x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.

The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:

<__hrtimer_run_queues+249>:  nopl   0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>:  mov    %r14,%rdi
<__hrtimer_run_queues+257>:  cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>:  mov    %eax,%r12d
<__hrtimer_run_queues+266>:  xchg   %ax,%ax
<__hrtimer_run_queues+268>:  mov    %r13,%rdi

Which triggers this crash:

  BUG: unable to handle page fault for address: 00000000000f41c9
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
  RIP: 0010:__hrtimer_run_queues+0x106/0x230

Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.

The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.

During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.

Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.

[ mingo: Refined the changelog ]

Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

1 files changed, 995 insertions, 0 deletions

diff --git a/net/devlink/sb.c b/net/devlink/sb.c
new file mode 100644
index 000000000..129bd016e
--- /dev/null
+++ b/net/devlink/sb.c
@@ -0,0 +1,995 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
+ */
+
+#include "devl_internal.h"
+
+struct devlink_sb {
+	struct list_head list;
+	unsigned int index;
+	u32 size;
+	u16 ingress_pools_count;
+	u16 egress_pools_count;
+	u16 ingress_tc_count;
+	u16 egress_tc_count;
+};
+
+static u16 devlink_sb_pool_count(struct devlink_sb *devlink_sb)
+{
+	return devlink_sb->ingress_pools_count + devlink_sb->egress_pools_count;
+}
+
+static struct devlink_sb *devlink_sb_get_by_index(struct devlink *devlink,
+						  unsigned int sb_index)
+{
+	struct devlink_sb *devlink_sb;
+
+	list_for_each_entry(devlink_sb, &devlink->sb_list, list) {
+		if (devlink_sb->index == sb_index)
+			return devlink_sb;
+	}
+	return NULL;
+}
+
+static bool devlink_sb_index_exists(struct devlink *devlink,
+				    unsigned int sb_index)
+{
+	return devlink_sb_get_by_index(devlink, sb_index);
+}
+
+static struct devlink_sb *devlink_sb_get_from_attrs(struct devlink *devlink,
+						    struct nlattr **attrs)
+{
+	if (attrs[DEVLINK_ATTR_SB_INDEX]) {
+		u32 sb_index = nla_get_u32(attrs[DEVLINK_ATTR_SB_INDEX]);
+		struct devlink_sb *devlink_sb;
+
+		devlink_sb = devlink_sb_get_by_index(devlink, sb_index);
+		if (!devlink_sb)
+			return ERR_PTR(-ENODEV);
+		return devlink_sb;
+	}
+	return ERR_PTR(-EINVAL);
+}
+
+static struct devlink_sb *devlink_sb_get_from_info(struct devlink *devlink,
+						   struct genl_info *info)
+{
+	return devlink_sb_get_from_attrs(devlink, info->attrs);
+}
+
+static int devlink_sb_pool_index_get_from_attrs(struct devlink_sb *devlink_sb,
+						struct nlattr **attrs,
+						u16 *p_pool_index)
+{
+	u16 val;
+
+	if (!attrs[DEVLINK_ATTR_SB_POOL_INDEX])
+		return -EINVAL;
+
+	val = nla_get_u16(attrs[DEVLINK_ATTR_SB_POOL_INDEX]);
+	if (val >= devlink_sb_pool_count(devlink_sb))
+		return -EINVAL;
+	*p_pool_index = val;
+	return 0;
+}
+
+static int devlink_sb_pool_index_get_from_info(struct devlink_sb *devlink_sb,
+					       struct genl_info *info,
+					       u16 *p_pool_index)
+{
+	return devlink_sb_pool_index_get_from_attrs(devlink_sb, info->attrs,
+						    p_pool_index);
+}
+
+static int
+devlink_sb_pool_type_get_from_attrs(struct nlattr **attrs,
+				    enum devlink_sb_pool_type *p_pool_type)
+{
+	u8 val;
+
+	if (!attrs[DEVLINK_ATTR_SB_POOL_TYPE])
+		return -EINVAL;
+
+	val = nla_get_u8(attrs[DEVLINK_ATTR_SB_POOL_TYPE]);
+	if (val != DEVLINK_SB_POOL_TYPE_INGRESS &&
+	    val != DEVLINK_SB_POOL_TYPE_EGRESS)
+		return -EINVAL;
+	*p_pool_type = val;
+	return 0;
+}
+
+static int
+devlink_sb_pool_type_get_from_info(struct genl_info *info,
+				   enum devlink_sb_pool_type *p_pool_type)
+{
+	return devlink_sb_pool_type_get_from_attrs(info->attrs, p_pool_type);
+}
+
+static int
+devlink_sb_th_type_get_from_attrs(struct nlattr **attrs,
+				  enum devlink_sb_threshold_type *p_th_type)
+{
+	u8 val;
+
+	if (!attrs[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE])
+		return -EINVAL;
+
+	val = nla_get_u8(attrs[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE]);
+	if (val != DEVLINK_SB_THRESHOLD_TYPE_STATIC &&
+	    val != DEVLINK_SB_THRESHOLD_TYPE_DYNAMIC)
+		return -EINVAL;
+	*p_th_type = val;
+	return 0;
+}
+
+static int
+devlink_sb_th_type_get_from_info(struct genl_info *info,
+				 enum devlink_sb_threshold_type *p_th_type)
+{
+	return devlink_sb_th_type_get_from_attrs(info->attrs, p_th_type);
+}
+
+static int
+devlink_sb_tc_index_get_from_attrs(struct devlink_sb *devlink_sb,
+				   struct nlattr **attrs,
+				   enum devlink_sb_pool_type pool_type,
+				   u16 *p_tc_index)
+{
+	u16 val;
+
+	if (!attrs[DEVLINK_ATTR_SB_TC_INDEX])
+		return -EINVAL;
+
+	val = nla_get_u16(attrs[DEVLINK_ATTR_SB_TC_INDEX]);
+	if (pool_type == DEVLINK_SB_POOL_TYPE_INGRESS &&
+	    val >= devlink_sb->ingress_tc_count)
+		return -EINVAL;
+	if (pool_type == DEVLINK_SB_POOL_TYPE_EGRESS &&
+	    val >= devlink_sb->egress_tc_count)
+		return -EINVAL;
+	*p_tc_index = val;
+	return 0;
+}
+
+static int
+devlink_sb_tc_index_get_from_info(struct devlink_sb *devlink_sb,
+				  struct genl_info *info,
+				  enum devlink_sb_pool_type pool_type,
+				  u16 *p_tc_index)
+{
+	return devlink_sb_tc_index_get_from_attrs(devlink_sb, info->attrs,
+						  pool_type, p_tc_index);
+}
+
+static int devlink_nl_sb_fill(struct sk_buff *msg, struct devlink *devlink,
+			      struct devlink_sb *devlink_sb,
+			      enum devlink_command cmd, u32 portid,
+			      u32 seq, int flags)
+{
+	void *hdr;
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_SB_SIZE, devlink_sb->size))
+		goto nla_put_failure;
+	if (nla_put_u16(msg, DEVLINK_ATTR_SB_INGRESS_POOL_COUNT,
+			devlink_sb->ingress_pools_count))
+		goto nla_put_failure;
+	if (nla_put_u16(msg, DEVLINK_ATTR_SB_EGRESS_POOL_COUNT,
+			devlink_sb->egress_pools_count))
+		goto nla_put_failure;
+	if (nla_put_u16(msg, DEVLINK_ATTR_SB_INGRESS_TC_COUNT,
+			devlink_sb->ingress_tc_count))
+		goto nla_put_failure;
+	if (nla_put_u16(msg, DEVLINK_ATTR_SB_EGRESS_TC_COUNT,
+			devlink_sb->egress_tc_count))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+int devlink_nl_sb_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink *devlink = devlink_nl_ctx(info)->devlink;
+	struct devlink_sb *devlink_sb;
+	struct sk_buff *msg;
+	int err;
+
+	devlink_sb = devlink_sb_get_from_info(devlink, info);
+	if (IS_ERR(devlink_sb))
+		return PTR_ERR(devlink_sb);
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_nl_sb_fill(msg, devlink, devlink_sb,
+				 DEVLINK_CMD_SB_NEW,
+				 info->snd_portid, info->snd_seq, 0);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static int
+devlink_nl_sb_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
+			   struct netlink_callback *cb, int flags)
+{
+	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
+	struct devlink_sb *devlink_sb;
+	int idx = 0;
+	int err = 0;
+
+	list_for_each_entry(devlink_sb, &devlink->sb_list, list) {
+		if (idx < state->idx) {
+			idx++;
+			continue;
+		}
+		err = devlink_nl_sb_fill(msg, devlink, devlink_sb,
+					 DEVLINK_CMD_SB_NEW,
+					 NETLINK_CB(cb->skb).portid,
+					 cb->nlh->nlmsg_seq, flags);
+		if (err) {
+			state->idx = idx;
+			break;
+		}
+		idx++;
+	}
+
+	return err;
+}
+
+int devlink_nl_sb_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_sb_get_dump_one);
+}
+
+static int devlink_nl_sb_pool_fill(struct sk_buff *msg, struct devlink *devlink,
+				   struct devlink_sb *devlink_sb,
+				   u16 pool_index, enum devlink_command cmd,
+				   u32 portid, u32 seq, int flags)
+{
+	struct devlink_sb_pool_info pool_info;
+	void *hdr;
+	int err;
+
+	err = devlink->ops->sb_pool_get(devlink, devlink_sb->index,
+					pool_index, &pool_info);
+	if (err)
+		return err;
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index))
+		goto nla_put_failure;
+	if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index))
+		goto nla_put_failure;
+	if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_TYPE, pool_info.pool_type))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_SB_POOL_SIZE, pool_info.size))
+		goto nla_put_failure;
+	if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE,
+		       pool_info.threshold_type))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_SB_POOL_CELL_SIZE,
+			pool_info.cell_size))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+int devlink_nl_sb_pool_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink *devlink = devlink_nl_ctx(info)->devlink;
+	struct devlink_sb *devlink_sb;
+	struct sk_buff *msg;
+	u16 pool_index;
+	int err;
+
+	devlink_sb = devlink_sb_get_from_info(devlink, info);
+	if (IS_ERR(devlink_sb))
+		return PTR_ERR(devlink_sb);
+
+	err = devlink_sb_pool_index_get_from_info(devlink_sb, info,
+						  &pool_index);
+	if (err)
+		return err;
+
+	if (!devlink->ops->sb_pool_get)
+		return -EOPNOTSUPP;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_nl_sb_pool_fill(msg, devlink, devlink_sb, pool_index,
+				      DEVLINK_CMD_SB_POOL_NEW,
+				      info->snd_portid, info->snd_seq, 0);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static int __sb_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx,
+				struct devlink *devlink,
+				struct devlink_sb *devlink_sb,
+				u32 portid, u32 seq, int flags)
+{
+	u16 pool_count = devlink_sb_pool_count(devlink_sb);
+	u16 pool_index;
+	int err;
+
+	for (pool_index = 0; pool_index < pool_count; pool_index++) {
+		if (*p_idx < start) {
+			(*p_idx)++;
+			continue;
+		}
+		err = devlink_nl_sb_pool_fill(msg, devlink,
+					      devlink_sb,
+					      pool_index,
+					      DEVLINK_CMD_SB_POOL_NEW,
+					      portid, seq, flags);
+		if (err)
+			return err;
+		(*p_idx)++;
+	}
+	return 0;
+}
+
+static int
+devlink_nl_sb_pool_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
+				struct netlink_callback *cb, int flags)
+{
+	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
+	struct devlink_sb *devlink_sb;
+	int err = 0;
+	int idx = 0;
+
+	if (!devlink->ops->sb_pool_get)
+		return 0;
+
+	list_for_each_entry(devlink_sb, &devlink->sb_list, list) {
+		err = __sb_pool_get_dumpit(msg, state->idx, &idx,
+					   devlink, devlink_sb,
+					   NETLINK_CB(cb->skb).portid,
+					   cb->nlh->nlmsg_seq, flags);
+		if (err == -EOPNOTSUPP) {
+			err = 0;
+		} else if (err) {
+			state->idx = idx;
+			break;
+		}
+	}
+
+	return err;
+}
+
+int devlink_nl_sb_pool_get_dumpit(struct sk_buff *skb,
+				  struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_sb_pool_get_dump_one);
+}
+
+static int devlink_sb_pool_set(struct devlink *devlink, unsigned int sb_index,
+			       u16 pool_index, u32 size,
+			       enum devlink_sb_threshold_type threshold_type,
+			       struct netlink_ext_ack *extack)
+
+{
+	const struct devlink_ops *ops = devlink->ops;
+
+	if (ops->sb_pool_set)
+		return ops->sb_pool_set(devlink, sb_index, pool_index,
+					size, threshold_type, extack);
+	return -EOPNOTSUPP;
+}
+
+int devlink_nl_sb_pool_set_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink *devlink = devlink_nl_ctx(info)->devlink;
+	enum devlink_sb_threshold_type threshold_type;
+	struct devlink_sb *devlink_sb;
+	u16 pool_index;
+	u32 size;
+	int err;
+
+	devlink_sb = devlink_sb_get_from_info(devlink, info);
+	if (IS_ERR(devlink_sb))
+		return PTR_ERR(devlink_sb);
+
+	err = devlink_sb_pool_index_get_from_info(devlink_sb, info,
+						  &pool_index);
+	if (err)
+		return err;
+
+	err = devlink_sb_th_type_get_from_info(info, &threshold_type);
+	if (err)
+		return err;
+
+	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SB_POOL_SIZE))
+		return -EINVAL;
+
+	size = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_POOL_SIZE]);
+	return devlink_sb_pool_set(devlink, devlink_sb->index,
+				   pool_index, size, threshold_type,
+				   info->extack);
+}
+
+static int devlink_nl_sb_port_pool_fill(struct sk_buff *msg,
+					struct devlink *devlink,
+					struct devlink_port *devlink_port,
+					struct devlink_sb *devlink_sb,
+					u16 pool_index,
+					enum devlink_command cmd,
+					u32 portid, u32 seq, int flags)
+{
+	const struct devlink_ops *ops = devlink->ops;
+	u32 threshold;
+	void *hdr;
+	int err;
+
+	err = ops->sb_port_pool_get(devlink_port, devlink_sb->index,
+				    pool_index, &threshold);
+	if (err)
+		return err;
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index))
+		goto nla_put_failure;
+	if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_SB_THRESHOLD, threshold))
+		goto nla_put_failure;
+
+	if (ops->sb_occ_port_pool_get) {
+		u32 cur;
+		u32 max;
+
+		err = ops->sb_occ_port_pool_get(devlink_port, devlink_sb->index,
+						pool_index, &cur, &max);
+		if (err && err != -EOPNOTSUPP)
+			goto sb_occ_get_failure;
+		if (!err) {
+			if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur))
+				goto nla_put_failure;
+			if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_MAX, max))
+				goto nla_put_failure;
+		}
+	}
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	err = -EMSGSIZE;
+sb_occ_get_failure:
+	genlmsg_cancel(msg, hdr);
+	return err;
+}
+
+int devlink_nl_sb_port_pool_get_doit(struct sk_buff *skb,
+				     struct genl_info *info)
+{
+	struct devlink_port *devlink_port = devlink_nl_ctx(info)->devlink_port;
+	struct devlink *devlink = devlink_port->devlink;
+	struct devlink_sb *devlink_sb;
+	struct sk_buff *msg;
+	u16 pool_index;
+	int err;
+
+	devlink_sb = devlink_sb_get_from_info(devlink, info);
+	if (IS_ERR(devlink_sb))
+		return PTR_ERR(devlink_sb);
+
+	err = devlink_sb_pool_index_get_from_info(devlink_sb, info,
+						  &pool_index);
+	if (err)
+		return err;
+
+	if (!devlink->ops->sb_port_pool_get)
+		return -EOPNOTSUPP;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_nl_sb_port_pool_fill(msg, devlink, devlink_port,
+					   devlink_sb, pool_index,
+					   DEVLINK_CMD_SB_PORT_POOL_NEW,
+					   info->snd_portid, info->snd_seq, 0);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static int __sb_port_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx,
+				     struct devlink *devlink,
+				     struct devlink_sb *devlink_sb,
+				     u32 portid, u32 seq, int flags)
+{
+	struct devlink_port *devlink_port;
+	u16 pool_count = devlink_sb_pool_count(devlink_sb);
+	unsigned long port_index;
+	u16 pool_index;
+	int err;
+
+	xa_for_each(&devlink->ports, port_index, devlink_port) {
+		for (pool_index = 0; pool_index < pool_count; pool_index++) {
+			if (*p_idx < start) {
+				(*p_idx)++;
+				continue;
+			}
+			err = devlink_nl_sb_port_pool_fill(msg, devlink,
+							   devlink_port,
+							   devlink_sb,
+							   pool_index,
+							   DEVLINK_CMD_SB_PORT_POOL_NEW,
+							   portid, seq, flags);
+			if (err)
+				return err;
+			(*p_idx)++;
+		}
+	}
+	return 0;
+}
+
+static int
+devlink_nl_sb_port_pool_get_dump_one(struct sk_buff *msg,
+				     struct devlink *devlink,
+				     struct netlink_callback *cb, int flags)
+{
+	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
+	struct devlink_sb *devlink_sb;
+	int idx = 0;
+	int err = 0;
+
+	if (!devlink->ops->sb_port_pool_get)
+		return 0;
+
+	list_for_each_entry(devlink_sb, &devlink->sb_list, list) {
+		err = __sb_port_pool_get_dumpit(msg, state->idx, &idx,
+						devlink, devlink_sb,
+						NETLINK_CB(cb->skb).portid,
+						cb->nlh->nlmsg_seq, flags);
+		if (err == -EOPNOTSUPP) {
+			err = 0;
+		} else if (err) {
+			state->idx = idx;
+			break;
+		}
+	}
+
+	return err;
+}
+
+int devlink_nl_sb_port_pool_get_dumpit(struct sk_buff *skb,
+				       struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb, devlink_nl_sb_port_pool_get_dump_one);
+}
+
+static int devlink_sb_port_pool_set(struct devlink_port *devlink_port,
+				    unsigned int sb_index, u16 pool_index,
+				    u32 threshold,
+				    struct netlink_ext_ack *extack)
+
+{
+	const struct devlink_ops *ops = devlink_port->devlink->ops;
+
+	if (ops->sb_port_pool_set)
+		return ops->sb_port_pool_set(devlink_port, sb_index,
+					     pool_index, threshold, extack);
+	return -EOPNOTSUPP;
+}
+
+int devlink_nl_sb_port_pool_set_doit(struct sk_buff *skb,
+				     struct genl_info *info)
+{
+	struct devlink_port *devlink_port = devlink_nl_ctx(info)->devlink_port;
+	struct devlink *devlink = devlink_nl_ctx(info)->devlink;
+	struct devlink_sb *devlink_sb;
+	u16 pool_index;
+	u32 threshold;
+	int err;
+
+	devlink_sb = devlink_sb_get_from_info(devlink, info);
+	if (IS_ERR(devlink_sb))
+		return PTR_ERR(devlink_sb);
+
+	err = devlink_sb_pool_index_get_from_info(devlink_sb, info,
+						  &pool_index);
+	if (err)
+		return err;
+
+	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SB_THRESHOLD))
+		return -EINVAL;
+
+	threshold = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_THRESHOLD]);
+	return devlink_sb_port_pool_set(devlink_port, devlink_sb->index,
+					pool_index, threshold, info->extack);
+}
+
+static int
+devlink_nl_sb_tc_pool_bind_fill(struct sk_buff *msg, struct devlink *devlink,
+				struct devlink_port *devlink_port,
+				struct devlink_sb *devlink_sb, u16 tc_index,
+				enum devlink_sb_pool_type pool_type,
+				enum devlink_command cmd,
+				u32 portid, u32 seq, int flags)
+{
+	const struct devlink_ops *ops = devlink->ops;
+	u16 pool_index;
+	u32 threshold;
+	void *hdr;
+	int err;
+
+	err = ops->sb_tc_pool_bind_get(devlink_port, devlink_sb->index,
+				       tc_index, pool_type,
+				       &pool_index, &threshold);
+	if (err)
+		return err;
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index))
+		goto nla_put_failure;
+	if (nla_put_u16(msg, DEVLINK_ATTR_SB_TC_INDEX, tc_index))
+		goto nla_put_failure;
+	if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_TYPE, pool_type))
+		goto nla_put_failure;
+	if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_SB_THRESHOLD, threshold))
+		goto nla_put_failure;
+
+	if (ops->sb_occ_tc_port_bind_get) {
+		u32 cur;
+		u32 max;
+
+		err = ops->sb_occ_tc_port_bind_get(devlink_port,
+						   devlink_sb->index,
+						   tc_index, pool_type,
+						   &cur, &max);
+		if (err && err != -EOPNOTSUPP)
+			return err;
+		if (!err) {
+			if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur))
+				goto nla_put_failure;
+			if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_MAX, max))
+				goto nla_put_failure;
+		}
+	}
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+int devlink_nl_sb_tc_pool_bind_get_doit(struct sk_buff *skb,
+					struct genl_info *info)
+{
+	struct devlink_port *devlink_port = devlink_nl_ctx(info)->devlink_port;
+	struct devlink *devlink = devlink_port->devlink;
+	struct devlink_sb *devlink_sb;
+	struct sk_buff *msg;
+	enum devlink_sb_pool_type pool_type;
+	u16 tc_index;
+	int err;
+
+	devlink_sb = devlink_sb_get_from_info(devlink, info);
+	if (IS_ERR(devlink_sb))
+		return PTR_ERR(devlink_sb);
+
+	err = devlink_sb_pool_type_get_from_info(info, &pool_type);
+	if (err)
+		return err;
+
+	err = devlink_sb_tc_index_get_from_info(devlink_sb, info,
+						pool_type, &tc_index);
+	if (err)
+		return err;
+
+	if (!devlink->ops->sb_tc_pool_bind_get)
+		return -EOPNOTSUPP;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink, devlink_port,
+					      devlink_sb, tc_index, pool_type,
+					      DEVLINK_CMD_SB_TC_POOL_BIND_NEW,
+					      info->snd_portid,
+					      info->snd_seq, 0);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static int __sb_tc_pool_bind_get_dumpit(struct sk_buff *msg,
+					int start, int *p_idx,
+					struct devlink *devlink,
+					struct devlink_sb *devlink_sb,
+					u32 portid, u32 seq, int flags)
+{
+	struct devlink_port *devlink_port;
+	unsigned long port_index;
+	u16 tc_index;
+	int err;
+
+	xa_for_each(&devlink->ports, port_index, devlink_port) {
+		for (tc_index = 0;
+		     tc_index < devlink_sb->ingress_tc_count; tc_index++) {
+			if (*p_idx < start) {
+				(*p_idx)++;
+				continue;
+			}
+			err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink,
+							      devlink_port,
+							      devlink_sb,
+							      tc_index,
+							      DEVLINK_SB_POOL_TYPE_INGRESS,
+							      DEVLINK_CMD_SB_TC_POOL_BIND_NEW,
+							      portid, seq,
+							      flags);
+			if (err)
+				return err;
+			(*p_idx)++;
+		}
+		for (tc_index = 0;
+		     tc_index < devlink_sb->egress_tc_count; tc_index++) {
+			if (*p_idx < start) {
+				(*p_idx)++;
+				continue;
+			}
+			err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink,
+							      devlink_port,
+							      devlink_sb,
+							      tc_index,
+							      DEVLINK_SB_POOL_TYPE_EGRESS,
+							      DEVLINK_CMD_SB_TC_POOL_BIND_NEW,
+							      portid, seq,
+							      flags);
+			if (err)
+				return err;
+			(*p_idx)++;
+		}
+	}
+	return 0;
+}
+
+static int devlink_nl_sb_tc_pool_bind_get_dump_one(struct sk_buff *msg,
+						   struct devlink *devlink,
+						   struct netlink_callback *cb,
+						   int flags)
+{
+	struct devlink_nl_dump_state *state = devlink_dump_state(cb);
+	struct devlink_sb *devlink_sb;
+	int idx = 0;
+	int err = 0;
+
+	if (!devlink->ops->sb_tc_pool_bind_get)
+		return 0;
+
+	list_for_each_entry(devlink_sb, &devlink->sb_list, list) {
+		err = __sb_tc_pool_bind_get_dumpit(msg, state->idx, &idx,
+						   devlink, devlink_sb,
+						   NETLINK_CB(cb->skb).portid,
+						   cb->nlh->nlmsg_seq, flags);
+		if (err == -EOPNOTSUPP) {
+			err = 0;
+		} else if (err) {
+			state->idx = idx;
+			break;
+		}
+	}
+
+	return err;
+}
+
+int devlink_nl_sb_tc_pool_bind_get_dumpit(struct sk_buff *skb,
+					  struct netlink_callback *cb)
+{
+	return devlink_nl_dumpit(skb, cb,
+				 devlink_nl_sb_tc_pool_bind_get_dump_one);
+}
+
+static int devlink_sb_tc_pool_bind_set(struct devlink_port *devlink_port,
+				       unsigned int sb_index, u16 tc_index,
+				       enum devlink_sb_pool_type pool_type,
+				       u16 pool_index, u32 threshold,
+				       struct netlink_ext_ack *extack)
+
+{
+	const struct devlink_ops *ops = devlink_port->devlink->ops;
+
+	if (ops->sb_tc_pool_bind_set)
+		return ops->sb_tc_pool_bind_set(devlink_port, sb_index,
+						tc_index, pool_type,
+						pool_index, threshold, extack);
+	return -EOPNOTSUPP;
+}
+
+int devlink_nl_sb_tc_pool_bind_set_doit(struct sk_buff *skb,
+					struct genl_info *info)
+{
+	struct devlink_port *devlink_port = devlink_nl_ctx(info)->devlink_port;
+	struct devlink *devlink = devlink_nl_ctx(info)->devlink;
+	enum devlink_sb_pool_type pool_type;
+	struct devlink_sb *devlink_sb;
+	u16 tc_index;
+	u16 pool_index;
+	u32 threshold;
+	int err;
+
+	devlink_sb = devlink_sb_get_from_info(devlink, info);
+	if (IS_ERR(devlink_sb))
+		return PTR_ERR(devlink_sb);
+
+	err = devlink_sb_pool_type_get_from_info(info, &pool_type);
+	if (err)
+		return err;
+
+	err = devlink_sb_tc_index_get_from_info(devlink_sb, info,
+						pool_type, &tc_index);
+	if (err)
+		return err;
+
+	err = devlink_sb_pool_index_get_from_info(devlink_sb, info,
+						  &pool_index);
+	if (err)
+		return err;
+
+	if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SB_THRESHOLD))
+		return -EINVAL;
+
+	threshold = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_THRESHOLD]);
+	return devlink_sb_tc_pool_bind_set(devlink_port, devlink_sb->index,
+					   tc_index, pool_type,
+					   pool_index, threshold, info->extack);
+}
+
+int devlink_nl_sb_occ_snapshot_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink *devlink = devlink_nl_ctx(info)->devlink;
+	const struct devlink_ops *ops = devlink->ops;
+	struct devlink_sb *devlink_sb;
+
+	devlink_sb = devlink_sb_get_from_info(devlink, info);
+	if (IS_ERR(devlink_sb))
+		return PTR_ERR(devlink_sb);
+
+	if (ops->sb_occ_snapshot)
+		return ops->sb_occ_snapshot(devlink, devlink_sb->index);
+	return -EOPNOTSUPP;
+}
+
+int devlink_nl_sb_occ_max_clear_doit(struct sk_buff *skb,
+				     struct genl_info *info)
+{
+	struct devlink *devlink = devlink_nl_ctx(info)->devlink;
+	const struct devlink_ops *ops = devlink->ops;
+	struct devlink_sb *devlink_sb;
+
+	devlink_sb = devlink_sb_get_from_info(devlink, info);
+	if (IS_ERR(devlink_sb))
+		return PTR_ERR(devlink_sb);
+
+	if (ops->sb_occ_max_clear)
+		return ops->sb_occ_max_clear(devlink, devlink_sb->index);
+	return -EOPNOTSUPP;
+}
+
+int devl_sb_register(struct devlink *devlink, unsigned int sb_index,
+		     u32 size, u16 ingress_pools_count,
+		     u16 egress_pools_count, u16 ingress_tc_count,
+		     u16 egress_tc_count)
+{
+	struct devlink_sb *devlink_sb;
+
+	lockdep_assert_held(&devlink->lock);
+
+	if (devlink_sb_index_exists(devlink, sb_index))
+		return -EEXIST;
+
+	devlink_sb = kzalloc_obj(*devlink_sb);
+	if (!devlink_sb)
+		return -ENOMEM;
+	devlink_sb->index = sb_index;
+	devlink_sb->size = size;
+	devlink_sb->ingress_pools_count = ingress_pools_count;
+	devlink_sb->egress_pools_count = egress_pools_count;
+	devlink_sb->ingress_tc_count = ingress_tc_count;
+	devlink_sb->egress_tc_count = egress_tc_count;
+	list_add_tail(&devlink_sb->list, &devlink->sb_list);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devl_sb_register);
+
+int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
+			u32 size, u16 ingress_pools_count,
+			u16 egress_pools_count, u16 ingress_tc_count,
+			u16 egress_tc_count)
+{
+	int err;
+
+	devl_lock(devlink);
+	err = devl_sb_register(devlink, sb_index, size, ingress_pools_count,
+			       egress_pools_count, ingress_tc_count,
+			       egress_tc_count);
+	devl_unlock(devlink);
+	return err;
+}
+EXPORT_SYMBOL_GPL(devlink_sb_register);
+
+void devl_sb_unregister(struct devlink *devlink, unsigned int sb_index)
+{
+	struct devlink_sb *devlink_sb;
+
+	lockdep_assert_held(&devlink->lock);
+
+	devlink_sb = devlink_sb_get_by_index(devlink, sb_index);
+	WARN_ON(!devlink_sb);
+	list_del(&devlink_sb->list);
+	kfree(devlink_sb);
+}
+EXPORT_SYMBOL_GPL(devl_sb_unregister);
+
+void devlink_sb_unregister(struct devlink *devlink, unsigned int sb_index)
+{
+	devl_lock(devlink);
+	devl_sb_unregister(devlink, sb_index);
+	devl_unlock(devlink);
+}
+EXPORT_SYMBOL_GPL(devlink_sb_unregister);