Commit Graph

339 Commits

Author SHA1 Message Date
787d34f650 introduction of ihk_mc_pt_virt_to_phys_size() 2016-11-23 08:40:33 +09:00
5f973ab51e IKC2: adjust master channel message queue size dynamically
Determine master channel's message queue size based on the number of
LWK CPUs so that all cores can communicate simultaneously during
syscall channel initialization.
2016-10-24 20:49:00 +09:00
994b9a19ac NUMA: expose CPU and memory info in /proc/self/status 2016-10-14 21:34:32 +09:00
b068fde9cd NUMA: use IHK CPU and NUMA mappings for sysfs entries 2016-10-14 21:34:31 +09:00
f4df713846 munmap(): fix memory leak in non page backed mappings 2016-10-14 21:34:31 +09:00
8f4f68b877 eliminate arch_alloc_page() and move ihk_mc_alloc_pages() to arch independent code 2016-10-14 21:34:30 +09:00
2929fbb803 NUMA: support multiple physical allocators 2016-10-14 21:34:30 +09:00
9b82f1a52c use ihk_mc_alloc/free_pages() and eliminate direct calls to low level routines 2016-10-14 21:34:29 +09:00
02536b7724 Merge remote-tracking branch 'remotes/origin/ikc2'
Conflicts:
	executer/kernel/mcctrl/syscall.c
It is resolved.
2016-09-27 11:48:12 +09:00
9390fe5d2c signal: send signal to thread using thread-id. not cpu-id 2016-09-12 15:43:29 +09:00
20ea65b38c fix some vDSO bugs.
- vDSO sometimes becomes invalid.
- vDSO is not succeeded for child process.
- vDSO becomes invalid when execve.
refs #744
2016-09-04 23:13:00 +09:00
b5e4459a34 support AVX-512 registers 2016-08-30 18:39:33 +09:00
a7ee3f531b sched_setaffinity(): error handling for invalid input 2016-08-19 11:52:44 +09:00
7ebc34ddcc do_fork(): fix tids memory leak; additional sanity checks 2016-08-18 14:31:52 +09:00
bd6a2c2311 sys_mmap(): correct initial address check 2016-08-18 07:32:31 +09:00
5fd68eae54 PF handler: fix up various error msgs 2016-08-18 07:31:25 +09:00
f5857cfc9e MM: use ihk_mc_{alloc/free}_pages() everywhere and fix free_pages() on kmalloc()ed object bug 2016-08-17 18:02:05 +09:00
1a207e19c2 clean up a couple of debug messages 2016-08-17 13:55:36 +09:00
3fa3920bb3 fix a couple of debug msgs 2016-08-14 11:30:17 +09:00
0884e3d543 IHK-IKC: map queue in McKernel as cacheable 2016-08-14 11:16:40 +09:00
689da07ac6 ihk_mc_ikc_init_first_local(): hold ref to master channel 2016-08-06 08:52:14 +09:00
57690479bd read/patch_process_vm(): map non-LWK physical addresses properly 2016-07-22 20:48:54 +09:00
d0539a9cac eclair: make idle threads visible 2016-07-22 18:06:11 +09:00
4c8f583c0c split_large_page(): avoid panic when splitting "non-mapped" large pages 2016-07-14 17:11:52 +09:00
f6908f21a8 do_kill: wake PS_INTERRUPTIBLE process when send SIGKILL
sched_wakeup_thread: don't change process status if process status is PS_EXITED
2016-07-13 14:06:32 +09:00
5c190beb04 save fpregs when to call sighandler
refs #50
2016-07-05 15:26:00 +09:00
648bacc90f device file mappings: communicate map flags and fault missing translations 2016-06-24 12:44:59 -07:00
dd37443fc7 PAPI support: performance counter's overflow.
and support mckfd fcntl.
2016-06-24 13:50:12 +09:00
e34322702a x86_init_perfctr: discover perf counters dynamically from MSRs 2016-06-22 10:47:57 -07:00
14ec92518e KVM support: detect KVM and avoid touching unimplemented MSRs 2016-05-26 01:11:08 +09:00
f06d8041e3 don't send SIGCONT when sending SIGSTOP derived from PTRACE_ATTACH
refs #747
2016-05-19 10:54:12 +09:00
9b35eaca42 remote_flush_tlb_cpumask() dead locking
refs #728
2016-05-10 14:02:25 +09:00
130b1f4327 update PAPI support. other process and child process monitoring. 2016-04-26 19:01:47 +09:00
d4a0b32f06 support large pages 2016-04-21 23:22:55 +09:00
2048980820 remove ihk_mc_pt_alloc_range() 2016-04-21 23:22:54 +09:00
176f6d23a9 ihk_mc_pt_virt_to_pagemap: refactor 2016-04-21 23:22:54 +09:00
328175547f Revert "fix REQ-37: remap_one_page: remove to check page size"
This reverts commit 6790126a23.

- reverted commit should remove a 'pgsize' check in remap_one_page()
  instead of a 'pgsize' check in pte_make_fileoff().
- In IA-32e, PTE format varies with page size. Therefore 'pgsize'
  parameter of pte_make_fileoff() is preferable.
2016-04-21 23:22:54 +09:00
e2e0fad849 arch_clear_host_user_space: set zero to args[2]
to avoid duplicated per_proc_list entry.
2016-04-21 23:22:54 +09:00
aa77228453 resupport ptrace(PTRACE_ATTACH)
refs #733
2016-04-21 20:13:27 +09:00
82cb8f95ed update PAPI support. 2016-04-18 13:07:45 +09:00
1bb948f43b hwloc support 2016-04-11 22:25:27 +09:00
2a1823d52c vdso: set enable bit of pvti_msr 2016-04-11 22:20:39 +09:00
89943dc5ba vdso: set physical address at pvti_msr 2016-04-11 22:20:39 +09:00
fceb02a44a vdso: add zero clear for pvti 2016-04-11 22:20:38 +09:00
7298d8e179 vdso: correct pvti array element type
struct pvclock_vsyscall_time_info <-- struct pvclock_vcpu_time_info
2016-04-11 22:20:38 +09:00
41bb2ab5e6 support vdso which borrows clocksource from linux 2016-03-28 22:57:44 +09:00
a587c8f5e5 x86: encode cpu# in IA32_TSC_AUX and size of GDTe#15 2016-03-28 22:57:44 +09:00
c760a01a79 add pte_get_attr() 2016-03-28 22:57:44 +09:00
a2548f5421 Revert "fix REQ-42"
This reverts commit 4a0682bbc1.

The reverted commit appears to be wrong, for example:
- arch_range_check()'s arguments and parameters are mismatch.
- arch_range_check() implementation is not checking range.

Conflicts:
	kernel/syscall.c
2016-03-28 13:51:57 +09:00
6790126a23 fix REQ-37: remap_one_page: remove to check page size 2016-03-27 14:05:00 +09:00