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"

// 64 KB, as on Linux, in pages taken the first time each is written.
//
// It was 512 bytes in the struct. That is xv6's size, and it made every pipe a
// handoff per half kilobyte: busybox's wget does TLS in a helper process that
// talks to it over pipes, a TLS record is 16 KB, and an HTTPS download that
// should have taken nine seconds was still going after a minute and a half. A
// shell pipeline that only ever moves a line still costs one page.
#define PIPESIZE   65536
#define PIPE_PAGES (PIPESIZE / PGSIZE)
#define PIPE_BUF   4096   // writes up to this size are not interleaved

struct pipe {
  struct spinlock lock;
  char *page[PIPE_PAGES];
  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
};

// The struct is small and comes from a cache; the buffer is pages. The cache
// is created on first use so a kernel that never opens a pipe holds no page
// for one.
static struct kmem_cache *pipe_cache;

static void
pipe_free(struct pipe *p)
{
  for(int i = 0; i < PIPE_PAGES; i++)
    if(p->page[i])
      kfree(p->page[i]);
  kmem_cache_free(pipe_cache, p);
}

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;
  memset(p->page, 0, sizeof(p->page));
  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;
  (*f1)->ino = (*f0)->ino;     // one pipe, as /proc/<pid>/fd names it
  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);
    pipe_free(p);
  } else
    release(&p->lock);
  poll_kick();             // a poller sees the hangup now, not at the tick
}

//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;
  }

  // A write of PIPE_BUF or less goes in whole or waits for room, so two
  // writers' records never interleave; a larger one goes in as room appears.
  uint want_room = (n <= PIPE_BUF) ? (uint)n : 1;
  i = 0;
  while(i < n){
    while(PIPESIZE - (p->nwrite - p->nread) < want_room){  //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);
      release(&p->lock);
      poll_kick();
      acquire(&p->lock);
      if(PIPESIZE - (p->nwrite - p->nread) >= want_room)
        break;
      sleep(&p->nwrite, &p->lock);  //DOC: pipewrite-sleep
    }
    // One run: up to the end of this page, of what is left, of the room.
    uint off  = p->nwrite % PIPESIZE;
    uint run  = PGSIZE - off % PGSIZE;
    uint room = PIPESIZE - (p->nwrite - p->nread);
    if(run > (uint)(n - i)) run = (uint)(n - i);
    if(run > room) run = room;
    char **pg = &p->page[off / PGSIZE];
    if(*pg == 0 && (*pg = kalloc()) == 0){
      release(&p->lock);
      return i > 0 ? i : -ENOMEM;
    }
    memmove(*pg + off % PGSIZE, addr + i, run);
    p->nwrite += run;
    i += run;
    want_room = 1;
  }
  wakeup(&p->nread);  //DOC: pipewrite-wakeup1
  release(&p->lock);
  poll_kick();
  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;
    }
    if(sig_attention(myproc())){     // stopped, or a handler wants to run
      release(&p->lock);
      int e = sig_blocking_check();
      if(e)
        return e;
      acquire(&p->lock);
      continue;
    }
    sleep(&p->nread, &p->lock); //DOC: piperead-sleep
  }
  i = 0;
  while(i < n && p->nread != p->nwrite){  //DOC: piperead-copy
    uint off = p->nread % PIPESIZE;
    uint run = PGSIZE - off % PGSIZE;
    if(run > (uint)(n - i)) run = (uint)(n - i);
    if(run > p->nwrite - p->nread) run = p->nwrite - p->nread;
    memmove(addr + i, p->page[off / PGSIZE] + off % PGSIZE, run);
    p->nread += run;
    i += run;
  }
  wakeup(&p->nwrite);  //DOC: piperead-wakeup
  release(&p->lock);
  poll_kick();         // a writer polling for room
  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(PIPESIZE - (p->nwrite - p->nread) >= PIPE_BUF)
      rev |= POLLOUT;    // room for a whole PIPE_BUF write, as on Linux
  }
  release(&p->lock);
  return rev;
}

// Bytes waiting to be read, for FIONREAD.
int
pipe_avail(struct pipe *p)
{
  acquire(&p->lock);
  int n = (int)(p->nwrite - p->nread);
  release(&p->lock);
  return n;
}