aboutsummaryrefslogtreecommitdiff
path: root/net/caif/cfpkt_skbuff.c
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /net/caif/cfpkt_skbuff.c
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted
Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ...
Diffstat (limited to 'net/caif/cfpkt_skbuff.c')
-rw-r--r--net/caif/cfpkt_skbuff.c382
1 files changed, 382 insertions, 0 deletions
diff --git a/net/caif/cfpkt_skbuff.c b/net/caif/cfpkt_skbuff.c
new file mode 100644
index 000000000..7796414d4
--- /dev/null
+++ b/net/caif/cfpkt_skbuff.c
@@ -0,0 +1,382 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) ST-Ericsson AB 2010
+ * Author: Sjur Brendeland
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ":%s(): " fmt, __func__
+
+#include <linux/string.h>
+#include <linux/skbuff.h>
+#include <linux/export.h>
+#include <net/caif/cfpkt.h>
+
+#define PKT_PREFIX 48
+#define PKT_POSTFIX 2
+#define PKT_LEN_WHEN_EXTENDING 128
+#define PKT_ERROR(pkt, errmsg) \
+do { \
+ cfpkt_priv(pkt)->erronous = true; \
+ skb_reset_tail_pointer(&pkt->skb); \
+ pr_warn(errmsg); \
+} while (0)
+
+struct cfpktq {
+ struct sk_buff_head head;
+ atomic_t count;
+ /* Lock protects count updates */
+ spinlock_t lock;
+};
+
+/*
+ * net/caif/ is generic and does not
+ * understand SKB, so we do this typecast
+ */
+struct cfpkt {
+ struct sk_buff skb;
+};
+
+/* Private data inside SKB */
+struct cfpkt_priv_data {
+ struct dev_info dev_info;
+ bool erronous;
+};
+
+static inline struct cfpkt_priv_data *cfpkt_priv(struct cfpkt *pkt)
+{
+ return (struct cfpkt_priv_data *) pkt->skb.cb;
+}
+
+static inline bool is_erronous(struct cfpkt *pkt)
+{
+ return cfpkt_priv(pkt)->erronous;
+}
+
+static inline struct sk_buff *pkt_to_skb(struct cfpkt *pkt)
+{
+ return &pkt->skb;
+}
+
+static inline struct cfpkt *skb_to_pkt(struct sk_buff *skb)
+{
+ return (struct cfpkt *) skb;
+}
+
+struct cfpkt *cfpkt_fromnative(enum caif_direction dir, void *nativepkt)
+{
+ struct cfpkt *pkt = skb_to_pkt(nativepkt);
+ cfpkt_priv(pkt)->erronous = false;
+ return pkt;
+}
+EXPORT_SYMBOL(cfpkt_fromnative);
+
+void *cfpkt_tonative(struct cfpkt *pkt)
+{
+ return (void *) pkt;
+}
+EXPORT_SYMBOL(cfpkt_tonative);
+
+static struct cfpkt *cfpkt_create_pfx(u16 len, u16 pfx)
+{
+ struct sk_buff *skb;
+
+ skb = alloc_skb(len + pfx, GFP_ATOMIC);
+ if (unlikely(skb == NULL))
+ return NULL;
+
+ skb_reserve(skb, pfx);
+ return skb_to_pkt(skb);
+}
+
+inline struct cfpkt *cfpkt_create(u16 len)
+{
+ return cfpkt_create_pfx(len + PKT_POSTFIX, PKT_PREFIX);
+}
+
+void cfpkt_destroy(struct cfpkt *pkt)
+{
+ struct sk_buff *skb = pkt_to_skb(pkt);
+ kfree_skb(skb);
+}
+
+inline bool cfpkt_more(struct cfpkt *pkt)
+{
+ struct sk_buff *skb = pkt_to_skb(pkt);
+ return skb->len > 0;
+}
+
+int cfpkt_peek_head(struct cfpkt *pkt, void *data, u16 len)
+{
+ struct sk_buff *skb = pkt_to_skb(pkt);
+ if (skb_headlen(skb) >= len) {
+ memcpy(data, skb->data, len);
+ return 0;
+ }
+ return !cfpkt_extr_head(pkt, data, len) &&
+ !cfpkt_add_head(pkt, data, len);
+}
+
+int cfpkt_extr_head(struct cfpkt *pkt, void *data, u16 len)
+{
+ struct sk_buff *skb = pkt_to_skb(pkt);
+ u8 *from;
+ if (unlikely(is_erronous(pkt)))
+ return -EPROTO;
+
+ if (unlikely(len > skb->len)) {
+ PKT_ERROR(pkt, "read beyond end of packet\n");
+ return -EPROTO;
+ }
+
+ if (unlikely(len > skb_headlen(skb))) {
+ if (unlikely(skb_linearize(skb) != 0)) {
+ PKT_ERROR(pkt, "linearize failed\n");
+ return -EPROTO;
+ }
+ }
+ from = skb_pull(skb, len);
+ from -= len;
+ if (data)
+ memcpy(data, from, len);
+ return 0;
+}
+EXPORT_SYMBOL(cfpkt_extr_head);
+
+int cfpkt_extr_trail(struct cfpkt *pkt, void *dta, u16 len)
+{
+ struct sk_buff *skb = pkt_to_skb(pkt);
+ u8 *data = dta;
+ u8 *from;
+ if (unlikely(is_erronous(pkt)))
+ return -EPROTO;
+
+ if (unlikely(skb_linearize(skb) != 0)) {
+ PKT_ERROR(pkt, "linearize failed\n");
+ return -EPROTO;
+ }
+ if (unlikely(skb->data + len > skb_tail_pointer(skb))) {
+ PKT_ERROR(pkt, "read beyond end of packet\n");
+ return -EPROTO;
+ }
+ from = skb_tail_pointer(skb) - len;
+ skb_trim(skb, skb->len - len);
+ memcpy(data, from, len);
+ return 0;
+}
+
+int cfpkt_pad_trail(struct cfpkt *pkt, u16 len)
+{
+ return cfpkt_add_body(pkt, NULL, len);
+}
+
+int cfpkt_add_body(struct cfpkt *pkt, const void *data, u16 len)
+{
+ struct sk_buff *skb = pkt_to_skb(pkt);
+ struct sk_buff *lastskb;
+ u8 *to;
+ u16 addlen = 0;
+
+
+ if (unlikely(is_erronous(pkt)))
+ return -EPROTO;
+
+ lastskb = skb;
+
+ /* Check whether we need to add space at the tail */
+ if (unlikely(skb_tailroom(skb) < len)) {
+ if (likely(len < PKT_LEN_WHEN_EXTENDING))
+ addlen = PKT_LEN_WHEN_EXTENDING;
+ else
+ addlen = len;
+ }
+
+ /* Check whether we need to change the SKB before writing to the tail */
+ if (unlikely((addlen > 0) || skb_cloned(skb) || skb_shared(skb))) {
+
+ /* Make sure data is writable */
+ if (unlikely(skb_cow_data(skb, addlen, &lastskb) < 0)) {
+ PKT_ERROR(pkt, "cow failed\n");
+ return -EPROTO;
+ }
+ }
+
+ /* All set to put the last SKB and optionally write data there. */
+ to = pskb_put(skb, lastskb, len);
+ if (likely(data))
+ memcpy(to, data, len);
+ return 0;
+}
+
+inline int cfpkt_addbdy(struct cfpkt *pkt, u8 data)
+{
+ return cfpkt_add_body(pkt, &data, 1);
+}
+
+int cfpkt_add_head(struct cfpkt *pkt, const void *data2, u16 len)
+{
+ struct sk_buff *skb = pkt_to_skb(pkt);
+ struct sk_buff *lastskb;
+ u8 *to;
+ const u8 *data = data2;
+ int ret;
+ if (unlikely(is_erronous(pkt)))
+ return -EPROTO;
+ if (unlikely(skb_headroom(skb) < len)) {
+ PKT_ERROR(pkt, "no headroom\n");
+ return -EPROTO;
+ }
+
+ /* Make sure data is writable */
+ ret = skb_cow_data(skb, 0, &lastskb);
+ if (unlikely(ret < 0)) {
+ PKT_ERROR(pkt, "cow failed\n");
+ return ret;
+ }
+
+ to = skb_push(skb, len);
+ memcpy(to, data, len);
+ return 0;
+}
+EXPORT_SYMBOL(cfpkt_add_head);
+
+inline int cfpkt_add_trail(struct cfpkt *pkt, const void *data, u16 len)
+{
+ return cfpkt_add_body(pkt, data, len);
+}
+
+inline u16 cfpkt_getlen(struct cfpkt *pkt)
+{
+ struct sk_buff *skb = pkt_to_skb(pkt);
+ return skb->len;
+}
+
+int cfpkt_iterate(struct cfpkt *pkt,
+ u16 (*iter_func)(u16, void *, u16),
+ u16 data)
+{
+ /*
+ * Don't care about the performance hit of linearizing,
+ * Checksum should not be used on high-speed interfaces anyway.
+ */
+ if (unlikely(is_erronous(pkt)))
+ return -EPROTO;
+ if (unlikely(skb_linearize(&pkt->skb) != 0)) {
+ PKT_ERROR(pkt, "linearize failed\n");
+ return -EPROTO;
+ }
+ return iter_func(data, pkt->skb.data, cfpkt_getlen(pkt));
+}
+
+int cfpkt_setlen(struct cfpkt *pkt, u16 len)
+{
+ struct sk_buff *skb = pkt_to_skb(pkt);
+
+
+ if (unlikely(is_erronous(pkt)))
+ return -EPROTO;
+
+ if (likely(len <= skb->len)) {
+ if (unlikely(skb->data_len))
+ ___pskb_trim(skb, len);
+ else
+ skb_trim(skb, len);
+
+ return cfpkt_getlen(pkt);
+ }
+
+ /* Need to expand SKB */
+ if (unlikely(!cfpkt_pad_trail(pkt, len - skb->len)))
+ PKT_ERROR(pkt, "skb_pad_trail failed\n");
+
+ return cfpkt_getlen(pkt);
+}
+
+struct cfpkt *cfpkt_append(struct cfpkt *dstpkt,
+ struct cfpkt *addpkt,
+ u16 expectlen)
+{
+ struct sk_buff *dst = pkt_to_skb(dstpkt);
+ struct sk_buff *add = pkt_to_skb(addpkt);
+ u16 addlen = skb_headlen(add);
+ u16 neededtailspace;
+ struct sk_buff *tmp;
+ u16 dstlen;
+ u16 createlen;
+ if (unlikely(is_erronous(dstpkt) || is_erronous(addpkt))) {
+ return dstpkt;
+ }
+ if (expectlen > addlen)
+ neededtailspace = expectlen;
+ else
+ neededtailspace = addlen;
+
+ if (dst->tail + neededtailspace > dst->end) {
+ /* Create a dumplicate of 'dst' with more tail space */
+ struct cfpkt *tmppkt;
+ dstlen = skb_headlen(dst);
+ createlen = dstlen + neededtailspace;
+ tmppkt = cfpkt_create(createlen + PKT_PREFIX + PKT_POSTFIX);
+ if (tmppkt == NULL)
+ return NULL;
+ tmp = pkt_to_skb(tmppkt);
+ skb_put_data(tmp, dst->data, dstlen);
+ cfpkt_destroy(dstpkt);
+ dst = tmp;
+ }
+ skb_put_data(dst, add->data, skb_headlen(add));
+ cfpkt_destroy(addpkt);
+ return skb_to_pkt(dst);
+}
+
+struct cfpkt *cfpkt_split(struct cfpkt *pkt, u16 pos)
+{
+ struct sk_buff *skb2;
+ struct sk_buff *skb = pkt_to_skb(pkt);
+ struct cfpkt *tmppkt;
+ u8 *split = skb->data + pos;
+ u16 len2nd = skb_tail_pointer(skb) - split;
+
+ if (unlikely(is_erronous(pkt)))
+ return NULL;
+
+ if (skb->data + pos > skb_tail_pointer(skb)) {
+ PKT_ERROR(pkt, "trying to split beyond end of packet\n");
+ return NULL;
+ }
+
+ /* Create a new packet for the second part of the data */
+ tmppkt = cfpkt_create_pfx(len2nd + PKT_PREFIX + PKT_POSTFIX,
+ PKT_PREFIX);
+ if (tmppkt == NULL)
+ return NULL;
+ skb2 = pkt_to_skb(tmppkt);
+
+
+ if (skb2 == NULL)
+ return NULL;
+
+ skb_put_data(skb2, split, len2nd);
+
+ /* Reduce the length of the original packet */
+ skb_trim(skb, pos);
+
+ skb2->priority = skb->priority;
+ return skb_to_pkt(skb2);
+}
+
+bool cfpkt_erroneous(struct cfpkt *pkt)
+{
+ return cfpkt_priv(pkt)->erronous;
+}
+
+struct caif_payload_info *cfpkt_info(struct cfpkt *pkt)
+{
+ return (struct caif_payload_info *)&pkt_to_skb(pkt)->cb;
+}
+EXPORT_SYMBOL(cfpkt_info);
+
+void cfpkt_set_prio(struct cfpkt *pkt, int prio)
+{
+ pkt_to_skb(pkt)->priority = prio;
+}
+EXPORT_SYMBOL(cfpkt_set_prio);