From 2b144498350860b6ee9dc57ff27a93ad488de5dc Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Thu, 9 Feb 2012 14:56:42 +0530 Subject: uprobes, mm, x86: Add the ability to install and remove uprobes breakpoints Add uprobes support to the core kernel, with x86 support. This commit adds the kernel facilities, the actual uprobes user-space ABI and perf probe support comes in later commits. General design: Uprobes are maintained in an rb-tree indexed by inode and offset (the offset here is from the start of the mapping). For a unique (inode, offset) tuple, there can be at most one uprobe in the rb-tree. Since the (inode, offset) tuple identifies a unique uprobe, more than one user may be interested in the same uprobe. This provides the ability to connect multiple 'consumers' to the same uprobe. Each consumer defines a handler and a filter (optional). The 'handler' is run every time the uprobe is hit, if it matches the 'filter' criteria. The first consumer of a uprobe causes the breakpoint to be inserted at the specified address and subsequent consumers are appended to this list. On subsequent probes, the consumer gets appended to the existing list of consumers. The breakpoint is removed when the last consumer unregisters. For all other unregisterations, the consumer is removed from the list of consumers. Given a inode, we get a list of the mms that have mapped the inode. Do the actual registration if mm maps the page where a probe needs to be inserted/removed. We use a temporary list to walk through the vmas that map the inode. - The number of maps that map the inode, is not known before we walk the rmap and keeps changing. - extending vm_area_struct wasn't recommended, it's a size-critical data structure. - There can be more than one maps of the inode in the same mm. We add callbacks to the mmap methods to keep an eye on text vmas that are of interest to uprobes. When a vma of interest is mapped, we insert the breakpoint at the right address. Uprobe works by replacing the instruction at the address defined by (inode, offset) with the arch specific breakpoint instruction. We save a copy of the original instruction at the uprobed address. This is needed for: a. executing the instruction out-of-line (xol). b. instruction analysis for any subsequent fixups. c. restoring the instruction back when the uprobe is unregistered. We insert or delete a breakpoint instruction, and this breakpoint instruction is assumed to be the smallest instruction available on the platform. For fixed size instruction platforms this is trivially true, for variable size instruction platforms the breakpoint instruction is typically the smallest (often a single byte). Writing the instruction is done by COWing the page and changing the instruction during the copy, this even though most platforms allow atomic writes of the breakpoint instruction. This also mirrors the behaviour of a ptrace() memory write to a PRIVATE file map. The core worker is derived from KSM's replace_page() logic. In essence, similar to KSM: a. allocate a new page and copy over contents of the page that has the uprobed vaddr b. modify the copy and insert the breakpoint at the required address c. switch the original page with the copy containing the breakpoint d. flush page tables. replace_page() is being replicated here because of some minor changes in the type of pages and also because Hugh Dickins had plans to improve replace_page() for KSM specific work. Instruction analysis on x86 is based on instruction decoder and determines if an instruction can be probed and determines the necessary fixups after singlestep. Instruction analysis is done at probe insertion time so that we avoid having to repeat the same analysis every time a probe is hit. A lot of code here is due to the improvement/suggestions/inputs from Peter Zijlstra. Changelog: (v10): - Add code to clear REX.B prefix as suggested by Denys Vlasenko and Masami Hiramatsu. (v9): - Use insn_offset_modrm as suggested by Masami Hiramatsu. (v7): Handle comments from Peter Zijlstra: - Dont take reference to inode. (expect inode to uprobe_register to be sane). - Use PTR_ERR to set the return value. - No need to take reference to inode. - use PTR_ERR to return error value. - register and uprobe_unregister share code. (v5): - Modified del_consumer as per comments from Peter. - Drop reference to inode before dropping reference to uprobe. - Use i_size_read(inode) instead of inode->i_size. - Ensure uprobe->consumers is NULL, before __uprobe_unregister() is called. - Includes errno.h as recommended by Stephen Rothwell to fix a build issue on sparc defconfig - Remove restrictions while unregistering. - Earlier code leaked inode references under some conditions while registering/unregistering. - Continue the vma-rmap walk even if the intermediate vma doesnt meet the requirements. - Validate the vma found by find_vma before inserting/removing the breakpoint - Call del_consumer under mutex_lock. - Use hash locks. - Handle mremap. - Introduce find_least_offset_node() instead of close match logic in find_uprobe - Uprobes no more depends on MM_OWNER; No reference to task_structs while inserting/removing a probe. - Uses read_mapping_page instead of grab_cache_page so that the pages have valid content. - pass NULL to get_user_pages for the task parameter. - call SetPageUptodate on the new page allocated in write_opcode. - fix leaking a reference to the new page under certain conditions. - Include Instruction Decoder if Uprobes gets defined. - Remove const attributes for instruction prefix arrays. - Uses mm_context to know if the application is 32 bit. Signed-off-by: Srikar Dronamraju Also-written-by: Jim Keniston Reviewed-by: Peter Zijlstra Cc: Oleg Nesterov Cc: Andi Kleen Cc: Christoph Hellwig Cc: Steven Rostedt Cc: Roland McGrath Cc: Masami Hiramatsu Cc: Arnaldo Carvalho de Melo Cc: Anton Arapov Cc: Ananth N Mavinakayanahalli Cc: Stephen Rothwell Cc: Denys Vlasenko Cc: Peter Zijlstra Cc: Linus Torvalds Cc: Andrew Morton Cc: Linux-mm Link: http://lkml.kernel.org/r/20120209092642.GE16600@linux.vnet.ibm.com [ Made various small edits to the commit log ] Signed-off-by: Ingo Molnar --- arch/Kconfig | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'arch/Kconfig') diff --git a/arch/Kconfig b/arch/Kconfig index 4f55c736be1..284f5898f52 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -65,6 +65,17 @@ config OPTPROBES depends on KPROBES && HAVE_OPTPROBES depends on !PREEMPT +config UPROBES + bool "User-space probes (EXPERIMENTAL)" + depends on ARCH_SUPPORTS_UPROBES + default n + help + Uprobes enables kernel subsystems to establish probepoints + in user applications and execute handler functions when + the probepoints are hit. + + If in doubt, say "N". + config HAVE_EFFICIENT_UNALIGNED_ACCESS bool help -- cgit v1.2.3-70-g09d2 From 7b2d81d48a2d8e37efb6ce7b4d5ef58822b30d89 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 17 Feb 2012 09:27:41 +0100 Subject: uprobes/core: Clean up, refactor and improve the code Make the uprobes code readable to me: - improve the Kconfig text so that a mere mortal gets some idea what CONFIG_UPROBES=y is really about - do trivial renames to standardize around the uprobes_*() namespace - clean up and simplify various code flow details - separate basic blocks of functionality - line break artifact and white space related removal - use standard local varible definition blocks - use vertical spacing to make things more readable - remove unnecessary volatile - restructure comment blocks to make them more uniform and more readable in general Cc: Srikar Dronamraju Cc: Jim Keniston Cc: Peter Zijlstra Cc: Oleg Nesterov Cc: Masami Hiramatsu Cc: Arnaldo Carvalho de Melo Cc: Anton Arapov Cc: Ananth N Mavinakayanahalli Link: http://lkml.kernel.org/n/tip-ewbwhb8o6navvllsauu7k07p@git.kernel.org Signed-off-by: Ingo Molnar --- arch/Kconfig | 14 ++- arch/x86/include/asm/uprobes.h | 17 ++-- arch/x86/kernel/uprobes.c | 129 ++++++++++++------------ include/linux/uprobes.h | 28 +++--- kernel/uprobes.c | 219 ++++++++++++++++++++++++----------------- mm/mmap.c | 12 +-- 6 files changed, 233 insertions(+), 186 deletions(-) (limited to 'arch/Kconfig') diff --git a/arch/Kconfig b/arch/Kconfig index 284f5898f52..cca5b545d80 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -66,13 +66,19 @@ config OPTPROBES depends on !PREEMPT config UPROBES - bool "User-space probes (EXPERIMENTAL)" + bool "Transparent user-space probes (EXPERIMENTAL)" depends on ARCH_SUPPORTS_UPROBES default n help - Uprobes enables kernel subsystems to establish probepoints - in user applications and execute handler functions when - the probepoints are hit. + Uprobes is the user-space counterpart to kprobes: they + enable instrumentation applications (such as 'perf probe') + to establish unintrusive probes in user-space binaries and + libraries, by executing handler functions when the probes + are hit by user-space applications. + + ( These probes come in the form of single-byte breakpoints, + managed by the kernel and kept transparent to the probed + application. ) If in doubt, say "N". diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h index 8208234391f..072df390263 100644 --- a/arch/x86/include/asm/uprobes.h +++ b/arch/x86/include/asm/uprobes.h @@ -1,7 +1,7 @@ #ifndef _ASM_UPROBES_H #define _ASM_UPROBES_H /* - * Userspace Probes (UProbes) for x86 + * User-space Probes (UProbes) for x86 * * 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 @@ -24,19 +24,20 @@ */ typedef u8 uprobe_opcode_t; -#define MAX_UINSN_BYTES 16 -#define UPROBES_XOL_SLOT_BYTES 128 /* to keep it cache aligned */ -#define UPROBES_BKPT_INSN 0xcc -#define UPROBES_BKPT_INSN_SIZE 1 +#define MAX_UINSN_BYTES 16 +#define UPROBES_XOL_SLOT_BYTES 128 /* to keep it cache aligned */ + +#define UPROBES_BKPT_INSN 0xcc +#define UPROBES_BKPT_INSN_SIZE 1 struct uprobe_arch_info { - u16 fixups; + u16 fixups; #ifdef CONFIG_X86_64 - unsigned long rip_rela_target_address; + unsigned long rip_rela_target_address; #endif }; struct uprobe; -extern int analyze_insn(struct mm_struct *mm, struct uprobe *uprobe); +extern int arch_uprobes_analyze_insn(struct mm_struct *mm, struct uprobe *uprobe); #endif /* _ASM_UPROBES_H */ diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 2a301bb91bd..cf2a1849842 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -1,5 +1,5 @@ /* - * Userspace Probes (UProbes) for x86 + * User-space Probes (UProbes) for x86 * * 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 @@ -20,7 +20,6 @@ * Srikar Dronamraju * Jim Keniston */ - #include #include #include @@ -42,10 +41,10 @@ #define UPROBES_FIX_RIP_CX 0x4000 /* Adaptations for mhiramat x86 decoder v14. */ -#define OPCODE1(insn) ((insn)->opcode.bytes[0]) -#define OPCODE2(insn) ((insn)->opcode.bytes[1]) -#define OPCODE3(insn) ((insn)->opcode.bytes[2]) -#define MODRM_REG(insn) X86_MODRM_REG(insn->modrm.value) +#define OPCODE1(insn) ((insn)->opcode.bytes[0]) +#define OPCODE2(insn) ((insn)->opcode.bytes[1]) +#define OPCODE3(insn) ((insn)->opcode.bytes[2]) +#define MODRM_REG(insn) X86_MODRM_REG(insn->modrm.value) #define W(row, b0, b1, b2, b3, b4, b5, b6, b7, b8, b9, ba, bb, bc, bd, be, bf)\ (((b0##UL << 0x0)|(b1##UL << 0x1)|(b2##UL << 0x2)|(b3##UL << 0x3) | \ @@ -55,7 +54,7 @@ << (row % 32)) #ifdef CONFIG_X86_64 -static volatile u32 good_insns_64[256 / 32] = { +static u32 good_insns_64[256 / 32] = { /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ /* ---------------------------------------------- */ W(0x00, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0) | /* 00 */ @@ -81,7 +80,7 @@ static volatile u32 good_insns_64[256 / 32] = { /* Good-instruction tables for 32-bit apps */ -static volatile u32 good_insns_32[256 / 32] = { +static u32 good_insns_32[256 / 32] = { /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ /* ---------------------------------------------- */ W(0x00, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0) | /* 00 */ @@ -105,7 +104,7 @@ static volatile u32 good_insns_32[256 / 32] = { }; /* Using this for both 64-bit and 32-bit apps */ -static volatile u32 good_2byte_insns[256 / 32] = { +static u32 good_2byte_insns[256 / 32] = { /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ /* ---------------------------------------------- */ W(0x00, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1) | /* 00 */ @@ -132,42 +131,47 @@ static volatile u32 good_2byte_insns[256 / 32] = { /* * opcodes we'll probably never support: - * 6c-6d, e4-e5, ec-ed - in - * 6e-6f, e6-e7, ee-ef - out - * cc, cd - int3, int - * cf - iret - * d6 - illegal instruction - * f1 - int1/icebp - * f4 - hlt - * fa, fb - cli, sti - * 0f - lar, lsl, syscall, clts, sysret, sysenter, sysexit, invd, wbinvd, ud2 + * + * 6c-6d, e4-e5, ec-ed - in + * 6e-6f, e6-e7, ee-ef - out + * cc, cd - int3, int + * cf - iret + * d6 - illegal instruction + * f1 - int1/icebp + * f4 - hlt + * fa, fb - cli, sti + * 0f - lar, lsl, syscall, clts, sysret, sysenter, sysexit, invd, wbinvd, ud2 * * invalid opcodes in 64-bit mode: - * 06, 0e, 16, 1e, 27, 2f, 37, 3f, 60-62, 82, c4-c5, d4-d5 * - * 63 - we support this opcode in x86_64 but not in i386. + * 06, 0e, 16, 1e, 27, 2f, 37, 3f, 60-62, 82, c4-c5, d4-d5 + * 63 - we support this opcode in x86_64 but not in i386. * * opcodes we may need to refine support for: - * 0f - 2-byte instructions: For many of these instructions, the validity - * depends on the prefix and/or the reg field. On such instructions, we - * just consider the opcode combination valid if it corresponds to any - * valid instruction. - * 8f - Group 1 - only reg = 0 is OK - * c6-c7 - Group 11 - only reg = 0 is OK - * d9-df - fpu insns with some illegal encodings - * f2, f3 - repnz, repz prefixes. These are also the first byte for - * certain floating-point instructions, such as addsd. - * fe - Group 4 - only reg = 0 or 1 is OK - * ff - Group 5 - only reg = 0-6 is OK + * + * 0f - 2-byte instructions: For many of these instructions, the validity + * depends on the prefix and/or the reg field. On such instructions, we + * just consider the opcode combination valid if it corresponds to any + * valid instruction. + * + * 8f - Group 1 - only reg = 0 is OK + * c6-c7 - Group 11 - only reg = 0 is OK + * d9-df - fpu insns with some illegal encodings + * f2, f3 - repnz, repz prefixes. These are also the first byte for + * certain floating-point instructions, such as addsd. + * + * fe - Group 4 - only reg = 0 or 1 is OK + * ff - Group 5 - only reg = 0-6 is OK * * others -- Do we need to support these? - * 0f - (floating-point?) prefetch instructions - * 07, 17, 1f - pop es, pop ss, pop ds - * 26, 2e, 36, 3e - es:, cs:, ss:, ds: segment prefixes -- + * + * 0f - (floating-point?) prefetch instructions + * 07, 17, 1f - pop es, pop ss, pop ds + * 26, 2e, 36, 3e - es:, cs:, ss:, ds: segment prefixes -- * but 64 and 65 (fs: and gs:) seem to be used, so we support them - * 67 - addr16 prefix - * ce - into - * f0 - lock prefix + * 67 - addr16 prefix + * ce - into + * f0 - lock prefix */ /* @@ -182,11 +186,11 @@ static bool is_prefix_bad(struct insn *insn) for (i = 0; i < insn->prefixes.nbytes; i++) { switch (insn->prefixes.bytes[i]) { - case 0x26: /*INAT_PFX_ES */ - case 0x2E: /*INAT_PFX_CS */ - case 0x36: /*INAT_PFX_DS */ - case 0x3E: /*INAT_PFX_SS */ - case 0xF0: /*INAT_PFX_LOCK */ + case 0x26: /* INAT_PFX_ES */ + case 0x2E: /* INAT_PFX_CS */ + case 0x36: /* INAT_PFX_DS */ + case 0x3E: /* INAT_PFX_SS */ + case 0xF0: /* INAT_PFX_LOCK */ return true; } } @@ -201,12 +205,15 @@ static int validate_insn_32bits(struct uprobe *uprobe, struct insn *insn) insn_get_opcode(insn); if (is_prefix_bad(insn)) return -ENOTSUPP; + if (test_bit(OPCODE1(insn), (unsigned long *)good_insns_32)) return 0; + if (insn->opcode.nbytes == 2) { if (test_bit(OPCODE2(insn), (unsigned long *)good_2byte_insns)) return 0; } + return -ENOTSUPP; } @@ -282,12 +289,12 @@ static void prepare_fixups(struct uprobe *uprobe, struct insn *insn) * disastrous. * * Some useful facts about rip-relative instructions: - * - There's always a modrm byte. - * - There's never a SIB byte. - * - The displacement is always 4 bytes. + * + * - There's always a modrm byte. + * - There's never a SIB byte. + * - The displacement is always 4 bytes. */ -static void handle_riprel_insn(struct mm_struct *mm, struct uprobe *uprobe, - struct insn *insn) +static void handle_riprel_insn(struct mm_struct *mm, struct uprobe *uprobe, struct insn *insn) { u8 *cursor; u8 reg; @@ -342,13 +349,12 @@ static void handle_riprel_insn(struct mm_struct *mm, struct uprobe *uprobe, } /* Target address = address of next instruction + (signed) offset */ - uprobe->arch_info.rip_rela_target_address = (long)insn->length - + insn->displacement.value; + uprobe->arch_info.rip_rela_target_address = (long)insn->length + insn->displacement.value; + /* Displacement field is gone; slide immediate field (if any) over. */ if (insn->immediate.nbytes) { cursor++; - memmove(cursor, cursor + insn->displacement.nbytes, - insn->immediate.nbytes); + memmove(cursor, cursor + insn->displacement.nbytes, insn->immediate.nbytes); } return; } @@ -361,8 +367,10 @@ static int validate_insn_64bits(struct uprobe *uprobe, struct insn *insn) insn_get_opcode(insn); if (is_prefix_bad(insn)) return -ENOTSUPP; + if (test_bit(OPCODE1(insn), (unsigned long *)good_insns_64)) return 0; + if (insn->opcode.nbytes == 2) { if (test_bit(OPCODE2(insn), (unsigned long *)good_2byte_insns)) return 0; @@ -370,34 +378,31 @@ static int validate_insn_64bits(struct uprobe *uprobe, struct insn *insn) return -ENOTSUPP; } -static int validate_insn_bits(struct mm_struct *mm, struct uprobe *uprobe, - struct insn *insn) +static int validate_insn_bits(struct mm_struct *mm, struct uprobe *uprobe, struct insn *insn) { if (mm->context.ia32_compat) return validate_insn_32bits(uprobe, insn); return validate_insn_64bits(uprobe, insn); } -#else -static void handle_riprel_insn(struct mm_struct *mm, struct uprobe *uprobe, - struct insn *insn) +#else /* 32-bit: */ +static void handle_riprel_insn(struct mm_struct *mm, struct uprobe *uprobe, struct insn *insn) { - return; + /* No RIP-relative addressing on 32-bit */ } -static int validate_insn_bits(struct mm_struct *mm, struct uprobe *uprobe, - struct insn *insn) +static int validate_insn_bits(struct mm_struct *mm, struct uprobe *uprobe, struct insn *insn) { return validate_insn_32bits(uprobe, insn); } #endif /* CONFIG_X86_64 */ /** - * analyze_insn - instruction analysis including validity and fixups. + * arch_uprobes_analyze_insn - instruction analysis including validity and fixups. * @mm: the probed address space. * @uprobe: the probepoint information. * Return 0 on success or a -ve number on error. */ -int analyze_insn(struct mm_struct *mm, struct uprobe *uprobe) +int arch_uprobes_analyze_insn(struct mm_struct *mm, struct uprobe *uprobe) { int ret; struct insn insn; @@ -406,7 +411,9 @@ int analyze_insn(struct mm_struct *mm, struct uprobe *uprobe) ret = validate_insn_bits(mm, uprobe, &insn); if (ret != 0) return ret; + handle_riprel_insn(mm, uprobe, &insn); prepare_fixups(uprobe, &insn); + return 0; } diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index f1d13fd140f..64e45f116b2 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -1,7 +1,7 @@ #ifndef _LINUX_UPROBES_H #define _LINUX_UPROBES_H /* - * Userspace Probes (UProbes) + * User-space Probes (UProbes) * * 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 @@ -40,8 +40,10 @@ struct uprobe_arch_info {}; #define uprobe_opcode_sz sizeof(uprobe_opcode_t) /* flags that denote/change uprobes behaviour */ + /* Have a copy of original instruction */ #define UPROBES_COPY_INSN 0x1 + /* Dont run handlers when first register/ last unregister in progress*/ #define UPROBES_RUN_HANDLER 0x2 @@ -70,27 +72,23 @@ struct uprobe { }; #ifdef CONFIG_UPROBES -extern int __weak set_bkpt(struct mm_struct *mm, struct uprobe *uprobe, - unsigned long vaddr); -extern int __weak set_orig_insn(struct mm_struct *mm, struct uprobe *uprobe, - unsigned long vaddr, bool verify); +extern int __weak set_bkpt(struct mm_struct *mm, struct uprobe *uprobe, unsigned long vaddr); +extern int __weak set_orig_insn(struct mm_struct *mm, struct uprobe *uprobe, unsigned long vaddr, bool verify); extern bool __weak is_bkpt_insn(uprobe_opcode_t *insn); -extern int register_uprobe(struct inode *inode, loff_t offset, - struct uprobe_consumer *consumer); -extern void unregister_uprobe(struct inode *inode, loff_t offset, - struct uprobe_consumer *consumer); -extern int mmap_uprobe(struct vm_area_struct *vma); +extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *consumer); +extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *consumer); +extern int uprobe_mmap(struct vm_area_struct *vma); #else /* CONFIG_UPROBES is not defined */ -static inline int register_uprobe(struct inode *inode, loff_t offset, - struct uprobe_consumer *consumer) +static inline int +uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *consumer) { return -ENOSYS; } -static inline void unregister_uprobe(struct inode *inode, loff_t offset, - struct uprobe_consumer *consumer) +static inline void +uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *consumer) { } -static inline int mmap_uprobe(struct vm_area_struct *vma) +static inline int uprobe_mmap(struct vm_area_struct *vma) { return 0; } diff --git a/kernel/uprobes.c b/kernel/uprobes.c index 72e8bb3b52c..884817f1b0d 100644 --- a/kernel/uprobes.c +++ b/kernel/uprobes.c @@ -1,5 +1,5 @@ /* - * Userspace Probes (UProbes) + * User-space Probes (UProbes) * * 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 @@ -29,24 +29,26 @@ #include /* anon_vma_prepare */ #include /* set_pte_at_notify */ #include /* try_to_free_swap */ + #include static struct rb_root uprobes_tree = RB_ROOT; + static DEFINE_SPINLOCK(uprobes_treelock); /* serialize rbtree access */ #define UPROBES_HASH_SZ 13 + /* serialize (un)register */ static struct mutex uprobes_mutex[UPROBES_HASH_SZ]; -#define uprobes_hash(v) (&uprobes_mutex[((unsigned long)(v)) %\ - UPROBES_HASH_SZ]) + +#define uprobes_hash(v) (&uprobes_mutex[((unsigned long)(v)) % UPROBES_HASH_SZ]) /* serialize uprobe->pending_list */ static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ]; -#define uprobes_mmap_hash(v) (&uprobes_mmap_mutex[((unsigned long)(v)) %\ - UPROBES_HASH_SZ]) +#define uprobes_mmap_hash(v) (&uprobes_mmap_mutex[((unsigned long)(v)) % UPROBES_HASH_SZ]) /* - * uprobe_events allows us to skip the mmap_uprobe if there are no uprobe + * uprobe_events allows us to skip the uprobe_mmap if there are no uprobe * events active at this time. Probably a fine grained per inode count is * better? */ @@ -58,9 +60,9 @@ static atomic_t uprobe_events = ATOMIC_INIT(0); * vm_area_struct wasnt recommended. */ struct vma_info { - struct list_head probe_list; - struct mm_struct *mm; - loff_t vaddr; + struct list_head probe_list; + struct mm_struct *mm; + loff_t vaddr; }; /* @@ -79,8 +81,7 @@ static bool valid_vma(struct vm_area_struct *vma, bool is_register) if (!is_register) return true; - if ((vma->vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)) == - (VM_READ|VM_EXEC)) + if ((vma->vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)) == (VM_READ|VM_EXEC)) return true; return false; @@ -92,6 +93,7 @@ static loff_t vma_address(struct vm_area_struct *vma, loff_t offset) vaddr = vma->vm_start + offset; vaddr -= vma->vm_pgoff << PAGE_SHIFT; + return vaddr; } @@ -105,8 +107,7 @@ static loff_t vma_address(struct vm_area_struct *vma, loff_t offset) * * Returns 0 on success, -EFAULT on failure. */ -static int __replace_page(struct vm_area_struct *vma, struct page *page, - struct page *kpage) +static int __replace_page(struct vm_area_struct *vma, struct page *page, struct page *kpage) { struct mm_struct *mm = vma->vm_mm; pgd_t *pgd; @@ -163,7 +164,7 @@ out: */ bool __weak is_bkpt_insn(uprobe_opcode_t *insn) { - return (*insn == UPROBES_BKPT_INSN); + return *insn == UPROBES_BKPT_INSN; } /* @@ -203,6 +204,7 @@ static int write_opcode(struct mm_struct *mm, struct uprobe *uprobe, ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &old_page, &vma); if (ret <= 0) return ret; + ret = -EINVAL; /* @@ -239,6 +241,7 @@ static int write_opcode(struct mm_struct *mm, struct uprobe *uprobe, vaddr_new = kmap_atomic(new_page); memcpy(vaddr_new, vaddr_old, PAGE_SIZE); + /* poke the new insn in, ASSUMES we don't cross page boundary */ vaddr &= ~PAGE_MASK; BUG_ON(vaddr + uprobe_opcode_sz > PAGE_SIZE); @@ -260,7 +263,8 @@ unlock_out: page_cache_release(new_page); put_out: - put_page(old_page); /* we did a get_page in the beginning */ + put_page(old_page); + return ret; } @@ -276,8 +280,7 @@ put_out: * For mm @mm, read the opcode at @vaddr and store it in @opcode. * Return 0 (success) or a negative errno. */ -static int read_opcode(struct mm_struct *mm, unsigned long vaddr, - uprobe_opcode_t *opcode) +static int read_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t *opcode) { struct page *page; void *vaddr_new; @@ -293,15 +296,18 @@ static int read_opcode(struct mm_struct *mm, unsigned long vaddr, memcpy(opcode, vaddr_new + vaddr, uprobe_opcode_sz); kunmap_atomic(vaddr_new); unlock_page(page); - put_page(page); /* we did a get_user_pages in the beginning */ + + put_page(page); + return 0; } static int is_bkpt_at_addr(struct mm_struct *mm, unsigned long vaddr) { uprobe_opcode_t opcode; - int result = read_opcode(mm, vaddr, &opcode); + int result; + result = read_opcode(mm, vaddr, &opcode); if (result) return result; @@ -320,11 +326,11 @@ static int is_bkpt_at_addr(struct mm_struct *mm, unsigned long vaddr) * For mm @mm, store the breakpoint instruction at @vaddr. * Return 0 (success) or a negative errno. */ -int __weak set_bkpt(struct mm_struct *mm, struct uprobe *uprobe, - unsigned long vaddr) +int __weak set_bkpt(struct mm_struct *mm, struct uprobe *uprobe, unsigned long vaddr) { - int result = is_bkpt_at_addr(mm, vaddr); + int result; + result = is_bkpt_at_addr(mm, vaddr); if (result == 1) return -EEXIST; @@ -344,35 +350,35 @@ int __weak set_bkpt(struct mm_struct *mm, struct uprobe *uprobe, * For mm @mm, restore the original opcode (opcode) at @vaddr. * Return 0 (success) or a negative errno. */ -int __weak set_orig_insn(struct mm_struct *mm, struct uprobe *uprobe, - unsigned long vaddr, bool verify) +int __weak +set_orig_insn(struct mm_struct *mm, struct uprobe *uprobe, unsigned long vaddr, bool verify) { if (verify) { - int result = is_bkpt_at_addr(mm, vaddr); + int result; + result = is_bkpt_at_addr(mm, vaddr); if (!result) return -EINVAL; if (result != 1) return result; } - return write_opcode(mm, uprobe, vaddr, - *(uprobe_opcode_t *)uprobe->insn); + return write_opcode(mm, uprobe, vaddr, *(uprobe_opcode_t *)uprobe->insn); } static int match_uprobe(struct uprobe *l, struct uprobe *r) { if (l->inode < r->inode) return -1; + if (l->inode > r->inode) return 1; - else { - if (l->offset < r->offset) - return -1; - if (l->offset > r->offset) - return 1; - } + if (l->offset < r->offset) + return -1; + + if (l->offset > r->offset) + return 1; return 0; } @@ -391,6 +397,7 @@ static struct uprobe *__find_uprobe(struct inode *inode, loff_t offset) atomic_inc(&uprobe->ref); return uprobe; } + if (match < 0) n = n->rb_left; else @@ -411,6 +418,7 @@ static struct uprobe *find_uprobe(struct inode *inode, loff_t offset) spin_lock_irqsave(&uprobes_treelock, flags); uprobe = __find_uprobe(inode, offset); spin_unlock_irqrestore(&uprobes_treelock, flags); + return uprobe; } @@ -436,16 +444,18 @@ static struct uprobe *__insert_uprobe(struct uprobe *uprobe) p = &parent->rb_right; } + u = NULL; rb_link_node(&uprobe->rb_node, parent, p); rb_insert_color(&uprobe->rb_node, &uprobes_tree); /* get access + creation ref */ atomic_set(&uprobe->ref, 2); + return u; } /* - * Acquires uprobes_treelock. + * Acquire uprobes_treelock. * Matching uprobe already exists in rbtree; * increment (access refcount) and return the matching uprobe. * @@ -460,6 +470,7 @@ static struct uprobe *insert_uprobe(struct uprobe *uprobe) spin_lock_irqsave(&uprobes_treelock, flags); u = __insert_uprobe(uprobe); spin_unlock_irqrestore(&uprobes_treelock, flags); + return u; } @@ -490,19 +501,22 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset) kfree(uprobe); uprobe = cur_uprobe; iput(inode); - } else + } else { atomic_inc(&uprobe_events); + } + return uprobe; } /* Returns the previous consumer */ -static struct uprobe_consumer *add_consumer(struct uprobe *uprobe, - struct uprobe_consumer *consumer) +static struct uprobe_consumer * +consumer_add(struct uprobe *uprobe, struct uprobe_consumer *consumer) { down_write(&uprobe->consumer_rwsem); consumer->next = uprobe->consumers; uprobe->consumers = consumer; up_write(&uprobe->consumer_rwsem); + return consumer->next; } @@ -511,8 +525,7 @@ static struct uprobe_consumer *add_consumer(struct uprobe *uprobe, * Return true if the @consumer is deleted successfully * or return false. */ -static bool del_consumer(struct uprobe *uprobe, - struct uprobe_consumer *consumer) +static bool consumer_del(struct uprobe *uprobe, struct uprobe_consumer *consumer) { struct uprobe_consumer **con; bool ret = false; @@ -526,6 +539,7 @@ static bool del_consumer(struct uprobe *uprobe, } } up_write(&uprobe->consumer_rwsem); + return ret; } @@ -557,15 +571,15 @@ static int __copy_insn(struct address_space *mapping, memcpy(insn, vaddr + off1, nbytes); kunmap_atomic(vaddr); page_cache_release(page); + return 0; } -static int copy_insn(struct uprobe *uprobe, struct vm_area_struct *vma, - unsigned long addr) +static int copy_insn(struct uprobe *uprobe, struct vm_area_struct *vma, unsigned long addr) { struct address_space *mapping; - int bytes; unsigned long nbytes; + int bytes; addr &= ~PAGE_MASK; nbytes = PAGE_SIZE - addr; @@ -605,6 +619,7 @@ static int install_breakpoint(struct mm_struct *mm, struct uprobe *uprobe, return -EEXIST; addr = (unsigned long)vaddr; + if (!(uprobe->flags & UPROBES_COPY_INSN)) { ret = copy_insn(uprobe, vma, addr); if (ret) @@ -613,7 +628,7 @@ static int install_breakpoint(struct mm_struct *mm, struct uprobe *uprobe, if (is_bkpt_insn((uprobe_opcode_t *)uprobe->insn)) return -EEXIST; - ret = analyze_insn(mm, uprobe); + ret = arch_uprobes_analyze_insn(mm, uprobe); if (ret) return ret; @@ -624,8 +639,7 @@ static int install_breakpoint(struct mm_struct *mm, struct uprobe *uprobe, return ret; } -static void remove_breakpoint(struct mm_struct *mm, struct uprobe *uprobe, - loff_t vaddr) +static void remove_breakpoint(struct mm_struct *mm, struct uprobe *uprobe, loff_t vaddr) { set_orig_insn(mm, uprobe, (unsigned long)vaddr, true); } @@ -649,9 +663,11 @@ static struct vma_info *__find_next_vma_info(struct list_head *head, struct prio_tree_iter iter; struct vm_area_struct *vma; struct vma_info *tmpvi; - loff_t vaddr; - unsigned long pgoff = offset >> PAGE_SHIFT; + unsigned long pgoff; int existing_vma; + loff_t vaddr; + + pgoff = offset >> PAGE_SHIFT; vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { if (!valid_vma(vma, is_register)) @@ -659,6 +675,7 @@ static struct vma_info *__find_next_vma_info(struct list_head *head, existing_vma = 0; vaddr = vma_address(vma, offset); + list_for_each_entry(tmpvi, head, probe_list) { if (tmpvi->mm == vma->vm_mm && tmpvi->vaddr == vaddr) { existing_vma = 1; @@ -670,14 +687,15 @@ static struct vma_info *__find_next_vma_info(struct list_head *head, * Another vma needs a probe to be installed. However skip * installing the probe if the vma is about to be unlinked. */ - if (!existing_vma && - atomic_inc_not_zero(&vma->vm_mm->mm_users)) { + if (!existing_vma && atomic_inc_not_zero(&vma->vm_mm->mm_users)) { vi->mm = vma->vm_mm; vi->vaddr = vaddr; list_add(&vi->probe_list, head); + return vi; } } + return NULL; } @@ -685,11 +703,12 @@ static struct vma_info *__find_next_vma_info(struct list_head *head, * Iterate in the rmap prio tree and find a vma where a probe has not * yet been inserted. */ -static struct vma_info *find_next_vma_info(struct list_head *head, - loff_t offset, struct address_space *mapping, - bool is_register) +static struct vma_info * +find_next_vma_info(struct list_head *head, loff_t offset, struct address_space *mapping, + bool is_register) { struct vma_info *vi, *retvi; + vi = kzalloc(sizeof(struct vma_info), GFP_KERNEL); if (!vi) return ERR_PTR(-ENOMEM); @@ -700,6 +719,7 @@ static struct vma_info *find_next_vma_info(struct list_head *head, if (!retvi) kfree(vi); + return retvi; } @@ -711,16 +731,23 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register) struct vma_info *vi, *tmpvi; struct mm_struct *mm; loff_t vaddr; - int ret = 0; + int ret; mapping = uprobe->inode->i_mapping; INIT_LIST_HEAD(&try_list); - while ((vi = find_next_vma_info(&try_list, uprobe->offset, - mapping, is_register)) != NULL) { + + ret = 0; + + for (;;) { + vi = find_next_vma_info(&try_list, uprobe->offset, mapping, is_register); + if (!vi) + break; + if (IS_ERR(vi)) { ret = PTR_ERR(vi); break; } + mm = vi->mm; down_read(&mm->mmap_sem); vma = find_vma(mm, (unsigned long)vi->vaddr); @@ -755,19 +782,21 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register) break; } } + list_for_each_entry_safe(vi, tmpvi, &try_list, probe_list) { list_del(&vi->probe_list); kfree(vi); } + return ret; } -static int __register_uprobe(struct uprobe *uprobe) +static int __uprobe_register(struct uprobe *uprobe) { return register_for_each_vma(uprobe, true); } -static void __unregister_uprobe(struct uprobe *uprobe) +static void __uprobe_unregister(struct uprobe *uprobe) { if (!register_for_each_vma(uprobe, false)) delete_uprobe(uprobe); @@ -776,15 +805,15 @@ static void __unregister_uprobe(struct uprobe *uprobe) } /* - * register_uprobe - register a probe + * uprobe_register - register a probe * @inode: the file in which the probe has to be placed. * @offset: offset from the start of the file. * @consumer: information on howto handle the probe.. * - * Apart from the access refcount, register_uprobe() takes a creation + * Apart from the access refcount, uprobe_register() takes a creation * refcount (thro alloc_uprobe) if and only if this @uprobe is getting * inserted into the rbtree (i.e first consumer for a @inode:@offset - * tuple). Creation refcount stops unregister_uprobe from freeing the + * tuple). Creation refcount stops uprobe_unregister from freeing the * @uprobe even before the register operation is complete. Creation * refcount is released when the last @consumer for the @uprobe * unregisters. @@ -792,28 +821,29 @@ static void __unregister_uprobe(struct uprobe *uprobe) * Return errno if it cannot successully install probes * else return 0 (success) */ -int register_uprobe(struct inode *inode, loff_t offset, - struct uprobe_consumer *consumer) +int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *consumer) { struct uprobe *uprobe; - int ret = -EINVAL; + int ret; if (!inode || !consumer || consumer->next) - return ret; + return -EINVAL; if (offset > i_size_read(inode)) - return ret; + return -EINVAL; ret = 0; mutex_lock(uprobes_hash(inode)); uprobe = alloc_uprobe(inode, offset); - if (uprobe && !add_consumer(uprobe, consumer)) { - ret = __register_uprobe(uprobe); + + if (uprobe && !consumer_add(uprobe, consumer)) { + ret = __uprobe_register(uprobe); if (ret) { uprobe->consumers = NULL; - __unregister_uprobe(uprobe); - } else + __uprobe_unregister(uprobe); + } else { uprobe->flags |= UPROBES_RUN_HANDLER; + } } mutex_unlock(uprobes_hash(inode)); @@ -823,15 +853,14 @@ int register_uprobe(struct inode *inode, loff_t offset, } /* - * unregister_uprobe - unregister a already registered probe. + * uprobe_unregister - unregister a already registered probe. * @inode: the file in which the probe has to be removed. * @offset: offset from the start of the file. * @consumer: identify which probe if multiple probes are colocated. */ -void unregister_uprobe(struct inode *inode, loff_t offset, - struct uprobe_consumer *consumer) +void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *consumer) { - struct uprobe *uprobe = NULL; + struct uprobe *uprobe; if (!inode || !consumer) return; @@ -841,15 +870,14 @@ void unregister_uprobe(struct inode *inode, loff_t offset, return; mutex_lock(uprobes_hash(inode)); - if (!del_consumer(uprobe, consumer)) - goto unreg_out; - if (!uprobe->consumers) { - __unregister_uprobe(uprobe); - uprobe->flags &= ~UPROBES_RUN_HANDLER; + if (consumer_del(uprobe, consumer)) { + if (!uprobe->consumers) { + __uprobe_unregister(uprobe); + uprobe->flags &= ~UPROBES_RUN_HANDLER; + } } -unreg_out: mutex_unlock(uprobes_hash(inode)); if (uprobe) put_uprobe(uprobe); @@ -870,6 +898,7 @@ static struct rb_node *find_least_offset_node(struct inode *inode) while (n) { uprobe = rb_entry(n, struct uprobe, rb_node); match = match_uprobe(&u, uprobe); + if (uprobe->inode == inode) close_node = n; @@ -881,6 +910,7 @@ static struct rb_node *find_least_offset_node(struct inode *inode) else n = n->rb_right; } + return close_node; } @@ -890,11 +920,13 @@ static struct rb_node *find_least_offset_node(struct inode *inode) static void build_probe_list(struct inode *inode, struct list_head *head) { struct uprobe *uprobe; - struct rb_node *n; unsigned long flags; + struct rb_node *n; spin_lock_irqsave(&uprobes_treelock, flags); + n = find_least_offset_node(inode); + for (; n; n = rb_next(n)) { uprobe = rb_entry(n, struct uprobe, rb_node); if (uprobe->inode != inode) @@ -903,6 +935,7 @@ static void build_probe_list(struct inode *inode, struct list_head *head) list_add(&uprobe->pending_list, head); atomic_inc(&uprobe->ref); } + spin_unlock_irqrestore(&uprobes_treelock, flags); } @@ -912,42 +945,44 @@ static void build_probe_list(struct inode *inode, struct list_head *head) * * Return -ve no if we fail to insert probes and we cannot * bail-out. - * Return 0 otherwise. i.e : + * Return 0 otherwise. i.e: + * * - successful insertion of probes * - (or) no possible probes to be inserted. * - (or) insertion of probes failed but we can bail-out. */ -int mmap_uprobe(struct vm_area_struct *vma) +int uprobe_mmap(struct vm_area_struct *vma) { struct list_head tmp_list; struct uprobe *uprobe, *u; struct inode *inode; - int ret = 0; + int ret; if (!atomic_read(&uprobe_events) || !valid_vma(vma, true)) - return ret; /* Bail-out */ + return 0; inode = vma->vm_file->f_mapping->host; if (!inode) - return ret; + return 0; INIT_LIST_HEAD(&tmp_list); mutex_lock(uprobes_mmap_hash(inode)); build_probe_list(inode, &tmp_list); + + ret = 0; + list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) { loff_t vaddr; list_del(&uprobe->pending_list); if (!ret) { vaddr = vma_address(vma, uprobe->offset); - if (vaddr < vma->vm_start || vaddr >= vma->vm_end) { - put_uprobe(uprobe); - continue; + if (vaddr >= vma->vm_start && vaddr < vma->vm_end) { + ret = install_breakpoint(vma->vm_mm, uprobe, vma, vaddr); + /* Ignore double add: */ + if (ret == -EEXIST) + ret = 0; } - ret = install_breakpoint(vma->vm_mm, uprobe, vma, - vaddr); - if (ret == -EEXIST) - ret = 0; } put_uprobe(uprobe); } diff --git a/mm/mmap.c b/mm/mmap.c index 1aed183636d..5a863d328a4 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -618,10 +618,10 @@ again: remove_next = 1 + (end > next->vm_end); mutex_unlock(&mapping->i_mmap_mutex); if (root) { - mmap_uprobe(vma); + uprobe_mmap(vma); if (adjust_next) - mmap_uprobe(next); + uprobe_mmap(next); } if (remove_next) { @@ -646,7 +646,7 @@ again: remove_next = 1 + (end > next->vm_end); } } if (insert && file) - mmap_uprobe(insert); + uprobe_mmap(insert); validate_mm(mm); @@ -1340,7 +1340,7 @@ out: } else if ((flags & MAP_POPULATE) && !(flags & MAP_NONBLOCK)) make_pages_present(addr, addr + len); - if (file && mmap_uprobe(vma)) + if (file && uprobe_mmap(vma)) /* matching probes but cannot insert */ goto unmap_and_free_vma; @@ -2301,7 +2301,7 @@ int insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma) security_vm_enough_memory_mm(mm, vma_pages(vma))) return -ENOMEM; - if (vma->vm_file && mmap_uprobe(vma)) + if (vma->vm_file && uprobe_mmap(vma)) return -EINVAL; vma_link(mm, vma, prev, rb_link, rb_parent); @@ -2374,7 +2374,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, if (new_vma->vm_file) { get_file(new_vma->vm_file); - if (mmap_uprobe(new_vma)) + if (uprobe_mmap(new_vma)) goto out_free_mempol; if (vma->vm_flags & VM_EXECUTABLE) -- cgit v1.2.3-70-g09d2 From a5f4374a9610fd7286c2164d4e680436727eff71 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 22 Feb 2012 11:01:49 +0100 Subject: uprobes: Move to kernel/events/ Consolidate the uprobes code under kernel/events/, where the various core kernel event handling routines live. Acked-by: Peter Zijlstra Cc: Srikar Dronamraju Cc: Jim Keniston Cc: Oleg Nesterov Cc: Masami Hiramatsu Cc: Arnaldo Carvalho de Melo Cc: Anton Arapov Cc: Ananth N Mavinakayanahalli Link: http://lkml.kernel.org/n/tip-biuyhhwohxgbp2vzbap5yr8o@git.kernel.org Signed-off-by: Ingo Molnar --- arch/Kconfig | 2 +- kernel/Makefile | 1 - kernel/events/Makefile | 3 + kernel/events/uprobes.c | 1011 +++++++++++++++++++++++++++++++++++++++++++++++ kernel/uprobes.c | 1011 ----------------------------------------------- 5 files changed, 1015 insertions(+), 1013 deletions(-) create mode 100644 kernel/events/uprobes.c delete mode 100644 kernel/uprobes.c (limited to 'arch/Kconfig') diff --git a/arch/Kconfig b/arch/Kconfig index cca5b545d80..d0e37c9d5f6 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -67,7 +67,7 @@ config OPTPROBES config UPROBES bool "Transparent user-space probes (EXPERIMENTAL)" - depends on ARCH_SUPPORTS_UPROBES + depends on ARCH_SUPPORTS_UPROBES && PERF_EVENTS default n help Uprobes is the user-space counterpart to kprobes: they diff --git a/kernel/Makefile b/kernel/Makefile index 8609dd3d875..2d9de86b7e7 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -107,7 +107,6 @@ obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o obj-$(CONFIG_PADATA) += padata.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o -obj-$(CONFIG_UPROBES) += uprobes.o $(obj)/configs.o: $(obj)/config_data.h diff --git a/kernel/events/Makefile b/kernel/events/Makefile index 22d901f9caf..103f5d147b2 100644 --- a/kernel/events/Makefile +++ b/kernel/events/Makefile @@ -3,4 +3,7 @@ CFLAGS_REMOVE_core.o = -pg endif obj-y := core.o ring_buffer.o callchain.o + obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o +obj-$(CONFIG_UPROBES) += uprobes.o + diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c new file mode 100644 index 00000000000..884817f1b0d --- /dev/null +++ b/kernel/events/uprobes.c @@ -0,0 +1,1011 @@ +/* + * User-space Probes (UProbes) + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2008-2011 + * Authors: + * Srikar Dronamraju + * Jim Keniston + */ + +#include +#include +#include /* read_mapping_page */ +#include +#include +#include /* anon_vma_prepare */ +#include /* set_pte_at_notify */ +#include /* try_to_free_swap */ + +#include + +static struct rb_root uprobes_tree = RB_ROOT; + +static DEFINE_SPINLOCK(uprobes_treelock); /* serialize rbtree access */ + +#define UPROBES_HASH_SZ 13 + +/* serialize (un)register */ +static struct mutex uprobes_mutex[UPROBES_HASH_SZ]; + +#define uprobes_hash(v) (&uprobes_mutex[((unsigned long)(v)) % UPROBES_HASH_SZ]) + +/* serialize uprobe->pending_list */ +static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ]; +#define uprobes_mmap_hash(v) (&uprobes_mmap_mutex[((unsigned long)(v)) % UPROBES_HASH_SZ]) + +/* + * uprobe_events allows us to skip the uprobe_mmap if there are no uprobe + * events active at this time. Probably a fine grained per inode count is + * better? + */ +static atomic_t uprobe_events = ATOMIC_INIT(0); + +/* + * Maintain a temporary per vma info that can be used to search if a vma + * has already been handled. This structure is introduced since extending + * vm_area_struct wasnt recommended. + */ +struct vma_info { + struct list_head probe_list; + struct mm_struct *mm; + loff_t vaddr; +}; + +/* + * valid_vma: Verify if the specified vma is an executable vma + * Relax restrictions while unregistering: vm_flags might have + * changed after breakpoint was inserted. + * - is_register: indicates if we are in register context. + * - Return 1 if the specified virtual address is in an + * executable vma. + */ +static bool valid_vma(struct vm_area_struct *vma, bool is_register) +{ + if (!vma->vm_file) + return false; + + if (!is_register) + return true; + + if ((vma->vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)) == (VM_READ|VM_EXEC)) + return true; + + return false; +} + +static loff_t vma_address(struct vm_area_struct *vma, loff_t offset) +{ + loff_t vaddr; + + vaddr = vma->vm_start + offset; + vaddr -= vma->vm_pgoff << PAGE_SHIFT; + + return vaddr; +} + +/** + * __replace_page - replace page in vma by new page. + * based on replace_page in mm/ksm.c + * + * @vma: vma that holds the pte pointing to page + * @page: the cowed page we are replacing by kpage + * @kpage: the modified page we replace page by + * + * Returns 0 on success, -EFAULT on failure. + */ +static int __replace_page(struct vm_area_struct *vma, struct page *page, struct page *kpage) +{ + struct mm_struct *mm = vma->vm_mm; + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *ptep; + spinlock_t *ptl; + unsigned long addr; + int err = -EFAULT; + + addr = page_address_in_vma(page, vma); + if (addr == -EFAULT) + goto out; + + pgd = pgd_offset(mm, addr); + if (!pgd_present(*pgd)) + goto out; + + pud = pud_offset(pgd, addr); + if (!pud_present(*pud)) + goto out; + + pmd = pmd_offset(pud, addr); + if (!pmd_present(*pmd)) + goto out; + + ptep = pte_offset_map_lock(mm, pmd, addr, &ptl); + if (!ptep) + goto out; + + get_page(kpage); + page_add_new_anon_rmap(kpage, vma, addr); + + flush_cache_page(vma, addr, pte_pfn(*ptep)); + ptep_clear_flush(vma, addr, ptep); + set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot)); + + page_remove_rmap(page); + if (!page_mapped(page)) + try_to_free_swap(page); + put_page(page); + pte_unmap_unlock(ptep, ptl); + err = 0; + +out: + return err; +} + +/** + * is_bkpt_insn - check if instruction is breakpoint instruction. + * @insn: instruction to be checked. + * Default implementation of is_bkpt_insn + * Returns true if @insn is a breakpoint instruction. + */ +bool __weak is_bkpt_insn(uprobe_opcode_t *insn) +{ + return *insn == UPROBES_BKPT_INSN; +} + +/* + * NOTE: + * 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 read_opcode / + * write_opcode accordingly. This would never be a problem for archs that + * have fixed length instructions. + */ + +/* + * write_opcode - write the opcode at a given virtual address. + * @mm: the probed process address space. + * @uprobe: the breakpointing information. + * @vaddr: the virtual address to store the opcode. + * @opcode: opcode to be written at @vaddr. + * + * Called with mm->mmap_sem held (for read and with a reference to + * mm). + * + * For mm @mm, write the opcode at @vaddr. + * Return 0 (success) or a negative errno. + */ +static int write_opcode(struct mm_struct *mm, struct uprobe *uprobe, + unsigned long vaddr, uprobe_opcode_t opcode) +{ + struct page *old_page, *new_page; + struct address_space *mapping; + void *vaddr_old, *vaddr_new; + struct vm_area_struct *vma; + loff_t addr; + int ret; + + /* Read the page with vaddr into memory */ + ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &old_page, &vma); + if (ret <= 0) + return ret; + + ret = -EINVAL; + + /* + * We are interested in text pages only. Our pages of interest + * should be mapped for read and execute only. We desist from + * adding probes in write mapped pages since the breakpoints + * might end up in the file copy. + */ + if (!valid_vma(vma, is_bkpt_insn(&opcode))) + goto put_out; + + mapping = uprobe->inode->i_mapping; + if (mapping != vma->vm_file->f_mapping) + goto put_out; + + addr = vma_address(vma, uprobe->offset); + if (vaddr != (unsigned long)addr) + goto put_out; + + ret = -ENOMEM; + new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr); + if (!new_page) + goto put_out; + + __SetPageUptodate(new_page); + + /* + * lock page will serialize against do_wp_page()'s + * PageAnon() handling + */ + lock_page(old_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); + + /* poke the new insn in, ASSUMES we don't cross page boundary */ + vaddr &= ~PAGE_MASK; + BUG_ON(vaddr + uprobe_opcode_sz > PAGE_SIZE); + memcpy(vaddr_new + vaddr, &opcode, uprobe_opcode_sz); + + kunmap_atomic(vaddr_new); + kunmap_atomic(vaddr_old); + + ret = anon_vma_prepare(vma); + if (ret) + goto unlock_out; + + lock_page(new_page); + ret = __replace_page(vma, old_page, new_page); + unlock_page(new_page); + +unlock_out: + unlock_page(old_page); + page_cache_release(new_page); + +put_out: + put_page(old_page); + + return ret; +} + +/** + * read_opcode - read the opcode at a given virtual address. + * @mm: the probed process address space. + * @vaddr: the virtual address to read the opcode. + * @opcode: location to store the read opcode. + * + * Called with mm->mmap_sem held (for read and with a reference to + * mm. + * + * For mm @mm, read the opcode at @vaddr and store it in @opcode. + * Return 0 (success) or a negative errno. + */ +static int read_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t *opcode) +{ + struct page *page; + void *vaddr_new; + int ret; + + ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &page, NULL); + if (ret <= 0) + return ret; + + lock_page(page); + vaddr_new = kmap_atomic(page); + vaddr &= ~PAGE_MASK; + memcpy(opcode, vaddr_new + vaddr, uprobe_opcode_sz); + kunmap_atomic(vaddr_new); + unlock_page(page); + + put_page(page); + + return 0; +} + +static int is_bkpt_at_addr(struct mm_struct *mm, unsigned long vaddr) +{ + uprobe_opcode_t opcode; + int result; + + result = read_opcode(mm, vaddr, &opcode); + if (result) + return result; + + if (is_bkpt_insn(&opcode)) + return 1; + + return 0; +} + +/** + * set_bkpt - store breakpoint at a given address. + * @mm: the probed process address space. + * @uprobe: the probepoint information. + * @vaddr: the virtual address to insert the opcode. + * + * For mm @mm, store the breakpoint instruction at @vaddr. + * Return 0 (success) or a negative errno. + */ +int __weak set_bkpt(struct mm_struct *mm, struct uprobe *uprobe, unsigned long vaddr) +{ + int result; + + result = is_bkpt_at_addr(mm, vaddr); + if (result == 1) + return -EEXIST; + + if (result) + return result; + + return write_opcode(mm, uprobe, vaddr, UPROBES_BKPT_INSN); +} + +/** + * set_orig_insn - Restore the original instruction. + * @mm: the probed process address space. + * @uprobe: the probepoint information. + * @vaddr: the virtual address to insert the opcode. + * @verify: if true, verify existance of breakpoint instruction. + * + * For mm @mm, restore the original opcode (opcode) at @vaddr. + * Return 0 (success) or a negative errno. + */ +int __weak +set_orig_insn(struct mm_struct *mm, struct uprobe *uprobe, unsigned long vaddr, bool verify) +{ + if (verify) { + int result; + + result = is_bkpt_at_addr(mm, vaddr); + if (!result) + return -EINVAL; + + if (result != 1) + return result; + } + return write_opcode(mm, uprobe, vaddr, *(uprobe_opcode_t *)uprobe->insn); +} + +static int match_uprobe(struct uprobe *l, struct uprobe *r) +{ + if (l->inode < r->inode) + return -1; + + if (l->inode > r->inode) + return 1; + + if (l->offset < r->offset) + return -1; + + if (l->offset > r->offset) + return 1; + + return 0; +} + +static struct uprobe *__find_uprobe(struct inode *inode, loff_t offset) +{ + struct uprobe u = { .inode = inode, .offset = offset }; + struct rb_node *n = uprobes_tree.rb_node; + struct uprobe *uprobe; + int match; + + while (n) { + uprobe = rb_entry(n, struct uprobe, rb_node); + match = match_uprobe(&u, uprobe); + if (!match) { + atomic_inc(&uprobe->ref); + return uprobe; + } + + if (match < 0) + n = n->rb_left; + else + n = n->rb_right; + } + return NULL; +} + +/* + * Find a uprobe corresponding to a given inode:offset + * Acquires uprobes_treelock + */ +static struct uprobe *find_uprobe(struct inode *inode, loff_t offset) +{ + struct uprobe *uprobe; + unsigned long flags; + + spin_lock_irqsave(&uprobes_treelock, flags); + uprobe = __find_uprobe(inode, offset); + spin_unlock_irqrestore(&uprobes_treelock, flags); + + return uprobe; +} + +static struct uprobe *__insert_uprobe(struct uprobe *uprobe) +{ + struct rb_node **p = &uprobes_tree.rb_node; + struct rb_node *parent = NULL; + struct uprobe *u; + int match; + + while (*p) { + parent = *p; + u = rb_entry(parent, struct uprobe, rb_node); + match = match_uprobe(uprobe, u); + if (!match) { + atomic_inc(&u->ref); + return u; + } + + if (match < 0) + p = &parent->rb_left; + else + p = &parent->rb_right; + + } + + u = NULL; + rb_link_node(&uprobe->rb_node, parent, p); + rb_insert_color(&uprobe->rb_node, &uprobes_tree); + /* get access + creation ref */ + atomic_set(&uprobe->ref, 2); + + return u; +} + +/* + * Acquire uprobes_treelock. + * Matching uprobe already exists in rbtree; + * increment (access refcount) and return the matching uprobe. + * + * No matching uprobe; insert the uprobe in rb_tree; + * get a double refcount (access + creation) and return NULL. + */ +static struct uprobe *insert_uprobe(struct uprobe *uprobe) +{ + unsigned long flags; + struct uprobe *u; + + spin_lock_irqsave(&uprobes_treelock, flags); + u = __insert_uprobe(uprobe); + spin_unlock_irqrestore(&uprobes_treelock, flags); + + return u; +} + +static void put_uprobe(struct uprobe *uprobe) +{ + if (atomic_dec_and_test(&uprobe->ref)) + kfree(uprobe); +} + +static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset) +{ + struct uprobe *uprobe, *cur_uprobe; + + uprobe = kzalloc(sizeof(struct uprobe), GFP_KERNEL); + if (!uprobe) + return NULL; + + uprobe->inode = igrab(inode); + uprobe->offset = offset; + init_rwsem(&uprobe->consumer_rwsem); + INIT_LIST_HEAD(&uprobe->pending_list); + + /* add to uprobes_tree, sorted on inode:offset */ + cur_uprobe = insert_uprobe(uprobe); + + /* a uprobe exists for this inode:offset combination */ + if (cur_uprobe) { + kfree(uprobe); + uprobe = cur_uprobe; + iput(inode); + } else { + atomic_inc(&uprobe_events); + } + + return uprobe; +} + +/* Returns the previous consumer */ +static struct uprobe_consumer * +consumer_add(struct uprobe *uprobe, struct uprobe_consumer *consumer) +{ + down_write(&uprobe->consumer_rwsem); + consumer->next = uprobe->consumers; + uprobe->consumers = consumer; + up_write(&uprobe->consumer_rwsem); + + return consumer->next; +} + +/* + * For uprobe @uprobe, delete the consumer @consumer. + * Return true if the @consumer is deleted successfully + * or return false. + */ +static bool consumer_del(struct uprobe *uprobe, struct uprobe_consumer *consumer) +{ + struct uprobe_consumer **con; + bool ret = false; + + down_write(&uprobe->consumer_rwsem); + for (con = &uprobe->consumers; *con; con = &(*con)->next) { + if (*con == consumer) { + *con = consumer->next; + ret = true; + break; + } + } + up_write(&uprobe->consumer_rwsem); + + return ret; +} + +static int __copy_insn(struct address_space *mapping, + struct vm_area_struct *vma, char *insn, + unsigned long nbytes, unsigned long offset) +{ + struct file *filp = vma->vm_file; + struct page *page; + void *vaddr; + unsigned long off1; + unsigned long idx; + + if (!filp) + return -EINVAL; + + idx = (unsigned long)(offset >> PAGE_CACHE_SHIFT); + off1 = 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); + if (IS_ERR(page)) + return PTR_ERR(page); + + vaddr = kmap_atomic(page); + memcpy(insn, vaddr + off1, nbytes); + kunmap_atomic(vaddr); + page_cache_release(page); + + return 0; +} + +static int copy_insn(struct uprobe *uprobe, struct vm_area_struct *vma, unsigned long addr) +{ + struct address_space *mapping; + unsigned long nbytes; + int bytes; + + addr &= ~PAGE_MASK; + nbytes = PAGE_SIZE - addr; + mapping = uprobe->inode->i_mapping; + + /* Instruction at end of binary; copy only available bytes */ + if (uprobe->offset + MAX_UINSN_BYTES > uprobe->inode->i_size) + bytes = uprobe->inode->i_size - uprobe->offset; + else + bytes = MAX_UINSN_BYTES; + + /* Instruction at the page-boundary; copy bytes in second page */ + if (nbytes < bytes) { + if (__copy_insn(mapping, vma, uprobe->insn + nbytes, + bytes - nbytes, uprobe->offset + nbytes)) + return -ENOMEM; + + bytes = nbytes; + } + return __copy_insn(mapping, vma, uprobe->insn, bytes, uprobe->offset); +} + +static int install_breakpoint(struct mm_struct *mm, struct uprobe *uprobe, + struct vm_area_struct *vma, loff_t vaddr) +{ + unsigned long addr; + int ret; + + /* + * If probe is being deleted, unregister thread could be done with + * the vma-rmap-walk through. Adding a probe now can be fatal since + * nobody will be able to cleanup. Also we could be from fork or + * mremap path, where the probe might have already been inserted. + * Hence behave as if probe already existed. + */ + if (!uprobe->consumers) + return -EEXIST; + + addr = (unsigned long)vaddr; + + if (!(uprobe->flags & UPROBES_COPY_INSN)) { + ret = copy_insn(uprobe, vma, addr); + if (ret) + return ret; + + if (is_bkpt_insn((uprobe_opcode_t *)uprobe->insn)) + return -EEXIST; + + ret = arch_uprobes_analyze_insn(mm, uprobe); + if (ret) + return ret; + + uprobe->flags |= UPROBES_COPY_INSN; + } + ret = set_bkpt(mm, uprobe, addr); + + return ret; +} + +static void remove_breakpoint(struct mm_struct *mm, struct uprobe *uprobe, loff_t vaddr) +{ + set_orig_insn(mm, uprobe, (unsigned long)vaddr, true); +} + +static void delete_uprobe(struct uprobe *uprobe) +{ + unsigned long flags; + + spin_lock_irqsave(&uprobes_treelock, flags); + rb_erase(&uprobe->rb_node, &uprobes_tree); + spin_unlock_irqrestore(&uprobes_treelock, flags); + iput(uprobe->inode); + put_uprobe(uprobe); + atomic_dec(&uprobe_events); +} + +static struct vma_info *__find_next_vma_info(struct list_head *head, + loff_t offset, struct address_space *mapping, + struct vma_info *vi, bool is_register) +{ + struct prio_tree_iter iter; + struct vm_area_struct *vma; + struct vma_info *tmpvi; + unsigned long pgoff; + int existing_vma; + loff_t vaddr; + + pgoff = offset >> PAGE_SHIFT; + + vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { + if (!valid_vma(vma, is_register)) + continue; + + existing_vma = 0; + vaddr = vma_address(vma, offset); + + list_for_each_entry(tmpvi, head, probe_list) { + if (tmpvi->mm == vma->vm_mm && tmpvi->vaddr == vaddr) { + existing_vma = 1; + break; + } + } + + /* + * Another vma needs a probe to be installed. However skip + * installing the probe if the vma is about to be unlinked. + */ + if (!existing_vma && atomic_inc_not_zero(&vma->vm_mm->mm_users)) { + vi->mm = vma->vm_mm; + vi->vaddr = vaddr; + list_add(&vi->probe_list, head); + + return vi; + } + } + + return NULL; +} + +/* + * Iterate in the rmap prio tree and find a vma where a probe has not + * yet been inserted. + */ +static struct vma_info * +find_next_vma_info(struct list_head *head, loff_t offset, struct address_space *mapping, + bool is_register) +{ + struct vma_info *vi, *retvi; + + vi = kzalloc(sizeof(struct vma_info), GFP_KERNEL); + if (!vi) + return ERR_PTR(-ENOMEM); + + mutex_lock(&mapping->i_mmap_mutex); + retvi = __find_next_vma_info(head, offset, mapping, vi, is_register); + mutex_unlock(&mapping->i_mmap_mutex); + + if (!retvi) + kfree(vi); + + return retvi; +} + +static int register_for_each_vma(struct uprobe *uprobe, bool is_register) +{ + struct list_head try_list; + struct vm_area_struct *vma; + struct address_space *mapping; + struct vma_info *vi, *tmpvi; + struct mm_struct *mm; + loff_t vaddr; + int ret; + + mapping = uprobe->inode->i_mapping; + INIT_LIST_HEAD(&try_list); + + ret = 0; + + for (;;) { + vi = find_next_vma_info(&try_list, uprobe->offset, mapping, is_register); + if (!vi) + break; + + if (IS_ERR(vi)) { + ret = PTR_ERR(vi); + break; + } + + mm = vi->mm; + down_read(&mm->mmap_sem); + vma = find_vma(mm, (unsigned long)vi->vaddr); + if (!vma || !valid_vma(vma, is_register)) { + list_del(&vi->probe_list); + kfree(vi); + up_read(&mm->mmap_sem); + mmput(mm); + continue; + } + vaddr = vma_address(vma, uprobe->offset); + if (vma->vm_file->f_mapping->host != uprobe->inode || + vaddr != vi->vaddr) { + list_del(&vi->probe_list); + kfree(vi); + up_read(&mm->mmap_sem); + mmput(mm); + continue; + } + + if (is_register) + ret = install_breakpoint(mm, uprobe, vma, vi->vaddr); + else + remove_breakpoint(mm, uprobe, vi->vaddr); + + up_read(&mm->mmap_sem); + mmput(mm); + if (is_register) { + if (ret && ret == -EEXIST) + ret = 0; + if (ret) + break; + } + } + + list_for_each_entry_safe(vi, tmpvi, &try_list, probe_list) { + list_del(&vi->probe_list); + kfree(vi); + } + + return ret; +} + +static int __uprobe_register(struct uprobe *uprobe) +{ + return register_for_each_vma(uprobe, true); +} + +static void __uprobe_unregister(struct uprobe *uprobe) +{ + if (!register_for_each_vma(uprobe, false)) + delete_uprobe(uprobe); + + /* TODO : cant unregister? schedule a worker thread */ +} + +/* + * uprobe_register - register a probe + * @inode: the file in which the probe has to be placed. + * @offset: offset from the start of the file. + * @consumer: information on howto handle the probe.. + * + * Apart from the access refcount, uprobe_register() takes a creation + * refcount (thro alloc_uprobe) if and only if this @uprobe is getting + * inserted into the rbtree (i.e first consumer for a @inode:@offset + * tuple). Creation refcount stops uprobe_unregister from freeing the + * @uprobe even before the register operation is complete. Creation + * refcount is released when the last @consumer for the @uprobe + * unregisters. + * + * Return errno if it cannot successully install probes + * else return 0 (success) + */ +int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *consumer) +{ + struct uprobe *uprobe; + int ret; + + if (!inode || !consumer || consumer->next) + return -EINVAL; + + if (offset > i_size_read(inode)) + return -EINVAL; + + ret = 0; + mutex_lock(uprobes_hash(inode)); + uprobe = alloc_uprobe(inode, offset); + + if (uprobe && !consumer_add(uprobe, consumer)) { + ret = __uprobe_register(uprobe); + if (ret) { + uprobe->consumers = NULL; + __uprobe_unregister(uprobe); + } else { + uprobe->flags |= UPROBES_RUN_HANDLER; + } + } + + mutex_unlock(uprobes_hash(inode)); + put_uprobe(uprobe); + + return ret; +} + +/* + * uprobe_unregister - unregister a already registered probe. + * @inode: the file in which the probe has to be removed. + * @offset: offset from the start of the file. + * @consumer: identify which probe if multiple probes are colocated. + */ +void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *consumer) +{ + struct uprobe *uprobe; + + if (!inode || !consumer) + return; + + uprobe = find_uprobe(inode, offset); + if (!uprobe) + return; + + mutex_lock(uprobes_hash(inode)); + + if (consumer_del(uprobe, consumer)) { + if (!uprobe->consumers) { + __uprobe_unregister(uprobe); + uprobe->flags &= ~UPROBES_RUN_HANDLER; + } + } + + mutex_unlock(uprobes_hash(inode)); + if (uprobe) + put_uprobe(uprobe); +} + +/* + * Of all the nodes that correspond to the given inode, return the node + * with the least offset. + */ +static struct rb_node *find_least_offset_node(struct inode *inode) +{ + struct uprobe u = { .inode = inode, .offset = 0}; + struct rb_node *n = uprobes_tree.rb_node; + struct rb_node *close_node = NULL; + struct uprobe *uprobe; + int match; + + while (n) { + uprobe = rb_entry(n, struct uprobe, rb_node); + match = match_uprobe(&u, uprobe); + + if (uprobe->inode == inode) + close_node = n; + + if (!match) + return close_node; + + if (match < 0) + n = n->rb_left; + else + n = n->rb_right; + } + + return close_node; +} + +/* + * For a given inode, build a list of probes that need to be inserted. + */ +static void build_probe_list(struct inode *inode, struct list_head *head) +{ + struct uprobe *uprobe; + unsigned long flags; + struct rb_node *n; + + spin_lock_irqsave(&uprobes_treelock, flags); + + n = find_least_offset_node(inode); + + for (; n; n = rb_next(n)) { + uprobe = rb_entry(n, struct uprobe, rb_node); + if (uprobe->inode != inode) + break; + + list_add(&uprobe->pending_list, head); + atomic_inc(&uprobe->ref); + } + + spin_unlock_irqrestore(&uprobes_treelock, flags); +} + +/* + * Called from mmap_region. + * called with mm->mmap_sem acquired. + * + * Return -ve no if we fail to insert probes and we cannot + * bail-out. + * Return 0 otherwise. i.e: + * + * - successful insertion of probes + * - (or) no possible probes to be inserted. + * - (or) insertion of probes failed but we can bail-out. + */ +int uprobe_mmap(struct vm_area_struct *vma) +{ + struct list_head tmp_list; + struct uprobe *uprobe, *u; + struct inode *inode; + int ret; + + if (!atomic_read(&uprobe_events) || !valid_vma(vma, true)) + return 0; + + inode = vma->vm_file->f_mapping->host; + if (!inode) + return 0; + + INIT_LIST_HEAD(&tmp_list); + mutex_lock(uprobes_mmap_hash(inode)); + build_probe_list(inode, &tmp_list); + + ret = 0; + + list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) { + loff_t vaddr; + + list_del(&uprobe->pending_list); + if (!ret) { + vaddr = vma_address(vma, uprobe->offset); + if (vaddr >= vma->vm_start && vaddr < vma->vm_end) { + ret = install_breakpoint(vma->vm_mm, uprobe, vma, vaddr); + /* Ignore double add: */ + if (ret == -EEXIST) + ret = 0; + } + } + put_uprobe(uprobe); + } + + mutex_unlock(uprobes_mmap_hash(inode)); + + return ret; +} + +static int __init init_uprobes(void) +{ + int i; + + for (i = 0; i < UPROBES_HASH_SZ; i++) { + mutex_init(&uprobes_mutex[i]); + mutex_init(&uprobes_mmap_mutex[i]); + } + return 0; +} + +static void __exit exit_uprobes(void) +{ +} + +module_init(init_uprobes); +module_exit(exit_uprobes); diff --git a/kernel/uprobes.c b/kernel/uprobes.c deleted file mode 100644 index 884817f1b0d..00000000000 --- a/kernel/uprobes.c +++ /dev/null @@ -1,1011 +0,0 @@ -/* - * User-space Probes (UProbes) - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * - * Copyright (C) IBM Corporation, 2008-2011 - * Authors: - * Srikar Dronamraju - * Jim Keniston - */ - -#include -#include -#include /* read_mapping_page */ -#include -#include -#include /* anon_vma_prepare */ -#include /* set_pte_at_notify */ -#include /* try_to_free_swap */ - -#include - -static struct rb_root uprobes_tree = RB_ROOT; - -static DEFINE_SPINLOCK(uprobes_treelock); /* serialize rbtree access */ - -#define UPROBES_HASH_SZ 13 - -/* serialize (un)register */ -static struct mutex uprobes_mutex[UPROBES_HASH_SZ]; - -#define uprobes_hash(v) (&uprobes_mutex[((unsigned long)(v)) % UPROBES_HASH_SZ]) - -/* serialize uprobe->pending_list */ -static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ]; -#define uprobes_mmap_hash(v) (&uprobes_mmap_mutex[((unsigned long)(v)) % UPROBES_HASH_SZ]) - -/* - * uprobe_events allows us to skip the uprobe_mmap if there are no uprobe - * events active at this time. Probably a fine grained per inode count is - * better? - */ -static atomic_t uprobe_events = ATOMIC_INIT(0); - -/* - * Maintain a temporary per vma info that can be used to search if a vma - * has already been handled. This structure is introduced since extending - * vm_area_struct wasnt recommended. - */ -struct vma_info { - struct list_head probe_list; - struct mm_struct *mm; - loff_t vaddr; -}; - -/* - * valid_vma: Verify if the specified vma is an executable vma - * Relax restrictions while unregistering: vm_flags might have - * changed after breakpoint was inserted. - * - is_register: indicates if we are in register context. - * - Return 1 if the specified virtual address is in an - * executable vma. - */ -static bool valid_vma(struct vm_area_struct *vma, bool is_register) -{ - if (!vma->vm_file) - return false; - - if (!is_register) - return true; - - if ((vma->vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)) == (VM_READ|VM_EXEC)) - return true; - - return false; -} - -static loff_t vma_address(struct vm_area_struct *vma, loff_t offset) -{ - loff_t vaddr; - - vaddr = vma->vm_start + offset; - vaddr -= vma->vm_pgoff << PAGE_SHIFT; - - return vaddr; -} - -/** - * __replace_page - replace page in vma by new page. - * based on replace_page in mm/ksm.c - * - * @vma: vma that holds the pte pointing to page - * @page: the cowed page we are replacing by kpage - * @kpage: the modified page we replace page by - * - * Returns 0 on success, -EFAULT on failure. - */ -static int __replace_page(struct vm_area_struct *vma, struct page *page, struct page *kpage) -{ - struct mm_struct *mm = vma->vm_mm; - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *ptep; - spinlock_t *ptl; - unsigned long addr; - int err = -EFAULT; - - addr = page_address_in_vma(page, vma); - if (addr == -EFAULT) - goto out; - - pgd = pgd_offset(mm, addr); - if (!pgd_present(*pgd)) - goto out; - - pud = pud_offset(pgd, addr); - if (!pud_present(*pud)) - goto out; - - pmd = pmd_offset(pud, addr); - if (!pmd_present(*pmd)) - goto out; - - ptep = pte_offset_map_lock(mm, pmd, addr, &ptl); - if (!ptep) - goto out; - - get_page(kpage); - page_add_new_anon_rmap(kpage, vma, addr); - - flush_cache_page(vma, addr, pte_pfn(*ptep)); - ptep_clear_flush(vma, addr, ptep); - set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot)); - - page_remove_rmap(page); - if (!page_mapped(page)) - try_to_free_swap(page); - put_page(page); - pte_unmap_unlock(ptep, ptl); - err = 0; - -out: - return err; -} - -/** - * is_bkpt_insn - check if instruction is breakpoint instruction. - * @insn: instruction to be checked. - * Default implementation of is_bkpt_insn - * Returns true if @insn is a breakpoint instruction. - */ -bool __weak is_bkpt_insn(uprobe_opcode_t *insn) -{ - return *insn == UPROBES_BKPT_INSN; -} - -/* - * NOTE: - * 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 read_opcode / - * write_opcode accordingly. This would never be a problem for archs that - * have fixed length instructions. - */ - -/* - * write_opcode - write the opcode at a given virtual address. - * @mm: the probed process address space. - * @uprobe: the breakpointing information. - * @vaddr: the virtual address to store the opcode. - * @opcode: opcode to be written at @vaddr. - * - * Called with mm->mmap_sem held (for read and with a reference to - * mm). - * - * For mm @mm, write the opcode at @vaddr. - * Return 0 (success) or a negative errno. - */ -static int write_opcode(struct mm_struct *mm, struct uprobe *uprobe, - unsigned long vaddr, uprobe_opcode_t opcode) -{ - struct page *old_page, *new_page; - struct address_space *mapping; - void *vaddr_old, *vaddr_new; - struct vm_area_struct *vma; - loff_t addr; - int ret; - - /* Read the page with vaddr into memory */ - ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &old_page, &vma); - if (ret <= 0) - return ret; - - ret = -EINVAL; - - /* - * We are interested in text pages only. Our pages of interest - * should be mapped for read and execute only. We desist from - * adding probes in write mapped pages since the breakpoints - * might end up in the file copy. - */ - if (!valid_vma(vma, is_bkpt_insn(&opcode))) - goto put_out; - - mapping = uprobe->inode->i_mapping; - if (mapping != vma->vm_file->f_mapping) - goto put_out; - - addr = vma_address(vma, uprobe->offset); - if (vaddr != (unsigned long)addr) - goto put_out; - - ret = -ENOMEM; - new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr); - if (!new_page) - goto put_out; - - __SetPageUptodate(new_page); - - /* - * lock page will serialize against do_wp_page()'s - * PageAnon() handling - */ - lock_page(old_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); - - /* poke the new insn in, ASSUMES we don't cross page boundary */ - vaddr &= ~PAGE_MASK; - BUG_ON(vaddr + uprobe_opcode_sz > PAGE_SIZE); - memcpy(vaddr_new + vaddr, &opcode, uprobe_opcode_sz); - - kunmap_atomic(vaddr_new); - kunmap_atomic(vaddr_old); - - ret = anon_vma_prepare(vma); - if (ret) - goto unlock_out; - - lock_page(new_page); - ret = __replace_page(vma, old_page, new_page); - unlock_page(new_page); - -unlock_out: - unlock_page(old_page); - page_cache_release(new_page); - -put_out: - put_page(old_page); - - return ret; -} - -/** - * read_opcode - read the opcode at a given virtual address. - * @mm: the probed process address space. - * @vaddr: the virtual address to read the opcode. - * @opcode: location to store the read opcode. - * - * Called with mm->mmap_sem held (for read and with a reference to - * mm. - * - * For mm @mm, read the opcode at @vaddr and store it in @opcode. - * Return 0 (success) or a negative errno. - */ -static int read_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t *opcode) -{ - struct page *page; - void *vaddr_new; - int ret; - - ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &page, NULL); - if (ret <= 0) - return ret; - - lock_page(page); - vaddr_new = kmap_atomic(page); - vaddr &= ~PAGE_MASK; - memcpy(opcode, vaddr_new + vaddr, uprobe_opcode_sz); - kunmap_atomic(vaddr_new); - unlock_page(page); - - put_page(page); - - return 0; -} - -static int is_bkpt_at_addr(struct mm_struct *mm, unsigned long vaddr) -{ - uprobe_opcode_t opcode; - int result; - - result = read_opcode(mm, vaddr, &opcode); - if (result) - return result; - - if (is_bkpt_insn(&opcode)) - return 1; - - return 0; -} - -/** - * set_bkpt - store breakpoint at a given address. - * @mm: the probed process address space. - * @uprobe: the probepoint information. - * @vaddr: the virtual address to insert the opcode. - * - * For mm @mm, store the breakpoint instruction at @vaddr. - * Return 0 (success) or a negative errno. - */ -int __weak set_bkpt(struct mm_struct *mm, struct uprobe *uprobe, unsigned long vaddr) -{ - int result; - - result = is_bkpt_at_addr(mm, vaddr); - if (result == 1) - return -EEXIST; - - if (result) - return result; - - return write_opcode(mm, uprobe, vaddr, UPROBES_BKPT_INSN); -} - -/** - * set_orig_insn - Restore the original instruction. - * @mm: the probed process address space. - * @uprobe: the probepoint information. - * @vaddr: the virtual address to insert the opcode. - * @verify: if true, verify existance of breakpoint instruction. - * - * For mm @mm, restore the original opcode (opcode) at @vaddr. - * Return 0 (success) or a negative errno. - */ -int __weak -set_orig_insn(struct mm_struct *mm, struct uprobe *uprobe, unsigned long vaddr, bool verify) -{ - if (verify) { - int result; - - result = is_bkpt_at_addr(mm, vaddr); - if (!result) - return -EINVAL; - - if (result != 1) - return result; - } - return write_opcode(mm, uprobe, vaddr, *(uprobe_opcode_t *)uprobe->insn); -} - -static int match_uprobe(struct uprobe *l, struct uprobe *r) -{ - if (l->inode < r->inode) - return -1; - - if (l->inode > r->inode) - return 1; - - if (l->offset < r->offset) - return -1; - - if (l->offset > r->offset) - return 1; - - return 0; -} - -static struct uprobe *__find_uprobe(struct inode *inode, loff_t offset) -{ - struct uprobe u = { .inode = inode, .offset = offset }; - struct rb_node *n = uprobes_tree.rb_node; - struct uprobe *uprobe; - int match; - - while (n) { - uprobe = rb_entry(n, struct uprobe, rb_node); - match = match_uprobe(&u, uprobe); - if (!match) { - atomic_inc(&uprobe->ref); - return uprobe; - } - - if (match < 0) - n = n->rb_left; - else - n = n->rb_right; - } - return NULL; -} - -/* - * Find a uprobe corresponding to a given inode:offset - * Acquires uprobes_treelock - */ -static struct uprobe *find_uprobe(struct inode *inode, loff_t offset) -{ - struct uprobe *uprobe; - unsigned long flags; - - spin_lock_irqsave(&uprobes_treelock, flags); - uprobe = __find_uprobe(inode, offset); - spin_unlock_irqrestore(&uprobes_treelock, flags); - - return uprobe; -} - -static struct uprobe *__insert_uprobe(struct uprobe *uprobe) -{ - struct rb_node **p = &uprobes_tree.rb_node; - struct rb_node *parent = NULL; - struct uprobe *u; - int match; - - while (*p) { - parent = *p; - u = rb_entry(parent, struct uprobe, rb_node); - match = match_uprobe(uprobe, u); - if (!match) { - atomic_inc(&u->ref); - return u; - } - - if (match < 0) - p = &parent->rb_left; - else - p = &parent->rb_right; - - } - - u = NULL; - rb_link_node(&uprobe->rb_node, parent, p); - rb_insert_color(&uprobe->rb_node, &uprobes_tree); - /* get access + creation ref */ - atomic_set(&uprobe->ref, 2); - - return u; -} - -/* - * Acquire uprobes_treelock. - * Matching uprobe already exists in rbtree; - * increment (access refcount) and return the matching uprobe. - * - * No matching uprobe; insert the uprobe in rb_tree; - * get a double refcount (access + creation) and return NULL. - */ -static struct uprobe *insert_uprobe(struct uprobe *uprobe) -{ - unsigned long flags; - struct uprobe *u; - - spin_lock_irqsave(&uprobes_treelock, flags); - u = __insert_uprobe(uprobe); - spin_unlock_irqrestore(&uprobes_treelock, flags); - - return u; -} - -static void put_uprobe(struct uprobe *uprobe) -{ - if (atomic_dec_and_test(&uprobe->ref)) - kfree(uprobe); -} - -static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset) -{ - struct uprobe *uprobe, *cur_uprobe; - - uprobe = kzalloc(sizeof(struct uprobe), GFP_KERNEL); - if (!uprobe) - return NULL; - - uprobe->inode = igrab(inode); - uprobe->offset = offset; - init_rwsem(&uprobe->consumer_rwsem); - INIT_LIST_HEAD(&uprobe->pending_list); - - /* add to uprobes_tree, sorted on inode:offset */ - cur_uprobe = insert_uprobe(uprobe); - - /* a uprobe exists for this inode:offset combination */ - if (cur_uprobe) { - kfree(uprobe); - uprobe = cur_uprobe; - iput(inode); - } else { - atomic_inc(&uprobe_events); - } - - return uprobe; -} - -/* Returns the previous consumer */ -static struct uprobe_consumer * -consumer_add(struct uprobe *uprobe, struct uprobe_consumer *consumer) -{ - down_write(&uprobe->consumer_rwsem); - consumer->next = uprobe->consumers; - uprobe->consumers = consumer; - up_write(&uprobe->consumer_rwsem); - - return consumer->next; -} - -/* - * For uprobe @uprobe, delete the consumer @consumer. - * Return true if the @consumer is deleted successfully - * or return false. - */ -static bool consumer_del(struct uprobe *uprobe, struct uprobe_consumer *consumer) -{ - struct uprobe_consumer **con; - bool ret = false; - - down_write(&uprobe->consumer_rwsem); - for (con = &uprobe->consumers; *con; con = &(*con)->next) { - if (*con == consumer) { - *con = consumer->next; - ret = true; - break; - } - } - up_write(&uprobe->consumer_rwsem); - - return ret; -} - -static int __copy_insn(struct address_space *mapping, - struct vm_area_struct *vma, char *insn, - unsigned long nbytes, unsigned long offset) -{ - struct file *filp = vma->vm_file; - struct page *page; - void *vaddr; - unsigned long off1; - unsigned long idx; - - if (!filp) - return -EINVAL; - - idx = (unsigned long)(offset >> PAGE_CACHE_SHIFT); - off1 = 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); - if (IS_ERR(page)) - return PTR_ERR(page); - - vaddr = kmap_atomic(page); - memcpy(insn, vaddr + off1, nbytes); - kunmap_atomic(vaddr); - page_cache_release(page); - - return 0; -} - -static int copy_insn(struct uprobe *uprobe, struct vm_area_struct *vma, unsigned long addr) -{ - struct address_space *mapping; - unsigned long nbytes; - int bytes; - - addr &= ~PAGE_MASK; - nbytes = PAGE_SIZE - addr; - mapping = uprobe->inode->i_mapping; - - /* Instruction at end of binary; copy only available bytes */ - if (uprobe->offset + MAX_UINSN_BYTES > uprobe->inode->i_size) - bytes = uprobe->inode->i_size - uprobe->offset; - else - bytes = MAX_UINSN_BYTES; - - /* Instruction at the page-boundary; copy bytes in second page */ - if (nbytes < bytes) { - if (__copy_insn(mapping, vma, uprobe->insn + nbytes, - bytes - nbytes, uprobe->offset + nbytes)) - return -ENOMEM; - - bytes = nbytes; - } - return __copy_insn(mapping, vma, uprobe->insn, bytes, uprobe->offset); -} - -static int install_breakpoint(struct mm_struct *mm, struct uprobe *uprobe, - struct vm_area_struct *vma, loff_t vaddr) -{ - unsigned long addr; - int ret; - - /* - * If probe is being deleted, unregister thread could be done with - * the vma-rmap-walk through. Adding a probe now can be fatal since - * nobody will be able to cleanup. Also we could be from fork or - * mremap path, where the probe might have already been inserted. - * Hence behave as if probe already existed. - */ - if (!uprobe->consumers) - return -EEXIST; - - addr = (unsigned long)vaddr; - - if (!(uprobe->flags & UPROBES_COPY_INSN)) { - ret = copy_insn(uprobe, vma, addr); - if (ret) - return ret; - - if (is_bkpt_insn((uprobe_opcode_t *)uprobe->insn)) - return -EEXIST; - - ret = arch_uprobes_analyze_insn(mm, uprobe); - if (ret) - return ret; - - uprobe->flags |= UPROBES_COPY_INSN; - } - ret = set_bkpt(mm, uprobe, addr); - - return ret; -} - -static void remove_breakpoint(struct mm_struct *mm, struct uprobe *uprobe, loff_t vaddr) -{ - set_orig_insn(mm, uprobe, (unsigned long)vaddr, true); -} - -static void delete_uprobe(struct uprobe *uprobe) -{ - unsigned long flags; - - spin_lock_irqsave(&uprobes_treelock, flags); - rb_erase(&uprobe->rb_node, &uprobes_tree); - spin_unlock_irqrestore(&uprobes_treelock, flags); - iput(uprobe->inode); - put_uprobe(uprobe); - atomic_dec(&uprobe_events); -} - -static struct vma_info *__find_next_vma_info(struct list_head *head, - loff_t offset, struct address_space *mapping, - struct vma_info *vi, bool is_register) -{ - struct prio_tree_iter iter; - struct vm_area_struct *vma; - struct vma_info *tmpvi; - unsigned long pgoff; - int existing_vma; - loff_t vaddr; - - pgoff = offset >> PAGE_SHIFT; - - vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { - if (!valid_vma(vma, is_register)) - continue; - - existing_vma = 0; - vaddr = vma_address(vma, offset); - - list_for_each_entry(tmpvi, head, probe_list) { - if (tmpvi->mm == vma->vm_mm && tmpvi->vaddr == vaddr) { - existing_vma = 1; - break; - } - } - - /* - * Another vma needs a probe to be installed. However skip - * installing the probe if the vma is about to be unlinked. - */ - if (!existing_vma && atomic_inc_not_zero(&vma->vm_mm->mm_users)) { - vi->mm = vma->vm_mm; - vi->vaddr = vaddr; - list_add(&vi->probe_list, head); - - return vi; - } - } - - return NULL; -} - -/* - * Iterate in the rmap prio tree and find a vma where a probe has not - * yet been inserted. - */ -static struct vma_info * -find_next_vma_info(struct list_head *head, loff_t offset, struct address_space *mapping, - bool is_register) -{ - struct vma_info *vi, *retvi; - - vi = kzalloc(sizeof(struct vma_info), GFP_KERNEL); - if (!vi) - return ERR_PTR(-ENOMEM); - - mutex_lock(&mapping->i_mmap_mutex); - retvi = __find_next_vma_info(head, offset, mapping, vi, is_register); - mutex_unlock(&mapping->i_mmap_mutex); - - if (!retvi) - kfree(vi); - - return retvi; -} - -static int register_for_each_vma(struct uprobe *uprobe, bool is_register) -{ - struct list_head try_list; - struct vm_area_struct *vma; - struct address_space *mapping; - struct vma_info *vi, *tmpvi; - struct mm_struct *mm; - loff_t vaddr; - int ret; - - mapping = uprobe->inode->i_mapping; - INIT_LIST_HEAD(&try_list); - - ret = 0; - - for (;;) { - vi = find_next_vma_info(&try_list, uprobe->offset, mapping, is_register); - if (!vi) - break; - - if (IS_ERR(vi)) { - ret = PTR_ERR(vi); - break; - } - - mm = vi->mm; - down_read(&mm->mmap_sem); - vma = find_vma(mm, (unsigned long)vi->vaddr); - if (!vma || !valid_vma(vma, is_register)) { - list_del(&vi->probe_list); - kfree(vi); - up_read(&mm->mmap_sem); - mmput(mm); - continue; - } - vaddr = vma_address(vma, uprobe->offset); - if (vma->vm_file->f_mapping->host != uprobe->inode || - vaddr != vi->vaddr) { - list_del(&vi->probe_list); - kfree(vi); - up_read(&mm->mmap_sem); - mmput(mm); - continue; - } - - if (is_register) - ret = install_breakpoint(mm, uprobe, vma, vi->vaddr); - else - remove_breakpoint(mm, uprobe, vi->vaddr); - - up_read(&mm->mmap_sem); - mmput(mm); - if (is_register) { - if (ret && ret == -EEXIST) - ret = 0; - if (ret) - break; - } - } - - list_for_each_entry_safe(vi, tmpvi, &try_list, probe_list) { - list_del(&vi->probe_list); - kfree(vi); - } - - return ret; -} - -static int __uprobe_register(struct uprobe *uprobe) -{ - return register_for_each_vma(uprobe, true); -} - -static void __uprobe_unregister(struct uprobe *uprobe) -{ - if (!register_for_each_vma(uprobe, false)) - delete_uprobe(uprobe); - - /* TODO : cant unregister? schedule a worker thread */ -} - -/* - * uprobe_register - register a probe - * @inode: the file in which the probe has to be placed. - * @offset: offset from the start of the file. - * @consumer: information on howto handle the probe.. - * - * Apart from the access refcount, uprobe_register() takes a creation - * refcount (thro alloc_uprobe) if and only if this @uprobe is getting - * inserted into the rbtree (i.e first consumer for a @inode:@offset - * tuple). Creation refcount stops uprobe_unregister from freeing the - * @uprobe even before the register operation is complete. Creation - * refcount is released when the last @consumer for the @uprobe - * unregisters. - * - * Return errno if it cannot successully install probes - * else return 0 (success) - */ -int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *consumer) -{ - struct uprobe *uprobe; - int ret; - - if (!inode || !consumer || consumer->next) - return -EINVAL; - - if (offset > i_size_read(inode)) - return -EINVAL; - - ret = 0; - mutex_lock(uprobes_hash(inode)); - uprobe = alloc_uprobe(inode, offset); - - if (uprobe && !consumer_add(uprobe, consumer)) { - ret = __uprobe_register(uprobe); - if (ret) { - uprobe->consumers = NULL; - __uprobe_unregister(uprobe); - } else { - uprobe->flags |= UPROBES_RUN_HANDLER; - } - } - - mutex_unlock(uprobes_hash(inode)); - put_uprobe(uprobe); - - return ret; -} - -/* - * uprobe_unregister - unregister a already registered probe. - * @inode: the file in which the probe has to be removed. - * @offset: offset from the start of the file. - * @consumer: identify which probe if multiple probes are colocated. - */ -void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *consumer) -{ - struct uprobe *uprobe; - - if (!inode || !consumer) - return; - - uprobe = find_uprobe(inode, offset); - if (!uprobe) - return; - - mutex_lock(uprobes_hash(inode)); - - if (consumer_del(uprobe, consumer)) { - if (!uprobe->consumers) { - __uprobe_unregister(uprobe); - uprobe->flags &= ~UPROBES_RUN_HANDLER; - } - } - - mutex_unlock(uprobes_hash(inode)); - if (uprobe) - put_uprobe(uprobe); -} - -/* - * Of all the nodes that correspond to the given inode, return the node - * with the least offset. - */ -static struct rb_node *find_least_offset_node(struct inode *inode) -{ - struct uprobe u = { .inode = inode, .offset = 0}; - struct rb_node *n = uprobes_tree.rb_node; - struct rb_node *close_node = NULL; - struct uprobe *uprobe; - int match; - - while (n) { - uprobe = rb_entry(n, struct uprobe, rb_node); - match = match_uprobe(&u, uprobe); - - if (uprobe->inode == inode) - close_node = n; - - if (!match) - return close_node; - - if (match < 0) - n = n->rb_left; - else - n = n->rb_right; - } - - return close_node; -} - -/* - * For a given inode, build a list of probes that need to be inserted. - */ -static void build_probe_list(struct inode *inode, struct list_head *head) -{ - struct uprobe *uprobe; - unsigned long flags; - struct rb_node *n; - - spin_lock_irqsave(&uprobes_treelock, flags); - - n = find_least_offset_node(inode); - - for (; n; n = rb_next(n)) { - uprobe = rb_entry(n, struct uprobe, rb_node); - if (uprobe->inode != inode) - break; - - list_add(&uprobe->pending_list, head); - atomic_inc(&uprobe->ref); - } - - spin_unlock_irqrestore(&uprobes_treelock, flags); -} - -/* - * Called from mmap_region. - * called with mm->mmap_sem acquired. - * - * Return -ve no if we fail to insert probes and we cannot - * bail-out. - * Return 0 otherwise. i.e: - * - * - successful insertion of probes - * - (or) no possible probes to be inserted. - * - (or) insertion of probes failed but we can bail-out. - */ -int uprobe_mmap(struct vm_area_struct *vma) -{ - struct list_head tmp_list; - struct uprobe *uprobe, *u; - struct inode *inode; - int ret; - - if (!atomic_read(&uprobe_events) || !valid_vma(vma, true)) - return 0; - - inode = vma->vm_file->f_mapping->host; - if (!inode) - return 0; - - INIT_LIST_HEAD(&tmp_list); - mutex_lock(uprobes_mmap_hash(inode)); - build_probe_list(inode, &tmp_list); - - ret = 0; - - list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) { - loff_t vaddr; - - list_del(&uprobe->pending_list); - if (!ret) { - vaddr = vma_address(vma, uprobe->offset); - if (vaddr >= vma->vm_start && vaddr < vma->vm_end) { - ret = install_breakpoint(vma->vm_mm, uprobe, vma, vaddr); - /* Ignore double add: */ - if (ret == -EEXIST) - ret = 0; - } - } - put_uprobe(uprobe); - } - - mutex_unlock(uprobes_mmap_hash(inode)); - - return ret; -} - -static int __init init_uprobes(void) -{ - int i; - - for (i = 0; i < UPROBES_HASH_SZ; i++) { - mutex_init(&uprobes_mutex[i]); - mutex_init(&uprobes_mmap_mutex[i]); - } - return 0; -} - -static void __exit exit_uprobes(void) -{ -} - -module_init(init_uprobes); -module_exit(exit_uprobes); -- cgit v1.2.3-70-g09d2 From f3f096cfedf8113380c56fc855275cc75cd8cf55 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Wed, 11 Apr 2012 16:00:43 +0530 Subject: tracing: Provide trace events interface for uprobes Implements trace_event support for uprobes. In its current form it can be used to put probes at a specified offset in a file and dump the required registers when the code flow reaches the probed address. 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 zfree in /bin/zsh: # cd /sys/kernel/debug/tracing/ # 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 # echo 'p /bin/zsh:0x46420 %ip %ax' > uprobe_events # cat uprobe_events p:uprobes/p_zsh_0x46420 /bin/zsh:0x0000000000046420 # echo 1 > events/uprobes/enable # sleep 20 # echo 0 > events/uprobes/enable # cat trace # tracer: nop # # 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 Signed-off-by: Srikar Dronamraju Acked-by: Steven Rostedt Acked-by: Masami Hiramatsu Cc: Linus Torvalds Cc: Ananth N Mavinakayanahalli Cc: Jim Keniston Cc: Linux-mm Cc: Oleg Nesterov Cc: Andi Kleen Cc: Christoph Hellwig Cc: Arnaldo Carvalho de Melo Cc: Anton Arapov Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120411103043.GB29437@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- Documentation/trace/uprobetracer.txt | 95 +++++ arch/Kconfig | 2 +- kernel/trace/Kconfig | 16 + kernel/trace/Makefile | 1 + kernel/trace/trace.h | 5 + kernel/trace/trace_kprobe.c | 2 +- kernel/trace/trace_probe.c | 14 +- kernel/trace/trace_probe.h | 3 +- kernel/trace/trace_uprobe.c | 788 +++++++++++++++++++++++++++++++++++ 9 files changed, 919 insertions(+), 7 deletions(-) create mode 100644 Documentation/trace/uprobetracer.txt create mode 100644 kernel/trace/trace_uprobe.c (limited to 'arch/Kconfig') diff --git a/Documentation/trace/uprobetracer.txt b/Documentation/trace/uprobetracer.txt new file mode 100644 index 00000000000..eae40a003ee --- /dev/null +++ b/Documentation/trace/uprobetracer.txt @@ -0,0 +1,95 @@ + Uprobe-tracer: Uprobe-based Event Tracing + ========================================= + Documentation written by Srikar Dronamraju + +Overview +-------- +Uprobe based trace events are similar to kprobe based trace events. +To enable this feature, build your kernel with CONFIG_UPROBE_EVENTS=y. + +Similar to the kprobe-event tracer, this doesn't need to be activated via +current_tracer. Instead of that, add probe points via +/sys/kernel/debug/tracing/uprobe_events, and enable it 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 + +Synopsis of uprobe_tracer +------------------------- + p[:[GRP/]EVENT] PATH:SYMBOL[+offs] [FETCHARGS] : Set a probe + + 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. + + 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 +/sys/kernel/debug/tracing/uprobe_profile. + 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. + + 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 + + echo > /sys/kernel/debug/tracing/uprobe_events + + This clears all probe points. + +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 + + # cd /sys/kernel/debug/tracing/ + # 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 : + + # echo 'p /bin/zsh:0x46420 %ip %ax' > uprobe_events + +Please note: User has to explicitly calculate the offset of the probepoint +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:0x0000000000046420 + +Right after definition, each event is disabled by default. For tracing these +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 + +And you can see the traced information via /sys/kernel/debug/tracing/trace. + + # cat trace + # tracer: nop + # + # 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 + +Each line shows us probes were triggered for a pid 24842 with ip being +0x446421 and contents of ax register being 79. diff --git a/arch/Kconfig b/arch/Kconfig index e5d3778d555..0f8f968015e 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -78,7 +78,7 @@ config OPTPROBES config UPROBES bool "Transparent user-space probes (EXPERIMENTAL)" - depends on ARCH_SUPPORTS_UPROBES && PERF_EVENTS + depends on UPROBE_EVENTS && PERF_EVENTS default n help Uprobes is the user-space counterpart to kprobes: they diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index ce5a5c54ac8..ea4bff6295f 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -386,6 +386,22 @@ config KPROBE_EVENT This option is also required by perf-probe subcommand of perf tools. If you want to use perf tools, this option is strongly recommended. +config UPROBE_EVENT + bool "Enable uprobes-based dynamic events" + depends on ARCH_SUPPORTS_UPROBES + depends on MMU + select UPROBES + select PROBE_EVENTS + select TRACING + default n + help + This allows the user to add tracing events on top of userspace + dynamic events (similar to tracepoints) on the fly via the trace + events interface. Those events can be inserted wherever uprobes + can probe, and record various registers. + This option is required if you plan to use perf-probe subcommand + of perf tools on user space applications. + config PROBE_EVENTS def_bool n diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index fa10d5ca5ab..1734c03e048 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -62,5 +62,6 @@ ifeq ($(CONFIG_TRACING),y) obj-$(CONFIG_KGDB_KDB) += trace_kdb.o endif obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o +obj-$(CONFIG_UPROBE_EVENT) += trace_uprobe.o libftrace-y := ftrace.o diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 95059f091a2..1bcdbec95a1 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -103,6 +103,11 @@ struct kretprobe_trace_entry_head { unsigned long ret_ip; }; +struct uprobe_trace_entry_head { + struct trace_entry ent; + unsigned long ip; +}; + /* * trace_flag_type is an enumeration that holds different * states when a trace occurs. These are: diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index f8b777367d8..b31d3d5699f 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -525,7 +525,7 @@ static int create_trace_probe(int argc, char **argv) /* Parse fetch argument */ ret = traceprobe_parse_probe_arg(arg, &tp->size, &tp->args[i], - is_return); + is_return, true); if (ret) { pr_info("Parse error at argument[%d]. (%d)\n", i, ret); goto error; diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 8e526b9286e..daa9980153a 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -550,7 +550,7 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t, /* Recursive argument parser */ static int parse_probe_arg(char *arg, const struct fetch_type *t, - struct fetch_param *f, bool is_return) + struct fetch_param *f, bool is_return, bool is_kprobe) { unsigned long param; long offset; @@ -558,6 +558,11 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t, int ret; ret = 0; + + /* Until uprobe_events supports only reg arguments */ + if (!is_kprobe && arg[0] != '%') + return -EINVAL; + switch (arg[0]) { case '$': ret = parse_probe_vars(arg + 1, t, f, is_return); @@ -619,7 +624,8 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t, return -ENOMEM; dprm->offset = offset; - ret = parse_probe_arg(arg, t2, &dprm->orig, is_return); + ret = parse_probe_arg(arg, t2, &dprm->orig, is_return, + is_kprobe); if (ret) kfree(dprm); else { @@ -677,7 +683,7 @@ static int __parse_bitfield_probe_arg(const char *bf, /* String length checking wrapper */ int traceprobe_parse_probe_arg(char *arg, ssize_t *size, - struct probe_arg *parg, bool is_return) + struct probe_arg *parg, bool is_return, bool is_kprobe) { const char *t; int ret; @@ -703,7 +709,7 @@ int traceprobe_parse_probe_arg(char *arg, ssize_t *size, } parg->offset = *size; *size += parg->type->size; - ret = parse_probe_arg(arg, parg->type, &parg->fetch, is_return); + ret = parse_probe_arg(arg, parg->type, &parg->fetch, is_return, is_kprobe); if (ret >= 0 && t != NULL) ret = __parse_bitfield_probe_arg(t, parg->type, &parg->fetch); diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 2df9a18e025..93370867781 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -66,6 +66,7 @@ #define TP_FLAG_TRACE 1 #define TP_FLAG_PROFILE 2 #define TP_FLAG_REGISTERED 4 +#define TP_FLAG_UPROBE 8 /* data_rloc: data relative location, compatible with u32 */ @@ -143,7 +144,7 @@ static inline int is_good_name(const char *name) } extern int traceprobe_parse_probe_arg(char *arg, ssize_t *size, - struct probe_arg *parg, bool is_return); + struct probe_arg *parg, bool is_return, bool is_kprobe); extern int traceprobe_conflict_field_name(const char *name, struct probe_arg *args, int narg); diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c new file mode 100644 index 00000000000..2b36ac68549 --- /dev/null +++ b/kernel/trace/trace_uprobe.c @@ -0,0 +1,788 @@ +/* + * uprobes-based tracing events + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Copyright (C) IBM Corporation, 2010-2012 + * Author: Srikar Dronamraju + */ + +#include +#include +#include +#include + +#include "trace_probe.h" + +#define UPROBE_EVENT_SYSTEM "uprobes" + +/* + * uprobe event core functions + */ +struct trace_uprobe; +struct uprobe_trace_consumer { + struct uprobe_consumer cons; + struct trace_uprobe *tu; +}; + +struct trace_uprobe { + struct list_head list; + struct ftrace_event_class class; + struct ftrace_event_call call; + struct uprobe_trace_consumer *consumer; + struct inode *inode; + char *filename; + unsigned long offset; + unsigned long nhit; + unsigned int flags; /* For TP_FLAG_* */ + ssize_t size; /* trace entry size */ + unsigned int nr_args; + struct probe_arg args[]; +}; + +#define SIZEOF_TRACE_UPROBE(n) \ + (offsetof(struct trace_uprobe, args) + \ + (sizeof(struct probe_arg) * (n))) + +static int register_uprobe_event(struct trace_uprobe *tu); +static void unregister_uprobe_event(struct trace_uprobe *tu); + +static DEFINE_MUTEX(uprobe_lock); +static LIST_HEAD(uprobe_list); + +static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs); + +/* + * Allocate new trace_uprobe and initialize it (including uprobes). + */ +static struct trace_uprobe * +alloc_trace_uprobe(const char *group, const char *event, int nargs) +{ + struct trace_uprobe *tu; + + if (!event || !is_good_name(event)) + return ERR_PTR(-EINVAL); + + if (!group || !is_good_name(group)) + return ERR_PTR(-EINVAL); + + tu = kzalloc(SIZEOF_TRACE_UPROBE(nargs), GFP_KERNEL); + if (!tu) + return ERR_PTR(-ENOMEM); + + tu->call.class = &tu->class; + tu->call.name = kstrdup(event, GFP_KERNEL); + if (!tu->call.name) + goto error; + + tu->class.system = kstrdup(group, GFP_KERNEL); + if (!tu->class.system) + goto error; + + INIT_LIST_HEAD(&tu->list); + return tu; + +error: + kfree(tu->call.name); + kfree(tu); + + return ERR_PTR(-ENOMEM); +} + +static void free_trace_uprobe(struct trace_uprobe *tu) +{ + int i; + + for (i = 0; i < tu->nr_args; i++) + traceprobe_free_probe_arg(&tu->args[i]); + + iput(tu->inode); + kfree(tu->call.class->system); + kfree(tu->call.name); + kfree(tu->filename); + kfree(tu); +} + +static struct trace_uprobe *find_probe_event(const char *event, const char *group) +{ + struct trace_uprobe *tu; + + list_for_each_entry(tu, &uprobe_list, list) + if (strcmp(tu->call.name, event) == 0 && + strcmp(tu->call.class->system, group) == 0) + return tu; + + return NULL; +} + +/* Unregister a trace_uprobe and probe_event: call with locking uprobe_lock */ +static void unregister_trace_uprobe(struct trace_uprobe *tu) +{ + list_del(&tu->list); + unregister_uprobe_event(tu); + free_trace_uprobe(tu); +} + +/* Register a trace_uprobe and probe_event */ +static int register_trace_uprobe(struct trace_uprobe *tu) +{ + struct trace_uprobe *old_tp; + int ret; + + mutex_lock(&uprobe_lock); + + /* register as an event */ + old_tp = find_probe_event(tu->call.name, tu->call.class->system); + if (old_tp) + /* delete old event */ + unregister_trace_uprobe(old_tp); + + ret = register_uprobe_event(tu); + if (ret) { + pr_warning("Failed to register probe event(%d)\n", ret); + goto end; + } + + list_add_tail(&tu->list, &uprobe_list); + +end: + mutex_unlock(&uprobe_lock); + + return ret; +} + +/* + * Argument syntax: + * - Add uprobe: p[:[GRP/]EVENT] PATH:SYMBOL[+offs] [FETCHARGS] + * + * - Remove uprobe: -:[GRP/]EVENT + */ +static int create_trace_uprobe(int argc, char **argv) +{ + struct trace_uprobe *tu; + struct inode *inode; + char *arg, *event, *group, *filename; + char buf[MAX_EVENT_NAME_LEN]; + struct path path; + unsigned long offset; + bool is_delete; + int i, ret; + + inode = NULL; + ret = 0; + is_delete = false; + event = NULL; + group = NULL; + + /* argc must be >= 1 */ + if (argv[0][0] == '-') + is_delete = true; + else if (argv[0][0] != 'p') { + pr_info("Probe definition must be started with 'p', 'r' or" " '-'.\n"); + return -EINVAL; + } + + if (argv[0][1] == ':') { + event = &argv[0][2]; + arg = strchr(event, '/'); + + if (arg) { + group = event; + event = arg + 1; + event[-1] = '\0'; + + if (strlen(group) == 0) { + pr_info("Group name is not specified\n"); + return -EINVAL; + } + } + if (strlen(event) == 0) { + pr_info("Event name is not specified\n"); + return -EINVAL; + } + } + if (!group) + group = UPROBE_EVENT_SYSTEM; + + if (is_delete) { + if (!event) { + pr_info("Delete command needs an event name.\n"); + return -EINVAL; + } + mutex_lock(&uprobe_lock); + tu = find_probe_event(event, group); + + if (!tu) { + mutex_unlock(&uprobe_lock); + pr_info("Event %s/%s doesn't exist.\n", group, event); + return -ENOENT; + } + /* delete an event */ + unregister_trace_uprobe(tu); + mutex_unlock(&uprobe_lock); + return 0; + } + + if (argc < 2) { + pr_info("Probe point is not specified.\n"); + return -EINVAL; + } + if (isdigit(argv[1][0])) { + pr_info("probe point must be have a filename.\n"); + return -EINVAL; + } + arg = strchr(argv[1], ':'); + if (!arg) + goto fail_address_parse; + + *arg++ = '\0'; + filename = argv[1]; + ret = kern_path(filename, LOOKUP_FOLLOW, &path); + if (ret) + goto fail_address_parse; + + ret = strict_strtoul(arg, 0, &offset); + if (ret) + goto fail_address_parse; + + inode = igrab(path.dentry->d_inode); + + argc -= 2; + argv += 2; + + /* setup a probe */ + if (!event) { + char *tail = strrchr(filename, '/'); + char *ptr; + + ptr = kstrdup((tail ? tail + 1 : filename), GFP_KERNEL); + if (!ptr) { + ret = -ENOMEM; + goto fail_address_parse; + } + + tail = ptr; + ptr = strpbrk(tail, ".-_"); + if (ptr) + *ptr = '\0'; + + snprintf(buf, MAX_EVENT_NAME_LEN, "%c_%s_0x%lx", 'p', tail, offset); + event = buf; + kfree(tail); + } + + tu = alloc_trace_uprobe(group, event, argc); + if (IS_ERR(tu)) { + pr_info("Failed to allocate trace_uprobe.(%d)\n", (int)PTR_ERR(tu)); + ret = PTR_ERR(tu); + goto fail_address_parse; + } + tu->offset = offset; + tu->inode = inode; + tu->filename = kstrdup(filename, GFP_KERNEL); + + if (!tu->filename) { + pr_info("Failed to allocate filename.\n"); + ret = -ENOMEM; + goto error; + } + + /* parse arguments */ + ret = 0; + for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) { + /* Increment count for freeing args in error case */ + tu->nr_args++; + + /* Parse argument name */ + arg = strchr(argv[i], '='); + if (arg) { + *arg++ = '\0'; + tu->args[i].name = kstrdup(argv[i], GFP_KERNEL); + } else { + arg = argv[i]; + /* If argument name is omitted, set "argN" */ + snprintf(buf, MAX_EVENT_NAME_LEN, "arg%d", i + 1); + tu->args[i].name = kstrdup(buf, GFP_KERNEL); + } + + if (!tu->args[i].name) { + pr_info("Failed to allocate argument[%d] name.\n", i); + ret = -ENOMEM; + goto error; + } + + if (!is_good_name(tu->args[i].name)) { + pr_info("Invalid argument[%d] name: %s\n", i, tu->args[i].name); + ret = -EINVAL; + goto error; + } + + if (traceprobe_conflict_field_name(tu->args[i].name, tu->args, i)) { + pr_info("Argument[%d] name '%s' conflicts with " + "another field.\n", i, argv[i]); + ret = -EINVAL; + goto error; + } + + /* Parse fetch argument */ + ret = traceprobe_parse_probe_arg(arg, &tu->size, &tu->args[i], false, false); + if (ret) { + pr_info("Parse error at argument[%d]. (%d)\n", i, ret); + goto error; + } + } + + ret = register_trace_uprobe(tu); + if (ret) + goto error; + return 0; + +error: + free_trace_uprobe(tu); + return ret; + +fail_address_parse: + if (inode) + iput(inode); + + pr_info("Failed to parse address.\n"); + + return ret; +} + +static void cleanup_all_probes(void) +{ + struct trace_uprobe *tu; + + mutex_lock(&uprobe_lock); + while (!list_empty(&uprobe_list)) { + tu = list_entry(uprobe_list.next, struct trace_uprobe, list); + unregister_trace_uprobe(tu); + } + mutex_unlock(&uprobe_lock); +} + +/* Probes listing interfaces */ +static void *probes_seq_start(struct seq_file *m, loff_t *pos) +{ + mutex_lock(&uprobe_lock); + return seq_list_start(&uprobe_list, *pos); +} + +static void *probes_seq_next(struct seq_file *m, void *v, loff_t *pos) +{ + return seq_list_next(v, &uprobe_list, pos); +} + +static void probes_seq_stop(struct seq_file *m, void *v) +{ + mutex_unlock(&uprobe_lock); +} + +static int probes_seq_show(struct seq_file *m, void *v) +{ + struct trace_uprobe *tu = v; + int i; + + seq_printf(m, "p:%s/%s", 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++) + seq_printf(m, " %s=%s", tu->args[i].name, tu->args[i].comm); + + seq_printf(m, "\n"); + return 0; +} + +static const struct seq_operations probes_seq_op = { + .start = probes_seq_start, + .next = probes_seq_next, + .stop = probes_seq_stop, + .show = probes_seq_show +}; + +static int probes_open(struct inode *inode, struct file *file) +{ + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) + cleanup_all_probes(); + + return seq_open(file, &probes_seq_op); +} + +static ssize_t probes_write(struct file *file, const char __user *buffer, + size_t count, loff_t *ppos) +{ + return traceprobe_probes_write(file, buffer, count, ppos, create_trace_uprobe); +} + +static const struct file_operations uprobe_events_ops = { + .owner = THIS_MODULE, + .open = probes_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, + .write = probes_write, +}; + +/* Probes profiling interfaces */ +static int probes_profile_seq_show(struct seq_file *m, void *v) +{ + struct trace_uprobe *tu = v; + + seq_printf(m, " %s %-44s %15lu\n", tu->filename, tu->call.name, tu->nhit); + return 0; +} + +static const struct seq_operations profile_seq_op = { + .start = probes_seq_start, + .next = probes_seq_next, + .stop = probes_seq_stop, + .show = probes_profile_seq_show +}; + +static int profile_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &profile_seq_op); +} + +static const struct file_operations uprobe_profile_ops = { + .owner = THIS_MODULE, + .open = profile_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +/* uprobe handler */ +static void uprobe_trace_func(struct trace_uprobe *tu, 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; + struct ftrace_event_call *call = &tu->call; + + tu->nhit++; + + local_save_flags(irq_flags); + pc = preempt_count(); + + size = sizeof(*entry) + tu->size; + + event = trace_current_buffer_lock_reserve(&buffer, call->event.type, + size, irq_flags, pc); + if (!event) + return; + + entry = ring_buffer_event_data(event); + entry->ip = uprobe_get_swbp_addr(task_pt_regs(current)); + data = (u8 *)&entry[1]; + 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); +} + +/* 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 trace_seq *s = &iter->seq; + struct trace_uprobe *tu; + u8 *data; + int i; + + field = (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 (!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)) + goto partial; + } + + if (trace_seq_puts(s, "\n")) + return TRACE_TYPE_HANDLED; + +partial: + return TRACE_TYPE_PARTIAL_LINE; +} + +static int probe_event_enable(struct trace_uprobe *tu, int flag) +{ + struct uprobe_trace_consumer *utc; + int ret = 0; + + if (!tu->inode || tu->consumer) + return -EINTR; + + utc = kzalloc(sizeof(struct uprobe_trace_consumer), GFP_KERNEL); + if (!utc) + return -EINTR; + + utc->cons.handler = uprobe_dispatcher; + utc->cons.filter = NULL; + ret = uprobe_register(tu->inode, tu->offset, &utc->cons); + if (ret) { + kfree(utc); + return ret; + } + + tu->flags |= flag; + utc->tu = tu; + tu->consumer = utc; + + return 0; +} + +static void probe_event_disable(struct trace_uprobe *tu, int flag) +{ + if (!tu->inode || !tu->consumer) + return; + + uprobe_unregister(tu->inode, tu->offset, &tu->consumer->cons); + tu->flags &= ~flag; + kfree(tu->consumer); + tu->consumer = NULL; +} + +static int uprobe_event_define_fields(struct ftrace_event_call *event_call) +{ + int ret, i; + struct uprobe_trace_entry_head field; + struct trace_uprobe *tu = (struct trace_uprobe *)event_call->data; + + DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0); + /* 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, + tu->args[i].type->size, + tu->args[i].type->is_signed, + FILTER_OTHER); + + if (ret) + return ret; + } + return 0; +} + +#define LEN_OR_ZERO (len ? len - pos : 0) +static int __set_print_fmt(struct trace_uprobe *tu, char *buf, int len) +{ + const char *fmt, *arg; + int i; + int pos = 0; + + fmt = "(%lx)"; + arg = "REC->" FIELD_STRING_IP; + + /* When len=0, we just calculate the needed length */ + + pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt); + + for (i = 0; i < tu->nr_args; i++) { + pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%s", + tu->args[i].name, tu->args[i].type->fmt); + } + + pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg); + + for (i = 0; i < tu->nr_args; i++) { + pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s", + tu->args[i].name); + } + + return pos; /* return the length of print_fmt */ +} +#undef LEN_OR_ZERO + +static int set_print_fmt(struct trace_uprobe *tu) +{ + char *print_fmt; + int len; + + /* First: called with 0 length to calculate the needed length */ + len = __set_print_fmt(tu, NULL, 0); + print_fmt = kmalloc(len + 1, GFP_KERNEL); + if (!print_fmt) + return -ENOMEM; + + /* Second: actually write the @print_fmt */ + __set_print_fmt(tu, print_fmt, len + 1); + tu->call.print_fmt = print_fmt; + + return 0; +} + +#ifdef CONFIG_PERF_EVENTS +/* uprobe profile handler */ +static void uprobe_perf_func(struct trace_uprobe *tu, 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; + + __size = sizeof(*entry) + tu->size; + size = ALIGN(__size + sizeof(u32), sizeof(u64)); + size -= sizeof(u32); + if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough")) + return; + + preempt_disable(); + + entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx); + if (!entry) + goto out; + + entry->ip = uprobe_get_swbp_addr(task_pt_regs(current)); + data = (u8 *)&entry[1]; + 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); + + out: + preempt_enable(); +} +#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; + + switch (type) { + case TRACE_REG_REGISTER: + return probe_event_enable(tu, TP_FLAG_TRACE); + + case TRACE_REG_UNREGISTER: + probe_event_disable(tu, TP_FLAG_TRACE); + return 0; + +#ifdef CONFIG_PERF_EVENTS + case TRACE_REG_PERF_REGISTER: + return probe_event_enable(tu, TP_FLAG_PROFILE); + + case TRACE_REG_PERF_UNREGISTER: + probe_event_disable(tu, TP_FLAG_PROFILE); + return 0; +#endif + default: + return 0; + } + return 0; +} + +static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) +{ + struct uprobe_trace_consumer *utc; + struct trace_uprobe *tu; + + utc = container_of(con, struct uprobe_trace_consumer, cons); + tu = utc->tu; + if (!tu || tu->consumer != utc) + return 0; + + if (tu->flags & TP_FLAG_TRACE) + uprobe_trace_func(tu, regs); + +#ifdef CONFIG_PERF_EVENTS + if (tu->flags & TP_FLAG_PROFILE) + uprobe_perf_func(tu, regs); +#endif + return 0; +} + +static struct trace_event_functions uprobe_funcs = { + .trace = print_uprobe_event +}; + +static int register_uprobe_event(struct trace_uprobe *tu) +{ + struct ftrace_event_call *call = &tu->call; + int ret; + + /* Initialize ftrace_event_call */ + INIT_LIST_HEAD(&call->class->fields); + call->event.funcs = &uprobe_funcs; + call->class->define_fields = uprobe_event_define_fields; + + if (set_print_fmt(tu) < 0) + return -ENOMEM; + + ret = register_ftrace_event(&call->event); + if (!ret) { + kfree(call->print_fmt); + return -ENODEV; + } + call->flags = 0; + call->class->reg = trace_uprobe_register; + call->data = tu; + ret = trace_add_event_call(call); + + if (ret) { + pr_info("Failed to register uprobe event: %s\n", call->name); + kfree(call->print_fmt); + unregister_ftrace_event(&call->event); + } + + return ret; +} + +static void unregister_uprobe_event(struct trace_uprobe *tu) +{ + /* tu->event is unregistered in trace_remove_event_call() */ + trace_remove_event_call(&tu->call); + kfree(tu->call.print_fmt); + tu->call.print_fmt = NULL; +} + +/* Make a trace interface for controling probe points */ +static __init int init_uprobe_trace(void) +{ + struct dentry *d_tracer; + + d_tracer = tracing_init_dentry(); + if (!d_tracer) + return 0; + + trace_create_file("uprobe_events", 0644, d_tracer, + NULL, &uprobe_events_ops); + /* Profile interface */ + trace_create_file("uprobe_profile", 0444, d_tracer, + NULL, &uprobe_profile_ops); + return 0; +} + +fs_initcall(init_uprobe_trace); -- cgit v1.2.3-70-g09d2 From ec83db0f78cd44c3b586ec1c3a348d1a8a389797 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Tue, 8 May 2012 16:41:26 +0530 Subject: tracing: Fix kconfig warning due to a typo Commit f3f096cfe ("tracing: Provide trace events interface for uprobes") throws a warning about unmet dependencies. The exact warning message is: warning: (UPROBE_EVENT) selects UPROBES which has unmet direct dependencies (UPROBE_EVENTS && PERF_EVENTS) This is due to a typo in arch/Kconfig file. Fix similar typos in the uprobetracer documentation. Also add sample format of a uprobe event in the uprobetracer documentation as suggested by Masami Hiramatsu. Reported-by: Stephen Boyd Reported-by: Ingo Molnar Signed-off-by: Srikar Dronamraju Cc: Linus Torvalds Cc: Ananth N Mavinakayanahalli Cc: Oleg Nesterov Cc: Christoph Hellwig Cc: Steven Rostedt Cc: Arnaldo Carvalho de Melo Cc: Masami Hiramatsu Cc: Anton Arapov Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120508111126.21004.38285.sendpatchset@srdronam.in.ibm.com Signed-off-by: Ingo Molnar --- Documentation/trace/uprobetracer.txt | 22 ++++++++++++++++++++-- arch/Kconfig | 2 +- 2 files changed, 21 insertions(+), 3 deletions(-) (limited to 'arch/Kconfig') diff --git a/Documentation/trace/uprobetracer.txt b/Documentation/trace/uprobetracer.txt index eae40a003ee..24ce6823a09 100644 --- a/Documentation/trace/uprobetracer.txt +++ b/Documentation/trace/uprobetracer.txt @@ -5,7 +5,7 @@ Overview -------- Uprobe based trace events are similar to kprobe based trace events. -To enable this feature, build your kernel with CONFIG_UPROBE_EVENTS=y. +To enable this feature, build your kernel with CONFIG_UPROBE_EVENT=y. Similar to the kprobe-event tracer, this doesn't need to be activated via current_tracer. Instead of that, add probe points via @@ -68,7 +68,25 @@ 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:0x0000000000046420 + p:uprobes/p_zsh_0x46420 /bin/zsh:0x00046420 arg1=%ip arg2=%ax + +The format of events can be seen by viewing the file events/uprobes/p_zsh_0x46420/format + + # cat events/uprobes/p_zsh_0x46420/format + name: p_zsh_0x46420 + 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 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 Right after definition, each event is disabled by default. For tracing these events, you need to enable it by: diff --git a/arch/Kconfig b/arch/Kconfig index 0f8f968015e..2880abf8a26 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -78,7 +78,7 @@ config OPTPROBES config UPROBES bool "Transparent user-space probes (EXPERIMENTAL)" - depends on UPROBE_EVENTS && PERF_EVENTS + depends on UPROBE_EVENT && PERF_EVENTS default n help Uprobes is the user-space counterpart to kprobes: they -- cgit v1.2.3-70-g09d2