gh0s7/mckernel
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
2,365 Commits 1 Branch 61 Tags
2db3717e57fe30a0a79bf65a96d2836ee645c01a
Commit Graph

150 Commits

Author SHA1 Message Date
Balazs Gerofi
2db3717e57 handle_interrupt_gicv3(): check for CPU_FLAG_NEED_RESCHED as well 
Change-Id: Id6ade08e4e572a6d837476de2872126442d3591c
 2020-06-13 17:18:09 +09:00
Balazs Gerofi
5e44c9c9f9 epoll_wait(): make sure to schedule in offload 
Change-Id: I435416cb0ac005a03cd995bf1aae75c9ce7b2082
 2020-06-13 17:18:08 +09:00
Balazs Gerofi
6aa7b50e26 profile: refactor display code and fix ARM support 
Change-Id: Ic48102c42abe17eed014f2bfe7523d0d6f03c2e9
 2020-06-13 17:18:08 +09:00
Balazs Gerofi
7aa2d64294 obtain_clone_cpuid(): avoid locking while partitioned execution 
Change-Id: Iabb4784835be7dc9b2f555acc3a711fcc23ee7da
 2020-06-13 17:18:08 +09:00
Balazs Gerofi
d5aafca1ae VM: use RW spinlock for vm_range_lock 
Change-Id: Id4654084207d55bf77cc9f8b42795e0f9873cfa0
 2020-06-12 03:07:33 +00:00
Ken Sato
8f74888f87 sysinfo, procfs: Support memory info partially 
Change-Id: I597dae4f82d64d3f23889cef960db18ae879ff06
refs: #1389
 2020-05-14 00:53:25 +00:00
Masamichi Takagi
f1caaa9b74 freeze: arm64: use normal interrupt instead of NMI 
Fixes: 55faba7 "dump: rewrite NMI handling (for resume) and fix PANIC register saving"
Fixes: ff982b8 "freeze: change freeze-thaw to normal interrupt"
Change-Id: I9445cac191f91d20357cae11b2839e4e9384ac6f
 2020-04-15 01:04:20 +00:00
Balazs Gerofi
04d17dd3e9 Define MAP_KERNEL_START by resolving MODULES_END at cmake time 
Change-Id: Ib88fc045b64c4ad2dad6a4b13cb0372a735a26ab
 2020-04-09 00:30:05 -04:00
Toshiyuki Takahashi
bb7e140655 procfs cpuinfo: use sequence number as processor 
Change-Id: Idbfa48e9b60c03495d7ba72e962c55f0ffb8bec9
 2020-03-12 05:19:25 +00:00
Shiratori, Takehiro
edf7b36669 runq_lock: Fix deadlock due to cpu migration. 
Symptom and analysis:
runq_lock of the migration source is acquired on
the migration destination CPU.

This happens in the following steps:
 (1) The thread stores value of cpu_local_var(runq_lock)
     to its register when trying to perform
     ihk_mc_spinlock_lock() on the lock variable.
 (2) The thread takes IPI and migrates to another CPU.
 (3) The thread resumes execution and acquires the wrong lock.

Solution:
* Disable interrupts before getting the value of
  cpu_local_var(runq_lock)

Change-Id: Ia0ea450b97f872dd6116252537e4a79f85adfc88
Refs: #1400
 2020-03-05 01:51:40 +00:00
TOIDA,Suguru
305511b48f perf: accumulate counter in overflow handler 
Change-Id: If5f5a913e0fde889d1835ffb16c19ea0ad5e685a
 2020-03-03 13:23:30 +09:00
TOIDA,Suguru
5719b4c64a perf: update event structure 
Change-Id: I5bc0fdd42db509b5d2daca7d97e29ad1f7d11f1a
 2020-03-03 13:23:30 +09:00
TOIDA,Suguru
343121c3d0 perf: set event period 
Change-Id: Ibf569de7af8697e766c10b8d70905b8cdc4df083
 2020-03-03 13:23:30 +09:00
TOIDA,Suguru
86c45484e3 perf: add struct hw_perf_event 
Change-Id: I0938e2b18064ad805a9edb6e15d26cf438bf0a59
 2020-03-03 13:23:29 +09:00
TOIDA,Suguru
a27909be88 ihk_atomic64_set argument to long 
Change-Id: Ie9b5978028000236ae5846214a2ea14fcdffaf56
 2020-03-03 13:23:29 +09:00
TOIDA,Suguru
cec6f24559 PMU register support for cpufreq driver. 
Change-Id: I11462d25ef83867ddf2e643798d1e3d0257f7f33
 2020-03-02 07:14:27 +00:00
Tomoki Shirasawa
cafb46efc7 rt_sigtimedwait: could not wait for ignored signal 
Change-Id: I0f5a8e2eaae2b7c08a01f4ebb2c405b8972269a2
Refs: #1378
 2020-02-13 06:23:22 +00:00
Balazs Gerofi
4bbdee395e ptrace: fix execve and return value handling (fixes strace on aarch64) 
Change-Id: Icb5cb7f7e99fdb74a8628bc6b550688df5fb056b
 2020-02-10 07:45:06 +00:00
Balazs Gerofi
55faba77a5 dump: rewrite NMI handling (for resume) and fix PANIC register saving 
Change-Id: I360e9aa8efa64b6ebd99b209a5dd4ee0dc7806cf
 2020-02-10 07:45:01 +00:00
Balazs Gerofi
d1df17ffb7 eclair: fix register GDB response for descheduled threads 
Change-Id: I0001d094b624bc03f2b178ec28a4cab51e2acaf0
 2020-02-10 07:16:06 +00:00
Tomoki Shirasawa
f00d03445c epoll_pwait, ppoll, pselect: add to process sigmask 
Change-Id: I6aa1db3b4c6ad81a8b5926fa87fc645269b103b6
Refs: #1361
 2020-01-09 06:54:23 +00:00
Balazs Gerofi
5b26fe2956 do_process_vm_read_writev(): access local vector buffer using kernel virtual, PF if necessary 
Change-Id: Ic90dca79e32d4151f585a5cbd5b2c7710534db0e
 2019-12-23 02:54:52 +00:00
Ken Sato
7fc4272b89 handle execveat systemcall on McKernel 
Refs: #1366
Change-Id: I921e04a0df8d0d798fc94f675e5112dd2fec190a
 2019-12-06 09:33:13 +09:00
Masamichi Takagi
a8696d811d xpmem: Support large page attachment 
Change-Id: I4d672eee1c905160ece204d278f0afd9b6d7dc01
Refs: #1259
 2019-12-06 09:30:51 +09:00
Tomoki Shirasawa
4b252a990f SIGCONT: don't terminate process 
Change-Id: Ib959a9e5341fda37bd055724ecb9319a469b7420
Refs: #1410
 2019-12-05 07:13:56 +00:00
Tomoki Shirasawa
adb6cce3ce The process sending SIGCONT resumes the stopped process. 
Change-Id: I64ee10172b99aa58540ffe8e9dd80fa0a64f4d01
Refs: #1420
 2019-12-05 07:13:56 +00:00
Tomoki Shirasawa
37605740a4 support for backlog 
Change-Id: Id8f503234e7afaa284e6b97dc264eb3a2af145c7
 2019-12-05 07:08:13 +00:00
Dominique Martinet
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
Ken Sato
37ea770f8c mmap: Round up map size by pagesize when specified MAP_HUGETLB 
To match the behavior of Linux.

Change-Id: I7bcc2cb3c1e678ffc28f6b825c7a55032441dded
 2019-11-14 07:24:25 +00:00
Masamichi Takagi
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
Shiratori, Takehiro
ba80dd8650 arm64: Fix for ptrace instruction rewrite on thunder-x2. 
- Fixed the problem that instruction rewriting by PTRACE_POKETEXT is not reflected.
   The cause is that the instruction cache was not flushed.

 - Add instruction chache flush in ptrace_report_signal().

Change-Id: Ie9d34d3d33e1fd85aef5fe419345d82c6ca781fb
 2019-09-26 02:57:07 +00:00
TOIDA,Suguru
8e4073c2ca freeze: allow interrupts in frozen state 
Change-Id: I1d502f828ab9f9c0e1223d021979ac3dcf4d0c25
 2019-09-26 02:13:23 +00:00
TOIDA,Suguru
ff982b8594 freeze: change freeze-thaw to normal interrupt 
Change-Id: Ib4dbac28f0074595e92ef316945b37ef4bc18327
 2019-09-26 02:13:23 +00:00
TOIDA,Suguru
58f4593478 fork: fpregs: return error code. 
Change-Id: I6ff150a39cd8952adad9b21d0c9f8514126ef957
 2019-09-26 01:56:16 +00:00
Masamichi Takagi
51cd7cbb6c arm64: rusage: Fix counting contiguous PTEs 
Change-Id: I7e89c25d49dc1f6efe1c27c76c66c6fedd22af1f
Refs: #1342
 2019-08-16 03:55:29 +00:00
Ken Sato
0c1cae45fe coredump: Support signal number 
Change-Id: If220bcd0865569a566e08aa53cae748fdc6317d0
Refs: #1340
 2019-08-08 13:44:15 +09:00
Masamichi Takagi
11ef2f8092 coredump: Support threads 
Change-Id: Id75ade6c87b15abcff5d772d90f77950376a32c1
Refs: #1219
 2019-08-09 04:00:15 +00:00
Tomoki Shirasawa
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
Tomoki Shirasawa
258156b57e support for read/write-lock and read/write-trylock 
Change-Id: I609071c0f6234d0d413c8b312d8a8379abf6846e
Refs: #1323
 2019-08-08 00:38:55 +00:00
Ken Sato
8efced7bf7 mmap: Check if size exceeds available memory when MAP_HUGETLB 
If size exceeds, mmap fails and set -ENOMEM

Change-Id: I4f0d6e18ee3a7c8e32e251b7ed07ee9f76305603
Refs: #1183
 2019-08-08 00:31:36 +00:00
Balazs Gerofi
2dd8687974 flush instruction cache at context switch time if necessary 
Change-Id: Ic09415ea772a9de6dca43a98168a8346ca86d3e7
 2019-08-08 00:29:47 +00:00
TOIDA,Suguru
b6285c9aa9 pmu: Use bitmap instead of index to specify counters / events 
Let the software index (or number) same as the hardware index at the
same time.

Change-Id: I847180e94bf2c57644ae2f8f571cdb4a84eac991
 2019-07-31 16:17:20 +09:00
TOIDA,Suguru
b945367c90 pmu: add ihk_mc_perfctr_value function 
Change-Id: I88d25586dd470737a3eac4c3a4f1955ae6e41d64
 2019-07-23 16:20:17 +09:00
TOIDA,Suguru
0f434288e1 pmu: change to atomic register access. 
Change-Id: Iebbdb8ca97e7a73f9d74138650ae18ce3a0f2605
 2019-07-23 16:20:16 +09:00
TOIDA,Suguru
b5cd813229 pmu: remove comment 
Change-Id: If5819ce6f665c668f1f29724a814770957df0de0
 2019-07-23 16:20:16 +09:00
TOIDA,Suguru
7268942c35 pmu: implement ihk_mc_perf_get_num_counters. 
Change-Id: I752103aedd9201fc00bda11228ca0bcf5103f12d
 2019-07-23 16:20:16 +09:00
TOIDA,Suguru
f8cad24a9a pmu: move cpu cycle event type comparison to arch dependent code. 
Change-Id: If069f8893fe59e3517569b74b3a27b5267ebac03
 2019-07-23 16:20:16 +09:00
TOIDA,Suguru
2b6b3f31e5 pmu: remove pmc_{init|start|stop|reset} system call 
Change-Id: I6eb65ed8c18558418c7aabfee75cd1974f4c03ff
 2019-07-23 16:20:16 +09:00
TOIDA,Suguru
06af2d62c6 pmu: implement event mapping function. 
Change-Id: Iac1ec99152b17a19dba0bf1a35f07724b8abc5a1
 2019-07-18 16:39:18 +09:00
Masamichi Takagi
3b74b0a093 rusage: Move pgsize_to_pgshift to arch-memory.h 
Change-Id: Ia10b6e5c7d078d345347a79a3e98c06c16d28d6a
 2019-07-02 09:10:04 +00:00