/* drbd_bitmap.c This file is part of DRBD by Philipp Reisner and Lars Ellenberg. Copyright (C) 2004-2008, LINBIT Information Technologies GmbH. Copyright (C) 2004-2008, Philipp Reisner . Copyright (C) 2004-2008, Lars Ellenberg . drbd is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2, or (at your option) any later version. drbd is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with drbd; see the file COPYING. If not, write to the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. */ #include #include #include #include #include #include #include "drbd_int.h" /* OPAQUE outside this file! * interface defined in drbd_int.h * convention: * function name drbd_bm_... => used elsewhere, "public". * function name bm_... => internal to implementation, "private". */ /* * LIMITATIONS: * We want to support >= peta byte of backend storage, while for now still using * a granularity of one bit per 4KiB of storage. * 1 << 50 bytes backend storage (1 PiB) * 1 << (50 - 12) bits needed * 38 --> we need u64 to index and count bits * 1 << (38 - 3) bitmap bytes needed * 35 --> we still need u64 to index and count bytes * (that's 32 GiB of bitmap for 1 PiB storage) * 1 << (35 - 2) 32bit longs needed * 33 --> we'd even need u64 to index and count 32bit long words. * 1 << (35 - 3) 64bit longs needed * 32 --> we could get away with a 32bit unsigned int to index and count * 64bit long words, but I rather stay with unsigned long for now. * We probably should neither count nor point to bytes or long words * directly, but either by bitnumber, or by page index and offset. * 1 << (35 - 12) * 22 --> we need that much 4KiB pages of bitmap. * 1 << (22 + 3) --> on a 64bit arch, * we need 32 MiB to store the array of page pointers. * * Because I'm lazy, and because the resulting patch was too large, too ugly * and still incomplete, on 32bit we still "only" support 16 TiB (minus some), * (1 << 32) bits * 4k storage. * * bitmap storage and IO: * Bitmap is stored little endian on disk, and is kept little endian in * core memory. Currently we still hold the full bitmap in core as long * as we are "attached" to a local disk, which at 32 GiB for 1PiB storage * seems excessive. * * We plan to reduce the amount of in-core bitmap pages by paging them in * and out against their on-disk location as necessary, but need to make * sure we don't cause too much meta data IO, and must not deadlock in * tight memory situations. This needs some more work. */ /* * NOTE * Access to the *bm_pages is protected by bm_lock. * It is safe to read the other members within the lock. * * drbd_bm_set_bits is called from bio_endio callbacks, * We may be called with irq already disabled, * so we need spin_lock_irqsave(). * And we need the kmap_atomic. */ struct drbd_bitmap { struct page **bm_pages; spinlock_t bm_lock; /* see LIMITATIONS: above */ unsigned long bm_set; /* nr of set bits; THINK maybe atomic_t? */ unsigned long bm_bits; size_t bm_words; size_t bm_number_of_pages; sector_t bm_dev_capacity; struct mutex bm_change; /* serializes resize operations */ wait_queue_head_t bm_io_wait; /* used to serialize IO of single pages */ enum bm_flag bm_flags; /* debugging aid, in case we are still racy somewhere */ char *bm_why; struct task_struct *bm_task; }; #define bm_print_lock_info(m) __bm_print_lock_info(m, __func__) static void __bm_print_lock_info(struct drbd_conf *mdev, const char *func) { struct drbd_bitmap *b = mdev->bitmap; if (!__ratelimit(&drbd_ratelimit_state)) return; dev_err(DEV, "FIXME %s in %s, bitmap locked for '%s' by %s\n", current == mdev->receiver.task ? "receiver" : current == mdev->asender.task ? "asender" : current == mdev->worker.task ? "worker" : current->comm, func, b->bm_why ?: "?", b->bm_task == mdev->receiver.task ? "receiver" : b->bm_task == mdev->asender.task ? "asender" : b->bm_task == mdev->worker.task ? "worker" : "?"); } void drbd_bm_lock(struct drbd_conf *mdev, char *why, enum bm_flag flags) { struct drbd_bitmap *b = mdev->bitmap; int trylock_failed; if (!b) { dev_err(DEV, "FIXME no bitmap in drbd_bm_lock!?\n"); return; } trylock_failed = !mutex_trylock(&b->bm_change); if (trylock_failed) { dev_warn(DEV, "%s going to '%s' but bitmap already locked for '%s' by %s\n", current == mdev->receiver.task ? "receiver" : current == mdev->asender.task ? "asender" : current == mdev->worker.task ? "worker" : current->comm, why, b->bm_why ?: "?", b->bm_task == mdev->receiver.task ? "receiver" : b->bm_task == mdev->asender.task ? "asender" : b->bm_task == mdev->worker.task ? "worker" : "?"); mutex_lock(&b->bm_change); } if (BM_LOCKED_MASK & b->bm_flags) dev_err(DEV, "FIXME bitmap already locked in bm_lock\n"); b->bm_flags |= flags & BM_LOCKED_MASK; b->bm_why = why; b->bm_task = current; } void drbd_bm_unlock(struct drbd_conf *mdev) { struct drbd_bitmap *b = mdev->bitmap; if (!b) { dev_err(DEV, "FIXME no bitmap in drbd_bm_unlock!?\n"); return; } if (!(BM_LOCKED_MASK & mdev->bitmap->bm_flags)) dev_err(DEV, "FIXME bitmap not locked in bm_unlock\n"); b->bm_flags &= ~BM_LOCKED_MASK; b->bm_why = NULL; b->bm_task = NULL; mutex_unlock(&b->bm_change); } /* we store some "meta" info about our pages in page->private */ /* at a granularity of 4k storage per bitmap bit: * one peta byte storage: 1<<50 byte, 1<<38 * 4k storage blocks * 1<<38 bits, * 1<<23 4k bitmap pages. * Use 24 bits as page index, covers 2 peta byte storage * at a granularity of 4k per bit. * Used to report the failed page idx on io error from the endio handlers. */ #define BM_PAGE_IDX_MASK ((1UL<<24)-1) /* this page is currently read in, or written back */ #define BM_PAGE_IO_LOCK 31 /* if there has been an IO error for this page */ #define BM_PAGE_IO_ERROR 30 /* this is to be able to intelligently skip disk IO, * set if bits have been set since last IO. */ #define BM_PAGE_NEED_WRITEOUT 29 /* to mark for lazy writeout once syncer cleared all clearable bits, * we if bits have been cleared since last IO. */ #define BM_PAGE_LAZY_WRITEOUT 28 /* store_page_idx uses non-atomic assignment. It is only used directly after * allocating the page. All other bm_set_page_* and bm_clear_page_* need to * use atomic bit manipulation, as set_out_of_sync (and therefore bitmap * changes) may happen from various contexts, and wait_on_bit/wake_up_bit * requires it all to be atomic as well. */ static void bm_store_page_idx(struct page *page, unsigned long idx) { BUG_ON(0 != (idx & ~BM_PAGE_IDX_MASK)); page_private(page) |= idx; } static unsigned long bm_page_to_idx(struct page *page) { return page_private(page) & BM_PAGE_IDX_MASK; } /* As is very unlikely that the same page is under IO from more than one * context, we can get away with a bit per page and one wait queue per bitmap. */ static void bm_page_lock_io(struct drbd_conf *mdev, int page_nr) { struct drbd_bitmap *b = mdev->bitmap; void *addr = &page_private(b->bm_pages[page_nr]); wait_event(b->bm_io_wait, !test_and_set_bit(BM_PAGE_IO_LOCK, addr)); } static void bm_page_unlock_io(struct drbd_conf *mdev, int page_nr) { struct drbd_bitmap *b = mdev->bitmap; void *addr = &page_private(b->bm_pages[page_nr]); clear_bit(BM_PAGE_IO_LOCK, addr); smp_mb__after_clear_bit(); wake_up(&mdev->bitmap->bm_io_wait); } /* set _before_ submit_io, so it may be reset due to being changed * while this page is in flight... will get submitted later again */ static void bm_set_page_unchanged(struct page *page) { /* use cmpxchg? */ clear_bit(BM_PAGE_NEED_WRITEOUT, &page_private(page)); clear_bit(BM_PAGE_LAZY_WRITEOUT, &page_private(page)); } static void bm_set_page_need_writeout(struct page *page) { set_bit(BM_PAGE_NEED_WRITEOUT, &page_private(page)); } static int bm_test_page_unchanged(struct page *page) { volatile const unsigned long *addr = &page_private(page); return (*addr & ((1UL<> PAGE_SHIFT; */ unsigned int page_nr = long_nr >> (PAGE_SHIFT - LN2_BPL + 3); BUG_ON(page_nr >= b->bm_number_of_pages); return page_nr; } static unsigned int bm_bit_to_page_idx(struct drbd_bitmap *b, u64 bitnr) { /* page_nr = (bitnr/8) >> PAGE_SHIFT; */ unsigned int page_nr = bitnr >> (PAGE_SHIFT + 3); BUG_ON(page_nr >= b->bm_number_of_pages); return page_nr; } static unsigned long *__bm_map_pidx(struct drbd_bitmap *b, unsigned int idx, const enum km_type km) { struct page *page = b->bm_pages[idx]; return (unsigned long *) kmap_atomic(page, km); } static unsigned long *bm_map_pidx(struct drbd_bitmap *b, unsigned int idx) { return __bm_map_pidx(b, idx, KM_IRQ1); } static void __bm_unmap(unsigned long *p_addr, const enum km_type km) { kunmap_atomic(p_addr, km); }; static void bm_unmap(unsigned long *p_addr) { return __bm_unmap(p_addr, KM_IRQ1); } /* long word offset of _bitmap_ sector */ #define S2W(s) ((s)<<(BM_EXT_SHIFT-BM_BLOCK_SHIFT-LN2_BPL)) /* word offset from start of bitmap to word number _in_page_ * modulo longs per page #define MLPP(X) ((X) % (PAGE_SIZE/sizeof(long)) hm, well, Philipp thinks gcc might not optimize the % into & (... - 1) so do it explicitly: */ #define MLPP(X) ((X) & ((PAGE_SIZE/sizeof(long))-1)) /* Long words per page */ #define LWPP (PAGE_SIZE/sizeof(long)) /* * actually most functions herein should take a struct drbd_bitmap*, not a * struct drbd_conf*, but for the debug macros I like to have the mdev around * to be able to report device specific. */ static void bm_free_pages(struct page **pages, unsigned long number) { unsigned long i; if (!pages) return; for (i = 0; i < number; i++) { if (!pages[i]) { printk(KERN_ALERT "drbd: bm_free_pages tried to free " "a NULL pointer; i=%lu n=%lu\n", i, number); continue; } __free_page(pages[i]); pages[i] = NULL; } } static void bm_vk_free(void *ptr, int v) { if (v) vfree(ptr); else kfree(ptr); } /* * "have" and "want" are NUMBER OF PAGES. */ static struct page **bm_realloc_pages(struct drbd_bitmap *b, unsigned long want) { struct page **old_pages = b->bm_pages; struct page **new_pages, *page; unsigned int i, bytes, vmalloced = 0; unsigned long have = b->bm_number_of_pages; BUG_ON(have == 0 && old_pages != NULL); BUG_ON(have != 0 && old_pages == NULL); if (have == want) return old_pages; /* Trying kmalloc first, falling back to vmalloc. * GFP_KERNEL is ok, as this is done when a lower level disk is * "attached" to the drbd. Context is receiver thread or cqueue * thread. As we have no disk yet, we are not in the IO path, * not even the IO path of the peer. */ bytes = sizeof(struct page *)*want; new_pages = kmalloc(bytes, GFP_KERNEL); if (!new_pages) { new_pages = vmalloc(bytes); if (!new_pages) return NULL; vmalloced = 1; } memset(new_pages, 0, bytes); if (want >= have) { for (i = 0; i < have; i++) new_pages[i] = old_pages[i]; for (; i < want; i++) { page = alloc_page(GFP_HIGHUSER); if (!page) { bm_free_pages(new_pages + have, i - have); bm_vk_free(new_pages, vmalloced); return NULL; } /* we want to know which page it is * from the endio handlers */ bm_store_page_idx(page, i); new_pages[i] = page; } } else { for (i = 0; i < want; i++) new_pages[i] = old_pages[i]; /* NOT HERE, we are outside the spinlock! bm_free_pages(old_pages + want, have - want); */ } if (vmalloced) b->bm_flags |= BM_P_VMALLOCED; else b->bm_flags &= ~BM_P_VMALLOCED; return new_pages; } /* * called on driver init only. TODO call when a device is created. * allocates the drbd_bitmap, and stores it in mdev->bitmap. */ int drbd_bm_init(struct drbd_conf *mdev) { struct drbd_bitmap *b = mdev->bitmap; WARN_ON(b != NULL); b = kzalloc(sizeof(struct drbd_bitmap), GFP_KERNEL); if (!b) return -ENOMEM; spin_lock_init(&b->bm_lock); mutex_init(&b->bm_change); init_waitqueue_head(&b->bm_io_wait); mdev->bitmap = b; return 0; } sector_t drbd_bm_capacity(struct drbd_conf *mdev) { ERR_IF(!mdev->bitmap) return 0; return mdev->bitmap->bm_dev_capacity; } /* called on driver unload. TODO: call when a device is destroyed. */ void drbd_bm_cleanup(struct drbd_conf *mdev) { ERR_IF (!mdev->bitmap) return; bm_free_pages(mdev->bitmap->bm_pages, mdev->bitmap->bm_number_of_pages); bm_vk_free(mdev->bitmap->bm_pages, (BM_P_VMALLOCED & mdev->bitmap->bm_flags)); kfree(mdev->bitmap); mdev->bitmap = NULL; } /* * since (b->bm_bits % BITS_PER_LONG) != 0, * this masks out the remaining bits. * Returns the number of bits cleared. */ #define BITS_PER_PAGE (1UL << (PAGE_SHIFT + 3)) #define BITS_PER_PAGE_MASK (BITS_PER_PAGE - 1) #define BITS_PER_LONG_MASK (BITS_PER_LONG - 1) static int bm_clear_surplus(struct drbd_bitmap *b) { unsigned long mask; unsigned long *p_addr, *bm; int tmp; int cleared = 0; /* number of bits modulo bits per page */ tmp = (b->bm_bits & BITS_PER_PAGE_MASK); /* mask the used bits of the word containing the last bit */ mask = (1UL << (tmp & BITS_PER_LONG_MASK)) -1; /* bitmap is always stored little endian, * on disk and in core memory alike */ mask = cpu_to_lel(mask); p_addr = bm_map_pidx(b, b->bm_number_of_pages - 1); bm = p_addr + (tmp/BITS_PER_LONG); if (mask) { /* If mask != 0, we are not exactly aligned, so bm now points * to the long containing the last bit. * If mask == 0, bm already points to the word immediately * after the last (long word aligned) bit. */ cleared = hweight_long(*bm & ~mask); *bm &= mask; bm++; } if (BITS_PER_LONG == 32 && ((bm - p_addr) & 1) == 1) { /* on a 32bit arch, we may need to zero out * a padding long to align with a 64bit remote */ cleared += hweight_long(*bm); *bm = 0; } bm_unmap(p_addr); return cleared; } static void bm_set_surplus(struct drbd_bitmap *b) { unsigned long mask; unsigned long *p_addr, *bm; int tmp; /* number of bits modulo bits per page */ tmp = (b->bm_bits & BITS_PER_PAGE_MASK); /* mask the used bits of the word containing the last bit */ mask = (1UL << (tmp & BITS_PER_LONG_MASK)) -1; /* bitmap is always stored little endian, * on disk and in core memory alike */ mask = cpu_to_lel(mask); p_addr = bm_map_pidx(b, b->bm_number_of_pages - 1); bm = p_addr + (tmp/BITS_PER_LONG); if (mask) { /* If mask != 0, we are not exactly aligned, so bm now points * to the long containing the last bit. * If mask == 0, bm already points to the word immediately * after the last (long word aligned) bit. */ *bm |= ~mask; bm++; } if (BITS_PER_LONG == 32 && ((bm - p_addr) & 1) == 1) { /* on a 32bit arch, we may need to zero out * a padding long to align with a 64bit remote */ *bm = ~0UL; } bm_unmap(p_addr); } /* you better not modify the bitmap while this is running, * or its results will be stale */ static unsigned long bm_count_bits(struct drbd_bitmap *b) { unsigned long *p_addr; unsigned long bits = 0; unsigned long mask = (1UL << (b->bm_bits & BITS_PER_LONG_MASK)) -1; int idx, i, last_word; /* all but last page */ for (idx = 0; idx < b->bm_number_of_pages - 1; idx++) { p_addr = __bm_map_pidx(b, idx, KM_USER0); for (i = 0; i < LWPP; i++) bits += hweight_long(p_addr[i]); __bm_unmap(p_addr, KM_USER0); cond_resched(); } /* last (or only) page */ last_word = ((b->bm_bits - 1) & BITS_PER_PAGE_MASK) >> LN2_BPL; p_addr = __bm_map_pidx(b, idx, KM_USER0); for (i = 0; i < last_word; i++) bits += hweight_long(p_addr[i]); p_addr[last_word] &= cpu_to_lel(mask); bits += hweight_long(p_addr[last_word]); /* 32bit arch, may have an unused padding long */ if (BITS_PER_LONG == 32 && (last_word & 1) == 0) p_addr[last_word+1] = 0; __bm_unmap(p_addr, KM_USER0); return bits; } /* offset and len in long words.*/ static void bm_memset(struct drbd_bitmap *b, size_t offset, int c, size_t len) { unsigned long *p_addr, *bm; unsigned int idx; size_t do_now, end; end = offset + len; if (end > b->bm_words) { printk(KERN_ALERT "drbd: bm_memset end > bm_words\n"); return; } while (offset < end) { do_now = min_t(size_t, ALIGN(offset + 1, LWPP), end) - offset; idx = bm_word_to_page_idx(b, offset); p_addr = bm_map_pidx(b, 
/*
 * lib/socket.c		Netlink Socket
 *
 *	This library is free software; you can redistribute it and/or
 *	modify it under the terms of the GNU Lesser General Public
 *	License as published by the Free Software Foundation version 2.1
 *	of the License.
 *
 * Copyright (c) 2003-2008 Thomas Graf <tgraf@suug.ch>
 */

/**
 * @ingroup core
 * @defgroup socket Socket
 * @{
 */

#include <netlink-local.h>
#include <netlink/netlink.h>
#include <netlink/utils.h>
#include <netlink/handlers.h>
#include <netlink/msg.h>
#include <netlink/attr.h>

static uint32_t used_ports_map[32];

static uint32_t generate_local_port(void)
{
	int i, n;
	uint32_t pid = getpid() & 0x3FFFFF;

	for (i = 0; i < 32; i++) {
		if (used_ports_map[i] == 0xFFFFFFFF)
			continue;

		for (n = 0; n < 32; n++) {
			if (1UL & (used_ports_map[i] >> n))
				continue;

			used_ports_map[i] |= (1UL << n);
			n += (i * 32);

			/* PID_MAX_LIMIT is currently at 2^22, leaving 10 bit
			 * to, i.e. 1024 unique ports per application. */
			return pid + (n << 22);

		}
	}

	/* Out of sockets in our own PID namespace, what to do? FIXME */
	return UINT_MAX;
}

static void release_local_port(uint32_t port)
{
	int nr;

	if (port == UINT_MAX)
		return;
	
	nr = port >> 22;
	used_ports_map[nr / 32] &= ~(1 << nr % 32);
}

/**
 * @name Allocation
 * @{
 */

static struct nl_sock *__alloc_socket(struct nl_cb *cb)
{
	struct nl_sock *sk;

	sk = calloc(1, sizeof(*sk));
	if (!sk)
		return NULL;

	sk->s_fd = -1;
	sk->s_cb = cb;
	sk->s_local.nl_family = AF_NETLINK;
	sk->s_peer.nl_family = AF_NETLINK;
	sk->s_seq_expect = sk->s_seq_next = time(0);
	sk->s_local.nl_pid = generate_local_port();
	if (sk->s_local.nl_pid == UINT_MAX) {
		nl_socket_free(sk);
		return NULL;
	}

	return sk;
}

/**
 * Allocate new netlink socket
 *
 * @return Newly allocated netlink socket or NULL.
 */
struct nl_sock *nl_socket_alloc(void)
{
	struct nl_cb *cb;
	
	cb = nl_cb_alloc(NL_CB_DEFAULT);
	if (!cb)
		return NULL;

	return __alloc_socket(cb);
}

/**
 * Allocate new socket with custom callbacks
 * @arg cb		Callback handler
 *
 * The reference to the callback handler is taken into account
 * automatically, it is released again upon calling nl_socket_free().
 *
 *@return Newly allocted socket handle or NULL.
 */
struct nl_sock *nl_socket_alloc_cb(struct nl_cb *cb)
{
	if (cb == NULL)
		BUG();

	return __alloc_socket(nl_cb_get(cb));
}

/**
 * Free a netlink socket.
 * @arg sk		Netlink socket.
 */
void nl_socket_free(struct nl_sock *sk)
{
	if (!sk)
		return;

	if (sk->s_fd >= 0)
		close(sk->s_fd);

	if (!(sk->s_flags & NL_OWN_PORT))
		release_local_port(sk->s_local.nl_pid);

	nl_cb_put(sk->s_cb);
	free(sk);
}

/** @} */

/**
 * @name Sequence Numbers
 * @{
 */

static int noop_seq_check(struct nl_msg *msg, void *arg)
{
	return NL_OK;
}


/**
 * Disable sequence number checking.
 * @arg sk		Netlink socket.
 *
 * Disables checking of sequence numbers on the netlink socket This is
 * required to allow messages to be processed which were not requested by
 * a preceding request message, e.g. netlink events.
 *
 * @note This function modifies the NL_CB_SEQ_CHECK configuration in
 * the callback handle associated with the socket.
 */
void nl_socket_disable_seq_check(struct nl_sock *sk)
{
	nl_cb_set(sk->s_cb, NL_CB_SEQ_CHECK,
		  NL_CB_CUSTOM, noop_seq_check, NULL);
}

/** @} */

/**
 * Set local port of socket
 * @arg sk		Netlink socket.
 * @arg port		Local port identifier
 *
 * Assigns a local port identifier to the socket. If port is 0
 * a unique port identifier will be generated automatically.
 */
void nl_socket_set_local_port(struct nl_sock *sk, uint32_t port)
{
	if (port == 0) {
		port = generate_local_port(); 
		sk->s_flags &= ~NL_OWN_PORT;
	} else  {
		if (!(sk->s_flags & NL_OWN_PORT))
			release_local_port(sk->s_local.nl_pid);
		sk->s_flags |= NL_OWN_PORT;
	}

	sk->s_local.nl_pid = port;
}

/** @} */

/**
 * @name Group Subscriptions
 * @{
 */

/**
 * Join groups
 * @arg sk		Netlink socket
 * @arg group		Group identifier
 *
 * Joins the specified groups using the modern socket option which
 * is available since kernel version 2.6.14. It allows joining an
 * almost arbitary number of groups without limitation.  The list
 * of groups has to be terminated by 0 (%NFNLGRP_NONE).
 *
 * Make sure to use the correct group definitions as the older
 * bitmask definitions for nl_join_groups() are likely to still
 * be present for backward compatibility reasons.
 *
 * @return 0 on sucess or a negative error code.
 */
int nl_socket_add_memberships(struct nl_sock *sk, int group, ...)
{
	int err;
	va_list ap;

	if (sk->s_fd == -1)
		return -NLE_BAD_SOCK;

	va_start(ap, group);

	while (group != 0) {
		if (group < 0)
			return -NLE_INVAL;

		err = setsockopt(sk->s_fd, SOL_NETLINK, NETLINK_ADD_MEMBERSHIP,
						 &group, sizeof(group));
		if (err < 0)
			return -nl_syserr2nlerr(errno);

		group = va_arg(ap, int);
	}

	va_end(ap);

	return 0;
}

/**
 * Leave groups
 * @arg sk		Netlink socket
 * @arg group		Group identifier
 *
 * Leaves the specified groups using the modern socket option
 * which is available since kernel version 2.6.14. The list of groups
 * has to terminated by 0 (%NFNLGRP_NONE).
 *
 * @see nl_socket_add_membership
 * @return 0 on success or a negative error code.
 */
int nl_socket_drop_memberships(struct nl_sock *sk, int group, ...)
{
	int err;
	va_list ap;

	if (sk->s_fd == -1)
		return -NLE_BAD_SOCK;

	va_start(ap, group);

	while (group != 0) {
		if (group < 0)
			return -NLE_INVAL;

		err = setsockopt(sk->s_fd, SOL_NETLINK, NETLINK_DROP_MEMBERSHIP,
						 &group, sizeof(group));
		if (err < 0)
			return -nl_syserr2nlerr(errno);

		group = va_arg(ap, int);
	}

	va_end(ap);

	return 0;
}


/** @} */

/**
 * Set file descriptor of socket to non-blocking state
 * @arg sk		Netlink socket.
 *
 * @return 0 on success or a negative error code.
 */
int nl_socket_set_nonblocking(struct nl_sock *sk)
{
	if (sk->s_fd == -1)
		return -NLE_BAD_SOCK;

	if (fcntl(sk->s_fd, F_SETFL, O_NONBLOCK) < 0)
		return -nl_syserr2nlerr(errno);

	return 0;
}

/** @} */

/**
 * @name Utilities
 * @{
 */

/**
 * Set socket buffer size of netlink socket.
 * @arg sk		Netlink socket.
 * @arg rxbuf		New receive socket buffer size in bytes.
 * @arg txbuf		New transmit socket buffer size in bytes.
 *
 * Sets the socket buffer size of a netlink socket to the specified
 * values \c rxbuf and \c txbuf. Providing a value of \c 0 assumes a
 * good default value.
 *
 * @note It is not required to call this function prior to nl_connect().
 * @return 0 on sucess or a negative error code.
 */
int nl_socket_set_buffer_size(struct nl_sock *sk, int rxbuf, int txbuf)
{
	int err;

	if (rxbuf <= 0)
		rxbuf = 32768;

	if (txbuf <= 0)
		txbuf = 32768;

	if (sk->s_fd == -1)
		return -NLE_BAD_SOCK;
	
	err = setsockopt(sk->s_fd, SOL_SOCKET, SO_SNDBUF,
			 &txbuf, sizeof(txbuf));
	if (err < 0)
		return -nl_syserr2nlerr(errno);

	err = setsockopt(sk->s_fd, SOL_SOCKET, SO_RCVBUF,
			 &rxbuf, sizeof(rxbuf));
	if (err < 0)
		return -nl_syserr2nlerr(errno);

	sk->s_flags |= NL_SOCK_BUFSIZE_SET;

	return 0;
}

/**
 * Enable/disable credential passing on netlink socket.
 * @arg sk		Netlink socket.
 * @arg state		New state (0 - disabled, 1 - enabled)
 *
 * @return 0 on success or a negative error code
 */
int nl_socket_set_passcred(struct nl_sock *sk, int state)
{
	int err;

	if (sk->s_fd == -1)
		return -NLE_BAD_SOCK;

	err = setsockopt(sk->s_fd, SOL_SOCKET, SO_PASSCRED,
			 &state, sizeof(state));
	if (err < 0)
		return -nl_syserr2nlerr(errno);

	if (state)
		sk->s_flags |= NL_SOCK_PASSCRED;
	else
		sk->s_flags &= ~NL_SOCK_PASSCRED;

	return 0;
}

/**
 * Enable/disable receival of additional packet information
 * @arg sk		Netlink socket.
 * @arg state		New state (0 - disabled, 1 - enabled)
 *
 * @return 0 on success or a negative error code
 */
int nl_socket_recv_pktinfo(struct nl_sock *sk, int state)
{
	int err;

	if (sk->s_fd == -1)
		return -NLE_BAD_SOCK;

	err = setsockopt(sk->s_fd, SOL_NETLINK, NETLINK_PKTINFO,
			 &state, sizeof(state));
	if (err < 0)
		return -nl_syserr2nlerr(errno);

	return 0;
}

/** @} */

/** @} */
generated by cgit v1.2.3 (git 2.25.1) at 2026-01-31 18:40:32 +0000