#include <stdio.h>
#include <sys/time.h>
#include <time.h>

#define MAX_IOPORTS 4096
typedef void (IOPortWriteFunc)(void *opaque, unsigned int address, unsigned int data);

typedef struct IDEState
{
    void*           dummy;
    void*           curr;
    char*           data_ptr;
    char*           data_end;
} IDEState;

typedef struct PIOInfo {
    void*            dummy;
    IOPortWriteFunc* write;
    void*            opaque;
    char*            data_ptr;
    char*            data_end;
} PIOInfo;

typedef struct CPUState
{
    void*            dummy;
    PIOInfo*         info;
} CPUState;

void *ioport_opaque[MAX_IOPORTS];
IOPortWriteFunc *ioport_write_table[3][MAX_IOPORTS];
PIOInfo*    pio_info_table[MAX_IOPORTS];

unsigned int fake = 0;
int testIdx = 23;
int testCnt = 10;

void writeFake(void *opaque, unsigned int addr, unsigned int data)
{
    fake ^= data;
}

void writeLoop(void *opaque, unsigned int addr, unsigned int data)
{
    IDEState *s = ((IDEState *)opaque)->curr;
    char *p;

    p = s->data_ptr;
    *(unsigned int *)p = data;
    p += 4;
    s->data_ptr = p;
    if (p >= s->data_end)
        printf("oops");
}

void cpu_outl(CPUState *env, int addr, int val)
{
    // the if overhead is 7 ns (2.4 GHz P4) ...
    //if(ioport_opaque[addr] == 0)
    ioport_write_table[2][addr](ioport_opaque[addr], addr, val);
}

void cpu_outx(CPUState *env, int addr, int val)
{
    PIOInfo *i = pio_info_table[addr];
    if(i->data_ptr >= i->data_end)
       i->write(i->opaque, addr, val);
    else {
        *(int *)(i->data_ptr) = val;
        i->data_ptr += 4;
    }
}

int main(int argc, char** argv)
{
    struct timeval     tss, tse;
    CPUState    env;
    IDEState    ide;
    PIOInfo     pio;
    int         irun;
    char        buff[64];

    // TEST 1

    ioport_write_table[2][testIdx] = writeFake;
    ioport_opaque[testIdx] = 0;
    printf("start 1\n");
    gettimeofday(&tss, NULL);

    for(irun=0; irun < 1000*1000*testCnt; irun++) {
        cpu_outl(&env, testIdx, irun);
        cpu_outl(&env, testIdx, irun);
        cpu_outl(&env, testIdx, irun);
        cpu_outl(&env, testIdx, irun);
        cpu_outl(&env, testIdx, irun);

        cpu_outl(&env, testIdx, irun);
        cpu_outl(&env, testIdx, irun);
        cpu_outl(&env, testIdx, irun);
        cpu_outl(&env, testIdx, irun);
        cpu_outl(&env, testIdx, irun);
    }

    gettimeofday(&tse, NULL);
    tse.tv_sec -= tss.tv_sec;
    tse.tv_usec -= tss.tv_usec;
    printf("done (%.6g ns/call)\n", ((double)(tse.tv_usec/1000 + tse.tv_sec*1000))/testCnt);

    // TEST 2

    ioport_write_table[2][testIdx] = writeLoop;
    ioport_opaque[testIdx] = &ide;
    ide.curr = &ide;
    printf("start 2\n");
    gettimeofday(&tss, NULL);

    for(irun=0; irun < 1000*1000*testCnt; irun++) {
        ide.data_ptr = buff;
        ide.data_end = buff + sizeof(buff);

        cpu_outl(&env, testIdx, irun);
        cpu_outl(&env, testIdx, irun);
        cpu_outl(&env, testIdx, irun);
        cpu_outl(&env, testIdx, irun);
        cpu_outl(&env, testIdx, irun);

        cpu_outl(&env, testIdx, irun);
        cpu_outl(&env, testIdx, irun);
        cpu_outl(&env, testIdx, irun);
        cpu_outl(&env, testIdx, irun);
        cpu_outl(&env, testIdx, irun);
    }

    gettimeofday(&tse, NULL);
    tse.tv_sec -= tss.tv_sec;
    tse.tv_usec -= tss.tv_usec;
    printf("done (%.6g ns/call)\n", ((double)(tse.tv_usec/1000 + tse.tv_sec*1000))/testCnt);

    // TEST 3

    pio_info_table[testIdx] = &pio;
    pio.write  = writeFake;
    pio.opaque = &ide;
    printf("start 3\n");
    gettimeofday(&tss, NULL);

    for(irun=0; irun < 1000*1000*testCnt; irun++) {
        pio.data_ptr = buff + sizeof(buff);
        pio.data_end = 0;

        cpu_outx(&env, testIdx, irun);
        cpu_outx(&env, testIdx, irun);
        cpu_outx(&env, testIdx, irun);
        cpu_outx(&env, testIdx, irun);
        cpu_outx(&env, testIdx, irun);

        cpu_outx(&env, testIdx, irun);
        cpu_outx(&env, testIdx, irun);
        cpu_outx(&env, testIdx, irun);
        cpu_outx(&env, testIdx, irun);
        cpu_outx(&env, testIdx, irun);
    }

    gettimeofday(&tse, NULL);
    tse.tv_sec -= tss.tv_sec;
    tse.tv_usec -= tss.tv_usec;
    printf("done (%.6g ns/call)\n", ((double)(tse.tv_usec/1000 + tse.tv_sec*1000))/testCnt);

    // TEST 4

    pio.write  = writeFake;
    pio.opaque = &ide;
    printf("start 4\n");
    gettimeofday(&tss, NULL);

    for(irun=0; irun < 1000*1000*testCnt; irun++) {
        pio.data_ptr = buff;
        pio.data_end = buff + sizeof(buff);

        cpu_outx(&env, testIdx, irun);
        cpu_outx(&env, testIdx, irun);
        cpu_outx(&env, testIdx, irun);
        cpu_outx(&env, testIdx, irun);
        cpu_outx(&env, testIdx, irun);

        cpu_outx(&env, testIdx, irun);
        cpu_outx(&env, testIdx, irun);
        cpu_outx(&env, testIdx, irun);
        cpu_outx(&env, testIdx, irun);
        cpu_outx(&env, testIdx, irun);
    }

    gettimeofday(&tse, NULL);
    tse.tv_sec -= tss.tv_sec;
    tse.tv_usec -= tss.tv_usec;
    printf("done (%.6g ns/call)\n", ((double)(tse.tv_usec/1000 + tse.tv_sec*1000))/testCnt);

    return 0;
}