driver-install: implemented a simple installer

Kernel: Implemented banos - a WIP C driver API
Banos is a stable WIP C driver API that is supposed to provide a simple interface to interact with the kernel and load the modules dynamically. It is WIP and atm this just implements module loading with a custom banos_install syscall. Banos will not try to substitute parts of the kernel instead it will just expose kernel functionality via a stable BINARY API. Meaning binaries (should) remain forward and backward compatible on a binary level. Banos modules work similarly to those in linux, you expose symbols via BANOS_EXPORT which allows you to export a name + addr paired symbol. It puts it in the .banos-export section. Drivers provide metadata about themselves in the REQUIRED .banos-driver section. Symbols are resolved at runtime. The kernel exposes the driver functionality via the same .banos-export export mechanism. Banos modules are elf RELOCATABLE files (object files) which have partial linking (only banos symbols should remain). Modules will eventually define dependencies, will export symbols and will allow you to build a complex object hierarchy. This patch adds the banos_install syscall which takes in the driver image to install and may only be executed by super users. The API doesn't validate already loaded modules, as thats something the userspace MAY choose to keep track of. Multi-instance functionality shall be implemented via driver specific behaviuor (exposed in the dev filesystem or some other means). Modules are supposed to allow you to alter kernel behavior and extend it, allowing you to create filesystems, drivers, networking modifications, schedulers, probers, and more (hopefully) whilst remaining binary compatible with any version of the kernel (again, hopefully).
2026-05-20 17:34:44 +03:00 · 2026-05-20 17:34:42 +03:00 · 2026-05-20 17:34:39 +03:00
490 changed files with 7283 additions and 17148 deletions
@@ -98,8 +98,7 @@ namespace BAN

 		struct EntryHash
 		{
-			template<detail::HashMapFindable<Key, HASH, COMP> U>
-			constexpr bool operator()(const U& a)
+			constexpr bool operator()(const Key& a)
 			{
 				return HASH()(a);
 			}
@@ -111,8 +110,7 @@ namespace BAN

 		struct EntryComp
 		{
-			template<detail::HashMapFindable<Key, HASH, COMP> U>
-			constexpr bool operator()(const Entry& a, const U& b)
+			constexpr bool operator()(const Entry& a, const Key& b)
 			{
 				return COMP()(a.key, b);
 			}
@@ -2,7 +2,6 @@

 #include <BAN/Limits.h>
 #include <BAN/Numbers.h>
-#include <BAN/Swap.h>
 #include <BAN/Traits.h>

 #include <float.h>
@@ -82,37 +81,6 @@ namespace BAN::Math
 		return x + 1;
 	}

-	template<unsigned_integral T>
-	requires is_same_v<T, unsigned int> || is_same_v<T, unsigned long> || is_same_v<T, unsigned long long>
-	inline constexpr int clz(T x)
-	{
-		if constexpr (is_same_v<T, unsigned int>)
-			return __builtin_clz(x);
-		if constexpr (is_same_v<T, unsigned long>)
-			return __builtin_clzl(x);
-		return __builtin_clzll(x);
-	}
-
-	template<unsigned_integral T> requires(sizeof(T) <= sizeof(unsigned long long))
-	inline constexpr int ctz(T x)
-	{
-		if constexpr (sizeof(T) <= sizeof(unsigned int))
-			return __builtin_ctz(x);
-		if constexpr (sizeof(T) <= sizeof(unsigned long))
-			return __builtin_ctzl(x);
-		return __builtin_ctzll(x);
-	}
-
-	template<unsigned_integral T> requires(sizeof(T) <= sizeof(unsigned long long))
-	inline constexpr int popcount(T x)
-	{
-		if constexpr (sizeof(T) <= sizeof(unsigned int))
-			return __builtin_popcount(x);
-		if constexpr (sizeof(T) <= sizeof(unsigned long))
-			return __builtin_popcountl(x);
-		return __builtin_popcountll(x);
-	}
-
 	template<integral T>
 	__attribute__((always_inline))
 	inline constexpr bool will_multiplication_overflow(T a, T b)
@@ -133,7 +101,11 @@ namespace BAN::Math
 	requires is_same_v<T, unsigned int> || is_same_v<T, unsigned long> || is_same_v<T, unsigned long long>
 	inline constexpr T ilog2(T x)
 	{
-		return sizeof(T) * 8 - clz(x) - 1;
+		if constexpr(is_same_v<T, unsigned int>)
+			return sizeof(T) * 8 - __builtin_clz(x) - 1;
+		if constexpr(is_same_v<T, unsigned long>)
+			return sizeof(T) * 8 - __builtin_clzl(x) - 1;
+		return sizeof(T) * 8 - __builtin_clzll(x) - 1;
 	}

 // This is ugly but my clangd does not like including
@@ -336,6 +308,36 @@ namespace BAN::Math
 		return exp2<T>(y * log2<T>(x));
 	}

+	template<floating_point T>
+	inline constexpr T scalbn(T x, int n)
+	{
+		asm("fscale" : "+t"(x) : "u"(static_cast<T>(n)));
+		return x;
+	}
+
+	template<floating_point T>
+	inline constexpr T ldexp(T x, int y)
+	{
+		const bool exp_sign = y < 0;
+		if (exp_sign)
+			y = -y;
+
+		T exp = (T)1.0;
+		T mult = (T)2.0;
+		while (y)
+		{
+			if (y & 1)
+				exp *= mult;
+			mult *= mult;
+			y >>= 1;
+		}
+
+		if (exp_sign)
+			exp = (T)1.0 / exp;
+
+		return x * exp;
+	}
+
 	template<floating_point T>
 	inline constexpr T sqrt(T x)
 	{
@@ -468,17 +470,7 @@ namespace BAN::Math
 	template<floating_point T>
 	inline constexpr T hypot(T x, T y)
 	{
-		x = abs(x);
-		y = abs(y);
-
-		if (x < y)
-			swap(x, y);
-
-		if (y == (T)0.0)
-			return x;
-
-		const T r = y / x;
-		return x * sqrt<T>((T)1.0 + r * r);
+		return sqrt<T>(x * x + y * y);
 	}

 #ifdef BAN_MATH_POP_OPTIONS
@@ -67,20 +67,11 @@ namespace BAN::sort
 	template<typename It, typename Comp = less<it_value_type_t<It>>>
 	void quick_sort(It begin, It end, Comp comp = {})
 	{
-		while (distance(begin, end) > 1)
-		{
-			const auto [lt, gt] = detail::partition(begin, end, comp);
-			if (distance(begin, lt) < distance(gt, end))
-			{
-				quick_sort(begin, lt);
-				begin = gt;
-			}
-			else
-			{
-				quick_sort(gt, end);
-				end = lt;
-			}
-		}
+		if (distance(begin, end) <= 1)
+			return;
+		const auto [lt, gt] = detail::partition(begin, end, comp);
+		quick_sort(begin, lt, comp);
+		quick_sort(gt, end, comp);
 	}

 	template<typename It, typename Comp = less<it_value_type_t<It>>>
@@ -111,28 +102,13 @@ namespace BAN::sort
 		template<typename It, typename Comp>
 		void intro_sort_impl(It begin, It end, size_t max_depth, Comp comp)
 		{
-			for (size_t i = 0; i < max_depth; i++)
-			{
-				const size_t len = distance(begin, end);
-				if (len <= 1)
-					return;
-				if (len <= 16)
-					return insertion_sort(begin, end, comp);
-
-				const auto [lt, gt] = detail::partition(begin, end, comp);
-				if (distance(begin, lt) < distance(gt, end))
-				{
-					intro_sort_impl(begin, lt, max_depth - 1, comp);
-					begin = gt;
-				}
-				else
-				{
-					intro_sort_impl(gt, end, max_depth - 1, comp);
-					end = lt;
-				}
-			}
-
-			heap_sort(begin, end, comp);
+			if (distance(begin, end) <= 16)
+				return insertion_sort(begin, end, comp);
+			if (max_depth == 0)
+				return heap_sort(begin, end, comp);
+			const auto [lt, gt] = detail::partition(begin, end, comp);
+			intro_sort_impl(begin, lt, max_depth - 1, comp);
+			intro_sort_impl(gt, end, max_depth - 1, comp);
 		}

 	}
@@ -100,22 +100,3 @@ namespace BAN
 	};

 }
-
-#include <BAN/Formatter.h>
-
-namespace BAN::Formatter
-{
-
-	template<typename F, typename T>
-	void print_argument(F putc, const Span<T>& span, const ValueFormat& format)
-	{
-		putc('[');
-		for (typename Span<T>::size_type i = 0; i < span.size(); i++)
-		{
-			if (i != 0) putc(',');
-			print_argument(putc, span[i], format);
-		}
-		putc(']');
-	}
-
-}
@@ -27,12 +27,6 @@ set(BUILD_SHARED_LIBS True)

 set(CMAKE_EXPORT_COMPILE_COMMANDS ON)

-find_program(CCACHE_PROGRAM "ccache")
-if (CCACHE_PROGRAM)
-	set(CMAKE_C_COMPILER_LAUNCHER "${CCACHE_PROGRAM}")
-	set(CMAKE_CXX_COMPILER_LAUNCHER "${CCACHE_PROGRAM}")
-endif()
-
 # include headers of ${library} to ${target}
 function(banan_include_headers target library)
 	target_include_directories(${target} PUBLIC $<TARGET_PROPERTY:${library},SOURCE_DIR>/include)
@@ -9,7 +9,7 @@ This is my hobby operating system written in C++. Currently supports x86\_64 and

 You can find a live demo [here](https://bananymous.com/banan-os)

-![screenshot from qemu running banan-os](assets/banan-os.png)
+If you want to try out DOOM, you should first enter the GUI environment using the `start-gui` command. Then you can run `doom` in the GUI terminal.

 ### Features

@@ -18,8 +18,6 @@ You can find a live demo [here](https://bananymous.com/banan-os)
 - [x] SMP (multiprocessing)
 - [x] Linear framebuffer (VESA and GOP)
 - [x] Network stack
- [x] USB stack
- [x] Audio support
 - [x] ELF executable loading
 - [x] AML interpreter (partial)
 - [x] Basic graphical environment
@@ -29,14 +27,16 @@ You can find a live demo [here](https://bananymous.com/banan-os)
  - [ ] Some nice apps
 - [x] ELF dynamic linking
 - [x] copy-on-write memory
+  - [x] file mappings
+  - [ ] anonymous mappings

 #### Drivers
 - [x] NVMe disks
 - [x] ATA (IDE, SATA) disks
 - [x] E1000 and E1000E NICs
 - [x] RTL8111/8168/8211/8411 NICs
- [x] AC97 and iHDA audio cards
- [x] PS2 keyboard and mouse
+- [x] PS2 keyboard (all scancode sets)
+- [x] PS2 mouse
 - [x] USB
  - [x] xHCI
  - [ ] EHCI
@@ -46,8 +46,7 @@ You can find a live demo [here](https://bananymous.com/banan-os)
  - [x] Mouse
  - [x] Mass storage
  - [x] Hubs
-  - [ ] Network
-  - [ ] Audio
+  - [ ] ...
 - [ ] virtio devices (network, storage)

 #### Network
@@ -55,7 +54,7 @@ You can find a live demo [here](https://bananymous.com/banan-os)
 - [x] ICMP
 - [x] IPv4
 - [x] UDP
- [x] TCP
+- [x] TCP (partial and buggy)
 - [x] Unix domain sockets
 - [ ] SSL

@@ -66,6 +65,7 @@ You can find a live demo [here](https://bananymous.com/banan-os)
 - [x] Dev
 - [x] Ram
 - [x] Proc
+- [ ] Sys
 - [ ] 9P

 #### Bootloader support
@@ -73,6 +73,8 @@ You can find a live demo [here](https://bananymous.com/banan-os)
 - [x] Custom BIOS bootloader
 - [ ] Custom UEFI bootloader

+![screenshot from qemu running banan-os](assets/banan-os.png)
+
 ## Code structure

 Each major component and library has its own subdirectory (kernel, userspace, libc, ...). Each directory contains directory *include*, which has **all** of the header files of the component. Every header is included by its absolute path.
@@ -116,29 +118,15 @@ To change the bootloader you can set environment variable BANAN\_BOOTLOADER; sup

 To run with UEFI set environment variable BANAN\_UEFI\_BOOT=1. You will also have to set OVMF\_PATH to the correct OVMF (default */usr/share/ovmf/x64/OVMF.fd*).

-To build an image with no physical root filesystem, but an initrd set environment variable BANAN\_INITRD=1. This can be used when testing on hardware with unsupported USB controller. If BANAN\_INITRD is set to a value larger than 1, initrd will be gzip compressed.
+To build an image with no physical root filesystem, but an initrd set environment variable BANAN\_INITRD=1. This can be used when testing on hardware with unsupported USB controller.

 If you have corrupted your disk image or want to create new one, you can either manually delete *build/banan-os.img* and build system will automatically create you a new one or you can run the following command.
 ```sh
 ./bos image-full
 ```

-To test on real hardware, I have a script to generate a compressed ISO. The ISO can be copied directly to an USB drive with for example `dd`. The file is created at build/banan-os.iso and can be generated with
-```sh
-./bos iso
-```
-
 I have also created shell completion script for zsh. You can either copy the file in _script/shell-completion/zsh/\_bos_ to _/usr/share/zsh/site-functions/_ or add the _script/shell-completion/zsh_ to your fpath in _.zshrc_.

-### Package Manager
-
-banan-os uses xbps as its package manager for ports. All upstream ports are packaged into xbps packages hosted on a [repository on my server](https://packages.bananymous.com/banan-os). You can manage sysroot's xbps packages with `./bos` wrapper. You can use `xbps-install`, `xbps-remove` and `xbps-query` with repository and sysroot set to the correct values. For example to install xbps that can be used inside banan-os you can use
-```sh
-./bos xbps-install -S xbps
-```
-For xbps usage see [their documentation](https://docs.voidlinux.org/xbps/index.html).
-
-
 ## Contributing

 As the upstream is hosted on my server https://git.bananymous.com/Bananymous/banan-os, merging contributions is not as trivial as it would be on GitHub. You can still send PRs in GitHub in which case I should be able to download the diff and apply it manually. If you want, I can also provide you an account to my git server. In this case please contact me ([email](mailto:[email protected]), [discord](https://discord.gg/ehjGySwYdK)).
@@ -35,13 +35,13 @@ read_user_command_line:
 	cmpb $'\n', %al
 	je .read_user_command_line_done

-	movb %al, %bl
+	pushw %ax

 	call isprint
 	testb %al, %al
 	jz .read_user_command_line_loop

-	movb %bl, %al
+	popw %ax

 	# put byte to buffer
 	movb %al, (%di)
@@ -108,11 +108,9 @@ vesa_find_video_mode:
 	cmpb $0x4F, %al; jne .vesa_unsupported
 	cmpb $0x00, %ah; jne .vesa_error

-	# check whether in graphics mode and linear framebuffer
-	movb (vesa_mode_info_buffer + 0), %al
-	andb $(0x80 | 0x10), %al
-	cmpb $(0x80 | 0x10), %al
-	jne .vesa_find_video_mode_next_mode
+	# check whether in graphics mode
+	testb $0x10, (vesa_mode_info_buffer + 0)
+	jz .vesa_find_video_mode_next_mode

 	# compare mode's dimensions
 	movw -2(%ebp), %ax; cmpw %ax, (vesa_mode_info_buffer + 0x12)
@@ -2,8 +2,6 @@

 .section .stage2

-.set mmap_entry_size, 24
-
 # fills memory map data structure
 # doesn't return on error
 # NO REGISTERS SAVED
@@ -14,7 +12,7 @@ get_memory_map:
 	movl $0x0000E820, %eax
 	movl $0x534D4150, %edx
 	xorl %ebx, %ebx
-	movl $mmap_entry_size, %ecx
+	movl $20, %ecx
 	movw $memory_map_entries, %di

 	clc
@@ -26,15 +24,15 @@ get_memory_map:
 	cmpl $0x534D4150, %eax
 	jne .get_memory_map_error

-	# confirm that we got at least 20 bytes
+	# FIXME: don't assume BIOS to always return 20 bytes
 	cmpl $20, %ecx
-	jl .get_memory_map_error
+	jne .get_memory_map_error

 	# increment entry count
 	incl (memory_map_entry_count)

 	# increment entry pointer
-	addw $mmap_entry_size, %di
+	addw %cx, %di

 	# BIOS can indicate end of list by 0 in ebx
 	testl %ebx, %ebx
@@ -109,7 +107,7 @@ print_memory_map:

 	call print_newline

-	addw $mmap_entry_size, %si
+	addw $20, %si

 	decl %edx
 	jnz .loop_memory_map
@@ -129,8 +127,6 @@ memory_map_error_msg:
 memory_map:
 memory_map_entry_count:
 	.skip 4
-memory_map_padding:
-	.skip 4
-# 128 entries should be enough...
+# 100 entries should be enough...
 memory_map_entries:
-	.skip mmap_entry_size * 128
+	.skip 20 * 100
@@ -41,7 +41,6 @@ set(KERNEL_SOURCES
 	kernel/FS/USTARModule.cpp
 	kernel/FS/VirtualFileSystem.cpp
 	kernel/GDT.cpp
-	kernel/Graphics/BGA.cpp
 	kernel/IDT.cpp
 	kernel/Input/InputDevice.cpp
 	kernel/Input/PS2/Controller.cpp
@@ -52,8 +51,6 @@ set(KERNEL_SOURCES
 	kernel/Interruptable.cpp
 	kernel/InterruptController.cpp
 	kernel/kernel.cpp
-	kernel/Lock/Mutex.cpp
-	kernel/Lock/RWLock.cpp
 	kernel/Lock/SpinLock.cpp
 	kernel/Memory/ByteRingBuffer.cpp
 	kernel/Memory/DMARegion.cpp
@@ -86,7 +83,6 @@ set(KERNEL_SOURCES
 	kernel/Processor.cpp
 	kernel/Random.cpp
 	kernel/Scheduler.cpp
-	kernel/SchedulerThreadNode.cpp
 	kernel/SSP.cpp
 	kernel/Storage/ATA/AHCI/Controller.cpp
 	kernel/Storage/ATA/AHCI/Device.cpp
@@ -59,7 +59,7 @@ signal_trampoline:
 	addl $24, %esp

 	// restore sigmask
-	movl $79, %eax      // SYS_SIGPROCMASK
+	movl $83, %eax      // SYS_SIGPROCMASK
 	movl $3,  %ebx      // SIG_SETMASK
 	leal 72(%esp), %ecx // set
 	xorl %edx, %edx     // oset
@@ -63,7 +63,7 @@ sys_fork_trampoline:

 	call read_ip
 	testl %eax, %eax
-	jz .Lsys_fork_trampoline_done
+	jz .done

 	movl %esp, %ebx

@@ -73,7 +73,7 @@ sys_fork_trampoline:
 	call sys_fork
 	addl $16, %esp

- .Lsys_fork_trampoline_done:
+ .done:
 	popl %edi
 	popl %esi
 	popl %ebx
@@ -28,26 +28,27 @@ safe_user_strncpy:
 	testl %ecx, %ecx
 	jz safe_user_strncpy_fault

- .Lsafe_user_strncpy_loop:
+ .safe_user_strncpy_loop:
 	movb (%esi), %al
 	movb %al, (%edi)
 	testb %al, %al
-	jz .Lsafe_user_strncpy_done
+	jz .safe_user_strncpy_done

 	incl %edi
 	incl %esi
 	decl %ecx
-	jnz .Lsafe_user_strncpy_loop
+	jnz .safe_user_strncpy_loop

 safe_user_strncpy_fault:
 	xorl %eax, %eax
-	jmp .Lsafe_user_strncpy_return
+	jmp .safe_user_strncpy_return

- .Lsafe_user_strncpy_done:
+ .safe_user_strncpy_done:
 	movl $1, %eax

- .Lsafe_user_strncpy_return:
+ .safe_user_strncpy_return:
 	movl 4(%esp), %edi
 	movl 8(%esp), %esi
 	ret
+
 safe_user_strncpy_end:
@@ -12,7 +12,7 @@ asm_yield_trampoline:
 	pushl %ebp

 	pushl %esp
-	call scheduler_on_yield_trampoline
+	call scheduler_on_yield
 	addl $4, %esp

 	popl %ebp
@@ -168,12 +168,14 @@ has_sse:

 check_requirements:
 	call has_cpuid
-	jz system_halt
+	jz .exit
 	call has_pae
-	jz system_halt
+	jz .exit
 	call has_sse
-	jz system_halt
+	jz .exit
 	ret
+.exit:
+	jmp system_halt

 enable_sse:
 	movl %cr0, %eax
@@ -223,8 +225,8 @@ _start:

 	# load boot GDT
 	lgdt V2P(boot_gdtr)
-	ljmpl $0x08, $V2P(.Lgdt_flush)
-.Lgdt_flush:
+	ljmpl $0x08, $V2P(gdt_flush)
+gdt_flush:
 	# set correct segment registers
 	movw $0x10, %ax
 	movw %ax, %ds
@@ -241,10 +243,10 @@ _start:
 	movl $g_boot_stack_top, %esp

 	# jump to higher half
-	leal .Lhigher_half, %ecx
+	leal higher_half, %ecx
 	jmp *%ecx

-.Lhigher_half:
+higher_half:
 	# call global constuctors
 	call _init

@@ -296,18 +298,18 @@ ap_ready:
 	.skip 4

 1:	cli; cld
-	ljmpl $0x00, $AP_REL(.Lap_cs_clear)
+	ljmpl $0x00, $AP_REL(ap_cs_clear)

-.Lap_cs_clear:
+ap_cs_clear:
 	# load ap gdt and enter protected mode
 	lgdt AP_REL(ap_gdtr)
 	movl %cr0, %eax
 	orb $1, %al
 	movl %eax, %cr0
-	ljmpl $0x08, $AP_REL(.Lap_protected_mode)
+	ljmpl $0x08, $AP_REL(ap_protected_mode)

 .code32
-.Lap_protected_mode:
+ap_protected_mode:
 	movw $0x10, %ax
 	movw %ax, %ds
 	movw %ax, %ss
@@ -321,13 +323,13 @@ ap_ready:

 	# load boot gdt and enter long mode
 	lgdt V2P(boot_gdtr)
-	ljmpl $0x08, $AP_REL(.Lap_flush_gdt)
+	ljmpl $0x08, $AP_REL(ap_flush_gdt)

-.Lap_flush_gdt:
-	movl $.Lap_higher_half, %ecx
+ap_flush_gdt:
+	movl $ap_higher_half, %ecx
 	jmp *%ecx

-.Lap_higher_half:
+ap_higher_half:
 	movl AP_REL(ap_prepare_paging), %eax
 	call *%eax

@@ -27,10 +27,14 @@

 isr_stub:
 	intr_header 12
+	movl %cr0, %eax; pushl %eax
+	movl %cr2, %eax; pushl %eax
+	movl %cr3, %eax; pushl %eax
+	movl %cr4, %eax; pushl %eax

-	movl 32(%esp), %edi // isr number
-	movl 36(%esp), %esi // error code
-	leal 40(%esp), %edx // interrupt stack ptr
+	movl 48(%esp), %edi // isr number
+	movl 52(%esp), %esi // error code
+	leal 56(%esp), %edx // interrupt stack ptr
 	movl %esp,     %ecx // register ptr

 	# stack frame for stack trace
@@ -48,7 +52,7 @@ isr_stub:
 	call cpp_isr_handler

 	movl %ebp, %esp
-	addl $8, %esp
+	addl $24, %esp

 	intr_footer 12
 	addl $8, %esp
@@ -61,7 +61,7 @@ signal_trampoline:
 	addq $40, %rsp

 	// restore sigmask
-	movq $79, %rdi       // SYS_SIGPROCMASK
+	movq $83, %rdi       // SYS_SIGPROCMASK
 	movq $3,  %rsi       // SIG_SETMASK
 	leaq 192(%rsp), %rdx // set
 	xorq %r10, %r10      // oset
@@ -33,13 +33,13 @@ sys_fork_trampoline:

 	call read_ip
 	testq %rax, %rax
-	jz .Lsys_fork_trampoline_done
+	jz .done

 	movq %rax, %rsi
 	movq %rsp, %rdi
 	call sys_fork

- .Lsys_fork_trampoline_done:
+ .done:
 	popq %r15
 	popq %r14
 	popq %r13
@@ -20,28 +20,28 @@ safe_user_strncpy:
 	testq %rcx, %rcx
 	jz safe_user_strncpy_fault

- .Lsafe_user_strncpy_align_loop:
+ .safe_user_strncpy_align_loop:
 	testb $0x7, %sil
-	jz .Lsafe_user_strncpy_align_done
+	jz .safe_user_strncpy_align_done

 	movb (%rsi), %al
 	movb %al, (%rdi)
 	testb %al, %al
-	jz .Lsafe_user_strncpy_done
+	jz .safe_user_strncpy_done

 	incq %rdi
 	incq %rsi
 	decq %rcx
-	jnz .Lsafe_user_strncpy_align_loop
+	jnz .safe_user_strncpy_align_loop
 	jmp safe_user_strncpy_fault

- .Lsafe_user_strncpy_align_done:
+ .safe_user_strncpy_align_done:
 	movq $0x0101010101010101, %r8
 	movq $0x8080808080808080, %r9

- .Lsafe_user_strncpy_qword_loop:
+ .safe_user_strncpy_qword_loop:
 	cmpq $8, %rcx
-	jb .Lsafe_user_strncpy_qword_done
+	jb .safe_user_strncpy_qword_done

 	movq (%rsi), %rax
 	movq %rax, %r10
@@ -52,36 +52,36 @@ safe_user_strncpy:
 	notq %r11
 	andq %r11, %r10
 	andq %r9, %r10
-	jnz .Lsafe_user_strncpy_byte_loop
+	jnz .safe_user_strncpy_byte_loop

 	movq %rax, (%rdi)

 	addq $8, %rdi
 	addq $8, %rsi
 	subq $8, %rcx
-	jnz .Lsafe_user_strncpy_qword_loop
+	jnz .safe_user_strncpy_qword_loop
 	jmp safe_user_strncpy_fault

- .Lsafe_user_strncpy_qword_done:
+ .safe_user_strncpy_qword_done:
 	testq %rcx, %rcx
 	jz safe_user_strncpy_fault

- .Lsafe_user_strncpy_byte_loop:
+ .safe_user_strncpy_byte_loop:
 	movb (%rsi), %al
 	movb %al, (%rdi)
 	testb %al, %al
-	jz .Lsafe_user_strncpy_done
+	jz .safe_user_strncpy_done

 	incq %rdi
 	incq %rsi
 	decq %rcx
-	jnz .Lsafe_user_strncpy_byte_loop
+	jnz .safe_user_strncpy_byte_loop

 safe_user_strncpy_fault:
 	xorq %rax, %rax
 	ret

- .Lsafe_user_strncpy_done:
+ .safe_user_strncpy_done:
 	movb $1, %al
 	ret
 safe_user_strncpy_end:
@@ -15,7 +15,7 @@ asm_yield_trampoline:
 	pushq %r15

 	movq %rsp, %rdi
-	call scheduler_on_yield_trampoline
+	call scheduler_on_yield

 	popq %r15
 	popq %r14
@@ -161,10 +161,12 @@ is_64_bit:

 check_requirements:
 	call has_cpuid
-	jz system_halt
+	jz .exit
 	call is_64_bit
-	jz system_halt
+	jz .exit
 	ret
+.exit:
+	jmp system_halt

 enable_sse:
 	movl %cr0, %eax
@@ -224,10 +226,10 @@ _start:

 	# flush gdt and jump to 64 bit
 	lgdt V2P(boot_gdtr)
-	ljmpl $0x08, $V2P(.Llong_mode)
+	ljmpl $0x08, $V2P(long_mode)

 .code64
-.Llong_mode:
+long_mode:
 	movw $0x10, %ax
 	movw %ax, %ds
 	movw %ax, %ss
@@ -238,10 +240,10 @@ _start:
 	addq $KERNEL_OFFSET, %rsp

 	# jump to higher half
-	movabsq $.Lhigher_half, %rcx
+	movabsq $higher_half, %rcx
 	jmp *%rcx

-.Lhigher_half:
+higher_half:
 	# call global constuctors
 	call _init

@@ -291,18 +293,18 @@ ap_ready:
 	.skip 8

 1:	cli; cld
-	ljmpl $0x00, $AP_REL(.Lap_cs_clear)
+	ljmpl $0x00, $AP_REL(ap_cs_clear)

-.Lap_cs_clear:
+ap_cs_clear:
 	# load ap gdt and enter protected mode
 	lgdt AP_REL(ap_gdtr)
 	movl %cr0, %eax
 	orb $1, %al
 	movl %eax, %cr0
-	ljmpl $0x08, $AP_REL(.Lap_protected_mode)
+	ljmpl $0x08, $AP_REL(ap_protected_mode)

 .code32
-.Lap_protected_mode:
+ap_protected_mode:
 	movw $0x10, %ax
 	movw %ax, %ds
 	movw %ax, %ss
@@ -316,14 +318,14 @@ ap_ready:

 	# load boot gdt and enter long mode
 	lgdt V2P(boot_gdtr)
-	ljmpl $0x08, $AP_REL(.Lap_long_mode)
+	ljmpl $0x08, $AP_REL(ap_long_mode)

 .code64
-.Lap_long_mode:
-	movq $.Lap_higher_half, %rax
+ap_long_mode:
+	movq $ap_higher_half, %rax
 	jmp *%rax

-.Lap_higher_half:
+ap_higher_half:
 	movq AP_REL(ap_prepare_paging), %rax
 	call *%rax

@@ -44,12 +44,17 @@

 isr_stub:
 	intr_header 24
+	movq %cr0, %rax; pushq %rax
+	movq %cr2, %rax; pushq %rax
+	movq %cr3, %rax; pushq %rax
+	movq %cr4, %rax; pushq %rax

-	movq 120(%rsp), %rdi // isr number
-	movq 128(%rsp), %rsi // error code
-	leaq 136(%rsp), %rdx // interrupt stack ptr
-	movq %rsp, %rcx      // register ptr
+	movq 152(%rsp), %rdi	// isr number
+	movq 160(%rsp), %rsi	// error code
+	leaq 168(%rsp), %rdx	// interrupt stack ptr
+	movq %rsp, %rcx			// register ptr
 	call cpp_isr_handler
+	addq $32, %rsp

 	intr_footer 24
 	addq $16, %rsp
@@ -38,39 +38,25 @@ extern "C" void __cxa_finalize(void* f)
 	}
 };

-extern "C" int __cxa_guard_acquire(uint64_t* g)
+namespace __cxxabiv1
 {
-	uint8_t* guard = reinterpret_cast<uint8_t*>(g);
+	using __guard = uint64_t;

-	for (;;)
+	extern "C" int __cxa_guard_acquire (__guard* g)
 	{
-		if (BAN::atomic_load(guard[0], BAN::memory_order_acquire))
-			return 0;
+		uint8_t* byte = reinterpret_cast<uint8_t*>(g);
+		uint8_t zero = 0;
+		return __atomic_compare_exchange_n(byte, &zero, 1, false, __ATOMIC_ACQUIRE, __ATOMIC_ACQUIRE);
+	}

-		uint8_t expected = 0;
-		if (BAN::atomic_compare_exchange(guard[1], expected, 1, BAN::memory_order_acquire))
-		{
-			if (BAN::atomic_load(guard[0], BAN::memory_order_acquire))
-			{
-				BAN::atomic_store(guard[1], 0, BAN::memory_order_release);
-				return 0;
-			}
-			return 1;
-		}
+	extern "C" void __cxa_guard_release (__guard* g)
+	{
+		uint8_t* byte = reinterpret_cast<uint8_t*>(g);
+		__atomic_store_n(byte, 0, __ATOMIC_RELEASE);
+	}

-		while (BAN::atomic_load(guard[1], BAN::memory_order_acquire))
-			Kernel::Processor::pause();
+	extern "C" void __cxa_guard_abort (__guard*)
+	{
+		Kernel::panic("__cxa_guard_abort");
 	}
 }
-
-extern "C" void __cxa_guard_release(uint64_t* g)
-{
-	uint8_t* guard = reinterpret_cast<uint8_t*>(g);
-	BAN::atomic_store(guard[0], 1, BAN::memory_order_release);
-	BAN::atomic_store(guard[1], 0, BAN::memory_order_release);
-}
-
-extern "C" void __cxa_guard_abort(uint64_t*)
-{
-	Kernel::panic("__cxa_guard_abort");
-}
@@ -4,7 +4,6 @@
 #include <kernel/ACPI/AML/Namespace.h>
 #include <kernel/ACPI/EmbeddedController.h>
 #include <kernel/ACPI/Headers.h>
-#include <kernel/Interruptable.h>
 #include <kernel/Memory/Types.h>
 #include <kernel/ThreadBlocker.h>

@@ -24,7 +23,11 @@ namespace Kernel::ACPI

 		const SDTHeader* get_header(BAN::StringView signature, uint32_t index);

-		BAN::ErrorOr<void> enter_acpi_mode();
+		// mode
+		//   0: PIC
+		//   1: APIC
+		//   2: SAPIC
+		BAN::ErrorOr<void> enter_acpi_mode(uint8_t mode);

 		BAN::ErrorOr<void> initialize_acpi_devices();

@@ -54,7 +57,6 @@ namespace Kernel::ACPI

 		BAN::ErrorOr<void> initialize_embedded_controller(const AML::Scope& embedded_controller);
 		BAN::ErrorOr<void> initialize_embedded_controllers();
-		void initialize_embedded_controller_gpes();

 		BAN::Optional<GAS> find_gpe_block(size_t index);
 		bool enable_gpe(uint8_t gpe);
@@ -1,12 +1,11 @@
 #pragma once

 #include <BAN/Atomic.h>
-#include <BAN/Optional.h>
 #include <BAN/UniqPtr.h>

 #include <kernel/ACPI/AML/Scope.h>
 #include <kernel/Lock/Mutex.h>
-#include <kernel/ThreadBlocker.h>
+#include <kernel/Thread.h>

 namespace Kernel::ACPI
 {
@@ -14,7 +13,7 @@ namespace Kernel::ACPI
 	class EmbeddedController
 	{
 	public:
-		static BAN::ErrorOr<BAN::UniqPtr<EmbeddedController>> create(AML::Scope&& scope, uint16_t command_port, uint16_t data_port);
+		static BAN::ErrorOr<BAN::UniqPtr<EmbeddedController>> create(AML::Scope&& scope, uint16_t command_port, uint16_t data_port, BAN::Optional<uint8_t> gpe);
 		~EmbeddedController();

 		BAN::ErrorOr<uint8_t> read_byte(uint8_t offset);
@@ -22,21 +21,21 @@ namespace Kernel::ACPI

 		const AML::Scope& scope() const { return m_scope; }

-		static void handle_gpe_trampoline(void*);
-
 	private:
-		EmbeddedController(AML::Scope&& scope, uint16_t command_port, uint16_t data_port)
+		EmbeddedController(AML::Scope&& scope, uint16_t command_port, uint16_t data_port, bool has_gpe)
 			: m_scope(BAN::move(scope))
 			, m_command_port(command_port)
 			, m_data_port(data_port)
+			, m_has_gpe(has_gpe)
 		{ }

 	private:
-		void wait_status_bit(uint8_t mask, bool set);
+		void wait_status_bit(uint8_t bit, uint8_t value);

 		uint8_t read_one(uint16_t port);
 		void write_one(uint16_t port, uint8_t value);

+		static void handle_gpe_wrapper(void*);
 		void handle_gpe();

 		BAN::ErrorOr<void> call_query_method(uint8_t notification);
@@ -57,6 +56,7 @@ namespace Kernel::ACPI
 		const AML::Scope m_scope;
 		const uint16_t m_command_port;
 		const uint16_t m_data_port;
+		const bool m_has_gpe;

 		Mutex m_mutex;
 		ThreadBlocker m_thread_blocker;
@@ -8,7 +8,6 @@ namespace Kernel::API
 	enum SharedPageFeature : uint32_t
 	{
 		SPF_GETTIME = 1 << 0,
-		SPF_RDTSCP  = 1 << 1,
 	};

 	struct SharedPage
@@ -19,8 +18,9 @@ namespace Kernel::API

 		struct
 		{
-			uint64_t realtime_s;
-			uint32_t realtime_ns;
+			uint8_t shift;
+			uint64_t mult;
+			uint64_t realtime_seconds;
 		} gettime_shared;

 		struct
@@ -28,8 +28,6 @@ namespace Kernel::API
 			struct
 			{
 				uint32_t seq;
-				uint32_t mult;
-				int8_t shift;
 				uint64_t last_ns;
 				uint64_t last_tsc;
 			} gettime_local;
@@ -2,7 +2,6 @@

 #include <BAN/Vector.h>
 #include <kernel/InterruptController.h>
-#include <kernel/InterruptNumbers.h>
 #include <kernel/Lock/SpinLock.h>
 #include <kernel/Memory/Types.h>

@@ -13,10 +12,10 @@ namespace Kernel
 	{
 	public:
 		virtual void eoi(uint8_t) override;
-		virtual void enable_irq(uint8_t, bool level_triggered) override;
+		virtual void enable_irq(uint8_t) override;
 		virtual bool is_in_service(uint8_t) override;

-		virtual BAN::ErrorOr<void> reserve_irq(uint8_t irq, bool shared) override;
+		virtual BAN::ErrorOr<void> reserve_irq(uint8_t irq) override;
 		virtual BAN::Optional<uint8_t> get_free_irq() override;

 		virtual void initialize_multiprocessor() override;
@@ -24,10 +23,9 @@ namespace Kernel
 		virtual void broadcast_ipi() override;
 		virtual void enable() override;

-		BAN::ErrorOr<uint8_t> reserve_gsi(uint32_t gsi, bool shared = false);
+		BAN::ErrorOr<uint8_t> reserve_gsi(uint32_t gsi);

 		void initialize_timer();
-		void set_timer_dealine(uint64_t ns);

 	private:
 		uint32_t read_from_local_apic(ptrdiff_t);
@@ -72,8 +70,7 @@ namespace Kernel
 		Kernel::vaddr_t        m_local_apic_vaddr = 0;
 		BAN::Vector<IOAPIC>    m_io_apics;
 		uint8_t                m_irq_overrides[0x100] {};
-		uint8_t                m_used_gsis[m_irq_count / 8] {};
-		uint8_t                m_excl_gsis[m_irq_count / 8] {};
+		uint8_t                m_reserved_gsis[m_irq_count / 8] {};
 		uint64_t               m_lapic_timer_frequency_hz { 0 };
 	};

@@ -38,7 +38,7 @@ namespace Kernel

 		BAN::ErrorOr<size_t> write_impl(off_t, BAN::ConstByteSpan) override;

-		BAN::ErrorOr<long> ioctl_impl(unsigned long request, void* arg) override;
+		BAN::ErrorOr<long> ioctl_impl(int cmd, void* arg) override;

 	protected:
 		ThreadBlocker m_sample_data_blocker;
@@ -67,7 +67,6 @@ namespace Kernel
 		BAN::Vector<BAN::Vector<const HDAudio::AFGWidget*>> m_output_paths;
 		BAN::Vector<const HDAudio::AFGWidget*> m_output_pins;
 		size_t m_output_path_index { SIZE_MAX };
-		size_t m_amplifier_idx { SIZE_MAX };

 		uint8_t m_stream_id    { 0xFF };
 		uint8_t m_stream_index { 0xFF };
@@ -1,6 +1,5 @@
 #pragma once

-#include <BAN/Optional.h>
 #include <BAN/Vector.h>

 namespace Kernel::HDAudio
@@ -65,7 +64,6 @@ namespace Kernel::HDAudio
 		};

 		BAN::Optional<Amplifier> output_amplifier;
-		BAN::Optional<Amplifier> input_amplifier;

 		BAN::Vector<uint16_t> connections;
 	};
@@ -21,17 +21,13 @@ struct BananBootloaderMemoryMapEntry
 	uint64_t address;
 	uint64_t length;
 	uint32_t type;
-	uint32_t unused;
-};
-static_assert(sizeof(BananBootloaderMemoryMapEntry) == 24);
+} __attribute__((packed));

 struct BananBootloaderMemoryMapInfo
 {
 	uint32_t entry_count;
-	uint32_t padding;
 	struct BananBootloaderMemoryMapEntry entries[];
-};
-static_assert(sizeof(BananBootloaderMemoryMapInfo) == 8);
+} __attribute__((packed));

 struct BananBootloaderInfo
 {
@@ -39,5 +35,4 @@ struct BananBootloaderInfo
 	uint32_t framebuffer_addr;
 	uint32_t memory_map_addr;
 	uint32_t kernel_paddr;
-};
-static_assert(sizeof(BananBootloaderInfo) == 16);
+} __attribute__((packed));
@@ -82,8 +82,5 @@ namespace CPUID
 	bool has_pat();
 	bool has_1gib_pages();
 	bool has_invariant_tsc();
-	bool has_rdtscp();
-	uint64_t get_tsc_frequency();
-	bool has_kvm_pvclock();

 }
@@ -6,22 +6,15 @@
 namespace Kernel
 {

-	class BGAController;
-
 	class FramebufferDevice : public CharacterDevice
 	{
 	public:
-		static BAN::ErrorOr<BAN::RefPtr<FramebufferDevice>> create(paddr_t paddr, uint32_t width, uint32_t height, uint32_t pitch, uint8_t bpp);
-		static BAN::ErrorOr<BAN::RefPtr<FramebufferDevice>> create(BAN::RefPtr<BGAController>);
 		static BAN::ErrorOr<BAN::RefPtr<FramebufferDevice>> create_from_boot_framebuffer();
 		static BAN::RefPtr<FramebufferDevice> boot_framebuffer();
 		~FramebufferDevice();

 		uint32_t width() const { return m_width; }
 		uint32_t height() const { return m_height; }
-		uint8_t bpp() const { return m_bpp; }
-
-		BAN::ErrorOr<void> set_bga_controller(BAN::RefPtr<BGAController>);

 		uint32_t get_pixel(uint32_t x, uint32_t y) const;
 		void set_pixel(uint32_t x, uint32_t y, uint32_t rgb);
@@ -43,7 +36,7 @@ namespace Kernel
 		virtual BAN::ErrorOr<size_t> read_impl(off_t, BAN::ByteSpan) override;
 		virtual BAN::ErrorOr<size_t> write_impl(off_t, BAN::ConstByteSpan) override;

-		BAN::ErrorOr<long> ioctl_impl(unsigned long request, void* arg) override;
+		BAN::ErrorOr<long> ioctl_impl(int cmd, void* arg) override;

 		virtual bool can_read_impl() const override { return true; }
 		virtual bool can_write_impl() const override { return true; }
@@ -57,16 +50,14 @@ namespace Kernel
 	private:
 		const BAN::String m_name;

-		vaddr_t m_video_memory_vaddr { 0 };
-		paddr_t m_video_memory_paddr { 0 };
-
-		uint32_t m_width  { 0 };
-		uint32_t m_height { 0 };
-		uint32_t m_pitch  { 0 };
-		uint8_t  m_bpp    { 0 };
+		vaddr_t			m_video_memory_vaddr { 0 };
+		const paddr_t	m_video_memory_paddr;
+		const uint32_t	m_width;
+		const uint32_t	m_height;
+		const uint32_t	m_pitch;
+		const uint8_t	m_bpp;

 		BAN::UniqPtr<VirtualRange> m_video_buffer;
-		BAN::RefPtr<BGAController> m_bga_controller;

 		friend class FramebufferMemoryRegion;
 	};
@@ -14,8 +14,8 @@ namespace Kernel::ELF
 			size_t size;
 		};

+		bool open_execfd;
 		vaddr_t entry_point;
-		BAN::Optional<vaddr_t> interp_base;
 		BAN::Optional<TLS> master_tls;
 		BAN::Vector<BAN::UniqPtr<MemoryRegion>> regions;
 	};
@@ -3,7 +3,6 @@
 #include <BAN/HashMap.h>
 #include <kernel/FS/Inode.h>
 #include <kernel/Lock/Mutex.h>
-#include <kernel/ThreadBlocker.h>

 #include <sys/epoll.h>

@@ -1,6 +1,7 @@
 #pragma once

 #include <BAN/Vector.h>
+#include <kernel/Device/Device.h>
 #include <kernel/FS/TmpFS/FileSystem.h>
 #include <kernel/Lock/Mutex.h>
 #include <kernel/ThreadBlocker.h>
@@ -8,8 +9,6 @@
 namespace Kernel
 {

-	class Device;
-
 	class DevFileSystem final : public TmpFileSystem
 	{
 	public:
@@ -2,7 +2,6 @@

 #include <kernel/FS/Inode.h>
 #include <kernel/Lock/Mutex.h>
-#include <kernel/ThreadBlocker.h>

 namespace Kernel
 {
@@ -23,16 +22,16 @@ namespace Kernel
 		BAN::ErrorOr<size_t> read_impl(off_t, BAN::ByteSpan) override;
 		BAN::ErrorOr<size_t> write_impl(off_t, BAN::ConstByteSpan) override;

-		bool can_read_impl() const override;
-		bool can_write_impl() const override;
+		bool can_read_impl() const override { return m_value > 0; }
+		bool can_write_impl() const override { return m_value < UINT64_MAX - 1; }
 		bool has_error_impl() const override { return false; }
 		bool has_hungup_impl() const override { return false; }

 	private:
 		const bool m_is_semaphore;
-		uint64_t m_value;
+		BAN::Atomic<uint64_t> m_value;

-		mutable Mutex m_mutex;
+		Mutex m_mutex;
 		ThreadBlocker m_thread_blocker;
 	};

@@ -2,9 +2,8 @@

 #include <BAN/HashMap.h>
 #include <kernel/Device/Device.h>
-#include <kernel/FS/Ext2/Inode.h>
 #include <kernel/FS/FileSystem.h>
-#include <kernel/Memory/VirtualRange.h>
+#include <kernel/FS/Ext2/Inode.h>

 namespace Kernel
 {
@@ -29,7 +28,7 @@ namespace Kernel
 			BAN_NON_COPYABLE(BlockBufferWrapper);

 		public:
-			BlockBufferWrapper(BAN::ByteSpan buffer, void (*callback)(void*, const uint8_t*), void* argument)
+			BlockBufferWrapper(BAN::Span<uint8_t> buffer, void (*callback)(void*, const uint8_t*), void* argument)
 				: m_buffer(buffer)
 				, m_callback(callback)
 				, m_argument(argument)
@@ -61,13 +60,13 @@ namespace Kernel
 			const uint8_t* data() const { return m_buffer.data(); }

 			BAN::ByteSpan span() { return m_buffer; }
-			BAN::ConstByteSpan span() const { return m_buffer; }
+			BAN::ConstByteSpan span() const { return m_buffer.as_const(); }

 			uint8_t& operator[](size_t index) { return m_buffer[index]; }
 			uint8_t operator[](size_t index) const { return m_buffer[index]; }

 		private:
-			BAN::ByteSpan m_buffer;
+			BAN::Span<uint8_t> m_buffer;
 			void (*m_callback)(void*, const uint8_t*);
 			void* m_argument;
 		};
@@ -100,8 +99,7 @@ namespace Kernel
 		BAN::ErrorOr<uint32_t> reserve_free_block(uint32_t primary_bgd);
 		BAN::ErrorOr<void> release_block(uint32_t block);

-		BAN::ErrorOr<BAN::RefPtr<Ext2Inode>> open_inode(ino_t);
-		void remove_from_cache(ino_t);
+		BAN::HashMap<ino_t, BAN::RefPtr<Ext2Inode>>& inode_cache() { return m_inode_cache; }

 		const Ext2::Superblock& superblock() const { return m_superblock; }

@@ -129,7 +127,7 @@ namespace Kernel
 		private:
 			struct BlockBuffer
 			{
-				BAN::ByteSpan buffer;
+				BAN::Vector<uint8_t> buffer;
 				bool used { false };
 			};

@@ -145,7 +143,6 @@ namespace Kernel

 			Mutex m_buffer_mutex;
 			ThreadBlocker m_buffer_blocker;
-			BAN::UniqPtr<VirtualRange> m_buffer_data;
 			BAN::Array<BlockBuffer, max_threads * max_buffers_per_thread> m_buffers;
 			BAN::Array<ThreadInfo, max_threads> m_thread_infos;
 		};
@@ -158,7 +155,6 @@ namespace Kernel
 		BAN::RefPtr<Inode> m_root_inode;
 		BAN::Vector<uint32_t> m_superblock_backups;

-		Mutex m_inode_cache_lock;
 		BAN::HashMap<ino_t, BAN::RefPtr<Ext2Inode>> m_inode_cache;

 		BlockBufferManager m_buffer_manager;
@@ -55,7 +55,7 @@ namespace Kernel
 		BAN::ErrorOr<BAN::RefPtr<Inode>> find_inode_no_lock(BAN::StringView);

 		/* needs write end of the lock when allocate is true*/
-		BAN::ErrorOr<BAN::Optional<uint32_t>> block_from_indirect_block_no_lock(uint32_t block, uint32_t index, uint32_t depth, bool allocate);
+		BAN::ErrorOr<BAN::Optional<uint32_t>> block_from_indirect_block_no_lock(uint32_t& block, uint32_t index, uint32_t depth, bool allocate);
 		BAN::ErrorOr<BAN::Optional<uint32_t>> fs_block_of_data_block_index_no_lock(uint32_t data_block_index, bool allocate);

 		/* needs write end of the lock */
@@ -71,13 +71,7 @@ namespace Kernel
 	private:
 		Ext2Inode(Ext2FS& fs, Ext2::Inode inode, uint32_t ino);

-		BAN::Optional<uint32_t> block_cache_find(uint32_t block, uint32_t index) const;
-		void block_cache_remove(uint32_t block, uint32_t index);
-		void block_cache_add(uint32_t block, uint32_t index, uint32_t target);
-
-		BAN::RefPtr<Inode> dir_cache_find(BAN::StringView) const;
-		void dir_cache_remove(BAN::StringView);
-		void dir_cache_add(BAN::StringView, BAN::RefPtr<Inode>);
+		static BAN::ErrorOr<BAN::RefPtr<Ext2Inode>> create(Ext2FS&, uint32_t);

 	private:
 		struct ScopedSync
@@ -113,27 +107,6 @@ namespace Kernel
 		const uint32_t m_og_faddr;
 		const Ext2::Osd2 m_og_osd2;

-		struct BlockCacheEntry
-		{
-			mutable uint32_t freq;
-			uint32_t block;
-			uint32_t index;
-			uint32_t target;
-		};
-		mutable SpinLock m_block_cache_lock;
-		BAN::Array<BlockCacheEntry, 8> m_block_cache;
-
-		struct DirCacheEntry
-		{
-			mutable size_t freq { 0 };
-			BAN::RefPtr<Inode> inode;
-			size_t name_len { 0 };
-			char   name[256];
-		};
-		static constexpr size_t dir_cache_size = 32;
-		mutable RWLock m_dir_cache_lock;
-		BAN::Vector<DirCacheEntry> m_dir_cache;
-
 		friend class Ext2FS;
 		friend class BAN::RefPtr<Ext2Inode>;
 	};
@@ -5,7 +5,6 @@
 #include <kernel/FS/FAT/Definitions.h>
 #include <kernel/FS/FAT/Inode.h>
 #include <kernel/FS/FileSystem.h>
-#include <kernel/Lock/Mutex.h>

 namespace Kernel
 {
@@ -1,12 +1,11 @@
 #pragma once

+#include <kernel/Device/Device.h>
 #include <kernel/FS/Inode.h>

 namespace Kernel
 {

-	class BlockDevice;
-
 	class FileSystem : public BAN::RefCounted<FileSystem>
 	{
 	public:
@@ -83,7 +83,6 @@ namespace Kernel
 	public:
 		virtual ~Inode() {}

-		static bool can_access(uid_t uid, gid_t gid, mode_t mode, const Credentials& credentials, int);
 		bool can_access(const Credentials&, int) const;

 		bool operator==(const Inode& other) const { return dev() == other.dev() && ino() == other.ino(); }
@@ -151,7 +150,7 @@ namespace Kernel
 		bool has_error() const  { return has_error_impl(); }
 		bool has_hungup() const { return has_hungup_impl(); }

-		BAN::ErrorOr<long> ioctl(unsigned long request, void* arg);
+		BAN::ErrorOr<long> ioctl(int request, void* arg);

 		BAN::ErrorOr<void> add_epoll(class Epoll*);
 		void del_epoll(class Epoll*);
@@ -200,7 +199,7 @@ namespace Kernel
 		virtual bool has_error_impl() const = 0;
 		virtual bool has_hungup_impl() const = 0;

-		virtual BAN::ErrorOr<long> ioctl_impl(unsigned long, void*) { return BAN::Error::from_errno(ENOTSUP); }
+		virtual BAN::ErrorOr<long> ioctl_impl(int, void*) { return BAN::Error::from_errno(ENOTSUP); }

 	protected:
 		// TODO: this is supposed to be const I guess?
@@ -2,20 +2,17 @@

 #include <kernel/FS/TmpFS/FileSystem.h>
 #include <kernel/FS/TmpFS/Inode.h>
+#include <kernel/Process.h>

 namespace Kernel
 {

-	class Process;
-
 	class ProcFileSystem final : public TmpFileSystem
 	{
 	public:
 		static void initialize();
 		static ProcFileSystem& get();

-		void post_scheduler_initialize();
-
 		BAN::ErrorOr<void> on_process_create(Process&);
 		void on_process_delete(Process&);

@@ -2,12 +2,11 @@

 #include <kernel/FS/TmpFS/FileSystem.h>
 #include <kernel/FS/TmpFS/Inode.h>
+#include <kernel/Process.h>

 namespace Kernel
 {

-	class Process;
-
 	class ProcPidInode final : public TmpDirectoryInode
 	{
 		// FIXME: dynamically update ruid/rgid.
@@ -77,7 +76,7 @@ namespace Kernel
 	class ProcROInode final : public TmpInode
 	{
 	public:
-		static BAN::ErrorOr<BAN::RefPtr<ProcROInode>> create_new(BAN::ErrorOr<size_t> (*callback)(off_t, BAN::ByteSpan, void*), TmpFileSystem&, void*, mode_t, uid_t, gid_t);
+		static BAN::ErrorOr<BAN::RefPtr<ProcROInode>> create_new(size_t (*callback)(off_t, BAN::ByteSpan), TmpFileSystem&, mode_t, uid_t, gid_t);
 		~ProcROInode() = default;

 	protected:
@@ -93,11 +92,10 @@ namespace Kernel
 		virtual bool has_hungup_impl() const override { return false; }

 	private:
-		ProcROInode(BAN::ErrorOr<size_t> (*callback)(off_t, BAN::ByteSpan, void*), TmpFileSystem&, void*, const TmpInodeInfo&);
+		ProcROInode(size_t (*callback)(off_t, BAN::ByteSpan), TmpFileSystem&, const TmpInodeInfo&);

 	private:
-		BAN::ErrorOr<size_t> (*m_callback)(off_t, BAN::ByteSpan, void*);
-		void* m_argument;
+		size_t (*m_callback)(off_t, BAN::ByteSpan);
 	};

 	class ProcSymlinkInode final : public TmpInode
@@ -92,9 +92,8 @@ namespace Kernel
 		MountPoint* mount_from_root_inode(BAN::RefPtr<Inode>);

 	private:
+		Mutex					m_mutex;
 		BAN::RefPtr<FileSystem>	m_root_fs;
-
-		Mutex					m_mount_point_lock;
 		BAN::Vector<MountPoint>	m_mount_points;

 		friend class BAN::RefPtr<VirtualFileSystem>;
@@ -1,37 +0,0 @@
-#pragma once
-
-#include <BAN/RefPtr.h>
-#include <kernel/Lock/SpinLock.h>
-#include <kernel/PCI.h>
-
-#include <sys/framebuffer.h>
-
-namespace Kernel
-{
-
-	class BGAController : public BAN::RefCounted<BGAController>
-	{
-	public:
-		static BAN::ErrorOr<BAN::RefPtr<BGAController>> create(PCI::Device&);
-
-		fb_fix_info get_fb_fix_info() const;
-		fb_var_info get_fb_var_info() const;
-		BAN::ErrorOr<void> set_fb_var_info(const fb_var_info&);
-
-	private:
-		BGAController(PCI::Device&);
-		BAN::ErrorOr<void> initialize();
-
-		void write_reg(uint16_t reg, uint16_t value);
-		uint16_t read_reg(uint16_t reg);
-
-	private:
-		mutable RecursiveSpinLock m_lock;
-		PCI::Device& m_pci_device;
-		BAN::UniqPtr<PCI::BarRegion> m_lfb_bar;
-
-		fb_fix_info m_fix_info {};
-		fb_var_info m_var_info {};
-	};
-
-}
@@ -10,6 +10,21 @@
 namespace Kernel
 {

+	// IDT entries
+	//   0x00->0x1F (32):  ISR
+	//   0x20->0x7F (96):  PIC/IOAPIC
+	//   0x80->0xEF (112): MSI
+	//   0xF0->0xFE (15):  internal
+
+	constexpr uint8_t IRQ_VECTOR_BASE   = 0x20;
+	constexpr uint8_t IRQ_MSI_BASE      = 0x80;
+	constexpr uint8_t IRQ_MSI_END       = 0xF0;
+#if ARCH(i686)
+	constexpr uint8_t IRQ_SYSCALL       = 0xF0; // hard coded in kernel/API/Syscall.h
+#endif
+	constexpr uint8_t IRQ_IPI           = 0xF1;
+	constexpr uint8_t IRQ_TIMER         = 0xF2;
+
 #if ARCH(x86_64)
 	struct GateDescriptor
 	{
@@ -36,7 +36,6 @@ namespace Kernel::Input
 		uint8_t m_byte_index { 0 };
 		bool m_basic { false };

-		bool m_scancode_set_uncertain { false };
 		uint8_t m_scancode_set { 0xFF };
 		uint16_t m_modifiers { 0 };

@@ -14,7 +14,7 @@ namespace Kernel
 		virtual ~InterruptController() {}

 		virtual void eoi(uint8_t) = 0;
-		virtual void enable_irq(uint8_t, bool level_triggered = false) = 0;
+		virtual void enable_irq(uint8_t) = 0;
 		virtual bool is_in_service(uint8_t) = 0;

 		static void initialize(bool force_pic);
@@ -26,7 +26,7 @@ namespace Kernel
 		virtual void broadcast_ipi() = 0;
 		virtual void enable() = 0;

-		virtual BAN::ErrorOr<void> reserve_irq(uint8_t irq, bool shared = false) = 0;
+		virtual BAN::ErrorOr<void> reserve_irq(uint8_t irq) = 0;
 		virtual BAN::Optional<uint8_t> get_free_irq() = 0;

 		bool is_using_apic() const { return m_using_apic; }
@@ -1,23 +0,0 @@
-#pragma once
-
-#include <kernel/Arch.h>
-
-namespace Kernel
-{
-
-	// IDT entries
-	//   0x00->0x1F (32):  ISR
-	//   0x20->0x7F (96):  PIC/IOAPIC
-	//   0x80->0xEF (112): MSI
-	//   0xF0->0xFE (15):  internal
-
-	constexpr uint8_t IRQ_VECTOR_BASE   = 0x20;
-	constexpr uint8_t IRQ_MSI_BASE      = 0x80;
-	constexpr uint8_t IRQ_MSI_END       = 0xF0;
-#if ARCH(i686)
-	constexpr uint8_t IRQ_SYSCALL       = 0xF0; // hard coded in kernel/API/Syscall.h
-#endif
-	constexpr uint8_t IRQ_IPI           = 0xF1;
-	constexpr uint8_t IRQ_TIMER         = 0xF2;
-
-}
@@ -1,41 +0,0 @@
-#pragma once
-
-#include <kernel/Lock/SpinLock.h>
-#include <kernel/Lock/Mutex.h>
-
-namespace Kernel
-{
-
-	// FIXME: These classes are HACKS to allow passing spinlock
-	//        to unblock functions. Write a better API that either
-	//        allows passing spinlocks or do something cleaner that
-	//        whatever shit this is
-
-	template<typename Lock> requires requires (Lock& lock) { lock.lock(); lock.unlock(InterruptState::Disabled); lock.current_processor_has_lock(); }
-	class BlockableSpinLock : public BaseMutex
-	{
-	public:
-		BlockableSpinLock(Lock& lock)
-			: m_lock(lock)
-		{
-			ASSERT(m_lock.current_processor_has_lock());
-		}
-
-		void lock() override
-		{
-			m_lock.lock();
-		}
-
-		void unlock() override
-		{
-			m_lock.unlock(InterruptState::Disabled);
-		}
-
-		uint32_t lock_depth() const override { return m_lock.lock_depth(); }
-		bool is_locked_by_current_thread() const override { return m_lock.current_processor_has_lock(); }
-
-	private:
-		Lock& m_lock;
-	};
-
-}
@@ -2,6 +2,7 @@

 #include <BAN/Atomic.h>
 #include <BAN/NoCopyMove.h>
+#include <kernel/Thread.h>

 #include <sys/types.h>

@@ -12,10 +13,12 @@ namespace Kernel
 	{
 	public:
 		virtual void lock() = 0;
+		virtual bool try_lock() = 0;
 		virtual void unlock() = 0;

+		virtual pid_t locker() const = 0;
+		virtual bool is_locked() const = 0;
 		virtual uint32_t lock_depth() const = 0;
-		virtual bool is_locked_by_current_thread() const = 0;
 	};

 	class Mutex final : public BaseMutex
@@ -26,14 +29,63 @@ namespace Kernel
 	public:
 		Mutex() = default;

-		bool try_lock();
-		void lock() override;
-		void unlock() override;
+		void lock() override
+		{
+			const auto tid = Thread::current_tid();
+			if (tid == m_locker)
+				ASSERT(m_lock_depth > 0);
+			else
+			{
+				ASSERT(!tid || !Thread::current().has_spinlock());
+				pid_t expected = -1;
+				while (!m_locker.compare_exchange(expected, tid))
+				{
+					ASSERT(Processor::get_interrupt_state() == InterruptState::Enabled);
+					Processor::yield();
+					expected = -1;
+				}
+				ASSERT(m_lock_depth == 0);
+				if (tid)
+					Thread::current().add_mutex();
+			}
+			m_lock_depth++;
+		}

-		pid_t locker() const { return m_locker; }
-		bool is_locked() const { return m_locker != -1; }
+		bool try_lock() override
+		{
+			const auto tid = Thread::current_tid();
+			if (tid == m_locker)
+				ASSERT(m_lock_depth > 0);
+			else
+			{
+				pid_t expected = -1;
+				if (!m_locker.compare_exchange(expected, tid))
+					return false;
+				ASSERT(m_lock_depth == 0);
+				if (tid)
+					Thread::current().add_mutex();
+			}
+			m_lock_depth++;
+			return true;
+		}
+
+		void unlock() override
+		{
+			const auto tid = Thread::current_tid();
+			ASSERT(m_locker == tid);
+			ASSERT(m_lock_depth > 0);
+			if (--m_lock_depth == 0)
+			{
+				m_locker = -1;
+				if (tid)
+					Thread::current().remove_mutex();
+			}
+		}
+
+		pid_t locker() const override { return m_locker; }
+		bool is_locked() const override { return m_locker != -1; }
 		uint32_t lock_depth() const override { return m_lock_depth; }
-		bool is_locked_by_current_thread() const override;
+		bool is_locked_by_current_thread() const { return m_locker == Thread::current_tid(); }

 	private:
 		BAN::Atomic<pid_t>	m_locker		{ -1 };
@@ -48,14 +100,74 @@ namespace Kernel
 	public:
 		PriorityMutex() = default;

-		bool try_lock();
-		void lock() override;
-		void unlock() override;
+		void lock() override
+		{
+			const auto tid = Thread::current_tid();

-		pid_t locker() const { return m_locker; }
-		bool is_locked() const { return m_locker != -1; }
+			if (tid == m_locker)
+				ASSERT(m_lock_depth > 0);
+			else
+			{
+				ASSERT(!tid || !Thread::current().has_spinlock());
+				bool has_priority = tid ? !Thread::current().is_userspace() : true;
+				if (has_priority)
+					m_queue_length++;
+				pid_t expected = -1;
+				while (!(has_priority || m_queue_length == 0) || !m_locker.compare_exchange(expected, tid))
+				{
+					ASSERT(Processor::get_interrupt_state() == InterruptState::Enabled);
+					Processor::yield();
+					expected = -1;
+				}
+				ASSERT(m_lock_depth == 0);
+				if (tid)
+					Thread::current().add_mutex();
+			}
+			m_lock_depth++;
+		}
+
+		bool try_lock() override
+		{
+			const auto tid = Thread::current_tid();
+
+			if (tid == m_locker)
+				ASSERT(m_lock_depth > 0);
+			else
+			{
+				bool has_priority = tid ? !Thread::current().is_userspace() : true;
+				pid_t expected = -1;
+				if (!(has_priority || m_queue_length == 0) || !m_locker.compare_exchange(expected, tid))
+					return false;
+				if (has_priority)
+					m_queue_length++;
+				ASSERT(m_lock_depth == 0);
+				if (tid)
+					Thread::current().add_mutex();
+			}
+			m_lock_depth++;
+			return true;
+		}
+
+		void unlock() override
+		{
+			const auto tid = Thread::current_tid();
+			ASSERT(m_locker == tid);
+			ASSERT(m_lock_depth > 0);
+			if (--m_lock_depth == 0)
+			{
+				bool has_priority = tid ? !Thread::current().is_userspace() : true;
+				if (has_priority)
+					m_queue_length--;
+				m_locker = -1;
+				if (tid)
+					Thread::current().remove_mutex();
+			}
+		}
+
+		pid_t locker() const override { return m_locker; }
+		bool is_locked() const override { return m_locker != -1; }
 		uint32_t lock_depth() const override { return m_lock_depth; }
-		bool is_locked_by_current_thread() const override;
+		bool is_locked_by_current_thread() const { return m_locker == Thread::current_tid(); }

 	private:
 		BAN::Atomic<pid_t>		m_locker		{ -1 };
@@ -1,7 +1,7 @@
 #pragma once

-#include <kernel/Lock/SpinLock.h>
-#include <kernel/ThreadBlocker.h>
+#include <kernel/Lock/Mutex.h>
+#include <kernel/Lock/LockGuard.h>

 namespace Kernel
 {
@@ -13,13 +13,51 @@ namespace Kernel
 	public:
 		RWLock() = default;

-		void rd_lock();
-		void rd_unlock();
-		void wr_lock();
-		void wr_unlock();
+		void rd_lock()
+		{
+			LockGuard _(m_mutex);
+			while (m_writers_waiting > 0 || m_writer != -1)
+				m_thread_blocker.block_indefinite(&m_mutex);
+			m_readers_active++;
+		}
+
+		void rd_unlock()
+		{
+			LockGuard _(m_mutex);
+			if (--m_readers_active == 0)
+				m_thread_blocker.unblock();
+		}
+
+		void wr_lock()
+		{
+			if (m_writer == Thread::current_tid())
+			{
+				m_writer_depth++;
+				return;
+			}
+
+			LockGuard _(m_mutex);
+
+			m_writers_waiting++;
+			while (m_readers_active > 0 || m_writer != -1)
+				m_thread_blocker.block_indefinite(&m_mutex);
+			m_writers_waiting--;
+
+			m_writer = Thread::current_tid();
+			m_writer_depth = 1;
+		}
+
+		void wr_unlock()
+		{
+			if (--m_writer_depth != 0)
+				return;
+			LockGuard _(m_mutex);
+			m_writer = -1;
+			m_thread_blocker.unblock();
+		}

 	private:
-		SpinLock m_lock;
+		Mutex m_mutex;
 		ThreadBlocker m_thread_blocker;
 		uint32_t m_readers_active  { 0 };
 		uint32_t m_writers_waiting { 0 };
@@ -61,6 +61,9 @@ namespace Kernel
 		uint32_t                             m_lock_depth { 0 };
 	};

+	template<typename Lock>
+	class SpinLockGuardAsMutex;
+
 	template<typename Lock>
 	class SpinLockGuard
 	{
@@ -82,6 +85,7 @@ namespace Kernel
 	private:
 		Lock& m_lock;
 		InterruptState m_state;
+		friend class SpinLockGuardAsMutex<Lock>;
 	};

 }
@@ -0,0 +1,64 @@
+#pragma once
+
+#include <kernel/Lock/SpinLock.h>
+#include <kernel/Lock/Mutex.h>
+
+namespace Kernel
+{
+
+	// FIXME: These classes are HACKS to allow passing spinlock
+	//        to unblock functions. Write a better API that either
+	//        allows passing spinlocks or do something cleaner that
+	//        whatever shit this is
+
+	template<typename Lock>
+	class SpinLockAsMutex : public BaseMutex
+	{
+	public:
+		SpinLockAsMutex(Lock& lock, InterruptState state)
+			: m_lock(lock)
+			, m_lock_depth(lock.lock_depth())
+			, m_state(state)
+			, m_locker(Thread::current_tid())
+		{
+			ASSERT(m_lock.current_processor_has_lock());
+		}
+
+		void lock() override
+		{
+			m_lock.lock();
+			m_lock_depth++;
+		}
+
+		bool try_lock() override
+		{
+			lock();
+			return true;
+		}
+
+		void unlock() override
+		{
+			m_lock.unlock(--m_lock_depth ? InterruptState::Disabled : m_state);
+		}
+
+		pid_t locker() const override { return is_locked() ? m_locker : -1; }
+		bool is_locked() const override { return m_lock_depth; }
+		uint32_t lock_depth() const override { return m_lock_depth; }
+
+	private:
+		Lock& m_lock;
+		uint32_t m_lock_depth { 0 };
+		InterruptState m_state;
+		const pid_t m_locker;
+	};
+
+	template<typename Lock>
+	class SpinLockGuardAsMutex : public SpinLockAsMutex<Lock>
+	{
+	public:
+		SpinLockGuardAsMutex(SpinLockGuard<Lock>& guard)
+			: SpinLockAsMutex<Lock>(guard.m_lock, guard.m_state)
+		{}
+	};
+
+}
@@ -1,6 +1,5 @@
 #pragma once

-#include <BAN/Vector.h>
 #include <kernel/Memory/MemoryRegion.h>

 namespace Kernel
@@ -1,27 +1,30 @@
 #pragma once

 #include <BAN/HashMap.h>
-#include <BAN/RefPtr.h>
 #include <BAN/UniqPtr.h>
-#include <BAN/Vector.h>
 #include <kernel/Lock/Mutex.h>
 #include <kernel/Lock/SpinLock.h>
 #include <kernel/Memory/MemoryRegion.h>

-#include <sys/shm.h>
+#include <fcntl.h>

 namespace Kernel
 {

+	class SharedMemoryObject;
+
 	class SharedMemoryObjectManager
 	{
+	public:
+		using Key = size_t;
+
 	public:
 		static BAN::ErrorOr<void> initialize();
 		static SharedMemoryObjectManager& get();

-		BAN::ErrorOr<int> shmget(key_t key, size_t size, int shmflg);
-		BAN::ErrorOr<void> shmctl(int shmid, int cmd, struct shmid_ds* user_buf);
-		BAN::ErrorOr<BAN::UniqPtr<MemoryRegion>> shmat(int shmid, const void* shmaddr, int shmflg);
+		BAN::ErrorOr<Key> create_object(size_t size, PageTable::flags_t);
+		BAN::ErrorOr<void> delete_object(Key);
+		BAN::ErrorOr<BAN::UniqPtr<SharedMemoryObject>> map_object(Key, PageTable&, AddressRange);

 	private:
 		SharedMemoryObjectManager() {}
@@ -29,31 +32,49 @@ namespace Kernel
 	private:
 		struct Object : public BAN::RefCounted<Object>
 		{
-			Object(key_t key, int id, shmid_ds info)
-				: key(key)
-				, id(id)
-				, info(info)
-			{ }
 			~Object();

-			bool can_current_process_access(int flags) const;
-
-			const key_t key;
-			const int id;
-			shmid_ds info;
-
-			Mutex mutex;
+			Key key;
+			size_t size;
+			PageTable::flags_t flags;
 			BAN::Vector<paddr_t> paddrs;
-			bool marked_for_deletion { false };
+			SpinLock spin_lock;
 		};

 	private:
 		Mutex m_mutex;
-		BAN::HashMap<key_t, int> m_ids;
-		BAN::HashMap<int, BAN::RefPtr<Object>> m_objects;
+		BAN::HashMap<Key, BAN::RefPtr<Object>> m_objects;

 		friend class SharedMemoryObject;
 		friend class BAN::UniqPtr<SharedMemoryObjectManager>;
 	};

+	class SharedMemoryObject : public MemoryRegion
+	{
+		BAN_NON_COPYABLE(SharedMemoryObject);
+		BAN_NON_MOVABLE(SharedMemoryObject);
+
+	public:
+		static BAN::ErrorOr<BAN::UniqPtr<SharedMemoryObject>> create(BAN::RefPtr<SharedMemoryObjectManager::Object>, PageTable&, AddressRange);
+
+		BAN::ErrorOr<BAN::UniqPtr<MemoryRegion>> clone(PageTable& new_page_table) override;
+		BAN::ErrorOr<BAN::UniqPtr<MemoryRegion>> split(size_t offset) override;
+
+		BAN::ErrorOr<void> msync(vaddr_t, size_t, int) override { return {}; }
+
+	protected:
+		BAN::ErrorOr<bool> allocate_page_containing_impl(vaddr_t vaddr, bool wants_write) override;
+
+	private:
+		SharedMemoryObject(BAN::RefPtr<SharedMemoryObjectManager::Object> object, PageTable& page_table)
+			: MemoryRegion(page_table, object->size, MemoryRegion::Type::SHARED, object->flags, O_EXEC | O_RDWR)
+			, m_object(object)
+		{ }
+
+	private:
+		BAN::RefPtr<SharedMemoryObjectManager::Object> m_object;
+
+		friend class BAN::UniqPtr<SharedMemoryObject>;
+	};
+
 }
@@ -4,6 +4,8 @@
 #include <BAN/HashMap.h>
 #include <BAN/UniqPtr.h>
 #include <kernel/Networking/NetworkInterface.h>
+#include <kernel/Thread.h>
+#include <kernel/ThreadBlocker.h>

 namespace Kernel
 {
@@ -29,7 +29,6 @@ namespace Kernel
 		REG_TDLEN	= 0x3808,
 		REG_TDH		= 0x3810,
 		REG_TDT		= 0x3818,
-		REG_RXCSUM	= 0x5000,
 		REG_MTA		= 0x5200,
 	};

@@ -168,15 +167,6 @@ namespace Kernel
 		RCTL_BSIZE_16384	= (0b01 << 16) | RCTL_BSEX,
 	};

-	enum E1000_RXCSUM : uint32_t
-	{
-		RXSUM_IPOFLD  = 1 << 8,
-		RXSUM_TUOFLD  = 1 << 9,
-		RXSUM_CRCOFLD = 1 << 11,
-		RXSUM_IPPCE   = 1 << 12,
-		RXSUM_PCSD    = 1 << 13,
-	};
-
 	enum E1000_CMD : uint8_t
 	{
 		CMD_EOP		= 1 << 0,
@@ -188,26 +178,6 @@ namespace Kernel
 		CMD_IDE		= 1 << 7,
 	};

-	enum E1000_RX_STS : uint8_t
-	{
-		RX_STS_IPCS  = 1 << 6,
-		RX_STS_TCPCS = 1 << 5,
-		RX_STS_UDPCS = 1 << 5,
-		RX_STS_EOP   = 1 << 1,
-		RX_STS_DD    = 1 << 0,
-	};
-
-	enum E1000_RX_ERR : uint8_t
-	{
-		RX_ERR_RXE  = 1 << 7,
-		RX_ERR_IPE  = 1 << 6,
-		RX_ERR_TCPE = 1 << 5,
-		RX_ERR_CXE  = 1 << 4,
-		RX_ERR_SEQ  = 1 << 2,
-		RX_ERR_SE   = 1 << 1,
-		RX_ERR_CE   = 1 << 0,
-	};
-
 	struct e1000_rx_desc
 	{
 		uint64_t addr;
@@ -45,7 +45,7 @@ namespace Kernel
 		uint32_t read32(uint16_t reg);
 		void write32(uint16_t reg, uint32_t value);

-		BAN::ErrorOr<void> send_raw_bytes(BAN::Span<const BAN::ConstByteSpan> buffers) override;
+		BAN::ErrorOr<void> send_bytes(BAN::MACAddress destination, EtherType protocol, BAN::Span<const BAN::ConstByteSpan> payload) override;

 		bool can_read_impl() const override { return false; }
 		bool can_write_impl() const override { return false; }
@@ -74,8 +74,8 @@ namespace Kernel
 		BAN::UniqPtr<DMARegion>	m_rx_descriptor_region;
 		BAN::UniqPtr<DMARegion>	m_tx_descriptor_region;

-		BAN::Atomic<uint32_t> m_tx_head   { 0 };
-		BAN::Atomic<uint32_t> m_tx_commit { 0 };
+		BAN::Atomic<uint32_t> m_tx_head1 { 0 };
+		BAN::Atomic<uint32_t> m_tx_head2 { 0 };

 		SpinLock m_rx_lock;
 		ThreadBlocker m_rx_blocker;
@@ -11,6 +11,7 @@
 #include <kernel/Networking/NetworkInterface.h>
 #include <kernel/Networking/NetworkLayer.h>
 #include <kernel/Networking/NetworkSocket.h>
+#include <kernel/Thread.h>

 namespace Kernel
 {
@@ -40,14 +41,14 @@ namespace Kernel

 		ARPTable& arp_table() { return *m_arp_table; }

-		BAN::ErrorOr<void> handle_ipv4_packet(NetworkInterface&, BAN::ConstByteSpan, uint32_t validated_cksums);
+		BAN::ErrorOr<void> handle_ipv4_packet(NetworkInterface&, BAN::ConstByteSpan);

 		virtual void unbind_socket(uint16_t port) override;
 		virtual BAN::ErrorOr<void> bind_socket_with_target(BAN::RefPtr<NetworkSocket>, const sockaddr* target_address, socklen_t target_address_len) override;
 		virtual BAN::ErrorOr<void> bind_socket_to_address(BAN::RefPtr<NetworkSocket>, const sockaddr* address, socklen_t address_len) override;
 		virtual BAN::ErrorOr<void> get_socket_address(BAN::RefPtr<NetworkSocket>, sockaddr* address, socklen_t* address_len) override;

-		virtual BAN::ErrorOr<void> sendto(NetworkSocket&, BAN::ConstByteSpan, const sockaddr*, socklen_t) override;
+		virtual BAN::ErrorOr<size_t> sendto(NetworkSocket&, BAN::ConstByteSpan, const sockaddr*, socklen_t) override;

 		virtual Socket::Domain domain() const override { return Socket::Domain::INET ;}
 		virtual size_t header_size() const override { return sizeof(IPv4Header); }
@@ -1,7 +1,6 @@
 #pragma once

 #include <kernel/Networking/NetworkInterface.h>
-#include <kernel/Memory/VirtualRange.h>

 namespace Kernel
 {
@@ -28,7 +27,7 @@ namespace Kernel
 		{}
 		~LoopbackInterface();

-		BAN::ErrorOr<void> send_raw_bytes(BAN::Span<const BAN::ConstByteSpan> buffers) override;
+		BAN::ErrorOr<void> send_bytes(BAN::MACAddress destination, EtherType protocol, BAN::Span<const BAN::ConstByteSpan> payload) override;

 		bool can_read_impl() const override { return false; }
 		bool can_write_impl() const override { return false; }
@@ -47,7 +46,7 @@ namespace Kernel
 		};

 	private:
-		SpinLock m_buffer_lock;
+		Mutex m_buffer_lock;
 		BAN::UniqPtr<VirtualRange> m_buffer;

 		uint32_t m_buffer_tail { 0 };
@@ -23,13 +23,6 @@ namespace Kernel
 		ARP = 0x0806,
 	};

-	enum NetworkChecksum : uint32_t
-	{
-		CKSUM_IPV4 = 1 << 0,
-		CKSUM_TCP  = 1 << 1,
-		CKSUM_UDP  = 1 << 2,
-	};
-
 	class NetworkInterface : public CharacterDevice
 	{
 		BAN_NON_COPYABLE(NetworkInterface);
@@ -66,33 +59,11 @@ namespace Kernel

 		virtual BAN::StringView name() const override { return m_name; }

-		BAN::ErrorOr<void> send_with_ethernet_header(BAN::MACAddress dst_mac, EtherType ether_type, BAN::ConstByteSpan buffer)
+		BAN::ErrorOr<void> send_bytes(BAN::MACAddress destination, EtherType protocol, BAN::ConstByteSpan payload)
 		{
-			BAN::ConstByteSpan buffer_array[1] { buffer };
-			return send_with_ethernet_header(dst_mac, ether_type, buffer_array);
+			return send_bytes(destination, protocol, { &payload, 1 });
 		}
-
-		template<size_t SIZE>
-		BAN::ErrorOr<void> send_with_ethernet_header(BAN::MACAddress dst_mac, EtherType ether_type, const BAN::ConstByteSpan (&buffer_array)[SIZE])
-		{
-			const auto ethernet_header = EthernetHeader {
-				.dst_mac = dst_mac,
-				.src_mac = get_mac_address(),
-				.ether_type = ether_type,
-			};
-
-			BAN::ConstByteSpan new_buffer_array[SIZE + 1];
-			new_buffer_array[0] = BAN::ConstByteSpan::from(ethernet_header);
-			for (size_t i = 0; i < SIZE; i++)
-				new_buffer_array[i + 1] = buffer_array[i];
-
-			return send_raw_bytes({ new_buffer_array, SIZE + 1 });
-		}
-
-		virtual BAN::ErrorOr<void> send_raw_bytes(BAN::Span<const BAN::ConstByteSpan> buffers) = 0;
-
-	private:
-		BAN::ErrorOr<long> ioctl_impl(unsigned long, void*) override;
+		virtual BAN::ErrorOr<void> send_bytes(BAN::MACAddress destination, EtherType protocol, BAN::Span<const BAN::ConstByteSpan> payload) = 0;

 	private:
 		const Type m_type;
@@ -27,7 +27,7 @@ namespace Kernel
 		virtual BAN::ErrorOr<void> bind_socket_to_address(BAN::RefPtr<NetworkSocket>, const sockaddr* address, socklen_t address_len) = 0;
 		virtual BAN::ErrorOr<void> get_socket_address(BAN::RefPtr<NetworkSocket>, sockaddr* address, socklen_t* address_len) = 0;

-		virtual BAN::ErrorOr<void> sendto(NetworkSocket&, BAN::ConstByteSpan, const sockaddr*, socklen_t) = 0;
+		virtual BAN::ErrorOr<size_t> sendto(NetworkSocket&, BAN::ConstByteSpan, const sockaddr*, socklen_t) = 0;

 		virtual Socket::Domain domain() const = 0;
 		virtual size_t header_size() const = 0;
@@ -27,7 +27,7 @@ namespace Kernel
 		BAN::ErrorOr<BAN::RefPtr<Socket>> create_socket(Socket::Domain, Socket::Type, mode_t, uid_t, gid_t);
 		BAN::ErrorOr<void> connect_sockets(Socket::Domain, BAN::RefPtr<Socket>, BAN::RefPtr<Socket>);

-		void on_receive(NetworkInterface&, BAN::ConstByteSpan, uint32_t validated_cksums);
+		void on_receive(NetworkInterface&, BAN::ConstByteSpan);

 	private:
 		NetworkManager() {}
@@ -35,7 +35,7 @@ namespace Kernel
 		virtual void get_protocol_header(BAN::ByteSpan header, BAN::ConstByteSpan payload, uint16_t dst_port, PseudoHeader) = 0;
 		virtual NetworkProtocol protocol() const = 0;

-		virtual void receive_packet(BAN::ConstByteSpan, const sockaddr* sender, socklen_t sender_len, uint32_t validated_cksums) = 0;
+		virtual void receive_packet(BAN::ConstByteSpan, const sockaddr* sender, socklen_t sender_len) = 0;

 		bool is_bound() const { return m_address_len >= static_cast<socklen_t>(sizeof(sa_family_t)) && m_address.ss_family != AF_UNSPEC; }
 		in_port_t bound_port() const
@@ -54,7 +54,7 @@ namespace Kernel
 	protected:
 		NetworkSocket(NetworkLayer&, const Socket::Info&);

-		virtual BAN::ErrorOr<long> ioctl_impl(unsigned long request, void* arg) override;
+		virtual BAN::ErrorOr<long> ioctl_impl(int request, void* arg) override;
 		virtual BAN::ErrorOr<void> getsockname_impl(sockaddr*, socklen_t*) override;
 		virtual BAN::ErrorOr<void> getpeername_impl(sockaddr*, socklen_t*) override = 0;

@@ -7,25 +7,25 @@ namespace Kernel

 	enum RTL8169_IO_REGS : uint16_t
 	{
-		RTL8169_IO_IDR0    = 0x00,
-		RTL8169_IO_IDR1    = 0x01,
-		RTL8169_IO_IDR2    = 0x02,
-		RTL8169_IO_IDR3    = 0x03,
-		RTL8169_IO_IDR4    = 0x04,
-		RTL8169_IO_IDR5    = 0x05,
+		RTL8169_IO_IDR0   = 0x00,
+		RTL8169_IO_IDR1   = 0x01,
+		RTL8169_IO_IDR2   = 0x02,
+		RTL8169_IO_IDR3   = 0x03,
+		RTL8169_IO_IDR4   = 0x04,
+		RTL8169_IO_IDR5   = 0x05,

-		RTL8169_IO_TNPDS   = 0x20,
-		RTL8169_IO_CR      = 0x37,
-		RTL8169_IO_TPPoll  = 0x38,
-		RTL8169_IO_IMR     = 0x3C,
-		RTL8169_IO_ISR     = 0x3E,
-		RTL8169_IO_TCR     = 0x40,
-		RTL8169_IO_RCR     = 0x44,
-		RTL8169_IO_PHYSts  = 0x6C,
-		RTL8169_IO_RMS     = 0xDA,
-		RTL8169_IO_CPlusCR = 0xE0,
-		RTL8169_IO_RDSAR   = 0xE4,
-		RTL8169_IO_MTPS    = 0xEC,
+		RTL8169_IO_TNPDS  = 0x20,
+		RTL8169_IO_CR     = 0x37,
+		RTL8169_IO_TPPoll = 0x38,
+		RTL8169_IO_IMR    = 0x3C,
+		RTL8169_IO_ISR    = 0x3E,
+		RTL8169_IO_TCR    = 0x40,
+		RTL8169_IO_RCR    = 0x44,
+		RTL8169_IO_9346CR = 0x50,
+		RTL8169_IO_PHYSts = 0x6C,
+		RTL8169_IO_RMS    = 0xDA,
+		RTL8169_IO_RDSAR  = 0xE4,
+		RTL8169_IO_MTPS   = 0xEC,
 	};

 	enum RTL8169_CR : uint8_t
@@ -20,7 +20,7 @@ namespace Kernel
 		virtual bool link_up() override { return m_link_up; }
 		virtual int link_speed() override;

-		virtual size_t payload_mtu() const override { return 0x1FF8 - sizeof(EthernetHeader); }
+		virtual size_t payload_mtu() const override { return 7436 - sizeof(EthernetHeader); }

 		virtual void handle_irq() override;

@@ -33,7 +33,7 @@ namespace Kernel

 		BAN::ErrorOr<void> initialize();

-		virtual BAN::ErrorOr<void> send_raw_bytes(BAN::Span<const BAN::ConstByteSpan> buffers) override;
+		virtual BAN::ErrorOr<void> send_bytes(BAN::MACAddress destination, EtherType protocol, BAN::Span<const BAN::ConstByteSpan>) override;

 		virtual bool can_read_impl() const override { return false; }
 		virtual bool can_write_impl() const override { return false; }
@@ -64,17 +64,14 @@ namespace Kernel
 		BAN::UniqPtr<DMARegion>	m_rx_descriptor_region;
 		BAN::UniqPtr<DMARegion>	m_tx_descriptor_region;

-		BAN::Atomic<bool> m_rx_thread_should_die { false };
-		BAN::Atomic<bool> m_rx_thread_is_dead { true };
+		SpinLock m_lock;

-		uint32_t m_rx_head { 0 };
-		SpinLock m_rx_lock;
-		ThreadBlocker m_rx_blocker;
+		bool m_thread_should_die { false };
+		BAN::Atomic<bool> m_thread_is_dead { true };
+		ThreadBlocker m_thread_blocker;

-		BAN::Atomic<uint32_t> m_tx_head { 0 };
-		BAN::Atomic<uint32_t> m_tx_commit { 0 };
-		SpinLock m_tx_lock;
-		ThreadBlocker m_tx_blocker;
+		uint32_t m_rx_current { 0 };
+		size_t m_tx_current { 0 };

 		BAN::MACAddress	m_mac_address {};
 		BAN::Atomic<bool> m_link_up { false };
@@ -7,6 +7,7 @@
 #include <kernel/Memory/ByteRingBuffer.h>
 #include <kernel/Networking/NetworkInterface.h>
 #include <kernel/Networking/NetworkSocket.h>
+#include <kernel/Thread.h>
 #include <kernel/ThreadBlocker.h>

 namespace Kernel
@@ -65,9 +66,9 @@ namespace Kernel
 		BAN::ErrorOr<void> getsockopt_impl(int, int, void*, socklen_t*) override;
 		BAN::ErrorOr<void> setsockopt_impl(int, int, const void*, socklen_t) override;

-		BAN::ErrorOr<long> ioctl_impl(unsigned long, void*) override;
+		BAN::ErrorOr<long> ioctl_impl(int, void*) override;

-		void receive_packet(BAN::ConstByteSpan, const sockaddr* sender, socklen_t sender_len, uint32_t validated_cksums) override;
+		void receive_packet(BAN::ConstByteSpan, const sockaddr* sender, socklen_t sender_len) override;

 		bool can_read_impl() const override;
 		bool can_write_impl() const override;
@@ -31,7 +31,7 @@ namespace Kernel
 		void get_protocol_header(BAN::ByteSpan header, BAN::ConstByteSpan payload, uint16_t dst_port, PseudoHeader) override;

 	protected:
-		void receive_packet(BAN::ConstByteSpan, const sockaddr* sender, socklen_t sender_len, uint32_t validated_cksums) override;
+		void receive_packet(BAN::ConstByteSpan, const sockaddr* sender, socklen_t sender_len) override;

 		BAN::ErrorOr<void> connect_impl(const sockaddr*, socklen_t) override;
 		BAN::ErrorOr<void> bind_impl(const sockaddr* address, socklen_t address_len) override;
@@ -41,7 +41,7 @@ namespace Kernel
 		BAN::ErrorOr<void> getsockopt_impl(int, int, void*, socklen_t*) override;
 		BAN::ErrorOr<void> setsockopt_impl(int, int, const void*, socklen_t) override;

-		BAN::ErrorOr<long> ioctl_impl(unsigned long, void*) override;
+		BAN::ErrorOr<long> ioctl_impl(int, void*) override;

 		bool can_read_impl() const override { return !m_packets.empty(); }
 		bool can_write_impl() const override { return true; }
@@ -6,7 +6,6 @@
 #include <kernel/FS/Socket.h>
 #include <kernel/FS/TmpFS/Inode.h>
 #include <kernel/FS/VirtualFileSystem.h>
-#include <kernel/Memory/VirtualRange.h>
 #include <kernel/OpenFileDescriptorSet.h>

 namespace Kernel
@@ -31,7 +30,6 @@ namespace Kernel
 		virtual BAN::ErrorOr<void> bind_impl(const sockaddr*, socklen_t) override;
 		virtual BAN::ErrorOr<size_t> recvmsg_impl(msghdr& message, int flags) override;
 		virtual BAN::ErrorOr<size_t> sendmsg_impl(const msghdr& message, int flags) override;
-		virtual BAN::ErrorOr<void> getsockname_impl(sockaddr*, socklen_t*) override;
 		virtual BAN::ErrorOr<void> getpeername_impl(sockaddr*, socklen_t*) override;
 		virtual BAN::ErrorOr<void> getsockopt_impl(int, int, void*, socklen_t*) override;
 		virtual BAN::ErrorOr<void> setsockopt_impl(int, int, const void*, socklen_t) override;
@@ -34,7 +34,6 @@ namespace Kernel
 		BAN::ErrorOr<int> dup2(int, int);

 		BAN::ErrorOr<int> fcntl(int fd, int cmd, uintptr_t extra);
-		BAN::ErrorOr<long> ioctl(int fd, unsigned long request, void* arg);

 		BAN::ErrorOr<off_t> seek(int fd, off_t offset, int whence);
 		BAN::ErrorOr<off_t> tell(int) const;
@@ -59,8 +58,6 @@ namespace Kernel
 		BAN::ErrorOr<size_t> recvmsg(int socket, msghdr& message, int flags);
 		BAN::ErrorOr<size_t> sendmsg(int socket, const msghdr& message, int flags);

-		int get_max_open_fd() const;
-
 		BAN::ErrorOr<VirtualFileSystem::File> file_of(int) const;
 		BAN::ErrorOr<BAN::String> path_of(int) const;
 		BAN::ErrorOr<BAN::RefPtr<Inode>> inode_of(int);
@@ -3,9 +3,8 @@
 #include <BAN/UniqPtr.h>
 #include <BAN/Vector.h>
 #include <kernel/ACPI/AML/Node.h>
-#include <kernel/InterruptNumbers.h>
-#include <kernel/Interruptable.h>
 #include <kernel/Memory/Types.h>
+#include <kernel/Storage/StorageController.h>

 #include <sys/types.h>

@@ -180,7 +179,7 @@ namespace Kernel::PCI
 	private:
 		struct PCIeInfo
 		{
-			paddr_t bus_paddr[256] {};
+			paddr_t bus_paddr[256];
 		};

 		PCIManager() = default;
@@ -10,10 +10,10 @@ namespace Kernel
 	{
 	public:
 		virtual void eoi(uint8_t) override;
-		virtual void enable_irq(uint8_t, bool level_triggered) override;
+		virtual void enable_irq(uint8_t) override;
 		virtual bool is_in_service(uint8_t) override;

-		virtual BAN::ErrorOr<void> reserve_irq(uint8_t irq, bool shared) override;
+		virtual BAN::ErrorOr<void> reserve_irq(uint8_t irq) override;
 		virtual BAN::Optional<uint8_t> get_free_irq() override;

 		virtual void initialize_multiprocessor() override;
@@ -29,8 +29,7 @@ namespace Kernel

 	private:
 		SpinLock m_lock;
-		uint16_t m_used_irqs { 1u << 2 };
-		uint16_t m_excl_irqs { 1u << 2 };
+		uint16_t m_reserved_irqs { 1u << 2 };

 		friend class InterruptController;
 	};
@@ -19,7 +19,6 @@

 #include <poll.h>
 #include <sys/banan-os.h>
-#include <sys/epoll.h>
 #include <sys/mman.h>
 #include <sys/select.h>
 #include <sys/socket.h>
@@ -27,6 +26,8 @@
 #include <sys/time.h>
 #include <termios.h>

+struct epoll_event;
+
 namespace Kernel
 {

@@ -43,10 +44,10 @@ namespace Kernel
 		~Process();
 		void cleanup_function(Thread*);

-		BAN::ErrorOr<vaddr_t> setup_initial_process_stack(MemoryBackedRegion&, BAN::Span<BAN::String> argv, BAN::Span<BAN::String> envp, BAN::Span<LibELF::AuxiliaryVector> auxv);
-
+		void register_to_scheduler();
 		void exit(int status, int signal);

+		void add_thread(Thread*);
 		// returns true if thread was the last one
 		bool on_thread_exit(Thread&);

@@ -67,6 +68,7 @@ namespace Kernel
 		BAN::ErrorOr<long> sys_exec(const char* path, const char* const* argv, const char* const* envp);

 		BAN::ErrorOr<long> sys_wait(pid_t pid, int* stat_loc, int options);
+		BAN::ErrorOr<long> sys_sleep(int seconds);
 		BAN::ErrorOr<long> sys_nanosleep(const timespec* rqtp, timespec* rmtp);
 		BAN::ErrorOr<long> sys_setitimer(int which, const itimerval* value, itimerval* ovalue);

@@ -135,7 +137,7 @@ namespace Kernel
 		BAN::ErrorOr<long> sys_recvmsg(int socket, msghdr* message, int flags);
 		BAN::ErrorOr<long> sys_sendmsg(int socket, const msghdr* message, int flags);

-		BAN::ErrorOr<long> sys_ioctl(int fildes, unsigned long request, void* arg);
+		BAN::ErrorOr<long> sys_ioctl(int fildes, int request, void* arg);

 		BAN::ErrorOr<long> sys_pselect(sys_pselect_t* arguments);
 		BAN::ErrorOr<long> sys_ppoll(pollfd* fds, nfds_t nfds, const timespec* tmp_p, const sigset_t* sigmask);
@@ -178,10 +180,9 @@ namespace Kernel
 		BAN::ErrorOr<long> sys_mprotect(void* addr, size_t len, int prot);
 		BAN::ErrorOr<long> sys_msync(void* addr, size_t len, int flags);

-		BAN::ErrorOr<long> sys_shmget(key_t key, size_t size, int shmflg);
-		BAN::ErrorOr<long> sys_shmctl(int shmid, int cmd, struct shmid_ds* buf);
-		BAN::ErrorOr<long> sys_shmat(int shmid, const void* shmaddr, int shmflg);
-		BAN::ErrorOr<long> sys_shmdt(const void* shmaddr);
+		BAN::ErrorOr<long> sys_smo_create(size_t len, int prot);
+		BAN::ErrorOr<long> sys_smo_delete(SharedMemoryObjectManager::Key);
+		BAN::ErrorOr<long> sys_smo_map(SharedMemoryObjectManager::Key);

 		BAN::ErrorOr<long> sys_ttyname(int fildes, char* name, size_t namesize);
 		BAN::ErrorOr<long> sys_posix_openpt(int flags);
@@ -209,12 +210,12 @@ namespace Kernel
 		BAN::ErrorOr<long> sys_set_gsbase(void*);
 		BAN::ErrorOr<long> sys_get_gsbase();

-		BAN::ErrorOr<long> sys_thread_create(void (*entry)(void*), void* arg, void* stack_base, size_t stack_size);
-		BAN::ErrorOr<long> sys_thread_exit(void* value);
-		BAN::ErrorOr<long> sys_thread_join(pid_t tid, void** value);
-		BAN::ErrorOr<long> sys_thread_getid();
-		BAN::ErrorOr<long> sys_thread_kill(pid_t tid, int signal);
-		BAN::ErrorOr<long> sys_thread_detach(pid_t tid);
+		BAN::ErrorOr<long> sys_pthread_create(const pthread_attr_t* attr, void (*entry)(void*), void* arg);
+		BAN::ErrorOr<long> sys_pthread_exit(void* value);
+		BAN::ErrorOr<long> sys_pthread_join(pthread_t thread, void** value);
+		BAN::ErrorOr<long> sys_pthread_self();
+		BAN::ErrorOr<long> sys_pthread_kill(pthread_t thread, int signal);
+		BAN::ErrorOr<long> sys_pthread_detach(pthread_t thread);

 		BAN::ErrorOr<long> sys_clock_gettime(clockid_t, timespec*);

@@ -228,12 +229,11 @@ namespace Kernel

 		vaddr_t shared_page_vaddr() const { return m_shared_page_vaddr; }

-		PageTable& page_table() { return *m_page_table; }
+		PageTable& page_table() { return m_page_table ? *m_page_table : PageTable::kernel(); }

 		size_t proc_meminfo(off_t offset, BAN::ByteSpan) const;
 		size_t proc_cmdline(off_t offset, BAN::ByteSpan) const;
 		size_t proc_environ(off_t offset, BAN::ByteSpan) const;
-		size_t proc_cputime(off_t offset, BAN::ByteSpan) const;
 		BAN::ErrorOr<BAN::String> proc_cwd() const;
 		BAN::ErrorOr<BAN::String> proc_exe() const;

@@ -255,8 +255,6 @@ namespace Kernel
 		const VirtualFileSystem::File& working_directory() const { return m_working_directory; }
 		const VirtualFileSystem::File& root_file() const { return m_root_file; }

-		BAN::ErrorOr<AddressRange> find_free_address_range(size_t size);
-
 	private:
 		Process(const Credentials&, pid_t pid, pid_t parent, pid_t sid, pid_t pgrp);
 		static Process* create_process(const Credentials&, pid_t parent, pid_t sid = 0, pid_t pgrp = 0);
@@ -282,11 +280,13 @@ namespace Kernel
 		// You must hold reader end of m_mapped_region_lock when calling this.
 		size_t find_mapped_region(vaddr_t) const;

+		BAN::ErrorOr<AddressRange> find_free_address_range(size_t size);
+
 		BAN::ErrorOr<VirtualFileSystem::File> find_file(int fd, const char* path, int flags) const;
 		BAN::ErrorOr<FileParent> find_parent_file(int fd, const char* path, int flags) const;
 		BAN::ErrorOr<VirtualFileSystem::File> find_relative_parent(int fd, const char* path) const;

-		BAN::ErrorOr<void> validate_and_pin_pointer_access(const void*, size_t, bool needs_write, BAN::Vector<MemoryRegion*>&);
+		BAN::ErrorOr<MemoryRegion*> validate_and_pin_pointer_access(const void*, size_t, bool needs_write);

 		uint64_t signal_pending_mask() const
 		{
@@ -364,13 +364,13 @@ namespace Kernel

 		BAN::Vector<Thread*> m_threads;

-		struct exited_thread_info_t
+		struct pthread_info_t
 		{
-			pid_t tid;
+			pthread_t thread;
 			void* value;
 		};
-		BAN::Vector<exited_thread_info_t> m_exited_threads;
-		ThreadBlocker m_thread_exit_blocker;
+		BAN::Vector<pthread_info_t> m_exited_pthreads;
+		ThreadBlocker m_pthread_exit_blocker;

 		uint64_t m_alarm_interval_ns { 0 };
 		uint64_t m_alarm_wake_time_ns { 0 };
@@ -1,14 +1,17 @@
 #pragma once

-#include <BAN/Array.h>
 #include <BAN/Atomic.h>
-#include <BAN/NoCopyMove.h>
+#include <BAN/ForwardList.h>
 #include <BAN/Math.h>

 #include <kernel/API/SharedPage.h>
 #include <kernel/Arch.h>
+#include <kernel/GDT.h>
+#include <kernel/IDT.h>
+#include <kernel/InterruptStack.h>
 #include <kernel/Memory/Types.h>
 #include <kernel/ProcessorID.h>
+#include <kernel/Scheduler.h>

 namespace Kernel
 {
@@ -19,11 +22,6 @@ namespace Kernel
 		Enabled,
 	};

-	class GDT;
-	class IDT;
-	class Scheduler;
-	class Thread;
-
 #if ARCH(x86_64) || ARCH(i686)
 	class Processor
 	{
@@ -53,18 +51,12 @@ namespace Kernel
 			union
 			{
 				TLBEntry flush_tlb;
-				Thread* new_thread;
-				Thread* unblock_thread;
+				SchedulerQueue::Node* new_thread;
+				SchedulerQueue::Node* unblock_thread;
 				bool dummy;
 			};
 		};

-		struct LoadStats
-		{
-			uint64_t ns_idle;
-			uint64_t ns_total;
-		};
-
 	public:
 		static Processor& create(ProcessorID id);
 		static Processor& initialize();
@@ -80,6 +72,9 @@ namespace Kernel
 		static void set_smp_enabled() { s_is_smp_enabled = true; }
 		static void wait_until_processors_ready();

+		static void toggle_should_print_cpu_load() { s_should_print_cpu_load = !s_should_print_cpu_load; }
+		static bool get_should_print_cpu_load() { return s_should_print_cpu_load; }
+
 		static ProcessorID bsp_id() { return s_bsp_id; }
 		static bool current_is_bsp() { return current_id() == bsp_id(); }

@@ -106,17 +101,10 @@ namespace Kernel
 		static void pause()
 		{
 			__builtin_ia32_pause();
-			if (is_smp_enabled() && !smp_messages_disabled())
+			if (is_smp_enabled())
 				handle_smp_messages();
 		}

-		static bool smp_messages_disabled() { return read_gs_sized<bool>(offsetof(Processor, m_smp_messages_disabled)); }
-		static void set_disable_smp_messages(bool disabled)
-		{
-			ASSERT(smp_messages_disabled() != disabled);
-			write_gs_sized<bool>(offsetof(Processor, m_smp_messages_disabled), disabled);
-		}
-
 		vaddr_t stack_top_vaddr() const { return m_stack_vaddr + s_stack_size; }
 		paddr_t stack_top_paddr() const { return m_stack_paddr + s_stack_size; }

@@ -128,12 +116,10 @@ namespace Kernel
 		static void* get_current_page_table()					{ return read_gs_sized<void*>(offsetof(Processor, m_current_page_table)); }
 		static void set_current_page_table(void* page_table)	{ write_gs_sized<void*>(offsetof(Processor, m_current_page_table), page_table); }

-		static LoadStats get_load_stats(size_t index);
-
 		static void yield();
 		static Scheduler& scheduler() { return *read_gs_sized<Scheduler*>(offsetof(Processor, m_scheduler)); }

-		static void initialize_tsc(uint64_t realtime_seconds);
+		static void initialize_tsc(uint8_t shift, uint64_t mult, uint64_t realtime_seconds);
 		static void update_tsc();
 		static uint64_t ns_since_boot_tsc();

@@ -181,23 +167,17 @@ namespace Kernel
 		}

 		template<typename T>
-		static T read_gs_sized(uintptr_t offset) requires(sizeof(T) <= sizeof(uintptr_t) && BAN::Math::is_power_of_two(sizeof(T)))
+		static T read_gs_sized(uintptr_t offset) requires(sizeof(T) <= 8 && BAN::Math::is_power_of_two(sizeof(T)))
 		{
 			T value;
-			if constexpr (sizeof(T) == 1 && ARCH(i686))
-				asm volatile("mov %%gs:%a[offset], %[value]" : [value]"=q"(value) : [offset]"ir"(offset) : "memory");
-			else
-				asm volatile("mov %%gs:%a[offset], %[value]" : [value]"=r"(value) : [offset]"ir"(offset) : "memory");
+			asm volatile("mov %%gs:%a[offset], %[value]" : [value]"=r"(value) : [offset]"ir"(offset));
 			return value;
 		}

 		template<typename T>
-		static void write_gs_sized(uintptr_t offset, T value) requires(sizeof(T) <= sizeof(uintptr_t) && BAN::Math::is_power_of_two(sizeof(T)))
+		static void write_gs_sized(uintptr_t offset, T value) requires(sizeof(T) <= 8 && BAN::Math::is_power_of_two(sizeof(T)))
 		{
-			if constexpr (sizeof(T) == 1 && ARCH(i686))
-				asm volatile("mov %[value], %%gs:%a[offset]" :: [value]"q"(value), [offset]"ir"(offset) : "memory");
-			else
-				asm volatile("mov %[value], %%gs:%a[offset]" :: [value]"r"(value), [offset]"ir"(offset) : "memory");
+			asm volatile("mov %[value], %%gs:%a[offset]" :: [value]"r"(value), [offset]"ir"(offset) : "memory");
 		}

 		void lock_tlb_lock();
@@ -207,14 +187,13 @@ namespace Kernel
 		static ProcessorID s_bsp_id;
 		static BAN::Atomic<uint8_t> s_processor_count;
 		static BAN::Atomic<bool>    s_is_smp_enabled;
+		static BAN::Atomic<bool>    s_should_print_cpu_load;
 		static paddr_t              s_shared_page_paddr;
 		static vaddr_t              s_shared_page_vaddr;

 		ProcessorID m_id { 0 };
 		uint8_t m_index { 0 };

-		bool m_smp_messages_disabled { false };
-
 		vaddr_t m_thread_syscall_stack;

 		Thread* m_sse_thread { nullptr };
@@ -228,9 +207,10 @@ namespace Kernel

 		Scheduler* m_scheduler { nullptr };

-		BAN::Atomic<bool> m_load_stat_lock;
-		uint64_t m_load_start_ns { 0 };
-		LoadStats m_load_stats {};
+		uint64_t m_start_ns { 0 };
+		uint64_t m_idle_ns { 0 };
+		uint64_t m_last_update_ns { 0 };
+		uint64_t m_next_update_ns { 0 };

 		BAN::Atomic<SMPMessage*> m_smp_pending { nullptr };
 		BAN::Atomic<SMPMessage*> m_smp_free    { nullptr };
@@ -5,7 +5,6 @@
 #include <BAN/NoCopyMove.h>
 #include <kernel/InterruptStack.h>
 #include <kernel/ProcessorID.h>
-#include <kernel/SchedulerThreadNode.h>

 #include <sys/types.h>

@@ -15,6 +14,29 @@ namespace Kernel
 	class BaseMutex;
 	class Thread;
 	class ThreadBlocker;
+	struct SchedulerQueueNode;
+
+	class SchedulerQueue
+	{
+	public:
+		using Node = SchedulerQueueNode;
+
+	public:
+		void add_thread_to_back(Node*);
+		void add_thread_with_wake_time(Node*);
+		template<typename F>
+		Node* remove_with_condition(F callback);
+		void remove_node(Node*);
+		Node* front();
+		Node* pop_front();
+
+		bool empty() const { return m_head == nullptr; }
+
+	private:
+		Node* m_head { nullptr };
+		Node* m_tail { nullptr };
+	};
+
 	class Scheduler
 	{
 		BAN_NON_COPYABLE(Scheduler);
@@ -23,12 +45,12 @@ namespace Kernel
 	public:
 		struct NewThreadRequest
 		{
-			SchedulerThreadNode* node;
+			SchedulerQueue::Node* node;
 		};

 		struct UnblockRequest
 		{
-			SchedulerThreadNode* node;
+			SchedulerQueue::Node* node;
 		};

 	public:
@@ -36,13 +58,13 @@ namespace Kernel
 		BAN::ErrorOr<void> initialize();

 		void reschedule(YieldRegisters*);
-		void reschedule_if_needed();
+		void reschedule_if_idle();

-		void on_timer_interrupt();
-		void on_yield(YieldRegisters*);
+		void timer_interrupt();

-		static void bind_thread_to_processor(Thread*, ProcessorID);
-		void add_thread(Thread*);
+		static BAN::ErrorOr<void> bind_thread_to_processor(Thread*, ProcessorID);
+		// if thread is already bound, this will never fail
+		BAN::ErrorOr<void> add_thread(Thread*);

 		void block_current_thread(ThreadBlocker* thread_blocker, uint64_t wake_time_ns, BaseMutex* mutex);
 		void unblock_thread(Thread*);
@@ -56,21 +78,23 @@ namespace Kernel
 	private:
 		Scheduler() = default;

-		void add_current_to_most_loaded(void* target_list);
-		void update_most_loaded_node_list(SchedulerThreadNode*, void* target_list);
-		void remove_node_from_most_loaded(SchedulerThreadNode*);
+		void add_current_to_most_loaded(SchedulerQueue* target_queue);
+		void update_most_loaded_node_queue(SchedulerQueue::Node*, SchedulerQueue* target_queue);
+		void remove_node_from_most_loaded(SchedulerQueue::Node*);

-		void update_wake_up_deadline();
 		void wake_up_sleeping_threads();

 		void do_load_balancing();

 		class ProcessorID find_least_loaded_processor() const;

+		void add_thread(SchedulerQueue::Node*);
+		void unblock_thread(SchedulerQueue::Node*);
+
 	private:
-		SchedulerQueue m_run_list;
-		SchedulerHeap m_block_list;
-		SchedulerThreadNode* m_current { nullptr };
+		SchedulerQueue m_run_queue;
+		SchedulerQueue m_block_queue;
+		SchedulerQueue::Node* m_current { nullptr };

 		uint32_t m_thread_count { 0 };

@@ -82,8 +106,8 @@ namespace Kernel

 		struct ThreadInfo
 		{
-			void*                list { nullptr };
-			SchedulerThreadNode* node { nullptr };
+			SchedulerQueue*       queue { nullptr };
+			SchedulerQueue::Node* node  { nullptr };
 		};
 		BAN::Array<ThreadInfo, 10> m_most_loaded_threads;

@@ -92,8 +116,6 @@ namespace Kernel

 		bool m_should_calculate_max_load_threads { true };

-		bool m_has_pending_reschedule { false };
-
 		Thread* m_idle_thread { nullptr };

 		friend class ThreadBlocker;
@@ -0,0 +1,36 @@
+#pragma once
+
+#include <kernel/ProcessorID.h>
+#include <kernel/Lock/SpinLock.h>
+
+namespace Kernel
+{
+
+	class Thread;
+	class ThreadBlocker;
+
+	struct SchedulerQueueNode
+	{
+		SchedulerQueueNode(Thread* thread)
+			: thread(thread)
+		{}
+
+		Thread* const thread;
+
+		SchedulerQueueNode* next { nullptr };
+		SchedulerQueueNode* prev { nullptr };
+
+		uint64_t wake_time_ns { static_cast<uint64_t>(-1) };
+
+		BAN::Atomic<ThreadBlocker*> blocker { nullptr };
+		SchedulerQueueNode* block_chain_prev { nullptr };
+		SchedulerQueueNode* block_chain_next { nullptr };
+
+		ProcessorID processor_id { PROCESSOR_NONE };
+		bool blocked { false };
+
+		uint64_t last_start_ns { 0 };
+		uint64_t time_used_ns  { 0 };
+	};
+
+}
@@ -1,96 +0,0 @@
-#pragma once
-
-#include <BAN/Atomic.h>
-#include <BAN/NoCopyMove.h>
-#include <kernel/ProcessorID.h>
-
-namespace Kernel
-{
-
-	class Thread;
-	class ThreadBlocker;
-
-	struct SchedulerThreadNode
-	{
-		SchedulerThreadNode(Thread* thread)
-			: thread(thread)
-			, heap({ nullptr, nullptr, nullptr })
-		{}
-
-		Thread* const thread;
-
-		union
-		{
-			struct
-			{
-				SchedulerThreadNode* next;
-				SchedulerThreadNode* prev;
-			} queue;
-			struct
-			{
-				SchedulerThreadNode* parent;
-				SchedulerThreadNode* lchild;
-				SchedulerThreadNode* rchild;
-			} heap;
-		};
-
-		uint64_t wake_time_ns { static_cast<uint64_t>(-1) };
-
-		BAN::Atomic<ThreadBlocker*> blocker { nullptr };
-		SchedulerThreadNode* block_chain_prev { nullptr };
-		SchedulerThreadNode* block_chain_next { nullptr };
-
-		ProcessorID processor_id { PROCESSOR_NONE };
-		bool blocked { false };
-
-		uint64_t last_start_ns { 0 };
-		uint64_t time_used_ns  { 0 };
-	};
-
-	class SchedulerQueue
-	{
-		BAN_NON_COPYABLE(SchedulerQueue);
-		BAN_NON_MOVABLE(SchedulerQueue);
-	public:
-		SchedulerQueue() = default;
-
-		SchedulerThreadNode* front();
-		SchedulerThreadNode* pop_front();
-
-		void push(SchedulerThreadNode*);
-		void pop(SchedulerThreadNode*);
-
-		void walk(void (*)(const SchedulerThreadNode*, void*), void*) const;
-		bool empty() const { return m_head == nullptr; }
-
-	private:
-		SchedulerThreadNode* m_head { nullptr };
-		SchedulerThreadNode* m_tail { nullptr };
-	};
-
-	class SchedulerHeap
-	{
-		BAN_NON_COPYABLE(SchedulerHeap);
-		BAN_NON_MOVABLE(SchedulerHeap);
-	public:
-		SchedulerHeap() = default;
-
-		SchedulerThreadNode* front();
-		SchedulerThreadNode* pop_front();
-
-		void push(SchedulerThreadNode*);
-		void pop(SchedulerThreadNode*);
-
-		void walk(void (*)(const SchedulerThreadNode*, void*), void*) const;
-		bool empty() const { return m_root == nullptr; }
-
-	private:
-		void walk_impl(void (*)(const SchedulerThreadNode*, void*), void*, const SchedulerThreadNode*) const;
-		void swap_nodes(SchedulerThreadNode*, SchedulerThreadNode*);
-
-	private:
-		SchedulerThreadNode* m_root { nullptr };
-		SchedulerThreadNode* m_last { nullptr };
-	};
-
-}
@@ -10,19 +10,16 @@
 namespace Kernel
 {

-	class AHCIController final : public BAN::RefCounted<AHCIController>, public Interruptable
+	class AHCIController final : public StorageController, public Interruptable
 	{
 		BAN_NON_COPYABLE(AHCIController);
 		BAN_NON_MOVABLE(AHCIController);

 	public:
-		static BAN::ErrorOr<BAN::RefPtr<AHCIController>> create(PCI::Device&);
-
 		~AHCIController();

 		virtual void handle_irq() override;

-		bool supports_64bit() const { return m_supports_64bit; }
 		uint32_t command_slot_count() const { return m_command_slot_count; }

 	private:
@@ -30,7 +27,6 @@ namespace Kernel
 			: m_pci_device(pci_device)
 		{ }
 		BAN::ErrorOr<void> initialize();
-
 		BAN::Optional<AHCIPortType> check_port_type(volatile HBAPortMemorySpace&);

 	private:
@@ -39,8 +35,9 @@ namespace Kernel

 		BAN::Array<AHCIDevice*, 32> m_devices;

-		bool m_supports_64bit { false };
 		uint32_t m_command_slot_count { 0 };
+
+		friend class ATAController;
 	};

 }
@@ -32,6 +32,8 @@
 namespace Kernel
 {

+	static constexpr uint32_t s_hba_prdt_count { 8 };
+
 	struct FISRegisterH2D
 	{
 		uint8_t  fis_type;			// FIS_TYPE_REGISTER_H2D
@@ -59,8 +61,7 @@ namespace Kernel
 		uint8_t  control;

 		uint8_t  __reserved1[4];
-	};
-	static_assert(sizeof(FISRegisterH2D) == 20);
+	} __attribute__((packed));

 	struct FISRegisterD2H
 	{
@@ -89,8 +90,7 @@ namespace Kernel
 		uint8_t  __reserved3[2];

 		uint8_t  __reserved4[4];
-	};
-	static_assert(sizeof(FISRegisterD2H) == 20);
+	} __attribute__((packed));

 	struct FISDataBI
 	{
@@ -102,8 +102,7 @@ namespace Kernel
 		uint8_t  __reserved1[2];

 		uint32_t data[0];			// Payload (1 - 2048 dwords)
-	};
-	static_assert(sizeof(FISDataBI) == 4);
+	} __attribute__((packed));

 	struct SetDeviceBitsD2H
 	{
@@ -118,8 +117,7 @@ namespace Kernel
 		uint8_t error;

 		uint32_t __reserved1;
-	};
-	static_assert(sizeof(SetDeviceBitsD2H) == 8);
+	} __attribute__((packed));

 	struct PIOSetupD2H
 	{
@@ -151,8 +149,7 @@ namespace Kernel

 		uint16_t tc;				// Transfer count
 		uint8_t  __reserved4[2];
-	};
-	static_assert(sizeof(PIOSetupD2H) == 20);
+	} __attribute__((packed));

 	struct DMASetupBI
 	{
@@ -166,8 +163,8 @@ namespace Kernel

 		uint8_t  __reserved1[2];

-		uint32_t dma_buffer_id_lo;		// DMA Buffer Identifier. Used to Identify DMA buffer in host memory.
-		uint32_t dma_buffer_id_hi;		// SATA Spec says host specific and not in Spec. Trying AHCI spec might work.
+		uint64_t dma_buffer_id;			// DMA Buffer Identifier. Used to Identify DMA buffer in host memory.
+										// SATA Spec says host specific and not in Spec. Trying AHCI spec might work.

 		uint32_t __reserved2;

@@ -176,8 +173,7 @@ namespace Kernel
 		uint32_t dma_transfer_count;	// Number of bytes to transfer. Bit 0 must be 0

 		uint32_t __reserved3;
-	};
-	static_assert(sizeof(DMASetupBI) == 28);
+	} __attribute__((packed));

 	struct HBAPortMemorySpace
 	{
@@ -200,8 +196,7 @@ namespace Kernel
 		uint32_t fbs;		// FIS-based switch control
 		uint32_t __reserved1[11];
 		uint32_t vendor[4];
-	};
-	static_assert(sizeof(HBAPortMemorySpace) == 128);
+	} __attribute__((packed));

 	struct HBAGeneralMemorySpace
 	{
@@ -222,8 +217,7 @@ namespace Kernel
 		uint8_t  vendor[0x100-0xA0];

 		HBAPortMemorySpace ports[0]; // 1 - 32 ports
-	};
-	static_assert(sizeof(HBAGeneralMemorySpace) == 256);
+	} __attribute__((packed));

 	struct ReceivedFIS
 	{
@@ -241,8 +235,7 @@ namespace Kernel
 		uint8_t				ufis[64];

 		uint8_t				__reserved[0x100-0xA0];
-	};
-	static_assert(sizeof(ReceivedFIS) == 256);
+	} __attribute__((packed));

 	struct HBACommandHeader
 	{
@@ -259,14 +252,13 @@ namespace Kernel

 		uint16_t prdtl;		// Physical region descriptor table length in entries

-		uint32_t prdbc;		// Physical region descriptor byte count transferred
+		volatile uint32_t prdbc;	// Physical region descriptor byte count transferred

 		uint32_t ctba;		// Command table descriptor base address
 		uint32_t ctbau;		// Command table descriptor base address upper 32 bits

 		uint32_t __reserved1[4];
-	};
-	static_assert(sizeof(HBACommandHeader) == 32);
+	} __attribute__((packed));

 	struct HBAPRDTEntry
 	{
@@ -277,17 +269,15 @@ namespace Kernel
 		uint32_t dbc : 22;		// Byte count, 4M max
 		uint32_t __reserved1 : 9;
 		uint32_t i : 1;			// Interrupt on completion
-	};
-	static_assert(sizeof(HBAPRDTEntry) == 16);
+	} __attribute__((packed));

 	struct HBACommandTable
 	{
 		uint8_t cfis[64];
 		uint8_t acmd[16];
 		uint8_t __reserved[48];
-		HBAPRDTEntry prdt_entry[0];
-	};
-	static_assert(sizeof(HBACommandTable) == 128);
+		HBAPRDTEntry prdt_entry[s_hba_prdt_count];
+	} __attribute__((packed));

 	enum class AHCIPortType
 	{
@@ -20,39 +20,30 @@ namespace Kernel
 			, m_port(port)
 		{ }
 		BAN::ErrorOr<void> initialize();
+		BAN::ErrorOr<void> allocate_buffers();
 		BAN::ErrorOr<void> rebase();
 		BAN::ErrorOr<void> read_identify_data();

-		paddr_t read_paddr(volatile uint32_t& lo, volatile uint32_t& hi) const;
-		void write_paddr(volatile uint32_t& lo, volatile uint32_t& hi, paddr_t paddr);
-
-		bool can_use_buffer_directly(BAN::ConstByteSpan buffer) const;
-
 		virtual BAN::ErrorOr<void> read_sectors_impl(uint64_t lba, uint64_t sector_count, BAN::ByteSpan) override;
 		virtual BAN::ErrorOr<void> write_sectors_impl(uint64_t lba, uint64_t sector_count, BAN::ConstByteSpan) override;
-		BAN::ErrorOr<size_t> send_command_sync(uint64_t lba, BAN::ConstByteSpan buffer, Command command);
+		BAN::ErrorOr<void> send_command_and_block(uint64_t lba, uint64_t sector_count, Command command);

-		BAN::ErrorOr<void> send_command_and_wait(uint32_t slot);
-		BAN::ErrorOr<uint32_t> find_free_command_slot();
+		BAN::Optional<uint32_t> find_free_command_slot();

 		void handle_irq();

-	private:
-		static constexpr uint32_t m_max_hba_prdt_count { 64 };
+		BAN::ErrorOr<void> block_until_command_completed(uint32_t command_slot);

-		BAN::Atomic<uint32_t> m_prev_is { 0 };
-		uint32_t m_free_slots { 0 };
+	private:
+		Mutex m_mutex;

 		BAN::RefPtr<AHCIController> m_controller;
 		volatile HBAPortMemorySpace* const m_port;

 		BAN::UniqPtr<DMARegion> m_dma_region;
-
-		Mutex m_temp_buffer_mutex;
-		BAN::UniqPtr<DMARegion> m_temp_buffer;
-
-		SpinLock m_command_lock;
-		ThreadBlocker m_command_blocker;
+		// Intermediate read/write buffer
+		// TODO: can we read straight to user buffer?
+		BAN::UniqPtr<DMARegion> m_data_dma_region;

 		friend class AHCIController;
 	};
@@ -56,6 +56,8 @@ namespace Kernel

 		// Non-owning pointers
 		BAN::Vector<ATADevice*> m_devices;
+
+		friend class ATAController;
 	};

 }
@@ -2,22 +2,23 @@

 #include <BAN/UniqPtr.h>
 #include <kernel/PCI.h>
+#include <kernel/Storage/StorageController.h>
 #include <kernel/Storage/ATA/ATABus.h>
 #include <kernel/Storage/ATA/ATADevice.h>

 namespace Kernel
 {

-	class ATAController : public BAN::RefCounted<ATAController>
+	class ATAController : public StorageController
 	{
 	public:
-		static BAN::ErrorOr<BAN::RefPtr<ATAController>> create(PCI::Device&);
+		static BAN::ErrorOr<BAN::RefPtr<StorageController>> create(PCI::Device&);
+		virtual BAN::ErrorOr<void> initialize() override;

 	private:
 		ATAController(PCI::Device& pci_device)
 			: m_pci_device(pci_device)
 		{ }
-		BAN::ErrorOr<void> initialize();

 	private:
 		PCI::Device& m_pci_device;
@@ -10,13 +10,13 @@
 namespace Kernel
 {

-	class NVMeController final : public CharacterDevice
+	class NVMeController final : public StorageController, public CharacterDevice
 	{
 		BAN_NON_COPYABLE(NVMeController);
 		BAN_NON_MOVABLE(NVMeController);

 	public:
-		static BAN::ErrorOr<BAN::RefPtr<NVMeController>> create(PCI::Device&);
+		static BAN::ErrorOr<BAN::RefPtr<StorageController>> create(PCI::Device&);

 		NVMeQueue& io_queue() { return *m_io_queue; }

@@ -30,7 +30,7 @@ namespace Kernel

 	private:
 		NVMeController(PCI::Device& pci_device);
-		BAN::ErrorOr<void> initialize();
+		virtual BAN::ErrorOr<void> initialize() override;

 		BAN::ErrorOr<void> identify_controller();
 		BAN::ErrorOr<void> identify_namespaces();
@@ -0,0 +1,15 @@
+#pragma once
+
+#include <BAN/RefPtr.h>
+
+namespace Kernel
+{
+
+	class StorageController : public BAN::RefCounted<StorageController>
+	{
+	public:
+		virtual ~StorageController() {}
+		virtual BAN::ErrorOr<void> initialize() = 0;
+	};
+
+}
@@ -1,7 +1,6 @@
 #pragma once

 #include <BAN/WeakPtr.h>
-#include <kernel/Memory/VirtualRange.h>
 #include <kernel/Terminal/TTY.h>

 namespace Kernel
@@ -33,7 +32,7 @@ namespace Kernel

 		void on_close(int) override;

-		BAN::ErrorOr<long> ioctl_impl(unsigned long, void*) override;
+		BAN::ErrorOr<long> ioctl_impl(int, void*) override;

 	private:
 		PseudoTerminalMaster(BAN::UniqPtr<VirtualRange>, mode_t, uid_t, gid_t);
@@ -53,8 +53,6 @@ namespace Kernel

 		virtual bool master_has_closed() const { return false; }

-		virtual bool is_vtty() const { return false; }
-
 	protected:
 		TTY(termios termios, mode_t mode, uid_t uid, gid_t gid);

@@ -70,7 +68,7 @@ namespace Kernel
 		virtual bool has_error_impl() const override { return false; }
 		virtual bool has_hungup_impl() const override { return false; }

-		virtual BAN::ErrorOr<long> ioctl_impl(unsigned long, void*) override;
+		virtual BAN::ErrorOr<long> ioctl_impl(int, void*) override;

 	private:
 		bool putchar(uint8_t ch);
@@ -102,9 +100,9 @@ namespace Kernel
 		termios m_termios;

 	protected:
-		Mutex m_input_mutex;
+		Mutex m_mutex;

-		RecursiveSpinLock m_write_lock;
+		Mutex m_write_lock;
 		ThreadBlocker m_write_blocker;
 	};

@@ -21,9 +21,6 @@ namespace Kernel

 		void clear() override;

-		bool is_vtty() const override { return true; }
-		BAN::ErrorOr<void> set_terminal_driver(BAN::RefPtr<TerminalDriver>);
-
 	protected:
 		BAN::StringView name() const override { return m_name; }
 		bool putchar_impl(uint8_t ch) override;
@@ -99,6 +96,8 @@ namespace Kernel
 		uint32_t m_last_cursor_row { static_cast<uint32_t>(-1) };
 		uint32_t m_last_cursor_column { static_cast<uint32_t>(-1) };

+		const Palette& m_palette;
+
 		TerminalDriver::Color m_foreground;
 		TerminalDriver::Color m_background;
 		bool m_colors_inverted { false };
@@ -5,9 +5,8 @@
 #include <BAN/RefPtr.h>
 #include <BAN/UniqPtr.h>
 #include <kernel/InterruptStack.h>
-#include <kernel/Lock/Mutex.h>
 #include <kernel/Memory/VirtualRange.h>
-#include <kernel/SchedulerThreadNode.h>
+#include <kernel/ThreadBlocker.h>

 #include <LibELF/AuxiliaryVector.h>

@@ -19,7 +18,6 @@ namespace Kernel

 	class MemoryBackedRegion;
 	class Process;
-	class ThreadBlocker;

 	class Thread
 	{
@@ -43,20 +41,22 @@ namespace Kernel
 		// TODO: userspace stack size is hard limited, maybe make this dynamic?
 #if ARCH(x86_64)
 		static constexpr size_t userspace_stack_size { 32 << 20 };
-		static constexpr vaddr_t userspace_stack_base { 0x0000700000000000 };
 #elif ARCH(i686)
 		static constexpr size_t userspace_stack_size { 4 << 20 };
-		static constexpr vaddr_t userspace_stack_base { 0xB0000000 };
 #endif

 	public:
 		static BAN::ErrorOr<Thread*> create_kernel(entry_t, void*);
-		static BAN::ErrorOr<Thread*> create_userspace(Process*, PageTable&, vaddr_t userspace_stack_vaddr, size_t userspace_stack_size, vaddr_t entry_point, vaddr_t stack_pointer);
+		static BAN::ErrorOr<Thread*> create_userspace(Process*, PageTable&);
 		~Thread();

+		BAN::ErrorOr<Thread*> pthread_create(entry_t, void*);
+
 		BAN::ErrorOr<Thread*> clone(Process*, uintptr_t sp, uintptr_t ip);
 		void setup_process_cleanup();

+		BAN::ErrorOr<void> initialize_userspace(vaddr_t entry, BAN::Span<BAN::String> argv, BAN::Span<BAN::String> envp, BAN::Span<LibELF::AuxiliaryVector> auxv);
+
 		// Returns true, if thread is going to trigger signal
 		bool is_interrupted_by_signal(bool skip_stop_and_cont = false) const;

@@ -77,21 +77,15 @@ namespace Kernel

 		// blocks current thread and returns either on unblock, eintr, spuriously or after timeout
 		// if mutex is not nullptr, it will be atomically freed before blocking and automatically locked on wake
-		BAN::ErrorOr<void> sleep_or_eintr_for_ns(uint64_t timeout_ns);
-		BAN::ErrorOr<void> sleep_or_eintr_until_ns(uint64_t waketime_ns);
+		BAN::ErrorOr<void> sleep_or_eintr_ns(uint64_t ns);
 		BAN::ErrorOr<void> block_or_eintr_indefinite(ThreadBlocker& thread_blocker, BaseMutex* mutex);
 		BAN::ErrorOr<void> block_or_eintr_or_timeout_ns(ThreadBlocker& thread_blocker, uint64_t timeout_ns, bool etimedout, BaseMutex* mutex);
 		BAN::ErrorOr<void> block_or_eintr_or_waketime_ns(ThreadBlocker& thread_blocker, uint64_t wake_time_ns, bool etimedout, BaseMutex* mutex);

-		BAN::ErrorOr<void> sleep_or_eintr_for_ms(uint64_t timeout_ms)
+		BAN::ErrorOr<void> sleep_or_eintr_ms(uint64_t ms)
 		{
-			ASSERT(!BAN::Math::will_multiplication_overflow<uint64_t>(timeout_ms, 1'000'000));
-			return sleep_or_eintr_for_ns(timeout_ms * 1'000'000);
-		}
-		BAN::ErrorOr<void> sleep_or_eintr_until_ms(uint64_t waketime_ms)
-		{
-			ASSERT(!BAN::Math::will_multiplication_overflow<uint64_t>(waketime_ms, 1'000'000));
-			return sleep_or_eintr_until_ns(waketime_ms * 1'000'000);
+			ASSERT(!BAN::Math::will_multiplication_overflow<uint64_t>(ms, 1'000'000));
+			return sleep_or_eintr_ns(ms * 1'000'000);
 		}
 		BAN::ErrorOr<void> block_or_eintr_or_timeout_ms(ThreadBlocker& thread_blocker, uint64_t timeout_ms, bool etimedout, BaseMutex* mutex)
 		{
@@ -112,6 +106,8 @@ namespace Kernel
 		vaddr_t kernel_stack_top() const	{ return m_kernel_stack->vaddr() + m_kernel_stack->size(); }
 		VirtualRange& kernel_stack() { return *m_kernel_stack; }

+		MemoryBackedRegion& userspace_stack() { ASSERT(is_userspace() && m_userspace_stack); return *m_userspace_stack; }
+
 		static Thread& current();
 		static pid_t current_tid();

@@ -126,14 +122,10 @@ namespace Kernel

 		bool is_userspace() const { return m_is_userspace; }

-		uint64_t cpu_time_total_ns() const;
-		void cpu_time_ns(uint64_t& user_ns, uint64_t& system_ns) const;
+		uint64_t cpu_time_ns() const;
 		void set_cpu_time_start();
 		void set_cpu_time_stop();

-		void set_is_in_syscall(bool is_in_syscall);
-		bool is_in_syscall() const { return m_is_in_syscall; }
-
 		void update_processor_index_address();

 		void set_fsbase(vaddr_t base) { m_fsbase = base; }
@@ -159,6 +151,8 @@ namespace Kernel
 	private:
 		Thread(pid_t tid, Process*);

+		void setup_exec(vaddr_t ip, vaddr_t sp);
+
 		static void on_exit_trampoline(Thread*);
 		void on_exit();

@@ -180,6 +174,7 @@ namespace Kernel
 		BAN::UniqPtr<PageTable>    m_keep_alive_page_table;

 		BAN::UniqPtr<VirtualRange> m_kernel_stack;
+		MemoryBackedRegion*        m_userspace_stack      { nullptr };
 		const pid_t                m_tid                  { 0 };
 		State                      m_state                { State::NotStarted };
 		Process*                   m_process              { nullptr };
@@ -187,13 +182,10 @@ namespace Kernel
 		BAN::Atomic<bool>          m_is_detached          { false };
 		bool                       m_delete_process       { false };

-		vaddr_t                    m_userspace_stack_vaddr { 0 };
-		size_t                     m_userspace_stack_size  { 0 };
-
 		vaddr_t                    m_fsbase               { 0 };
 		vaddr_t                    m_gsbase               { 0 };

-		SchedulerThreadNode        m_scheduler_node;
+		SchedulerQueue::Node*      m_scheduler_node       { nullptr };

 		YieldRegisters             m_yield_registers      { };

@@ -206,10 +198,8 @@ namespace Kernel
 		static_assert(_SIGMAX < 64);

 		mutable SpinLock           m_cpu_time_lock;
-		uint64_t                   m_cpu_time_user_ns     { 0 };
-		uint64_t                   m_cpu_time_system_ns   { 0 };
+		uint64_t                   m_cpu_time_ns          { 0 };
 		uint64_t                   m_cpu_time_start_ns    { UINT64_MAX };
-		BAN::Atomic<bool>          m_is_in_syscall        { false };

 		BAN::Atomic<uint32_t>      m_spinlock_count       { 0 };
 		BAN::Atomic<uint32_t>      m_mutex_count          { 0 };
@@ -1,14 +1,12 @@
 #pragma once

 #include <BAN/Math.h>
-#include <kernel/Lock/Mutex.h>
 #include <kernel/Lock/SpinLock.h>
+#include <kernel/Scheduler.h>

 namespace Kernel
 {

-	class SchedulerThreadNode;
-
 	class ThreadBlocker
 	{
 	public:
@@ -29,11 +27,11 @@ namespace Kernel
 		}

 	private:
-		void add_thread_to_block_queue(SchedulerThreadNode*);
-		void remove_thread_from_block_queue(SchedulerThreadNode*);
+		void add_thread_to_block_queue(SchedulerQueue::Node*);
+		void remove_thread_from_block_queue(SchedulerQueue::Node*);

 	private:
-		SchedulerThreadNode* m_block_chain { nullptr };
+		SchedulerQueue::Node* m_block_chain { nullptr };
 		SpinLock m_lock;

 		friend class Scheduler;
@@ -12,7 +12,7 @@ namespace Kernel
 	class HPET final : public Timer, public Interruptable
 	{
 	public:
-		static BAN::ErrorOr<BAN::UniqPtr<HPET>> create();
+		static BAN::ErrorOr<BAN::UniqPtr<HPET>> create(bool force_pic);
 		~HPET();

 		virtual uint64_t ms_since_boot() const override;
@@ -26,7 +26,7 @@ namespace Kernel

 	private:
 		HPET() = default;
-		BAN::ErrorOr<void> initialize();
+		BAN::ErrorOr<void> initialize(bool force_pic);

 		volatile HPETRegisters& registers();
 		const volatile HPETRegisters& registers() const;
@@ -2,7 +2,6 @@

 #include <BAN/UniqPtr.h>
 #include <BAN/Vector.h>
-#include <kernel/Memory/DMARegion.h>
 #include <kernel/Timer/RTC.h>

 #include <time.h>
@@ -32,14 +31,7 @@ namespace Kernel
 	class SystemTimer : public Timer
 	{
 	public:
-		struct TSCInfo
-		{
-			int8_t shift;
-			uint32_t mult;
-		};
-
-	public:
-		static void initialize();
+		static void initialize(bool force_pic);
 		static SystemTimer& get();
 		static bool is_initialized();

@@ -52,60 +44,29 @@ namespace Kernel
 		virtual bool pre_scheduler_sleep_needs_lock() const override;
 		virtual void pre_scheduler_sleep_ns(uint64_t) override;

-		void sleep_for_ns(uint64_t timeout_ns) const;
-		void sleep_until_ns(uint64_t waketime_ns) const;
-
-		void sleep_for_ms(uint64_t timeout_ms) const
-		{
-			ASSERT(!BAN::Math::will_multiplication_overflow<uint64_t>(timeout_ms, 1'000'000));
-			return sleep_for_ns(timeout_ms * 1'000'000);
-		}
-		void sleep_until_ms(uint64_t waketime_ms) const
-		{
-			ASSERT(!BAN::Math::will_multiplication_overflow<uint64_t>(waketime_ms, 1'000'000));
-			return sleep_until_ns(waketime_ms * 1'000'000);
-		}
+		void sleep_ms(uint64_t ms) const { ASSERT(!BAN::Math::will_multiplication_overflow<uint64_t>(ms, 1'000'000)); return sleep_ns(ms * 1'000'000); }
+		void sleep_ns(uint64_t ns) const;

 		void dont_invoke_scheduler() { m_timer->m_should_invoke_scheduler = false; }

-		void update_tsc();
-		TSCInfo tsc_info() const;
-
-		uint64_t ns_since_boot_no_tsc() const { return m_timer->ns_since_boot(); }
+		void update_tsc() const;
+		uint64_t ns_since_boot_no_tsc() const;

 		timespec real_time() const;

 	private:
 		SystemTimer() = default;

-		void initialize_timers();
+		void initialize_timers(bool force_pic);

-		void initialize_invariant_tsc();
-		void initialize_pvclock();
+		uint64_t get_tsc_frequency() const;

 	private:
-		enum class TSCType
-		{
-			None,
-			Invariant,
-			PVClock,
-		};
-
 		uint64_t m_boot_time { 0 };
 		BAN::UniqPtr<RTC> m_rtc;
 		BAN::UniqPtr<Timer> m_timer;
-
-		TSCType m_tsc_type = TSCType::None;
-
-		union {
-			struct {
-				int8_t shift;
-				uint32_t mult;
-			} invariant;
-		} m_tsc_info;
-
-		BAN::UniqPtr<DMARegion> m_tsc_page;
-		uint64_t m_tsc_update_ns { 0 };
+		bool m_has_invariant_tsc { false };
+		mutable uint32_t m_timer_ticks { 0 };
 	};

 }
@@ -30,7 +30,6 @@ namespace Kernel
 			Hub                        = 0x09,
 			BillboardDeviceClass       = 0x11,
 			DiagnosticDevice           = 0xDC,
-			WirelessController         = 0xE0,
 			Miscellaneous              = 0xEF,
 			VendorSpecific             = 0xFF,
 		};
@@ -23,8 +23,6 @@ namespace Kernel

 		virtual void handle_stall(uint8_t endpoint_id) = 0;
 		virtual void handle_input_data(size_t byte_count, uint8_t endpoint_id) = 0;
-
-		virtual bool is_hid_driver() const { return false; }
 	};

 	class USBDevice
@@ -64,12 +62,6 @@ namespace Kernel
 			uint8_t tt_think_time;
 		};

-		struct HIDInfo
-		{
-			BAN::Atomic<uint32_t> led_mask { 0 };
-			BAN::Vector<USBClassDriver*> led_controls;
-		};
-
 	public:
 		USBDevice(USBController& controller, USB::SpeedClass speed_class, uint8_t depth)
 			: m_controller(controller)
@@ -100,8 +92,6 @@ namespace Kernel
 		void register_hub_to_init() { m_controller.register_hub_to_init(m_depth + 1); };
 		void mark_hub_init_done() { m_controller.mark_hub_init_done(m_depth + 1); };

-		void update_led_mask(uint32_t led_mask);
-
 	protected:
 		void handle_stall(uint8_t endpoint_id);
 		void handle_input_data(size_t byte_count, uint8_t endpoint_id);
@@ -122,7 +112,6 @@ namespace Kernel
 		BAN::UniqPtr<DMARegion> m_dma_buffer;

 		BAN::Vector<BAN::UniqPtr<USBClassDriver>> m_class_drivers;
-		HIDInfo m_hid_info;
 	};

 }
@@ -74,7 +74,6 @@ namespace Kernel
 		struct DeviceReport
 		{
 			BAN::Vector<USBHID::Report> inputs;
-			BAN::Vector<USBHID::Report> outputs;
 			BAN::RefPtr<USBHIDDevice> device;
 		};

@@ -82,43 +81,27 @@ namespace Kernel
 		void handle_stall(uint8_t endpoint_id) override;
 		void handle_input_data(size_t byte_count, uint8_t endpoint_id) override;

-		bool is_hid_driver() const override { return true; }
-
 		USBDevice& device() { return m_device; }
 		const USBDevice::InterfaceDescriptor& interface() const { return m_interface; }

-		bool has_led_control() const { return !m_led_controls.empty(); }
-		void set_leds(uint32_t led_mask);
-
 	private:
 		USBHIDDriver(USBDevice&, const USBDevice::InterfaceDescriptor&);
 		~USBHIDDriver();

 		BAN::ErrorOr<void> initialize() override;

-		BAN::ErrorOr<void> initializes_device_reports(const BAN::Vector<USBHID::Collection>&);
-
-	private:
-		struct LEDControl
-		{
-			DeviceReport* report;
-			uint32_t report_id;
-			uint32_t report_bits;
-		};
+		BAN::ErrorOr<BAN::Vector<DeviceReport>> initializes_device_reports(const BAN::Vector<USBHID::Collection>&);

 	private:
 		USBDevice& m_device;
 		USBDevice::InterfaceDescriptor m_interface;

 		bool m_uses_report_id { false };
-		BAN::Vector<DeviceReport> m_device_reports;
+		BAN::Vector<DeviceReport> m_device_inputs;

 		uint8_t m_data_endpoint_id = 0;
 		BAN::UniqPtr<DMARegion> m_data_buffer;

-		BAN::Vector<LEDControl> m_led_controls;
-		BAN::UniqPtr<DMARegion> m_led_region;
-
 		friend class BAN::UniqPtr<USBHIDDriver>;
 	};

@@ -34,7 +34,7 @@ namespace Kernel
 		BAN::ErrorOr<size_t> read_impl(off_t, BAN::ByteSpan) override;
 		bool can_read_impl() const override { return true; }

-		BAN::ErrorOr<long> ioctl_impl(unsigned long request, void* arg) override;
+		BAN::ErrorOr<long> ioctl_impl(int request, void* arg) override;

 	private:
 		USBJoystick(USBHIDDriver&);
@@ -11,6 +11,8 @@ namespace Kernel
 		BAN_NON_MOVABLE(USBKeyboard);

 	public:
+		BAN::ErrorOr<void> initialize() override;
+
 		void start_report() override;
 		void stop_report() override;

@@ -21,9 +23,12 @@ namespace Kernel
 		void update() override;

 	private:
-		USBKeyboard(USBHIDDriver& driver);
+		USBKeyboard(USBHIDDriver& driver, BAN::Vector<USBHID::Report>&& outputs);
 		~USBKeyboard() = default;

+		void set_leds(uint16_t mask);
+		void set_leds(uint8_t report_id, uint16_t mask);
+
 	private:
 		USBHIDDriver& m_driver;

@@ -33,7 +38,11 @@ namespace Kernel
 		BAN::Array<bool, 0x100> m_keyboard_state      { false };
 		BAN::Array<bool, 0x100> m_keyboard_state_temp { false };
 		uint16_t m_toggle_mask { 0 };
+
 		uint16_t m_led_mask { 0 };
+		BAN::UniqPtr<DMARegion> m_led_region;
+
+		BAN::Vector<USBHID::Report> m_outputs;

 		BAN::Optional<uint8_t> m_repeat_scancode;
 		uint8_t m_repeat_modifier { 0 };
@@ -1,5 +1,6 @@
 #pragma once

+#include <kernel/Process.h>
 #include <kernel/USB/Device.h>

 namespace Kernel
--- a/Show More
+++ b/Show More