Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

1 files changed, 256 insertions, 35 deletions

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
index 26c26cd30c3d..310c38247b5c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
@@ -39,55 +39,276 @@
 
 #define MLXSW_SP_KVDL_SINGLE_BASE 0
 #define MLXSW_SP_KVDL_SINGLE_SIZE 16384
+#define MLXSW_SP_KVDL_SINGLE_END \
+	(MLXSW_SP_KVDL_SINGLE_SIZE + MLXSW_SP_KVDL_SINGLE_BASE - 1)
+
 #define MLXSW_SP_KVDL_CHUNKS_BASE \
 	(MLXSW_SP_KVDL_SINGLE_BASE + MLXSW_SP_KVDL_SINGLE_SIZE)
-#define MLXSW_SP_KVDL_CHUNKS_SIZE \
-	(MLXSW_SP_KVD_LINEAR_SIZE - MLXSW_SP_KVDL_CHUNKS_BASE)
+#define MLXSW_SP_KVDL_CHUNKS_SIZE 49152
+#define MLXSW_SP_KVDL_CHUNKS_END \
+	(MLXSW_SP_KVDL_CHUNKS_SIZE + MLXSW_SP_KVDL_CHUNKS_BASE - 1)
+
+#define MLXSW_SP_KVDL_LARGE_CHUNKS_BASE \
+	(MLXSW_SP_KVDL_CHUNKS_BASE + MLXSW_SP_KVDL_CHUNKS_SIZE)
+#define MLXSW_SP_KVDL_LARGE_CHUNKS_SIZE \
+	(MLXSW_SP_KVD_LINEAR_SIZE - MLXSW_SP_KVDL_LARGE_CHUNKS_BASE)
+#define MLXSW_SP_KVDL_LARGE_CHUNKS_END \
+	(MLXSW_SP_KVDL_LARGE_CHUNKS_SIZE + MLXSW_SP_KVDL_LARGE_CHUNKS_BASE - 1)
+
 #define MLXSW_SP_CHUNK_MAX 32
+#define MLXSW_SP_LARGE_CHUNK_MAX 512
+
+struct mlxsw_sp_kvdl_part_info {
+	unsigned int part_index;
+	unsigned int start_index;
+	unsigned int end_index;
+	unsigned int alloc_size;
+};
+
+struct mlxsw_sp_kvdl_part {
+	struct list_head list;
+	const struct mlxsw_sp_kvdl_part_info *info;
+	unsigned long usage[0];	/* Entries */
+};
+
+struct mlxsw_sp_kvdl {
+	struct list_head parts_list;
+};
+
+static struct mlxsw_sp_kvdl_part *
+mlxsw_sp_kvdl_alloc_size_part(struct mlxsw_sp_kvdl *kvdl,
+			      unsigned int alloc_size)
+{
+	struct mlxsw_sp_kvdl_part *part, *min_part = NULL;
+
+	list_for_each_entry(part, &kvdl->parts_list, list) {
+		if (alloc_size <= part->info->alloc_size &&
+		    (!min_part ||
+		     part->info->alloc_size <= min_part->info->alloc_size))
+			min_part = part;
+	}
+
+	return min_part ?: ERR_PTR(-ENOBUFS);
+}
+
+static struct mlxsw_sp_kvdl_part *
+mlxsw_sp_kvdl_index_part(struct mlxsw_sp_kvdl *kvdl, u32 kvdl_index)
+{
+	struct mlxsw_sp_kvdl_part *part;
+
+	list_for_each_entry(part, &kvdl->parts_list, list) {
+		if (kvdl_index >= part->info->start_index &&
+		    kvdl_index <= part->info->end_index)
+			return part;
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static u32
+mlxsw_sp_entry_index_kvdl_index(const struct mlxsw_sp_kvdl_part_info *info,
+				unsigned int entry_index)
+{
+	return info->start_index + entry_index * info->alloc_size;
+}
+
+static unsigned int
+mlxsw_sp_kvdl_index_entry_index(const struct mlxsw_sp_kvdl_part_info *info,
+				u32 kvdl_index)
+{
+	return (kvdl_index - info->start_index) / info->alloc_size;
+}
+
+static int mlxsw_sp_kvdl_part_alloc(struct mlxsw_sp_kvdl_part *part,
+				    u32 *p_kvdl_index)
+{
+	const struct mlxsw_sp_kvdl_part_info *info = part->info;
+	unsigned int entry_index, nr_entries;
+
+	nr_entries = (info->end_index - info->start_index + 1) /
+		     info->alloc_size;
+	entry_index = find_first_zero_bit(part->usage, nr_entries);
+	if (entry_index == nr_entries)
+		return -ENOBUFS;
+	__set_bit(entry_index, part->usage);
+
+	*p_kvdl_index = mlxsw_sp_entry_index_kvdl_index(part->info,
+							entry_index);
+
+	return 0;
+}
+
+static void mlxsw_sp_kvdl_part_free(struct mlxsw_sp_kvdl_part *part,
+				    u32 kvdl_index)
+{
+	unsigned int entry_index;
+
+	entry_index = mlxsw_sp_kvdl_index_entry_index(part->info,
+						      kvdl_index);
+	__clear_bit(entry_index, part->usage);
+}
 
 int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count,
 			u32 *p_entry_index)
 {
-	int entry_index;
-	int size;
-	int type_base;
-	int type_size;
-	int type_entries;
-
-	if (entry_count == 0 || entry_count > MLXSW_SP_CHUNK_MAX) {
-		return -EINVAL;
-	} else if (entry_count == 1) {
-		type_base = MLXSW_SP_KVDL_SINGLE_BASE;
-		type_size = MLXSW_SP_KVDL_SINGLE_SIZE;
-		type_entries = 1;
-	} else {
-		type_base = MLXSW_SP_KVDL_CHUNKS_BASE;
-		type_size = MLXSW_SP_KVDL_CHUNKS_SIZE;
-		type_entries = MLXSW_SP_CHUNK_MAX;
+	struct mlxsw_sp_kvdl_part *part;
+
+	/* Find partition with smallest allocation size satisfying the
+	 * requested size.
+	 */
+	part = mlxsw_sp_kvdl_alloc_size_part(mlxsw_sp->kvdl, entry_count);
+	if (IS_ERR(part))
+		return PTR_ERR(part);
+
+	return mlxsw_sp_kvdl_part_alloc(part, p_entry_index);
+}
+
+void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index)
+{
+	struct mlxsw_sp_kvdl_part *part;
+
+	part = mlxsw_sp_kvdl_index_part(mlxsw_sp->kvdl, entry_index);
+	if (IS_ERR(part))
+		return;
+	mlxsw_sp_kvdl_part_free(part, entry_index);
+}
+
+int mlxsw_sp_kvdl_alloc_size_query(struct mlxsw_sp *mlxsw_sp,
+				   unsigned int entry_count,
+				   unsigned int *p_alloc_size)
+{
+	struct mlxsw_sp_kvdl_part *part;
+
+	part = mlxsw_sp_kvdl_alloc_size_part(mlxsw_sp->kvdl, entry_count);
+	if (IS_ERR(part))
+		return PTR_ERR(part);
+
+	*p_alloc_size = part->info->alloc_size;
+
+	return 0;
+}
+
+static const struct mlxsw_sp_kvdl_part_info kvdl_parts_info[] = {
+	{
+		.part_index	= 0,
+		.start_index	= MLXSW_SP_KVDL_SINGLE_BASE,
+		.end_index	= MLXSW_SP_KVDL_SINGLE_END,
+		.alloc_size	= 1,
+	},
+	{
+		.part_index	= 1,
+		.start_index	= MLXSW_SP_KVDL_CHUNKS_BASE,
+		.end_index	= MLXSW_SP_KVDL_CHUNKS_END,
+		.alloc_size	= MLXSW_SP_CHUNK_MAX,
+	},
+	{
+		.part_index	= 2,
+		.start_index	= MLXSW_SP_KVDL_LARGE_CHUNKS_BASE,
+		.end_index	= MLXSW_SP_KVDL_LARGE_CHUNKS_END,
+		.alloc_size	= MLXSW_SP_LARGE_CHUNK_MAX,
+	},
+};
+
+static struct mlxsw_sp_kvdl_part *
+mlxsw_sp_kvdl_part_find(struct mlxsw_sp *mlxsw_sp, unsigned int part_index)
+{
+	struct mlxsw_sp_kvdl_part *part;
+
+	list_for_each_entry(part, &mlxsw_sp->kvdl->parts_list, list) {
+		if (part->info->part_index == part_index)
+			return part;
 	}
 
-	entry_index = type_base;
-	size = type_base + type_size;
-	for_each_clear_bit_from(entry_index, mlxsw_sp->kvdl.usage, size) {
-		int i;
+	return NULL;
+}
+
+static int mlxsw_sp_kvdl_part_init(struct mlxsw_sp *mlxsw_sp,
+				   unsigned int part_index)
+{
+	const struct mlxsw_sp_kvdl_part_info *info;
+	struct mlxsw_sp_kvdl_part *part;
+	unsigned int nr_entries;
+	size_t usage_size;
+
+	info = &kvdl_parts_info[part_index];
+
+	nr_entries = (info->end_index - info->start_index + 1) /
+		     info->alloc_size;
+	usage_size = BITS_TO_LONGS(nr_entries) * sizeof(unsigned long);
+	part = kzalloc(sizeof(*part) + usage_size, GFP_KERNEL);
+	if (!part)
+		return -ENOMEM;
+
+	part->info = info;
+	list_add(&part->list, &mlxsw_sp->kvdl->parts_list);
+
+	return 0;
+}
+
+static void mlxsw_sp_kvdl_part_fini(struct mlxsw_sp *mlxsw_sp,
+				    unsigned int part_index)
+{
+	struct mlxsw_sp_kvdl_part *part;
+
+	part = mlxsw_sp_kvdl_part_find(mlxsw_sp, part_index);
+	if (!part)
+		return;
+
+	list_del(&part->list);
+	kfree(part);
+}
+
+static int mlxsw_sp_kvdl_parts_init(struct mlxsw_sp *mlxsw_sp)
+{
+	int err, i;
+
+	INIT_LIST_HEAD(&mlxsw_sp->kvdl->parts_list);
 
-		for (i = 0; i < type_entries; i++)
-			set_bit(entry_index + i, mlxsw_sp->kvdl.usage);
-		*p_entry_index = entry_index;
-		return 0;
+	for (i = 0; i < ARRAY_SIZE(kvdl_parts_info); i++) {
+		err = mlxsw_sp_kvdl_part_init(mlxsw_sp, i);
+		if (err)
+			goto err_kvdl_part_init;
 	}
-	return -ENOBUFS;
+
+	return 0;
+
+err_kvdl_part_init:
+	for (i--; i >= 0; i--)
+		mlxsw_sp_kvdl_part_fini(mlxsw_sp, i);
+	return err;
 }
 
-void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index)
+static void mlxsw_sp_kvdl_parts_fini(struct mlxsw_sp *mlxsw_sp)
 {
-	int type_entries;
 	int i;
 
-	if (entry_index < MLXSW_SP_KVDL_CHUNKS_BASE)
-		type_entries = 1;
-	else
-		type_entries = MLXSW_SP_CHUNK_MAX;
-	for (i = 0; i < type_entries; i++)
-		clear_bit(entry_index + i, mlxsw_sp->kvdl.usage);
+	for (i = ARRAY_SIZE(kvdl_parts_info) - 1; i >= 0; i--)
+		mlxsw_sp_kvdl_part_fini(mlxsw_sp, i);
+}
+
+int mlxsw_sp_kvdl_init(struct mlxsw_sp *mlxsw_sp)
+{
+	struct mlxsw_sp_kvdl *kvdl;
+	int err;
+
+	kvdl = kzalloc(sizeof(*mlxsw_sp->kvdl), GFP_KERNEL);
+	if (!kvdl)
+		return -ENOMEM;
+	mlxsw_sp->kvdl = kvdl;
+
+	err = mlxsw_sp_kvdl_parts_init(mlxsw_sp);
+	if (err)
+		goto err_kvdl_parts_init;
+
+	return 0;
+
+err_kvdl_parts_init:
+	kfree(mlxsw_sp->kvdl);
+	return err;
+}
+
+void mlxsw_sp_kvdl_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	mlxsw_sp_kvdl_parts_fini(mlxsw_sp);
+	kfree(mlxsw_sp->kvdl);
 }