diff options
Diffstat (limited to '')
| -rw-r--r-- | kernel/cpuset.c | 25 | ||||
| -rw-r--r-- | kernel/extable.c | 2 | ||||
| -rw-r--r-- | kernel/module.c | 12 | ||||
| -rw-r--r-- | kernel/rcupdate.c | 19 | ||||
| -rw-r--r-- | kernel/timer.c | 16 |
5 files changed, 58 insertions, 16 deletions
diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 72248d1b9e3f..ab81fdd4572b 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2231,19 +2231,25 @@ static const struct cpuset *nearest_exclusive_ancestor(const struct cpuset *cs) * So only GFP_KERNEL allocations, if all nodes in the cpuset are * short of memory, might require taking the callback_mutex mutex. * - * The first loop over the zonelist in mm/page_alloc.c:__alloc_pages() - * calls here with __GFP_HARDWALL always set in gfp_mask, enforcing - * hardwall cpusets - no allocation on a node outside the cpuset is - * allowed (unless in interrupt, of course). - * - * The second loop doesn't even call here for GFP_ATOMIC requests - * (if the __alloc_pages() local variable 'wait' is set). That check - * and the checks below have the combined affect in the second loop of - * the __alloc_pages() routine that: + * The first call here from mm/page_alloc:get_page_from_freelist() + * has __GFP_HARDWALL set in gfp_mask, enforcing hardwall cpusets, so + * no allocation on a node outside the cpuset is allowed (unless in + * interrupt, of course). + * + * The second pass through get_page_from_freelist() doesn't even call + * here for GFP_ATOMIC calls. For those calls, the __alloc_pages() + * variable 'wait' is not set, and the bit ALLOC_CPUSET is not set + * in alloc_flags. That logic and the checks below have the combined + * affect that: * in_interrupt - any node ok (current task context irrelevant) * GFP_ATOMIC - any node ok * GFP_KERNEL - any node in enclosing mem_exclusive cpuset ok * GFP_USER - only nodes in current tasks mems allowed ok. + * + * Rule: + * Don't call cpuset_zone_allowed() if you can't sleep, unless you + * pass in the __GFP_HARDWALL flag set in gfp_flag, which disables + * the code that might scan up ancestor cpusets and sleep. **/ int __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) @@ -2255,6 +2261,7 @@ int __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) if (in_interrupt()) return 1; node = z->zone_pgdat->node_id; + might_sleep_if(!(gfp_mask & __GFP_HARDWALL)); if (node_isset(node, current->mems_allowed)) return 1; if (gfp_mask & __GFP_HARDWALL) /* If hardwall request, stop here */ diff --git a/kernel/extable.c b/kernel/extable.c index 7501b531ceed..7fe262855317 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -40,7 +40,7 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr) return e; } -static int core_kernel_text(unsigned long addr) +int core_kernel_text(unsigned long addr) { if (addr >= (unsigned long)_stext && addr <= (unsigned long)_etext) diff --git a/kernel/module.c b/kernel/module.c index d24deb0dbbc9..bbe04862e1b0 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -705,14 +705,14 @@ EXPORT_SYMBOL(__symbol_put); void symbol_put_addr(void *addr) { - unsigned long flags; + struct module *modaddr; - spin_lock_irqsave(&modlist_lock, flags); - if (!kernel_text_address((unsigned long)addr)) - BUG(); + if (core_kernel_text((unsigned long)addr)) + return; - module_put(module_text_address((unsigned long)addr)); - spin_unlock_irqrestore(&modlist_lock, flags); + if (!(modaddr = module_text_address((unsigned long)addr))) + BUG(); + module_put(modaddr); } EXPORT_SYMBOL_GPL(symbol_put_addr); diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 6d32ff26f948..2058f88c7bbb 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -479,12 +479,31 @@ static int __rcu_pending(struct rcu_ctrlblk *rcp, struct rcu_data *rdp) return 0; } +/* + * Check to see if there is any immediate RCU-related work to be done + * by the current CPU, returning 1 if so. This function is part of the + * RCU implementation; it is -not- an exported member of the RCU API. + */ int rcu_pending(int cpu) { return __rcu_pending(&rcu_ctrlblk, &per_cpu(rcu_data, cpu)) || __rcu_pending(&rcu_bh_ctrlblk, &per_cpu(rcu_bh_data, cpu)); } +/* + * Check to see if any future RCU-related work will need to be done + * by the current CPU, even if none need be done immediately, returning + * 1 if so. This function is part of the RCU implementation; it is -not- + * an exported member of the RCU API. + */ +int rcu_needs_cpu(int cpu) +{ + struct rcu_data *rdp = &per_cpu(rcu_data, cpu); + struct rcu_data *rdp_bh = &per_cpu(rcu_bh_data, cpu); + + return (!!rdp->curlist || !!rdp_bh->curlist || rcu_pending(cpu)); +} + void rcu_check_callbacks(int cpu, int user) { if (user || diff --git a/kernel/timer.c b/kernel/timer.c index 67eaf0f54096..9e49deed468c 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -541,6 +541,22 @@ found: } spin_unlock(&base->lock); + /* + * It can happen that other CPUs service timer IRQs and increment + * jiffies, but we have not yet got a local timer tick to process + * the timer wheels. In that case, the expiry time can be before + * jiffies, but since the high-resolution timer here is relative to + * jiffies, the default expression when high-resolution timers are + * not active, + * + * time_before(MAX_JIFFY_OFFSET + jiffies, expires) + * + * would falsely evaluate to true. If that is the case, just + * return jiffies so that we can immediately fire the local timer + */ + if (time_before(expires, jiffies)) + return jiffies; + if (time_before(hr_expires, expires)) return hr_expires; |