a19e6938eb
Kernel: Remove TTY keyboard thread
...
This was really hacky as it had no idea when the keyboard had events
and the blocking was just one millisecond sleeps :D
Now keyboard device checks if current tty is receiving input and if so
it forwards the events to the TTY.
2026-05-20 04:17:03 +03:00
32206069bc
Kernel: Use per cpu fast page for {Memory,File}BackedRegion
2026-05-20 02:51:48 +03:00
46a1903f8d
Kernel: Use per cpu fast page for PMM
2026-05-20 02:46:50 +03:00
a3ca49ff1f
Kernel: Don't sync ext2 inode on read
...
This is the most common operation and we don't even update any fields
during read (although we should update atime). The disk read+write is a
bit too heavy with the current cache system
2026-05-20 02:14:40 +03:00
94f92d982c
Kernel: Optimize PageTable address space reservation
...
I only did this for the 64 bit target.
2026-05-20 02:01:16 +03:00
4f5f84bb5b
Kernel: Speed up mmap address space reservation by a lot
...
Instead of scanning the page table for free range, we not use the
process's mapped regions to find a slot. This speeds up mmap by a lot!
2026-05-20 01:08:08 +03:00
5cb5ae2dfe
Kernel: Use per cpu fast pages for DiskCache
...
This makes accessing disk cache a lot faster
2026-05-20 00:17:51 +03:00
7704e3c5c0
Kernel: Implement per cpu fast pages
...
Basically every fast page usage should be converted into this but I'll
do them one by one when they show up in profiles
2026-05-20 00:16:56 +03:00
376e4b4c45
Kernel: Reduce the number of sent IPIs
...
Only send an IPI when the target processors don't have pending messages.
This basically gets rid of TLB shootdowns from showing up in profiles.
Before they were taking maybe >10% kernel time :^D
2026-05-19 23:52:38 +03:00
24c37e7381
Kernel: Move TLB invalidation out of standard SMPMessages
...
This makes accessing TLB messages much faster as TLB flushes are very
frequent in comparison to other messages
2026-05-19 23:51:01 +03:00
fb9c67ab15
Kernel: Add PageTable API to invalidate full address space
2026-05-19 23:46:56 +03:00
1dc26d3c06
Kernel: Cleanup inode stat updating
...
Inode now handles stat upates itself and calls sync function to make
updates visible on the underlying filesystem
2026-05-19 13:00:05 +03:00
a05fcdde8c
Kernel: Move UTIME_OMIT handling to the syscall from inode
2026-05-19 11:56:12 +03:00
deb2f52a35
Kernel: Add support for named pipes
...
These only copy inodes stat when created, if you fchmod/fchown a named
pipe, the change will not be visible on the filesystem
2026-05-19 00:15:25 +03:00
8224659c48
Kernel: Allow creating FIFOs in tmpfs
2026-05-19 00:05:22 +03:00
1922d78661
Kernel: Add support for mkfifo{,at} mkdir at
...
Opening FIFOs still dont work as expected but at least you can create
them now :D
2026-05-18 23:53:09 +03:00
6d1ecc2388
Kernel: Clean up file creation
2026-05-18 15:26:59 +03:00
5cf658c175
Kernel: Fix 2 memory pinning bugs
...
If pinning a region succeeded but pushing the region to a vector failed,
we would leak the pin preventing the process from cleaning up
2026-05-17 03:38:18 +03:00
ef2738bfb7
Kernel: Disable devfs device add/remove logging
2026-05-17 03:38:18 +03:00
d7865b2929
Kernel: Don't msync file backed pages that were never mapped writable
2026-05-17 03:21:08 +03:00
9c79971bdc
LibC/Kernel: Add support for detached pthreads
2026-05-17 00:40:56 +03:00
ff75c15ba3
LibC: Move pthread keys to TCB
...
This removes all TLS relocations from libc which may become handy ;)
2026-05-17 00:29:20 +03:00
9e6fa0a1ba
Kernel: Add fast path for invalid address during region pin
...
Before I was falling through to the write lock which does allocation,
but as the read loop already saw, specified address was not mapped.
2026-05-17 00:29:20 +03:00
6e95519acc
Kernel: Make TTY write lock a mutex instead of a spinlock
...
The mutex could not be locked while processing ANSI DGR in VTTY
2026-05-17 00:29:20 +03:00
d081655913
Kernel: Add API for mutex to check if it is locked by current thread
...
Also add assertion that you have interrupts enabled :^)
2026-05-17 00:29:20 +03:00
d528314ae3
Kernel: Make SYS_FUTEX restartable
2026-05-17 00:29:20 +03:00
4ef7b8e71c
Kernel: AFG reset return value
2026-05-15 21:38:23 +03:00
1fcd72e578
Kernel: replaced is_partition/storage with kind
2026-05-15 21:37:18 +03:00
5e1b5c329b
Kernel: Allow HDA stream reset to timeout
...
This was hanging on some version of qemu :^)
2026-05-15 21:30:41 +03:00
b2f795b1e1
Kernel: Pipe ignore tc attr ioctls
2026-05-15 21:23:19 +03:00
16967cd9c0
Kernel: Replace is_* with kind field
...
Replaced the is_* virtual functions with a kind field instead
2026-05-15 21:23:12 +03:00
647d6a273d
Kernel: Changed stat values from func to be field
...
- Removed virtual functions for all of the stat stuff.
This did however introduce some issues, mainly with /proc
becoming out of sync if you changed your ID. I propose we
do the linux thing and just have a stat update function
which is optional, but allows dynamic updates of stat fields
for cases such as those in uid/gid in /proc.
- Simplified the API, although still kind of annoying
it is a bit simpler.
- Moved some of the FS structure from having the FS inode inside
the in memory inode to a Serialise <-> Deserialise model where
Inodes are deserialised from disk into in memory ones and then
back into on disk ones when it comes time for syncing.
This makes it semantically better in my opinion, as it explicitly
separates disk and non-disk functionality.
2026-05-15 20:49:04 +03:00
05c9f0640c
Kernel/LibC: Replace terminal syscalls with ioctls
...
isatty, tc{get,set}attr, tc{get,set}pgrp are now implemented as ioctls
instead of separate syscalls
2026-05-15 17:03:33 +03:00
28b873b949
Kernel: Allow recursive rwlock write lock
2026-05-15 17:03:33 +03:00
c352fb600f
Kernel: Reduce ext2 locking
...
Replace the mutex with a rwlock and lock when its not necessary
2026-05-14 17:23:06 +03:00
dd8a9b1793
Kernel: clamp msync address range instead of calling contains
2026-05-13 20:03:37 +03:00
5f237abc3b
Kernel: Don't lock Ext2FS while reading and writing blocks
...
There is really no reason for this. The underlying block devices are
(should be) thread safe themselves
2026-05-09 23:28:00 +03:00
0bf7328e04
Kernel: Handle TIOC{G,S}WINSZ on pipes
...
GCC likes to do this a lot and debug logging is excessive
2026-05-09 23:28:00 +03:00
9f4271f6d8
Kernel: Remove the big inode lock
...
This moves locking to the inodes themselves which allows reducing lock
times significantly. Main inodes (ext2 and tmpfs) still do contain a
single big mutex that gets locked during operations but now we have the
architecture to optimize these.
2026-05-09 23:28:00 +03:00
a7356716ff
Kernel: Reduce locking FileBackedRegions
2026-05-09 15:08:26 +03:00
d2e21f9380
Kernel: Fix 64 bit page table range reservation from lower->higher half
2026-05-06 17:30:43 +03:00
443be800b7
Kernel: Fix remote TLB shootdown for <= 32 pages
...
I was modifying the `vaddr` argument while invalidating which lead to
the smp message containing wrong virtual address. This showed up in
really weird bugs from invalid TLB
2026-05-06 17:30:43 +03:00
3ac955714b
Kernel: Optimize FileBackedRegion CoW
...
Just copy data from the existing page instead of locking inode's shared
data, copying to temporary buffer and finally copying to destination
2026-05-06 17:30:43 +03:00
62f5292f38
Kernel: Send only one TLB invalidation when creating a ByteRingBuffer
2026-05-06 17:30:43 +03:00
7553ede3b4
Kernel: Send only one TLB invalidation when creating a VirtualRange
2026-05-06 00:27:26 +03:00
eba97c1fc7
Kernel: Avoid possible dead lock while sending smp messages
...
Process own events while waiting for space on another processor. This
fixes a dead lock when processors are sending messages to each other
2026-05-06 00:09:05 +03:00
efeaafaff6
Kernel: Cleanup E1000 link speed code
2026-05-04 21:23:04 +03:00
6966475dcf
Kernel: Make E1000 sending lockless and mostly non-blocking
...
Now we only block if all 256 tx descriptors are waiting to be sent. This
removes TCP acks from taking 30% of profiles while DOWNLOADING files
2026-05-04 21:15:15 +03:00
dfe24b69e0
Kernel: Don't keep devfs locked while performing disk sync
2026-05-04 20:26:02 +03:00
93e1091252
Kernel: Rewrite kmalloc
...
Kmalloc is now a bitmap allocator with dynamic resizing and we dont need
to allocate 64 MiB static block of memory reserved for kmalloc :^)
2026-05-04 20:26:02 +03:00
