Mita Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/fault-inject.c | 2 +- lib/list_sort.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/fault-inject.c b/lib/fault-inject.c index f7210ad6cff..c5c7a762b85 100644 --- a/lib/fault-inject.c +++ b/lib/fault-inject.c @@ -122,7 +122,7 @@ bool should_fail(struct fault_attr *attr, ssize_t size) return false; } - if (attr->probability <= random32() % 100) + if (attr->probability <= prandom_u32() % 100) return false; if (!fail_stacktrace(attr)) diff --git a/lib/list_sort.c b/lib/list_sort.c index d7325c6b103..1183fa70a44 100644 --- a/lib/list_sort.c +++ b/lib/list_sort.c @@ -229,7 +229,7 @@ static int __init list_sort_test(void) goto exit; } /* force some equivalencies */ - el->value = random32() % (TEST_LIST_LEN/3); + el->value = prandom_u32() % (TEST_LIST_LEN / 3); el->serial = i; el->poison1 = TEST_POISON1; el->poison2 = TEST_POISON2; -- cgit v1.2.3-70-g09d2