From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next 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(). ... --- arch/xtensa/lib/strncpy_user.S | 216 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 216 insertions(+) create mode 100644 arch/xtensa/lib/strncpy_user.S (limited to 'arch/xtensa/lib/strncpy_user.S') diff --git a/arch/xtensa/lib/strncpy_user.S b/arch/xtensa/lib/strncpy_user.S new file mode 100644 index 000000000..073191222 --- /dev/null +++ b/arch/xtensa/lib/strncpy_user.S @@ -0,0 +1,216 @@ +/* + * arch/xtensa/lib/strncpy_user.S + * + * This file is subject to the terms and conditions of the GNU General + * Public License. See the file "COPYING" in the main directory of + * this archive for more details. + * + * Returns: -EFAULT if exception before terminator, N if the entire + * buffer filled, else strlen. + * + * Copyright (C) 2002 Tensilica Inc. + */ + +#include +#include +#include +#include + +/* + * char *__strncpy_user(char *dst, const char *src, size_t len) + */ + +#ifdef __XTENSA_EB__ +# define MASK0 0xff000000 +# define MASK1 0x00ff0000 +# define MASK2 0x0000ff00 +# define MASK3 0x000000ff +#else +# define MASK0 0x000000ff +# define MASK1 0x0000ff00 +# define MASK2 0x00ff0000 +# define MASK3 0xff000000 +#endif + +# Register use +# a0/ return address +# a1/ stack pointer +# a2/ return value +# a3/ src +# a4/ len +# a5/ mask0 +# a6/ mask1 +# a7/ mask2 +# a8/ mask3 +# a9/ tmp +# a10/ tmp +# a11/ dst + +.text +ENTRY(__strncpy_user) + + abi_entry_default + # a2/ dst, a3/ src, a4/ len + mov a11, a2 # leave dst in return value register + beqz a4, .Lret # if len is zero + movi a5, MASK0 # mask for byte 0 + movi a6, MASK1 # mask for byte 1 + movi a7, MASK2 # mask for byte 2 + movi a8, MASK3 # mask for byte 3 + bbsi.l a3, 0, .Lsrc1mod2 # if only 8-bit aligned + bbsi.l a3, 1, .Lsrc2mod4 # if only 16-bit aligned +.Lsrcaligned: # return here when src is word-aligned + srli a10, a4, 2 # number of loop iterations with 4B per loop + movi a9, 3 + bnone a11, a9, .Laligned + j .Ldstunaligned + +.Lsrc1mod2: # src address is odd +EX(11f) l8ui a9, a3, 0 # get byte 0 + addi a3, a3, 1 # advance src pointer +EX(10f) s8i a9, a11, 0 # store byte 0 + beqz a9, .Lret # if byte 0 is zero + addi a11, a11, 1 # advance dst pointer + addi a4, a4, -1 # decrement len + beqz a4, .Lret # if len is zero + bbci.l a3, 1, .Lsrcaligned # if src is now word-aligned + +.Lsrc2mod4: # src address is 2 mod 4 +EX(11f) l8ui a9, a3, 0 # get byte 0 + /* 1-cycle interlock */ +EX(10f) s8i a9, a11, 0 # store byte 0 + beqz a9, .Lret # if byte 0 is zero + addi a11, a11, 1 # advance dst pointer + addi a4, a4, -1 # decrement len + beqz a4, .Lret # if len is zero +EX(11f) l8ui a9, a3, 1 # get byte 0 + addi a3, a3, 2 # advance src pointer +EX(10f) s8i a9, a11, 0 # store byte 0 + beqz a9, .Lret # if byte 0 is zero + addi a11, a11, 1 # advance dst pointer + addi a4, a4, -1 # decrement len + bnez a4, .Lsrcaligned # if len is nonzero +.Lret: + sub a2, a11, a2 # compute strlen + abi_ret_default + +/* + * dst is word-aligned, src is word-aligned + */ + .align 4 # 1 mod 4 alignment for LOOPNEZ + .byte 0 # (0 mod 4 alignment for LBEG) +.Laligned: +#if XCHAL_HAVE_LOOPS + loopnez a10, .Loop1done +#else + beqz a10, .Loop1done + slli a10, a10, 2 + add a10, a10, a11 # a10 = end of last 4B chunck +#endif +.Loop1: +EX(11f) l32i a9, a3, 0 # get word from src + addi a3, a3, 4 # advance src pointer + bnone a9, a5, .Lz0 # if byte 0 is zero + bnone a9, a6, .Lz1 # if byte 1 is zero + bnone a9, a7, .Lz2 # if byte 2 is zero +EX(10f) s32i a9, a11, 0 # store word to dst + bnone a9, a8, .Lz3 # if byte 3 is zero + addi a11, a11, 4 # advance dst pointer +#if !XCHAL_HAVE_LOOPS + blt a11, a10, .Loop1 +#endif + +.Loop1done: + bbci.l a4, 1, .L100 + # copy 2 bytes +EX(11f) l16ui a9, a3, 0 + addi a3, a3, 2 # advance src pointer +#ifdef __XTENSA_EB__ + bnone a9, a7, .Lz0 # if byte 2 is zero + bnone a9, a8, .Lz1 # if byte 3 is zero +#else + bnone a9, a5, .Lz0 # if byte 0 is zero + bnone a9, a6, .Lz1 # if byte 1 is zero +#endif +EX(10f) s16i a9, a11, 0 + addi a11, a11, 2 # advance dst pointer +.L100: + bbci.l a4, 0, .Lret +EX(11f) l8ui a9, a3, 0 + /* slot */ +EX(10f) s8i a9, a11, 0 + beqz a9, .Lret # if byte is zero + addi a11, a11, 1-3 # advance dst ptr 1, but also cancel + # the effect of adding 3 in .Lz3 code + /* fall thru to .Lz3 and "retw" */ + +.Lz3: # byte 3 is zero + addi a11, a11, 3 # advance dst pointer + sub a2, a11, a2 # compute strlen + abi_ret_default +.Lz0: # byte 0 is zero +#ifdef __XTENSA_EB__ + movi a9, 0 +#endif /* __XTENSA_EB__ */ +EX(10f) s8i a9, a11, 0 + sub a2, a11, a2 # compute strlen + abi_ret_default +.Lz1: # byte 1 is zero +#ifdef __XTENSA_EB__ + extui a9, a9, 16, 16 +#endif /* __XTENSA_EB__ */ +EX(10f) s16i a9, a11, 0 + addi a11, a11, 1 # advance dst pointer + sub a2, a11, a2 # compute strlen + abi_ret_default +.Lz2: # byte 2 is zero +#ifdef __XTENSA_EB__ + extui a9, a9, 16, 16 +#endif /* __XTENSA_EB__ */ +EX(10f) s16i a9, a11, 0 + movi a9, 0 +EX(10f) s8i a9, a11, 2 + addi a11, a11, 2 # advance dst pointer + sub a2, a11, a2 # compute strlen + abi_ret_default + + .align 4 # 1 mod 4 alignment for LOOPNEZ + .byte 0 # (0 mod 4 alignment for LBEG) +.Ldstunaligned: +/* + * for now just use byte copy loop + */ +#if XCHAL_HAVE_LOOPS + loopnez a4, .Lunalignedend +#else + beqz a4, .Lunalignedend + add a10, a11, a4 # a10 = ending address +#endif /* XCHAL_HAVE_LOOPS */ +.Lnextbyte: +EX(11f) l8ui a9, a3, 0 + addi a3, a3, 1 +EX(10f) s8i a9, a11, 0 + beqz a9, .Lunalignedend + addi a11, a11, 1 +#if !XCHAL_HAVE_LOOPS + blt a11, a10, .Lnextbyte +#endif + +.Lunalignedend: + sub a2, a11, a2 # compute strlen + abi_ret_default + +ENDPROC(__strncpy_user) + + .section .fixup, "ax" + .align 4 + + /* For now, just return -EFAULT. Future implementations might + * like to clear remaining kernel space, like the fixup + * implementation in memset(). Thus, we differentiate between + * load/store fixups. */ + +10: +11: + movi a2, -EFAULT + abi_ret_default -- cgit v1.2.3