From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail.kernel.org (mail.kernel.org [198.145.29.136]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 3rJxPh6HS5zDqc9 for ; Wed, 1 Jun 2016 00:55:52 +1000 (AEST) Date: Tue, 31 May 2016 23:55:38 +0900 From: Masami Hiramatsu To: Anju T Cc: linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, ananth@in.ibm.com, naveen.n.rao@linux.vnet.ibm.com, paulus@samba.org, srikar@linux.vnet.ibm.com, benh@kernel.crashing.org, mpe@ellerman.id.au, hemant@linux.vnet.ibm.com, mahesh@linux.vnet.ibm.com, mhiramat@kernel.org, anjutsudhakar@gmail.com Subject: Re: [RFC PATCH v3 2/3] arch/powerpc : optprobes for powerpc core Message-Id: <20160531235538.2cddbe49246f5ab3162d879b@kernel.org> In-Reply-To: <201605311058.u4VAsdah009164@mx0a-001b2d01.pphosted.com> References: <1464692191-1167-1-git-send-email-anju@linux.vnet.ibm.com> <201605311058.u4VAsdah009164@mx0a-001b2d01.pphosted.com> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On Tue, 31 May 2016 16:26:30 +0530 Anju T wrote: > Instructions which can be emulated are suppliants for > optimization. Before optimization ensure that the address range > between the detour buffer allocated and the instruction being probed > is within +/- 32MB. > > Signed-off-by: Anju T > --- > arch/powerpc/kernel/optprobes.c | 351 ++++++++++++++++++++++++++++++++++++++++ > 1 file changed, 351 insertions(+) > create mode 100644 arch/powerpc/kernel/optprobes.c > > diff --git a/arch/powerpc/kernel/optprobes.c b/arch/powerpc/kernel/optprobes.c > new file mode 100644 > index 0000000..c4253b6 > --- /dev/null > +++ b/arch/powerpc/kernel/optprobes.c > @@ -0,0 +1,351 @@ > +/* > + * Code for Kernel probes Jump optimization. > + * > + * Copyright 2016, Anju T, IBM Corp. > + * > + * This program is free software; you can redistribute it and/or > + * modify it under the terms of the GNU General Public License > + * as published by the Free Software Foundation; either version > + * 2 of the License, or (at your option) any later version. > + */ > + > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > + > +DEFINE_INSN_CACHE_OPS(ppc_optinsn) > + > +#define TMPL_CALL_HDLR_IDX \ > + (optprobe_template_call_handler - optprobe_template_entry) > +#define TMPL_EMULATE_IDX \ > + (optprobe_template_call_emulate - optprobe_template_entry) > +#define TMPL_RET_BRANCH_IDX \ > + (optprobe_template_ret_branch - optprobe_template_entry) > +#define TMPL_RET_IDX \ > + (optprobe_template_ret - optprobe_template_entry) > +#define TMPL_KP_IDX \ > + (optprobe_template_kp_addr - optprobe_template_entry) > +#define TMPL_OP1_IDX \ > + (optprobe_template_op_address1 - optprobe_template_entry) > +#define TMPL_OP2_IDX \ > + (optprobe_template_op_address2 - optprobe_template_entry) > +#define TMPL_INSN_IDX \ > + (optprobe_template_insn - optprobe_template_entry) > +#define TMPL_END_IDX \ > + (optprobe_template_end - optprobe_template_entry) > + > +static unsigned long val_nip; > + > +static void *__ppc_alloc_insn_page(void) > +{ > + return &optinsn_slot; > +} > + > +static void *__ppc_free_insn_page(void *page __maybe_unused) > +{ > + return; > +} Hmm, you should not return optinsn_slot twice or more, because it actually doesn't allocate memory but just returns reserved memory area. So, it should be something like this; static bool insn_page_in_use; static void *__ppc_alloc_insn_page(void) { if (insn_page_in_use) return NULL; insn_page_in_use = true; return &optinsn_slot; } static void *__ppc_free_insn_page(void *page __maybe_unused) { insn_page_in_use = false; } > + > +struct kprobe_insn_cache kprobe_ppc_optinsn_slots = { > + .mutex = __MUTEX_INITIALIZER(kprobe_ppc_optinsn_slots.mutex), > + .pages = LIST_HEAD_INIT(kprobe_ppc_optinsn_slots.pages), > + /* insn_size initialized later */ > + .alloc = __ppc_alloc_insn_page, > + .free = __ppc_free_insn_page, > + .nr_garbage = 0, > +}; > + > +kprobe_opcode_t *ppc_get_optinsn_slot(struct optimized_kprobe *op) > +{ > + /* > + * The insn slot is allocated from the reserved > + * area(ie &optinsn_slot).We are not optimizing probes > + * at module_addr now. > + */ > + kprobe_opcode_t *slot = NULL; > + > + if (is_kernel_addr(op->kp.addr)) > + slot = get_ppc_optinsn_slot(); > + return slot; > +} > + > +static void ppc_free_optinsn_slot(struct optimized_kprobe *op) > +{ > + if (!op->optinsn.insn) > + return; > + if (is_kernel_addr((unsigned long)op->kp.addr)) > + free_ppc_optinsn_slot(op->optinsn.insn, 0); > +} > + > +static void > +__arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty) > +{ > + ppc_free_optinsn_slot(op); > + op->optinsn.insn = NULL; > +} > + > +static int can_optimize(struct kprobe *p) > +{ > + struct pt_regs *regs; > + unsigned int instr; > + int r; > + > + /* > + * Not optimizing the kprobe placed by > + * kretprobe during boot time > + */ > + if ((kprobe_opcode_t)p->addr == (kprobe_opcode_t)&kretprobe_trampoline) > + return 0; > + > + regs = kmalloc(sizeof(*regs), GFP_KERNEL); > + if (!regs) > + return -ENOMEM; > + memset(regs, 0, sizeof(struct pt_regs)); > + memcpy(regs, current_pt_regs(), sizeof(struct pt_regs)); > + regs->nip = p->addr; > + instr = *(p->ainsn.insn); > + > + /* Ensure the instruction can be emulated*/ > + r = emulate_step(regs, instr); > + val_nip = regs->nip; > + if (r != 1) > + return 0; > + > + return 1; > +} > + > +static void > +create_return_branch(struct optimized_kprobe *op, struct pt_regs *regs) > +{ > + /* > + * Create a branch back to the return address > + * after the probed instruction is emulated > + */ > + > + kprobe_opcode_t branch, *buff; > + unsigned long ret; > + > + ret = regs->nip; > + buff = op->optinsn.insn; > + /* > + * TODO: For conditional branch instructions, the return > + * address may differ in SMP systems.This has to be addressed. > + */ > + > + branch = create_branch((unsigned int *)buff + TMPL_RET_IDX, > + (unsigned long)ret, 0); > + buff[TMPL_RET_IDX] = branch; > + isync(); > +} > + > +static void > +optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) > +{ > + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); > + unsigned long flags; > + > + local_irq_save(flags); > + > + if (kprobe_running()) > + kprobes_inc_nmissed_count(&op->kp); > + else { > + __this_cpu_write(current_kprobe, &op->kp); > + kcb->kprobe_status = KPROBE_HIT_ACTIVE; > + opt_pre_handler(&op->kp, regs); > + __this_cpu_write(current_kprobe, NULL); > + } > + local_irq_restore(flags); > +} > +NOKPROBE_SYMBOL(optimized_callback); > + > +void arch_remove_optimized_kprobe(struct optimized_kprobe *op) > +{ > + __arch_remove_optimized_kprobe(op, 1); > +} > + > +void create_insn(unsigned int insn, kprobe_opcode_t *addr) > +{ > + u32 instr, instr2; > + > + /* > + * emulate_step() requires insn to be emulated as > + * second parameter. Hence r4 should be loaded > + * with 'insn'. > + * synthesize addis r4,0,(insn)@h > + */ > + instr = 0x3c000000 | 0x800000 | ((insn >> 16) & 0xffff); > + *addr++ = instr; > + > + /* ori r4,r4,(insn)@l */ > + instr2 = 0x60000000 | 0x40000 | 0x800000; > + instr2 = instr2 | (insn & 0xffff); > + *addr = instr2; > +} > + > +void create_load_address_insn(unsigned long val, kprobe_opcode_t *addr) > +{ > + u32 instr1, instr2, instr3, instr4, instr5; > + /* > + * Optimized_kprobe structure is required as a parameter > + * for invoking optimized_callback() and create_return_branch() > + * from detour buffer. Hence need to have a 64bit immediate > + * load into r3. > + * > + * lis r3,(op)@highest > + */ > + instr1 = 0x3c000000 | 0x600000 | ((val >> 48) & 0xffff); > + *addr++ = instr1; > + > + /* ori r3,r3,(op)@higher */ > + instr2 = 0x60000000 | 0x30000 | 0x600000 | ((val >> 32) & 0xffff); > + *addr++ = instr2; > + > + /* rldicr r3,r3,32,31 */ > + instr3 = 0x78000004 | 0x30000 | 0x600000 | ((32 & 0x1f) << 11); > + instr3 = instr3 | ((31 & 0x1f) << 6) | ((32 & 0x20) >> 4); > + *addr++ = instr3; > + > + /* oris r3,r3,(op)@h */ > + instr4 = 0x64000000 | 0x30000 | 0x600000 | ((val >> 16) & 0xffff); > + *addr++ = instr4; > + > + /* ori r3,r3,(op)@l */ > + instr5 = 0x60000000 | 0x30000 | 0x600000 | (val & 0xffff); > + *addr = instr5; > +} > + > +int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *p) > +{ > + kprobe_opcode_t *buff, branch, branch2, branch3; > + long rel_chk, ret_chk; > + > + kprobe_ppc_optinsn_slots.insn_size = MAX_OPTINSN_SIZE; > + op->optinsn.insn = NULL; > + > + if (!can_optimize(p)) > + return -EILSEQ; > + > + /* Allocate instruction slot for detour buffer*/ > + buff = ppc_get_optinsn_slot(op); > + if (!buff) > + return -ENOMEM; > + > + /* > + * OPTPROBE use a 'b' instruction to branch to optinsn.insn. > + * > + * The target address has to be relatively nearby, to permit use > + * of branch instruction in powerpc because the address is specified > + * in an immediate field in the instruction opcode itself, ie 24 bits > + * in the opcode specify the address. Therefore the address gap should > + * be 32MB on either side of the current instruction. > + */ > + rel_chk = (long)buff - (unsigned long)p->addr; > + if (rel_chk < -0x2000000 || rel_chk > 0x1fffffc || rel_chk & 0x3) { > + ppc_free_optinsn_slot(op); > + return -ERANGE; > + } > + /* Check the return address is also within 32MB range */ > + ret_chk = (long)(buff + TMPL_RET_IDX) - (unsigned long)val_nip; No, please don't pass the "regs->nip" via hidden channel like as this val_nip static local variable. Instead, you should run emulate_step() again here, or, at least you must keep the address and compare it. I recommend former. Thank you, > + if (ret_chk < -0x2000000 || ret_chk > 0x1fffffc || ret_chk & 0x3) { > + ppc_free_optinsn_slot(op); > + return -ERANGE; > + } > + > + /* Do Copy arch specific instance from template*/ > + memcpy(buff, optprobe_template_entry, > + TMPL_END_IDX * sizeof(kprobe_opcode_t)); > + create_load_address_insn((unsigned long)p->addr, buff + TMPL_KP_IDX); > + create_load_address_insn((unsigned long)op, buff + TMPL_OP1_IDX); > + create_load_address_insn((unsigned long)op, buff + TMPL_OP2_IDX); > + > + /* Create a branch to the optimized_callback function */ > + branch = create_branch((unsigned int *)buff + TMPL_CALL_HDLR_IDX, > + (unsigned long)optimized_callback + 8, > + BRANCH_SET_LINK); > + > + /* Place the branch instr into the trampoline */ > + buff[TMPL_CALL_HDLR_IDX] = branch; > + create_insn(*(p->ainsn.insn), buff + TMPL_INSN_IDX); > + > + /*Create a branch instruction into the emulate_step*/ > + branch3 = create_branch((unsigned int *)buff + TMPL_EMULATE_IDX, > + (unsigned long)emulate_step + 8, > + BRANCH_SET_LINK); > + buff[TMPL_EMULATE_IDX] = branch3; > + > + /* Create a branch for jumping back*/ > + branch2 = create_branch((unsigned int *)buff + TMPL_RET_BRANCH_IDX, > + (unsigned long)create_return_branch + 8, > + BRANCH_SET_LINK); > + buff[TMPL_RET_BRANCH_IDX] = branch2; > + > + op->optinsn.insn = buff; > + smp_mb(); > + return 0; > +} > + > +int arch_prepared_optinsn(struct arch_optimized_insn *optinsn) > +{ > + return optinsn->insn; > +} > + > +/* > + * Here,kprobe opt always replace one instruction (4 bytes > + * aligned and 4 bytes long). It is impossible to encounter another > + * kprobe in the address range. So always return 0. > + */ > +int arch_check_optimized_kprobe(struct optimized_kprobe *op) > +{ > + return 0; > +} > + > +void arch_optimize_kprobes(struct list_head *oplist) > +{ > + struct optimized_kprobe *op; > + struct optimized_kprobe *tmp; > + > + unsigned int branch; > + > + list_for_each_entry_safe(op, tmp, oplist, list) { > + /* > + * Backup instructions which will be replaced > + *by jump address > + */ > + memcpy(op->optinsn.copied_insn, op->kp.addr, > + RELATIVEJUMP_SIZE); > + branch = create_branch((unsigned int *)op->kp.addr, > + (unsigned long)op->optinsn.insn, 0); > + *op->kp.addr = branch; > + list_del_init(&op->list); > + } > +} > + > +void arch_unoptimize_kprobe(struct optimized_kprobe *op) > +{ > + arch_arm_kprobe(&op->kp); > +} > + > +void arch_unoptimize_kprobes(struct list_head *oplist, > + struct list_head *done_list) > +{ > + struct optimized_kprobe *op; > + struct optimized_kprobe *tmp; > + > + list_for_each_entry_safe(op, tmp, oplist, list) { > + arch_unoptimize_kprobe(op); > + list_move(&op->list, done_list); > + } > +} > + > +int arch_within_optimized_kprobe(struct optimized_kprobe *op, > + unsigned long addr) > +{ > + return 0; > +} > -- > 2.1.0 > -- Masami Hiramatsu