Revision df4793505abd5df399bc6d9a4d8fe81761f557cd authored by Linus Torvalds on 07 March 2024, 17:23:33 UTC, committed by Linus Torvalds on 07 March 2024, 17:23:33 UTC
Pull networking fixes from Paolo Abeni:
 "Including fixes from bpf, ipsec and netfilter.

  No solution yet for the stmmac issue mentioned in the last PR, but it
  proved to be a lockdep false positive, not a blocker.

  Current release - regressions:

   - dpll: move all dpll<>netdev helpers to dpll code, fix build
     regression with old compilers

  Current release - new code bugs:

   - page_pool: fix netlink dump stop/resume

  Previous releases - regressions:

   - bpf: fix verifier to check bpf_func_state->callback_depth when
     pruning states as otherwise unsafe programs could get accepted

   - ipv6: avoid possible UAF in ip6_route_mpath_notify()

   - ice: reconfig host after changing MSI-X on VF

   - mlx5:
       - e-switch, change flow rule destination checking
       - add a memory barrier to prevent a possible null-ptr-deref
       - switch to using _bh variant of of spinlock where needed

  Previous releases - always broken:

   - netfilter: nf_conntrack_h323: add protection for bmp length out of
     range

   - bpf: fix to zero-initialise xdp_rxq_info struct before running XDP
     program in CPU map which led to random xdp_md fields

   - xfrm: fix UDP encapsulation in TX packet offload

   - netrom: fix data-races around sysctls

   - ice:
       - fix potential NULL pointer dereference in ice_bridge_setlink()
       - fix uninitialized dplls mutex usage

   - igc: avoid returning frame twice in XDP_REDIRECT

   - i40e: disable NAPI right after disabling irqs when handling
     xsk_pool

   - geneve: make sure to pull inner header in geneve_rx()

   - sparx5: fix use after free inside sparx5_del_mact_entry

   - dsa: microchip: fix register write order in ksz8_ind_write8()

  Misc:

   - selftests: mptcp: fixes for diag.sh"

* tag 'net-6.8-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (63 commits)
  net: pds_core: Fix possible double free in error handling path
  netrom: Fix data-races around sysctl_net_busy_read
  netrom: Fix a data-race around sysctl_netrom_link_fails_count
  netrom: Fix a data-race around sysctl_netrom_routing_control
  netrom: Fix a data-race around sysctl_netrom_transport_no_activity_timeout
  netrom: Fix a data-race around sysctl_netrom_transport_requested_window_size
  netrom: Fix a data-race around sysctl_netrom_transport_busy_delay
  netrom: Fix a data-race around sysctl_netrom_transport_acknowledge_delay
  netrom: Fix a data-race around sysctl_netrom_transport_maximum_tries
  netrom: Fix a data-race around sysctl_netrom_transport_timeout
  netrom: Fix data-races around sysctl_netrom_network_ttl_initialiser
  netrom: Fix a data-race around sysctl_netrom_obsolescence_count_initialiser
  netrom: Fix a data-race around sysctl_netrom_default_path_quality
  netfilter: nf_conntrack_h323: Add protection for bmp length out of range
  netfilter: nf_tables: mark set as dead when unbinding anonymous set with timeout
  netfilter: nft_ct: fix l3num expectations with inet pseudo family
  netfilter: nf_tables: reject constant set with timeout
  netfilter: nf_tables: disallow anonymous set with timeout flag
  net/rds: fix WARNING in rds_conn_connect_if_down
  net: dsa: microchip: fix register write order in ksz8_ind_write8()
  ...
2 parent s 67be068 + ba18ded
Raw File
mmzone.c
// SPDX-License-Identifier: GPL-2.0
/*
 * linux/mm/mmzone.c
 *
 * management codes for pgdats, zones and page flags
 */


#include <linux/stddef.h>
#include <linux/mm.h>
#include <linux/mmzone.h>

struct pglist_data *first_online_pgdat(void)
{
	return NODE_DATA(first_online_node);
}

struct pglist_data *next_online_pgdat(struct pglist_data *pgdat)
{
	int nid = next_online_node(pgdat->node_id);

	if (nid == MAX_NUMNODES)
		return NULL;
	return NODE_DATA(nid);
}

/*
 * next_zone - helper magic for for_each_zone()
 */
struct zone *next_zone(struct zone *zone)
{
	pg_data_t *pgdat = zone->zone_pgdat;

	if (zone < pgdat->node_zones + MAX_NR_ZONES - 1)
		zone++;
	else {
		pgdat = next_online_pgdat(pgdat);
		if (pgdat)
			zone = pgdat->node_zones;
		else
			zone = NULL;
	}
	return zone;
}

static inline int zref_in_nodemask(struct zoneref *zref, nodemask_t *nodes)
{
#ifdef CONFIG_NUMA
	return node_isset(zonelist_node_idx(zref), *nodes);
#else
	return 1;
#endif /* CONFIG_NUMA */
}

/* Returns the next zone at or below highest_zoneidx in a zonelist */
struct zoneref *__next_zones_zonelist(struct zoneref *z,
					enum zone_type highest_zoneidx,
					nodemask_t *nodes)
{
	/*
	 * Find the next suitable zone to use for the allocation.
	 * Only filter based on nodemask if it's set
	 */
	if (unlikely(nodes == NULL))
		while (zonelist_zone_idx(z) > highest_zoneidx)
			z++;
	else
		while (zonelist_zone_idx(z) > highest_zoneidx ||
				(z->zone && !zref_in_nodemask(z, nodes)))
			z++;

	return z;
}

void lruvec_init(struct lruvec *lruvec)
{
	enum lru_list lru;

	memset(lruvec, 0, sizeof(struct lruvec));
	spin_lock_init(&lruvec->lru_lock);
	zswap_lruvec_state_init(lruvec);

	for_each_lru(lru)
		INIT_LIST_HEAD(&lruvec->lists[lru]);
	/*
	 * The "Unevictable LRU" is imaginary: though its size is maintained,
	 * it is never scanned, and unevictable pages are not threaded on it
	 * (so that their lru fields can be reused to hold mlock_count).
	 * Poison its list head, so that any operations on it would crash.
	 */
	list_del(&lruvec->lists[LRU_UNEVICTABLE]);

	lru_gen_init_lruvec(lruvec);
}

#if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS)
int folio_xchg_last_cpupid(struct folio *folio, int cpupid)
{
	unsigned long old_flags, flags;
	int last_cpupid;

	old_flags = READ_ONCE(folio->flags);
	do {
		flags = old_flags;
		last_cpupid = (flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK;

		flags &= ~(LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT);
		flags |= (cpupid & LAST_CPUPID_MASK) << LAST_CPUPID_PGSHIFT;
	} while (unlikely(!try_cmpxchg(&folio->flags, &old_flags, flags)));

	return last_cpupid;
}
#endif
back to top