diff --git a/Documentation/trace/uprobetracer.txt b/Documentation/trace/uprobetracer.txt index 24ce6823a09e..d9c3e682312c 100644 --- a/Documentation/trace/uprobetracer.txt +++ b/Documentation/trace/uprobetracer.txt @@ -1,6 +1,8 @@ - Uprobe-tracer: Uprobe-based Event Tracing - ========================================= - Documentation written by Srikar Dronamraju + Uprobe-tracer: Uprobe-based Event Tracing + ========================================= + + Documentation written by Srikar Dronamraju + Overview -------- @@ -13,78 +15,94 @@ current_tracer. Instead of that, add probe points via /sys/kernel/debug/tracing/events/uprobes//enabled. However unlike kprobe-event tracer, the uprobe event interface expects the -user to calculate the offset of the probepoint in the object +user to calculate the offset of the probepoint in the object. Synopsis of uprobe_tracer ------------------------- - p[:[GRP/]EVENT] PATH:SYMBOL[+offs] [FETCHARGS] : Set a probe + p[:[GRP/]EVENT] PATH:SYMBOL[+offs] [FETCHARGS] : Set a uprobe + r[:[GRP/]EVENT] PATH:SYMBOL[+offs] [FETCHARGS] : Set a return uprobe (uretprobe) + -:[GRP/]EVENT : Clear uprobe or uretprobe event - GRP : Group name. If omitted, use "uprobes" for it. - EVENT : Event name. If omitted, the event name is generated - based on SYMBOL+offs. - PATH : path to an executable or a library. - SYMBOL[+offs] : Symbol+offset where the probe is inserted. + GRP : Group name. If omitted, "uprobes" is the default value. + EVENT : Event name. If omitted, the event name is generated based + on SYMBOL+offs. + PATH : Path to an executable or a library. + SYMBOL[+offs] : Symbol+offset where the probe is inserted. - FETCHARGS : Arguments. Each probe can have up to 128 args. - %REG : Fetch register REG + FETCHARGS : Arguments. Each probe can have up to 128 args. + %REG : Fetch register REG Event Profiling --------------- - You can check the total number of probe hits and probe miss-hits via +You can check the total number of probe hits and probe miss-hits via /sys/kernel/debug/tracing/uprobe_profile. - The first column is event name, the second is the number of probe hits, +The first column is event name, the second is the number of probe hits, the third is the number of probe miss-hits. Usage examples -------------- -To add a probe as a new event, write a new definition to uprobe_events -as below. + * Add a probe as a new uprobe event, write a new definition to uprobe_events +as below: (sets a uprobe at an offset of 0x4245c0 in the executable /bin/bash) - echo 'p: /bin/bash:0x4245c0' > /sys/kernel/debug/tracing/uprobe_events + echo 'p: /bin/bash:0x4245c0' > /sys/kernel/debug/tracing/uprobe_events - This sets a uprobe at an offset of 0x4245c0 in the executable /bin/bash + * Add a probe as a new uretprobe event: - echo > /sys/kernel/debug/tracing/uprobe_events + echo 'r: /bin/bash:0x4245c0' > /sys/kernel/debug/tracing/uprobe_events - This clears all probe points. + * Unset registered event: -The following example shows how to dump the instruction pointer and %ax -a register at the probed text address. Here we are trying to probe -function zfree in /bin/zsh + echo '-:bash_0x4245c0' >> /sys/kernel/debug/tracing/uprobe_events + + * Print out the events that are registered: + + cat /sys/kernel/debug/tracing/uprobe_events + + * Clear all events: + + echo > /sys/kernel/debug/tracing/uprobe_events + +Following example shows how to dump the instruction pointer and %ax register +at the probed text address. Probe zfree function in /bin/zsh: # cd /sys/kernel/debug/tracing/ - # cat /proc/`pgrep zsh`/maps | grep /bin/zsh | grep r-xp + # cat /proc/`pgrep zsh`/maps | grep /bin/zsh | grep r-xp 00400000-0048a000 r-xp 00000000 08:03 130904 /bin/zsh # objdump -T /bin/zsh | grep -w zfree 0000000000446420 g DF .text 0000000000000012 Base zfree -0x46420 is the offset of zfree in object /bin/zsh that is loaded at -0x00400000. Hence the command to probe would be : + 0x46420 is the offset of zfree in object /bin/zsh that is loaded at + 0x00400000. Hence the command to uprobe would be: - # echo 'p /bin/zsh:0x46420 %ip %ax' > uprobe_events + # echo 'p:zfree_entry /bin/zsh:0x46420 %ip %ax' > uprobe_events -Please note: User has to explicitly calculate the offset of the probepoint + And the same for the uretprobe would be: + + # echo 'r:zfree_exit /bin/zsh:0x46420 %ip %ax' >> uprobe_events + +Please note: User has to explicitly calculate the offset of the probe-point in the object. We can see the events that are registered by looking at the uprobe_events file. # cat uprobe_events - p:uprobes/p_zsh_0x46420 /bin/zsh:0x00046420 arg1=%ip arg2=%ax + p:uprobes/zfree_entry /bin/zsh:0x00046420 arg1=%ip arg2=%ax + r:uprobes/zfree_exit /bin/zsh:0x00046420 arg1=%ip arg2=%ax -The format of events can be seen by viewing the file events/uprobes/p_zsh_0x46420/format +Format of events can be seen by viewing the file events/uprobes/zfree_entry/format - # cat events/uprobes/p_zsh_0x46420/format - name: p_zsh_0x46420 + # cat events/uprobes/zfree_entry/format + name: zfree_entry ID: 922 format: - field:unsigned short common_type; offset:0; size:2; signed:0; - field:unsigned char common_flags; offset:2; size:1; signed:0; - field:unsigned char common_preempt_count; offset:3; size:1; signed:0; - field:int common_pid; offset:4; size:4; signed:1; - field:int common_padding; offset:8; size:4; signed:1; + field:unsigned short common_type; offset:0; size:2; signed:0; + field:unsigned char common_flags; offset:2; size:1; signed:0; + field:unsigned char common_preempt_count; offset:3; size:1; signed:0; + field:int common_pid; offset:4; size:4; signed:1; + field:int common_padding; offset:8; size:4; signed:1; - field:unsigned long __probe_ip; offset:12; size:4; signed:0; - field:u32 arg1; offset:16; size:4; signed:0; - field:u32 arg2; offset:20; size:4; signed:0; + field:unsigned long __probe_ip; offset:12; size:4; signed:0; + field:u32 arg1; offset:16; size:4; signed:0; + field:u32 arg2; offset:20; size:4; signed:0; print fmt: "(%lx) arg1=%lx arg2=%lx", REC->__probe_ip, REC->arg1, REC->arg2 @@ -94,6 +112,7 @@ events, you need to enable it by: # echo 1 > events/uprobes/enable Lets disable the event after sleeping for some time. + # sleep 20 # echo 0 > events/uprobes/enable @@ -104,10 +123,11 @@ And you can see the traced information via /sys/kernel/debug/tracing/trace. # # TASK-PID CPU# TIMESTAMP FUNCTION # | | | | | - zsh-24842 [006] 258544.995456: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79 - zsh-24842 [007] 258545.000270: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79 - zsh-24842 [002] 258545.043929: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79 - zsh-24842 [004] 258547.046129: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79 + zsh-24842 [006] 258544.995456: zfree_entry: (0x446420) arg1=446420 arg2=79 + zsh-24842 [007] 258545.000270: zfree_exit: (0x446540 <- 0x446420) arg1=446540 arg2=0 + zsh-24842 [002] 258545.043929: zfree_entry: (0x446420) arg1=446420 arg2=79 + zsh-24842 [004] 258547.046129: zfree_exit: (0x446540 <- 0x446420) arg1=446540 arg2=0 -Each line shows us probes were triggered for a pid 24842 with ip being -0x446421 and contents of ax register being 79. +Output shows us uprobe was triggered for a pid 24842 with ip being 0x446420 +and contents of ax register being 79. And uretprobe was triggered with ip at +0x446540 with counterpart function entry at 0x446420. diff --git a/arch/powerpc/include/asm/uprobes.h b/arch/powerpc/include/asm/uprobes.h index b532060d0916..23016020915e 100644 --- a/arch/powerpc/include/asm/uprobes.h +++ b/arch/powerpc/include/asm/uprobes.h @@ -51,4 +51,5 @@ extern int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs); extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk); extern int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data); extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs); +extern unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs); #endif /* _ASM_UPROBES_H */ diff --git a/arch/powerpc/kernel/uprobes.c b/arch/powerpc/kernel/uprobes.c index bc77834dbf43..59f419b935f2 100644 --- a/arch/powerpc/kernel/uprobes.c +++ b/arch/powerpc/kernel/uprobes.c @@ -30,6 +30,16 @@ #define UPROBE_TRAP_NR UINT_MAX +/** + * is_trap_insn - check if the instruction is a trap variant + * @insn: instruction to be checked. + * Returns true if @insn is a trap variant. + */ +bool is_trap_insn(uprobe_opcode_t *insn) +{ + return (is_trap(*insn)); +} + /** * arch_uprobe_analyze_insn * @mm: the probed address space. @@ -43,12 +53,6 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, if (addr & 0x03) return -EINVAL; - /* - * We currently don't support a uprobe on an already - * existing breakpoint instruction underneath - */ - if (is_trap(auprobe->ainsn)) - return -ENOTSUPP; return 0; } @@ -188,3 +192,16 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) return false; } + +unsigned long +arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs) +{ + unsigned long orig_ret_vaddr; + + orig_ret_vaddr = regs->link; + + /* Replace the return addr with trampoline addr */ + regs->link = trampoline_vaddr; + + return orig_ret_vaddr; +} diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h index 8ff8be7835ab..6e5197910fd8 100644 --- a/arch/x86/include/asm/uprobes.h +++ b/arch/x86/include/asm/uprobes.h @@ -55,4 +55,5 @@ extern int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs); extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk); extern int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data); extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs); +extern unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs); #endif /* _ASM_UPROBES_H */ diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 0ba4cfb4f412..2ed845928b5f 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -697,3 +697,32 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) send_sig(SIGTRAP, current, 0); return ret; } + +unsigned long +arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs) +{ + int rasize, ncopied; + unsigned long orig_ret_vaddr = 0; /* clear high bits for 32-bit apps */ + + rasize = is_ia32_task() ? 4 : 8; + ncopied = copy_from_user(&orig_ret_vaddr, (void __user *)regs->sp, rasize); + if (unlikely(ncopied)) + return -1; + + /* check whether address has been already hijacked */ + if (orig_ret_vaddr == trampoline_vaddr) + return orig_ret_vaddr; + + ncopied = copy_to_user((void __user *)regs->sp, &trampoline_vaddr, rasize); + if (likely(!ncopied)) + return orig_ret_vaddr; + + if (ncopied != rasize) { + pr_err("uprobe: return address clobbered: pid=%d, %%sp=%#lx, " + "%%ip=%#lx\n", current->pid, regs->sp, regs->ip); + + force_sig_info(SIGSEGV, SEND_SIG_FORCED, current); + } + + return -1; +} diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 02b83db8e2c5..06f28beed7c2 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -38,6 +38,8 @@ struct inode; #define UPROBE_HANDLER_REMOVE 1 #define UPROBE_HANDLER_MASK 1 +#define MAX_URETPROBE_DEPTH 64 + enum uprobe_filter_ctx { UPROBE_FILTER_REGISTER, UPROBE_FILTER_UNREGISTER, @@ -46,6 +48,9 @@ enum uprobe_filter_ctx { struct uprobe_consumer { int (*handler)(struct uprobe_consumer *self, struct pt_regs *regs); + int (*ret_handler)(struct uprobe_consumer *self, + unsigned long func, + struct pt_regs *regs); bool (*filter)(struct uprobe_consumer *self, enum uprobe_filter_ctx ctx, struct mm_struct *mm); @@ -68,6 +73,8 @@ struct uprobe_task { enum uprobe_task_state state; struct arch_uprobe_task autask; + struct return_instance *return_instances; + unsigned int depth; struct uprobe *active_uprobe; unsigned long xol_vaddr; @@ -100,6 +107,7 @@ struct uprobes_state { extern int __weak set_swbp(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr); extern int __weak set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr); extern bool __weak is_swbp_insn(uprobe_opcode_t *insn); +extern bool __weak is_trap_insn(uprobe_opcode_t *insn); extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool); extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index a567c8c7ef31..f3569747d629 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -75,6 +75,15 @@ struct uprobe { struct arch_uprobe arch; }; +struct return_instance { + struct uprobe *uprobe; + unsigned long func; + unsigned long orig_ret_vaddr; /* original return address */ + bool chained; /* true, if instance is nested */ + + struct return_instance *next; /* keep as stack */ +}; + /* * valid_vma: Verify if the specified vma is an executable vma * Relax restrictions while unregistering: vm_flags might have @@ -173,10 +182,31 @@ bool __weak is_swbp_insn(uprobe_opcode_t *insn) return *insn == UPROBE_SWBP_INSN; } -static void copy_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t *opcode) +/** + * is_trap_insn - check if instruction is breakpoint instruction. + * @insn: instruction to be checked. + * Default implementation of is_trap_insn + * Returns true if @insn is a breakpoint instruction. + * + * This function is needed for the case where an architecture has multiple + * trap instructions (like powerpc). + */ +bool __weak is_trap_insn(uprobe_opcode_t *insn) +{ + return is_swbp_insn(insn); +} + +static void copy_from_page(struct page *page, unsigned long vaddr, void *dst, int len) { void *kaddr = kmap_atomic(page); - memcpy(opcode, kaddr + (vaddr & ~PAGE_MASK), UPROBE_SWBP_INSN_SIZE); + memcpy(dst, kaddr + (vaddr & ~PAGE_MASK), len); + kunmap_atomic(kaddr); +} + +static void copy_to_page(struct page *page, unsigned long vaddr, const void *src, int len) +{ + void *kaddr = kmap_atomic(page); + memcpy(kaddr + (vaddr & ~PAGE_MASK), src, len); kunmap_atomic(kaddr); } @@ -185,7 +215,16 @@ static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t uprobe_opcode_t old_opcode; bool is_swbp; - copy_opcode(page, vaddr, &old_opcode); + /* + * Note: We only check if the old_opcode is UPROBE_SWBP_INSN here. + * We do not check if it is any other 'trap variant' which could + * be conditional trap instruction such as the one powerpc supports. + * + * The logic is that we do not care if the underlying instruction + * is a trap variant; uprobes always wins over any other (gdb) + * breakpoint. + */ + copy_from_page(page, vaddr, &old_opcode, UPROBE_SWBP_INSN_SIZE); is_swbp = is_swbp_insn(&old_opcode); if (is_swbp_insn(new_opcode)) { @@ -204,7 +243,7 @@ static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t * Expect the breakpoint instruction to be the smallest size instruction for * the architecture. If an arch has variable length instruction and the * breakpoint instruction is not of the smallest length instruction - * supported by that architecture then we need to modify is_swbp_at_addr and + * supported by that architecture then we need to modify is_trap_at_addr and * write_opcode accordingly. This would never be a problem for archs that * have fixed length instructions. */ @@ -225,7 +264,6 @@ static int write_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t opcode) { struct page *old_page, *new_page; - void *vaddr_old, *vaddr_new; struct vm_area_struct *vma; int ret; @@ -246,15 +284,8 @@ retry: __SetPageUptodate(new_page); - /* copy the page now that we've got it stable */ - vaddr_old = kmap_atomic(old_page); - vaddr_new = kmap_atomic(new_page); - - memcpy(vaddr_new, vaddr_old, PAGE_SIZE); - memcpy(vaddr_new + (vaddr & ~PAGE_MASK), &opcode, UPROBE_SWBP_INSN_SIZE); - - kunmap_atomic(vaddr_new); - kunmap_atomic(vaddr_old); + copy_highpage(new_page, old_page); + copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE); ret = anon_vma_prepare(vma); if (ret) @@ -477,30 +508,18 @@ __copy_insn(struct address_space *mapping, struct file *filp, char *insn, unsigned long nbytes, loff_t offset) { struct page *page; - void *vaddr; - unsigned long off; - pgoff_t idx; - - if (!filp) - return -EINVAL; if (!mapping->a_ops->readpage) return -EIO; - - idx = offset >> PAGE_CACHE_SHIFT; - off = offset & ~PAGE_MASK; - /* * Ensure that the page that has the original instruction is * populated and in page-cache. */ - page = read_mapping_page(mapping, idx, filp); + page = read_mapping_page(mapping, offset >> PAGE_CACHE_SHIFT, filp); if (IS_ERR(page)) return PTR_ERR(page); - vaddr = kmap_atomic(page); - memcpy(insn, vaddr + off, nbytes); - kunmap_atomic(vaddr); + copy_from_page(page, offset, insn, nbytes); page_cache_release(page); return 0; @@ -550,7 +569,7 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file, goto out; ret = -ENOTSUPP; - if (is_swbp_insn((uprobe_opcode_t *)uprobe->arch.insn)) + if (is_trap_insn((uprobe_opcode_t *)uprobe->arch.insn)) goto out; ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr); @@ -758,7 +777,7 @@ register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new) down_write(&mm->mmap_sem); vma = find_vma(mm, info->vaddr); if (!vma || !valid_vma(vma, is_register) || - vma->vm_file->f_mapping->host != uprobe->inode) + file_inode(vma->vm_file) != uprobe->inode) goto unlock; if (vma->vm_start > info->vaddr || @@ -828,6 +847,10 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer * struct uprobe *uprobe; int ret; + /* Uprobe must have at least one set consumer */ + if (!uc->handler && !uc->ret_handler) + return -EINVAL; + /* Racy, just to catch the obvious mistakes */ if (offset > i_size_read(inode)) return -EINVAL; @@ -917,7 +940,7 @@ static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm) loff_t offset; if (!valid_vma(vma, false) || - vma->vm_file->f_mapping->host != uprobe->inode) + file_inode(vma->vm_file) != uprobe->inode) continue; offset = (loff_t)vma->vm_pgoff << PAGE_SHIFT; @@ -1010,7 +1033,7 @@ int uprobe_mmap(struct vm_area_struct *vma) if (no_uprobe_events() || !valid_vma(vma, true)) return 0; - inode = vma->vm_file->f_mapping->host; + inode = file_inode(vma->vm_file); if (!inode) return 0; @@ -1041,7 +1064,7 @@ vma_has_uprobes(struct vm_area_struct *vma, unsigned long start, unsigned long e struct inode *inode; struct rb_node *n; - inode = vma->vm_file->f_mapping->host; + inode = file_inode(vma->vm_file); min = vaddr_to_offset(vma, start); max = min + (end - start) - 1; @@ -1114,6 +1137,7 @@ static struct xol_area *get_xol_area(void) { struct mm_struct *mm = current->mm; struct xol_area *area; + uprobe_opcode_t insn = UPROBE_SWBP_INSN; area = mm->uprobes_state.xol_area; if (area) @@ -1131,7 +1155,12 @@ static struct xol_area *get_xol_area(void) if (!area->page) goto free_bitmap; + /* allocate first slot of task's xol_area for the return probes */ + set_bit(0, area->bitmap); + copy_to_page(area->page, 0, &insn, UPROBE_SWBP_INSN_SIZE); + atomic_set(&area->slot_count, 1); init_waitqueue_head(&area->wq); + if (!xol_add_vma(area)) return area; @@ -1216,9 +1245,7 @@ static unsigned long xol_take_insn_slot(struct xol_area *area) static unsigned long xol_get_insn_slot(struct uprobe *uprobe) { struct xol_area *area; - unsigned long offset; unsigned long xol_vaddr; - void *vaddr; area = get_xol_area(); if (!area) @@ -1229,10 +1256,7 @@ static unsigned long xol_get_insn_slot(struct uprobe *uprobe) return 0; /* Initialize the slot */ - offset = xol_vaddr & ~PAGE_MASK; - vaddr = kmap_atomic(area->page); - memcpy(vaddr + offset, uprobe->arch.insn, MAX_UINSN_BYTES); - kunmap_atomic(vaddr); + copy_to_page(area->page, xol_vaddr, uprobe->arch.insn, MAX_UINSN_BYTES); /* * We probably need flush_icache_user_range() but it needs vma. * This should work on supported architectures too. @@ -1298,6 +1322,7 @@ unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs) void uprobe_free_utask(struct task_struct *t) { struct uprobe_task *utask = t->utask; + struct return_instance *ri, *tmp; if (!utask) return; @@ -1305,6 +1330,15 @@ void uprobe_free_utask(struct task_struct *t) if (utask->active_uprobe) put_uprobe(utask->active_uprobe); + ri = utask->return_instances; + while (ri) { + tmp = ri; + ri = ri->next; + + put_uprobe(tmp->uprobe); + kfree(tmp); + } + xol_free_insn_slot(t); kfree(utask); t->utask = NULL; @@ -1333,6 +1367,93 @@ static struct uprobe_task *get_utask(void) return current->utask; } +/* + * Current area->vaddr notion assume the trampoline address is always + * equal area->vaddr. + * + * Returns -1 in case the xol_area is not allocated. + */ +static unsigned long get_trampoline_vaddr(void) +{ + struct xol_area *area; + unsigned long trampoline_vaddr = -1; + + area = current->mm->uprobes_state.xol_area; + smp_read_barrier_depends(); + if (area) + trampoline_vaddr = area->vaddr; + + return trampoline_vaddr; +} + +static void prepare_uretprobe(struct uprobe *uprobe, struct pt_regs *regs) +{ + struct return_instance *ri; + struct uprobe_task *utask; + unsigned long orig_ret_vaddr, trampoline_vaddr; + bool chained = false; + + if (!get_xol_area()) + return; + + utask = get_utask(); + if (!utask) + return; + + if (utask->depth >= MAX_URETPROBE_DEPTH) { + printk_ratelimited(KERN_INFO "uprobe: omit uretprobe due to" + " nestedness limit pid/tgid=%d/%d\n", + current->pid, current->tgid); + return; + } + + ri = kzalloc(sizeof(struct return_instance), GFP_KERNEL); + if (!ri) + goto fail; + + trampoline_vaddr = get_trampoline_vaddr(); + orig_ret_vaddr = arch_uretprobe_hijack_return_addr(trampoline_vaddr, regs); + if (orig_ret_vaddr == -1) + goto fail; + + /* + * We don't want to keep trampoline address in stack, rather keep the + * original return address of first caller thru all the consequent + * instances. This also makes breakpoint unwrapping easier. + */ + if (orig_ret_vaddr == trampoline_vaddr) { + if (!utask->return_instances) { + /* + * This situation is not possible. Likely we have an + * attack from user-space. + */ + pr_warn("uprobe: unable to set uretprobe pid/tgid=%d/%d\n", + current->pid, current->tgid); + goto fail; + } + + chained = true; + orig_ret_vaddr = utask->return_instances->orig_ret_vaddr; + } + + atomic_inc(&uprobe->ref); + ri->uprobe = uprobe; + ri->func = instruction_pointer(regs); + ri->orig_ret_vaddr = orig_ret_vaddr; + ri->chained = chained; + + utask->depth++; + + /* add instance to the stack */ + ri->next = utask->return_instances; + utask->return_instances = ri; + + return; + + fail: + kfree(ri); +} + /* Prepare to single-step probed instruction out of line. */ static int pre_ssout(struct uprobe *uprobe, struct pt_regs *regs, unsigned long bp_vaddr) @@ -1431,7 +1552,7 @@ static void mmf_recalc_uprobes(struct mm_struct *mm) clear_bit(MMF_HAS_UPROBES, &mm->flags); } -static int is_swbp_at_addr(struct mm_struct *mm, unsigned long vaddr) +static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr) { struct page *page; uprobe_opcode_t opcode; @@ -1449,10 +1570,11 @@ static int is_swbp_at_addr(struct mm_struct *mm, unsigned long vaddr) if (result < 0) return result; - copy_opcode(page, vaddr, &opcode); + copy_from_page(page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE); put_page(page); out: - return is_swbp_insn(&opcode); + /* This needs to return true for any variant of the trap insn */ + return is_trap_insn(&opcode); } static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp) @@ -1465,14 +1587,14 @@ static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp) vma = find_vma(mm, bp_vaddr); if (vma && vma->vm_start <= bp_vaddr) { if (valid_vma(vma, false)) { - struct inode *inode = vma->vm_file->f_mapping->host; + struct inode *inode = file_inode(vma->vm_file); loff_t offset = vaddr_to_offset(vma, bp_vaddr); uprobe = find_uprobe(inode, offset); } if (!uprobe) - *is_swbp = is_swbp_at_addr(mm, bp_vaddr); + *is_swbp = is_trap_at_addr(mm, bp_vaddr); } else { *is_swbp = -EFAULT; } @@ -1488,16 +1610,27 @@ static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs) { struct uprobe_consumer *uc; int remove = UPROBE_HANDLER_REMOVE; + bool need_prep = false; /* prepare return uprobe, when needed */ down_read(&uprobe->register_rwsem); for (uc = uprobe->consumers; uc; uc = uc->next) { - int rc = uc->handler(uc, regs); + int rc = 0; + + if (uc->handler) { + rc = uc->handler(uc, regs); + WARN(rc & ~UPROBE_HANDLER_MASK, + "bad rc=0x%x from %pf()\n", rc, uc->handler); + } + + if (uc->ret_handler) + need_prep = true; - WARN(rc & ~UPROBE_HANDLER_MASK, - "bad rc=0x%x from %pf()\n", rc, uc->handler); remove &= rc; } + if (need_prep && !remove) + prepare_uretprobe(uprobe, regs); /* put bp at return */ + if (remove && uprobe->consumers) { WARN_ON(!uprobe_is_active(uprobe)); unapply_uprobe(uprobe, current->mm); @@ -1505,6 +1638,64 @@ static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs) up_read(&uprobe->register_rwsem); } +static void +handle_uretprobe_chain(struct return_instance *ri, struct pt_regs *regs) +{ + struct uprobe *uprobe = ri->uprobe; + struct uprobe_consumer *uc; + + down_read(&uprobe->register_rwsem); + for (uc = uprobe->consumers; uc; uc = uc->next) { + if (uc->ret_handler) + uc->ret_handler(uc, ri->func, regs); + } + up_read(&uprobe->register_rwsem); +} + +static bool handle_trampoline(struct pt_regs *regs) +{ + struct uprobe_task *utask; + struct return_instance *ri, *tmp; + bool chained; + + utask = current->utask; + if (!utask) + return false; + + ri = utask->return_instances; + if (!ri) + return false; + + /* + * TODO: we should throw out return_instance's invalidated by + * longjmp(), currently we assume that the probed function always + * returns. + */ + instruction_pointer_set(regs, ri->orig_ret_vaddr); + + for (;;) { + handle_uretprobe_chain(ri, regs); + + chained = ri->chained; + put_uprobe(ri->uprobe); + + tmp = ri; + ri = ri->next; + kfree(tmp); + + if (!chained) + break; + + utask->depth--; + + BUG_ON(!ri); + } + + utask->return_instances = ri; + + return true; +} + /* * Run handler and ask thread to singlestep. * Ensure all non-fatal signals cannot interrupt thread while it singlesteps. @@ -1516,8 +1707,15 @@ static void handle_swbp(struct pt_regs *regs) int uninitialized_var(is_swbp); bp_vaddr = uprobe_get_swbp_addr(regs); - uprobe = find_active_uprobe(bp_vaddr, &is_swbp); + if (bp_vaddr == get_trampoline_vaddr()) { + if (handle_trampoline(regs)) + return; + pr_warn("uprobe: unable to handle uretprobe pid/tgid=%d/%d\n", + current->pid, current->tgid); + } + + uprobe = find_active_uprobe(bp_vaddr, &is_swbp); if (!uprobe) { if (is_swbp > 0) { /* No matching uprobe; signal SIGTRAP. */ @@ -1616,7 +1814,11 @@ void uprobe_notify_resume(struct pt_regs *regs) */ int uprobe_pre_sstep_notifier(struct pt_regs *regs) { - if (!current->mm || !test_bit(MMF_HAS_UPROBES, ¤t->mm->flags)) + if (!current->mm) + return 0; + + if (!test_bit(MMF_HAS_UPROBES, ¤t->mm->flags) && + (!current->utask || !current->utask->return_instances)) return 0; set_thread_flag(TIF_UPROBE); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 2081971367ea..8bed1dfcb938 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -103,11 +103,6 @@ struct kretprobe_trace_entry_head { unsigned long ret_ip; }; -struct uprobe_trace_entry_head { - struct trace_entry ent; - unsigned long ip; -}; - /* * trace_flag_type is an enumeration that holds different * states when a trace occurs. These are: diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 8dad2a92dee9..32494fb0ee64 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -28,6 +28,18 @@ #define UPROBE_EVENT_SYSTEM "uprobes" +struct uprobe_trace_entry_head { + struct trace_entry ent; + unsigned long vaddr[]; +}; + +#define SIZEOF_TRACE_ENTRY(is_return) \ + (sizeof(struct uprobe_trace_entry_head) + \ + sizeof(unsigned long) * (is_return ? 2 : 1)) + +#define DATAOF_TRACE_ENTRY(entry, is_return) \ + ((void*)(entry) + SIZEOF_TRACE_ENTRY(is_return)) + struct trace_uprobe_filter { rwlock_t rwlock; int nr_systemwide; @@ -64,6 +76,8 @@ static DEFINE_MUTEX(uprobe_lock); static LIST_HEAD(uprobe_list); static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs); +static int uretprobe_dispatcher(struct uprobe_consumer *con, + unsigned long func, struct pt_regs *regs); static inline void init_trace_uprobe_filter(struct trace_uprobe_filter *filter) { @@ -77,11 +91,16 @@ static inline bool uprobe_filter_is_empty(struct trace_uprobe_filter *filter) return !filter->nr_systemwide && list_empty(&filter->perf_events); } +static inline bool is_ret_probe(struct trace_uprobe *tu) +{ + return tu->consumer.ret_handler != NULL; +} + /* * Allocate new trace_uprobe and initialize it (including uprobes). */ static struct trace_uprobe * -alloc_trace_uprobe(const char *group, const char *event, int nargs) +alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) { struct trace_uprobe *tu; @@ -106,6 +125,8 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs) INIT_LIST_HEAD(&tu->list); tu->consumer.handler = uprobe_dispatcher; + if (is_ret) + tu->consumer.ret_handler = uretprobe_dispatcher; init_trace_uprobe_filter(&tu->filter); return tu; @@ -180,7 +201,7 @@ end: /* * Argument syntax: - * - Add uprobe: p[:[GRP/]EVENT] PATH:SYMBOL[+offs] [FETCHARGS] + * - Add uprobe: p|r[:[GRP/]EVENT] PATH:SYMBOL [FETCHARGS] * * - Remove uprobe: -:[GRP/]EVENT */ @@ -192,20 +213,23 @@ static int create_trace_uprobe(int argc, char **argv) char buf[MAX_EVENT_NAME_LEN]; struct path path; unsigned long offset; - bool is_delete; + bool is_delete, is_return; int i, ret; inode = NULL; ret = 0; is_delete = false; + is_return = false; event = NULL; group = NULL; /* argc must be >= 1 */ if (argv[0][0] == '-') is_delete = true; + else if (argv[0][0] == 'r') + is_return = true; else if (argv[0][0] != 'p') { - pr_info("Probe definition must be started with 'p' or '-'.\n"); + pr_info("Probe definition must be started with 'p', 'r' or '-'.\n"); return -EINVAL; } @@ -303,7 +327,7 @@ static int create_trace_uprobe(int argc, char **argv) kfree(tail); } - tu = alloc_trace_uprobe(group, event, argc); + tu = alloc_trace_uprobe(group, event, argc, is_return); if (IS_ERR(tu)) { pr_info("Failed to allocate trace_uprobe.(%d)\n", (int)PTR_ERR(tu)); ret = PTR_ERR(tu); @@ -414,9 +438,10 @@ static void probes_seq_stop(struct seq_file *m, void *v) static int probes_seq_show(struct seq_file *m, void *v) { struct trace_uprobe *tu = v; + char c = is_ret_probe(tu) ? 'r' : 'p'; int i; - seq_printf(m, "p:%s/%s", tu->call.class->system, tu->call.name); + seq_printf(m, "%c:%s/%s", c, tu->call.class->system, tu->call.name); seq_printf(m, " %s:0x%p", tu->filename, (void *)tu->offset); for (i = 0; i < tu->nr_args; i++) @@ -485,65 +510,81 @@ static const struct file_operations uprobe_profile_ops = { .release = seq_release, }; -/* uprobe handler */ -static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs) +static void uprobe_trace_print(struct trace_uprobe *tu, + unsigned long func, struct pt_regs *regs) { struct uprobe_trace_entry_head *entry; struct ring_buffer_event *event; struct ring_buffer *buffer; - u8 *data; - int size, i, pc; - unsigned long irq_flags; + void *data; + int size, i; struct ftrace_event_call *call = &tu->call; - local_save_flags(irq_flags); - pc = preempt_count(); - - size = sizeof(*entry) + tu->size; - + size = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); event = trace_current_buffer_lock_reserve(&buffer, call->event.type, - size, irq_flags, pc); + size + tu->size, 0, 0); if (!event) - return 0; + return; entry = ring_buffer_event_data(event); - entry->ip = instruction_pointer(task_pt_regs(current)); - data = (u8 *)&entry[1]; + if (is_ret_probe(tu)) { + entry->vaddr[0] = func; + entry->vaddr[1] = instruction_pointer(regs); + data = DATAOF_TRACE_ENTRY(entry, true); + } else { + entry->vaddr[0] = instruction_pointer(regs); + data = DATAOF_TRACE_ENTRY(entry, false); + } + for (i = 0; i < tu->nr_args; i++) call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset); if (!filter_current_check_discard(buffer, call, entry, event)) - trace_buffer_unlock_commit(buffer, event, irq_flags, pc); + trace_buffer_unlock_commit(buffer, event, 0, 0); +} +/* uprobe handler */ +static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs) +{ + if (!is_ret_probe(tu)) + uprobe_trace_print(tu, 0, regs); return 0; } +static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func, + struct pt_regs *regs) +{ + uprobe_trace_print(tu, func, regs); +} + /* Event entry printers */ static enum print_line_t print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *event) { - struct uprobe_trace_entry_head *field; + struct uprobe_trace_entry_head *entry; struct trace_seq *s = &iter->seq; struct trace_uprobe *tu; u8 *data; int i; - field = (struct uprobe_trace_entry_head *)iter->ent; + entry = (struct uprobe_trace_entry_head *)iter->ent; tu = container_of(event, struct trace_uprobe, call.event); - if (!trace_seq_printf(s, "%s: (", tu->call.name)) - goto partial; + if (is_ret_probe(tu)) { + if (!trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)", tu->call.name, + entry->vaddr[1], entry->vaddr[0])) + goto partial; + data = DATAOF_TRACE_ENTRY(entry, true); + } else { + if (!trace_seq_printf(s, "%s: (0x%lx)", tu->call.name, + entry->vaddr[0])) + goto partial; + data = DATAOF_TRACE_ENTRY(entry, false); + } - if (!seq_print_ip_sym(s, field->ip, flags | TRACE_ITER_SYM_OFFSET)) - goto partial; - - if (!trace_seq_puts(s, ")")) - goto partial; - - data = (u8 *)&field[1]; for (i = 0; i < tu->nr_args; i++) { if (!tu->args[i].type->print(s, tu->args[i].name, - data + tu->args[i].offset, field)) + data + tu->args[i].offset, entry)) goto partial; } @@ -595,16 +636,23 @@ static void probe_event_disable(struct trace_uprobe *tu, int flag) static int uprobe_event_define_fields(struct ftrace_event_call *event_call) { - int ret, i; + int ret, i, size; struct uprobe_trace_entry_head field; - struct trace_uprobe *tu = (struct trace_uprobe *)event_call->data; + struct trace_uprobe *tu = event_call->data; - DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0); + if (is_ret_probe(tu)) { + DEFINE_FIELD(unsigned long, vaddr[0], FIELD_STRING_FUNC, 0); + DEFINE_FIELD(unsigned long, vaddr[1], FIELD_STRING_RETIP, 0); + size = SIZEOF_TRACE_ENTRY(true); + } else { + DEFINE_FIELD(unsigned long, vaddr[0], FIELD_STRING_IP, 0); + size = SIZEOF_TRACE_ENTRY(false); + } /* Set argument names as fields */ for (i = 0; i < tu->nr_args; i++) { ret = trace_define_field(event_call, tu->args[i].type->fmttype, tu->args[i].name, - sizeof(field) + tu->args[i].offset, + size + tu->args[i].offset, tu->args[i].type->size, tu->args[i].type->is_signed, FILTER_OTHER); @@ -622,8 +670,13 @@ static int __set_print_fmt(struct trace_uprobe *tu, char *buf, int len) int i; int pos = 0; - fmt = "(%lx)"; - arg = "REC->" FIELD_STRING_IP; + if (is_ret_probe(tu)) { + fmt = "(%lx <- %lx)"; + arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP; + } else { + fmt = "(%lx)"; + arg = "REC->" FIELD_STRING_IP; + } /* When len=0, we just calculate the needed length */ @@ -752,49 +805,68 @@ static bool uprobe_perf_filter(struct uprobe_consumer *uc, return ret; } -/* uprobe profile handler */ -static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs) +static void uprobe_perf_print(struct trace_uprobe *tu, + unsigned long func, struct pt_regs *regs) { struct ftrace_event_call *call = &tu->call; struct uprobe_trace_entry_head *entry; struct hlist_head *head; - u8 *data; - int size, __size, i; - int rctx; + void *data; + int size, rctx, i; - if (!uprobe_perf_filter(&tu->consumer, 0, current->mm)) - return UPROBE_HANDLER_REMOVE; - - __size = sizeof(*entry) + tu->size; - size = ALIGN(__size + sizeof(u32), sizeof(u64)); - size -= sizeof(u32); + size = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); + size = ALIGN(size + tu->size + sizeof(u32), sizeof(u64)) - sizeof(u32); if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough")) - return 0; + return; preempt_disable(); + head = this_cpu_ptr(call->perf_events); + if (hlist_empty(head)) + goto out; entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx); if (!entry) goto out; - entry->ip = instruction_pointer(task_pt_regs(current)); - data = (u8 *)&entry[1]; + if (is_ret_probe(tu)) { + entry->vaddr[0] = func; + entry->vaddr[1] = instruction_pointer(regs); + data = DATAOF_TRACE_ENTRY(entry, true); + } else { + entry->vaddr[0] = instruction_pointer(regs); + data = DATAOF_TRACE_ENTRY(entry, false); + } + for (i = 0; i < tu->nr_args; i++) call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset); - head = this_cpu_ptr(call->perf_events); - perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head, NULL); - + perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL); out: preempt_enable(); +} + +/* uprobe profile handler */ +static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs) +{ + if (!uprobe_perf_filter(&tu->consumer, 0, current->mm)) + return UPROBE_HANDLER_REMOVE; + + if (!is_ret_probe(tu)) + uprobe_perf_print(tu, 0, regs); return 0; } + +static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func, + struct pt_regs *regs) +{ + uprobe_perf_print(tu, func, regs); +} #endif /* CONFIG_PERF_EVENTS */ static int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type, void *data) { - struct trace_uprobe *tu = (struct trace_uprobe *)event->data; + struct trace_uprobe *tu = event->data; switch (type) { case TRACE_REG_REGISTER: @@ -843,6 +915,23 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) return ret; } +static int uretprobe_dispatcher(struct uprobe_consumer *con, + unsigned long func, struct pt_regs *regs) +{ + struct trace_uprobe *tu; + + tu = container_of(con, struct trace_uprobe, consumer); + + if (tu->flags & TP_FLAG_TRACE) + uretprobe_trace_func(tu, func, regs); + +#ifdef CONFIG_PERF_EVENTS + if (tu->flags & TP_FLAG_PROFILE) + uretprobe_perf_func(tu, func, regs); +#endif + return 0; +} + static struct trace_event_functions uprobe_funcs = { .trace = print_uprobe_event };