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/x86/kernel/ftrace.c | 670 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 670 insertions(+) create mode 100644 arch/x86/kernel/ftrace.c (limited to 'arch/x86/kernel/ftrace.c') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c new file mode 100644 index 000000000..5e7ead52c --- /dev/null +++ b/arch/x86/kernel/ftrace.c @@ -0,0 +1,670 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Dynamic function tracing support. + * + * Copyright (C) 2007-2008 Steven Rostedt + * + * Thanks goes to Ingo Molnar, for suggesting the idea. + * Mathieu Desnoyers, for suggesting postponing the modifications. + * Arjan van de Ven, for keeping me straight, and explaining to me + * the dangers of modifying code on the run. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include +#include +#include +#include + +#ifdef CONFIG_DYNAMIC_FTRACE + +static int ftrace_poke_late = 0; + +void ftrace_arch_code_modify_prepare(void) + __acquires(&text_mutex) +{ + /* + * Need to grab text_mutex to prevent a race from module loading + * and live kernel patching from changing the text permissions while + * ftrace has it set to "read/write". + */ + mutex_lock(&text_mutex); + ftrace_poke_late = 1; +} + +void ftrace_arch_code_modify_post_process(void) + __releases(&text_mutex) +{ + /* + * ftrace_make_{call,nop}() may be called during + * module load, and we need to finish the text_poke_queue() + * that they do, here. + */ + text_poke_finish(); + ftrace_poke_late = 0; + mutex_unlock(&text_mutex); +} + +static const char *ftrace_nop_replace(void) +{ + return x86_nops[5]; +} + +static const char *ftrace_call_replace(unsigned long ip, unsigned long addr) +{ + /* + * No need to translate into a callthunk. The trampoline does + * the depth accounting itself. + */ + return text_gen_insn(CALL_INSN_OPCODE, (void *)ip, (void *)addr); +} + +static int ftrace_verify_code(unsigned long ip, const char *old_code) +{ + char cur_code[MCOUNT_INSN_SIZE]; + + /* + * Note: + * We are paranoid about modifying text, as if a bug was to happen, it + * could cause us to read or write to someplace that could cause harm. + * Carefully read and modify the code with probe_kernel_*(), and make + * sure what we read is what we expected it to be before modifying it. + */ + /* read the text we want to modify */ + if (copy_from_kernel_nofault(cur_code, (void *)ip, MCOUNT_INSN_SIZE)) { + WARN_ON(1); + return -EFAULT; + } + + /* Make sure it is what we expect it to be */ + if (memcmp(cur_code, old_code, MCOUNT_INSN_SIZE) != 0) { + ftrace_expected = old_code; + WARN_ON(1); + return -EINVAL; + } + + return 0; +} + +/* + * Marked __ref because it calls text_poke_early() which is .init.text. That is + * ok because that call will happen early, during boot, when .init sections are + * still present. + */ +static int __ref +ftrace_modify_code_direct(unsigned long ip, const char *old_code, + const char *new_code) +{ + int ret = ftrace_verify_code(ip, old_code); + if (ret) + return ret; + + /* replace the text with the new text */ + if (ftrace_poke_late) + text_poke_queue((void *)ip, new_code, MCOUNT_INSN_SIZE, NULL); + else + text_poke_early((void *)ip, new_code, MCOUNT_INSN_SIZE); + return 0; +} + +int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned long ip = rec->ip; + const char *new, *old; + + old = ftrace_call_replace(ip, addr); + new = ftrace_nop_replace(); + + /* + * On boot up, and when modules are loaded, the MCOUNT_ADDR + * is converted to a nop, and will never become MCOUNT_ADDR + * again. This code is either running before SMP (on boot up) + * or before the code will ever be executed (module load). + * We do not want to use the breakpoint version in this case, + * just modify the code directly. + */ + if (addr == MCOUNT_ADDR) + return ftrace_modify_code_direct(ip, old, new); + + /* + * x86 overrides ftrace_replace_code -- this function will never be used + * in this case. + */ + WARN_ONCE(1, "invalid use of ftrace_make_nop"); + return -EINVAL; +} + +int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned long ip = rec->ip; + const char *new, *old; + + old = ftrace_nop_replace(); + new = ftrace_call_replace(ip, addr); + + /* Should only be called when module is loaded */ + return ftrace_modify_code_direct(rec->ip, old, new); +} + +/* + * Should never be called: + * As it is only called by __ftrace_replace_code() which is called by + * ftrace_replace_code() that x86 overrides, and by ftrace_update_code() + * which is called to turn mcount into nops or nops into function calls + * but not to convert a function from not using regs to one that uses + * regs, which ftrace_modify_call() is for. + */ +int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) +{ + WARN_ON(1); + return -EINVAL; +} + +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + unsigned long ip; + const char *new; + + ip = (unsigned long)(&ftrace_call); + new = ftrace_call_replace(ip, (unsigned long)func); + text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL); + + ip = (unsigned long)(&ftrace_regs_call); + new = ftrace_call_replace(ip, (unsigned long)func); + text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL); + + return 0; +} + +void ftrace_replace_code(int enable) +{ + struct ftrace_rec_iter *iter; + struct dyn_ftrace *rec; + const char *new, *old; + int ret; + + for_ftrace_rec_iter(iter) { + rec = ftrace_rec_iter_record(iter); + + switch (ftrace_test_record(rec, enable)) { + case FTRACE_UPDATE_IGNORE: + default: + continue; + + case FTRACE_UPDATE_MAKE_CALL: + old = ftrace_nop_replace(); + break; + + case FTRACE_UPDATE_MODIFY_CALL: + case FTRACE_UPDATE_MAKE_NOP: + old = ftrace_call_replace(rec->ip, ftrace_get_addr_curr(rec)); + break; + } + + ret = ftrace_verify_code(rec->ip, old); + if (ret) { + ftrace_expected = old; + ftrace_bug(ret, rec); + ftrace_expected = NULL; + return; + } + } + + for_ftrace_rec_iter(iter) { + rec = ftrace_rec_iter_record(iter); + + switch (ftrace_test_record(rec, enable)) { + case FTRACE_UPDATE_IGNORE: + default: + continue; + + case FTRACE_UPDATE_MAKE_CALL: + case FTRACE_UPDATE_MODIFY_CALL: + new = ftrace_call_replace(rec->ip, ftrace_get_addr_new(rec)); + break; + + case FTRACE_UPDATE_MAKE_NOP: + new = ftrace_nop_replace(); + break; + } + + text_poke_queue((void *)rec->ip, new, MCOUNT_INSN_SIZE, NULL); + ftrace_update_record(rec, enable); + } + text_poke_finish(); +} + +void arch_ftrace_update_code(int command) +{ + ftrace_modify_all_code(command); +} + +/* Currently only x86_64 supports dynamic trampolines */ +#ifdef CONFIG_X86_64 + +#ifdef CONFIG_MODULES +#include +/* Module allocation simplifies allocating memory for code */ +static inline void *alloc_tramp(unsigned long size) +{ + return module_alloc(size); +} +static inline void tramp_free(void *tramp) +{ + module_memfree(tramp); +} +#else +/* Trampolines can only be created if modules are supported */ +static inline void *alloc_tramp(unsigned long size) +{ + return NULL; +} +static inline void tramp_free(void *tramp) { } +#endif + +/* Defined as markers to the end of the ftrace default trampolines */ +extern void ftrace_regs_caller_end(void); +extern void ftrace_regs_caller_ret(void); +extern void ftrace_caller_end(void); +extern void ftrace_caller_op_ptr(void); +extern void ftrace_regs_caller_op_ptr(void); +extern void ftrace_regs_caller_jmp(void); + +/* movq function_trace_op(%rip), %rdx */ +/* 0x48 0x8b 0x15 */ +#define OP_REF_SIZE 7 + +/* + * The ftrace_ops is passed to the function callback. Since the + * trampoline only services a single ftrace_ops, we can pass in + * that ops directly. + * + * The ftrace_op_code_union is used to create a pointer to the + * ftrace_ops that will be passed to the callback function. + */ +union ftrace_op_code_union { + char code[OP_REF_SIZE]; + struct { + char op[3]; + int offset; + } __attribute__((packed)); +}; + +#define RET_SIZE (IS_ENABLED(CONFIG_RETPOLINE) ? 5 : 1 + IS_ENABLED(CONFIG_SLS)) + +static unsigned long +create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) +{ + unsigned long start_offset; + unsigned long end_offset; + unsigned long op_offset; + unsigned long call_offset; + unsigned long jmp_offset; + unsigned long offset; + unsigned long npages; + unsigned long size; + unsigned long *ptr; + void *trampoline; + void *ip, *dest; + /* 48 8b 15 is movq (%rip), %rdx */ + unsigned const char op_ref[] = { 0x48, 0x8b, 0x15 }; + unsigned const char retq[] = { RET_INSN_OPCODE, INT3_INSN_OPCODE }; + union ftrace_op_code_union op_ptr; + int ret; + + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) { + start_offset = (unsigned long)ftrace_regs_caller; + end_offset = (unsigned long)ftrace_regs_caller_end; + op_offset = (unsigned long)ftrace_regs_caller_op_ptr; + call_offset = (unsigned long)ftrace_regs_call; + jmp_offset = (unsigned long)ftrace_regs_caller_jmp; + } else { + start_offset = (unsigned long)ftrace_caller; + end_offset = (unsigned long)ftrace_caller_end; + op_offset = (unsigned long)ftrace_caller_op_ptr; + call_offset = (unsigned long)ftrace_call; + jmp_offset = 0; + } + + size = end_offset - start_offset; + + /* + * Allocate enough size to store the ftrace_caller code, + * the iret , as well as the address of the ftrace_ops this + * trampoline is used for. + */ + trampoline = alloc_tramp(size + RET_SIZE + sizeof(void *)); + if (!trampoline) + return 0; + + *tramp_size = size + RET_SIZE + sizeof(void *); + npages = DIV_ROUND_UP(*tramp_size, PAGE_SIZE); + + /* Copy ftrace_caller onto the trampoline memory */ + ret = copy_from_kernel_nofault(trampoline, (void *)start_offset, size); + if (WARN_ON(ret < 0)) + goto fail; + + ip = trampoline + size; + if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + __text_gen_insn(ip, JMP32_INSN_OPCODE, ip, x86_return_thunk, JMP32_INSN_SIZE); + else + memcpy(ip, retq, sizeof(retq)); + + /* No need to test direct calls on created trampolines */ + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) { + /* NOP the jnz 1f; but make sure it's a 2 byte jnz */ + ip = trampoline + (jmp_offset - start_offset); + if (WARN_ON(*(char *)ip != 0x75)) + goto fail; + ret = copy_from_kernel_nofault(ip, x86_nops[2], 2); + if (ret < 0) + goto fail; + } + + /* + * The address of the ftrace_ops that is used for this trampoline + * is stored at the end of the trampoline. This will be used to + * load the third parameter for the callback. Basically, that + * location at the end of the trampoline takes the place of + * the global function_trace_op variable. + */ + + ptr = (unsigned long *)(trampoline + size + RET_SIZE); + *ptr = (unsigned long)ops; + + op_offset -= start_offset; + memcpy(&op_ptr, trampoline + op_offset, OP_REF_SIZE); + + /* Are we pointing to the reference? */ + if (WARN_ON(memcmp(op_ptr.op, op_ref, 3) != 0)) + goto fail; + + /* Load the contents of ptr into the callback parameter */ + offset = (unsigned long)ptr; + offset -= (unsigned long)trampoline + op_offset + OP_REF_SIZE; + + op_ptr.offset = offset; + + /* put in the new offset to the ftrace_ops */ + memcpy(trampoline + op_offset, &op_ptr, OP_REF_SIZE); + + /* put in the call to the function */ + mutex_lock(&text_mutex); + call_offset -= start_offset; + /* + * No need to translate into a callthunk. The trampoline does + * the depth accounting before the call already. + */ + dest = ftrace_ops_get_func(ops); + memcpy(trampoline + call_offset, + text_gen_insn(CALL_INSN_OPCODE, trampoline + call_offset, dest), + CALL_INSN_SIZE); + mutex_unlock(&text_mutex); + + /* ALLOC_TRAMP flags lets us know we created it */ + ops->flags |= FTRACE_OPS_FL_ALLOC_TRAMP; + + set_memory_rox((unsigned long)trampoline, npages); + return (unsigned long)trampoline; +fail: + tramp_free(trampoline); + return 0; +} + +void set_ftrace_ops_ro(void) +{ + struct ftrace_ops *ops; + unsigned long start_offset; + unsigned long end_offset; + unsigned long npages; + unsigned long size; + + do_for_each_ftrace_op(ops, ftrace_ops_list) { + if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) + continue; + + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) { + start_offset = (unsigned long)ftrace_regs_caller; + end_offset = (unsigned long)ftrace_regs_caller_end; + } else { + start_offset = (unsigned long)ftrace_caller; + end_offset = (unsigned long)ftrace_caller_end; + } + size = end_offset - start_offset; + size = size + RET_SIZE + sizeof(void *); + npages = DIV_ROUND_UP(size, PAGE_SIZE); + set_memory_ro((unsigned long)ops->trampoline, npages); + } while_for_each_ftrace_op(ops); +} + +static unsigned long calc_trampoline_call_offset(bool save_regs) +{ + unsigned long start_offset; + unsigned long call_offset; + + if (save_regs) { + start_offset = (unsigned long)ftrace_regs_caller; + call_offset = (unsigned long)ftrace_regs_call; + } else { + start_offset = (unsigned long)ftrace_caller; + call_offset = (unsigned long)ftrace_call; + } + + return call_offset - start_offset; +} + +void arch_ftrace_update_trampoline(struct ftrace_ops *ops) +{ + ftrace_func_t func; + unsigned long offset; + unsigned long ip; + unsigned int size; + const char *new; + + if (!ops->trampoline) { + ops->trampoline = create_trampoline(ops, &size); + if (!ops->trampoline) + return; + ops->trampoline_size = size; + return; + } + + /* + * The ftrace_ops caller may set up its own trampoline. + * In such a case, this code must not modify it. + */ + if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) + return; + + offset = calc_trampoline_call_offset(ops->flags & FTRACE_OPS_FL_SAVE_REGS); + ip = ops->trampoline + offset; + func = ftrace_ops_get_func(ops); + + mutex_lock(&text_mutex); + /* Do a safe modify in case the trampoline is executing */ + new = ftrace_call_replace(ip, (unsigned long)func); + text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL); + mutex_unlock(&text_mutex); +} + +/* Return the address of the function the trampoline calls */ +static void *addr_from_call(void *ptr) +{ + union text_poke_insn call; + int ret; + + ret = copy_from_kernel_nofault(&call, ptr, CALL_INSN_SIZE); + if (WARN_ON_ONCE(ret < 0)) + return NULL; + + /* Make sure this is a call */ + if (WARN_ON_ONCE(call.opcode != CALL_INSN_OPCODE)) { + pr_warn("Expected E8, got %x\n", call.opcode); + return NULL; + } + + return ptr + CALL_INSN_SIZE + call.disp; +} + +void prepare_ftrace_return(unsigned long ip, unsigned long *parent, + unsigned long frame_pointer); + +/* + * If the ops->trampoline was not allocated, then it probably + * has a static trampoline func, or is the ftrace caller itself. + */ +static void *static_tramp_func(struct ftrace_ops *ops, struct dyn_ftrace *rec) +{ + unsigned long offset; + bool save_regs = rec->flags & FTRACE_FL_REGS_EN; + void *ptr; + + if (ops && ops->trampoline) { +#if !defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) && \ + defined(CONFIG_FUNCTION_GRAPH_TRACER) + /* + * We only know about function graph tracer setting as static + * trampoline. + */ + if (ops->trampoline == FTRACE_GRAPH_ADDR) + return (void *)prepare_ftrace_return; +#endif + return NULL; + } + + offset = calc_trampoline_call_offset(save_regs); + + if (save_regs) + ptr = (void *)FTRACE_REGS_ADDR + offset; + else + ptr = (void *)FTRACE_ADDR + offset; + + return addr_from_call(ptr); +} + +void *arch_ftrace_trampoline_func(struct ftrace_ops *ops, struct dyn_ftrace *rec) +{ + unsigned long offset; + + /* If we didn't allocate this trampoline, consider it static */ + if (!ops || !(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) + return static_tramp_func(ops, rec); + + offset = calc_trampoline_call_offset(ops->flags & FTRACE_OPS_FL_SAVE_REGS); + return addr_from_call((void *)ops->trampoline + offset); +} + +void arch_ftrace_trampoline_free(struct ftrace_ops *ops) +{ + if (!ops || !(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) + return; + + tramp_free((void *)ops->trampoline); + ops->trampoline = 0; +} + +#endif /* CONFIG_X86_64 */ +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + +#if defined(CONFIG_DYNAMIC_FTRACE) && !defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) +extern void ftrace_graph_call(void); +static const char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) +{ + return text_gen_insn(JMP32_INSN_OPCODE, (void *)ip, (void *)addr); +} + +static int ftrace_mod_jmp(unsigned long ip, void *func) +{ + const char *new; + + new = ftrace_jmp_replace(ip, (unsigned long)func); + text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL); + return 0; +} + +int ftrace_enable_ftrace_graph_caller(void) +{ + unsigned long ip = (unsigned long)(&ftrace_graph_call); + + return ftrace_mod_jmp(ip, &ftrace_graph_caller); +} + +int ftrace_disable_ftrace_graph_caller(void) +{ + unsigned long ip = (unsigned long)(&ftrace_graph_call); + + return ftrace_mod_jmp(ip, &ftrace_stub); +} +#endif /* CONFIG_DYNAMIC_FTRACE && !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ + +/* + * Hook the return address and push it in the stack of return addrs + * in current thread info. + */ +void prepare_ftrace_return(unsigned long ip, unsigned long *parent, + unsigned long frame_pointer) +{ + unsigned long return_hooker = (unsigned long)&return_to_handler; + int bit; + + /* + * When resuming from suspend-to-ram, this function can be indirectly + * called from early CPU startup code while the CPU is in real mode, + * which would fail miserably. Make sure the stack pointer is a + * virtual address. + * + * This check isn't as accurate as virt_addr_valid(), but it should be + * good enough for this purpose, and it's fast. + */ + if (unlikely((long)__builtin_frame_address(0) >= 0)) + return; + + if (unlikely(ftrace_graph_is_dead())) + return; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + + bit = ftrace_test_recursion_trylock(ip, *parent); + if (bit < 0) + return; + + if (!function_graph_enter(*parent, ip, frame_pointer, parent)) + *parent = return_hooker; + + ftrace_test_recursion_unlock(bit); +} + +#ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS +void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs) +{ + struct pt_regs *regs = &fregs->regs; + unsigned long *stack = (unsigned long *)kernel_stack_pointer(regs); + + prepare_ftrace_return(ip, (unsigned long *)stack, 0); +} +#endif + +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -- cgit v1.2.3