SchOS/kernel/fs/pipe.c

#include "core/types.h"
#include "core/defs.h"
#include "core/param.h"
#include "arch/mmu.h"
#include "core/proc.h"
#include "fs/fs.h"
#include "core/spinlock.h"
#include "core/sleeplock.h"
#include "fs/file.h"
#include "core/kmem.h"
#include "uapi/posix.h"
#include "uapi/errno.h"

#define PIPESIZE 512

struct pipe {
  struct spinlock lock;
  char data[PIPESIZE];
  uint nread;     // number of bytes read
  uint nwrite;    // number of bytes written
  int readopen;   // read fd is still open
  int writeopen;  // write fd is still open
};

// A pipe is about 560 bytes and used to come from kalloc(), which is a whole
// 4096-byte page -- so every `|` in a shell command burned three and a half
// kilobytes it never touched. This is what kmem_cache exists for, and the
// cache is created on first use rather than at boot so a kernel that never
// opens a pipe holds no page for one.
static struct kmem_cache *pipe_cache;

int
pipealloc(struct file **f0, struct file **f1)
{
  struct pipe *p;

  p = 0;
  *f0 = *f1 = 0;
  if((*f0 = filealloc()) == 0 || (*f1 = filealloc()) == 0)
    goto bad;
  if(!pipe_cache && !(pipe_cache = kmem_cache_create("pipe", sizeof(*p))))
    goto bad;
  if((p = kmem_cache_alloc(pipe_cache)) == 0)
    goto bad;
  p->readopen = 1;
  p->writeopen = 1;
  p->nwrite = 0;
  p->nread = 0;
  initlock(&p->lock, "pipe");
  (*f0)->type = FD_PIPE;
  (*f0)->readable = 1;
  (*f0)->writable = 0;
  (*f0)->pipe = p;
  (*f1)->type = FD_PIPE;
  (*f1)->readable = 0;
  (*f1)->writable = 1;
  (*f1)->pipe = p;
  return 0;

//PAGEBREAK: 20
 bad:
  if(p)
    kmem_cache_free(pipe_cache, p);
  if(*f0)
    fileclose(*f0);
  if(*f1)
    fileclose(*f1);
  return -1;
}

void
pipeclose(struct pipe *p, int writable)
{
  acquire(&p->lock);
  if(writable){
    p->writeopen = 0;
    wakeup(&p->nread);
  } else {
    p->readopen = 0;
    wakeup(&p->nwrite);
  }
  if(p->readopen == 0 && p->writeopen == 0){
    release(&p->lock);
    kmem_cache_free(pipe_cache, p);
  } else
    release(&p->lock);
}

//PAGEBREAK: 40
int
pipewrite(struct pipe *p, char *addr, int n)
{
  int i;

  acquire(&p->lock);

  // Writing to a pipe nobody is reading is SIGPIPE and EPIPE, in that order.
  //
  // This returned a bare -1 with no signal and no errno, so `yes | head -2`
  // came back with whatever errno happened to be lying around -- "Invalid
  // argument" -- instead of quietly ending the way every shell pipeline is
  // built to. Checked up front as well as in the blocking loop below: the
  // common case is that head has already exited by the time the next write
  // arrives, and the pipe is nowhere near full.
  if(p->readopen == 0){
    release(&p->lock);
    sigsend(myproc()->pid, SIGPIPE);
    return -EPIPE;
  }

  for(i = 0; i < n; i++){
    while(p->nwrite == p->nread + PIPESIZE){  //DOC: pipewrite-full
      if(p->readopen == 0){
        release(&p->lock);
        sigsend(myproc()->pid, SIGPIPE);
        return i > 0 ? i : -EPIPE;    // a short write is still a write
      }
      if(myproc()->killed){
        release(&p->lock);
        return -1;
      }
      wakeup(&p->nread);
      sleep(&p->nwrite, &p->lock);  //DOC: pipewrite-sleep
    }
    p->data[p->nwrite++ % PIPESIZE] = addr[i];
  }
  wakeup(&p->nread);  //DOC: pipewrite-wakeup1
  release(&p->lock);
  return n;
}

int
piperead(struct pipe *p, char *addr, int n)
{
  int i;

  acquire(&p->lock);
  while(p->nread == p->nwrite && p->writeopen){  //DOC: pipe-empty
    if(myproc()->killed){
      release(&p->lock);
      return -1;
    }
    sleep(&p->nread, &p->lock); //DOC: piperead-sleep
  }
  for(i = 0; i < n; i++){  //DOC: piperead-copy
    if(p->nread == p->nwrite)
      break;
    addr[i] = p->data[p->nread++ % PIPESIZE];
  }
  wakeup(&p->nwrite);  //DOC: piperead-wakeup
  release(&p->lock);
  return i;
}

// Readiness for poll(2)/select(2). Reports state, doesn't block.
int
pipe_poll(struct pipe *p, int readable, int writable)
{
  int rev = 0;

  acquire(&p->lock);
  if(readable){
    if(p->nread != p->nwrite)
      rev |= POLLIN;
    if(p->writeopen == 0)
      rev |= POLLHUP;
  }
  if(writable){
    if(p->readopen == 0)
      rev |= POLLERR;
    else if(p->nwrite < p->nread + PIPESIZE)
      rev |= POLLOUT;
  }
  release(&p->lock);
  return rev;
}