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/arm/kernel/entry-ftrace.S | 288 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 288 insertions(+) create mode 100644 arch/arm/kernel/entry-ftrace.S (limited to 'arch/arm/kernel/entry-ftrace.S') diff --git a/arch/arm/kernel/entry-ftrace.S b/arch/arm/kernel/entry-ftrace.S new file mode 100644 index 000000000..3e7bcaca5 --- /dev/null +++ b/arch/arm/kernel/entry-ftrace.S @@ -0,0 +1,288 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include +#include +#include + +#include "entry-header.S" + +/* + * When compiling with -pg, gcc inserts a call to the mcount routine at the + * start of every function. In mcount, apart from the function's address (in + * lr), we need to get hold of the function's caller's address. + * + * Newer GCCs (4.4+) solve this problem by using a version of mcount with call + * sites like: + * + * push {lr} + * bl __gnu_mcount_nc + * + * With these compilers, frame pointers are not necessary. + * + * mcount can be thought of as a function called in the middle of a subroutine + * call. As such, it needs to be transparent for both the caller and the + * callee: the original lr needs to be restored when leaving mcount, and no + * registers should be clobbered. + * + * When using dynamic ftrace, we patch out the mcount call by a "add sp, #4" + * instead of the __gnu_mcount_nc call (see arch/arm/kernel/ftrace.c). + */ + +.macro mcount_adjust_addr rd, rn + bic \rd, \rn, #1 @ clear the Thumb bit if present + sub \rd, \rd, #MCOUNT_INSN_SIZE +.endm + +.macro __mcount suffix + mcount_enter + ldr_va r2, ftrace_trace_function + badr r0, .Lftrace_stub + cmp r0, r2 + bne 1f + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + ldr_va r2, ftrace_graph_return + cmp r0, r2 + bne ftrace_graph_caller\suffix + + ldr_va r2, ftrace_graph_entry + mov_l r0, ftrace_graph_entry_stub + cmp r0, r2 + bne ftrace_graph_caller\suffix +#endif + + mcount_exit + +1: mcount_get_lr r1 @ lr of instrumented func + mcount_adjust_addr r0, lr @ instrumented function + badr lr, 2f + mov pc, r2 +2: mcount_exit +.endm + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + +.macro __ftrace_regs_caller + + str lr, [sp, #-8]! @ store LR as PC and make space for CPSR/OLD_R0, + @ OLD_R0 will overwrite previous LR + + ldr lr, [sp, #8] @ get previous LR + + str r0, [sp, #8] @ write r0 as OLD_R0 over previous LR + + str lr, [sp, #-4]! @ store previous LR as LR + + add lr, sp, #16 @ move in LR the value of SP as it was + @ before the push {lr} of the mcount mechanism + + push {r0-r11, ip, lr} + + @ stack content at this point: + @ 0 4 48 52 56 60 64 68 72 + @ R0 | R1 | ... | IP | SP + 4 | previous LR | LR | PSR | OLD_R0 | + + mov r3, sp @ struct pt_regs* + + ldr_va r2, function_trace_op @ pointer to the current + @ function tracing op + + ldr r1, [sp, #S_LR] @ lr of instrumented func + + ldr lr, [sp, #S_PC] @ get LR + + mcount_adjust_addr r0, lr @ instrumented function + + .globl ftrace_regs_call +ftrace_regs_call: + bl ftrace_stub + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + .globl ftrace_graph_regs_call +ftrace_graph_regs_call: +ARM( mov r0, r0 ) +THUMB( nop.w ) +#endif + + @ pop saved regs + pop {r0-r11, ip, lr} @ restore r0 through r12 + ldr lr, [sp], #4 @ restore LR + ldr pc, [sp], #12 +.endm + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +.macro __ftrace_graph_regs_caller + +#ifdef CONFIG_UNWINDER_FRAME_POINTER + sub r0, fp, #4 @ lr of instrumented routine (parent) +#else + add r0, sp, #S_LR +#endif + + @ called from __ftrace_regs_caller + ldr r1, [sp, #S_PC] @ instrumented routine (func) + mcount_adjust_addr r1, r1 + + mov r2, fpreg @ frame pointer + add r3, sp, #PT_REGS_SIZE + bl prepare_ftrace_return + + @ pop registers saved in ftrace_regs_caller + pop {r0-r11, ip, lr} @ restore r0 through r12 + ldr lr, [sp], #4 @ restore LR + ldr pc, [sp], #12 + +.endm +#endif +#endif + +.macro __ftrace_caller suffix + mcount_enter + + mcount_get_lr r1 @ lr of instrumented func + mcount_adjust_addr r0, lr @ instrumented function + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + ldr_va r2, function_trace_op @ pointer to the current + @ function tracing op + mov r3, #0 @ regs is NULL +#endif + + .globl ftrace_call\suffix +ftrace_call\suffix: + bl ftrace_stub + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + .globl ftrace_graph_call\suffix +ftrace_graph_call\suffix: +ARM( mov r0, r0 ) +THUMB( nop.w ) +#endif + + mcount_exit +.endm + +.macro __ftrace_graph_caller +#ifdef CONFIG_UNWINDER_FRAME_POINTER + sub r0, fp, #4 @ &lr of instrumented routine (&parent) +#else + add r0, sp, #20 +#endif +#ifdef CONFIG_DYNAMIC_FTRACE + @ called from __ftrace_caller, saved in mcount_enter + ldr r1, [sp, #16] @ instrumented routine (func) + mcount_adjust_addr r1, r1 +#else + @ called from __mcount, untouched in lr + mcount_adjust_addr r1, lr @ instrumented routine (func) +#endif + mov r2, fpreg @ frame pointer + add r3, sp, #24 + bl prepare_ftrace_return + mcount_exit +.endm + +/* + * __gnu_mcount_nc + */ + +.macro mcount_enter +/* + * This pad compensates for the push {lr} at the call site. Note that we are + * unable to unwind through a function which does not otherwise save its lr. + */ + UNWIND(.pad #4) + stmdb sp!, {r0-r3, lr} + UNWIND(.save {r0-r3, lr}) +.endm + +.macro mcount_get_lr reg + ldr \reg, [sp, #20] +.endm + +.macro mcount_exit + ldmia sp!, {r0-r3} + ldr lr, [sp, #4] + ldr pc, [sp], #8 +.endm + +ENTRY(__gnu_mcount_nc) +UNWIND(.fnstart) +#ifdef CONFIG_DYNAMIC_FTRACE + push {lr} + ldr lr, [sp, #4] + ldr pc, [sp], #8 +#else + __mcount +#endif +UNWIND(.fnend) +ENDPROC(__gnu_mcount_nc) + +#ifdef CONFIG_DYNAMIC_FTRACE +ENTRY(ftrace_caller) +UNWIND(.fnstart) + __ftrace_caller +UNWIND(.fnend) +ENDPROC(ftrace_caller) + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +ENTRY(ftrace_regs_caller) +UNWIND(.fnstart) + __ftrace_regs_caller +UNWIND(.fnend) +ENDPROC(ftrace_regs_caller) +#endif + +#endif + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +ENTRY(ftrace_graph_caller) +UNWIND(.fnstart) + __ftrace_graph_caller +UNWIND(.fnend) +ENDPROC(ftrace_graph_caller) + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +ENTRY(ftrace_graph_regs_caller) +UNWIND(.fnstart) + __ftrace_graph_regs_caller +UNWIND(.fnend) +ENDPROC(ftrace_graph_regs_caller) +#endif +#endif + +.purgem mcount_enter +.purgem mcount_get_lr +.purgem mcount_exit + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +ENTRY(return_to_handler) + stmdb sp!, {r0-r3} + add r0, sp, #16 @ sp at exit of instrumented routine + bl ftrace_return_to_handler + mov lr, r0 @ r0 has real ret addr + ldmia sp!, {r0-r3} + ret lr +ENDPROC(return_to_handler) +#endif + +ENTRY(ftrace_stub) +.Lftrace_stub: + ret lr +ENDPROC(ftrace_stub) + +#ifdef CONFIG_DYNAMIC_FTRACE + + __INIT + + .macro init_tramp, dst:req +ENTRY(\dst\()_from_init) + ldr pc, =\dst +ENDPROC(\dst\()_from_init) + .endm + + init_tramp ftrace_caller +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + init_tramp ftrace_regs_caller +#endif +#endif -- cgit v1.2.3