Merge tag 'net-next-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextHEADmaster

Pull networking updates from Jakub Kicinski:
 "Not much excitement - a handful of large patchsets (devmem among them)
  did not make it in time.

  Core & protocols:

   - Use local_lock in addition to local_bh_disable() to protect per-CPU
     resources in networking, a step closer for local_bh_disable() not
     to act as a big lock on PREEMPT_RT

   - Use flex array for netdevice priv area, ensure its cache alignment

   - Add a sysctl knob to allow user to specify a default rto_min at
     socket init time. Bit of a big hammer but multiple companies were
     independently carrying such patch downstream so clearly it's useful

   - Support scheduling transmission of packets based on CLOCK_TAI

   - Un-pin TCP TIMEWAIT timer to avoid it firing on CPUs later cordoned
     off using cpusets

   - Support multiple L2TPv3 UDP tunnels using the same 5-tuple address

   - Allow configuration of multipath hash seed, to both allow
     synchronizing hashing of two routers, and preventing partial
     accidental sync

   - Improve TCP compliance with RFC 9293 for simultaneous connect()

   - Support sending NAT keepalives in IPsec ESP in UDP states.
     Userspace IKE daemon had to do this before, but the kernel can
     better keep track of it

   - Support sending supervision HSR frames with MAC addresses stored in
     ProxyNodeTable when RedBox (i.e. HSR-SAN) is enabled

   - Introduce IPPROTO_SMC for selecting SMC when socket is created

   - Allow UDP GSO transmit from devices with no checksum offload

   - openvswitch: add packet sampling via psample, separating the
     sampled traffic from "upcall" packets sent to user space for
     forwarding

   - nf_tables: shrink memory consumption for transaction objects

  Things we sprinkled into general kernel code:

   - Power Sequencing subsystem (used by Qualcomm Bluetooth driver for
     QCA6390)           [ Already merged separately - Linus ]

   - Add IRQ information in sysfs for auxiliary bus

   - Introduce guard definition for local_lock

   - Add aligned flavor of __cacheline_group_{begin, end}() markings for
     grouping fields in structures

  BPF:

   - Notify user space (via epoll) when a struct_ops object is getting
     detached/unregistered

   - Add new kfuncs for a generic, open-coded bits iterator

   - Enable BPF programs to declare arrays of kptr, bpf_rb_root, and
     bpf_list_head

   - Support resilient split BTF which cuts down on duplication and
     makes BTF as compact as possible WRT BTF from modules

   - Add support for dumping kfunc prototypes from BTF which enables
     both detecting as well as dumping compilable prototypes for kfuncs

   - riscv64 BPF JIT improvements in particular to add 12-argument
     support for BPF trampolines and to utilize bpf_prog_pack for the
     latter

   - Add the capability to offload the netfilter flowtable in XDP layer
     through kfuncs

  Driver API:

   - Allow users to configure IRQ tresholds between which automatic IRQ
     moderation can choose

   - Expand Power Sourcing (PoE) status with power, class and failure
     reason. Support setting power limits

   - Track additional RSS contexts in the core, make sure configuration
     changes don't break them

   - Support IPsec crypto offload for IPv6 ESP and IPv4 UDP-encapsulated
     ESP data paths

   - Support updating firmware on SFP modules

  Tests and tooling:

   - mptcp: use net/lib.sh to manage netns

   - TCP-AO and TCP-MD5: replace debug prints used by tests with
     tracepoints

   - openvswitch: make test self-contained (don't depend on OvS CLI
     tools)

  Drivers:

   - Ethernet high-speed NICs:
      - Broadcom (bnxt):
         - increase the max total outstanding PTP TX packets to 4
         - add timestamping statistics support
         - implement netdev_queue_mgmt_ops
         - support new RSS context API
      - Intel (100G, ice, idpf):
         - implement FEC statistics and dumping signal quality indicators
         - support E825C products (with 56Gbps PHYs)
      - nVidia/Mellanox:
         - support HW-GRO
         - mlx4/mlx5: support per-queue statistics via netlink
         - obey the max number of EQs setting in sub-functions
      - AMD/Solarflare:
         - support new RSS context API
      - AMD/Pensando:
         - ionic: rework fix for doorbell miss to lower overhead and
           skip it on new HW
      - Wangxun:
         - txgbe: support Flow Director perfect filters

   - Ethernet NICs consumer, embedded and virtual:
      - Add driver for Tehuti Networks TN40xx chips
      - Add driver for Meta's internal NIC chips
      - Add driver for Ethernet MAC on Airoha EN7581 SoCs
      - Add driver for Renesas Ethernet-TSN devices
      - Google cloud vNIC:
         - flow steering support
      - Microsoft vNIC:
         - support page sizes other than 4KB on ARM64
      - vmware vNIC:
         - support latency measurement (update to version 9)
      - VirtIO net:
         - support for Byte Queue Limits
         - support configuring thresholds for automatic IRQ moderation
         - support for AF_XDP Rx zero-copy
      - Synopsys (stmmac):
         - support for STM32MP13 SoC
         - let platforms select the right PCS implementation
      - TI:
         - icssg-prueth: add multicast filtering support
         - icssg-prueth: enable PTP timestamping and PPS
      - Renesas:
         - ravb: improve Rx performance 30-400% by using page pool,
           theaded NAPI and timer-based IRQ coalescing
         - ravb: add MII support for R-Car V4M
      - Cadence (macb):
         - macb: add ARP support to Wake-On-LAN
      - Cortina:
         - use phylib for RX and TX pause configuration

   - Ethernet switches:
      - nVidia/Mellanox:
         - support configuration of multipath hash seed
         - report more accurate max MTU
         - use page_pool to improve Rx performance
      - MediaTek:
         - mt7530: add support for bridge port isolation
      - Qualcomm:
         - qca8k: add support for bridge port isolation
      - Microchip:
         - lan9371/2: add 100BaseTX PHY support
      - NXP:
         - vsc73xx: implement VLAN operations

   - Ethernet PHYs:
      - aquantia: enable support for aqr115c
      - aquantia: add support for PHY LEDs
      - realtek: add support for rtl8224 2.5Gbps PHY
      - xpcs: add memory-mapped device support
      - add BroadR-Reach link mode and support in Broadcom's PHY driver

   - CAN:
      - add document for ISO 15765-2 protocol support
      - mcp251xfd: workaround for erratum DS80000789E, use timestamps to
        catch when device returns incorrect FIFO status

   - WiFi:
      - mac80211/cfg80211:
         - parse Transmit Power Envelope (TPE) data in mac80211 instead
           of in drivers
         - improvements for 6 GHz regulatory flexibility
         - multi-link improvements
         - support multiple radios per wiphy
         - remove DEAUTH_NEED_MGD_TX_PREP flag
      - Intel (iwlwifi):
         - bump FW API to 91 for BZ/SC devices
         - report 64-bit radiotap timestamp
         - enable P2P low latency by default
         - handle Transmit Power Envelope (TPE) advertised by AP
         - remove support for older FW for new devices
         - fast resume (keeping the device configured)
         - mvm: re-enable Multi-Link Operation (MLO)
         - aggregation (A-MSDU) optimizations
      - MediaTek (mt76):
         - mt7925 Multi-Link Operation (MLO) support
      - Qualcomm (ath10k):
         - LED support for various chipsets
      - Qualcomm (ath12k):
         - remove unsupported Tx monitor handling
         - support channel 2 in 6 GHz band
         - support Spatial Multiplexing Power Save (SMPS) in 6 GHz band
         - supprt multiple BSSID (MBSSID) and Enhanced Multi-BSSID
           Advertisements (EMA)
         - support dynamic VLAN
         - add panic handler for resetting the firmware state
         - DebugFS support for datapath statistics
         - WCN7850: support for Wake on WLAN
      - Microchip (wilc1000):
         - read MAC address during probe to make it visible to user space
         - suspend/resume improvements
      - TI (wl18xx):
         - support newer firmware versions
      - RealTek (rtw89):
         - preparation for RTL8852BE-VT support
         - Wake on WLAN support for WiFi 6 chips
         - 36-bit PCI DMA support
      - RealTek (rtlwifi):
         - RTL8192DU support
      - Broadcom (brcmfmac):
         - Management Frame Protection support (to enable WPA3)

   - Bluetooth:
      - qualcomm: use the power sequencer for QCA6390
      - btusb: mediatek: add ISO data transmission functions
      - hci_bcm4377: add BCM4388 support
      - btintel: add support for BlazarU core
      - btintel: add support for Whale Peak2
      - btnxpuart: add support for AW693 A1 chipset
      - btnxpuart: add support for IW615 chipset
      - btusb: add Realtek RTL8852BE support ID 0x13d3:0x3591"

* tag 'net-next-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1589 commits)
  eth: fbnic: Fix spelling mistake "tiggerring" -> "triggering"
  tcp: Replace strncpy() with strscpy()
  wifi: ath12k: fix build vs old compiler
  tcp: Don't access uninit tcp_rsk(req)->ao_keyid in tcp_create_openreq_child().
  eth: fbnic: Write the TCAM tables used for RSS control and Rx to host
  eth: fbnic: Add L2 address programming
  eth: fbnic: Add basic Rx handling
  eth: fbnic: Add basic Tx handling
  eth: fbnic: Add link detection
  eth: fbnic: Add initial messaging to notify FW of our presence
  eth: fbnic: Implement Rx queue alloc/start/stop/free
  eth: fbnic: Implement Tx queue alloc/start/stop/free
  eth: fbnic: Allocate a netdevice and napi vectors with queues
  eth: fbnic: Add FW communication mechanism
  eth: fbnic: Add message parsing for FW messages
  eth: fbnic: Add register init to set PCIe/Ethernet device config
  eth: fbnic: Allocate core device specific structures and devlink interface
  eth: fbnic: Add scaffolding for Meta's NIC driver
  PCI: Add Meta Platforms vendor ID
  net/sched: cls_flower: propagate tca[TCA_OPTIONS] to NL_REQ_ATTR_CHECK
  ...

1 files changed, 167 insertions, 157 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 214a9fa8c6fb..8da132a1ef28 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2982,8 +2982,10 @@ static int check_subprogs(struct bpf_verifier_env *env)
 
 		if (code == (BPF_JMP | BPF_CALL) &&
 		    insn[i].src_reg == 0 &&
-		    insn[i].imm == BPF_FUNC_tail_call)
+		    insn[i].imm == BPF_FUNC_tail_call) {
 			subprog[cur_subprog].has_tail_call = true;
+			subprog[cur_subprog].tail_call_reachable = true;
+		}
 		if (BPF_CLASS(code) == BPF_LD &&
 		    (BPF_MODE(code) == BPF_ABS || BPF_MODE(code) == BPF_IND))
 			subprog[cur_subprog].has_ld_abs = true;
@@ -3215,7 +3217,8 @@ static int insn_def_regno(const struct bpf_insn *insn)
 	case BPF_ST:
 		return -1;
 	case BPF_STX:
-		if (BPF_MODE(insn->code) == BPF_ATOMIC &&
+		if ((BPF_MODE(insn->code) == BPF_ATOMIC ||
+		     BPF_MODE(insn->code) == BPF_PROBE_ATOMIC) &&
 		    (insn->imm & BPF_FETCH)) {
 			if (insn->imm == BPF_CMPXCHG)
 				return BPF_REG_0;
@@ -3991,7 +3994,7 @@ static bool idset_contains(struct bpf_idset *s, u32 id)
 	u32 i;
 
 	for (i = 0; i < s->count; ++i)
-		if (s->ids[i] == id)
+		if (s->ids[i] == (id & ~BPF_ADD_CONST))
 			return true;
 
 	return false;
@@ -4001,7 +4004,7 @@ static int idset_push(struct bpf_idset *s, u32 id)
 {
 	if (WARN_ON_ONCE(s->count >= ARRAY_SIZE(s->ids)))
 		return -EFAULT;
-	s->ids[s->count++] = id;
+	s->ids[s->count++] = id & ~BPF_ADD_CONST;
 	return 0;
 }
 
@@ -4438,8 +4441,20 @@ static bool __is_pointer_value(bool allow_ptr_leaks,
 static void assign_scalar_id_before_mov(struct bpf_verifier_env *env,
 					struct bpf_reg_state *src_reg)
 {
-	if (src_reg->type == SCALAR_VALUE && !src_reg->id &&
-	    !tnum_is_const(src_reg->var_off))
+	if (src_reg->type != SCALAR_VALUE)
+		return;
+
+	if (src_reg->id & BPF_ADD_CONST) {
+		/*
+		 * The verifier is processing rX = rY insn and
+		 * rY->id has special linked register already.
+		 * Cleared it, since multiple rX += const are not supported.
+		 */
+		src_reg->id = 0;
+		src_reg->off = 0;
+	}
+
+	if (!src_reg->id && !tnum_is_const(src_reg->var_off))
 		/* Ensure that src_reg has a valid ID that will be copied to
 		 * dst_reg and then will be used by find_equal_scalars() to
 		 * propagate min/max range.
@@ -5449,7 +5464,7 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
 		 * this program. To check that [x1, x2) overlaps with [y1, y2),
 		 * it is sufficient to check x1 < y2 && y1 < x2.
 		 */
-		if (reg->smin_value + off < p + btf_field_type_size(field->type) &&
+		if (reg->smin_value + off < p + field->size &&
 		    p < reg->umax_value + off + size) {
 			switch (field->type) {
 			case BPF_KPTR_UNREF:
@@ -7715,6 +7730,13 @@ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn
 	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
 	int err;
 
+	if (reg->type != PTR_TO_STACK && reg->type != CONST_PTR_TO_DYNPTR) {
+		verbose(env,
+			"arg#%d expected pointer to stack or const struct bpf_dynptr\n",
+			regno);
+		return -EINVAL;
+	}
+
 	/* MEM_UNINIT and MEM_RDONLY are exclusive, when applied to an
 	 * ARG_PTR_TO_DYNPTR (or ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_*):
 	 */
@@ -9464,6 +9486,10 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog,
 				return -EINVAL;
 			}
 		} else if (arg->arg_type == (ARG_PTR_TO_DYNPTR | MEM_RDONLY)) {
+			ret = check_func_arg_reg_off(env, reg, regno, ARG_PTR_TO_DYNPTR);
+			if (ret)
+				return ret;
+
 			ret = process_dynptr_func(env, regno, -1, arg->arg_type, 0);
 			if (ret)
 				return ret;
@@ -10917,7 +10943,7 @@ enum {
 };
 
 BTF_ID_LIST(kf_arg_btf_ids)
-BTF_ID(struct, bpf_dynptr_kern)
+BTF_ID(struct, bpf_dynptr)
 BTF_ID(struct, bpf_list_head)
 BTF_ID(struct, bpf_list_node)
 BTF_ID(struct, bpf_rb_root)
@@ -11190,6 +11216,9 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env,
 	if (btf_is_prog_ctx_type(&env->log, meta->btf, t, resolve_prog_type(env->prog), argno))
 		return KF_ARG_PTR_TO_CTX;
 
+	if (is_kfunc_arg_nullable(meta->btf, &args[argno]) && register_is_null(reg))
+		return KF_ARG_PTR_TO_NULL;
+
 	if (is_kfunc_arg_alloc_obj(meta->btf, &args[argno]))
 		return KF_ARG_PTR_TO_ALLOC_BTF_ID;
 
@@ -11235,9 +11264,6 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env,
 	if (is_kfunc_arg_callback(env, meta->btf, &args[argno]))
 		return KF_ARG_PTR_TO_CALLBACK;
 
-	if (is_kfunc_arg_nullable(meta->btf, &args[argno]) && register_is_null(reg))
-		return KF_ARG_PTR_TO_NULL;
-
 	if (argno + 1 < nargs &&
 	    (is_kfunc_arg_mem_size(meta->btf, &args[argno + 1], &regs[regno + 1]) ||
 	     is_kfunc_arg_const_mem_size(meta->btf, &args[argno + 1], &regs[regno + 1])))
@@ -11268,6 +11294,8 @@ static int process_kf_arg_ptr_to_btf_id(struct bpf_verifier_env *env,
 	bool strict_type_match = false;
 	const struct btf *reg_btf;
 	const char *reg_ref_tname;
+	bool taking_projection;
+	bool struct_same;
 	u32 reg_ref_id;
 
 	if (base_type(reg->type) == PTR_TO_BTF_ID) {
@@ -11307,11 +11335,19 @@ static int process_kf_arg_ptr_to_btf_id(struct bpf_verifier_env *env,
 	    btf_type_ids_nocast_alias(&env->log, reg_btf, reg_ref_id, meta->btf, ref_id))
 		strict_type_match = true;
 
-	WARN_ON_ONCE(is_kfunc_trusted_args(meta) && reg->off);
+	WARN_ON_ONCE(is_kfunc_release(meta) &&
+		     (reg->off || !tnum_is_const(reg->var_off) ||
+		      reg->var_off.value));
 
 	reg_ref_t = btf_type_skip_modifiers(reg_btf, reg_ref_id, &reg_ref_id);
 	reg_ref_tname = btf_name_by_offset(reg_btf, reg_ref_t->name_off);
-	if (!btf_struct_ids_match(&env->log, reg_btf, reg_ref_id, reg->off, meta->btf, ref_id, strict_type_match)) {
+	struct_same = btf_struct_ids_match(&env->log, reg_btf, reg_ref_id, reg->off, meta->btf, ref_id, strict_type_match);
+	/* If kfunc is accepting a projection type (ie. __sk_buff), it cannot
+	 * actually use it -- it must cast to the underlying type. So we allow
+	 * caller to pass in the underlying type.
+	 */
+	taking_projection = btf_is_projection_of(ref_tname, reg_ref_tname);
+	if (!taking_projection && !struct_same) {
 		verbose(env, "kernel function %s args#%d expected pointer to %s %s but R%d has a pointer to %s %s\n",
 			meta->func_name, argno, btf_type_str(ref_t), ref_tname, argno + 1,
 			btf_type_str(reg_ref_t), reg_ref_tname);
@@ -11651,7 +11687,7 @@ __process_kf_arg_ptr_to_graph_node(struct bpf_verifier_env *env,
 
 	node_off = reg->off + reg->var_off.value;
 	field = reg_find_field_offset(reg, node_off, node_field_type);
-	if (!field || field->offset != node_off) {
+	if (!field) {
 		verbose(env, "%s not found at offset=%u\n", node_type_name, node_off);
 		return -EINVAL;
 	}
@@ -11883,12 +11919,8 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 					return -EINVAL;
 				}
 			}
-
 			fallthrough;
 		case KF_ARG_PTR_TO_CTX:
-			/* Trusted arguments have the same offset checks as release arguments */
-			arg_type |= OBJ_RELEASE;
-			break;
 		case KF_ARG_PTR_TO_DYNPTR:
 		case KF_ARG_PTR_TO_ITER:
 		case KF_ARG_PTR_TO_LIST_HEAD:
@@ -11901,7 +11933,6 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 		case KF_ARG_PTR_TO_REFCOUNTED_KPTR:
 		case KF_ARG_PTR_TO_CONST_STR:
 		case KF_ARG_PTR_TO_WORKQUEUE:
-			/* Trusted by default */
 			break;
 		default:
 			WARN_ON_ONCE(1);
@@ -11957,12 +11988,6 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 			enum bpf_arg_type dynptr_arg_type = ARG_PTR_TO_DYNPTR;
 			int clone_ref_obj_id = 0;
 
-			if (reg->type != PTR_TO_STACK &&
-			    reg->type != CONST_PTR_TO_DYNPTR) {
-				verbose(env, "arg#%d expected pointer to stack or dynptr_ptr\n", i);
-				return -EINVAL;
-			}
-
 			if (reg->type == CONST_PTR_TO_DYNPTR)
 				dynptr_arg_type |= MEM_RDONLY;
 
@@ -12701,56 +12726,6 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 	return 0;
 }
 
-static bool signed_add_overflows(s64 a, s64 b)
-{
-	/* Do the add in u64, where overflow is well-defined */
-	s64 res = (s64)((u64)a + (u64)b);
-
-	if (b < 0)
-		return res > a;
-	return res < a;
-}
-
-static bool signed_add32_overflows(s32 a, s32 b)
-{
-	/* Do the add in u32, where overflow is well-defined */
-	s32 res = (s32)((u32)a + (u32)b);
-
-	if (b < 0)
-		return res > a;
-	return res < a;
-}
-
-static bool signed_add16_overflows(s16 a, s16 b)
-{
-	/* Do the add in u16, where overflow is well-defined */
-	s16 res = (s16)((u16)a + (u16)b);
-
-	if (b < 0)
-		return res > a;
-	return res < a;
-}
-
-static bool signed_sub_overflows(s64 a, s64 b)
-{
-	/* Do the sub in u64, where overflow is well-defined */
-	s64 res = (s64)((u64)a - (u64)b);
-
-	if (b < 0)
-		return res < a;
-	return res > a;
-}
-
-static bool signed_sub32_overflows(s32 a, s32 b)
-{
-	/* Do the sub in u32, where overflow is well-defined */
-	s32 res = (s32)((u32)a - (u32)b);
-
-	if (b < 0)
-		return res < a;
-	return res > a;
-}
-
 static bool check_reg_sane_offset(struct bpf_verifier_env *env,
 				  const struct bpf_reg_state *reg,
 				  enum bpf_reg_type type)
@@ -13232,21 +13207,15 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		 * added into the variable offset, and we copy the fixed offset
 		 * from ptr_reg.
 		 */
-		if (signed_add_overflows(smin_ptr, smin_val) ||
-		    signed_add_overflows(smax_ptr, smax_val)) {
+		if (check_add_overflow(smin_ptr, smin_val, &dst_reg->smin_value) ||
+		    check_add_overflow(smax_ptr, smax_val, &dst_reg->smax_value)) {
 			dst_reg->smin_value = S64_MIN;
 			dst_reg->smax_value = S64_MAX;
-		} else {
-			dst_reg->smin_value = smin_ptr + smin_val;
-			dst_reg->smax_value = smax_ptr + smax_val;
 		}
-		if (umin_ptr + umin_val < umin_ptr ||
-		    umax_ptr + umax_val < umax_ptr) {
+		if (check_add_overflow(umin_ptr, umin_val, &dst_reg->umin_value) ||
+		    check_add_overflow(umax_ptr, umax_val, &dst_reg->umax_value)) {
 			dst_reg->umin_value = 0;
 			dst_reg->umax_value = U64_MAX;
-		} else {
-			dst_reg->umin_value = umin_ptr + umin_val;
-			dst_reg->umax_value = umax_ptr + umax_val;
 		}
 		dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off);
 		dst_reg->off = ptr_reg->off;
@@ -13289,14 +13258,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		/* A new variable offset is created.  If the subtrahend is known
 		 * nonnegative, then any reg->range we had before is still good.
 		 */
-		if (signed_sub_overflows(smin_ptr, smax_val) ||
-		    signed_sub_overflows(smax_ptr, smin_val)) {
+		if (check_sub_overflow(smin_ptr, smax_val, &dst_reg->smin_value) ||
+		    check_sub_overflow(smax_ptr, smin_val, &dst_reg->smax_value)) {
 			/* Overflow possible, we know nothing */
 			dst_reg->smin_value = S64_MIN;
 			dst_reg->smax_value = S64_MAX;
-		} else {
-			dst_reg->smin_value = smin_ptr - smax_val;
-			dst_reg->smax_value = smax_ptr - smin_val;
 		}
 		if (umin_ptr < umax_val) {
 			/* Overflow possible, we know nothing */
@@ -13349,71 +13315,56 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 static void scalar32_min_max_add(struct bpf_reg_state *dst_reg,
 				 struct bpf_reg_state *src_reg)
 {
-	s32 smin_val = src_reg->s32_min_value;
-	s32 smax_val = src_reg->s32_max_value;
-	u32 umin_val = src_reg->u32_min_value;
-	u32 umax_val = src_reg->u32_max_value;
+	s32 *dst_smin = &dst_reg->s32_min_value;
+	s32 *dst_smax = &dst_reg->s32_max_value;
+	u32 *dst_umin = &dst_reg->u32_min_value;
+	u32 *dst_umax = &dst_reg->u32_max_value;
 
-	if (signed_add32_overflows(dst_reg->s32_min_value, smin_val) ||
-	    signed_add32_overflows(dst_reg->s32_max_value, smax_val)) {
-		dst_reg->s32_min_value = S32_MIN;
-		dst_reg->s32_max_value = S32_MAX;
-	} else {
-		dst_reg->s32_min_value += smin_val;
-		dst_reg->s32_max_value += smax_val;
+	if (check_add_overflow(*dst_smin, src_reg->s32_min_value, dst_smin) ||
+	    check_add_overflow(*dst_smax, src_reg->s32_max_value, dst_smax)) {
+		*dst_smin = S32_MIN;
+		*dst_smax = S32_MAX;
 	}
-	if (dst_reg->u32_min_value + umin_val < umin_val ||
-	    dst_reg->u32_max_value + umax_val < umax_val) {
-		dst_reg->u32_min_value = 0;
-		dst_reg->u32_max_value = U32_MAX;
-	} else {
-		dst_reg->u32_min_value += umin_val;
-		dst_reg->u32_max_value += umax_val;
+	if (check_add_overflow(*dst_umin, src_reg->u32_min_value, dst_umin) ||
+	    check_add_overflow(*dst_umax, src_reg->u32_max_value, dst_umax)) {
+		*dst_umin = 0;
+		*dst_umax = U32_MAX;
 	}
 }
 
 static void scalar_min_max_add(struct bpf_reg_state *dst_reg,
 			       struct bpf_reg_state *src_reg)
 {
-	s64 smin_val = src_reg->smin_value;
-	s64 smax_val = src_reg->smax_value;
-	u64 umin_val = src_reg->umin_value;
-	u64 umax_val = src_reg->umax_value;
+	s64 *dst_smin = &dst_reg->smin_value;
+	s64 *dst_smax = &dst_reg->smax_value;
+	u64 *dst_umin = &dst_reg->umin_value;
+	u64 *dst_umax = &dst_reg->umax_value;
 
-	if (signed_add_overflows(dst_reg->smin_value, smin_val) ||
-	    signed_add_overflows(dst_reg->smax_value, smax_val)) {
-		dst_reg->smin_value = S64_MIN;
-		dst_reg->smax_value = S64_MAX;
-	} else {
-		dst_reg->smin_value += smin_val;
-		dst_reg->smax_value += smax_val;
+	if (check_add_overflow(*dst_smin, src_reg->smin_value, dst_smin) ||
+	    check_add_overflow(*dst_smax, src_reg->smax_value, dst_smax)) {
+		*dst_smin = S64_MIN;
+		*dst_smax = S64_MAX;
 	}
-	if (dst_reg->umin_value + umin_val < umin_val ||
-	    dst_reg->umax_value + umax_val < umax_val) {
-		dst_reg->umin_value = 0;
-		dst_reg->umax_value = U64_MAX;
-	} else {
-		dst_reg->umin_value += umin_val;
-		dst_reg->umax_value += umax_val;
+	if (check_add_overflow(*dst_umin, src_reg->umin_value, dst_umin) ||
+	    check_add_overflow(*dst_umax, src_reg->umax_value, dst_umax)) {
+		*dst_umin = 0;
+		*dst_umax = U64_MAX;
 	}
 }
 
 static void scalar32_min_max_sub(struct bpf_reg_state *dst_reg,
 				 struct bpf_reg_state *src_reg)
 {
-	s32 smin_val = src_reg->s32_min_value;
-	s32 smax_val = src_reg->s32_max_value;
+	s32 *dst_smin = &dst_reg->s32_min_value;
+	s32 *dst_smax = &dst_reg->s32_max_value;
 	u32 umin_val = src_reg->u32_min_value;
 	u32 umax_val = src_reg->u32_max_value;
 
-	if (signed_sub32_overflows(dst_reg->s32_min_value, smax_val) ||
-	    signed_sub32_overflows(dst_reg->s32_max_value, smin_val)) {
+	if (check_sub_overflow(*dst_smin, src_reg->s32_max_value, dst_smin) ||
+	    check_sub_overflow(*dst_smax, src_reg->s32_min_value, dst_smax)) {
 		/* Overflow possible, we know nothing */
-		dst_reg->s32_min_value = S32_MIN;
-		dst_reg->s32_max_value = S32_MAX;
-	} else {
-		dst_reg->s32_min_value -= smax_val;
-		dst_reg->s32_max_value -= smin_val;
+		*dst_smin = S32_MIN;
+		*dst_smax = S32_MAX;
 	}
 	if (dst_reg->u32_min_value < umax_val) {
 		/* Overflow possible, we know nothing */
@@ -13429,19 +13380,16 @@ static void scalar32_min_max_sub(struct bpf_reg_state *dst_reg,
 static void scalar_min_max_sub(struct bpf_reg_state *dst_reg,
 			       struct bpf_reg_state *src_reg)
 {
-	s64 smin_val = src_reg->smin_value;
-	s64 smax_val = src_reg->smax_value;
+	s64 *dst_smin = &dst_reg->smin_value;
+	s64 *dst_smax = &dst_reg->smax_value;
 	u64 umin_val = src_reg->umin_value;
 	u64 umax_val = src_reg->umax_value;
 
-	if (signed_sub_overflows(dst_reg->smin_value, smax_val) ||
-	    signed_sub_overflows(dst_reg->smax_value, smin_val)) {
+	if (check_sub_overflow(*dst_smin, src_reg->smax_value, dst_smin) ||
+	    check_sub_overflow(*dst_smax, src_reg->smin_value, dst_smax)) {
 		/* Overflow possible, we know nothing */
-		dst_reg->smin_value = S64_MIN;
-		dst_reg->smax_value = S64_MAX;
-	} else {
-		dst_reg->smin_value -= smax_val;
-		dst_reg->smax_value -= smin_val;
+		*dst_smin = S64_MIN;
+		*dst_smax = S64_MAX;
 	}
 	if (dst_reg->umin_value < umax_val) {
 		/* Overflow possible, we know nothing */
@@ -14047,6 +13995,7 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 	struct bpf_func_state *state = vstate->frame[vstate->curframe];
 	struct bpf_reg_state *regs = state->regs, *dst_reg, *src_reg;
 	struct bpf_reg_state *ptr_reg = NULL, off_reg = {0};
+	bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64);
 	u8 opcode = BPF_OP(insn->code);
 	int err;
 
@@ -14069,11 +14018,7 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 
 	if (dst_reg->type != SCALAR_VALUE)
 		ptr_reg = dst_reg;
-	else
-		/* Make sure ID is cleared otherwise dst_reg min/max could be
-		 * incorrectly propagated into other registers by find_equal_scalars()
-		 */
-		dst_reg->id = 0;
+
 	if (BPF_SRC(insn->code) == BPF_X) {
 		src_reg = &regs[insn->src_reg];
 		if (src_reg->type != SCALAR_VALUE) {
@@ -14137,7 +14082,43 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 		verbose(env, "verifier internal error: no src_reg\n");
 		return -EINVAL;
 	}
-	return adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg);
+	err = adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg);
+	if (err)
+		return err;
+	/*
+	 * Compilers can generate the code
+	 * r1 = r2
+	 * r1 += 0x1
+	 * if r2 < 1000 goto ...
+	 * use r1 in memory access
+	 * So remember constant delta between r2 and r1 and update r1 after
+	 * 'if' condition.
+	 */
+	if (env->bpf_capable && BPF_OP(insn->code) == BPF_ADD &&
+	    dst_reg->id && is_reg_const(src_reg, alu32)) {
+		u64 val = reg_const_value(src_reg, alu32);
+
+		if ((dst_reg->id & BPF_ADD_CONST) ||
+		    /* prevent overflow in find_equal_scalars() later */
+		    val > (u32)S32_MAX) {
+			/*
+			 * If the register already went through rX += val
+			 * we cannot accumulate another val into rx->off.
+			 */
+			dst_reg->off = 0;
+			dst_reg->id = 0;
+		} else {
+			dst_reg->id |= BPF_ADD_CONST;
+			dst_reg->off = val;
+		}
+	} else {
+		/*
+		 * Make sure ID is cleared otherwise dst_reg min/max could be
+		 * incorrectly propagated into other registers by find_equal_scalars()
+		 */
+		dst_reg->id = 0;
+	}
+	return 0;
 }
 
 /* check validity of 32-bit and 64-bit arithmetic operations */
@@ -15109,12 +15090,36 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn,
 static void find_equal_scalars(struct bpf_verifier_state *vstate,
 			       struct bpf_reg_state *known_reg)
 {
+	struct bpf_reg_state fake_reg;
 	struct bpf_func_state *state;
 	struct bpf_reg_state *reg;
 
 	bpf_for_each_reg_in_vstate(vstate, state, reg, ({
-		if (reg->type == SCALAR_VALUE && reg->id == known_reg->id)
+		if (reg->type != SCALAR_VALUE || reg == known_reg)
+			continue;
+		if ((reg->id & ~BPF_ADD_CONST) != (known_reg->id & ~BPF_ADD_CONST))
+			continue;
+		if ((!(reg->id & BPF_ADD_CONST) && !(known_reg->id & BPF_ADD_CONST)) ||
+		    reg->off == known_reg->off) {
+			copy_register_state(reg, known_reg);
+		} else {
+			s32 saved_off = reg->off;
+
+			fake_reg.type = SCALAR_VALUE;
+			__mark_reg_known(&fake_reg, (s32)reg->off - (s32)known_reg->off);
+
+			/* reg = known_reg; reg += delta */
 			copy_register_state(reg, known_reg);
+			/*
+			 * Must preserve off, id and add_const flag,
+			 * otherwise another find_equal_scalars() will be incorrect.
+			 */
+			reg->off = saved_off;
+
+			scalar32_min_max_add(reg, &fake_reg);
+			scalar_min_max_add(reg, &fake_reg);
+			reg->var_off = tnum_add(reg->var_off, fake_reg.var_off);
+		}
 	}));
 }
 
@@ -16749,6 +16754,10 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
 		}
 		if (!rold->precise && exact == NOT_EXACT)
 			return true;
+		if ((rold->id & BPF_ADD_CONST) != (rcur->id & BPF_ADD_CONST))
+			return false;
+		if ((rold->id & BPF_ADD_CONST) && (rold->off != rcur->off))
+			return false;
 		/* Why check_ids() for scalar registers?
 		 *
 		 * Consider the following BPF code:
@@ -18630,8 +18639,7 @@ static void release_maps(struct bpf_verifier_env *env)
 /* drop refcnt of maps used by the rejected program */
 static void release_btfs(struct bpf_verifier_env *env)
 {
-	__bpf_free_used_btfs(env->prog->aux, env->used_btfs,
-			     env->used_btf_cnt);
+	__bpf_free_used_btfs(env->used_btfs, env->used_btf_cnt);
 }
 
 /* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */
@@ -18750,6 +18758,8 @@ static int adjust_jmp_off(struct bpf_prog *prog, u32 tgt_idx, u32 delta)
 {
 	struct bpf_insn *insn = prog->insnsi;
 	u32 insn_cnt = prog->len, i;
+	s32 imm;
+	s16 off;
 
 	for (i = 0; i < insn_cnt; i++, insn++) {
 		u8 code = insn->code;
@@ -18761,15 +18771,15 @@ static int adjust_jmp_off(struct bpf_prog *prog, u32 tgt_idx, u32 delta)
 		if (insn->code == (BPF_JMP32 | BPF_JA)) {
 			if (i + 1 + insn->imm != tgt_idx)
 				continue;
-			if (signed_add32_overflows(insn->imm, delta))
+			if (check_add_overflow(insn->imm, delta, &imm))
 				return -ERANGE;
-			insn->imm += delta;
+			insn->imm = imm;
 		} else {
 			if (i + 1 + insn->off != tgt_idx)
 				continue;
-			if (signed_add16_overflows(insn->imm, delta))
+			if (check_add_overflow(insn->off, delta, &off))
 				return -ERANGE;
-			insn->off += delta;
+			insn->off = off;
 		}
 	}
 	return 0;