Commit Graph

220 Commits

Author SHA1 Message Date
19cb302d5f uti: util_indicate_clone: check --enable-uti mcexec option
Change-Id: Ic7474d01c18acd1edbc07844d7a7b010b2175f71
2021-02-26 10:37:56 +09:00
aef50d710c mempolicy: Support MPOL_INTERLEAVE
Change-Id: I6357892d792b2de8ea859a0a6799250f05066713
Refs: #959
2021-02-18 06:16:17 +00:00
0b82c8942b Tofu: keep track of stags per memory range
Change-Id: I033beaeee3b141dab4485dd3a2a3848eaa84e54e
2020-12-29 16:31:40 +09:00
530110e3a9 Tofu: fix ENABLE_TOFU switching
Change-Id: Ib33323d4b59ea8fb4f5f40dff7ea25a36773d5e2
2020-12-24 15:00:14 +09:00
33dd2e60b1 mcexec: memory policy control by environmental variable
Refs: #1470
Change-Id: I3d556cae90d31d81572b1c4e5c680e826577d428
2020-12-24 11:18:01 +09:00
1918df7765 Tofu: support for barrier gate, kmalloc cache
Change-Id: I6f4cfec2ec404efd03b332fc3f449a775816230e
2020-12-09 13:05:54 +09:00
92902d36fc Tofu: initial version
Change-Id: I9c464d5af883c18715a97ca9e9981cf73b260f90
2020-12-09 13:03:01 +09:00
201f5ce500 MM: straight mapping
Change-Id: I70871f8c382fb00aa719ed501cc5de436d916d7f
2020-12-08 12:32:10 +09:00
58106d791a struct process: fix type of group_exit_status
Change-Id: Ib8492cbb077106cef1d0fa2d6d5e8e13bbb209c0
Refs: #1377
2020-07-13 08:33:07 +00:00
3328ce03d9 Record pthread routine address in clone(), keep helper threads on caller CPU core (workaround for Fugaku)
Change-Id: I29d1589e430dc1396558cdf3df4d068c27173612
2020-06-16 13:26:53 +09:00
6332903f0d Revert "xpmem: Support large page attachment"
This reverts commit a8696d811d.

Conflicts:
	kernel/include/process.h
	kernel/syscall.c
	kernel/xpmem.c

Change-Id: I726e74450f6228d3fc78fc62dda15b2067732a53
2020-06-16 13:25:57 +09:00
e774e1b984 Revert "xpmem: fix mapping of attachment and segment"
This reverts commit a5fcc91656.

Change-Id: If29415369d724391b291939ecce76482138e82f5
2020-06-16 11:28:02 +09:00
a5fcc91656 xpmem: fix mapping of attachment and segment
* Mapping attached part of segment is done at attach time instead of
  make time to work with runtimes (e.g. OpenMPI) xpmem_make-ing the
  entire user-space
* Mapping attached part of segment at attach time can be turned off by
  specifying xpmem_remote_on_demand in kernel argument
* Mapping attachment chooses appropriate page-sizes, i.e., largest
  allowed by memory range and segment page boundary

Fixes: a8696d8 "xpmem: Support large page attachment"
Change-Id: I44663865204036520e5f62fe22b9134ee4629f9b
2020-06-15 10:11:29 +09:00
d5aafca1ae VM: use RW spinlock for vm_range_lock
Change-Id: Id4654084207d55bf77cc9f8b42795e0f9873cfa0
2020-06-12 03:07:33 +00:00
3300e65efc madvise: Support MADV_WIPEONFORK, MADV_KEEPONFORK and MADV_NORMAL
Change-Id: I1d4cf5affa580d7304dfdc34fa4f1707c0df617c
refs: #1374
2020-03-23 09:13:01 +09:00
5719b4c64a perf: update event structure
Change-Id: I5bc0fdd42db509b5d2daca7d97e29ad1f7d11f1a
2020-03-03 13:23:30 +09:00
4bbdee395e ptrace: fix execve and return value handling (fixes strace on aarch64)
Change-Id: Icb5cb7f7e99fdb74a8628bc6b550688df5fb056b
2020-02-10 07:45:06 +00:00
a8696d811d xpmem: Support large page attachment
Change-Id: I4d672eee1c905160ece204d278f0afd9b6d7dc01
Refs: #1259
2019-12-06 09:30:51 +09:00
a563d780c1 munmap: fix deadlock with remote pagefault on vm range lock
Add similar protection to clear_host_pte than to set_host_vma (see #986)

Also make the page fault handler only skip taking lock if the munmap
happened on the same cpu id

Change-Id: I6d9e68e8f8905b20bb2ccfa72848e04fe6404ab6
2019-11-28 02:07:45 +00:00
edd3ea0103 Revert "memory_range_lock: Enable interrupt when trylock fails"
This reverts commit 0d3ef65092.

Reason for revert: This fix causes circular dependency with memory_range manipulation and TLB flush. See #1394.

Change-Id: I4774e81ff300c199629e283e538c0a30ad0eeaae
2019-11-11 15:28:08 +09:00
bb08742467 fork: clone_thread: free resources when an error is detected
Change-Id: I922f3fddc35942ef2c67db6673980770731dced9
2019-09-26 01:56:16 +00:00
58f4593478 fork: fpregs: return error code.
Change-Id: I6ff150a39cd8952adad9b21d0c9f8514126ef957
2019-09-26 01:56:16 +00:00
11ef2f8092 coredump: Support threads
Change-Id: Id75ade6c87b15abcff5d772d90f77950376a32c1
Refs: #1219
2019-08-09 04:00:15 +00:00
0d3ef65092 memory_range_lock: Enable interrupt when trylock fails
Also use read-write-lock

Change-Id: I03150b7208325ec1fe422dcd5f931e4e41c8e40e
Refs: #452
2019-08-08 00:38:55 +00:00
bb2589bac4 uti: futex_wait: Use kmalloc area for wait queue
Change-Id: Ida994c87334f9613bbf5cbda45b6b5474fd4c6be
2019-07-23 04:53:51 +00:00
516ab87ab9 Copyrights: fujitsu 2018 bump
Separate copyright bumps in a different commit.
A lot of files only had the copyright change at this point; these
were probably changes I added separatly in other patches but just
split these in a different commit instead to simplify git stats

Change-Id: I93cf3fc1c0fa04ee743a79c3fe9768933e6bd0d2
2019-02-01 13:18:52 +09:00
f299fff266 stack: add hwcap auxval
Fix the AUXV_LEN to account for hwcap and remove the ifdefs

Change-Id: I303fc2c5fa4c8cea7ec9823f8580b8a66de2f58f
Fujitsu: POSTK_DEBUG_ARCH_DEP_65
2019-02-01 13:17:58 +09:00
dfd23c3ebe prctl: Add support for PR_SET_THP_DISABLE and PR_GET_THP_DISABLE
Change-Id: I04c5568a9eb78bcac632b734f34bba49cf602c4d
Refs: #1181
2019-01-22 05:40:56 +00:00
38e68f358a Add kernel argument to turn on/off time sharing
Add "-T 0" to mcreboot.sh if you want to turn off time sharing.  When
it's turned off, McKernel doesn't activate interval timer when the
length of per-CPU run-queue is larger than one.

Change-Id: I2cedc1b30a9cd9a0f4608a32ecec0a0d58c6225e
2018-11-21 07:37:01 +00:00
06dd71a7e0 Revert "procfs: add '/proc/pid/stat' to mckernel side and fix its comm"
This reverts commit b70d470e20.

That commit had been landed too fast after a mistake during migration
from old to new gerrit that didn't keep -1 vote ; it needs some fix

Change-Id: Ifc8a23e42449dfe471049270b4706e9b137e096e
2018-10-12 10:54:14 +09:00
b70d470e20 procfs: add '/proc/pid/stat' to mckernel side and fix its comm
This lets ps show the proper executable name instead of mcexec's comm
on linux side

Change-Id: I62732037451f129fc2e905357ebdc351bf7f6d2d
Refs: #1114
2018-10-04 01:01:19 +00:00
ed1edb152b ptrace supports threads
Fujitsu: POSTK_DEBUG_TEMP_FIX_53, POSTK_DEBUG_ARCH_DEP_44
Refs: #771, #1179, #1143
Change-Id: Ie17ece6864f0eeb0c0e550f4e369abb77980a0d0
2018-10-01 03:57:16 +00:00
e4da71010c check_signal: system call restart is done only once
Fujitsu: POSTK_TEMP_FIX_66
Refs: #1009
Change-Id: Ic0f04ac6b7f6c6bb01b55fb389bf9befd56b1dd9
2018-09-13 07:00:49 +00:00
cd00fc3a78 set_timer: Start timer when runnable thread count is bigger than one
Change-Id: Ie32799fff2936ffc057f166db5681edccdbf5920
2018-09-04 19:53:03 +09:00
04d4145b3e uti: Replace dead uti thread with new mcexec thread in proc->tids
Change-Id: Ic6e906dd1bfac1b07f1317732cbe0a5191831cd8
2018-09-04 19:53:03 +09:00
5cb8a1f10f uti: Workaround not to share CPU with OpenMP threads
* Assign uti thread to the last idle CPU so that it's not shared with
  an OpenMP thread

Change-Id: Ia42cae056ce81fde9b6dab6286b39a52f3c9e172
2018-09-04 19:53:01 +09:00
b6ab5911b7 uti: Identify uti thread by clone count
--uti-thread-count <count> is added to mcexec.

Change-Id: Id9ec464412a5bb71e4d9e87d05f79de22d35b067
2018-09-04 19:53:01 +09:00
0b0b7b03d7 Prevent one CPU from getting chosen by concurrent forks
One CPU could be chosen by concurrent forks because CPU selection and
runq addition are not done atomicly. So this fix makes the two steps
atomic.

Change-Id: Ib6b75ad655789385d13207e0a47fa4717dec854a
2018-09-04 19:51:11 +09:00
567dcd3846 Fix deadlock involving mmap_sem and memory_range_lock
Change-Id: I187246271163e708af6542c057d0a8dfde5b211e
Fujitsu: TEMP_FIX_1
Refs: #986
2018-09-04 19:51:10 +09:00
2db69d0f24 process/vm: implement access_ok() 2018-09-04 19:51:10 +09:00
a697f5e98d partitioned execution: pass process rank to LWK
Cherry-pick of d2d134d5e6a4b16a34d55d31b14614a2a91ecf47

Conflicts:
	kernel/include/process.h
2018-09-04 19:51:10 +09:00
f57b0c5d4f wait: Delay wake-up parent within switch context
Fujitsu: POSTK_DEBUG_TEMP_FIX_41
Refs: #1006
Change-Id: Ia98e896505ad0f6549766604ade84550eee8bd2d
2018-08-30 02:13:51 +00:00
c716e87c53 execve: Clear sigaltstack and fp_regs
Fujitsu: POSTK_DEBUG_TEMP_FIX_19
Refs: #976
Change-Id: I16895eab13eecbb47b7e6da961fae82ee5e570ee
2018-08-01 15:11:05 +09:00
0758f6254e headers: declare void arguments for functions
Not giving any argument means that any argument is OK,
this is not what is meant here.

Change-Id: Ide651c1dec973d4b8709cf00646988f4c4f3acdd
2018-07-03 09:18:25 +00:00
c52f7a5b49 syscall wait4: add _WALL (POSTK_DEBUG_ARCH_DEP_44)
Needed by strace -f
2018-05-11 09:22:54 +09:00
fe42481d6f Add allow_oversubscribe kernel argument
It's not allowed in the default setting.
Execute mcreboot.sh with -O option to allow it.

refs #1072
2018-03-10 13:08:38 +09:00
65667709a8 Fix thread status race-condition caused by hold_thread() in do_kill() and terminate()
Conflicts:
	arch/x86_64/kernel/syscall.c
	kernel/syscall.c
2018-03-09 17:53:17 +09:00
c260b5c6f3 xpmem: support for fork()
refs #925
2018-02-22 09:37:48 +09:00
4bb65494e9 signal: When the process receives a termination signal, it first terminates mcexec.
refs #863
refs #870
2018-01-23 14:40:38 +09:00
2f2b3cdc6f signal: interrupt_syscall is called by the core executing the thread that recieved the signal.
refs #999
2018-01-23 14:31:04 +09:00