runtime, internal/task: refactor to simplify stack switching

The Cortex-M target isn't much changed, but much of the logic for the
AVR stack switcher that was previously in assembly has now been moved to
Go to make it more maintainable and in fact smaller in code size. Three
functions (tinygo_getCurrentStackPointer, tinygo_switchToTask,
tinygo_switchToScheduler) have been changed to one: tinygo_swapTask.

This reduction in assembly code should make the code more maintainable
and should make it easier to port stack switching to other
architectures.

I've also moved the assembly files to src/internal/task, which seems
like a more appropriate location to me.
This commit is contained in:
Ayke van Laethem
2020-09-24 23:56:48 +02:00
committed by Ron Evans
parent bb58783158
commit abb09e869e
9 changed files with 169 additions and 268 deletions
-189
View File
@@ -1,189 +0,0 @@
.section .bss.tinygo_systemStack
.global tinygo_systemStack
.type tinygo_systemStack, %object
tinygo_systemStack:
.short 0
.section .text.tinygo_startTask
.global tinygo_startTask
.type tinygo_startTask, %function
tinygo_startTask:
// Small assembly stub for starting a goroutine. This is already run on the
// new stack, with the callee-saved registers already loaded.
// Most importantly, r2r3 contain the pc of the to-be-started function and
// r4r5 contain the only argument it is given. Multiple arguments are packed
// into one by storing them in a new allocation.
// Set the first argument of the goroutine start wrapper, which contains all
// the arguments.
movw r24, r4
// Branch to the "goroutine start" function. Note that the Z register is
// call-clobbered, so does not need to be restored after use.
movw Z, r2
icall
// After return, exit this goroutine. This is a tail call.
#if __AVR_ARCH__ == 2 || __AVR_ARCH__ == 25
// Small memory devices (8kB flash) that do not have the long call
// instruction availble will need to use rcall instead.
// Note that they will probably not be able to run more than the main
// goroutine anyway, but this file is compiled for all AVRs so it needs to
// compile at least.
rcall tinygo_pause
#else
// Other devices can (and must) use the regular call instruction.
call tinygo_pause
#endif
// Get the system stack pointer, independent of whether we're currently on the
// system stack or a task stack.
.global tinygo_getSystemStackPointer
.type tinygo_getSystemStackPointer, %function
tinygo_getSystemStackPointer:
// Load system stack pointer.
lds r24, tinygo_systemStack
lds r25, tinygo_systemStack+1
// Compare against 0.
cp r24, r1
cpc r25, r1
// Branch (and then return) if tinygo_systemStack has a non-zero value.
brne 1f
// tinygo_systemStack is zero, so return the current stack pointer.
in r24, 0x3d; SPL
in r25, 0x3e; SPH
1:
ret
.global tinygo_switchToTask
.type tinygo_switchToTask, %function
tinygo_switchToTask:
// The sp parameter is the only parameter, so it will take up r24:r25.
// r24:r25 = sp uintptr
// Save all call-saved registers:
// https://gcc.gnu.org/wiki/avr-gcc#Call-Saved_Registers
push r29 // Y
push r28 // Y
push r17
push r16
push r15
push r14
push r13
push r12
push r11
push r10
push r9
push r8
push r7
push r6
push r5
push r4
push r3
push r2
// Save the system stack pointer in a global.
in r2, 0x3d; SPL
in r3, 0x3e; SPH
sts tinygo_systemStack+0, r2
sts tinygo_systemStack+1, r3
// Switch to the task stack pointer.
out 0x3d, r24; SPL
out 0x3e, r25; SPH
// Load saved register from the task stack.
pop r2
pop r3
pop r4
pop r5
pop r6
pop r7
pop r8
pop r9
pop r10
pop r11
pop r12
pop r13
pop r14
pop r15
pop r16
pop r17
pop r28 // Y
pop r29 // Y
// Return into the new task, as if tinygo_switchToScheduler was a regular
// call.
ret
.global tinygo_switchToScheduler
.type tinygo_switchToScheduler, %function
tinygo_switchToScheduler:
// The sp parameter is the only parameter, so it will take up r24:r25.
// r24:r25 = sp *uintptr
// Save all call-saved registers on the task stack:
// https://gcc.gnu.org/wiki/avr-gcc#Call-Saved_Registers
push r29 // Y
push r28 // Y
push r17
push r16
push r15
push r14
push r13
push r12
push r11
push r10
push r9
push r8
push r7
push r6
push r5
push r4
push r3
push r2
// Save the task stack.
in r2, 0x3d; SPL
in r3, 0x3e; SPH
movw Y, r24
std Y+0, r2
std Y+1, r3
// Switch to the system stack.
lds r2, tinygo_systemStack
lds r3, tinygo_systemStack+1
out 0x3d, r2; SPL
out 0x3e, r3; SPH
// Clear tinygo_systemStack to make sure tinygo_getSystemStackPointer knows
// which pointer to return.
sts tinygo_systemStack+0, r1
sts tinygo_systemStack+1, r1
// Load saved register from the system stack.
pop r2
pop r3
pop r4
pop r5
pop r6
pop r7
pop r8
pop r9
pop r10
pop r11
pop r12
pop r13
pop r14
pop r15
pop r16
pop r17
pop r28 // Y
pop r29 // Y
// Return into the scheduler, as if tinygo_switchToTask was a regular call.
ret
-138
View File
@@ -1,138 +0,0 @@
// Only generate .debug_frame, don't generate .eh_frame.
.cfi_sections .debug_frame
.section .text.tinygo_startTask
.global tinygo_startTask
.type tinygo_startTask, %function
tinygo_startTask:
.cfi_startproc
// Small assembly stub for starting a goroutine. This is already run on the
// new stack, with the callee-saved registers already loaded.
// Most importantly, r4 contains the pc of the to-be-started function and r5
// contains the only argument it is given. Multiple arguments are packed
// into one by storing them in a new allocation.
// Indicate to the unwinder that there is nothing to unwind, this is the
// root frame. It avoids the following (bogus) error message in GDB:
// Backtrace stopped: previous frame identical to this frame (corrupt stack?)
.cfi_undefined lr
// Set the first argument of the goroutine start wrapper, which contains all
// the arguments.
mov r0, r5
// Branch to the "goroutine start" function. By using blx instead of bx,
// we'll return here instead of tail calling.
blx r4
// After return, exit this goroutine. This is a tail call.
bl tinygo_pause
.cfi_endproc
.size tinygo_startTask, .-tinygo_startTask
.section .text.tinygo_getSystemStackPointer
.global tinygo_getSystemStackPointer
.type tinygo_getSystemStackPointer, %function
tinygo_getSystemStackPointer:
.cfi_startproc
// The system stack pointer is always stored in the MSP register.
mrs r0, MSP
bx lr
.cfi_endproc
.size tinygo_getSystemStackPointer, .-tinygo_getSystemStackPointer
.section .text.tinygo_switchToScheduler
.global tinygo_switchToScheduler
.type tinygo_switchToScheduler, %function
tinygo_switchToScheduler:
.cfi_startproc
// r0 = sp *uintptr
// Currently on the task stack (SP=PSP). We need to store the position on
// the stack where the in-use registers will be stored.
mov r1, sp
subs r1, #36
str r1, [r0]
b tinygo_swapTask
.cfi_endproc
.size tinygo_switchToScheduler, .-tinygo_switchToScheduler
.section .text.tinygo_switchToTask
.global tinygo_switchToTask
.type tinygo_switchToTask, %function
tinygo_switchToTask:
.cfi_startproc
// r0 = sp uintptr
// Currently on the scheduler stack (SP=MSP). We'll have to update the PSP,
// and then we can invoke swapTask.
msr PSP, r0
b.n tinygo_swapTask
.cfi_endproc
.size tinygo_switchToTask, .-tinygo_switchToTask
.section .text.tinygo_swapTask
.global tinygo_swapTask
.type tinygo_swapTask, %function
tinygo_swapTask:
.cfi_startproc
// This function stores the current register state to the stack, switches to
// the other stack (MSP/PSP), and loads the register state from the other
// stack. Apart from saving and restoring all relevant callee-saved
// registers, it also ends with branching to the last program counter (saved
// as the lr register, to follow the ARM calling convention).
// On pre-Thumb2 CPUs (Cortex-M0 in particular), registers r8-r15 cannot be
// used directly. Only very few operations work on them, such as mov. That's
// why the higher register values are first stored in the temporary register
// r3 when loading/storing them.
// It is possible to reduce the swapTask by two instructions (~2 cycles) on
// Cortex-M0 by reordering the layout of the pushed registers from {r4-r11,
// lr} to {r8-r11, r4-r8, lr}. However, that also requires a change on the
// Go side (depending on thumb1/thumb2!) and so is not really worth the
// complexity.
// Store state to old task. It saves the lr instead of the pc, because that
// will be the pc after returning back to the old task (in a different
// invocation of swapTask).
#if defined(__thumb2__)
push {r4-r11, lr}
.cfi_def_cfa_offset 9*4
#else
mov r0, r8
mov r1, r9
mov r2, r10
mov r3, r11
push {r0-r3, lr}
.cfi_def_cfa_offset 5*4
push {r4-r7}
.cfi_def_cfa_offset 9*4
#endif
// Switch the stack. This could either switch from PSP to MSP, or from MSP
// to PSP. By using an XOR (eor), it will just switch to the other stack.
mrs r0, CONTROL // load CONTROL register
movs r3, #2
eors r0, r0, r3 // flip the SPSEL (active stack pointer) bit
msr CONTROL, r0 // store CONTROL register
isb // required to flush the pipeline
// Load state from new task and branch to the previous position in the
// program.
#if defined(__thumb2__)
pop {r4-r11, pc}
#else
pop {r4-r7}
.cfi_def_cfa_offset 5*9
pop {r0-r3}
.cfi_def_cfa_offset 1*9
mov r8, r0
mov r9, r1
mov r10, r2
mov r11, r3
pop {pc}
#endif
.cfi_endproc
.size tinygo_swapTask, .-tinygo_swapTask
+11 -2
View File
@@ -2,7 +2,16 @@
package runtime
import "internal/task"
// getSystemStackPointer returns the current stack pointer of the system stack.
// This is not necessarily the same as the current stack pointer.
//export tinygo_getSystemStackPointer
func getSystemStackPointer() uintptr
func getSystemStackPointer() uintptr {
// TODO: this always returns the correct stack on Cortex-M, so don't bother
// comparing against 0.
sp := task.SystemStack()
if sp == 0 {
sp = getCurrentStackPointer()
}
return sp
}