start to stack switching single processes

make

@@ -98,10 +98,13 @@ def compile():
             f.replace('src', 'build').replace('.cc', '.o'),
             CXX=CXX
         ))
-    Run('{CC} -c src/asm.s -o build/asm.o'.format(
-        CC=CC
-    ))
-    Run('{CC} -c src/asm_snippets.s -o build/asm_snippets.o'.format(
+    # Run('{CC} -c src/asm.s -o build/asm.o'.format(
+    #     CC=CC
+    # ))
+    # Run('{CC} -c src/asm_snippets.s -o build/asm_snippets.o'.format(
+    #     CC=CC
+    # ))
+    Run('{CC} -c src/asm_interface.s -o build/asm_snippets.o'.format(
         CC=CC
     ))
     after()

src/asm_context_switch.s

@@ -0,0 +1,98 @@
+/*
+            Copyright Oliver Kowalke 2009.
+   Distributed under the Boost Software License, Version 1.0.
+      (See accompanying file LICENSE_1_0.txt or copy at
+            http://www.boost.org/LICENSE_1_0.txt)
+*/
+
+/****************************************************************************************
+ *                                                                                      *
+ *  ----------------------------------------------------------------------------------  *
+ *  |    0    |    1    |    2    |    3    |    4     |    5    |    6    |    7    |  *
+ *  ----------------------------------------------------------------------------------  *
+ *  |   0x0   |   0x4   |   0x8   |   0xc   |   0x10   |   0x14  |   0x18  |   0x1c  |  *
+ *  ----------------------------------------------------------------------------------  *
+ *  | fc_mxcsr|fc_x87_cw|        R12        |         R13        |        R14        |  *
+ *  ----------------------------------------------------------------------------------  *
+ *  ----------------------------------------------------------------------------------  *
+ *  |    8    |    9    |   10    |   11    |    12    |    13   |    14   |    15   |  *
+ *  ----------------------------------------------------------------------------------  *
+ *  |   0x20  |   0x24  |   0x28  |  0x2c   |   0x30   |   0x34  |   0x38  |   0x3c  |  *
+ *  ----------------------------------------------------------------------------------  *
+ *  |        R15        |        RBX        |         RBP        |        RIP        |  *
+ *  ----------------------------------------------------------------------------------  *
+ *  ----------------------------------------------------------------------------------  *
+ *  |    16   |   17    |                                                            |  *
+ *  ----------------------------------------------------------------------------------  *
+ *  |   0x40  |   0x44  |                                                            |  *
+ *  ----------------------------------------------------------------------------------  *
+ *  |        EXIT       |                                                            |  *
+ *  ----------------------------------------------------------------------------------  *
+ *                                                                                      *
+ ****************************************************************************************/
+
+.text
+.globl jump_fcontext
+.type jump_fcontext,@function
+.align 16
+jump_fcontext:
+    pushq  %rbp  /* save RBP */
+    pushq  %rbx  /* save RBX */
+    pushq  %r15  /* save R15 */
+    pushq  %r14  /* save R14 */
+    pushq  %r13  /* save R13 */
+    pushq  %r12  /* save R12 */
+
+    /* prepare stack for FPU */
+    leaq  -0x8(%rsp), %rsp
+
+    /* test for flag preserve_fpu */
+    cmp  $0, %rcx
+    je  1f
+
+    /* save MMX control- and status-word */
+    stmxcsr  (%rsp)
+    /* save x87 control-word */
+    fnstcw   0x4(%rsp)
+
+1:
+    /* store RSP (pointing to context-data) in RDI */
+    movq  %rsp, (%rdi)
+
+    /* restore RSP (pointing to context-data) from RSI */
+    movq  %rsi, %rsp
+
+    /* test for flag preserve_fpu */
+    cmp  $0, %rcx
+    je  2f
+
+    /* restore MMX control- and status-word */
+    ldmxcsr  (%rsp)
+    /* restore x87 control-word */
+    fldcw  0x4(%rsp)
+
+2:
+    /* prepare stack for FPU */
+    leaq  0x8(%rsp), %rsp
+
+    popq  %r12  /* restrore R12 */
+    popq  %r13  /* restrore R13 */
+    popq  %r14  /* restrore R14 */
+    popq  %r15  /* restrore R15 */
+    popq  %rbx  /* restrore RBX */
+    popq  %rbp  /* restrore RBP */
+
+    /* restore return-address */
+    popq  %r8
+
+    /* use third arg as return-value after jump */
+    movq  %rdx, %rax
+    /* use third arg as first arg in context function */
+    movq  %rdx, %rdi
+
+    /* indirect jump to context */
+    jmp  *%r8
+.size jump_fcontext,.-jump_fcontext
+
+/* Mark that we don't need executable stack.  */
+.section .note.GNU-stack,"",%progbits

src/asm_interface.s

@@ -0,0 +1,147 @@
+/**
+  * argument registers:  rdi, rsi, rdx, rcx, r8, r9
+  * preserve registers: rbx, rsp, rbp, r12, r13, r14, r15
+  * scratch registers: rax, rdi, rsi, rdx, rcx, r8, r9, r10, r11
+  */
+
+  ////////////////////////////////////////////////////
+  .macro  m_push_all_regs
+  // should match the direction in sys/regs.h
+  push %r15
+  push %r14
+  push %r13
+  push %rbp
+  push %rbx
+  push %r11
+  push %r10
+  push %r9
+  push %r8
+  push %rax
+  push %rcx
+  push %rdx
+  push %rsi
+  push %rdi
+  // orig rax??
+  // push %rip (bad instruction)t
+  // push %cs (bad instruction)
+  sub $24, %rsp
+
+  //push %eflags
+  pushf
+
+  // stack pointer? ignore
+  push %rsp
+  // push %ss (bad instruction)
+  // fsbase (?)
+  // gsbase (?)
+  // push %ds (bad instruction)
+  // push %es (bad instruction)
+  sub $40, %rsp
+
+  push %fs
+  push %gs
+  .endm
+
+  //////////////////////////////////////////////////
+  .macro m_pop_all_regs
+  pop %gs
+  pop %fs
+
+  add $48, %rsp
+
+  // ignore the stack pointer
+
+  popf
+
+  add $24, %rsp
+  pop %rdi
+  pop %rsi
+  pop %rdx
+  pop %rcx
+  pop %rax
+  pop %r8
+  pop %r9
+  pop %r10
+  pop %r11
+  pop %rbx
+  pop %rbp
+  pop %r13
+  pop %r14
+  pop %r15
+  .endm
+
+
+
+  .global red_asm_push_all_regs_start
+  .global red_asm_push_all_regs_end
+red_asm_push_all_regs_start:
+  m_push_all_regs
+red_asm_push_all_regs_end:
+
+
+  .global red_asm_pop_all_regs_start
+  .global red_asm_pop_all_regs_end
+red_asm_pop_all_regs_start:
+  m_pop_all_regs
+red_asm_pop_all_regs_end:
+
+
+  .global red_asm_resume_tracer_block_start
+  .global red_asm_resume_tracer_block_end
+red_asm_resume_tracer_block_start:
+  sub $8, %rsp
+  m_push_all_regs
+  movq %rsp, %rax
+  movq $0xfafafafafafafafa, %rsp
+  movq 0(%rsp), %r12
+  movq 8(%rsp), %r13
+  movq 16(%rsp), %r14
+  movq 24(%rsp), %r15
+  movq 32(%rsp), %rbx
+  movq 40(%rsp), %rbp
+
+  movq 56(%rsp), %rsp
+
+  ret
+red_asm_resume_tracer_block_end:
+
+  .global red_asm_resume_eval_block
+red_asm_resume_eval_block:
+  movq %rsp, 56(%rdi)
+
+  movq %r12, 0(%rdi)
+  movq %r13, 8(%rdi)
+  movq %r14, 16(%rdi)
+  movq %r15, 24(%rdi)
+  movq %rbx, 32(%rdi)
+  movq %rbp, 40(%rdi)
+
+  movq %rsi, %rsp
+  m_pop_all_regs
+  ret
+
+
+  .global red_asm_return_to_block
+red_asm_return_to_block:
+  mov %rax, %rsp
+  m_pop_all_regs
+  ret
+
+  .global red_asm_start_tracing
+red_asm_start_tracing:
+  // [null (old stack pointer), method_to_call, tracer_this, new_stack]
+  sub $8, %rsp
+  m_push_all_regs
+  mov %rsp, %rdi
+  mov %rcx, %rsp
+  jmp *%rsi
+
+
+
+  .global red_asm_compile_buff_near
+red_asm_compile_buff_near:
+  ret
+
+
+// we don't need executable stack
+  .section .note.GNU-stack,"",%progbits