diff options
61 files changed, 3424 insertions, 487 deletions
diff --git a/Documentation/RCU/00-INDEX b/Documentation/RCU/00-INDEX index 461481dfb7c..7dc0695a8f9 100644 --- a/Documentation/RCU/00-INDEX +++ b/Documentation/RCU/00-INDEX @@ -16,6 +16,8 @@ RTFP.txt - List of RCU papers (bibliography) going back to 1980. torture.txt - RCU Torture Test Operation (CONFIG_RCU_TORTURE_TEST) +trace.txt + - CONFIG_RCU_TRACE debugfs files and formats UP.txt - RCU on Uniprocessor Systems whatisRCU.txt diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt new file mode 100644 index 00000000000..068848240a8 --- /dev/null +++ b/Documentation/RCU/trace.txt @@ -0,0 +1,413 @@ +CONFIG_RCU_TRACE debugfs Files and Formats + + +The rcupreempt and rcutree implementations of RCU provide debugfs trace +output that summarizes counters and state. This information is useful for +debugging RCU itself, and can sometimes also help to debug abuses of RCU. +Note that the rcuclassic implementation of RCU does not provide debugfs +trace output. + +The following sections describe the debugfs files and formats for +preemptable RCU (rcupreempt) and hierarchical RCU (rcutree). + + +Preemptable RCU debugfs Files and Formats + +This implementation of RCU provides three debugfs files under the +top-level directory RCU: rcu/rcuctrs (which displays the per-CPU +counters used by preemptable RCU) rcu/rcugp (which displays grace-period +counters), and rcu/rcustats (which internal counters for debugging RCU). + +The output of "cat rcu/rcuctrs" looks as follows: + +CPU last cur F M + 0 5 -5 0 0 + 1 -1 0 0 0 + 2 0 1 0 0 + 3 0 1 0 0 + 4 0 1 0 0 + 5 0 1 0 0 + 6 0 2 0 0 + 7 0 -1 0 0 + 8 0 1 0 0 +ggp = 26226, state = waitzero + +The per-CPU fields are as follows: + +o "CPU" gives the CPU number. Offline CPUs are not displayed. + +o "last" gives the value of the counter that is being decremented + for the current grace period phase. In the example above, + the counters sum to 4, indicating that there are still four + RCU read-side critical sections still running that started + before the last counter flip. + +o "cur" gives the value of the counter that is currently being + both incremented (by rcu_read_lock()) and decremented (by + rcu_read_unlock()). In the example above, the counters sum to + 1, indicating that there is only one RCU read-side critical section + still running that started after the last counter flip. + +o "F" indicates whether RCU is waiting for this CPU to acknowledge + a counter flip. In the above example, RCU is not waiting on any, + which is consistent with the state being "waitzero" rather than + "waitack". + +o "M" indicates whether RCU is waiting for this CPU to execute a + memory barrier. In the above example, RCU is not waiting on any, + which is consistent with the state being "waitzero" rather than + "waitmb". + +o "ggp" is the global grace-period counter. + +o "state" is the RCU state, which can be one of the following: + + o "idle": there is no grace period in progress. + + o "waitack": RCU just incremented the global grace-period + counter, which has the effect of reversing the roles of + the "last" and "cur" counters above, and is waiting for + all the CPUs to acknowledge the flip. Once the flip has + been acknowledged, CPUs will no longer be incrementing + what are now the "last" counters, so that their sum will + decrease monotonically down to zero. + + o "waitzero": RCU is waiting for the sum of the "last" counters + to decrease to zero. + + o "waitmb": RCU is waiting for each CPU to execute a memory + barrier, which ensures that instructions from a given CPU's + last RCU read-side critical section cannot be reordered + with instructions following the memory-barrier instruction. + +The output of "cat rcu/rcugp" looks as follows: + +oldggp=48870 newggp=48873 + +Note that reading from this file provokes a synchronize_rcu(). The +"oldggp" value is that of "ggp" from rcu/rcuctrs above, taken before +executing the synchronize_rcu(), and the "newggp" value is also the +"ggp" value, but taken after the synchronize_rcu() command returns. + + +The output of "cat rcu/rcugp" looks as follows: + +na=1337955 nl=40 wa=1337915 wl=44 da=1337871 dl=0 dr=1337871 di=1337871 +1=50989 e1=6138 i1=49722 ie1=82 g1=49640 a1=315203 ae1=265563 a2=49640 +z1=1401244 ze1=1351605 z2=49639 m1=5661253 me1=5611614 m2=49639 + +These are counters tracking internal preemptable-RCU events, however, +some of them may be useful for debugging algorithms using RCU. In +particular, the "nl", "wl", and "dl" values track the number of RCU +callbacks in various states. The fields are as follows: + +o "na" is the total number of RCU callbacks that have been enqueued + since boot. + +o "nl" is the number of RCU callbacks waiting for the previous + grace period to end so that they can start waiting on the next + grace period. + +o "wa" is the total number of RCU callbacks that have started waiting + for a grace period since boot. "na" should be roughly equal to + "nl" plus "wa". + +o "wl" is the number of RCU callbacks currently waiting for their + grace period to end. + +o "da" is the total number of RCU callbacks whose grace periods + have completed since boot. "wa" should be roughly equal to + "wl" plus "da". + +o "dr" is the total number of RCU callbacks that have been removed + from the list of callbacks ready to invoke. "dr" should be roughly + equal to "da". + +o "di" is the total number of RCU callbacks that have been invoked + since boot. "di" should be roughly equal to "da", though some + early versions of preemptable RCU had a bug so that only the + last CPU's count of invocations was displayed, rather than the + sum of all CPU's counts. + +o "1" is the number of calls to rcu_try_flip(). This should be + roughly equal to the sum of "e1", "i1", "a1", "z1", and "m1" + described below. In other words, the number of times that + the state machine is visited should be equal to the sum of the + number of times that each state is visited plus the number of + times that the state-machine lock acquisition failed. + +o "e1" is the number of times that rcu_try_flip() was unable to + acquire the fliplock. + +o "i1" is the number of calls to rcu_try_flip_idle(). + +o "ie1" is the number of times rcu_try_flip_idle() exited early + due to the calling CPU having no work for RCU. + +o "g1" is the number of times that rcu_try_flip_idle() decided + to start a new grace period. "i1" should be roughly equal to + "ie1" plus "g1". + +o "a1" is the number of calls to rcu_try_flip_waitack(). + +o "ae1" is the number of times that rcu_try_flip_waitack() found + that at least one CPU had not yet acknowledge the new grace period + (AKA "counter flip"). + +o "a2" is the number of time rcu_try_flip_waitack() found that + all CPUs had acknowledged. "a1" should be roughly equal to + "ae1" plus "a2". (This particular output was collected on + a 128-CPU machine, hence the smaller-than-usual fraction of + calls to rcu_try_flip_waitack() finding all CPUs having already + acknowledged.) + +o "z1" is the number of calls to rcu_try_flip_waitzero(). + +o "ze1" is the number of times that rcu_try_flip_waitzero() found + that not all of the old RCU read-side critical sections had + completed. + +o "z2" is the number of times that rcu_try_flip_waitzero() finds + the sum of the counters equal to zero, in other words, that + all of the old RCU read-side critical sections had completed. + The value of "z1" should be roughly equal to "ze1" plus + "z2". + +o "m1" is the number of calls to rcu_try_flip_waitmb(). + +o "me1" is the number of times that rcu_try_flip_waitmb() finds + that at least one CPU has not yet executed a memory barrier. + +o "m2" is the number of times that rcu_try_flip_waitmb() finds that + all CPUs have executed a memory barrier. + + +Hierarchical RCU debugfs Files and Formats + +This implementation of RCU provides three debugfs files under the +top-level directory RCU: rcu/rcudata (which displays fields in struct +rcu_data), rcu/rcugp (which displays grace-period counters), and +rcu/rcuhier (which displays the struct rcu_node hierarchy). + +The output of "cat rcu/rcudata" looks as follows: + +rcu: + 0 c=4011 g=4012 pq=1 pqc=4011 qp=0 rpfq=1 rp=3c2a dt=23301/73 dn=2 df=1882 of=0 ri=2126 ql=2 b=10 + 1 c=4011 g=4012 pq=1 pqc=4011 qp=0 rpfq=3 rp=39a6 dt=78073/1 dn=2 df=1402 of=0 ri=1875 ql=46 b=10 + 2 c=4010 g=4010 pq=1 pqc=4010 qp=0 rpfq=-5 rp=1d12 dt=16646/0 dn=2 df=3140 of=0 ri=2080 ql=0 b=10 + 3 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=2b50 dt=21159/1 dn=2 df=2230 of=0 ri=1923 ql=72 b=10 + 4 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=1644 dt=5783/1 dn=2 df=3348 of=0 ri=2805 ql=7 b=10 + 5 c=4012 g=4013 pq=0 pqc=4011 qp=1 rpfq=3 rp=1aac dt=5879/1 dn=2 df=3140 of=0 ri=2066 ql=10 b=10 + 6 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=ed8 dt=5847/1 dn=2 df=3797 of=0 ri=1266 ql=10 b=10 + 7 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=1fa2 dt=6199/1 dn=2 df=2795 of=0 ri=2162 ql=28 b=10 +rcu_bh: + 0 c=-268 g=-268 pq=1 pqc=-268 qp=0 rpfq=-145 rp=21d6 dt=23301/73 dn=2 df=0 of=0 ri=0 ql=0 b=10 + 1 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-170 rp=20ce dt=78073/1 dn=2 df=26 of=0 ri=5 ql=0 b=10 + 2 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-83 rp=fbd dt=16646/0 dn=2 df=28 of=0 ri=4 ql=0 b=10 + 3 c=-268 g=-268 pq=1 pqc=-268 qp=0 rpfq=-105 rp=178c dt=21159/1 dn=2 df=28 of=0 ri=2 ql=0 b=10 + 4 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-30 rp=b54 dt=5783/1 dn=2 df=32 of=0 ri=0 ql=0 b=10 + 5 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-29 rp=df5 dt=5879/1 dn=2 df=30 of=0 ri=3 ql=0 b=10 + 6 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-28 rp=788 dt=5847/1 dn=2 df=32 of=0 ri=0 ql=0 b=10 + 7 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-53 rp=1098 dt=6199/1 dn=2 df=30 of=0 ri=3 ql=0 b=10 + +The first section lists the rcu_data structures for rcu, the second for +rcu_bh. Each section has one line per CPU, or eight for this 8-CPU system. +The fields are as follows: + +o The number at the beginning of each line is the CPU number. + CPUs numbers followed by an exclamation mark are offline, + but have been online at least once since boot. There will be + no output for CPUs that have never been online, which can be + a good thing in the surprisingly common case where NR_CPUS is + substantially larger than the number of actual CPUs. + +o "c" is the count of grace periods that this CPU believes have + completed. CPUs in dynticks idle mode may lag quite a ways + behind, for example, CPU 4 under "rcu" above, which has slept + through the past 25 RCU grace periods. It is not unusual to + see CPUs lagging by thousands of grace periods. + +o "g" is the count of grace periods that this CPU believes have + started. Again, CPUs in dynticks idle mode may lag behind. + If the "c" and "g" values are equal, this CPU has already + reported a quiescent state for the last RCU grace period that + it is aware of, otherwise, the CPU believes that it owes RCU a + quiescent state. + +o "pq" indicates that this CPU has passed through a quiescent state + for the current grace period. It is possible for "pq" to be + "1" and "c" different than "g", which indicates that although + the CPU has passed through a quiescent state, either (1) this + CPU has not yet reported that fact, (2) some other CPU has not + yet reported for this grace period, or (3) both. + +o "pqc" indicates which grace period the last-observed quiescent + state for this CPU corresponds to. This is important for handling + the race between CPU 0 reporting an extended dynticks-idle + quiescent state for CPU 1 and CPU 1 suddenly waking up and + reporting its own quiescent state. If CPU 1 was the last CPU + for the current grace period, then the CPU that loses this race + will attempt to incorrectly mark CPU 1 as having checked in for + the next grace period! + +o "qp" indicates that RCU still expects a quiescent state from + this CPU. + +o "rpfq" is the number of rcu_pending() calls on this CPU required + to induce this CPU to invoke force_quiescent_state(). + +o "rp" is low-order four hex digits of the count of how many times + rcu_pending() has been invoked on this CPU. + +o "dt" is the current value of the dyntick counter that is incremented + when entering or leaving dynticks idle state, either by the + scheduler or by irq. The number after the "/" is the interrupt + nesting depth when in dyntick-idle state, or one greater than + the interrupt-nesting depth otherwise. + + This field is displayed only for CONFIG_NO_HZ kernels. + +o "dn" is the current value of the dyntick counter that is incremented + when entering or leaving dynticks idle state via NMI. If both + the "dt" and "dn" values are even, then this CPU is in dynticks + idle mode and may be ignored by RCU. If either of these two + counters is odd, then RCU must be alert to the possibility of + an RCU read-side critical section running on this CPU. + + This field is displayed only for CONFIG_NO_HZ kernels. + +o "df" is the number of times that some other CPU has forced a + quiescent state on behalf of this CPU due to this CPU being in + dynticks-idle state. + + This field is displayed only for CONFIG_NO_HZ kernels. + +o "of" is the number of times that some other CPU has forced a + quiescent state on behalf of this CPU due to this CPU being + offline. In a perfect world, this might neve happen, but it + turns out that offlining and onlining a CPU can take several grace + periods, and so there is likely to be an extended period of time + when RCU believes that the CPU is online when it really is not. + Please note that erring in the other direction (RCU believing a + CPU is offline when it is really alive and kicking) is a fatal + error, so it makes sense to err conservatively. + +o "ri" is the number of times that RCU has seen fit to send a + reschedule IPI to this CPU in order to get it to report a + quiescent state. + +o "ql" is the number of RCU callbacks currently residing on + this CPU. This is the total number of callbacks, regardless + of what state they are in (new, waiting for grace period to + start, waiting for grace period to end, ready to invoke). + +o "b" is the batch limit for this CPU. If more than this number + of RCU callbacks is ready to invoke, then the remainder will + be deferred. + + +The output of "cat rcu/rcugp" looks as follows: + +rcu: completed=33062 gpnum=33063 +rcu_bh: completed=464 gpnum=464 + +Again, this output is for both "rcu" and "rcu_bh". The fields are +taken from the rcu_state structure, and are as follows: + +o "completed" is the number of grace periods that have completed. + It is comparable to the "c" field from rcu/rcudata in that a + CPU whose "c" field matches the value of "completed" is aware + that the corresponding RCU grace period has completed. + +o "gpnum" is the number of grace periods that have started. It is + comparable to the "g" field from rcu/rcudata in that a CPU + whose "g" field matches the value of "gpnum" is aware that the + corresponding RCU grace period has started. + + If these two fields are equal (as they are for "rcu_bh" above), + then there is no grace period in progress, in other words, RCU + is idle. On the other hand, if the two fields differ (as they + do for "rcu" above), then an RCU grace period is in progress. + + +The output of "cat rcu/rcuhier" looks as follows, with very long lines: + +c=6902 g=6903 s=2 jfq=3 j=72c7 nfqs=13142/nfqsng=0(13142) fqlh=6 +1/1 0:127 ^0 +3/3 0:35 ^0 0/0 36:71 ^1 0/0 72:107 ^2 0/0 108:127 ^3 +3/3f 0:5 ^0 2/3 6:11 ^1 0/0 12:17 ^2 0/0 18:23 ^3 0/0 24:29 ^4 0/0 30:35 ^5 0/0 36:41 ^0 0/0 42:47 ^1 0/0 48:53 ^2 0/0 54:59 ^3 0/0 60:65 ^4 0/0 66:71 ^5 0/0 72:77 ^0 0/0 78:83 ^1 0/0 84:89 ^2 0/0 90:95 ^3 0/0 96:101 ^4 0/0 102:107 ^5 0/0 108:113 ^0 0/0 114:119 ^1 0/0 120:125 ^2 0/0 126:127 ^3 +rcu_bh: +c=-226 g=-226 s=1 jfq=-5701 j=72c7 nfqs=88/nfqsng=0(88) fqlh=0 +0/1 0:127 ^0 +0/3 0:35 ^0 0/0 36:71 ^1 0/0 72:107 ^2 0/0 108:127 ^3 +0/3f 0:5 ^0 0/3 6:11 ^1 0/0 12:17 ^2 0/0 18:23 ^3 0/0 24:29 ^4 0/0 30:35 ^5 0/0 36:41 ^0 0/0 42:47 ^1 0/0 48:53 ^2 0/0 54:59 ^3 0/0 60:65 ^4 0/0 66:71 ^5 0/0 72:77 ^0 0/0 78:83 ^1 0/0 84:89 ^2 0/0 90:95 ^3 0/0 96:101 ^4 0/0 102:107 ^5 0/0 108:113 ^0 0/0 114:119 ^1 0/0 120:125 ^2 0/0 126:127 ^3 + +This is once again split into "rcu" and "rcu_bh" portions. The fields are +as follows: + +o "c" is exactly the same as "completed" under rcu/rcugp. + +o "g" is exactly the same as "gpnum" under rcu/rcugp. + +o "s" is the "signaled" state that drives force_quiescent_state()'s + state machine. + +o "jfq" is the number of jiffies remaining for this grace period + before force_quiescent_state() is invoked to help push things + along. Note that CPUs in dyntick-idle mode thoughout the grace + period will not report on their own, but rather must be check by + some other CPU via force_quiescent_state(). + +o "j" is the low-order four hex digits of the jiffies counter. + Yes, Paul did run into a number of problems that turned out to + be due to the jiffies counter no longer counting. Why do you ask? + +o "nfqs" is the number of calls to force_quiescent_state() since + boot. + +o "nfqsng" is the number of useless calls to force_quiescent_state(), + where there wasn't actually a grace period active. This can + happen due to races. The number in parentheses is the difference + between "nfqs" and "nfqsng", or the number of times that + force_quiescent_state() actually did some real work. + +o "fqlh" is the number of calls to force_quiescent_state() that + exited immediately (without even being counted in nfqs above) + due to contention on ->fqslock. + +o Each element of the form "1/1 0:127 ^0" represents one struct + rcu_node. Each line represents one level of the hierarchy, from + root to leaves. It is best to think of the rcu_data structures + as forming yet another level after the leaves. Note that there + might be either one, two, or three levels of rcu_node structures, + depending on the relationship between CONFIG_RCU_FANOUT and + CONFIG_NR_CPUS. + + o The numbers separated by the "/" are the qsmask followed + by the qsmaskinit. The qsmask will have one bit + set for each entity in the next lower level that + has not yet checked in for the current grace period. + The qsmaskinit will have one bit for each entity that is + currently expected to check in during each grace period. + The value of qsmaskinit is assigned to that of qsmask + at the beginning of each grace period. + + For example, for "rcu", the qsmask of the first entry + of the lowest level is 0x14, meaning that we are still + waiting for CPUs 2 and 4 to check in for the current + grace period. + + o The numbers separated by the ":" are the range of CPUs + served by this struct rcu_node. This can be helpful + in working out how the hierarchy is wired together. + + For example, the first entry at the lowest level shows + "0:5", indicating that it covers CPUs 0 through 5. + + o The number after the "^" indicates the bit in the + next higher level rcu_node structure that this + rcu_node structure corresponds to. + + For example, the first entry at the lowest level shows + "^0", indicating that it corresponds to bit zero in + the first entry at the middle level. diff --git a/Documentation/lockstat.txt b/Documentation/lockstat.txt index 4ba4664ce5c..9cb9138f7a7 100644 --- a/Documentation/lockstat.txt +++ b/Documentation/lockstat.txt @@ -71,35 +71,50 @@ Look at the current lock statistics: # less /proc/lock_stat -01 lock_stat version 0.2 +01 lock_stat version 0.3 02 ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- 03 class name con-bounces contentions waittime-min waittime-max waittime-total acq-bounces acquisitions holdtime-min holdtime-max holdtime-total 04 ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- 05 -06 &inode->i_data.tree_lock-W: 15 21657 0.18 1093295.30 11547131054.85 58 10415 0.16 87.51 6387.60 -07 &inode->i_data.tree_lock-R: 0 0 0.00 0.00 0.00 23302 231198 0.25 8.45 98023.38 -08 -------------------------- -09 &inode->i_data.tree_lock 0 [<ffffffff8027c08f>] add_to_page_cache+0x5f/0x190 -10 -11 ............................................................................................................................................................................................... -12 -13 dcache_lock: 1037 1161 0.38 45.32 774.51 6611 243371 0.15 306.48 77387.24 -14 ----------- -15 dcache_lock 180 [<ffffffff802c0d7e>] sys_getcwd+0x11e/0x230 -16 dcache_lock 165 [<ffffffff802c002a>] d_alloc+0x15a/0x210 -17 dcache_lock 33 [<ffffffff8035818d>] _atomic_dec_and_lock+0x4d/0x70 -18 dcache_lock 1 [<ffffffff802beef8>] shrink_dcache_parent+0x18/0x130 +06 &mm->mmap_sem-W: 233 538 18446744073708 22924.27 607243.51 1342 45806 1.71 8595.89 1180582.34 +07 &mm->mmap_sem-R: 205 587 18446744073708 28403.36 731975.00 1940 412426 0.58 187825.45 6307502.88 +08 --------------- +09 &mm->mmap_sem 487 [<ffffffff8053491f>] do_page_fault+0x466/0x928 +10 &mm->mmap_sem 179 [<ffffffff802a6200>] sys_mprotect+0xcd/0x21d +11 &mm->mmap_sem 279 [<ffffffff80210a57>] sys_mmap+0x75/0xce +12 &mm->mmap_sem 76 [<ffffffff802a490b>] sys_munmap+0x32/0x59 +13 --------------- +14 &mm->mmap_sem 270 [<ffffffff80210a57>] sys_mmap+0x75/0xce +15 &mm->mmap_sem 431 [<ffffffff8053491f>] do_page_fault+0x466/0x928 +16 &mm->mmap_sem 138 [<ffffffff802a490b>] sys_munmap+0x32/0x59 +17 &mm->mmap_sem 145 [<ffffffff802a6200>] sys_mprotect+0xcd/0x21d +18 +19 ............................................................................................................................................................................................... +20 +21 dcache_lock: 621 623 0.52 118.26 1053.02 6745 91930 0.29 316.29 118423.41 +22 ----------- +23 dcache_lock 179 [<ffffffff80378274>] _atomic_dec_and_lock+0x34/0x54 +24 dcache_lock 113 [<ffffffff802cc17b>] d_alloc+0x19a/0x1eb +25 dcache_lock 99 [<ffffffff802ca0dc>] d_rehash+0x1b/0x44 +26 dcache_lock 104 [<ffffffff802cbca0>] d_instantiate+0x36/0x8a +27 ----------- +28 dcache_lock 192 [<ffffffff80378274>] _atomic_dec_and_lock+0x34/0x54 +29 dcache_lock 98 [<ffffffff802ca0dc>] d_rehash+0x1b/0x44 +30 dcache_lock 72 [<ffffffff802cc17b>] d_alloc+0x19a/0x1eb +31 dcache_lock 112 [<ffffffff802cbca0>] d_instantiate+0x36/0x8a This excerpt shows the first two lock class statistics. Line 01 shows the output version - each time the format changes this will be updated. Line 02-04 -show the header with column descriptions. Lines 05-10 and 13-18 show the actual +show the header with column descriptions. Lines 05-18 and 20-31 show the actual statistics. These statistics come in two parts; the actual stats separated by a -short separator (line 08, 14) from the contention points. +short separator (line 08, 13) from the contention points. -The first lock (05-10) is a read/write lock, and shows two lines above the +The first lock (05-18) is a read/write lock, and shows two lines above the short separator. The contention points don't match the column descriptors, -they have two: contentions and [<IP>] symbol. +they have two: contentions and [<IP>] symbol. The second set of contention +points are the points we're contending with. +The integer part of the time values is in us. View the top contending locks: diff --git a/arch/powerpc/platforms/pseries/rtasd.c b/arch/powerpc/platforms/pseries/rtasd.c index f4e55be2eea..afad9f5ac0a 100644 --- a/arch/powerpc/platforms/pseries/rtasd.c +++ b/arch/powerpc/platforms/pseries/rtasd.c @@ -208,6 +208,7 @@ void pSeries_log_error(char *buf, unsigned int err_type, int fatal) break; case ERR_TYPE_KERNEL_PANIC: default: + WARN_ON_ONCE(!irqs_disabled()); /* @@@ DEBUG @@@ */ spin_unlock_irqrestore(&rtasd_log_lock, s); return; } @@ -227,6 +228,7 @@ void pSeries_log_error(char *buf, unsigned int err_type, int fatal) /* Check to see if we need to or have stopped logging */ if (fatal || !logging_enabled) { logging_enabled = 0; + WARN_ON_ONCE(!irqs_disabled()); /* @@@ DEBUG @@@ */ spin_unlock_irqrestore(&rtasd_log_lock, s); return; } @@ -249,11 +251,13 @@ void pSeries_log_error(char *buf, unsigned int err_type, int fatal) else rtas_log_start += 1; + WARN_ON_ONCE(!irqs_disabled()); /* @@@ DEBUG @@@ */ spin_unlock_irqrestore(&rtasd_log_lock, s); wake_up_interruptible(&rtas_log_wait); break; case ERR_TYPE_KERNEL_PANIC: default: + WARN_ON_ONCE(!irqs_disabled()); /* @@@ DEBUG @@@ */ spin_unlock_irqrestore(&rtasd_log_lock, s); return; } diff --git a/arch/um/include/asm/system.h b/arch/um/include/asm/system.h index 753346e2cdf..ae5f94d6317 100644 --- a/arch/um/include/asm/system.h +++ b/arch/um/include/asm/system.h @@ -11,21 +11,21 @@ extern int get_signals(void); extern void block_signals(void); extern void unblock_signals(void); -#define local_save_flags(flags) do { typecheck(unsigned long, flags); \ +#define raw_local_save_flags(flags) do { typecheck(unsigned long, flags); \ (flags) = get_signals(); } while(0) -#define local_irq_restore(flags) do { typecheck(unsigned long, flags); \ +#define raw_local_irq_restore(flags) do { typecheck(unsigned long, flags); \ set_signals(flags); } while(0) -#define local_irq_save(flags) do { local_save_flags(flags); \ - local_irq_disable(); } while(0) +#define raw_local_irq_save(flags) do { raw_local_save_flags(flags); \ + raw_local_irq_disable(); } while(0) -#define local_irq_enable() unblock_signals() -#define local_irq_disable() block_signals() +#define raw_local_irq_enable() unblock_signals() +#define raw_local_irq_disable() block_signals() #define irqs_disabled() \ ({ \ unsigned long flags; \ - local_save_flags(flags); \ + raw_local_save_flags(flags); \ (flags == 0); \ }) diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index dc22c073328..4035357f5b9 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -65,7 +65,7 @@ static inline struct dma_mapping_ops *get_dma_ops(struct device *dev) return dma_ops; else return dev->archdata.dma_ops; -#endif /* _ASM_X86_DMA_MAPPING_H */ +#endif } /* Make sure we keep the same behaviour */ diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h index 295b13193f4..a6ee9e6f530 100644 --- a/arch/x86/include/asm/iommu.h +++ b/arch/x86/include/asm/iommu.h @@ -7,8 +7,6 @@ extern struct dma_mapping_ops nommu_dma_ops; extern int force_iommu, no_iommu; extern int iommu_detected; -extern unsigned long iommu_nr_pages(unsigned long addr, unsigned long len); - /* 10 seconds */ #define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000) diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 647781298e7..66834c41c04 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -84,6 +84,8 @@ static inline void pci_dma_burst_advice(struct pci_dev *pdev, static inline void early_quirks(void) { } #endif +extern void pci_iommu_alloc(void); + #endif /* __KERNEL__ */ #ifdef CONFIG_X86_32 diff --git a/arch/x86/include/asm/pci_64.h b/arch/x86/include/asm/pci_64.h index d02d936840a..4da20798277 100644 --- a/arch/x86/include/asm/pci_64.h +++ b/arch/x86/include/asm/pci_64.h @@ -23,7 +23,6 @@ extern int (*pci_config_write)(int seg, int bus, int dev, int fn, int reg, int len, u32 value); extern void dma32_reserve_bootmem(void); -extern void pci_iommu_alloc(void); /* The PCI address space does equal the physical memory * address space. The networking and block device layers use diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 580c3ee6c58..4340055b755 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -157,6 +157,7 @@ extern int __get_user_bad(void); int __ret_gu; \ unsigned long __val_gu; \ __chk_user_ptr(ptr); \ + might_fault(); \ switch (sizeof(*(ptr))) { \ case 1: \ __get_user_x(1, __ret_gu, __val_gu, ptr); \ @@ -241,6 +242,7 @@ extern void __put_user_8(void); int __ret_pu; \ __typeof__(*(ptr)) __pu_val; \ __chk_user_ptr(ptr); \ + might_fault(); \ __pu_val = x; \ switch (sizeof(*(ptr))) { \ case 1: \ diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index d095a3aeea1..5e06259e90e 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -82,8 +82,8 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) static __always_inline unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n) { - might_sleep(); - return __copy_to_user_inatomic(to, from, n); + might_fault(); + return __copy_to_user_inatomic(to, from, n); } static __always_inline unsigned long @@ -137,7 +137,7 @@ __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) static __always_inline unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { - might_sleep(); + might_fault(); if (__builtin_constant_p(n)) { unsigned long ret; @@ -159,7 +159,7 @@ __copy_from_user(void *to, const void __user *from, unsigned long n) static __always_inline unsigned long __copy_from_user_nocache(void *to, const void __user *from, unsigned long n) { - might_sleep(); + might_fault(); if (__builtin_constant_p(n)) { unsigned long ret; diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index f8cfd00db45..84210c479fc 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -29,6 +29,8 @@ static __always_inline __must_check int __copy_from_user(void *dst, const void __user *src, unsigned size) { int ret = 0; + + might_fault(); if (!__builtin_constant_p(size)) return copy_user_generic(dst, (__force void *)src, size); switch (size) { @@ -71,6 +73,8 @@ static __always_inline __must_check int __copy_to_user(void __user *dst, const void *src, unsigned size) { int ret = 0; + + might_fault(); if (!__builtin_constant_p(size)) return copy_user_generic((__force void *)dst, src, size); switch (size) { @@ -113,6 +117,8 @@ static __always_inline __must_check int __copy_in_user(void __user *dst, const void __user *src, unsigned size) { int ret = 0; + + might_fault(); if (!__builtin_constant_p(size)) return copy_user_generic((__force void *)dst, (__force void *)src, size); diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 88dd768eab6..d364df03c1d 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -109,6 +109,8 @@ obj-$(CONFIG_MICROCODE) += microcode.o obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o +obj-$(CONFIG_SWIOTLB) += pci-swiotlb_64.o # NB rename without _64 + ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) @@ -122,7 +124,6 @@ ifeq ($(CONFIG_X86_64),y) obj-$(CONFIG_GART_IOMMU) += pci-gart_64.o aperture_64.o obj-$(CONFIG_CALGARY_IOMMU) += pci-calgary_64.o tce_64.o obj-$(CONFIG_AMD_IOMMU) += amd_iommu_init.o amd_iommu.o - obj-$(CONFIG_SWIOTLB) += pci-swiotlb_64.o obj-$(CONFIG_PCI_MMCONFIG) += mmconf-fam10h_64.o endif diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 7a3dfceb90e..19a1044a0cd 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -101,11 +101,15 @@ static void __init dma32_free_bootmem(void) dma32_bootmem_ptr = NULL; dma32_bootmem_size = 0; } +#endif void __init pci_iommu_alloc(void) { +#ifdef CONFIG_X86_64 /* free the range so iommu could get some range less than 4G */ dma32_free_bootmem(); +#endif + /* * The order of these functions is important for * fall-back/fail-over reasons @@ -121,15 +125,6 @@ void __init pci_iommu_alloc(void) pci_swiotlb_init(); } -unsigned long iommu_nr_pages(unsigned long addr, unsigned long len) -{ - unsigned long size = roundup((addr & ~PAGE_MASK) + len, PAGE_SIZE); - - return size >> PAGE_SHIFT; -} -EXPORT_SYMBOL(iommu_nr_pages); -#endif - void *dma_generic_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, gfp_t flag) { diff --git a/arch/x86/kernel/pci-swiotlb_64.c b/arch/x86/kernel/pci-swiotlb_64.c index 3c539d111ab..242c3440687 100644 --- a/arch/x86/kernel/pci-swiotlb_64.c +++ b/arch/x86/kernel/pci-swiotlb_64.c @@ -3,6 +3,8 @@ #include <linux/pci.h> #include <linux/cache.h> #include <linux/module.h> +#include <linux/swiotlb.h> +#include <linux/bootmem.h> #include <linux/dma-mapping.h> #include <asm/iommu.h> @@ -11,6 +13,31 @@ int swiotlb __read_mostly; +void *swiotlb_alloc_boot(size_t size, unsigned long nslabs) +{ + return alloc_bootmem_low_pages(size); +} + +void *swiotlb_alloc(unsigned order, unsigned long nslabs) +{ + return (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, order); +} + +dma_addr_t swiotlb_phys_to_bus(phys_addr_t paddr) +{ + return paddr; +} + +phys_addr_t swiotlb_bus_to_phys(dma_addr_t baddr) +{ + return baddr; +} + +int __weak swiotlb_arch_range_needs_mapping(void *ptr, size_t size) +{ + return 0; +} + static dma_addr_t swiotlb_map_single_phys(struct device *hwdev, phys_addr_t paddr, size_t size, int direction) @@ -50,8 +77,10 @@ struct dma_mapping_ops swiotlb_dma_ops = { void __init pci_swiotlb_init(void) { /* don't initialize swiotlb if iommu=off (no_iommu=1) */ +#ifdef CONFIG_X86_64 if (!iommu_detected && !no_iommu && max_pfn > MAX_DMA32_PFN) swiotlb = 1; +#endif if (swiotlb_force) swiotlb = 1; if (swiotlb) { diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index 9e68075544f..4a20b2f9a38 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -39,7 +39,7 @@ static inline int __movsl_is_ok(unsigned long a1, unsigned long a2, unsigned lon #define __do_strncpy_from_user(dst, src, count, res) \ do { \ int __d0, __d1, __d2; \ - might_sleep(); \ + might_fault(); \ __asm__ __volatile__( \ " testl %1,%1\n" \ " jz 2f\n" \ @@ -126,7 +126,7 @@ EXPORT_SYMBOL(strncpy_from_user); #define __do_clear_user(addr,size) \ do { \ int __d0; \ - might_sleep(); \ + might_fault(); \ __asm__ __volatile__( \ "0: rep; stosl\n" \ " movl %2,%0\n" \ @@ -155,7 +155,7 @@ do { \ unsigned long clear_user(void __user *to, unsigned long n) { - might_sleep(); + might_fault(); if (access_ok(VERIFY_WRITE, to, n)) __do_clear_user(to, n); return n; @@ -197,7 +197,7 @@ long strnlen_user(const char __user *s, long n) unsigned long mask = -__addr_ok(s); unsigned long res, tmp; - might_sleep(); + might_fault(); __asm__ __volatile__( " testl %0, %0\n" diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index f4df6e7c718..64d6c84e635 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -15,7 +15,7 @@ #define __do_strncpy_from_user(dst,src,count,res) \ do { \ long __d0, __d1, __d2; \ - might_sleep(); \ + might_fault(); \ __asm__ __volatile__( \ " testq %1,%1\n" \ " jz 2f\n" \ @@ -64,7 +64,7 @@ EXPORT_SYMBOL(strncpy_from_user); unsigned long __clear_user(void __user *addr, unsigned long size) { long __d0; - might_sleep(); + might_fault(); /* no memory constraint because it doesn't change any memory gcc knows about */ asm volatile( diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 800e1d94c1b..8655b5bb096 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -21,6 +21,7 @@ #include <linux/init.h> #include <linux/highmem.h> #include <linux/pagemap.h> +#include <linux/pci.h> #include <linux/pfn.h> #include <linux/poison.h> #include <linux/bootmem.h> @@ -967,6 +968,8 @@ void __init mem_init(void) int codesize, reservedpages, datasize, initsize; int tmp; + pci_iommu_alloc(); + #ifdef CONFIG_FLATMEM BUG_ON(!mem_map); #endif diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index 4c794d73fb8..8af276361bf 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -41,15 +41,14 @@ struct bug_entry { #ifndef __WARN #ifndef __ASSEMBLY__ -extern void warn_on_slowpath(const char *file, const int line); extern void warn_slowpath(const char *file, const int line, const char *fmt, ...) __attribute__((format(printf, 3, 4))); #define WANT_WARN_ON_SLOWPATH #endif -#define __WARN() warn_on_slowpath(__FILE__, __LINE__) -#define __WARN_printf(arg...) warn_slowpath(__FILE__, __LINE__, arg) +#define __WARN() warn_slowpath(__FILE__, __LINE__, NULL) +#define __WARN_printf(arg...) warn_slowpath(__FILE__, __LINE__, arg) #else -#define __WARN_printf(arg...) do { printk(arg); __WARN(); } while (0) +#define __WARN_printf(arg...) do { printk(arg); __WARN(); } while (0) #endif #ifndef WARN_ON diff --git a/include/linux/bottom_half.h b/include/linux/bottom_half.h index 777dbf695d4..27b1bcffe40 100644 --- a/include/linux/bottom_half.h +++ b/include/linux/bottom_half.h @@ -2,7 +2,6 @@ #define _LINUX_BH_H extern void local_bh_disable(void); -extern void __local_bh_enable(void); extern void _local_bh_enable(void); extern void local_bh_enable(void); extern void local_bh_enable_ip(unsigned long ip); diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h index 4aaa4afb1cb..096476f1fb3 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -17,7 +17,7 @@ extern int debug_locks_off(void); ({ \ int __ret = 0; \ \ - if (unlikely(c)) { \ + if (!oops_in_progress && unlikely(c)) { \ if (debug_locks_off() && !debug_locks_silent) \ WARN_ON(1); \ __ret = 1; \ diff --git a/include/linux/futex.h b/include/linux/futex.h index 586ab56a3ec..3bf5bb5a34f 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -25,7 +25,8 @@ union ktime; #define FUTEX_WAKE_BITSET 10 #define FUTEX_PRIVATE_FLAG 128 -#define FUTEX_CMD_MASK ~FUTEX_PRIVATE_FLAG +#define FUTEX_CLOCK_REALTIME 256 +#define FUTEX_CMD_MASK ~(FUTEX_PRIVATE_FLAG | FUTEX_CLOCK_REALTIME) #define FUTEX_WAIT_PRIVATE (FUTEX_WAIT | FUTEX_PRIVATE_FLAG) #define FUTEX_WAKE_PRIVATE (FUTEX_WAKE | FUTEX_PRIVATE_FLAG) @@ -164,6 +165,8 @@ union futex_key { } both; }; +#define FUTEX_KEY_INIT (union futex_key) { .both = { .ptr = NULL } } + #ifdef CONFIG_FUTEX extern void exit_robust_list(struct task_struct *curr); extern void exit_pi_state_list(struct task_struct *curr); diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 89a56d79e4c..f83288347dd 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -119,13 +119,17 @@ static inline void account_system_vtime(struct task_struct *tsk) } #endif -#if defined(CONFIG_PREEMPT_RCU) && defined(CONFIG_NO_HZ) +#if defined(CONFIG_NO_HZ) && !defined(CONFIG_CLASSIC_RCU) extern void rcu_irq_enter(void); extern void rcu_irq_exit(void); +extern void rcu_nmi_enter(void); +extern void rcu_nmi_exit(void); #else # define rcu_irq_enter() do { } while (0) # define rcu_irq_exit() do { } while (0) -#endif /* CONFIG_PREEMPT_RCU */ +# define rcu_nmi_enter() do { } while (0) +# define rcu_nmi_exit() do { } while (0) +#endif /* #if defined(CONFIG_NO_HZ) && !defined(CONFIG_CLASSIC_RCU) */ /* * It is safe to do non-atomic ops on ->hardirq_context, @@ -135,7 +139,6 @@ extern void rcu_irq_exit(void); */ #define __irq_enter() \ do { \ - rcu_irq_enter(); \ account_system_vtime(current); \ add_preempt_count(HARDIRQ_OFFSET); \ trace_hardirq_enter(); \ @@ -154,7 +157,6 @@ extern void irq_enter(void); trace_hardirq_exit(); \ account_system_vtime(current); \ sub_preempt_count(HARDIRQ_OFFSET); \ - rcu_irq_exit(); \ } while (0) /* @@ -166,11 +168,14 @@ extern void irq_exit(void); do { \ ftrace_nmi_enter(); \ lockdep_off(); \ + rcu_nmi_enter(); \ __irq_enter(); \ } while (0) + #define nmi_exit() \ do { \ __irq_exit(); \ + rcu_nmi_exit(); \ lockdep_on(); \ ftrace_nmi_exit(); \ } while (0) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 6002ae76785..ca9ff6411df 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -141,6 +141,15 @@ extern int _cond_resched(void); (__x < 0) ? -__x : __x; \ }) +#ifdef CONFIG_PROVE_LOCKING +void might_fault(void); +#else +static inline void might_fault(void) +{ + might_sleep(); +} +#endif + extern struct atomic_notifier_head panic_notifier_list; extern long (*panic_blink)(long time); NORET_TYPE void panic(const char * fmt, ...) @@ -188,6 +197,8 @@ extern unsigned long long memparse(const char *ptr, char **retptr); extern int core_kernel_text(unsigned long addr); extern int __kernel_text_address(unsigned long addr); extern int kernel_text_address(unsigned long addr); +extern int func_ptr_is_kernel_text(void *ptr); + struct pid; extern struct pid *session_of_pgrp(struct pid *pgrp); diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 29aec6e1002..37a0361f468 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -73,6 +73,8 @@ struct lock_class_key { struct lockdep_subclass_key subkeys[MAX_LOCKDEP_SUBCLASSES]; }; +#define LOCKSTAT_POINTS 4 + /* * The lock-class itself: */ @@ -119,7 +121,8 @@ struct lock_class { int name_version; #ifdef CONFIG_LOCK_STAT - unsigned long contention_point[4]; + unsigned long contention_point[LOCKSTAT_POINTS]; + unsigned long contending_point[LOCKSTAT_POINTS]; #endif }; @@ -144,6 +147,7 @@ enum bounce_type { struct lock_class_stats { unsigned long contention_point[4]; + unsigned long contending_point[4]; struct lock_time read_waittime; struct lock_time write_waittime; struct lock_time read_holdtime; @@ -165,6 +169,7 @@ struct lockdep_map { const char *name; #ifdef CONFIG_LOCK_STAT int cpu; + unsigned long ip; #endif }; @@ -309,8 +314,15 @@ extern void lock_acquire(struct lockdep_map *lock, unsigned int subclass, extern void lock_release(struct lockdep_map *lock, int nested, unsigned long ip); -extern void lock_set_subclass(struct lockdep_map *lock, unsigned int subclass, - unsigned long ip); +extern void lock_set_class(struct lockdep_map *lock, const char *name, + struct lock_class_key *key, unsigned int subclass, + unsigned long ip); + +static inline void lock_set_subclass(struct lockdep_map *lock, + unsigned int subclass, unsigned long ip) +{ + lock_set_class(lock, lock->name, lock->key, subclass, ip); +} # define INIT_LOCKDEP .lockdep_recursion = 0, @@ -328,6 +340,7 @@ static inline void lockdep_on(void) # define lock_acquire(l, s, t, r, c, n, i) do { } while (0) # define lock_release(l, n, i) do { } while (0) +# define lock_set_class(l, n, k, s, i) do { } while (0) # define lock_set_subclass(l, s, i) do { } while (0) # define lockdep_init() do { } while (0) # define lockdep_info() do { } while (0) @@ -356,7 +369,7 @@ struct lock_class_key { }; #ifdef CONFIG_LOCK_STAT extern void lock_contended(struct lockdep_map *lock, unsigned long ip); -extern void lock_acquired(struct lockdep_map *lock); +extern void lock_acquired(struct lockdep_map *lock, unsigned long ip); #define LOCK_CONTENDED(_lock, try, lock) \ do { \ @@ -364,13 +377,13 @@ do { \ lock_contended(&(_lock)->dep_map, _RET_IP_); \ lock(_lock); \ } \ - lock_acquired(&(_lock)->dep_map); \ + lock_acquired(&(_lock)->dep_map, _RET_IP_); \ } while (0) #else /* CONFIG_LOCK_STAT */ #define lock_contended(lockdep_map, ip) do {} while (0) -#define lock_acquired(lockdep_map) do {} while (0) +#define lock_acquired(lockdep_map, ip) do {} while (0) #define LOCK_CONTENDED(_lock, try, lock) \ lock(_lock) @@ -481,4 +494,22 @@ static inline void print_irqtrace_events(struct task_struct *curr) # define lock_map_release(l) do { } while (0) #endif +#ifdef CONFIG_PROVE_LOCKING +# define might_lock(lock) \ +do { \ + typecheck(struct lockdep_map *, &(lock)->dep_map); \ + lock_acquire(&(lock)->dep_map, 0, 0, 0, 2, NULL, _THIS_IP_); \ + lock_release(&(lock)->dep_map, 0, _THIS_IP_); \ +} while (0) +# define might_lock_read(lock) \ +do { \ + typecheck(struct lockdep_map *, &(lock)->dep_map); \ + lock_acquire(&(lock)->dep_map, 0, 0, 1, 2, NULL, _THIS_IP_); \ + lock_release(&(lock)->dep_map, 0, _THIS_IP_); \ +} while (0) +#else +# define might_lock(lock) do { } while (0) +# define might_lock_read(lock) do { } while (0) +#endif + #endif /* __LINUX_LOCKDEP_H */ diff --git a/include/linux/mutex.h b/include/linux/mutex.h index bc6da10ceee..7a0e5c4f807 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -144,6 +144,8 @@ extern int __must_check mutex_lock_killable(struct mutex *lock); /* * NOTE: mutex_trylock() follows the spin_trylock() convention, * not the down_trylock() convention! + * + * Returns 1 if the mutex has been acquired successfully, and 0 on contention. */ extern int mutex_trylock(struct mutex *lock); extern void mutex_unlock(struct mutex *lock); diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h index 5f89b62e698..301dda829e3 100644 --- a/include/linux/rcuclassic.h +++ b/include/linux/rcuclassic.h @@ -41,7 +41,7 @@ #include <linux/seqlock.h> #ifdef CONFIG_RCU_CPU_STALL_DETECTOR -#define RCU_SECONDS_TILL_STALL_CHECK ( 3 * HZ) /* for rcp->jiffies_stall */ +#define RCU_SECONDS_TILL_STALL_CHECK (10 * HZ) /* for rcp->jiffies_stall */ #define RCU_SECONDS_TILL_STALL_RECHECK (30 * HZ) /* for rcp->jiffies_stall */ #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 895dc9c1088..1168fbcea8d 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -52,11 +52,15 @@ struct rcu_head { void (*func)(struct rcu_head *head); }; -#ifdef CONFIG_CLASSIC_RCU +#if defined(CONFIG_CLASSIC_RCU) #include <linux/rcuclassic.h> -#else /* #ifdef CONFIG_CLASSIC_RCU */ +#elif defined(CONFIG_TREE_RCU) +#include <linux/rcutree.h> +#elif defined(CONFIG_PREEMPT_RCU) #include <linux/rcupreempt.h> -#endif /* #else #ifdef CONFIG_CLASSIC_RCU */ +#else +#error "Unknown RCU implementation specified to kernel configuration" +#endif /* #else #if defined(CONFIG_CLASSIC_RCU) */ #define RCU_HEAD_INIT { .next = NULL, .func = NULL } #define RCU_HEAD(head) struct rcu_head head = RCU_HEAD_INIT diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h new file mode 100644 index 00000000000..d4368b7975c --- /dev/null +++ b/include/linux/rcutree.h @@ -0,0 +1,329 @@ +/* + * Read-Copy Update mechanism for mutual exclusion (tree-based version) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright IBM Corporation, 2008 + * + * Author: Dipankar Sarma <dipankar@in.ibm.com> + * Paul E. McKenney <paulmck@linux.vnet.ibm.com> Hierarchical algorithm + * + * Based on the original work by Paul McKenney <paulmck@us.ibm.com> + * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. + * + * For detailed explanation of Read-Copy Update mechanism see - + * Documentation/RCU + */ + +#ifndef __LINUX_RCUTREE_H +#define __LINUX_RCUTREE_H + +#include <linux/cache.h> +#include <linux/spinlock.h> +#include <linux/threads.h> +#include <linux/percpu.h> +#include <linux/cpumask.h> +#include <linux/seqlock.h> + +/* + * Define shape of hierarchy based on NR_CPUS and CONFIG_RCU_FANOUT. + * In theory, it should be possible to add more levels straightforwardly. + * In practice, this has not been tested, so there is probably some + * bug somewhere. + */ +#define MAX_RCU_LVLS 3 +#define RCU_FANOUT (CONFIG_RCU_FANOUT) +#define RCU_FANOUT_SQ (RCU_FANOUT * RCU_FANOUT) +#define RCU_FANOUT_CUBE (RCU_FANOUT_SQ * RCU_FANOUT) + +#if NR_CPUS <= RCU_FANOUT +# define NUM_RCU_LVLS 1 +# define NUM_RCU_LVL_0 1 +# define NUM_RCU_LVL_1 (NR_CPUS) +# define NUM_RCU_LVL_2 0 +# define NUM_RCU_LVL_3 0 +#elif NR_CPUS <= RCU_FANOUT_SQ +# define NUM_RCU_LVLS 2 +# define NUM_RCU_LVL_0 1 +# define NUM_RCU_LVL_1 (((NR_CPUS) + RCU_FANOUT - 1) / RCU_FANOUT) +# define NUM_RCU_LVL_2 (NR_CPUS) +# define NUM_RCU_LVL_3 0 +#elif NR_CPUS <= RCU_FANOUT_CUBE +# define NUM_RCU_LVLS 3 +# define NUM_RCU_LVL_0 1 +# define NUM_RCU_LVL_1 (((NR_CPUS) + RCU_FANOUT_SQ - 1) / RCU_FANOUT_SQ) +# define NUM_RCU_LVL_2 (((NR_CPUS) + (RCU_FANOUT) - 1) / (RCU_FANOUT)) +# define NUM_RCU_LVL_3 NR_CPUS +#else +# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS" +#endif /* #if (NR_CPUS) <= RCU_FANOUT */ + +#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3) +#define NUM_RCU_NODES (RCU_SUM - NR_CPUS) + +/* + * Dynticks per-CPU state. + */ +struct rcu_dynticks { + int dynticks_nesting; /* Track nesting level, sort of. */ + int dynticks; /* Even value for dynticks-idle, else odd. */ + int dynticks_nmi; /* Even value for either dynticks-idle or */ + /* not in nmi handler, else odd. So this */ + /* remains even for nmi from irq handler. */ +}; + +/* + * Definition for node within the RCU grace-period-detection hierarchy. + */ +struct rcu_node { + spinlock_t lock; + unsigned long qsmask; /* CPUs or groups that need to switch in */ + /* order for current grace period to proceed.*/ + unsigned long qsmaskinit; + /* Per-GP initialization for qsmask. */ + unsigned long grpmask; /* Mask to apply to parent qsmask. */ + int grplo; /* lowest-numbered CPU or group here. */ + int grphi; /* highest-numbered CPU or group here. */ + u8 grpnum; /* CPU/group number for next level up. */ + u8 level; /* root is at level 0. */ + struct rcu_node *parent; +} ____cacheline_internodealigned_in_smp; + +/* Index values for nxttail array in struct rcu_data. */ +#define RCU_DONE_TAIL 0 /* Also RCU_WAIT head. */ +#define RCU_WAIT_TAIL 1 /* Also RCU_NEXT_READY head. */ +#define RCU_NEXT_READY_TAIL 2 /* Also RCU_NEXT head. */ +#define RCU_NEXT_TAIL 3 +#define RCU_NEXT_SIZE 4 + +/* Per-CPU data for read-copy update. */ +struct rcu_data { + /* 1) quiescent-state and grace-period handling : */ + long completed; /* Track rsp->completed gp number */ + /* in order to detect GP end. */ + long gpnum; /* Highest gp number that this CPU */ + /* is aware of having started. */ + long passed_quiesc_completed; + /* Value of completed at time of qs. */ + bool passed_quiesc; /* User-mode/idle loop etc. */ + bool qs_pending; /* Core waits for quiesc state. */ + bool beenonline; /* CPU online at least once. */ + struct rcu_node *mynode; /* This CPU's leaf of hierarchy */ + unsigned long grpmask; /* Mask to apply to leaf qsmask. */ + + /* 2) batch handling */ + /* + * If nxtlist is not NULL, it is partitioned as follows. + * Any of the partitions might be empty, in which case the + * pointer to that partition will be equal to the pointer for + * the following partition. When the list is empty, all of + * the nxttail elements point to nxtlist, which is NULL. + * + * [*nxttail[RCU_NEXT_READY_TAIL], NULL = *nxttail[RCU_NEXT_TAIL]): + * Entries that might have arrived after current GP ended + * [*nxttail[RCU_WAIT_TAIL], *nxttail[RCU_NEXT_READY_TAIL]): + * Entries known to have arrived before current GP ended + * [*nxttail[RCU_DONE_TAIL], *nxttail[RCU_WAIT_TAIL]): + * Entries that batch # <= ->completed - 1: waiting for current GP + * [nxtlist, *nxttail[RCU_DONE_TAIL]): + * Entries that batch # <= ->completed + * The grace period for these entries has completed, and + * the other grace-period-completed entries may be moved + * here temporarily in rcu_process_callbacks(). + */ + struct rcu_head *nxtlist; + struct rcu_head **nxttail[RCU_NEXT_SIZE]; + long qlen; /* # of queued callbacks */ + long blimit; /* Upper limit on a processed batch */ + +#ifdef CONFIG_NO_HZ + /* 3) dynticks interface. */ + struct rcu_dynticks *dynticks; /* Shared per-CPU dynticks state. */ + int dynticks_snap; /* Per-GP tracking for dynticks. */ + int dynticks_nmi_snap; /* Per-GP tracking for dynticks_nmi. */ +#endif /* #ifdef CONFIG_NO_HZ */ + + /* 4) reasons this CPU needed to be kicked by force_quiescent_state */ +#ifdef CONFIG_NO_HZ + unsigned long dynticks_fqs; /* Kicked due to dynticks idle. */ +#endif /* #ifdef CONFIG_NO_HZ */ + unsigned long offline_fqs; /* Kicked due to being offline. */ + unsigned long resched_ipi; /* Sent a resched IPI. */ + + /* 5) state to allow this CPU to force_quiescent_state on others */ + long n_rcu_pending; /* rcu_pending() calls since boot. */ + long n_rcu_pending_force_qs; /* when to force quiescent states. */ + + int cpu; +}; + +/* Values for signaled field in struct rcu_state. */ +#define RCU_GP_INIT 0 /* Grace period being initialized. */ +#define RCU_SAVE_DYNTICK 1 /* Need to scan dyntick state. */ +#define RCU_FORCE_QS 2 /* Need to force quiescent state. */ +#ifdef CONFIG_NO_HZ +#define RCU_SIGNAL_INIT RCU_SAVE_DYNTICK +#else /* #ifdef CONFIG_NO_HZ */ +#define RCU_SIGNAL_INIT RCU_FORCE_QS +#endif /* #else #ifdef CONFIG_NO_HZ */ + +#define RCU_JIFFIES_TILL_FORCE_QS 3 /* for rsp->jiffies_force_qs */ +#ifdef CONFIG_RCU_CPU_STALL_DETECTOR +#define RCU_SECONDS_TILL_STALL_CHECK (10 * HZ) /* for rsp->jiffies_stall */ +#define RCU_SECONDS_TILL_STALL_RECHECK (30 * HZ) /* for rsp->jiffies_stall */ +#define RCU_STALL_RAT_DELAY 2 /* Allow other CPUs time */ + /* to take at least one */ + /* scheduling clock irq */ + /* before ratting on them. */ + +#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ + +/* + * RCU global state, including node hierarchy. This hierarchy is + * represented in "heap" form in a dense array. The root (first level) + * of the hierarchy is in ->node[0] (referenced by ->level[0]), the second + * level in ->node[1] through ->node[m] (->node[1] referenced by ->level[1]), + * and the third level in ->node[m+1] and following (->node[m+1] referenced + * by ->level[2]). The number of levels is determined by the number of + * CPUs and by CONFIG_RCU_FANOUT. Small systems will have a "hierarchy" + * consisting of a single rcu_node. + */ +struct rcu_state { + struct rcu_node node[NUM_RCU_NODES]; /* Hierarchy. */ + struct rcu_node *level[NUM_RCU_LVLS]; /* Hierarchy levels. */ + u32 levelcnt[MAX_RCU_LVLS + 1]; /* # nodes in each level. */ + u8 levelspread[NUM_RCU_LVLS]; /* kids/node in each level. */ + struct rcu_data *rda[NR_CPUS]; /* array of rdp pointers. */ + + /* The following fields are guarded by the root rcu_node's lock. */ + + u8 signaled ____cacheline_internodealigned_in_smp; + /* Force QS state. */ + long gpnum; /* Current gp number. */ + long completed; /* # of last completed gp. */ + spinlock_t onofflock; /* exclude on/offline and */ + /* starting new GP. */ + spinlock_t fqslock; /* Only one task forcing */ + /* quiescent states. */ + unsigned long jiffies_force_qs; /* Time at which to invoke */ + /* force_quiescent_state(). */ + unsigned long n_force_qs; /* Number of calls to */ + /* force_quiescent_state(). */ + unsigned long n_force_qs_lh; /* ~Number of calls leaving */ + /* due to lock unavailable. */ + unsigned long n_force_qs_ngp; /* Number of calls leaving */ + /* due to no GP active. */ +#ifdef CONFIG_RCU_CPU_STALL_DETECTOR + unsigned long gp_start; /* Time at which GP started, */ + /* but in jiffies. */ + unsigned long jiffies_stall; /* Time at which to check */ + /* for CPU stalls. */ +#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ +#ifdef CONFIG_NO_HZ + long dynticks_completed; /* Value of completed @ snap. */ +#endif /* #ifdef CONFIG_NO_HZ */ +}; + +extern struct rcu_state rcu_state; +DECLARE_PER_CPU(struct rcu_data, rcu_data); + +extern struct rcu_state rcu_bh_state; +DECLARE_PER_CPU(struct rcu_data, rcu_bh_data); + +/* + * Increment the quiescent state counter. + * The counter is a bit degenerated: We do not need to know + * how many quiescent states passed, just if there was at least + * one since the start of the grace period. Thus just a flag. + */ +static inline void rcu_qsctr_inc(int cpu) +{ + struct rcu_data *rdp = &per_cpu(rcu_data, cpu); + rdp->passed_quiesc = 1; + rdp->passed_quiesc_completed = rdp->completed; +} +static inline void rcu_bh_qsctr_inc(int cpu) +{ + struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu); + rdp->passed_quiesc = 1; + rdp->passed_quiesc_completed = rdp->completed; +} + +extern int rcu_pending(int cpu); +extern int rcu_needs_cpu(int cpu); + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +extern struct lockdep_map rcu_lock_map; +# define rcu_read_acquire() \ + lock_acquire(&rcu_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_) +# define rcu_read_release() lock_release(&rcu_lock_map, 1, _THIS_IP_) +#else +# define rcu_read_acquire() do { } while (0) +# define rcu_read_release() do { } while (0) +#endif + +static inline void __rcu_read_lock(void) +{ + preempt_disable(); + __acquire(RCU); + rcu_read_acquire(); +} +static inline void __rcu_read_unlock(void) +{ + rcu_read_release(); + __release(RCU); + preempt_enable(); +} +static inline void __rcu_read_lock_bh(void) +{ + local_bh_disable(); + __acquire(RCU_BH); + rcu_read_acquire(); +} +static inline void __rcu_read_unlock_bh(void) +{ + rcu_read_release(); + __release(RCU_BH); + local_bh_enable(); +} + +#define __synchronize_sched() synchronize_rcu() + +#define call_rcu_sched(head, func) call_rcu(head, func) + +static inline void rcu_init_sched(void) +{ +} + +extern void __rcu_init(void); +extern void rcu_check_callbacks(int cpu, int user); +extern void rcu_restart_cpu(int cpu); + +extern long rcu_batches_completed(void); +extern long rcu_batches_completed_bh(void); + +#ifdef CONFIG_NO_HZ +void rcu_enter_nohz(void); +void rcu_exit_nohz(void); +#else /* CONFIG_NO_HZ */ +static inline void rcu_enter_nohz(void) +{ +} +static inline void rcu_exit_nohz(void) +{ +} +#endif /* CONFIG_NO_HZ */ + +#endif /* __LINUX_RCUTREE_H */ diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index b18ec5533e8..325af1de035 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -7,9 +7,31 @@ struct device; struct dma_attrs; struct scatterlist; +/* + * Maximum allowable number of contiguous slabs to map, + * must be a power of 2. What is the appropriate value ? + * The complexity of {map,unmap}_single is linearly dependent on this value. + */ +#define IO_TLB_SEGSIZE 128 + + +/* + * log of the size of each IO TLB slab. The number of slabs is command line + * controllable. + */ +#define IO_TLB_SHIFT 11 + extern void swiotlb_init(void); +extern void *swiotlb_alloc_boot(size_t bytes, unsigned long nslabs); +extern void *swiotlb_alloc(unsigned order, unsigned long nslabs); + +extern dma_addr_t swiotlb_phys_to_bus(phys_addr_t address); +extern phys_addr_t swiotlb_bus_to_phys(dma_addr_t address); + +extern int swiotlb_arch_range_needs_mapping(void *ptr, size_t size); + extern void *swiotlb_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_handle, gfp_t flags); diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index fec6decfb98..6b58367d145 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -78,7 +78,7 @@ static inline unsigned long __copy_from_user_nocache(void *to, \ set_fs(KERNEL_DS); \ pagefault_disable(); \ - ret = __get_user(retval, (__force typeof(retval) __user *)(addr)); \ + ret = __copy_from_user_inatomic(&(retval), (__force typeof(retval) __user *)(addr), sizeof(retval)); \ pagefault_enable(); \ set_fs(old_fs); \ ret; \ diff --git a/init/Kconfig b/init/Kconfig index 8a63c404ef4..13627191a60 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -936,10 +936,90 @@ source "block/Kconfig" config PREEMPT_NOTIFIERS bool +choice + prompt "RCU Implementation" + default CLASSIC_RCU + config CLASSIC_RCU - def_bool !PREEMPT_RCU + bool "Classic RCU" help This option selects the classic RCU implementation that is designed for best read-side performance on non-realtime - systems. Classic RCU is the default. Note that the - PREEMPT_RCU symbol is used to select/deselect this option. + systems. + + Select this option if you are unsure. + +config TREE_RCU + bool "Tree-based hierarchical RCU" + help + This option selects the RCU implementation that is + designed for very large SMP system with hundreds or + thousands of CPUs. + +config PREEMPT_RCU + bool "Preemptible RCU" + depends on PREEMPT + help + This option reduces the latency of the kernel by making certain + RCU sections preemptible. Normally RCU code is non-preemptible, if + this option is selected then read-only RCU sections become + preemptible. This helps latency, but may expose bugs due to + now-naive assumptions about each RCU read-side critical section + remaining on a given CPU through its execution. + +endchoice + +config RCU_TRACE + bool "Enable tracing for RCU" + depends on TREE_RCU || PREEMPT_RCU + help + This option provides tracing in RCU which presents stats + in debugfs for debugging RCU implementation. + + Say Y here if you want to enable RCU tracing + Say N if you are unsure. + +config RCU_FANOUT + int "Tree-based hierarchical RCU fanout value" + range 2 64 if 64BIT + range 2 32 if !64BIT + depends on TREE_RCU + default 64 if 64BIT + default 32 if !64BIT + help + This option controls the fanout of hierarchical implementations + of RCU, allowing RCU to work efficiently on machines with + large numbers of CPUs. This value must be at least the cube + root of NR_CPUS, which allows NR_CPUS up to 32,768 for 32-bit + systems and up to 262,144 for 64-bit systems. + + Select a specific number if testing RCU itself. + Take the default if unsure. + +config RCU_FANOUT_EXACT + bool "Disable tree-based hierarchical RCU auto-balancing" + depends on TREE_RCU + default n + help + This option forces use of the exact RCU_FANOUT value specified, + regardless of imbalances in the hierarchy. This is useful for + testing RCU itself, and might one day be useful on systems with + strong NUMA behavior. + + Without RCU_FANOUT_EXACT, the code will balance the hierarchy. + + Say N if unsure. + +config TREE_RCU_TRACE + def_bool RCU_TRACE && TREE_RCU + select DEBUG_FS + help + This option provides tracing for the TREE_RCU implementation, + permitting Makefile to trivially select kernel/rcutree_trace.c. + +config PREEMPT_RCU_TRACE + def_bool RCU_TRACE && PREEMPT_RCU + select DEBUG_FS + help + This option provides tracing for the PREEMPT_RCU implementation, + permitting Makefile to trivially select kernel/rcupreempt_trace.c. diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index 9fdba03dc1f..bf987b95b35 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -52,28 +52,3 @@ config PREEMPT endchoice -config PREEMPT_RCU - bool "Preemptible RCU" - depends on PREEMPT - default n - help - This option reduces the latency of the kernel by making certain - RCU sections preemptible. Normally RCU code is non-preemptible, if - this option is selected then read-only RCU sections become - preemptible. This helps latency, but may expose bugs due to - now-naive assumptions about each RCU read-side critical section - remaining on a given CPU through its execution. - - Say N if you are unsure. - -config RCU_TRACE - bool "Enable tracing for RCU - currently stats in debugfs" - depends on PREEMPT_RCU - select DEBUG_FS - default y - help - This option provides tracing in RCU which presents stats - in debugfs for debugging RCU implementation. - - Say Y here if you want to enable RCU tracing - Say N if you are unsure. diff --git a/kernel/Makefile b/kernel/Makefile index 027edda6351..e1c5bf3365c 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -73,10 +73,10 @@ obj-$(CONFIG_GENERIC_HARDIRQS) += irq/ obj-$(CONFIG_SECCOMP) += seccomp.o obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o obj-$(CONFIG_CLASSIC_RCU) += rcuclassic.o +obj-$(CONFIG_TREE_RCU) += rcutree.o obj-$(CONFIG_PREEMPT_RCU) += rcupreempt.o -ifeq ($(CONFIG_PREEMPT_RCU),y) -obj-$(CONFIG_RCU_TRACE) += rcupreempt_trace.o -endif +obj-$(CONFIG_TREE_RCU_TRACE) += rcutree_trace.o +obj-$(CONFIG_PREEMPT_RCU_TRACE) += rcupreempt_trace.o obj-$(CONFIG_RELAY) += relay.o obj-$(CONFIG_SYSCTL) += utsname_sysctl.o obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o diff --git a/kernel/exit.c b/kernel/exit.c index c7422ca9203..a946221879d 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1328,10 +1328,10 @@ static int wait_task_zombie(struct task_struct *p, int options, * group, which consolidates times for all threads in the * group including the group leader. */ + thread_group_cputime(p, &cputime); spin_lock_irq(&p->parent->sighand->siglock); psig = p->parent->signal; sig = p->signal; - thread_group_cputime(p, &cputime); psig->cutime = cputime_add(psig->cutime, cputime_add(cputime.utime, diff --git a/kernel/extable.c b/kernel/extable.c index feb0317cf09..e136ed8d82b 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -67,3 +67,19 @@ int kernel_text_address(unsigned long addr) return 1; return module_text_address(addr) != NULL; } + +/* + * On some architectures (PPC64, IA64) function pointers + * are actually only tokens to some data that then holds the + * real function address. As a result, to find if a function + * pointer is part of the kernel text, we need to do some + * special dereferencing first. + */ +int func_ptr_is_kernel_text(void *ptr) +{ + unsigned long addr; + addr = (unsigned long) dereference_function_descriptor(ptr); + if (core_kernel_text(addr)) + return 1; + return module_text_address(addr) != NULL; +} diff --git a/kernel/futex.c b/kernel/futex.c index 4fe790e89d0..7c6cbabe52b 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -92,11 +92,12 @@ struct futex_pi_state { * A futex_q has a woken state, just like tasks have TASK_RUNNING. * It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0. * The order of wakup is always to make the first condition true, then - * wake up q->waiters, then make the second condition true. + * wake up q->waiter, then make the second condition true. */ struct futex_q { struct plist_node list; - wait_queue_head_t waiters; + /* There can only be a single waiter */ + wait_queue_head_t waiter; /* Which hash list lock to use: */ spinlock_t *lock_ptr; @@ -123,24 +124,6 @@ struct futex_hash_bucket { static struct futex_hash_bucket futex_queues[1<<FUTEX_HASHBITS]; /* - * Take mm->mmap_sem, when futex is shared - */ -static inline void futex_lock_mm(struct rw_semaphore *fshared) -{ - if (fshared) - down_read(fshared); -} - -/* - * Release mm->mmap_sem, when the futex is shared - */ -static inline void futex_unlock_mm(struct rw_semaphore *fshared) -{ - if (fshared) - up_read(fshared); -} - -/* * We hash on the keys returned from get_futex_key (see below). */ static struct futex_hash_bucket *hash_futex(union futex_key *key) @@ -161,6 +144,45 @@ static inline int match_futex(union futex_key *key1, union futex_key *key2) && key1->both.offset == key2->both.offset); } +/* + * Take a reference to the resource addressed by a key. + * Can be called while holding spinlocks. + * + */ +static void get_futex_key_refs(union futex_key *key) +{ + if (!key->both.ptr) + return; + + switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { + case FUT_OFF_INODE: + atomic_inc(&key->shared.inode->i_count); + break; + case FUT_OFF_MMSHARED: + atomic_inc(&key->private.mm->mm_count); + break; + } +} + +/* + * Drop a reference to the resource addressed by a key. + * The hash bucket spinlock must not be held. + */ +static void drop_futex_key_refs(union futex_key *key) +{ + if (!key->both.ptr) + return; + + switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { + case FUT_OFF_INODE: + iput(key->shared.inode); + break; + case FUT_OFF_MMSHARED: + mmdrop(key->private.mm); + break; + } +} + /** * get_futex_key - Get parameters which are the keys for a futex. * @uaddr: virtual address of the futex @@ -179,12 +201,10 @@ static inline int match_futex(union futex_key *key1, union futex_key *key2) * For other futexes, it points to ¤t->mm->mmap_sem and * caller must have taken the reader lock. but NOT any spinlocks. */ -static int get_futex_key(u32 __user *uaddr, struct rw_semaphore *fshared, - union futex_key *key) +static int get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key) { unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; struct page *page; int err; @@ -208,100 +228,50 @@ static int get_futex_key(u32 __user *uaddr, struct rw_semaphore *fshared, return -EFAULT; key->private.mm = mm; key->private.address = address; + get_futex_key_refs(key); return 0; } - /* - * The futex is hashed differently depending on whether - * it's in a shared or private mapping. So check vma first. - */ - vma = find_extend_vma(mm, address); - if (unlikely(!vma)) - return -EFAULT; - /* - * Permissions. - */ - if (unlikely((vma->vm_flags & (VM_IO|VM_READ)) != VM_READ)) - return (vma->vm_flags & VM_IO) ? -EPERM : -EACCES; +again: + err = get_user_pages_fast(address, 1, 0, &page); + if (err < 0) + return err; + + lock_page(page); + if (!page->mapping) { + unlock_page(page); + put_page(page); + goto again; + } /* * Private mappings are handled in a simple way. * * NOTE: When userspace waits on a MAP_SHARED mapping, even if * it's a read-only handle, it's expected that futexes attach to - * the object not the particular process. Therefore we use - * VM_MAYSHARE here, not VM_SHARED which is restricted to shared - * mappings of _writable_ handles. + * the object not the particular process. */ - if (likely(!(vma->vm_flags & VM_MAYSHARE))) { - key->both.offset |= FUT_OFF_MMSHARED; /* reference taken on mm */ + if (PageAnon(page)) { + key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */ key->private.mm = mm; key->private.address = address; - return 0; + } else { + key->both.offset |= FUT_OFF_INODE; /* inode-based key */ + key->shared.inode = page->mapping->host; + key->shared.pgoff = page->index; } - /* - * Linear file mappings are also simple. - */ - key->shared.inode = vma->vm_file->f_path.dentry->d_inode; - key->both.offset |= FUT_OFF_INODE; /* inode-based key. */ - if (likely(!(vma->vm_flags & VM_NONLINEAR))) { - key->shared.pgoff = (((address - vma->vm_start) >> PAGE_SHIFT) - + vma->vm_pgoff); - return 0; - } + get_futex_key_refs(key); - /* - * We could walk the page table to read the non-linear - * pte, and get the page index without fetching the page - * from swap. But that's a lot of code to duplicate here - * for a rare case, so we simply fetch the page. - */ - err = get_user_pages(current, mm, address, 1, 0, 0, &page, NULL); - if (err >= 0) { - key->shared.pgoff = - page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - put_page(page); - return 0; - } - return err; -} - -/* - * Take a reference to the resource addressed by a key. - * Can be called while holding spinlocks. - * - */ -static void get_futex_key_refs(union futex_key *key) -{ - if (key->both.ptr == NULL) - return; - switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { - case FUT_OFF_INODE: - atomic_inc(&key->shared.inode->i_count); - break; - case FUT_OFF_MMSHARED: - atomic_inc(&key->private.mm->mm_count); - break; - } + unlock_page(page); + put_page(page); + return 0; } -/* - * Drop a reference to the resource addressed by a key. - * The hash bucket spinlock must not be held. - */ -static void drop_futex_key_refs(union futex_key *key) +static inline +void put_futex_key(int fshared, union futex_key *key) { - if (!key->both.ptr) - return; - switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { - case FUT_OFF_INODE: - iput(key->shared.inode); - break; - case FUT_OFF_MMSHARED: - mmdrop(key->private.mm); - break; - } + drop_futex_key_refs(key); } static u32 cmpxchg_futex_value_locked(u32 __user *uaddr, u32 uval, u32 newval) @@ -328,10 +298,8 @@ static int get_futex_value_locked(u32 *dest, u32 __user *from) /* * Fault handling. - * if fshared is non NULL, current->mm->mmap_sem is already held */ -static int futex_handle_fault(unsigned long address, - struct rw_semaphore *fshared, int attempt) +static int futex_handle_fault(unsigned long address, int attempt) { struct vm_area_struct * vma; struct mm_struct *mm = current->mm; @@ -340,8 +308,7 @@ static int futex_handle_fault(unsigned long address, if (attempt > 2) return ret; - if (!fshared) - down_read(&mm->mmap_sem); + down_read(&mm->mmap_sem); vma = find_vma(mm, address); if (vma && address >= vma->vm_start && (vma->vm_flags & VM_WRITE)) { @@ -361,8 +328,7 @@ static int futex_handle_fault(unsigned long address, current->min_flt++; } } - if (!fshared) - up_read(&mm->mmap_sem); + up_read(&mm->mmap_sem); return ret; } @@ -385,6 +351,7 @@ static int refill_pi_state_cache(void) /* pi_mutex gets initialized later */ pi_state->owner = NULL; atomic_set(&pi_state->refcount, 1); + pi_state->key = FUTEX_KEY_INIT; current->pi_state_cache = pi_state; @@ -469,7 +436,7 @@ void exit_pi_state_list(struct task_struct *curr) struct list_head *next, *head = &curr->pi_state_list; struct futex_pi_state *pi_state; struct futex_hash_bucket *hb; - union futex_key key; + union futex_key key = FUTEX_KEY_INIT; if (!futex_cmpxchg_enabled) return; @@ -614,7 +581,7 @@ static void wake_futex(struct futex_q *q) * The lock in wake_up_all() is a crucial memory barrier after the * plist_del() and also before assigning to q->lock_ptr. */ - wake_up_all(&q->waiters); + wake_up(&q->waiter); /* * The waiting task can free the futex_q as soon as this is written, * without taking any locks. This must come last. @@ -726,20 +693,17 @@ double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2) * Wake up all waiters hashed on the physical page that is mapped * to this virtual address: */ -static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared, - int nr_wake, u32 bitset) +static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset) { struct futex_hash_bucket *hb; struct futex_q *this, *next; struct plist_head *head; - union futex_key key; + union futex_key key = FUTEX_KEY_INIT; int ret; if (!bitset) return -EINVAL; - futex_lock_mm(fshared); - ret = get_futex_key(uaddr, fshared, &key); if (unlikely(ret != 0)) goto out; @@ -767,7 +731,7 @@ static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared, spin_unlock(&hb->lock); out: - futex_unlock_mm(fshared); + put_futex_key(fshared, &key); return ret; } @@ -776,19 +740,16 @@ out: * to this virtual address: */ static int -futex_wake_op(u32 __user *uaddr1, struct rw_semaphore *fshared, - u32 __user *uaddr2, +futex_wake_op(u32 __user *uaddr1, int fshared, u32 __user *uaddr2, int nr_wake, int nr_wake2, int op) { - union futex_key key1, key2; + union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT; struct futex_hash_bucket *hb1, *hb2; struct plist_head *head; struct futex_q *this, *next; int ret, op_ret, attempt = 0; retryfull: - futex_lock_mm(fshared); - ret = get_futex_key(uaddr1, fshared, &key1); if (unlikely(ret != 0)) goto out; @@ -833,18 +794,12 @@ retry: */ if (attempt++) { ret = futex_handle_fault((unsigned long)uaddr2, - fshared, attempt); + attempt); if (ret) goto out; goto retry; } - /* - * If we would have faulted, release mmap_sem, - * fault it in and start all over again. - */ - futex_unlock_mm(fshared); - ret = get_user(dummy, uaddr2); if (ret) return ret; @@ -880,7 +835,8 @@ retry: if (hb1 != hb2) spin_unlock(&hb2->lock); out: - futex_unlock_mm(fshared); + put_futex_key(fshared, &key2); + put_futex_key(fshared, &key1); return ret; } @@ -889,19 +845,16 @@ out: * Requeue all waiters hashed on one physical page to another * physical page. */ -static int futex_requeue(u32 __user *uaddr1, struct rw_semaphore *fshared, - u32 __user *uaddr2, +static int futex_requeue(u32 __user *uaddr1, int fshared, u32 __user *uaddr2, int nr_wake, int nr_requeue, u32 *cmpval) { - union futex_key key1, key2; + union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT; struct futex_hash_bucket *hb1, *hb2; struct plist_head *head1; struct futex_q *this, *next; int ret, drop_count = 0; retry: - futex_lock_mm(fshared); - ret = get_futex_key(uaddr1, fshared, &key1); if (unlikely(ret != 0)) goto out; @@ -924,12 +877,6 @@ static int futex_requeue(u32 __user *uaddr1, struct rw_semaphore *fshared, if (hb1 != hb2) spin_unlock(&hb2->lock); - /* - * If we would have faulted, release mmap_sem, fault - * it in and start all over again. - */ - futex_unlock_mm(fshared); - ret = get_user(curval, uaddr1); if (!ret) @@ -981,7 +928,8 @@ out_unlock: drop_futex_key_refs(&key1); out: - futex_unlock_mm(fshared); + put_futex_key(fshared, &key2); + put_futex_key(fshared, &key1); return ret; } @@ -990,7 +938,7 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q) { struct futex_hash_bucket *hb; - init_waitqueue_head(&q->waiters); + init_waitqueue_head(&q->waiter); get_futex_key_refs(&q->key); hb = hash_futex(&q->key); @@ -1103,8 +1051,7 @@ static void unqueue_me_pi(struct futex_q *q) * private futexes. */ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, - struct task_struct *newowner, - struct rw_semaphore *fshared) + struct task_struct *newowner, int fshared) { u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS; struct futex_pi_state *pi_state = q->pi_state; @@ -1183,7 +1130,7 @@ retry: handle_fault: spin_unlock(q->lock_ptr); - ret = futex_handle_fault((unsigned long)uaddr, fshared, attempt++); + ret = futex_handle_fault((unsigned long)uaddr, attempt++); spin_lock(q->lock_ptr); @@ -1203,12 +1150,13 @@ handle_fault: * In case we must use restart_block to restart a futex_wait, * we encode in the 'flags' shared capability */ -#define FLAGS_SHARED 1 +#define FLAGS_SHARED 0x01 +#define FLAGS_CLOCKRT 0x02 static long futex_wait_restart(struct restart_block *restart); -static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, - u32 val, ktime_t *abs_time, u32 bitset) +static int futex_wait(u32 __user *uaddr, int fshared, + u32 val, ktime_t *abs_time, u32 bitset, int clockrt) { struct task_struct *curr = current; DECLARE_WAITQUEUE(wait, curr); @@ -1225,8 +1173,7 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, q.pi_state = NULL; q.bitset = bitset; retry: - futex_lock_mm(fshared); - + q.key = FUTEX_KEY_INIT; ret = get_futex_key(uaddr, fshared, &q.key); if (unlikely(ret != 0)) goto out_release_sem; @@ -1258,12 +1205,6 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, if (unlikely(ret)) { queue_unlock(&q, hb); - /* - * If we would have faulted, release mmap_sem, fault it in and - * start all over again. - */ - futex_unlock_mm(fshared); - ret = get_user(uval, uaddr); if (!ret) @@ -1278,12 +1219,6 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, queue_me(&q, hb); /* - * Now the futex is queued and we have checked the data, we - * don't want to hold mmap_sem while we sleep. - */ - futex_unlock_mm(fshared); - - /* * There might have been scheduling since the queue_me(), as we * cannot hold a spinlock across the get_user() in case it * faults, and we cannot just set TASK_INTERRUPTIBLE state when @@ -1294,7 +1229,7 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, /* add_wait_queue is the barrier after __set_current_state. */ __set_current_state(TASK_INTERRUPTIBLE); - add_wait_queue(&q.waiters, &wait); + add_wait_queue(&q.waiter, &wait); /* * !plist_node_empty() is safe here without any lock. * q.lock_ptr != 0 is not safe, because of ordering against wakeup. @@ -1307,8 +1242,10 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, slack = current->timer_slack_ns; if (rt_task(current)) slack = 0; - hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, - HRTIMER_MODE_ABS); + hrtimer_init_on_stack(&t.timer, + clockrt ? CLOCK_REALTIME : + CLOCK_MONOTONIC, + HRTIMER_MODE_ABS); hrtimer_init_sleeper(&t, current); hrtimer_set_expires_range_ns(&t.timer, *abs_time, slack); @@ -1363,6 +1300,8 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, if (fshared) restart->futex.flags |= FLAGS_SHARED; + if (clockrt) + restart->futex.flags |= FLAGS_CLOCKRT; return -ERESTART_RESTARTBLOCK; } @@ -1370,7 +1309,7 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, queue_unlock(&q, hb); out_release_sem: - futex_unlock_mm(fshared); + put_futex_key(fshared, &q.key); return ret; } @@ -1378,15 +1317,16 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, static long futex_wait_restart(struct restart_block *restart) { u32 __user *uaddr = (u32 __user *)restart->futex.uaddr; - struct rw_semaphore *fshared = NULL; + int fshared = 0; ktime_t t; t.tv64 = restart->futex.time; restart->fn = do_no_restart_syscall; if (restart->futex.flags & FLAGS_SHARED) - fshared = ¤t->mm->mmap_sem; + fshared = 1; return (long)futex_wait(uaddr, fshared, restart->futex.val, &t, - restart->futex.bitset); + restart->futex.bitset, + restart->futex.flags & FLAGS_CLOCKRT); } @@ -1396,7 +1336,7 @@ static long futex_wait_restart(struct restart_block *restart) * if there are waiters then it will block, it does PI, etc. (Due to * races the kernel might see a 0 value of the futex too.) */ -static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, +static int futex_lock_pi(u32 __user *uaddr, int fshared, int detect, ktime_t *time, int trylock) { struct hrtimer_sleeper timeout, *to = NULL; @@ -1419,8 +1359,7 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, q.pi_state = NULL; retry: - futex_lock_mm(fshared); - + q.key = FUTEX_KEY_INIT; ret = get_futex_key(uaddr, fshared, &q.key); if (unlikely(ret != 0)) goto out_release_sem; @@ -1509,7 +1448,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, * exit to complete. */ queue_unlock(&q, hb); - futex_unlock_mm(fshared); cond_resched(); goto retry; @@ -1541,12 +1479,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, */ queue_me(&q, hb); - /* - * Now the futex is queued and we have checked the data, we - * don't want to hold mmap_sem while we sleep. - */ - futex_unlock_mm(fshared); - WARN_ON(!q.pi_state); /* * Block on the PI mutex: @@ -1559,7 +1491,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, ret = ret ? 0 : -EWOULDBLOCK; } - futex_lock_mm(fshared); spin_lock(q.lock_ptr); if (!ret) { @@ -1625,7 +1556,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, /* Unqueue and drop the lock */ unqueue_me_pi(&q); - futex_unlock_mm(fshared); if (to) destroy_hrtimer_on_stack(&to->timer); @@ -1635,34 +1565,30 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, queue_unlock(&q, hb); out_release_sem: - futex_unlock_mm(fshared); + put_futex_key(fshared, &q.key); if (to) destroy_hrtimer_on_stack(&to->timer); return ret; uaddr_faulted: /* - * We have to r/w *(int __user *)uaddr, but we can't modify it - * non-atomically. Therefore, if get_user below is not - * enough, we need to handle the fault ourselves, while - * still holding the mmap_sem. - * - * ... and hb->lock. :-) --ANK + * We have to r/w *(int __user *)uaddr, and we have to modify it + * atomically. Therefore, if we continue to fault after get_user() + * below, we need to handle the fault ourselves, while still holding + * the mmap_sem. This can occur if the uaddr is under contention as + * we have to drop the mmap_sem in order to call get_user(). */ queue_unlock(&q, hb); if (attempt++) { - ret = futex_handle_fault((unsigned long)uaddr, fshared, - attempt); + ret = futex_handle_fault((unsigned long)uaddr, attempt); if (ret) goto out_release_sem; goto retry_unlocked; } - futex_unlock_mm(fshared); - ret = get_user(uval, uaddr); - if (!ret && (uval != -EFAULT)) + if (!ret) goto retry; if (to) @@ -1675,13 +1601,13 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, * This is the in-kernel slowpath: we look up the PI state (if any), * and do the rt-mutex unlock. */ -static int futex_unlock_pi(u32 __user *uaddr, struct rw_semaphore *fshared) +static int futex_unlock_pi(u32 __user *uaddr, int fshared) { struct futex_hash_bucket *hb; struct futex_q *this, *next; u32 uval; struct plist_head *head; - union futex_key key; + union futex_key key = FUTEX_KEY_INIT; int ret, attempt = 0; retry: @@ -1692,10 +1618,6 @@ retry: */ if ((uval & FUTEX_TID_MASK) != task_pid_vnr(current)) return -EPERM; - /* - * First take all the futex related locks: - */ - futex_lock_mm(fshared); ret = get_futex_key(uaddr, fshared, &key); if (unlikely(ret != 0)) @@ -1754,34 +1676,30 @@ retry_unlocked: out_unlock: spin_unlock(&hb->lock); out: - futex_unlock_mm(fshared); + put_futex_key(fshared, &key); return ret; pi_faulted: /* - * We have to r/w *(int __user *)uaddr, but we can't modify it - * non-atomically. Therefore, if get_user below is not - * enough, we need to handle the fault ourselves, while - * still holding the mmap_sem. - * - * ... and hb->lock. --ANK + * We have to r/w *(int __user *)uaddr, and we have to modify it + * atomically. Therefore, if we continue to fault after get_user() + * below, we need to handle the fault ourselves, while still holding + * the mmap_sem. This can occur if the uaddr is under contention as + * we have to drop the mmap_sem in order to call get_user(). */ spin_unlock(&hb->lock); if (attempt++) { - ret = futex_handle_fault((unsigned long)uaddr, fshared, - attempt); + ret = futex_handle_fault((unsigned long)uaddr, attempt); if (ret) goto out; uval = 0; goto retry_unlocked; } - futex_unlock_mm(fshared); - ret = get_user(uval, uaddr); - if (!ret && (uval != -EFAULT)) + if (!ret) goto retry; return ret; @@ -1908,8 +1826,7 @@ retry: * PI futexes happens in exit_pi_state(): */ if (!pi && (uval & FUTEX_WAITERS)) - futex_wake(uaddr, &curr->mm->mmap_sem, 1, - FUTEX_BITSET_MATCH_ANY); + futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY); } return 0; } @@ -2003,18 +1920,22 @@ void exit_robust_list(struct task_struct *curr) long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3) { - int ret = -ENOSYS; + int clockrt, ret = -ENOSYS; int cmd = op & FUTEX_CMD_MASK; - struct rw_semaphore *fshared = NULL; + int fshared = 0; if (!(op & FUTEX_PRIVATE_FLAG)) - fshared = ¤t->mm->mmap_sem; + fshared = 1; + + clockrt = op & FUTEX_CLOCK_REALTIME; + if (clockrt && cmd != FUTEX_WAIT_BITSET) + return -ENOSYS; switch (cmd) { case FUTEX_WAIT: val3 = FUTEX_BITSET_MATCH_ANY; case FUTEX_WAIT_BITSET: - ret = futex_wait(uaddr, fshared, val, timeout, val3); + ret = futex_wait(uaddr, fshared, val, timeout, val3, clockrt); break; case FUTEX_WAKE: val3 = FUTEX_BITSET_MATCH_ANY; diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 801addda3c4..e9d1c8205a3 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -673,6 +673,18 @@ int request_irq(unsigned int irq, irq_handler_t handler, struct irq_desc *desc; int retval; + /* + * handle_IRQ_event() always ignores IRQF_DISABLED except for + * the _first_ irqaction (sigh). That can cause oopsing, but + * the behavior is classified as "will not fix" so we need to + * start nudging drivers away from using that idiom. + */ + if ((irqflags & (IRQF_SHARED|IRQF_DISABLED)) + == (IRQF_SHARED|IRQF_DISABLED)) + pr_warning("IRQ %d/%s: IRQF_DISABLED is not " + "guaranteed on shared IRQs\n", + irq, devname); + #ifdef CONFIG_LOCKDEP /* * Lockdep wants atomic interrupt handlers: diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 74b1878b8bb..06b0c3568f0 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -137,16 +137,16 @@ static inline struct lock_class *hlock_class(struct held_lock *hlock) #ifdef CONFIG_LOCK_STAT static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], lock_stats); -static int lock_contention_point(struct lock_class *class, unsigned long ip) +static int lock_point(unsigned long points[], unsigned long ip) { int i; - for (i = 0; i < ARRAY_SIZE(class->contention_point); i++) { - if (class->contention_point[i] == 0) { - class->contention_point[i] = ip; + for (i = 0; i < LOCKSTAT_POINTS; i++) { + if (points[i] == 0) { + points[i] = ip; break; } - if (class->contention_point[i] == ip) + if (points[i] == ip) break; } @@ -186,6 +186,9 @@ struct lock_class_stats lock_stats(struct lock_class *class) for (i = 0; i < ARRAY_SIZE(stats.contention_point); i++) stats.contention_point[i] += pcs->contention_point[i]; + for (i = 0; i < ARRAY_SIZE(stats.contending_point); i++) + stats.contending_point[i] += pcs->contending_point[i]; + lock_time_add(&pcs->read_waittime, &stats.read_waittime); lock_time_add(&pcs->write_waittime, &stats.write_waittime); @@ -210,6 +213,7 @@ void clear_lock_stats(struct lock_class *class) memset(cpu_stats, 0, sizeof(struct lock_class_stats)); } memset(class->contention_point, 0, sizeof(class->contention_point)); + memset(class->contending_point, 0, sizeof(class->contending_point)); } static struct lock_class_stats *get_lock_stats(struct lock_class *class) @@ -288,14 +292,12 @@ void lockdep_off(void) { current->lockdep_recursion++; } - EXPORT_SYMBOL(lockdep_off); void lockdep_on(void) { current->lockdep_recursion--; } - EXPORT_SYMBOL(lockdep_on); /* @@ -577,7 +579,8 @@ static void print_lock_class_header(struct lock_class *class, int depth) /* * printk all lock dependencies starting at <entry>: */ -static void print_lock_dependencies(struct lock_class *class, int depth) +static void __used +print_lock_dependencies(struct lock_class *class, int depth) { struct lock_list *entry; @@ -2509,7 +2512,6 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name, if (subclass) register_lock_class(lock, subclass, 1); } - EXPORT_SYMBOL_GPL(lockdep_init_map); /* @@ -2690,8 +2692,9 @@ static int check_unlock(struct task_struct *curr, struct lockdep_map *lock, } static int -__lock_set_subclass(struct lockdep_map *lock, - unsigned int subclass, unsigned long ip) +__lock_set_class(struct lockdep_map *lock, const char *name, + struct lock_class_key *key, unsigned int subclass, + unsigned long ip) { struct task_struct *curr = current; struct held_lock *hlock, *prev_hlock; @@ -2718,6 +2721,7 @@ __lock_set_subclass(struct lockdep_map *lock, return print_unlock_inbalance_bug(curr, lock, ip); found_it: + lockdep_init_map(lock, name, key, 0); class = register_lock_class(lock, subclass, 0); hlock->class_idx = class - lock_classes + 1; @@ -2902,9 +2906,9 @@ static void check_flags(unsigned long flags) #endif } -void -lock_set_subclass(struct lockdep_map *lock, - unsigned int subclass, unsigned long ip) +void lock_set_class(struct lockdep_map *lock, const char *name, + struct lock_class_key *key, unsigned int subclass, + unsigned long ip) { unsigned long flags; @@ -2914,13 +2918,12 @@ lock_set_subclass(struct lockdep_map *lock, raw_local_irq_save(flags); current->lockdep_recursion = 1; check_flags(flags); - if (__lock_set_subclass(lock, subclass, ip)) + if (__lock_set_class(lock, name, key, subclass, ip)) check_chain_key(current); current->lockdep_recursion = 0; raw_local_irq_restore(flags); } - -EXPORT_SYMBOL_GPL(lock_set_subclass); +EXPORT_SYMBOL_GPL(lock_set_class); /* * We are not always called with irqs disabled - do that here, @@ -2944,7 +2947,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, current->lockdep_recursion = 0; raw_local_irq_restore(flags); } - EXPORT_SYMBOL_GPL(lock_acquire); void lock_release(struct lockdep_map *lock, int nested, @@ -2962,7 +2964,6 @@ void lock_release(struct lockdep_map *lock, int nested, current->lockdep_recursion = 0; raw_local_irq_restore(flags); } - EXPORT_SYMBOL_GPL(lock_release); #ifdef CONFIG_LOCK_STAT @@ -3000,7 +3001,7 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip) struct held_lock *hlock, *prev_hlock; struct lock_class_stats *stats; unsigned int depth; - int i, point; + int i, contention_point, contending_point; depth = curr->lockdep_depth; if (DEBUG_LOCKS_WARN_ON(!depth)) @@ -3024,18 +3025,22 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip) found_it: hlock->waittime_stamp = sched_clock(); - point = lock_contention_point(hlock_class(hlock), ip); + contention_point = lock_point(hlock_class(hlock)->contention_point, ip); + contending_point = lock_point(hlock_class(hlock)->contending_point, + lock->ip); stats = get_lock_stats(hlock_class(hlock)); - if (point < ARRAY_SIZE(stats->contention_point)) - stats->contention_point[point]++; + if (contention_point < LOCKSTAT_POINTS) + stats->contention_point[contention_point]++; + if (contending_point < LOCKSTAT_POINTS) + stats->contending_point[contending_point]++; if (lock->cpu != smp_processor_id()) stats->bounces[bounce_contended + !!hlock->read]++; put_lock_stats(stats); } static void -__lock_acquired(struct lockdep_map *lock) +__lock_acquired(struct lockdep_map *lock, unsigned long ip) { struct task_struct *curr = current; struct held_lock *hlock, *prev_hlock; @@ -3084,6 +3089,7 @@ found_it: put_lock_stats(stats); lock->cpu = cpu; + lock->ip = ip; } void lock_contended(struct lockdep_map *lock, unsigned long ip) @@ -3105,7 +3111,7 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip) } EXPORT_SYMBOL_GPL(lock_contended); -void lock_acquired(struct lockdep_map *lock) +void lock_acquired(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; @@ -3118,7 +3124,7 @@ void lock_acquired(struct lockdep_map *lock) raw_local_irq_save(flags); check_flags(flags); current->lockdep_recursion = 1; - __lock_acquired(lock); + __lock_acquired(lock, ip); current->lockdep_recursion = 0; raw_local_irq_restore(flags); } @@ -3442,7 +3448,6 @@ retry: if (unlock) read_unlock(&tasklist_lock); } - EXPORT_SYMBOL_GPL(debug_show_all_locks); /* @@ -3463,7 +3468,6 @@ void debug_show_held_locks(struct task_struct *task) { __debug_show_held_locks(task); } - EXPORT_SYMBOL_GPL(debug_show_held_locks); void lockdep_sys_exit(void) diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c index 20dbcbf9c7d..13716b81389 100644 --- a/kernel/lockdep_proc.c +++ b/kernel/lockdep_proc.c @@ -470,11 +470,12 @@ static void seq_line(struct seq_file *m, char c, int offset, int length) static void snprint_time(char *buf, size_t bufsiz, s64 nr) { - unsigned long rem; + s64 div; + s32 rem; nr += 5; /* for display rounding */ - rem = do_div(nr, 1000); /* XXX: do_div_signed */ - snprintf(buf, bufsiz, "%lld.%02d", (long long)nr, (int)rem/10); + div = div_s64_rem(nr, 1000, &rem); + snprintf(buf, bufsiz, "%lld.%02d", (long long)div, (int)rem/10); } static void seq_time(struct seq_file *m, s64 time) @@ -556,7 +557,7 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data) if (stats->read_holdtime.nr) namelen += 2; - for (i = 0; i < ARRAY_SIZE(class->contention_point); i++) { + for (i = 0; i < LOCKSTAT_POINTS; i++) { char sym[KSYM_SYMBOL_LEN]; char ip[32]; @@ -573,6 +574,23 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data) stats->contention_point[i], ip, sym); } + for (i = 0; i < LOCKSTAT_POINTS; i++) { + char sym[KSYM_SYMBOL_LEN]; + char ip[32]; + + if (class->contending_point[i] == 0) + break; + + if (!i) + seq_line(m, '-', 40-namelen, namelen); + + sprint_symbol(sym, class->contending_point[i]); + snprintf(ip, sizeof(ip), "[<%p>]", + (void *)class->contending_point[i]); + seq_printf(m, "%40s %14lu %29s %s\n", name, + stats->contending_point[i], + ip, sym); + } if (i) { seq_puts(m, "\n"); seq_line(m, '.', 0, 40 + 1 + 10 * (14 + 1)); @@ -582,7 +600,7 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data) static void seq_header(struct seq_file *m) { - seq_printf(m, "lock_stat version 0.2\n"); + seq_printf(m, "lock_stat version 0.3\n"); seq_line(m, '-', 0, 40 + 1 + 10 * (14 + 1)); seq_printf(m, "%40s %14s %14s %14s %14s %14s %14s %14s %14s " "%14s %14s\n", diff --git a/kernel/mutex.c b/kernel/mutex.c index 12c779dc65d..4f45d4b658e 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -59,7 +59,7 @@ EXPORT_SYMBOL(__mutex_init); * We also put the fastpath first in the kernel image, to make sure the * branch is predicted by the CPU as default-untaken. */ -static void noinline __sched +static __used noinline void __sched __mutex_lock_slowpath(atomic_t *lock_count); /*** @@ -96,7 +96,7 @@ void inline __sched mutex_lock(struct mutex *lock) EXPORT_SYMBOL(mutex_lock); #endif -static noinline void __sched __mutex_unlock_slowpath(atomic_t *lock_count); +static __used noinline void __sched __mutex_unlock_slowpath(atomic_t *lock_count); /*** * mutex_unlock - release the mutex @@ -184,7 +184,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, } done: - lock_acquired(&lock->dep_map); + lock_acquired(&lock->dep_map, ip); /* got the lock - rejoice! */ mutex_remove_waiter(lock, &waiter, task_thread_info(task)); debug_mutex_set_owner(lock, task_thread_info(task)); @@ -268,7 +268,7 @@ __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested) /* * Release the lock, slowpath: */ -static noinline void +static __used noinline void __mutex_unlock_slowpath(atomic_t *lock_count) { __mutex_unlock_common_slowpath(lock_count, 1); @@ -313,7 +313,7 @@ int __sched mutex_lock_killable(struct mutex *lock) } EXPORT_SYMBOL(mutex_lock_killable); -static noinline void __sched +static __used noinline void __sched __mutex_lock_slowpath(atomic_t *lock_count) { struct mutex *lock = container_of(lock_count, struct mutex, count); diff --git a/kernel/notifier.c b/kernel/notifier.c index 4282c0a40a5..61d5aa5eced 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -82,6 +82,14 @@ static int __kprobes notifier_call_chain(struct notifier_block **nl, while (nb && nr_to_call) { next_nb = rcu_dereference(nb->next); + +#ifdef CONFIG_DEBUG_NOTIFIERS + if (unlikely(!func_ptr_is_kernel_text(nb->notifier_call))) { + WARN(1, "Invalid notifier called!"); + nb = next_nb; + continue; + } +#endif ret = nb->notifier_call(nb, val, v); if (nr_calls) diff --git a/kernel/panic.c b/kernel/panic.c index 4d5088355bf..13f06349a78 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -21,6 +21,7 @@ #include <linux/debug_locks.h> #include <linux/random.h> #include <linux/kallsyms.h> +#include <linux/dmi.h> int panic_on_oops; static unsigned long tainted_mask; @@ -321,36 +322,27 @@ void oops_exit(void) } #ifdef WANT_WARN_ON_SLOWPATH -void warn_on_slowpath(const char *file, int line) -{ - char function[KSYM_SYMBOL_LEN]; - unsigned long caller = (unsigned long) __builtin_return_address(0); - sprint_symbol(function, caller); - - printk(KERN_WARNING "------------[ cut here ]------------\n"); - printk(KERN_WARNING "WARNING: at %s:%d %s()\n", file, - line, function); - print_modules(); - dump_stack(); - print_oops_end_marker(); - add_taint(TAINT_WARN); -} -EXPORT_SYMBOL(warn_on_slowpath); - - void warn_slowpath(const char *file, int line, const char *fmt, ...) { va_list args; char function[KSYM_SYMBOL_LEN]; unsigned long caller = (unsigned long)__builtin_return_address(0); + const char *board; + sprint_symbol(function, caller); printk(KERN_WARNING "------------[ cut here ]------------\n"); printk(KERN_WARNING "WARNING: at %s:%d %s()\n", file, line, function); - va_start(args, fmt); - vprintk(fmt, args); - va_end(args); + board = dmi_get_system_info(DMI_PRODUCT_NAME); + if (board) + printk(KERN_WARNING "Hardware name: %s\n", board); + + if (fmt) { + va_start(args, fmt); + vprintk(fmt, args); + va_end(args); + } print_modules(); dump_stack(); diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 4e5288a831d..157de3a4783 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -58,21 +58,21 @@ void thread_group_cputime( struct task_struct *tsk, struct task_cputime *times) { - struct signal_struct *sig; + struct task_cputime *totals, *tot; int i; - struct task_cputime *tot; - sig = tsk->signal; - if (unlikely(!sig) || !sig->cputime.totals) { + totals = tsk->signal->cputime.totals; + if (!totals) { times->utime = tsk->utime; times->stime = tsk->stime; times->sum_exec_runtime = tsk->se.sum_exec_runtime; return; } + times->stime = times->utime = cputime_zero; times->sum_exec_runtime = 0; for_each_possible_cpu(i) { - tot = per_cpu_ptr(tsk->signal->cputime.totals, i); + tot = per_cpu_ptr(totals, i); times->utime = cputime_add(times->utime, tot->utime); times->stime = cputime_add(times->stime, tot->stime); times->sum_exec_runtime += tot->sum_exec_runtime; diff --git a/kernel/printk.c b/kernel/printk.c index f492f1583d7..e651ab05655 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -662,7 +662,7 @@ asmlinkage int vprintk(const char *fmt, va_list args) if (recursion_bug) { recursion_bug = 0; strcpy(printk_buf, recursion_bug_msg); - printed_len = sizeof(recursion_bug_msg); + printed_len = strlen(recursion_bug_msg); } /* Emit the output into the temporary buffer */ printed_len += vscnprintf(printk_buf + printed_len, diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c index 37f72e55154..e503a002f33 100644 --- a/kernel/rcuclassic.c +++ b/kernel/rcuclassic.c @@ -191,7 +191,7 @@ static void print_other_cpu_stall(struct rcu_ctrlblk *rcp) /* OK, time to rat on our buddy... */ - printk(KERN_ERR "RCU detected CPU stalls:"); + printk(KERN_ERR "INFO: RCU detected CPU stalls:"); for_each_possible_cpu(cpu) { if (cpu_isset(cpu, rcp->cpumask)) printk(" %d", cpu); @@ -204,7 +204,7 @@ static void print_cpu_stall(struct rcu_ctrlblk *rcp) { unsigned long flags; - printk(KERN_ERR "RCU detected CPU %d stall (t=%lu/%lu jiffies)\n", + printk(KERN_ERR "INFO: RCU detected CPU %d stall (t=%lu/%lu jiffies)\n", smp_processor_id(), jiffies, jiffies - rcp->gp_start); dump_stack(); diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c index 59236e8b9da..04982659875 100644 --- a/kernel/rcupreempt.c +++ b/kernel/rcupreempt.c @@ -551,6 +551,16 @@ void rcu_irq_exit(void) } } +void rcu_nmi_enter(void) +{ + rcu_irq_enter(); +} + +void rcu_nmi_exit(void) +{ + rcu_irq_exit(); +} + static void dyntick_save_progress_counter(int cpu) { struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu); diff --git a/kernel/rcupreempt_trace.c b/kernel/rcupreempt_trace.c index 35c2d3360ec..7c2665cac17 100644 --- a/kernel/rcupreempt_trace.c +++ b/kernel/rcupreempt_trace.c @@ -149,12 +149,12 @@ static void rcupreempt_trace_sum(struct rcupreempt_trace *sp) sp->done_length += cp->done_length; sp->done_add += cp->done_add; sp->done_remove += cp->done_remove; - atomic_set(&sp->done_invoked, atomic_read(&cp->done_invoked)); + atomic_add(atomic_read(&cp->done_invoked), &sp->done_invoked); sp->rcu_check_callbacks += cp->rcu_check_callbacks; - atomic_set(&sp->rcu_try_flip_1, - atomic_read(&cp->rcu_try_flip_1)); - atomic_set(&sp->rcu_try_flip_e1, - atomic_read(&cp->rcu_try_flip_e1)); + atomic_add(atomic_read(&cp->rcu_try_flip_1), + &sp->rcu_try_flip_1); + atomic_add(atomic_read(&cp->rcu_try_flip_e1), + &sp->rcu_try_flip_e1); sp->rcu_try_flip_i1 += cp->rcu_try_flip_i1; sp->rcu_try_flip_ie1 += cp->rcu_try_flip_ie1; sp->rcu_try_flip_g1 += cp->rcu_try_flip_g1; diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 85cb90588a5..b3106552210 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -39,6 +39,7 @@ #include <linux/moduleparam.h> #include <linux/percpu.h> #include <linux/notifier.h> +#include <linux/reboot.h> #include <linux/freezer.h> #include <linux/cpu.h> #include <linux/delay.h> @@ -108,7 +109,6 @@ struct rcu_torture { int rtort_mbtest; }; -static int fullstop = 0; /* stop generating callbacks at test end. */ static LIST_HEAD(rcu_torture_freelist); static struct rcu_torture *rcu_torture_current = NULL; static long rcu_torture_current_version = 0; @@ -136,6 +136,30 @@ static int stutter_pause_test = 0; #endif int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT; +#define FULLSTOP_SIGNALED 1 /* Bail due to signal. */ +#define FULLSTOP_CLEANUP 2 /* Orderly shutdown. */ +static int fullstop; /* stop generating callbacks at test end. */ +DEFINE_MUTEX(fullstop_mutex); /* protect fullstop transitions and */ + /* spawning of kthreads. */ + +/* + * Detect and respond to a signal-based shutdown. + */ +static int +rcutorture_shutdown_notify(struct notifier_block *unused1, + unsigned long unused2, void *unused3) +{ + if (fullstop) + return NOTIFY_DONE; + if (signal_pending(current)) { + mutex_lock(&fullstop_mutex); + if (!ACCESS_ONCE(fullstop)) + fullstop = FULLSTOP_SIGNALED; + mutex_unlock(&fullstop_mutex); + } + return NOTIFY_DONE; +} + /* * Allocate an element from the rcu_tortures pool. */ @@ -199,11 +223,12 @@ rcu_random(struct rcu_random_state *rrsp) static void rcu_stutter_wait(void) { - while (stutter_pause_test || !rcutorture_runnable) + while ((stutter_pause_test || !rcutorture_runnable) && !fullstop) { if (rcutorture_runnable) schedule_timeout_interruptible(1); else schedule_timeout_interruptible(round_jiffies_relative(HZ)); + } } /* @@ -599,7 +624,7 @@ rcu_torture_writer(void *arg) rcu_stutter_wait(); } while (!kthread_should_stop() && !fullstop); VERBOSE_PRINTK_STRING("rcu_torture_writer task stopping"); - while (!kthread_should_stop()) + while (!kthread_should_stop() && fullstop != FULLSTOP_SIGNALED) schedule_timeout_uninterruptible(1); return 0; } @@ -624,7 +649,7 @@ rcu_torture_fakewriter(void *arg) } while (!kthread_should_stop() && !fullstop); VERBOSE_PRINTK_STRING("rcu_torture_fakewriter task stopping"); - while (!kthread_should_stop()) + while (!kthread_should_stop() && fullstop != FULLSTOP_SIGNALED) schedule_timeout_uninterruptible(1); return 0; } @@ -734,7 +759,7 @@ rcu_torture_reader(void *arg) VERBOSE_PRINTK_STRING("rcu_torture_reader task stopping"); if (irqreader && cur_ops->irqcapable) del_timer_sync(&t); - while (!kthread_should_stop()) + while (!kthread_should_stop() && fullstop != FULLSTOP_SIGNALED) schedule_timeout_uninterruptible(1); return 0; } @@ -831,7 +856,7 @@ rcu_torture_stats(void *arg) do { schedule_timeout_interruptible(stat_interval * HZ); rcu_torture_stats_print(); - } while (!kthread_should_stop()); + } while (!kthread_should_stop() && !fullstop); VERBOSE_PRINTK_STRING("rcu_torture_stats task stopping"); return 0; } @@ -899,7 +924,7 @@ rcu_torture_shuffle(void *arg) do { schedule_timeout_interruptible(shuffle_interval * HZ); rcu_torture_shuffle_tasks(); - } while (!kthread_should_stop()); + } while (!kthread_should_stop() && !fullstop); VERBOSE_PRINTK_STRING("rcu_torture_shuffle task stopping"); return 0; } @@ -914,10 +939,10 @@ rcu_torture_stutter(void *arg) do { schedule_timeout_interruptible(stutter * HZ); stutter_pause_test = 1; - if (!kthread_should_stop()) + if (!kthread_should_stop() && !fullstop) schedule_timeout_interruptible(stutter * HZ); stutter_pause_test = 0; - } while (!kthread_should_stop()); + } while (!kthread_should_stop() && !fullstop); VERBOSE_PRINTK_STRING("rcu_torture_stutter task stopping"); return 0; } @@ -934,12 +959,27 @@ rcu_torture_print_module_parms(char *tag) stutter, irqreader); } +static struct notifier_block rcutorture_nb = { + .notifier_call = rcutorture_shutdown_notify, +}; + static void rcu_torture_cleanup(void) { int i; - fullstop = 1; + mutex_lock(&fullstop_mutex); + if (!fullstop) { + /* If being signaled, let it happen, then exit. */ + mutex_unlock(&fullstop_mutex); + schedule_timeout_interruptible(10 * HZ); + if (cur_ops->cb_barrier != NULL) + cur_ops->cb_barrier(); + return; + } + fullstop = FULLSTOP_CLEANUP; + mutex_unlock(&fullstop_mutex); + unregister_reboot_notifier(&rcutorture_nb); if (stutter_task) { VERBOSE_PRINTK_STRING("Stopping rcu_torture_stutter task"); kthread_stop(stutter_task); @@ -1015,6 +1055,8 @@ rcu_torture_init(void) { &rcu_ops, &rcu_sync_ops, &rcu_bh_ops, &rcu_bh_sync_ops, &srcu_ops, &sched_ops, &sched_ops_sync, }; + mutex_lock(&fullstop_mutex); + /* Process args and tell the world that the torturer is on the job. */ for (i = 0; i < ARRAY_SIZE(torture_ops); i++) { cur_ops = torture_ops[i]; @@ -1024,6 +1066,7 @@ rcu_torture_init(void) if (i == ARRAY_SIZE(torture_ops)) { printk(KERN_ALERT "rcutorture: invalid torture type: \"%s\"\n", torture_type); + mutex_unlock(&fullstop_mutex); return (-EINVAL); } if (cur_ops->init) @@ -1146,9 +1189,12 @@ rcu_torture_init(void) goto unwind; } } + register_reboot_notifier(&rcutorture_nb); + mutex_unlock(&fullstop_mutex); return 0; unwind: + mutex_unlock(&fullstop_mutex); rcu_torture_cleanup(); return firsterr; } diff --git a/kernel/rcutree.c b/kernel/rcutree.c new file mode 100644 index 00000000000..a342b032112 --- /dev/null +++ b/kernel/rcutree.c @@ -0,0 +1,1535 @@ +/* + * Read-Copy Update mechanism for mutual exclusion + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright IBM Corporation, 2008 + * + * Authors: Dipankar Sarma <dipankar@in.ibm.com> + * Manfred Spraul <manfred@colorfullife.com> + * Paul E. McKenney <paulmck@linux.vnet.ibm.com> Hierarchical version + * + * Based on the original work by Paul McKenney <paulmck@us.ibm.com> + * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. + * + * For detailed explanation of Read-Copy Update mechanism see - + * Documentation/RCU + */ +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/spinlock.h> +#include <linux/smp.h> +#include <linux/rcupdate.h> +#include <linux/interrupt.h> +#include <linux/sched.h> +#include <asm/atomic.h> +#include <linux/bitops.h> +#include <linux/module.h> +#include <linux/completion.h> +#include <linux/moduleparam.h> +#include <linux/percpu.h> +#include <linux/notifier.h> +#include <linux/cpu.h> +#include <linux/mutex.h> +#include <linux/time.h> + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +static struct lock_class_key rcu_lock_key; +struct lockdep_map rcu_lock_map = + STATIC_LOCKDEP_MAP_INIT("rcu_read_lock", &rcu_lock_key); +EXPORT_SYMBOL_GPL(rcu_lock_map); +#endif + +/* Data structures. */ + +#define RCU_STATE_INITIALIZER(name) { \ + .level = { &name.node[0] }, \ + .levelcnt = { \ + NUM_RCU_LVL_0, /* root of hierarchy. */ \ + NUM_RCU_LVL_1, \ + NUM_RCU_LVL_2, \ + NUM_RCU_LVL_3, /* == MAX_RCU_LVLS */ \ + }, \ + .signaled = RCU_SIGNAL_INIT, \ + .gpnum = -300, \ + .completed = -300, \ + .onofflock = __SPIN_LOCK_UNLOCKED(&name.onofflock), \ + .fqslock = __SPIN_LOCK_UNLOCKED(&name.fqslock), \ + .n_force_qs = 0, \ + .n_force_qs_ngp = 0, \ +} + +struct rcu_state rcu_state = RCU_STATE_INITIALIZER(rcu_state); +DEFINE_PER_CPU(struct rcu_data, rcu_data); + +struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh_state); +DEFINE_PER_CPU(struct rcu_data, rcu_bh_data); + +#ifdef CONFIG_NO_HZ +DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks); +#endif /* #ifdef CONFIG_NO_HZ */ + +static int blimit = 10; /* Maximum callbacks per softirq. */ +static int qhimark = 10000; /* If this many pending, ignore blimit. */ +static int qlowmark = 100; /* Once only this many pending, use blimit. */ + +static void force_quiescent_state(struct rcu_state *rsp, int relaxed); + +/* + * Return the number of RCU batches processed thus far for debug & stats. + */ +long rcu_batches_completed(void) +{ + return rcu_state.completed; +} +EXPORT_SYMBOL_GPL(rcu_batches_completed); + +/* + * Return the number of RCU BH batches processed thus far for debug & stats. + */ +long rcu_batches_completed_bh(void) +{ + return rcu_bh_state.completed; +} +EXPORT_SYMBOL_GPL(rcu_batches_completed_bh); + +/* + * Does the CPU have callbacks ready to be invoked? + */ +static int +cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp) +{ + return &rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]; +} + +/* + * Does the current CPU require a yet-as-unscheduled grace period? + */ +static int +cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp) +{ + /* ACCESS_ONCE() because we are accessing outside of lock. */ + return *rdp->nxttail[RCU_DONE_TAIL] && + ACCESS_ONCE(rsp->completed) == ACCESS_ONCE(rsp->gpnum); +} + +/* + * Return the root node of the specified rcu_state structure. + */ +static struct rcu_node *rcu_get_root(struct rcu_state *rsp) +{ + return &rsp->node[0]; +} + +#ifdef CONFIG_SMP + +/* + * If the specified CPU is offline, tell the caller that it is in + * a quiescent state. Otherwise, whack it with a reschedule IPI. + * Grace periods can end up waiting on an offline CPU when that + * CPU is in the process of coming online -- it will be added to the + * rcu_node bitmasks before it actually makes it online. The same thing + * can happen while a CPU is in the process of coming online. Because this + * race is quite rare, we check for it after detecting that the grace + * period has been delayed rather than checking each and every CPU + * each and every time we start a new grace period. + */ +static int rcu_implicit_offline_qs(struct rcu_data *rdp) +{ + /* + * If the CPU is offline, it is in a quiescent state. We can + * trust its state not to change because interrupts are disabled. + */ + if (cpu_is_offline(rdp->cpu)) { + rdp->offline_fqs++; + return 1; + } + + /* The CPU is online, so send it a reschedule IPI. */ + if (rdp->cpu != smp_processor_id()) + smp_send_reschedule(rdp->cpu); + else + set_need_resched(); + rdp->resched_ipi++; + return 0; +} + +#endif /* #ifdef CONFIG_SMP */ + +#ifdef CONFIG_NO_HZ +static DEFINE_RATELIMIT_STATE(rcu_rs, 10 * HZ, 5); + +/** + * rcu_enter_nohz - inform RCU that current CPU is entering nohz + * + * Enter nohz mode, in other words, -leave- the mode in which RCU + * read-side critical sections can occur. (Though RCU read-side + * critical sections can occur in irq handlers in nohz mode, a possibility + * handled by rcu_irq_enter() and rcu_irq_exit()). + */ +void rcu_enter_nohz(void) +{ + unsigned long flags; + struct rcu_dynticks *rdtp; + + smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */ + local_irq_save(flags); + rdtp = &__get_cpu_var(rcu_dynticks); + rdtp->dynticks++; + rdtp->dynticks_nesting--; + WARN_ON_RATELIMIT(rdtp->dynticks & 0x1, &rcu_rs); + local_irq_restore(flags); +} + +/* + * rcu_exit_nohz - inform RCU that current CPU is leaving nohz + * + * Exit nohz mode, in other words, -enter- the mode in which RCU + * read-side critical sections normally occur. + */ +void rcu_exit_nohz(void) +{ + unsigned long flags; + struct rcu_dynticks *rdtp; + + local_irq_save(flags); + rdtp = &__get_cpu_var(rcu_dynticks); + rdtp->dynticks++; + rdtp->dynticks_nesting++; + WARN_ON_RATELIMIT(!(rdtp->dynticks & 0x1), &rcu_rs); + local_irq_restore(flags); + smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */ +} + +/** + * rcu_nmi_enter - inform RCU of entry to NMI context + * + * If the CPU was idle with dynamic ticks active, and there is no + * irq handler running, this updates rdtp->dynticks_nmi to let the + * RCU grace-period handling know that the CPU is active. + */ +void rcu_nmi_enter(void) +{ + struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks); + + if (rdtp->dynticks & 0x1) + return; + rdtp->dynticks_nmi++; + WARN_ON_RATELIMIT(!(rdtp->dynticks_nmi & 0x1), &rcu_rs); + smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */ +} + +/** + * rcu_nmi_exit - inform RCU of exit from NMI context + * + * If the CPU was idle with dynamic ticks active, and there is no + * irq handler running, this updates rdtp->dynticks_nmi to let the + * RCU grace-period handling know that the CPU is no longer active. + */ +void rcu_nmi_exit(void) +{ + struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks); + + if (rdtp->dynticks & 0x1) + return; + smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */ + rdtp->dynticks_nmi++; + WARN_ON_RATELIMIT(rdtp->dynticks_nmi & 0x1, &rcu_rs); +} + +/** + * rcu_irq_enter - inform RCU of entry to hard irq context + * + * If the CPU was idle with dynamic ticks active, this updates the + * rdtp->dynticks to let the RCU handling know that the CPU is active. + */ +void rcu_irq_enter(void) +{ + struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks); + + if (rdtp->dynticks_nesting++) + return; + rdtp->dynticks++; + WARN_ON_RATELIMIT(!(rdtp->dynticks & 0x1), &rcu_rs); + smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */ +} + +/** + * rcu_irq_exit - inform RCU of exit from hard irq context + * + * If the CPU was idle with dynamic ticks active, update the rdp->dynticks + * to put let the RCU handling be aware that the CPU is going back to idle + * with no ticks. + */ +void rcu_irq_exit(void) +{ + struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks); + + if (--rdtp->dynticks_nesting) + return; + smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */ + rdtp->dynticks++; + WARN_ON_RATELIMIT(rdtp->dynticks & 0x1, &rcu_rs); + + /* If the interrupt queued a callback, get out of dyntick mode. */ + if (__get_cpu_var(rcu_data).nxtlist || + __get_cpu_var(rcu_bh_data).nxtlist) + set_need_resched(); +} + +/* + * Record the specified "completed" value, which is later used to validate + * dynticks counter manipulations. Specify "rsp->completed - 1" to + * unconditionally invalidate any future dynticks manipulations (which is + * useful at the beginning of a grace period). + */ +static void dyntick_record_completed(struct rcu_state *rsp, long comp) +{ + rsp->dynticks_completed = comp; +} + +#ifdef CONFIG_SMP + +/* + * Recall the previously recorded value of the completion for dynticks. + */ +static long dyntick_recall_completed(struct rcu_state *rsp) +{ + return rsp->dynticks_completed; +} + +/* + * Snapshot the specified CPU's dynticks counter so that we can later + * credit them with an implicit quiescent state. Return 1 if this CPU + * is already in a quiescent state courtesy of dynticks idle mode. + */ +static int dyntick_save_progress_counter(struct rcu_data *rdp) +{ + int ret; + int snap; + int snap_nmi; + + snap = rdp->dynticks->dynticks; + snap_nmi = rdp->dynticks->dynticks_nmi; + smp_mb(); /* Order sampling of snap with end of grace period. */ + rdp->dynticks_snap = snap; + rdp->dynticks_nmi_snap = snap_nmi; + ret = ((snap & 0x1) == 0) && ((snap_nmi & 0x1) == 0); + if (ret) + rdp->dynticks_fqs++; + return ret; +} + +/* + * Return true if the specified CPU has passed through a quiescent + * state by virtue of being in or having passed through an dynticks + * idle state since the last call to dyntick_save_progress_counter() + * for this same CPU. + */ +static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) +{ + long curr; + long curr_nmi; + long snap; + long snap_nmi; + + curr = rdp->dynticks->dynticks; + snap = rdp->dynticks_snap; + curr_nmi = rdp->dynticks->dynticks_nmi; + snap_nmi = rdp->dynticks_nmi_snap; + smp_mb(); /* force ordering with cpu entering/leaving dynticks. */ + + /* + * If the CPU passed through or entered a dynticks idle phase with + * no active irq/NMI handlers, then we can safely pretend that the CPU + * already acknowledged the request to pass through a quiescent + * state. Either way, that CPU cannot possibly be in an RCU + * read-side critical section that started before the beginning + * of the current RCU grace period. + */ + if ((curr != snap || (curr & 0x1) == 0) && + (curr_nmi != snap_nmi || (curr_nmi & 0x1) == 0)) { + rdp->dynticks_fqs++; + return 1; + } + + /* Go check for the CPU being offline. */ + return rcu_implicit_offline_qs(rdp); +} + +#endif /* #ifdef CONFIG_SMP */ + +#else /* #ifdef CONFIG_NO_HZ */ + +static void dyntick_record_completed(struct rcu_state *rsp, long comp) +{ +} + +#ifdef CONFIG_SMP + +/* + * If there are no dynticks, then the only way that a CPU can passively + * be in a quiescent state is to be offline. Unlike dynticks idle, which + * is a point in time during the prior (already finished) grace period, + * an offline CPU is always in a quiescent state, and thus can be + * unconditionally applied. So just return the current value of completed. + */ +static long dyntick_recall_completed(struct rcu_state *rsp) +{ + return rsp->completed; +} + +static int dyntick_save_progress_counter(struct rcu_data *rdp) +{ + return 0; +} + +static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) +{ + return rcu_implicit_offline_qs(rdp); +} + +#endif /* #ifdef CONFIG_SMP */ + +#endif /* #else #ifdef CONFIG_NO_HZ */ + +#ifdef CONFIG_RCU_CPU_STALL_DETECTOR + +static void record_gp_stall_check_time(struct rcu_state *rsp) +{ + rsp->gp_start = jiffies; + rsp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_CHECK; +} + +static void print_other_cpu_stall(struct rcu_state *rsp) +{ + int cpu; + long delta; + unsigned long flags; + struct rcu_node *rnp = rcu_get_root(rsp); + struct rcu_node *rnp_cur = rsp->level[NUM_RCU_LVLS - 1]; + struct rcu_node *rnp_end = &rsp->node[NUM_RCU_NODES]; + + /* Only let one CPU complain about others per time interval. */ + + spin_lock_irqsave(&rnp->lock, flags); + delta = jiffies - rsp->jiffies_stall; + if (delta < RCU_STALL_RAT_DELAY || rsp->gpnum == rsp->completed) { + spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + rsp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_RECHECK; + spin_unlock_irqrestore(&rnp->lock, flags); + + /* OK, time to rat on our buddy... */ + + printk(KERN_ERR "INFO: RCU detected CPU stalls:"); + for (; rnp_cur < rnp_end; rnp_cur++) { + if (rnp_cur->qsmask == 0) + continue; + for (cpu = 0; cpu <= rnp_cur->grphi - rnp_cur->grplo; cpu++) + if (rnp_cur->qsmask & (1UL << cpu)) + printk(" %d", rnp_cur->grplo + cpu); + } + printk(" (detected by %d, t=%ld jiffies)\n", + smp_processor_id(), (long)(jiffies - rsp->gp_start)); + force_quiescent_state(rsp, 0); /* Kick them all. */ +} + +static void print_cpu_stall(struct rcu_state *rsp) +{ + unsigned long flags; + struct rcu_node *rnp = rcu_get_root(rsp); + + printk(KERN_ERR "INFO: RCU detected CPU %d stall (t=%lu jiffies)\n", + smp_processor_id(), jiffies - rsp->gp_start); + dump_stack(); + spin_lock_irqsave(&rnp->lock, flags); + if ((long)(jiffies - rsp->jiffies_stall) >= 0) + rsp->jiffies_stall = + jiffies + RCU_SECONDS_TILL_STALL_RECHECK; + spin_unlock_irqrestore(&rnp->lock, flags); + set_need_resched(); /* kick ourselves to get things going. */ +} + +static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) +{ + long delta; + struct rcu_node *rnp; + + delta = jiffies - rsp->jiffies_stall; + rnp = rdp->mynode; + if ((rnp->qsmask & rdp->grpmask) && delta >= 0) { + + /* We haven't checked in, so go dump stack. */ + print_cpu_stall(rsp); + + } else if (rsp->gpnum != rsp->completed && + delta >= RCU_STALL_RAT_DELAY) { + + /* They had two time units to dump stack, so complain. */ + print_other_cpu_stall(rsp); + } +} + +#else /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ + +static void record_gp_stall_check_time(struct rcu_state *rsp) +{ +} + +static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) +{ +} + +#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ + +/* + * Update CPU-local rcu_data state to record the newly noticed grace period. + * This is used both when we started the grace period and when we notice + * that someone else started the grace period. + */ +static void note_new_gpnum(struct rcu_state *rsp, struct rcu_data *rdp) +{ + rdp->qs_pending = 1; + rdp->passed_quiesc = 0; + rdp->gpnum = rsp->gpnum; + rdp->n_rcu_pending_force_qs = rdp->n_rcu_pending + + RCU_JIFFIES_TILL_FORCE_QS; +} + +/* + * Did someone else start a new RCU grace period start since we last + * checked? Update local state appropriately if so. Must be called + * on the CPU corresponding to rdp. + */ +static int +check_for_new_grace_period(struct rcu_state *rsp, struct rcu_data *rdp) +{ + unsigned long flags; + int ret = 0; + + local_irq_save(flags); + if (rdp->gpnum != rsp->gpnum) { + note_new_gpnum(rsp, rdp); + ret = 1; + } + local_irq_restore(flags); + return ret; +} + +/* + * Start a new RCU grace period if warranted, re-initializing the hierarchy + * in preparation for detecting the next grace period. The caller must hold + * the root node's ->lock, which is released before return. Hard irqs must + * be disabled. + */ +static void +rcu_start_gp(struct rcu_state *rsp, unsigned long flags) + __releases(rcu_get_root(rsp)->lock) +{ + struct rcu_data *rdp = rsp->rda[smp_processor_id()]; + struct rcu_node *rnp = rcu_get_root(rsp); + struct rcu_node *rnp_cur; + struct rcu_node *rnp_end; + + if (!cpu_needs_another_gp(rsp, rdp)) { + spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + + /* Advance to a new grace period and initialize state. */ + rsp->gpnum++; + rsp->signaled = RCU_GP_INIT; /* Hold off force_quiescent_state. */ + rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS; + rdp->n_rcu_pending_force_qs = rdp->n_rcu_pending + + RCU_JIFFIES_TILL_FORCE_QS; + record_gp_stall_check_time(rsp); + dyntick_record_completed(rsp, rsp->completed - 1); + note_new_gpnum(rsp, rdp); + + /* + * Because we are first, we know that all our callbacks will + * be covered by this upcoming grace period, even the ones + * that were registered arbitrarily recently. + */ + rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; + rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; + + /* Special-case the common single-level case. */ + if (NUM_RCU_NODES == 1) { + rnp->qsmask = rnp->qsmaskinit; + spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + + spin_unlock(&rnp->lock); /* leave irqs disabled. */ + + + /* Exclude any concurrent CPU-hotplug operations. */ + spin_lock(&rsp->onofflock); /* irqs already disabled. */ + + /* + * Set the quiescent-state-needed bits in all the non-leaf RCU + * nodes for all currently online CPUs. This operation relies + * on the layout of the hierarchy within the rsp->node[] array. + * Note that other CPUs will access only the leaves of the + * hierarchy, which still indicate that no grace period is in + * progress. In addition, we have excluded CPU-hotplug operations. + * + * We therefore do not need to hold any locks. Any required + * memory barriers will be supplied by the locks guarding the + * leaf rcu_nodes in the hierarchy. + */ + + rnp_end = rsp->level[NUM_RCU_LVLS - 1]; + for (rnp_cur = &rsp->node[0]; rnp_cur < rnp_end; rnp_cur++) + rnp_cur->qsmask = rnp_cur->qsmaskinit; + + /* + * Now set up the leaf nodes. Here we must be careful. First, + * we need to hold the lock in order to exclude other CPUs, which + * might be contending for the leaf nodes' locks. Second, as + * soon as we initialize a given leaf node, its CPUs might run + * up the rest of the hierarchy. We must therefore acquire locks + * for each node that we touch during this stage. (But we still + * are excluding CPU-hotplug operations.) + * + * Note that the grace period cannot complete until we finish + * the initialization process, as there will be at least one + * qsmask bit set in the root node until that time, namely the + * one corresponding to this CPU. + */ + rnp_end = &rsp->node[NUM_RCU_NODES]; + rnp_cur = rsp->level[NUM_RCU_LVLS - 1]; + for (; rnp_cur < rnp_end; rnp_cur++) { + spin_lock(&rnp_cur->lock); /* irqs already disabled. */ + rnp_cur->qsmask = rnp_cur->qsmaskinit; + spin_unlock(&rnp_cur->lock); /* irqs already disabled. */ + } + + rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state now OK. */ + spin_unlock_irqrestore(&rsp->onofflock, flags); +} + +/* + * Advance this CPU's callbacks, but only if the current grace period + * has ended. This may be called only from the CPU to whom the rdp + * belongs. + */ +static void +rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp) +{ + long completed_snap; + unsigned long flags; + + local_irq_save(flags); + completed_snap = ACCESS_ONCE(rsp->completed); /* outside of lock. */ + + /* Did another grace period end? */ + if (rdp->completed != completed_snap) { + + /* Advance callbacks. No harm if list empty. */ + rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[RCU_WAIT_TAIL]; + rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_READY_TAIL]; + rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; + + /* Remember that we saw this grace-period completion. */ + rdp->completed = completed_snap; + } + local_irq_restore(flags); +} + +/* + * Similar to cpu_quiet(), for which it is a helper function. Allows + * a group of CPUs to be quieted at one go, though all the CPUs in the + * group must be represented by the same leaf rcu_node structure. + * That structure's lock must be held upon entry, and it is released + * before return. + */ +static void +cpu_quiet_msk(unsigned long mask, struct rcu_state *rsp, struct rcu_node *rnp, + unsigned long flags) + __releases(rnp->lock) +{ + /* Walk up the rcu_node hierarchy. */ + for (;;) { + if (!(rnp->qsmask & mask)) { + + /* Our bit has already been cleared, so done. */ + spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + rnp->qsmask &= ~mask; + if (rnp->qsmask != 0) { + + /* Other bits still set at this level, so done. */ + spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + mask = rnp->grpmask; + if (rnp->parent == NULL) { + + /* No more levels. Exit loop holding root lock. */ + + break; + } + spin_unlock_irqrestore(&rnp->lock, flags); + rnp = rnp->parent; + spin_lock_irqsave(&rnp->lock, flags); + } + + /* + * Get here if we are the last CPU to pass through a quiescent + * state for this grace period. Clean up and let rcu_start_gp() + * start up the next grace period if one is needed. Note that + * we still hold rnp->lock, as required by rcu_start_gp(), which + * will release it. + */ + rsp->completed = rsp->gpnum; + rcu_process_gp_end(rsp, rsp->rda[smp_processor_id()]); + rcu_start_gp(rsp, flags); /* releases rnp->lock. */ +} + +/* + * Record a quiescent state for the specified CPU, which must either be + * the current CPU or an offline CPU. The lastcomp argument is used to + * make sure we are still in the grace period of interest. We don't want + * to end the current grace period based on quiescent states detected in + * an earlier grace period! + */ +static void +cpu_quiet(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp) +{ + unsigned long flags; + unsigned long mask; + struct rcu_node *rnp; + + rnp = rdp->mynode; + spin_lock_irqsave(&rnp->lock, flags); + if (lastcomp != ACCESS_ONCE(rsp->completed)) { + + /* + * Someone beat us to it for this grace period, so leave. + * The race with GP start is resolved by the fact that we + * hold the leaf rcu_node lock, so that the per-CPU bits + * cannot yet be initialized -- so we would simply find our + * CPU's bit already cleared in cpu_quiet_msk() if this race + * occurred. + */ + rdp->passed_quiesc = 0; /* try again later! */ + spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + mask = rdp->grpmask; + if ((rnp->qsmask & mask) == 0) { + spin_unlock_irqrestore(&rnp->lock, flags); + } else { + rdp->qs_pending = 0; + + /* + * This GP can't end until cpu checks in, so all of our + * callbacks can be processed during the next GP. + */ + rdp = rsp->rda[smp_processor_id()]; + rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; + + cpu_quiet_msk(mask, rsp, rnp, flags); /* releases rnp->lock */ + } +} + +/* + * Check to see if there is a new grace period of which this CPU + * is not yet aware, and if so, set up local rcu_data state for it. + * Otherwise, see if this CPU has just passed through its first + * quiescent state for this grace period, and record that fact if so. + */ +static void +rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) +{ + /* If there is now a new grace period, record and return. */ + if (check_for_new_grace_period(rsp, rdp)) + return; + + /* + * Does this CPU still need to do its part for current grace period? + * If no, return and let the other CPUs do their part as well. + */ + if (!rdp->qs_pending) + return; + + /* + * Was there a quiescent state since the beginning of the grace + * period? If no, then exit and wait for the next call. + */ + if (!rdp->passed_quiesc) + return; + + /* Tell RCU we are done (but cpu_quiet() will be the judge of that). */ + cpu_quiet(rdp->cpu, rsp, rdp, rdp->passed_quiesc_completed); +} + +#ifdef CONFIG_HOTPLUG_CPU + +/* + * Remove the outgoing CPU from the bitmasks in the rcu_node hierarchy + * and move all callbacks from the outgoing CPU to the current one. + */ +static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) +{ + int i; + unsigned long flags; + long lastcomp; + unsigned long mask; + struct rcu_data *rdp = rsp->rda[cpu]; + struct rcu_data *rdp_me; + struct rcu_node *rnp; + + /* Exclude any attempts to start a new grace period. */ + spin_lock_irqsave(&rsp->onofflock, flags); + + /* Remove the outgoing CPU from the masks in the rcu_node hierarchy. */ + rnp = rdp->mynode; + mask = rdp->grpmask; /* rnp->grplo is constant. */ + do { + spin_lock(&rnp->lock); /* irqs already disabled. */ + rnp->qsmaskinit &= ~mask; + if (rnp->qsmaskinit != 0) { + spin_unlock(&rnp->lock); /* irqs already disabled. */ + break; + } + mask = rnp->grpmask; + spin_unlock(&rnp->lock); /* irqs already disabled. */ + rnp = rnp->parent; + } while (rnp != NULL); + lastcomp = rsp->completed; + + spin_unlock(&rsp->onofflock); /* irqs remain disabled. */ + + /* Being offline is a quiescent state, so go record it. */ + cpu_quiet(cpu, rsp, rdp, lastcomp); + + /* + * Move callbacks from the outgoing CPU to the running CPU. + * Note that the outgoing CPU is now quiscent, so it is now + * (uncharacteristically) safe to access it rcu_data structure. + * Note also that we must carefully retain the order of the + * outgoing CPU's callbacks in order for rcu_barrier() to work + * correctly. Finally, note that we start all the callbacks + * afresh, even those that have passed through a grace period + * and are therefore ready to invoke. The theory is that hotplug + * events are rare, and that if they are frequent enough to + * indefinitely delay callbacks, you have far worse things to + * be worrying about. + */ + rdp_me = rsp->rda[smp_processor_id()]; + if (rdp->nxtlist != NULL) { + *rdp_me->nxttail[RCU_NEXT_TAIL] = rdp->nxtlist; + rdp_me->nxttail[RCU_NEXT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; + rdp->nxtlist = NULL; + for (i = 0; i < RCU_NEXT_SIZE; i++) + rdp->nxttail[i] = &rdp->nxtlist; + rdp_me->qlen += rdp->qlen; + rdp->qlen = 0; + } + local_irq_restore(flags); +} + +/* + * Remove the specified CPU from the RCU hierarchy and move any pending + * callbacks that it might have to the current CPU. This code assumes + * that at least one CPU in the system will remain running at all times. + * Any attempt to offline -all- CPUs is likely to strand RCU callbacks. + */ +static void rcu_offline_cpu(int cpu) +{ + __rcu_offline_cpu(cpu, &rcu_state); + __rcu_offline_cpu(cpu, &rcu_bh_state); +} + +#else /* #ifdef CONFIG_HOTPLUG_CPU */ + +static void rcu_offline_cpu(int cpu) +{ +} + +#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */ + +/* + * Invoke any RCU callbacks that have made it to the end of their grace + * period. Thottle as specified by rdp->blimit. + */ +static void rcu_do_batch(struct rcu_data *rdp) +{ + unsigned long flags; + struct rcu_head *next, *list, **tail; + int count; + + /* If no callbacks are ready, just return.*/ + if (!cpu_has_callbacks_ready_to_invoke(rdp)) + return; + + /* + * Extract the list of ready callbacks, disabling to prevent + * races with call_rcu() from interrupt handlers. + */ + local_irq_save(flags); + list = rdp->nxtlist; + rdp->nxtlist = *rdp->nxttail[RCU_DONE_TAIL]; + *rdp->nxttail[RCU_DONE_TAIL] = NULL; + tail = rdp->nxttail[RCU_DONE_TAIL]; + for (count = RCU_NEXT_SIZE - 1; count >= 0; count--) + if (rdp->nxttail[count] == rdp->nxttail[RCU_DONE_TAIL]) + rdp->nxttail[count] = &rdp->nxtlist; + local_irq_restore(flags); + + /* Invoke callbacks. */ + count = 0; + while (list) { + next = list->next; + prefetch(next); + list->func(list); + list = next; + if (++count >= rdp->blimit) + break; + } + + local_irq_save(flags); + + /* Update count, and requeue any remaining callbacks. */ + rdp->qlen -= count; + if (list != NULL) { + *tail = rdp->nxtlist; + rdp->nxtlist = list; + for (count = 0; count < RCU_NEXT_SIZE; count++) + if (&rdp->nxtlist == rdp->nxttail[count]) + rdp->nxttail[count] = tail; + else + break; + } + + /* Reinstate batch limit if we have worked down the excess. */ + if (rdp->blimit == LONG_MAX && rdp->qlen <= qlowmark) + rdp->blimit = blimit; + + local_irq_restore(flags); + + /* Re-raise the RCU softirq if there are callbacks remaining. */ + if (cpu_has_callbacks_ready_to_invoke(rdp)) + raise_softirq(RCU_SOFTIRQ); +} + +/* + * Check to see if this CPU is in a non-context-switch quiescent state + * (user mode or idle loop for rcu, non-softirq execution for rcu_bh). + * Also schedule the RCU softirq handler. + * + * This function must be called with hardirqs disabled. It is normally + * invoked from the scheduling-clock interrupt. If rcu_pending returns + * false, there is no point in invoking rcu_check_callbacks(). + */ +void rcu_check_callbacks(int cpu, int user) +{ + if (user || + (idle_cpu(cpu) && !in_softirq() && + hardirq_count() <= (1 << HARDIRQ_SHIFT))) { + + /* + * Get here if this CPU took its interrupt from user + * mode or from the idle loop, and if this is not a + * nested interrupt. In this case, the CPU is in + * a quiescent state, so count it. + * + * No memory barrier is required here because both + * rcu_qsctr_inc() and rcu_bh_qsctr_inc() reference + * only CPU-local variables that other CPUs neither + * access nor modify, at least not while the corresponding + * CPU is online. + */ + + rcu_qsctr_inc(cpu); + rcu_bh_qsctr_inc(cpu); + + } else if (!in_softirq()) { + + /* + * Get here if this CPU did not take its interrupt from + * softirq, in other words, if it is not interrupting + * a rcu_bh read-side critical section. This is an _bh + * critical section, so count it. + */ + + rcu_bh_qsctr_inc(cpu); + } + raise_softirq(RCU_SOFTIRQ); +} + +#ifdef CONFIG_SMP + +/* + * Scan the leaf rcu_node structures, processing dyntick state for any that + * have not yet encountered a quiescent state, using the function specified. + * Returns 1 if the current grace period ends while scanning (possibly + * because we made it end). + */ +static int rcu_process_dyntick(struct rcu_state *rsp, long lastcomp, + int (*f)(struct rcu_data *)) +{ + unsigned long bit; + int cpu; + unsigned long flags; + unsigned long mask; + struct rcu_node *rnp_cur = rsp->level[NUM_RCU_LVLS - 1]; + struct rcu_node *rnp_end = &rsp->node[NUM_RCU_NODES]; + + for (; rnp_cur < rnp_end; rnp_cur++) { + mask = 0; + spin_lock_irqsave(&rnp_cur->lock, flags); + if (rsp->completed != lastcomp) { + spin_unlock_irqrestore(&rnp_cur->lock, flags); + return 1; + } + if (rnp_cur->qsmask == 0) { + spin_unlock_irqrestore(&rnp_cur->lock, flags); + continue; + } + cpu = rnp_cur->grplo; + bit = 1; + for (; cpu <= rnp_cur->grphi; cpu++, bit <<= 1) { + if ((rnp_cur->qsmask & bit) != 0 && f(rsp->rda[cpu])) + mask |= bit; + } + if (mask != 0 && rsp->completed == lastcomp) { + + /* cpu_quiet_msk() releases rnp_cur->lock. */ + cpu_quiet_msk(mask, rsp, rnp_cur, flags); + continue; + } + spin_unlock_irqrestore(&rnp_cur->lock, flags); + } + return 0; +} + +/* + * Force quiescent states on reluctant CPUs, and also detect which + * CPUs are in dyntick-idle mode. + */ +static void force_quiescent_state(struct rcu_state *rsp, int relaxed) +{ + unsigned long flags; + long lastcomp; + struct rcu_data *rdp = rsp->rda[smp_processor_id()]; + struct rcu_node *rnp = rcu_get_root(rsp); + u8 signaled; + + if (ACCESS_ONCE(rsp->completed) == ACCESS_ONCE(rsp->gpnum)) + return; /* No grace period in progress, nothing to force. */ + if (!spin_trylock_irqsave(&rsp->fqslock, flags)) { + rsp->n_force_qs_lh++; /* Inexact, can lose counts. Tough! */ + return; /* Someone else is already on the job. */ + } + if (relaxed && + (long)(rsp->jiffies_force_qs - jiffies) >= 0 && + (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) >= 0) + goto unlock_ret; /* no emergency and done recently. */ + rsp->n_force_qs++; + spin_lock(&rnp->lock); + lastcomp = rsp->completed; + signaled = rsp->signaled; + rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS; + rdp->n_rcu_pending_force_qs = rdp->n_rcu_pending + + RCU_JIFFIES_TILL_FORCE_QS; + if (lastcomp == rsp->gpnum) { + rsp->n_force_qs_ngp++; + spin_unlock(&rnp->lock); + goto unlock_ret; /* no GP in progress, time updated. */ + } + spin_unlock(&rnp->lock); + switch (signaled) { + case RCU_GP_INIT: + + break; /* grace period still initializing, ignore. */ + + case RCU_SAVE_DYNTICK: + + if (RCU_SIGNAL_INIT != RCU_SAVE_DYNTICK) + break; /* So gcc recognizes the dead code. */ + + /* Record dyntick-idle state. */ + if (rcu_process_dyntick(rsp, lastcomp, + dyntick_save_progress_counter)) + goto unlock_ret; + + /* Update state, record completion counter. */ + spin_lock(&rnp->lock); + if (lastcomp == rsp->completed) { + rsp->signaled = RCU_FORCE_QS; + dyntick_record_completed(rsp, lastcomp); + } + spin_unlock(&rnp->lock); + break; + + case RCU_FORCE_QS: + + /* Check dyntick-idle state, send IPI to laggarts. */ + if (rcu_process_dyntick(rsp, dyntick_recall_completed(rsp), + rcu_implicit_dynticks_qs)) + goto unlock_ret; + + /* Leave state in case more forcing is required. */ + + break; + } +unlock_ret: + spin_unlock_irqrestore(&rsp->fqslock, flags); +} + +#else /* #ifdef CONFIG_SMP */ + +static void force_quiescent_state(struct rcu_state *rsp, int relaxed) +{ + set_need_resched(); +} + +#endif /* #else #ifdef CONFIG_SMP */ + +/* + * This does the RCU processing work from softirq context for the + * specified rcu_state and rcu_data structures. This may be called + * only from the CPU to whom the rdp belongs. + */ +static void +__rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) +{ + unsigned long flags; + + /* + * If an RCU GP has gone long enough, go check for dyntick + * idle CPUs and, if needed, send resched IPIs. + */ + if ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0 || + (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) < 0) + force_quiescent_state(rsp, 1); + + /* + * Advance callbacks in response to end of earlier grace + * period that some other CPU ended. + */ + rcu_process_gp_end(rsp, rdp); + + /* Update RCU state based on any recent quiescent states. */ + rcu_check_quiescent_state(rsp, rdp); + + /* Does this CPU require a not-yet-started grace period? */ + if (cpu_needs_another_gp(rsp, rdp)) { + spin_lock_irqsave(&rcu_get_root(rsp)->lock, flags); + rcu_start_gp(rsp, flags); /* releases above lock */ + } + + /* If there are callbacks ready, invoke them. */ + rcu_do_batch(rdp); +} + +/* + * Do softirq processing for the current CPU. + */ +static void rcu_process_callbacks(struct softirq_action *unused) +{ + /* + * Memory references from any prior RCU read-side critical sections + * executed by the interrupted code must be seen before any RCU + * grace-period manipulations below. + */ + smp_mb(); /* See above block comment. */ + + __rcu_process_callbacks(&rcu_state, &__get_cpu_var(rcu_data)); + __rcu_process_callbacks(&rcu_bh_state, &__get_cpu_var(rcu_bh_data)); + + /* + * Memory references from any later RCU read-side critical sections + * executed by the interrupted code must be seen after any RCU + * grace-period manipulations above. + */ + smp_mb(); /* See above block comment. */ +} + +static void +__call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), + struct rcu_state *rsp) +{ + unsigned long flags; + struct rcu_data *rdp; + + head->func = func; + head->next = NULL; + + smp_mb(); /* Ensure RCU update seen before callback registry. */ + + /* + * Opportunistically note grace-period endings and beginnings. + * Note that we might see a beginning right after we see an + * end, but never vice versa, since this CPU has to pass through + * a quiescent state betweentimes. + */ + local_irq_save(flags); + rdp = rsp->rda[smp_processor_id()]; + rcu_process_gp_end(rsp, rdp); + check_for_new_grace_period(rsp, rdp); + + /* Add the callback to our list. */ + *rdp->nxttail[RCU_NEXT_TAIL] = head; + rdp->nxttail[RCU_NEXT_TAIL] = &head->next; + + /* Start a new grace period if one not already started. */ + if (ACCESS_ONCE(rsp->completed) == ACCESS_ONCE(rsp->gpnum)) { + unsigned long nestflag; + struct rcu_node *rnp_root = rcu_get_root(rsp); + + spin_lock_irqsave(&rnp_root->lock, nestflag); + rcu_start_gp(rsp, nestflag); /* releases rnp_root->lock. */ + } + + /* Force the grace period if too many callbacks or too long waiting. */ + if (unlikely(++rdp->qlen > qhimark)) { + rdp->blimit = LONG_MAX; + force_quiescent_state(rsp, 0); + } else if ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0 || + (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) < 0) + force_quiescent_state(rsp, 1); + local_irq_restore(flags); +} + +/* + * Queue an RCU callback for invocation after a grace period. + */ +void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) +{ + __call_rcu(head, func, &rcu_state); +} +EXPORT_SYMBOL_GPL(call_rcu); + +/* + * Queue an RCU for invocation after a quicker grace period. + */ +void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) +{ + __call_rcu(head, func, &rcu_bh_state); +} +EXPORT_SYMBOL_GPL(call_rcu_bh); + +/* + * Check to see if there is any immediate RCU-related work to be done + * by the current CPU, for the specified type of RCU, returning 1 if so. + * The checks are in order of increasing expense: checks that can be + * carried out against CPU-local state are performed first. However, + * we must check for CPU stalls first, else we might not get a chance. + */ +static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) +{ + rdp->n_rcu_pending++; + + /* Check for CPU stalls, if enabled. */ + check_cpu_stall(rsp, rdp); + + /* Is the RCU core waiting for a quiescent state from this CPU? */ + if (rdp->qs_pending) + return 1; + + /* Does this CPU have callbacks ready to invoke? */ + if (cpu_has_callbacks_ready_to_invoke(rdp)) + return 1; + + /* Has RCU gone idle with this CPU needing another grace period? */ + if (cpu_needs_another_gp(rsp, rdp)) + return 1; + + /* Has another RCU grace period completed? */ + if (ACCESS_ONCE(rsp->completed) != rdp->completed) /* outside of lock */ + return 1; + + /* Has a new RCU grace period started? */ + if (ACCESS_ONCE(rsp->gpnum) != rdp->gpnum) /* outside of lock */ + return 1; + + /* Has an RCU GP gone long enough to send resched IPIs &c? */ + if (ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum) && + ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0 || + (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) < 0)) + return 1; + + /* nothing to do */ + 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_state, &per_cpu(rcu_data, cpu)) || + __rcu_pending(&rcu_bh_state, &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) +{ + /* RCU callbacks either ready or pending? */ + return per_cpu(rcu_data, cpu).nxtlist || + per_cpu(rcu_bh_data, cpu).nxtlist; +} + +/* + * Initialize a CPU's per-CPU RCU data. We take this "scorched earth" + * approach so that we don't have to worry about how long the CPU has + * been gone, or whether it ever was online previously. We do trust the + * ->mynode field, as it is constant for a given struct rcu_data and + * initialized during early boot. + * + * Note that only one online or offline event can be happening at a given + * time. Note also that we can accept some slop in the rsp->completed + * access due to the fact that this CPU cannot possibly have any RCU + * callbacks in flight yet. + */ +static void +rcu_init_percpu_data(int cpu, struct rcu_state *rsp) +{ + unsigned long flags; + int i; + long lastcomp; + unsigned long mask; + struct rcu_data *rdp = rsp->rda[cpu]; + struct rcu_node *rnp = rcu_get_root(rsp); + + /* Set up local state, ensuring consistent view of global state. */ + spin_lock_irqsave(&rnp->lock, flags); + lastcomp = rsp->completed; + rdp->completed = lastcomp; + rdp->gpnum = lastcomp; + rdp->passed_quiesc = 0; /* We could be racing with new GP, */ + rdp->qs_pending = 1; /* so set up to respond to current GP. */ + rdp->beenonline = 1; /* We have now been online. */ + rdp->passed_quiesc_completed = lastcomp - 1; + rdp->grpmask = 1UL << (cpu - rdp->mynode->grplo); + rdp->nxtlist = NULL; + for (i = 0; i < RCU_NEXT_SIZE; i++) + rdp->nxttail[i] = &rdp->nxtlist; + rdp->qlen = 0; + rdp->blimit = blimit; +#ifdef CONFIG_NO_HZ + rdp->dynticks = &per_cpu(rcu_dynticks, cpu); +#endif /* #ifdef CONFIG_NO_HZ */ + rdp->cpu = cpu; + spin_unlock(&rnp->lock); /* irqs remain disabled. */ + + /* + * A new grace period might start here. If so, we won't be part + * of it, but that is OK, as we are currently in a quiescent state. + */ + + /* Exclude any attempts to start a new GP on large systems. */ + spin_lock(&rsp->onofflock); /* irqs already disabled. */ + + /* Add CPU to rcu_node bitmasks. */ + rnp = rdp->mynode; + mask = rdp->grpmask; + do { + /* Exclude any attempts to start a new GP on small systems. */ + spin_lock(&rnp->lock); /* irqs already disabled. */ + rnp->qsmaskinit |= mask; + mask = rnp->grpmask; + spin_unlock(&rnp->lock); /* irqs already disabled. */ + rnp = rnp->parent; + } while (rnp != NULL && !(rnp->qsmaskinit & mask)); + + spin_unlock(&rsp->onofflock); /* irqs remain disabled. */ + + /* + * A new grace period might start here. If so, we will be part of + * it, and its gpnum will be greater than ours, so we will + * participate. It is also possible for the gpnum to have been + * incremented before this function was called, and the bitmasks + * to not be filled out until now, in which case we will also + * participate due to our gpnum being behind. + */ + + /* Since it is coming online, the CPU is in a quiescent state. */ + cpu_quiet(cpu, rsp, rdp, lastcomp); + local_irq_restore(flags); +} + +static void __cpuinit rcu_online_cpu(int cpu) +{ +#ifdef CONFIG_NO_HZ + struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); + + rdtp->dynticks_nesting = 1; + rdtp->dynticks |= 1; /* need consecutive #s even for hotplug. */ + rdtp->dynticks_nmi = (rdtp->dynticks_nmi + 1) & ~0x1; +#endif /* #ifdef CONFIG_NO_HZ */ + rcu_init_percpu_data(cpu, &rcu_state); + rcu_init_percpu_data(cpu, &rcu_bh_state); + open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); +} + +/* + * Handle CPU online/offline notifcation events. + */ +static int __cpuinit rcu_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + long cpu = (long)hcpu; + + switch (action) { + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: + rcu_online_cpu(cpu); + break; + case CPU_DEAD: + case CPU_DEAD_FROZEN: + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: + rcu_offline_cpu(cpu); + break; + default: + break; + } + return NOTIFY_OK; +} + +/* + * Compute the per-level fanout, either using the exact fanout specified + * or balancing the tree, depending on CONFIG_RCU_FANOUT_EXACT. + */ +#ifdef CONFIG_RCU_FANOUT_EXACT +static void __init rcu_init_levelspread(struct rcu_state *rsp) +{ + int i; + + for (i = NUM_RCU_LVLS - 1; i >= 0; i--) + rsp->levelspread[i] = CONFIG_RCU_FANOUT; +} +#else /* #ifdef CONFIG_RCU_FANOUT_EXACT */ +static void __init rcu_init_levelspread(struct rcu_state *rsp) +{ + int ccur; + int cprv; + int i; + + cprv = NR_CPUS; + for (i = NUM_RCU_LVLS - 1; i >= 0; i--) { + ccur = rsp->levelcnt[i]; + rsp->levelspread[i] = (cprv + ccur - 1) / ccur; + cprv = ccur; + } +} +#endif /* #else #ifdef CONFIG_RCU_FANOUT_EXACT */ + +/* + * Helper function for rcu_init() that initializes one rcu_state structure. + */ +static void __init rcu_init_one(struct rcu_state *rsp) +{ + int cpustride = 1; + int i; + int j; + struct rcu_node *rnp; + + /* Initialize the level-tracking arrays. */ + + for (i = 1; i < NUM_RCU_LVLS; i++) + rsp->level[i] = rsp->level[i - 1] + rsp->levelcnt[i - 1]; + rcu_init_levelspread(rsp); + + /* Initialize the elements themselves, starting from the leaves. */ + + for (i = NUM_RCU_LVLS - 1; i >= 0; i--) { + cpustride *= rsp->levelspread[i]; + rnp = rsp->level[i]; + for (j = 0; j < rsp->levelcnt[i]; j++, rnp++) { + spin_lock_init(&rnp->lock); + rnp->qsmask = 0; + rnp->qsmaskinit = 0; + rnp->grplo = j * cpustride; + rnp->grphi = (j + 1) * cpustride - 1; + if (rnp->grphi >= NR_CPUS) + rnp->grphi = NR_CPUS - 1; + if (i == 0) { + rnp->grpnum = 0; + rnp->grpmask = 0; + rnp->parent = NULL; + } else { + rnp->grpnum = j % rsp->levelspread[i - 1]; + rnp->grpmask = 1UL << rnp->grpnum; + rnp->parent = rsp->level[i - 1] + + j / rsp->levelspread[i - 1]; + } + rnp->level = i; + } + } +} + +/* + * Helper macro for __rcu_init(). To be used nowhere else! + * Assigns leaf node pointers into each CPU's rcu_data structure. + */ +#define RCU_DATA_PTR_INIT(rsp, rcu_data) \ +do { \ + rnp = (rsp)->level[NUM_RCU_LVLS - 1]; \ + j = 0; \ + for_each_possible_cpu(i) { \ + if (i > rnp[j].grphi) \ + j++; \ + per_cpu(rcu_data, i).mynode = &rnp[j]; \ + (rsp)->rda[i] = &per_cpu(rcu_data, i); \ + } \ +} while (0) + +static struct notifier_block __cpuinitdata rcu_nb = { + .notifier_call = rcu_cpu_notify, +}; + +void __init __rcu_init(void) +{ + int i; /* All used by RCU_DATA_PTR_INIT(). */ + int j; + struct rcu_node *rnp; + + printk(KERN_WARNING "Experimental hierarchical RCU implementation.\n"); +#ifdef CONFIG_RCU_CPU_STALL_DETECTOR + printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n"); +#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ + rcu_init_one(&rcu_state); + RCU_DATA_PTR_INIT(&rcu_state, rcu_data); + rcu_init_one(&rcu_bh_state); + RCU_DATA_PTR_INIT(&rcu_bh_state, rcu_bh_data); + + for_each_online_cpu(i) + rcu_cpu_notify(&rcu_nb, CPU_UP_PREPARE, (void *)(long)i); + /* Register notifier for non-boot CPUs */ + register_cpu_notifier(&rcu_nb); + printk(KERN_WARNING "Experimental hierarchical RCU init done.\n"); +} + +module_param(blimit, int, 0); +module_param(qhimark, int, 0); +module_param(qlowmark, int, 0); diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c new file mode 100644 index 00000000000..d6db3e83782 --- /dev/null +++ b/kernel/rcutree_trace.c @@ -0,0 +1,271 @@ +/* + * Read-Copy Update tracing for classic implementation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright IBM Corporation, 2008 + * + * Papers: http://www.rdrop.com/users/paulmck/RCU + * + * For detailed explanation of Read-Copy Update mechanism see - + * Documentation/RCU + * + */ +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/spinlock.h> +#include <linux/smp.h> +#include <linux/rcupdate.h> +#include <linux/interrupt.h> +#include <linux/sched.h> +#include <asm/atomic.h> +#include <linux/bitops.h> +#include <linux/module.h> +#include <linux/completion.h> +#include <linux/moduleparam.h> +#include <linux/percpu.h> +#include <linux/notifier.h> +#include <linux/cpu.h> +#include <linux/mutex.h> +#include <linux/debugfs.h> +#include <linux/seq_file.h> + +static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) +{ + if (!rdp->beenonline) + return; + seq_printf(m, "%3d%cc=%ld g=%ld pq=%d pqc=%ld qp=%d rpfq=%ld rp=%x", + rdp->cpu, + cpu_is_offline(rdp->cpu) ? '!' : ' ', + rdp->completed, rdp->gpnum, + rdp->passed_quiesc, rdp->passed_quiesc_completed, + rdp->qs_pending, + rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending, + (int)(rdp->n_rcu_pending & 0xffff)); +#ifdef CONFIG_NO_HZ + seq_printf(m, " dt=%d/%d dn=%d df=%lu", + rdp->dynticks->dynticks, + rdp->dynticks->dynticks_nesting, + rdp->dynticks->dynticks_nmi, + rdp->dynticks_fqs); +#endif /* #ifdef CONFIG_NO_HZ */ + seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi); + seq_printf(m, " ql=%ld b=%ld\n", rdp->qlen, rdp->blimit); +} + +#define PRINT_RCU_DATA(name, func, m) \ + do { \ + int _p_r_d_i; \ + \ + for_each_possible_cpu(_p_r_d_i) \ + func(m, &per_cpu(name, _p_r_d_i)); \ + } while (0) + +static int show_rcudata(struct seq_file *m, void *unused) +{ + seq_puts(m, "rcu:\n"); + PRINT_RCU_DATA(rcu_data, print_one_rcu_data, m); + seq_puts(m, "rcu_bh:\n"); + PRINT_RCU_DATA(rcu_bh_data, print_one_rcu_data, m); + return 0; +} + +static int rcudata_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_rcudata, NULL); +} + +static struct file_operations rcudata_fops = { + .owner = THIS_MODULE, + .open = rcudata_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp) +{ + if (!rdp->beenonline) + return; + seq_printf(m, "%d,%s,%ld,%ld,%d,%ld,%d,%ld,%ld", + rdp->cpu, + cpu_is_offline(rdp->cpu) ? "\"Y\"" : "\"N\"", + rdp->completed, rdp->gpnum, + rdp->passed_quiesc, rdp->passed_quiesc_completed, + rdp->qs_pending, + rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending, + rdp->n_rcu_pending); +#ifdef CONFIG_NO_HZ + seq_printf(m, ",%d,%d,%d,%lu", + rdp->dynticks->dynticks, + rdp->dynticks->dynticks_nesting, + rdp->dynticks->dynticks_nmi, + rdp->dynticks_fqs); +#endif /* #ifdef CONFIG_NO_HZ */ + seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi); + seq_printf(m, ",%ld,%ld\n", rdp->qlen, rdp->blimit); +} + +static int show_rcudata_csv(struct seq_file *m, void *unused) +{ + seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pqc\",\"pq\",\"rpfq\",\"rp\","); +#ifdef CONFIG_NO_HZ + seq_puts(m, "\"dt\",\"dt nesting\",\"dn\",\"df\","); +#endif /* #ifdef CONFIG_NO_HZ */ + seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\"\n"); + seq_puts(m, "\"rcu:\"\n"); + PRINT_RCU_DATA(rcu_data, print_one_rcu_data_csv, m); + seq_puts(m, "\"rcu_bh:\"\n"); + PRINT_RCU_DATA(rcu_bh_data, print_one_rcu_data_csv, m); + return 0; +} + +static int rcudata_csv_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_rcudata_csv, NULL); +} + +static struct file_operations rcudata_csv_fops = { + .owner = THIS_MODULE, + .open = rcudata_csv_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) +{ + int level = 0; + struct rcu_node *rnp; + + seq_printf(m, "c=%ld g=%ld s=%d jfq=%ld j=%x " + "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu\n", + rsp->completed, rsp->gpnum, rsp->signaled, + (long)(rsp->jiffies_force_qs - jiffies), + (int)(jiffies & 0xffff), + rsp->n_force_qs, rsp->n_force_qs_ngp, + rsp->n_force_qs - rsp->n_force_qs_ngp, + rsp->n_force_qs_lh); + for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < NUM_RCU_NODES; rnp++) { + if (rnp->level != level) { + seq_puts(m, "\n"); + level = rnp->level; + } + seq_printf(m, "%lx/%lx %d:%d ^%d ", + rnp->qsmask, rnp->qsmaskinit, + rnp->grplo, rnp->grphi, rnp->grpnum); + } + seq_puts(m, "\n"); +} + +static int show_rcuhier(struct seq_file *m, void *unused) +{ + seq_puts(m, "rcu:\n"); + print_one_rcu_state(m, &rcu_state); + seq_puts(m, "rcu_bh:\n"); + print_one_rcu_state(m, &rcu_bh_state); + return 0; +} + +static int rcuhier_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_rcuhier, NULL); +} + +static struct file_operations rcuhier_fops = { + .owner = THIS_MODULE, + .open = rcuhier_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int show_rcugp(struct seq_file *m, void *unused) +{ + seq_printf(m, "rcu: completed=%ld gpnum=%ld\n", + rcu_state.completed, rcu_state.gpnum); + seq_printf(m, "rcu_bh: completed=%ld gpnum=%ld\n", + rcu_bh_state.completed, rcu_bh_state.gpnum); + return 0; +} + +static int rcugp_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_rcugp, NULL); +} + +static struct file_operations rcugp_fops = { + .owner = THIS_MODULE, + .open = rcugp_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static struct dentry *rcudir, *datadir, *datadir_csv, *hierdir, *gpdir; +static int __init rcuclassic_trace_init(void) +{ + rcudir = debugfs_create_dir("rcu", NULL); + if (!rcudir) + goto out; + + datadir = debugfs_create_file("rcudata", 0444, rcudir, + NULL, &rcudata_fops); + if (!datadir) + goto free_out; + + datadir_csv = debugfs_create_file("rcudata.csv", 0444, rcudir, + NULL, &rcudata_csv_fops); + if (!datadir_csv) + goto free_out; + + gpdir = debugfs_create_file("rcugp", 0444, rcudir, NULL, &rcugp_fops); + if (!gpdir) + goto free_out; + + hierdir = debugfs_create_file("rcuhier", 0444, rcudir, + NULL, &rcuhier_fops); + if (!hierdir) + goto free_out; + return 0; +free_out: + if (datadir) + debugfs_remove(datadir); + if (datadir_csv) + debugfs_remove(datadir_csv); + if (gpdir) + debugfs_remove(gpdir); + debugfs_remove(rcudir); +out: + return 1; +} + +static void __exit rcuclassic_trace_cleanup(void) +{ + debugfs_remove(datadir); + debugfs_remove(datadir_csv); + debugfs_remove(gpdir); + debugfs_remove(hierdir); + debugfs_remove(rcudir); +} + + +module_init(rcuclassic_trace_init); +module_exit(rcuclassic_trace_cleanup); + +MODULE_AUTHOR("Paul E. McKenney"); +MODULE_DESCRIPTION("Read-Copy Update tracing for hierarchical implementation"); +MODULE_LICENSE("GPL"); diff --git a/kernel/resource.c b/kernel/resource.c index 4337063663e..e633106b12f 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -853,6 +853,15 @@ int iomem_map_sanity_check(resource_size_t addr, unsigned long size) if (PFN_DOWN(p->start) <= PFN_DOWN(addr) && PFN_DOWN(p->end) >= PFN_DOWN(addr + size - 1)) continue; + /* + * if a resource is "BUSY", it's not a hardware resource + * but a driver mapping of such a resource; we don't want + * to warn for those; some drivers legitimately map only + * partial hardware resources. (example: vesafb) + */ + if (p->flags & IORESOURCE_BUSY) + continue; + printk(KERN_WARNING "resource map sanity check conflict: " "0x%llx 0x%llx 0x%llx 0x%llx %s\n", (unsigned long long)addr, diff --git a/kernel/sched.c b/kernel/sched.c index 748ff924a29..22aa9cab3fe 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4192,7 +4192,6 @@ void account_steal_time(struct task_struct *p, cputime_t steal) if (p == rq->idle) { p->stime = cputime_add(p->stime, steal); - account_group_system_time(p, steal); if (atomic_read(&rq->nr_iowait) > 0) cpustat->iowait = cputime64_add(cpustat->iowait, tmp); else @@ -4328,7 +4327,7 @@ void __kprobes sub_preempt_count(int val) /* * Underflow? */ - if (DEBUG_LOCKS_WARN_ON(val > preempt_count())) + if (DEBUG_LOCKS_WARN_ON(val > preempt_count() - (!!kernel_locked()))) return; /* * Is the spinlock portion underflowing? diff --git a/kernel/softirq.c b/kernel/softirq.c index e7c69a720d6..466e75ce271 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -102,20 +102,6 @@ void local_bh_disable(void) EXPORT_SYMBOL(local_bh_disable); -void __local_bh_enable(void) -{ - WARN_ON_ONCE(in_irq()); - - /* - * softirqs should never be enabled by __local_bh_enable(), - * it always nests inside local_bh_enable() sections: - */ - WARN_ON_ONCE(softirq_count() == SOFTIRQ_OFFSET); - - sub_preempt_count(SOFTIRQ_OFFSET); -} -EXPORT_SYMBOL_GPL(__local_bh_enable); - /* * Special-case - softirqs can safely be enabled in * cond_resched_softirq(), or by __do_softirq(), @@ -269,6 +255,7 @@ void irq_enter(void) { int cpu = smp_processor_id(); + rcu_irq_enter(); if (idle_cpu(cpu) && !in_interrupt()) { __irq_enter(); tick_check_idle(cpu); @@ -295,9 +282,9 @@ void irq_exit(void) #ifdef CONFIG_NO_HZ /* Make sure that timer wheel updates are propagated */ - if (!in_interrupt() && idle_cpu(smp_processor_id()) && !need_resched()) - tick_nohz_stop_sched_tick(0); rcu_irq_exit(); + if (idle_cpu(smp_processor_id()) && !in_interrupt() && !need_resched()) + tick_nohz_stop_sched_tick(0); #endif preempt_enable_no_resched(); } diff --git a/kernel/softlockup.c b/kernel/softlockup.c index dc0b3be6b7d..1ab790c67b1 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -164,7 +164,7 @@ unsigned long __read_mostly sysctl_hung_task_check_count = 1024; /* * Zero means infinite timeout - no checking done: */ -unsigned long __read_mostly sysctl_hung_task_timeout_secs = 120; +unsigned long __read_mostly sysctl_hung_task_timeout_secs = 480; unsigned long __read_mostly sysctl_hung_task_warnings = 10; diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c index 94b527ef1d1..eb212f8f8bc 100644 --- a/kernel/stacktrace.c +++ b/kernel/stacktrace.c @@ -6,6 +6,7 @@ * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> */ #include <linux/sched.h> +#include <linux/kernel.h> #include <linux/module.h> #include <linux/kallsyms.h> #include <linux/stacktrace.h> @@ -24,3 +25,13 @@ void print_stack_trace(struct stack_trace *trace, int spaces) } EXPORT_SYMBOL_GPL(print_stack_trace); +/* + * Architectures that do not implement save_stack_trace_tsk get this + * weak alias and a once-per-bootup warning (whenever this facility + * is utilized - for example by procfs): + */ +__weak void +save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) +{ + WARN_ONCE(1, KERN_INFO "save_stack_trace_tsk() not implemented yet.\n"); +} diff --git a/kernel/sys.c b/kernel/sys.c index ebe65c2c987..d356d79e84a 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -907,8 +907,8 @@ void do_sys_times(struct tms *tms) struct task_cputime cputime; cputime_t cutime, cstime; - spin_lock_irq(¤t->sighand->siglock); thread_group_cputime(current, &cputime); + spin_lock_irq(¤t->sighand->siglock); cutime = current->signal->cutime; cstime = current->signal->cstime; spin_unlock_irq(¤t->sighand->siglock); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index b0f239e443b..eae594cb6ea 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -252,6 +252,14 @@ config DEBUG_OBJECTS_TIMERS timer routines to track the life time of timer objects and validate the timer operations. +config DEBUG_OBJECTS_ENABLE_DEFAULT + int "debug_objects bootup default value (0-1)" + range 0 1 + default "1" + depends on DEBUG_OBJECTS + help + Debug objects boot parameter default value + config DEBUG_SLAB bool "Debug slab memory allocations" depends on DEBUG_KERNEL && SLAB @@ -545,6 +553,16 @@ config DEBUG_SG If unsure, say N. +config DEBUG_NOTIFIERS + bool "Debug notifier call chains" + depends on DEBUG_KERNEL + help + Enable this to turn on sanity checking for notifier call chains. + This is most useful for kernel developers to make sure that + modules properly unregister themselves from notifier chains. + This is a relatively cheap check but if you care about maximum + performance, say N. + config FRAME_POINTER bool "Compile the kernel with frame pointers" depends on DEBUG_KERNEL && \ @@ -619,6 +637,19 @@ config RCU_CPU_STALL_DETECTOR Say N if you are unsure. +config RCU_CPU_STALL_DETECTOR + bool "Check for stalled CPUs delaying RCU grace periods" + depends on CLASSIC_RCU || TREE_RCU + default n + help + This option causes RCU to printk information on which + CPUs are delaying the current grace period, but only when + the grace period extends for excessive time periods. + + Say Y if you want RCU to perform such checks. + + Say N if you are unsure. + config KPROBES_SANITY_TEST bool "Kprobes sanity tests" depends on DEBUG_KERNEL diff --git a/lib/debugobjects.c b/lib/debugobjects.c index e3ab374e133..5d99be1fd98 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -45,7 +45,9 @@ static struct kmem_cache *obj_cache; static int debug_objects_maxchain __read_mostly; static int debug_objects_fixups __read_mostly; static int debug_objects_warnings __read_mostly; -static int debug_objects_enabled __read_mostly; +static int debug_objects_enabled __read_mostly + = CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT; + static struct debug_obj_descr *descr_test __read_mostly; static int __init enable_object_debug(char *str) diff --git a/lib/swiotlb.c b/lib/swiotlb.c index 5f6c629a924..fa2dc4e5f9b 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -21,9 +21,12 @@ #include <linux/mm.h> #include <linux/module.h> #include <linux/spinlock.h> +#include <linux/swiotlb.h> #include <linux/string.h> +#include <linux/swiotlb.h> #include <linux/types.h> #include <linux/ctype.h> +#include <linux/highmem.h> #include <asm/io.h> #include <asm/dma.h> @@ -36,22 +39,6 @@ #define OFFSET(val,align) ((unsigned long) \ ( (val) & ( (align) - 1))) -#define SG_ENT_VIRT_ADDRESS(sg) (sg_virt((sg))) -#define SG_ENT_PHYS_ADDRESS(sg) virt_to_bus(SG_ENT_VIRT_ADDRESS(sg)) - -/* - * Maximum allowable number of contiguous slabs to map, - * must be a power of 2. What is the appropriate value ? - * The complexity of {map,unmap}_single is linearly dependent on this value. - */ -#define IO_TLB_SEGSIZE 128 - -/* - * log of the size of each IO TLB slab. The number of slabs is command line - * controllable. - */ -#define IO_TLB_SHIFT 11 - #define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT)) /* @@ -102,7 +89,10 @@ static unsigned int io_tlb_index; * We need to save away the original address corresponding to a mapped entry * for the sync operations. */ -static unsigned char **io_tlb_orig_addr; +static struct swiotlb_phys_addr { + struct page *page; + unsigned int offset; +} *io_tlb_orig_addr; /* * Protect the above data structures in the map and unmap calls @@ -126,6 +116,72 @@ setup_io_tlb_npages(char *str) __setup("swiotlb=", setup_io_tlb_npages); /* make io_tlb_overflow tunable too? */ +void * __weak swiotlb_alloc_boot(size_t size, unsigned long nslabs) +{ + return alloc_bootmem_low_pages(size); +} + +void * __weak swiotlb_alloc(unsigned order, unsigned long nslabs) +{ + return (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, order); +} + +dma_addr_t __weak swiotlb_phys_to_bus(phys_addr_t paddr) +{ + return paddr; +} + +phys_addr_t __weak swiotlb_bus_to_phys(dma_addr_t baddr) +{ + return baddr; +} + +static dma_addr_t swiotlb_virt_to_bus(volatile void *address) +{ + return swiotlb_phys_to_bus(virt_to_phys(address)); +} + +static void *swiotlb_bus_to_virt(dma_addr_t address) +{ + return phys_to_virt(swiotlb_bus_to_phys(address)); +} + +int __weak swiotlb_arch_range_needs_mapping(void *ptr, size_t size) +{ + return 0; +} + +static dma_addr_t swiotlb_sg_to_bus(struct scatterlist *sg) +{ + return swiotlb_phys_to_bus(page_to_phys(sg_page(sg)) + sg->offset); +} + +static void swiotlb_print_info(unsigned long bytes) +{ + phys_addr_t pstart, pend; + dma_addr_t bstart, bend; + + pstart = virt_to_phys(io_tlb_start); + pend = virt_to_phys(io_tlb_end); + + bstart = swiotlb_phys_to_bus(pstart); + bend = swiotlb_phys_to_bus(pend); + + printk(KERN_INFO "Placing %luMB software IO TLB between %p - %p\n", + bytes >> 20, io_tlb_start, io_tlb_end); + if (pstart != bstart || pend != bend) + printk(KERN_INFO "software IO TLB at phys %#llx - %#llx" + " bus %#llx - %#llx\n", + (unsigned long long)pstart, + (unsigned long long)pend, + (unsigned long long)bstart, + (unsigned long long)bend); + else + printk(KERN_INFO "software IO TLB at phys %#llx - %#llx\n", + (unsigned long long)pstart, + (unsigned long long)pend); +} + /* * Statically reserve bounce buffer space and initialize bounce buffer data * structures for the software IO TLB used to implement the DMA API. @@ -145,7 +201,7 @@ swiotlb_init_with_default_size(size_t default_size) /* * Get IO TLB memory from the low pages */ - io_tlb_start = alloc_bootmem_low_pages(bytes); + io_tlb_start = swiotlb_alloc_boot(bytes, io_tlb_nslabs); if (!io_tlb_start) panic("Cannot allocate SWIOTLB buffer"); io_tlb_end = io_tlb_start + bytes; @@ -159,7 +215,7 @@ swiotlb_init_with_default_size(size_t default_size) for (i = 0; i < io_tlb_nslabs; i++) io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE); io_tlb_index = 0; - io_tlb_orig_addr = alloc_bootmem(io_tlb_nslabs * sizeof(char *)); + io_tlb_orig_addr = alloc_bootmem(io_tlb_nslabs * sizeof(struct swiotlb_phys_addr)); /* * Get the overflow emergency buffer @@ -168,8 +224,7 @@ swiotlb_init_with_default_size(size_t default_size) if (!io_tlb_overflow_buffer) panic("Cannot allocate SWIOTLB overflow buffer!\n"); - printk(KERN_INFO "Placing software IO TLB between 0x%lx - 0x%lx\n", - virt_to_bus(io_tlb_start), virt_to_bus(io_tlb_end)); + swiotlb_print_info(bytes); } void __init @@ -202,8 +257,7 @@ swiotlb_late_init_with_default_size(size_t default_size) bytes = io_tlb_nslabs << IO_TLB_SHIFT; while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) { - io_tlb_start = (char *)__get_free_pages(GFP_DMA | __GFP_NOWARN, - order); + io_tlb_start = swiotlb_alloc(order, io_tlb_nslabs); if (io_tlb_start) break; order--; @@ -235,12 +289,12 @@ swiotlb_late_init_with_default_size(size_t default_size) io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE); io_tlb_index = 0; - io_tlb_orig_addr = (unsigned char **)__get_free_pages(GFP_KERNEL, - get_order(io_tlb_nslabs * sizeof(char *))); + io_tlb_orig_addr = (struct swiotlb_phys_addr *)__get_free_pages(GFP_KERNEL, + get_order(io_tlb_nslabs * sizeof(struct swiotlb_phys_addr))); if (!io_tlb_orig_addr) goto cleanup3; - memset(io_tlb_orig_addr, 0, io_tlb_nslabs * sizeof(char *)); + memset(io_tlb_orig_addr, 0, io_tlb_nslabs * sizeof(struct swiotlb_phys_addr)); /* * Get the overflow emergency buffer @@ -250,9 +304,7 @@ swiotlb_late_init_with_default_size(size_t default_size) if (!io_tlb_overflow_buffer) goto cleanup4; - printk(KERN_INFO "Placing %luMB software IO TLB between 0x%lx - " - "0x%lx\n", bytes >> 20, - virt_to_bus(io_tlb_start), virt_to_bus(io_tlb_end)); + swiotlb_print_info(bytes); return 0; @@ -279,16 +331,69 @@ address_needs_mapping(struct device *hwdev, dma_addr_t addr, size_t size) return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size); } +static inline int range_needs_mapping(void *ptr, size_t size) +{ + return swiotlb_force || swiotlb_arch_range_needs_mapping(ptr, size); +} + static int is_swiotlb_buffer(char *addr) { return addr >= io_tlb_start && addr < io_tlb_end; } +static struct swiotlb_phys_addr swiotlb_bus_to_phys_addr(char *dma_addr) +{ + int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT; + struct swiotlb_phys_addr buffer = io_tlb_orig_addr[index]; + buffer.offset += (long)dma_addr & ((1 << IO_TLB_SHIFT) - 1); + buffer.page += buffer.offset >> PAGE_SHIFT; + buffer.offset &= PAGE_SIZE - 1; + return buffer; +} + +static void +__sync_single(struct swiotlb_phys_addr buffer, char *dma_addr, size_t size, int dir) +{ + if (PageHighMem(buffer.page)) { + size_t len, bytes; + char *dev, *host, *kmp; + + len = size; + while (len != 0) { + unsigned long flags; + + bytes = len; + if ((bytes + buffer.offset) > PAGE_SIZE) + bytes = PAGE_SIZE - buffer.offset; + local_irq_save(flags); /* protects KM_BOUNCE_READ */ + kmp = kmap_atomic(buffer.page, KM_BOUNCE_READ); + dev = dma_addr + size - len; + host = kmp + buffer.offset; + if (dir == DMA_FROM_DEVICE) + memcpy(host, dev, bytes); + else + memcpy(dev, host, bytes); + kunmap_atomic(kmp, KM_BOUNCE_READ); + local_irq_restore(flags); + len -= bytes; + buffer.page++; + buffer.offset = 0; + } + } else { + void *v = page_address(buffer.page) + buffer.offset; + + if (dir == DMA_TO_DEVICE) + memcpy(dma_addr, v, size); + else + memcpy(v, dma_addr, size); + } +} + /* * Allocates bounce buffer and returns its kernel virtual address. */ static void * -map_single(struct device *hwdev, char *buffer, size_t size, int dir) +map_single(struct device *hwdev, struct swiotlb_phys_addr buffer, size_t size, int dir) { unsigned long flags; char *dma_addr; @@ -298,11 +403,16 @@ map_single(struct device *hwdev, char *buffer, size_t size, int dir) unsigned long mask; unsigned long offset_slots; unsigned long max_slots; + struct swiotlb_phys_addr slot_buf; mask = dma_get_seg_boundary(hwdev); - start_dma_addr = virt_to_bus(io_tlb_start) & mask; + start_dma_addr = swiotlb_virt_to_bus(io_tlb_start) & mask; offset_slots = ALIGN(start_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; + + /* + * Carefully handle integer overflow which can occur when mask == ~0UL. + */ max_slots = mask + 1 ? ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT); @@ -378,10 +488,15 @@ found: * This is needed when we sync the memory. Then we sync the buffer if * needed. */ - for (i = 0; i < nslots; i++) - io_tlb_orig_addr[index+i] = buffer + (i << IO_TLB_SHIFT); + slot_buf = buffer; + for (i = 0; i < nslots; i++) { + slot_buf.page += slot_buf.offset >> PAGE_SHIFT; + slot_buf.offset &= PAGE_SIZE - 1; + io_tlb_orig_addr[index+i] = slot_buf; + slot_buf.offset += 1 << IO_TLB_SHIFT; + } if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) - memcpy(dma_addr, buffer, size); + __sync_single(buffer, dma_addr, size, DMA_TO_DEVICE); return dma_addr; } @@ -395,17 +510,17 @@ unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir) unsigned long flags; int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT; - char *buffer = io_tlb_orig_addr[index]; + struct swiotlb_phys_addr buffer = swiotlb_bus_to_phys_addr(dma_addr); /* * First, sync the memory before unmapping the entry */ - if (buffer && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL))) + if ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)) /* * bounce... copy the data back into the original buffer * and * delete the bounce buffer. */ - memcpy(buffer, dma_addr, size); + __sync_single(buffer, dma_addr, size, DMA_FROM_DEVICE); /* * Return the buffer to the free list by setting the corresponding @@ -437,21 +552,18 @@ static void sync_single(struct device *hwdev, char *dma_addr, size_t size, int dir, int target) { - int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT; - char *buffer = io_tlb_orig_addr[index]; - - buffer += ((unsigned long)dma_addr & ((1 << IO_TLB_SHIFT) - 1)); + struct swiotlb_phys_addr buffer = swiotlb_bus_to_phys_addr(dma_addr); switch (target) { case SYNC_FOR_CPU: if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) - memcpy(buffer, dma_addr, size); + __sync_single(buffer, dma_addr, size, DMA_FROM_DEVICE); else BUG_ON(dir != DMA_TO_DEVICE); break; case SYNC_FOR_DEVICE: if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) - memcpy(dma_addr, buffer, size); + __sync_single(buffer, dma_addr, size, DMA_TO_DEVICE); else BUG_ON(dir != DMA_FROM_DEVICE); break; @@ -473,7 +585,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size, dma_mask = hwdev->coherent_dma_mask; ret = (void *)__get_free_pages(flags, order); - if (ret && !is_buffer_dma_capable(dma_mask, virt_to_bus(ret), size)) { + if (ret && !is_buffer_dma_capable(dma_mask, swiotlb_virt_to_bus(ret), size)) { /* * The allocated memory isn't reachable by the device. * Fall back on swiotlb_map_single(). @@ -488,13 +600,16 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size, * swiotlb_map_single(), which will grab memory from * the lowest available address range. */ - ret = map_single(hwdev, NULL, size, DMA_FROM_DEVICE); + struct swiotlb_phys_addr buffer; + buffer.page = virt_to_page(NULL); + buffer.offset = 0; + ret = map_single(hwdev, buffer, size, DMA_FROM_DEVICE); if (!ret) return NULL; } memset(ret, 0, size); - dev_addr = virt_to_bus(ret); + dev_addr = swiotlb_virt_to_bus(ret); /* Confirm address can be DMA'd by device */ if (!is_buffer_dma_capable(dma_mask, dev_addr, size)) { @@ -554,8 +669,9 @@ dma_addr_t swiotlb_map_single_attrs(struct device *hwdev, void *ptr, size_t size, int dir, struct dma_attrs *attrs) { - dma_addr_t dev_addr = virt_to_bus(ptr); + dma_addr_t dev_addr = swiotlb_virt_to_bus(ptr); void *map; + struct swiotlb_phys_addr buffer; BUG_ON(dir == DMA_NONE); /* @@ -563,19 +679,22 @@ swiotlb_map_single_attrs(struct device *hwdev, void *ptr, size_t size, * we can safely return the device addr and not worry about bounce * buffering it. */ - if (!address_needs_mapping(hwdev, dev_addr, size) && !swiotlb_force) + if (!address_needs_mapping(hwdev, dev_addr, size) && + !range_needs_mapping(ptr, size)) return dev_addr; /* * Oh well, have to allocate and map a bounce buffer. */ - map = map_single(hwdev, ptr, size, dir); + buffer.page = virt_to_page(ptr); + buffer.offset = (unsigned long)ptr & ~PAGE_MASK; + map = map_single(hwdev, buffer, size, dir); if (!map) { swiotlb_full(hwdev, size, dir, 1); map = io_tlb_overflow_buffer; } - dev_addr = virt_to_bus(map); + dev_addr = swiotlb_virt_to_bus(map); /* * Ensure that the address returned is DMA'ble @@ -605,7 +724,7 @@ void swiotlb_unmap_single_attrs(struct device *hwdev, dma_addr_t dev_addr, size_t size, int dir, struct dma_attrs *attrs) { - char *dma_addr = bus_to_virt(dev_addr); + char *dma_addr = swiotlb_bus_to_virt(dev_addr); BUG_ON(dir == DMA_NONE); if (is_swiotlb_buffer(dma_addr)) @@ -635,7 +754,7 @@ static void swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr, size_t size, int dir, int target) { - char *dma_addr = bus_to_virt(dev_addr); + char *dma_addr = swiotlb_bus_to_virt(dev_addr); BUG_ON(dir == DMA_NONE); if (is_swiotlb_buffer(dma_addr)) @@ -666,7 +785,7 @@ swiotlb_sync_single_range(struct device *hwdev, dma_addr_t dev_addr, unsigned long offset, size_t size, int dir, int target) { - char *dma_addr = bus_to_virt(dev_addr) + offset; + char *dma_addr = swiotlb_bus_to_virt(dev_addr) + offset; BUG_ON(dir == DMA_NONE); if (is_swiotlb_buffer(dma_addr)) @@ -714,18 +833,20 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, int dir, struct dma_attrs *attrs) { struct scatterlist *sg; - void *addr; + struct swiotlb_phys_addr buffer; dma_addr_t dev_addr; int i; BUG_ON(dir == DMA_NONE); for_each_sg(sgl, sg, nelems, i) { - addr = SG_ENT_VIRT_ADDRESS(sg); - dev_addr = virt_to_bus(addr); - if (swiotlb_force || + dev_addr = swiotlb_sg_to_bus(sg); + if (range_needs_mapping(sg_virt(sg), sg->length) || address_needs_mapping(hwdev, dev_addr, sg->length)) { - void *map = map_single(hwdev, addr, sg->length, dir); + void *map; + buffer.page = sg_page(sg); + buffer.offset = sg->offset; + map = map_single(hwdev, buffer, sg->length, dir); if (!map) { /* Don't panic here, we expect map_sg users to do proper error handling. */ @@ -735,7 +856,7 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, sgl[0].dma_length = 0; return 0; } - sg->dma_address = virt_to_bus(map); + sg->dma_address = swiotlb_virt_to_bus(map); } else sg->dma_address = dev_addr; sg->dma_length = sg->length; @@ -765,11 +886,11 @@ swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl, BUG_ON(dir == DMA_NONE); for_each_sg(sgl, sg, nelems, i) { - if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg)) - unmap_single(hwdev, bus_to_virt(sg->dma_address), + if (sg->dma_address != swiotlb_sg_to_bus(sg)) + unmap_single(hwdev, swiotlb_bus_to_virt(sg->dma_address), sg->dma_length, dir); else if (dir == DMA_FROM_DEVICE) - dma_mark_clean(SG_ENT_VIRT_ADDRESS(sg), sg->dma_length); + dma_mark_clean(swiotlb_bus_to_virt(sg->dma_address), sg->dma_length); } } EXPORT_SYMBOL(swiotlb_unmap_sg_attrs); @@ -798,11 +919,11 @@ swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl, BUG_ON(dir == DMA_NONE); for_each_sg(sgl, sg, nelems, i) { - if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg)) - sync_single(hwdev, bus_to_virt(sg->dma_address), + if (sg->dma_address != swiotlb_sg_to_bus(sg)) + sync_single(hwdev, swiotlb_bus_to_virt(sg->dma_address), sg->dma_length, dir, target); else if (dir == DMA_FROM_DEVICE) - dma_mark_clean(SG_ENT_VIRT_ADDRESS(sg), sg->dma_length); + dma_mark_clean(swiotlb_bus_to_virt(sg->dma_address), sg->dma_length); } } @@ -823,7 +944,7 @@ swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, int swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr) { - return (dma_addr == virt_to_bus(io_tlb_overflow_buffer)); + return (dma_addr == swiotlb_virt_to_bus(io_tlb_overflow_buffer)); } /* @@ -835,7 +956,7 @@ swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr) int swiotlb_dma_supported(struct device *hwdev, u64 mask) { - return virt_to_bus(io_tlb_end - 1) <= mask; + return swiotlb_virt_to_bus(io_tlb_end - 1) <= mask; } EXPORT_SYMBOL(swiotlb_map_single); diff --git a/mm/memory.c b/mm/memory.c index f01b7eed6e1..0a2010a9518 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3075,3 +3075,18 @@ void print_vma_addr(char *prefix, unsigned long ip) } up_read(¤t->mm->mmap_sem); } + +#ifdef CONFIG_PROVE_LOCKING +void might_fault(void) +{ + might_sleep(); + /* + * it would be nicer only to annotate paths which are not under + * pagefault_disable, however that requires a larger audit and + * providing helpers like get_user_atomic. + */ + if (!in_atomic() && current->mm) + might_lock_read(¤t->mm->mmap_sem); +} +EXPORT_SYMBOL(might_fault); +#endif |