sock.c

Linux Kernel 2.6.9 for OMAP1710

			break;
		
		case SO_RCVBUF:
			v.val = sk->sk_rcvbuf;
			break;

		case SO_REUSEADDR:
			v.val = sk->sk_reuse;
			break;

		case SO_KEEPALIVE:
			v.val = !!sock_flag(sk, SOCK_KEEPOPEN);
			break;

		case SO_TYPE:
			v.val = sk->sk_type;		  		
			break;

		case SO_ERROR:
			v.val = -sock_error(sk);
			if(v.val==0)
				v.val = xchg(&sk->sk_err_soft, 0);
			break;

		case SO_OOBINLINE:
			v.val = !!sock_flag(sk, SOCK_URGINLINE);
			break;
	
		case SO_NO_CHECK:
			v.val = sk->sk_no_check;
			break;

		case SO_PRIORITY:
			v.val = sk->sk_priority;
			break;
		
		case SO_LINGER:	
			lv		= sizeof(v.ling);
			v.ling.l_onoff	= !!sock_flag(sk, SOCK_LINGER);
 			v.ling.l_linger	= sk->sk_lingertime / HZ;
			break;
					
		case SO_BSDCOMPAT:
			sock_warn_obsolete_bsdism("getsockopt");
			break;

		case SO_TIMESTAMP:
			v.val = sk->sk_rcvtstamp;
			break;

		case SO_RCVTIMEO:
			lv=sizeof(struct timeval);
			if (sk->sk_rcvtimeo == MAX_SCHEDULE_TIMEOUT) {
				v.tm.tv_sec = 0;
				v.tm.tv_usec = 0;
			} else {
				v.tm.tv_sec = sk->sk_rcvtimeo / HZ;
				v.tm.tv_usec = ((sk->sk_rcvtimeo % HZ) * 1000000) / HZ;
			}
			break;

		case SO_SNDTIMEO:
			lv=sizeof(struct timeval);
			if (sk->sk_sndtimeo == MAX_SCHEDULE_TIMEOUT) {
				v.tm.tv_sec = 0;
				v.tm.tv_usec = 0;
			} else {
				v.tm.tv_sec = sk->sk_sndtimeo / HZ;
				v.tm.tv_usec = ((sk->sk_sndtimeo % HZ) * 1000000) / HZ;
			}
			break;

		case SO_RCVLOWAT:
			v.val = sk->sk_rcvlowat;
			break;

		case SO_SNDLOWAT:
			v.val=1;
			break; 

		case SO_PASSCRED:
			v.val = sock->passcred;
			break;

		case SO_PEERCRED:
			if (len > sizeof(sk->sk_peercred))
				len = sizeof(sk->sk_peercred);
			if (copy_to_user(optval, &sk->sk_peercred, len))
				return -EFAULT;
			goto lenout;

		case SO_PEERNAME:
		{
			char address[128];

			if (sock->ops->getname(sock, (struct sockaddr *)address, &lv, 2))
				return -ENOTCONN;
			if (lv < len)
				return -EINVAL;
			if (copy_to_user(optval, address, len))
				return -EFAULT;
			goto lenout;
		}

		/* Dubious BSD thing... Probably nobody even uses it, but
		 * the UNIX standard wants it for whatever reason... -DaveM
		 */
		case SO_ACCEPTCONN:
			v.val = sk->sk_state == TCP_LISTEN;
			break;

		case SO_PEERSEC:
			return security_socket_getpeersec(sock, optval, optlen, len);

		default:
			return(-ENOPROTOOPT);
	}
	if (len > lv)
		len = lv;
	if (copy_to_user(optval, &v, len))
		return -EFAULT;
lenout:
  	if (put_user(len, optlen))
  		return -EFAULT;
  	return 0;
}

static kmem_cache_t *sk_cachep;

/**
 *	sk_alloc - All socket objects are allocated here
 *	@family - protocol family
 *	@priority - for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
 *	@zero_it - zeroes the allocated sock
 *	@slab - alternate slab
 *
 *	All socket objects are allocated here. If @zero_it is non-zero
 *	it should have the size of the are to be zeroed, because the
 *	private slabcaches have different sizes of the generic struct sock.
 *	1 has been kept as a way to say sizeof(struct sock).
 */
struct sock *sk_alloc(int family, int priority, int zero_it, kmem_cache_t *slab)
{
	struct sock *sk = NULL;

	if (!slab)
		slab = sk_cachep;
	sk = kmem_cache_alloc(slab, priority);
	if (sk) {
		if (zero_it) {
			memset(sk, 0,
			       zero_it == 1 ? sizeof(struct sock) : zero_it);
			sk->sk_family = family;
			sock_lock_init(sk);
		}
		sk->sk_slab = slab;
		
		if (security_sk_alloc(sk, family, priority)) {
			kmem_cache_free(slab, sk);
			sk = NULL;
		}
	}
	return sk;
}

void sk_free(struct sock *sk)
{
	struct sk_filter *filter;
	struct module *owner = sk->sk_owner;

	if (sk->sk_destruct)
		sk->sk_destruct(sk);

	filter = sk->sk_filter;
	if (filter) {
		sk_filter_release(sk, filter);
		sk->sk_filter = NULL;
	}

	sock_disable_timestamp(sk);

	if (atomic_read(&sk->sk_omem_alloc))
		printk(KERN_DEBUG "%s: optmem leakage (%d bytes) detected.\n",
		       __FUNCTION__, atomic_read(&sk->sk_omem_alloc));

	security_sk_free(sk);
	kmem_cache_free(sk->sk_slab, sk);
	module_put(owner);
}

void __init sk_init(void)
{
	sk_cachep = kmem_cache_create("sock", sizeof(struct sock), 0,
				      SLAB_HWCACHE_ALIGN, NULL, NULL);
	if (!sk_cachep)
		printk(KERN_CRIT "sk_init: Cannot create sock SLAB cache!");

	if (num_physpages <= 4096) {
		sysctl_wmem_max = 32767;
		sysctl_rmem_max = 32767;
		sysctl_wmem_default = 32767;
		sysctl_rmem_default = 32767;
	} else if (num_physpages >= 131072) {
		sysctl_wmem_max = 131071;
		sysctl_rmem_max = 131071;
	}
}

/*
 *	Simple resource managers for sockets.
 */


/* 
 * Write buffer destructor automatically called from kfree_skb. 
 */
void sock_wfree(struct sk_buff *skb)
{
	struct sock *sk = skb->sk;

	/* In case it might be waiting for more memory. */
	atomic_sub(skb->truesize, &sk->sk_wmem_alloc);
	if (!sk->sk_use_write_queue)
		sk->sk_write_space(sk);
	sock_put(sk);
}

/* 
 * Read buffer destructor automatically called from kfree_skb. 
 */
void sock_rfree(struct sk_buff *skb)
{
	struct sock *sk = skb->sk;

	atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
}


int sock_i_uid(struct sock *sk)
{
	int uid;

	read_lock(&sk->sk_callback_lock);
	uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : 0;
	read_unlock(&sk->sk_callback_lock);
	return uid;
}

unsigned long sock_i_ino(struct sock *sk)
{
	unsigned long ino;

	read_lock(&sk->sk_callback_lock);
	ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0;
	read_unlock(&sk->sk_callback_lock);
	return ino;
}

/*
 * Allocate a skb from the socket's send buffer.
 */
struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, int priority)
{
	if (force || atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) {
		struct sk_buff * skb = alloc_skb(size, priority);
		if (skb) {
			skb_set_owner_w(skb, sk);
			return skb;
		}
	}
	return NULL;
}

/*
 * Allocate a skb from the socket's receive buffer.
 */ 
struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force, int priority)
{
	if (force || atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) {
		struct sk_buff *skb = alloc_skb(size, priority);
		if (skb) {
			skb_set_owner_r(skb, sk);
			return skb;
		}
	}
	return NULL;
}

/* 
 * Allocate a memory block from the socket's option memory buffer.
 */ 
void *sock_kmalloc(struct sock *sk, int size, int priority)
{
	if ((unsigned)size <= sysctl_optmem_max &&
	    atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
		void *mem;
		/* First do the add, to avoid the race if kmalloc
 		 * might sleep.
		 */
		atomic_add(size, &sk->sk_omem_alloc);
		mem = kmalloc(size, priority);
		if (mem)
			return mem;
		atomic_sub(size, &sk->sk_omem_alloc);
	}
	return NULL;
}

/*
 * Free an option memory block.
 */
void sock_kfree_s(struct sock *sk, void *mem, int size)
{
	kfree(mem);
	atomic_sub(size, &sk->sk_omem_alloc);
}

/* It is almost wait_for_tcp_memory minus release_sock/lock_sock.
   I think, these locks should be removed for datagram sockets.
 */
static long sock_wait_for_wmem(struct sock * sk, long timeo)
{
	DEFINE_WAIT(wait);

	clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
	for (;;) {
		if (!timeo)
			break;
		if (signal_pending(current))
			break;
		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
		prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
		if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf)
			break;
		if (sk->sk_shutdown & SEND_SHUTDOWN)
			break;
		if (sk->sk_err)
			break;
		timeo = schedule_timeout(timeo);
	}
	finish_wait(sk->sk_sleep, &wait);
	return timeo;
}


/*
 *	Generic send/receive buffer handlers
 */

struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
				     unsigned long data_len, int noblock, int *errcode)
{
	struct sk_buff *skb;
	unsigned int gfp_mask;
	long timeo;
	int err;

	gfp_mask = sk->sk_allocation;
	if (gfp_mask & __GFP_WAIT)
		gfp_mask |= __GFP_REPEAT;

	timeo = sock_sndtimeo(sk, noblock);
	while (1) {
		err = sock_error(sk);
		if (err != 0)
			goto failure;

		err = -EPIPE;
		if (sk->sk_shutdown & SEND_SHUTDOWN)
			goto failure;

		if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) {
			skb = alloc_skb(header_len, sk->sk_allocation);
			if (skb) {
				int npages;
				int i;

				/* No pages, we're done... */
				if (!data_len)
					break;

				npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
				skb->truesize += data_len;
				skb_shinfo(skb)->nr_frags = npages;
				for (i = 0; i < npages; i++) {
					struct page *page;
					skb_frag_t *frag;

					page = alloc_pages(sk->sk_allocation, 0);
					if (!page) {
						err = -ENOBUFS;
						skb_shinfo(skb)->nr_frags = i;
						kfree_skb(skb);
						goto failure;
					}

					frag = &skb_shinfo(skb)->frags[i];
					frag->page = page;
					frag->page_offset = 0;
					frag->size = (data_len >= PAGE_SIZE ?
						      PAGE_SIZE :
						      data_len);
					data_len -= PAGE_SIZE;
				}

				/* Full success... */
				break;
			}
			err = -ENOBUFS;
			goto failure;
		}
		set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
		err = -EAGAIN;
		if (!timeo)
			goto failure;
		if (signal_pending(current))
			goto interrupted;
		timeo = sock_wait_for_wmem(sk, timeo);
	}

	skb_set_owner_w(skb, sk);
	return skb;

interrupted:
	err = sock_intr_errno(timeo);
failure:
	*errcode = err;
	return NULL;
}

struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, 
				    int noblock, int *errcode)
{
	return sock_alloc_send_pskb(sk, size, 0, noblock, errcode);
}

void __lock_sock(struct sock *sk)
{
	DEFINE_WAIT(wait);

	for(;;) {
		prepare_to_wait_exclusive(&sk->sk_lock.wq, &wait,
					TASK_UNINTERRUPTIBLE);
		spin_unlock_bh(&sk->sk_lock.slock);
		schedule();
		spin_lock_bh(&sk->sk_lock.slock);
		if(!sock_owned_by_user(sk))
			break;
	}
	finish_wait(&sk->sk_lock.wq, &wait);
}

void __release_sock(struct sock *sk)
{
	struct sk_buff *skb = sk->sk_backlog.head;

	do {
		sk->sk_backlog.head = sk->sk_backlog.tail = NULL;
		bh_unlock_sock(sk);

		do {
			struct sk_buff *next = skb->next;

			skb->next = NULL;
			sk->sk_backlog_rcv(sk, skb);
			skb = next;
		} while (skb != NULL);