Something went wrong. Try again.
Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
Something went wrong. Try again.
12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021202220232024202520262027202820292030// SPDX-License-Identifier: GPL-2.0-only/* * linux/fs/exec.c * * Copyright (C) 1991, 1992 Linus Torvalds */
/* * #!-checking implemented by tytso. *//* * Demand-loading implemented 01.12.91 - no need to read anything but * the header into memory. The inode of the executable is put into * "current->executable", and page faults do the actual loading. Clean. * * Once more I can proudly say that linux stood up to being changed: it * was less than 2 hours work to get demand-loading completely implemented. * * Demand loading changed July 1993 by Eric Youngdale. Use mmap instead, * current->executable is only used by the procfs. This allows a dispatch * table to check for several different types of binary formats. We keep * trying until we recognize the file or we run out of supported binary * formats. */
#include <linux/kernel_read_file.h>#include <linux/slab.h>#include <linux/file.h>#include <linux/fdtable.h>#include <linux/mm.h>#include <linux/stat.h>#include <linux/fcntl.h>#include <linux/swap.h>#include <linux/string.h>#include <linux/init.h>#include <linux/sched/mm.h>#include <linux/sched/coredump.h>#include <linux/sched/exec_state.h>#include <linux/sched/signal.h>#include <linux/sched/numa_balancing.h>#include <linux/sched/task.h>#include <linux/pagemap.h>#include <linux/perf_event.h>#include <linux/highmem.h>#include <linux/spinlock.h>#include <linux/key.h>#include <linux/personality.h>#include <linux/binfmts.h>#include <linux/utsname.h>#include <linux/pid_namespace.h>#include <linux/module.h>#include <linux/namei.h>#include <linux/mount.h>#include <linux/security.h>#include <linux/syscalls.h>#include <linux/tsacct_kern.h>#include <linux/cn_proc.h>#include <linux/audit.h>#include <linux/kmod.h>#include <linux/fsnotify.h>#include <linux/fs_struct.h>#include <linux/oom.h>#include <linux/compat.h>#include <linux/vmalloc.h>#include <linux/io_uring.h>#include <linux/syscall_user_dispatch.h>#include <linux/coredump.h>#include <linux/time_namespace.h>#include <linux/user_events.h>#include <linux/rseq.h>#include <linux/ksm.h>
#include <linux/uaccess.h>#include <asm/mmu_context.h>#include <asm/tlb.h>
#include <trace/events/task.h>#include "internal.h"
#include <trace/events/sched.h>
/* For vma exec functions. */#include "../mm/internal.h"
static int bprm_creds_from_file(struct linux_binprm *bprm);
int suid_dumpable = 0;
static LIST_HEAD(formats);static DEFINE_RWLOCK(binfmt_lock);
void __register_binfmt(struct linux_binfmt * fmt, int insert){ write_lock(&binfmt_lock); insert ? list_add(&fmt->lh, &formats) : list_add_tail(&fmt->lh, &formats); write_unlock(&binfmt_lock);}
EXPORT_SYMBOL(__register_binfmt);
void unregister_binfmt(struct linux_binfmt * fmt){ write_lock(&binfmt_lock); list_del(&fmt->lh); write_unlock(&binfmt_lock);}
EXPORT_SYMBOL(unregister_binfmt);
static inline void put_binfmt(struct linux_binfmt * fmt){ module_put(fmt->module);}
bool path_noexec(const struct path *path){ /* If it's an anonymous inode make sure that we catch any shenanigans. */ VFS_WARN_ON_ONCE(IS_ANON_FILE(d_inode(path->dentry)) && !(path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC)); return (path->mnt->mnt_flags & MNT_NOEXEC) || (path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC);}
#ifdef CONFIG_MMU/* * The nascent bprm->mm is not visible until exec_mmap() but it can * use a lot of memory, account these pages in current->mm temporary * for oom_badness()->get_mm_rss(). Once exec succeeds or fails, we * change the counter back via acct_arg_size(0). */static void acct_arg_size(struct linux_binprm *bprm, unsigned long pages){ struct mm_struct *mm = current->mm; long diff = (long)(pages - bprm->vma_pages);
if (!mm || !diff) return;
bprm->vma_pages = pages; add_mm_counter(mm, MM_ANONPAGES, diff);}
static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, int write){ struct page *page; struct vm_area_struct *vma = bprm->vma; struct mm_struct *mm = bprm->mm; int ret;
/* * Avoid relying on expanding the stack down in GUP (which * does not work for STACK_GROWSUP anyway), and just do it * ahead of time. */ if (!mmap_read_lock_maybe_expand(mm, vma, pos, write)) return NULL;
/* * We are doing an exec(). 'current' is the process * doing the exec and 'mm' is the new process's mm. */ ret = get_user_pages_remote(mm, pos, 1, write ? FOLL_WRITE : 0, &page, NULL); mmap_read_unlock(mm); if (ret <= 0) return NULL;
if (write) acct_arg_size(bprm, vma_pages(vma));
return page;}
static void put_arg_page(struct page *page){ put_page(page);}
static void free_arg_pages(struct linux_binprm *bprm){}
static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos, struct page *page){ flush_cache_page(bprm->vma, pos, page_to_pfn(page));}
static bool valid_arg_len(struct linux_binprm *bprm, long len){ return len <= MAX_ARG_STRLEN;}
#else
static inline void acct_arg_size(struct linux_binprm *bprm, unsigned long pages){}
static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, int write){ struct page *page;
page = bprm->page[pos / PAGE_SIZE]; if (!page && write) { page = alloc_page(GFP_HIGHUSER|__GFP_ZERO); if (!page) return NULL; bprm->page[pos / PAGE_SIZE] = page; }
return page;}
static void put_arg_page(struct page *page){}
static void free_arg_page(struct linux_binprm *bprm, int i){ if (bprm->page[i]) { __free_page(bprm->page[i]); bprm->page[i] = NULL; }}
static void free_arg_pages(struct linux_binprm *bprm){ int i;
for (i = 0; i < MAX_ARG_PAGES; i++) free_arg_page(bprm, i);}
static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos, struct page *page){}
static bool valid_arg_len(struct linux_binprm *bprm, long len){ return len <= bprm->p;}
#endif /* CONFIG_MMU */
/* * Create a new mm_struct and populate it with a temporary stack * vm_area_struct. We don't have enough context at this point to set the stack * flags, permissions, and offset, so we use temporary values. We'll update * them later in setup_arg_pages(). */static int bprm_mm_init(struct linux_binprm *bprm){ int err; struct mm_struct *mm = NULL;
bprm->mm = mm = mm_alloc(); err = -ENOMEM; if (!mm) goto err;
/* Staged for would_dump() narrowing; consumed by begin_new_exec(). */ bprm->user_ns = get_user_ns(current_user_ns());
/* Save current stack limit for all calculations made during exec. */ task_lock(current->group_leader); bprm->rlim_stack = current->signal->rlim[RLIMIT_STACK]; task_unlock(current->group_leader);
#ifndef CONFIG_MMU bprm->p = PAGE_SIZE * MAX_ARG_PAGES - sizeof(void *);#else err = create_init_stack_vma(bprm->mm, &bprm->vma, &bprm->p); if (err) goto err;#endif
return 0;
err: if (mm) { bprm->mm = NULL; mmdrop(mm); }
return err;}
struct user_arg_ptr {#ifdef CONFIG_COMPAT bool is_compat;#endif union { const char __user *const __user *native;#ifdef CONFIG_COMPAT const compat_uptr_t __user *compat;#endif } ptr;};
static const char __user *get_user_arg_ptr(struct user_arg_ptr argv, int nr){ const char __user *native;
#ifdef CONFIG_COMPAT if (unlikely(argv.is_compat)) { compat_uptr_t compat;
if (get_user(compat, argv.ptr.compat + nr)) return ERR_PTR(-EFAULT);
return compat_ptr(compat); }#endif
if (get_user(native, argv.ptr.native + nr)) return ERR_PTR(-EFAULT);
return native;}
/* * count() counts the number of strings in array ARGV. */static int count(struct user_arg_ptr argv, int max){ int i = 0;
if (argv.ptr.native != NULL) { for (;;) { const char __user *p = get_user_arg_ptr(argv, i);
if (!p) break;
if (IS_ERR(p)) return -EFAULT;
if (i >= max) return -E2BIG; ++i;
if (fatal_signal_pending(current)) return -ERESTARTNOHAND; cond_resched(); } } return i;}
static int count_strings_kernel(const char *const *argv){ int i;
if (!argv) return 0;
for (i = 0; argv[i]; ++i) { if (i >= MAX_ARG_STRINGS) return -E2BIG; if (fatal_signal_pending(current)) return -ERESTARTNOHAND; cond_resched(); } return i;}
static inline int bprm_set_stack_limit(struct linux_binprm *bprm, unsigned long limit){#ifdef CONFIG_MMU /* Avoid a pathological bprm->p. */ if (bprm->p < limit) return -E2BIG; bprm->argmin = bprm->p - limit;#endif return 0;}static inline bool bprm_hit_stack_limit(struct linux_binprm *bprm){#ifdef CONFIG_MMU return bprm->p < bprm->argmin;#else return false;#endif}
/* * Calculate bprm->argmin from: * - _STK_LIM * - ARG_MAX * - bprm->rlim_stack.rlim_cur * - bprm->argc * - bprm->envc * - bprm->p */static int bprm_stack_limits(struct linux_binprm *bprm){ unsigned long limit, ptr_size;
/* * Limit to 1/4 of the max stack size or 3/4 of _STK_LIM * (whichever is smaller) for the argv+env strings. * This ensures that: * - the remaining binfmt code will not run out of stack space, * - the program will have a reasonable amount of stack left * to work from. */ limit = _STK_LIM / 4 * 3; limit = min(limit, bprm->rlim_stack.rlim_cur / 4); /* * We've historically supported up to 32 pages (ARG_MAX) * of argument strings even with small stacks */ limit = max_t(unsigned long, limit, ARG_MAX); /* Reject totally pathological counts. */ if (bprm->argc < 0 || bprm->envc < 0) return -E2BIG; /* * We must account for the size of all the argv and envp pointers to * the argv and envp strings, since they will also take up space in * the stack. They aren't stored until much later when we can't * signal to the parent that the child has run out of stack space. * Instead, calculate it here so it's possible to fail gracefully. * * In the case of argc = 0, make sure there is space for adding a * empty string (which will bump argc to 1), to ensure confused * userspace programs don't start processing from argv[1], thinking * argc can never be 0, to keep them from walking envp by accident. * See do_execveat_common(). */ if (check_add_overflow(max(bprm->argc, 1), bprm->envc, &ptr_size) || check_mul_overflow(ptr_size, sizeof(void *), &ptr_size)) return -E2BIG; if (limit <= ptr_size) return -E2BIG; limit -= ptr_size;
return bprm_set_stack_limit(bprm, limit);}
/* * 'copy_strings()' copies argument/environment strings from the old * processes's memory to the new process's stack. The call to get_user_pages() * ensures the destination page is created and not swapped out. */static int copy_strings(int argc, struct user_arg_ptr argv, struct linux_binprm *bprm){ struct page *kmapped_page = NULL; char *kaddr = NULL; unsigned long kpos = 0; int ret;
while (argc-- > 0) { const char __user *str; int len; unsigned long pos;
ret = -EFAULT; str = get_user_arg_ptr(argv, argc); if (IS_ERR(str)) goto out;
len = strnlen_user(str, MAX_ARG_STRLEN); if (!len) goto out;
ret = -E2BIG; if (!valid_arg_len(bprm, len)) goto out;
/* We're going to work our way backwards. */ pos = bprm->p; str += len; bprm->p -= len; if (bprm_hit_stack_limit(bprm)) goto out;
while (len > 0) { int offset, bytes_to_copy;
if (fatal_signal_pending(current)) { ret = -ERESTARTNOHAND; goto out; } cond_resched();
offset = pos % PAGE_SIZE; if (offset == 0) offset = PAGE_SIZE;
bytes_to_copy = offset; if (bytes_to_copy > len) bytes_to_copy = len;
offset -= bytes_to_copy; pos -= bytes_to_copy; str -= bytes_to_copy; len -= bytes_to_copy;
if (!kmapped_page || kpos != (pos & PAGE_MASK)) { struct page *page;
page = get_arg_page(bprm, pos, 1); if (!page) { ret = -E2BIG; goto out; }
if (kmapped_page) { flush_dcache_page(kmapped_page); kunmap_local(kaddr); put_arg_page(kmapped_page); } kmapped_page = page; kaddr = kmap_local_page(kmapped_page); kpos = pos & PAGE_MASK; flush_arg_page(bprm, kpos, kmapped_page); } if (copy_from_user(kaddr+offset, str, bytes_to_copy)) { ret = -EFAULT; goto out; } } } ret = 0;out: if (kmapped_page) { flush_dcache_page(kmapped_page); kunmap_local(kaddr); put_arg_page(kmapped_page); } return ret;}
/* * Copy and argument/environment string from the kernel to the processes stack. */int copy_string_kernel(const char *arg, struct linux_binprm *bprm){ int len = strnlen(arg, MAX_ARG_STRLEN) + 1 /* terminating NUL */; unsigned long pos = bprm->p;
if (len == 0) return -EFAULT; if (!valid_arg_len(bprm, len)) return -E2BIG;
/* We're going to work our way backwards. */ arg += len; bprm->p -= len; if (bprm_hit_stack_limit(bprm)) return -E2BIG;
while (len > 0) { unsigned int bytes_to_copy = min(len, min_not_zero(offset_in_page(pos), PAGE_SIZE)); struct page *page;
pos -= bytes_to_copy; arg -= bytes_to_copy; len -= bytes_to_copy;
page = get_arg_page(bprm, pos, 1); if (!page) return -E2BIG; flush_arg_page(bprm, pos & PAGE_MASK, page); memcpy_to_page(page, offset_in_page(pos), arg, bytes_to_copy); put_arg_page(page); }
return 0;}EXPORT_SYMBOL(copy_string_kernel);
static int copy_strings_kernel(int argc, const char *const *argv, struct linux_binprm *bprm){ while (argc-- > 0) { int ret = copy_string_kernel(argv[argc], bprm); if (ret < 0) return ret; if (fatal_signal_pending(current)) return -ERESTARTNOHAND; cond_resched(); } return 0;}
#ifdef CONFIG_MMU
/* * Finalizes the stack vm_area_struct. The flags and permissions are updated, * the stack is optionally relocated, and some extra space is added. */int setup_arg_pages(struct linux_binprm *bprm, unsigned long stack_top, int executable_stack){ int ret; unsigned long stack_shift; struct mm_struct *mm = current->mm; struct vm_area_struct *vma = bprm->vma; struct vm_area_struct *prev = NULL; vm_flags_t vm_flags; unsigned long stack_base; unsigned long stack_size; unsigned long stack_expand; unsigned long rlim_stack; struct mmu_gather tlb; struct vma_iterator vmi;
#ifdef CONFIG_STACK_GROWSUP /* Limit stack size */ stack_base = bprm->rlim_stack.rlim_max;
stack_base = calc_max_stack_size(stack_base);
/* Add space for stack randomization. */ if (current->flags & PF_RANDOMIZE) stack_base += (STACK_RND_MASK << PAGE_SHIFT);
/* Make sure we didn't let the argument array grow too large. */ if (vma->vm_end - vma->vm_start > stack_base) return -ENOMEM;
stack_base = PAGE_ALIGN(stack_top - stack_base);
stack_shift = vma->vm_start - stack_base; mm->arg_start = bprm->p - stack_shift; bprm->p = vma->vm_end - stack_shift;#else stack_top = arch_align_stack(stack_top); stack_top = PAGE_ALIGN(stack_top);
if (unlikely(stack_top < mmap_min_addr) || unlikely(vma->vm_end - vma->vm_start >= stack_top - mmap_min_addr)) return -ENOMEM;
stack_shift = vma->vm_end - stack_top;
bprm->p -= stack_shift; mm->arg_start = bprm->p;#endif
bprm->exec -= stack_shift;
if (mmap_write_lock_killable(mm)) return -EINTR;
vm_flags = VM_STACK_FLAGS;
/* * Adjust stack execute permissions; explicitly enable for * EXSTACK_ENABLE_X, disable for EXSTACK_DISABLE_X and leave alone * (arch default) otherwise. */ if (unlikely(executable_stack == EXSTACK_ENABLE_X)) vm_flags |= VM_EXEC; else if (executable_stack == EXSTACK_DISABLE_X) vm_flags &= ~VM_EXEC; vm_flags |= mm->def_flags; vm_flags |= VM_STACK_INCOMPLETE_SETUP;
vma_iter_init(&vmi, mm, vma->vm_start);
tlb_gather_mmu(&tlb, mm); ret = mprotect_fixup(&vmi, &tlb, vma, &prev, vma->vm_start, vma->vm_end, vm_flags); tlb_finish_mmu(&tlb);
if (ret) goto out_unlock; BUG_ON(prev != vma);
if (unlikely(vm_flags & VM_EXEC)) { pr_warn_once("process '%pD4' started with executable stack\n", bprm->file); }
/* Move stack pages down in memory. */ if (stack_shift) { /* * During bprm_mm_init(), we create a temporary stack at STACK_TOP_MAX. Once * the binfmt code determines where the new stack should reside, we shift it to * its final location. */ ret = relocate_vma_down(vma, stack_shift); if (ret) goto out_unlock; }
/* mprotect_fixup is overkill to remove the temporary stack flags */ vm_flags_clear(vma, VM_STACK_INCOMPLETE_SETUP);
stack_expand = 131072UL; /* randomly 32*4k (or 2*64k) pages */ stack_size = vma->vm_end - vma->vm_start; /* * Align this down to a page boundary as expand_stack * will align it up. */ rlim_stack = bprm->rlim_stack.rlim_cur & PAGE_MASK;
stack_expand = min(rlim_stack, stack_size + stack_expand);
#ifdef CONFIG_STACK_GROWSUP stack_base = vma->vm_start + stack_expand;#else stack_base = vma->vm_end - stack_expand;#endif current->mm->start_stack = bprm->p; ret = expand_stack_locked(vma, stack_base); if (ret) ret = -EFAULT;
out_unlock: mmap_write_unlock(mm); return ret;}EXPORT_SYMBOL(setup_arg_pages);
#else
/* * Transfer the program arguments and environment from the holding pages * onto the stack. The provided stack pointer is adjusted accordingly. */int transfer_args_to_stack(struct linux_binprm *bprm, unsigned long *sp_location){ unsigned long index, stop, sp; int ret = 0;
stop = bprm->p >> PAGE_SHIFT; sp = *sp_location;
for (index = MAX_ARG_PAGES; index-- > stop; ) { unsigned int offset = index == stop ? bprm->p & ~PAGE_MASK : 0; char *src = kmap_local_page(bprm->page[index]) + offset; sp -= PAGE_SIZE - offset; if (copy_to_user((void *) sp, src, PAGE_SIZE - offset) != 0) ret = -EFAULT; kunmap_local(src); if (ret) goto out; }
bprm->exec += *sp_location - MAX_ARG_PAGES * PAGE_SIZE; *sp_location = sp;
out: return ret;}EXPORT_SYMBOL(transfer_args_to_stack);
#endif /* CONFIG_MMU */
/* * On success, caller must call do_close_execat() on the returned * struct file to close it. */static struct file *do_open_execat(int fd, struct filename *name, int flags){ int err; struct file *file __free(fput) = NULL; struct open_flags open_exec_flags = { .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC, .acc_mode = MAY_EXEC, .intent = LOOKUP_OPEN, .lookup_flags = LOOKUP_FOLLOW, };
if ((flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH | AT_EXECVE_CHECK)) != 0) return ERR_PTR(-EINVAL); if (flags & AT_SYMLINK_NOFOLLOW) open_exec_flags.lookup_flags &= ~LOOKUP_FOLLOW;
file = do_file_open(fd, name, &open_exec_flags); if (IS_ERR(file)) return file;
if (path_noexec(&file->f_path)) return ERR_PTR(-EACCES);
/* * In the past the regular type check was here. It moved to may_open() in * 633fb6ac3980 ("exec: move S_ISREG() check earlier"). Since then it is * an invariant that all non-regular files error out before we get here. */ if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode))) return ERR_PTR(-EACCES);
err = exe_file_deny_write_access(file); if (err) return ERR_PTR(err);
return no_free_ptr(file);}
/** * open_exec - Open a path name for execution * * @name: path name to open with the intent of executing it. * * Returns ERR_PTR on failure or allocated struct file on success. * * As this is a wrapper for the internal do_open_execat(), callers * must call exe_file_allow_write_access() before fput() on release. Also see * do_close_execat(). */struct file *open_exec(const char *name){ CLASS(filename_kernel, filename)(name); return do_open_execat(AT_FDCWD, filename, 0);}EXPORT_SYMBOL(open_exec);
#if defined(CONFIG_BINFMT_FLAT) || defined(CONFIG_BINFMT_ELF_FDPIC)ssize_t read_code(struct file *file, unsigned long addr, loff_t pos, size_t len){ ssize_t res = vfs_read(file, (void __user *)addr, len, &pos); if (res > 0) flush_icache_user_range(addr, addr + len); return res;}EXPORT_SYMBOL(read_code);#endif
/* * Maps the mm_struct mm into the current task struct. * On success, this function returns with exec_update_lock * held for writing. The replaced address space is stashed in * bprm->old_mm for setup_new_exec() to release outside the lock. */static int exec_mmap(struct linux_binprm *bprm){ struct task_exec_state *exec_state __free(put_task_exec_state) = NULL; struct mm_struct *mm = bprm->mm; struct task_struct *tsk; struct mm_struct *old_mm, *active_mm; int ret;
exec_state = alloc_task_exec_state(bprm->user_ns); if (!exec_state) return -ENOMEM;
/* Notify parent that we're no longer interested in the old VM */ tsk = current; old_mm = current->mm; exec_mm_release(tsk, old_mm);
ret = down_write_killable(&tsk->signal->exec_update_lock); if (ret) return ret;
if (old_mm) { /* * If there is a pending fatal signal perhaps a signal * whose default action is to create a coredump get * out and die instead of going through with the exec. */ ret = mmap_read_lock_killable(old_mm); if (ret) { up_write(&tsk->signal->exec_update_lock); return ret; } }
task_lock(tsk); membarrier_exec_mmap(mm);
local_irq_disable(); active_mm = tsk->active_mm; tsk->active_mm = mm; tsk->mm = mm; mm_init_cid(mm, tsk); exec_state = task_exec_state_replace(tsk, exec_state); /* * This prevents preemption while active_mm is being loaded and * it and mm are being updated, which could cause problems for * lazy tlb mm refcounting when these are updated by context * switches. Not all architectures can handle irqs off over * activate_mm yet. */ if (!IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM)) local_irq_enable(); activate_mm(active_mm, mm); if (IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM)) local_irq_enable(); lru_gen_add_mm(mm); task_unlock(tsk); lru_gen_use_mm(mm); if (old_mm) { mmap_read_unlock(old_mm); BUG_ON(active_mm != old_mm); /* Defer teardown to setup_new_exec(), outside the exec locks. */ bprm->old_mm = old_mm; return 0; } mmdrop_lazy_tlb(active_mm); return 0;}
/* Release the address space replaced by exec, outside the exec locks. */static void exec_mm_put_old(struct mm_struct *old_mm){ setmax_mm_hiwater_rss(¤t->signal->maxrss, old_mm); mm_update_next_owner(old_mm); mmput(old_mm);}
static int de_thread(struct task_struct *tsk){ struct signal_struct *sig = tsk->signal; struct sighand_struct *oldsighand = tsk->sighand; spinlock_t *lock = &oldsighand->siglock;
if (thread_group_empty(tsk)) goto no_thread_group;
/* * Kill all other threads in the thread group. */ spin_lock_irq(lock); if ((sig->flags & SIGNAL_GROUP_EXIT) || sig->group_exec_task) { /* * Another group action in progress, just * return so that the signal is processed. */ spin_unlock_irq(lock); return -EAGAIN; }
sig->group_exec_task = tsk; sig->notify_count = zap_other_threads(tsk); if (!thread_group_leader(tsk)) sig->notify_count--;
while (sig->notify_count) { __set_current_state(TASK_KILLABLE); spin_unlock_irq(lock); schedule(); if (__fatal_signal_pending(tsk)) goto killed; spin_lock_irq(lock); } spin_unlock_irq(lock);
/* * At this point all other threads have exited, all we have to * do is to wait for the thread group leader to become inactive, * and to assume its PID: */ if (!thread_group_leader(tsk)) { struct task_struct *leader = tsk->group_leader;
for (;;) { cgroup_threadgroup_change_begin(tsk); write_lock_irq(&tasklist_lock); /* * Do this under tasklist_lock to ensure that * exit_notify() can't miss ->group_exec_task */ sig->notify_count = -1; if (likely(leader->exit_state)) break; __set_current_state(TASK_KILLABLE); write_unlock_irq(&tasklist_lock); cgroup_threadgroup_change_end(tsk); schedule(); if (__fatal_signal_pending(tsk)) goto killed; }
/* * The only record we have of the real-time age of a * process, regardless of execs it's done, is start_time. * All the past CPU time is accumulated in signal_struct * from sister threads now dead. But in this non-leader * exec, nothing survives from the original leader thread, * whose birth marks the true age of this process now. * When we take on its identity by switching to its PID, we * also take its birthdate (always earlier than our own). */ tsk->start_time = leader->start_time; tsk->start_boottime = leader->start_boottime;
BUG_ON(!same_thread_group(leader, tsk)); /* * An exec() starts a new thread group with the * TGID of the previous thread group. Rehash the * two threads with a switched PID, and release * the former thread group leader: */
/* Become a process group leader with the old leader's pid. * The old leader becomes a thread of the this thread group. */ exchange_tids(tsk, leader); transfer_pid(leader, tsk, PIDTYPE_TGID); transfer_pid(leader, tsk, PIDTYPE_PGID); transfer_pid(leader, tsk, PIDTYPE_SID);
list_replace_rcu(&leader->tasks, &tsk->tasks); list_replace_init(&leader->sibling, &tsk->sibling);
tsk->group_leader = tsk; leader->group_leader = tsk;
tsk->exit_signal = SIGCHLD; leader->exit_signal = -1;
BUG_ON(leader->exit_state != EXIT_ZOMBIE); leader->exit_state = EXIT_DEAD; /* * We are going to release_task()->ptrace_unlink() silently, * the tracer can sleep in do_wait(). EXIT_DEAD guarantees * the tracer won't block again waiting for this thread. */ if (unlikely(leader->ptrace)) __wake_up_parent(leader, leader->parent); write_unlock_irq(&tasklist_lock); cgroup_threadgroup_change_end(tsk);
release_task(leader); }
sig->group_exec_task = NULL; sig->notify_count = 0;
no_thread_group: /* we have changed execution domain */ tsk->exit_signal = SIGCHLD;
BUG_ON(!thread_group_leader(tsk)); return 0;
killed: /* protects against exit_notify() and __exit_signal() */ read_lock(&tasklist_lock); sig->group_exec_task = NULL; sig->notify_count = 0; read_unlock(&tasklist_lock); return -EAGAIN;}
/* * This function makes sure the current process has its own signal table, * so that flush_signal_handlers can later reset the handlers without * disturbing other processes. (Other processes might share the signal * table via the CLONE_SIGHAND option to clone().) */static int unshare_sighand(struct task_struct *me){ struct sighand_struct *oldsighand = me->sighand;
if (refcount_read(&oldsighand->count) != 1) { struct sighand_struct *newsighand; /* * This ->sighand is shared with the CLONE_SIGHAND * but not CLONE_THREAD task, switch to the new one. */ newsighand = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); if (!newsighand) return -ENOMEM;
refcount_set(&newsighand->count, 1);
write_lock_irq(&tasklist_lock); spin_lock(&oldsighand->siglock); memcpy(newsighand->action, oldsighand->action, sizeof(newsighand->action)); rcu_assign_pointer(me->sighand, newsighand); spin_unlock(&oldsighand->siglock); write_unlock_irq(&tasklist_lock);
__cleanup_sighand(oldsighand); } return 0;}
/* * This is unlocked -- the string will always be NUL-terminated, but * may show overlapping contents if racing concurrent reads. */void __set_task_comm(struct task_struct *tsk, const char *buf, bool exec){ size_t len = strnlen(buf, sizeof(tsk->comm) - 1);
trace_task_rename(tsk, buf); memcpy(tsk->comm, buf, len); memset(&tsk->comm[len], 0, sizeof(tsk->comm) - len); perf_event_comm(tsk, exec);}
/* * Calling this is the point of no return. None of the failures will be * seen by userspace since either the process is already taking a fatal * signal (via de_thread() or coredump), or will have SEGV raised * (after exec_mmap()) by search_binary_handler (see below). */int begin_new_exec(struct linux_binprm * bprm){ struct task_struct *me = current; int retval;
/* Once we are committed compute the creds */ retval = bprm_creds_from_file(bprm); if (retval) return retval;
/* * This tracepoint marks the point before flushing the old exec where * the current task is still unchanged, but errors are fatal (point of * no return). The later "sched_process_exec" tracepoint is called after * the current task has successfully switched to the new exec. */ trace_sched_prepare_exec(current, bprm);
/* * Ensure all future errors are fatal. */ bprm->point_of_no_return = true;
/* Make this the only thread in the thread group */ retval = de_thread(me); if (retval) goto out; /* see the comment in check_unsafe_exec() */ current->fs->in_exec = 0; /* * Cancel any io_uring activity across execve */ io_uring_task_cancel();
/* Ensure the files table is not shared. */ retval = unshare_files(); if (retval) goto out;
/* * Must be called _before_ exec_mmap() as bprm->mm is * not visible until then. Doing it here also ensures * we don't race against replace_mm_exe_file(). */ retval = set_mm_exe_file(bprm->mm, bprm->file); if (retval) goto out;
/* If the binary is not readable then enforce mm->dumpable=0 */ would_dump(bprm, bprm->file); if (bprm->have_execfd) would_dump(bprm, bprm->executable);
/* * Release all of the old mmap stuff */ acct_arg_size(bprm, 0); retval = exec_mmap(bprm); if (retval) goto out;
bprm->mm = NULL;
retval = exec_task_namespaces(); if (retval) goto out_unlock;
#ifdef CONFIG_POSIX_TIMERS spin_lock_irq(&me->sighand->siglock); posix_cpu_timers_exit(me); spin_unlock_irq(&me->sighand->siglock); exit_itimers(me); flush_itimer_signals();#endif
/* * Make the signal table private. */ retval = unshare_sighand(me); if (retval) goto out_unlock;
me->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_NOFREEZE | PF_NO_SETAFFINITY); flush_thread(); me->personality &= ~bprm->per_clear;
clear_syscall_work_syscall_user_dispatch(me);
/* * We have to apply CLOEXEC before we change whether the process is * dumpable (in setup_new_exec) to avoid a race with a process in userspace * trying to access the should-be-closed file descriptors of a process * undergoing exec(2). */ do_close_on_exec(me->files);
if (bprm->secureexec) { /* Make sure parent cannot signal privileged process. */ me->pdeath_signal = 0;
/* * For secureexec, reset the stack limit to sane default to * avoid bad behavior from the prior rlimits. This has to * happen before arch_pick_mmap_layout(), which examines * RLIMIT_STACK, but after the point of no return to avoid * needing to clean up the change on failure. */ if (bprm->rlim_stack.rlim_cur > _STK_LIM) bprm->rlim_stack.rlim_cur = _STK_LIM; }
me->sas_ss_sp = me->sas_ss_size = 0;
/* * Figure out dumpability. Note that this checking only of current * is wrong, but userspace depends on it. This should be testing * bprm->secureexec instead. */ if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP || !(uid_eq(current_euid(), current_uid()) && gid_eq(current_egid(), current_gid()))) task_exec_state_set_dumpable(suid_dumpable); else task_exec_state_set_dumpable(TASK_DUMPABLE_OWNER);
perf_event_exec();
/* * If the original filename was empty, alloc_bprm() made up a path * that will probably not be useful to admins running ps or similar. * Let's fix it up to be something reasonable. */ if (bprm->comm_from_dentry) { /* * Hold RCU lock to keep the name from being freed behind our back. * Use acquire semantics to make sure the terminating NUL from * __d_alloc() is seen. * * Note, we're deliberately sloppy here. We don't need to care about * detecting a concurrent rename and just want a terminated name. */ rcu_read_lock(); __set_task_comm(me, smp_load_acquire(&bprm->file->f_path.dentry->d_name.name), true); rcu_read_unlock(); } else { __set_task_comm(me, kbasename(bprm->filename), true); }
/* An exec changes our domain. We are no longer part of the thread group */ WRITE_ONCE(me->self_exec_id, me->self_exec_id + 1); flush_signal_handlers(me, 0);
retval = set_cred_ucounts(bprm->cred); if (retval < 0) goto out_unlock;
/* * install the new credentials for this executable */ security_bprm_committing_creds(bprm);
commit_creds(bprm->cred); bprm->cred = NULL;
/* * Disable monitoring for regular users * when executing setuid binaries. Must * wait until new credentials are committed * by commit_creds() above */ if (task_exec_state_get_dumpable(me) != TASK_DUMPABLE_OWNER) perf_event_exit_task(me); /* * cred_guard_mutex must be held at least to this point to prevent * ptrace_attach() from altering our determination of the task's * credentials; any time after this it may be unlocked. */ security_bprm_committed_creds(bprm);
/* Pass the opened binary to the interpreter. */ if (bprm->have_execfd) { retval = FD_ADD(0, bprm->executable); if (retval < 0) goto out_unlock; bprm->executable = NULL; bprm->execfd = retval; } return 0;
out_unlock: up_write(&me->signal->exec_update_lock); if (!bprm->cred) mutex_unlock(&me->signal->cred_guard_mutex);
out: return retval;}EXPORT_SYMBOL(begin_new_exec);
void would_dump(struct linux_binprm *bprm, struct file *file){ struct inode *inode = file_inode(file); struct mnt_idmap *idmap = file_mnt_idmap(file); if (inode_permission(idmap, inode, MAY_READ) < 0) { struct user_namespace *old, *user_ns; bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP;
/* Ensure bprm->user_ns contains the executable. */ user_ns = old = bprm->user_ns; while ((user_ns != &init_user_ns) && !privileged_wrt_inode_uidgid(user_ns, idmap, inode)) user_ns = user_ns->parent;
if (old != user_ns) { bprm->user_ns = get_user_ns(user_ns); put_user_ns(old); } }}EXPORT_SYMBOL(would_dump);
void setup_new_exec(struct linux_binprm * bprm){ /* Setup things that can depend upon the personality */ struct task_struct *me = current;
arch_pick_mmap_layout(me->mm, &bprm->rlim_stack);
arch_setup_new_exec();
/* Set the new mm task size. We have to do that late because it may * depend on TIF_32BIT which is only updated in flush_thread() on * some architectures like powerpc */ me->mm->task_size = TASK_SIZE; up_write(&me->signal->exec_update_lock); mutex_unlock(&me->signal->cred_guard_mutex);
/* The exec locks are dropped: release the old address space now. */ if (bprm->old_mm) { exec_mm_put_old(bprm->old_mm); bprm->old_mm = NULL; }}EXPORT_SYMBOL(setup_new_exec);
/* Runs immediately before start_thread() takes over. */void finalize_exec(struct linux_binprm *bprm){ /* Store any stack rlimit changes before starting thread. */ task_lock(current->group_leader); current->signal->rlim[RLIMIT_STACK] = bprm->rlim_stack; task_unlock(current->group_leader);}EXPORT_SYMBOL(finalize_exec);
/* * Prepare credentials and lock ->cred_guard_mutex. * setup_new_exec() commits the new creds and drops the lock. * Or, if exec fails before, free_bprm() should release ->cred * and unlock. */static int prepare_bprm_creds(struct linux_binprm *bprm){ if (mutex_lock_interruptible(¤t->signal->cred_guard_mutex)) return -ERESTARTNOINTR;
bprm->cred = prepare_exec_creds(); if (likely(bprm->cred)) return 0;
mutex_unlock(¤t->signal->cred_guard_mutex); return -ENOMEM;}
/* Matches do_open_execat() */static void do_close_execat(struct file *file){ if (!file) return; exe_file_allow_write_access(file); fput(file);}
static void free_bprm(struct linux_binprm *bprm){ if (bprm->mm) { acct_arg_size(bprm, 0); mmput(bprm->mm); } if (bprm->user_ns) put_user_ns(bprm->user_ns); free_arg_pages(bprm); if (bprm->cred) { /* in case exec fails before de_thread() succeeds */ current->fs->in_exec = 0; mutex_unlock(¤t->signal->cred_guard_mutex); abort_creds(bprm->cred); } /* exec swapped the mm but failed before setup_new_exec() freed it */ if (bprm->old_mm) exec_mm_put_old(bprm->old_mm); do_close_execat(bprm->file); if (bprm->executable) fput(bprm->executable); /* If a binfmt changed the interp, free it. */ if (bprm->interp != bprm->filename) kfree(bprm->interp); kfree(bprm->fdpath); kfree(bprm);}
static struct linux_binprm *alloc_bprm(int fd, struct filename *filename, int flags){ struct linux_binprm *bprm; struct file *file; int retval = -ENOMEM;
file = do_open_execat(fd, filename, flags); if (IS_ERR(file)) return ERR_CAST(file);
bprm = kzalloc_obj(*bprm); if (!bprm) { do_close_execat(file); return ERR_PTR(-ENOMEM); }
bprm->file = file;
if (fd == AT_FDCWD || filename->name[0] == '/') { bprm->filename = filename->name; } else { if (filename->name[0] == '\0') { bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d", fd); bprm->comm_from_dentry = 1; } else { bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d/%s", fd, filename->name); } if (!bprm->fdpath) goto out_free;
/* * Record that a name derived from an O_CLOEXEC fd will be * inaccessible after exec. This allows the code in exec to * choose to fail when the executable is not mmaped into the * interpreter and an open file descriptor is not passed to * the interpreter. This makes for a better user experience * than having the interpreter start and then immediately fail * when it finds the executable is inaccessible. */ if (get_close_on_exec(fd)) bprm->interp_flags |= BINPRM_FLAGS_PATH_INACCESSIBLE;
bprm->filename = bprm->fdpath; } bprm->interp = bprm->filename;
/* * At this point, security_file_open() has already been called (with * __FMODE_EXEC) and access control checks for AT_EXECVE_CHECK will * stop just after the security_bprm_creds_for_exec() call in * bprm_execve(). Indeed, the kernel should not try to parse the * content of the file with exec_binprm() nor change the calling * thread, which means that the following security functions will not * be called: * - security_bprm_check() * - security_bprm_creds_from_file() * - security_bprm_committing_creds() * - security_bprm_committed_creds() */ bprm->is_check = !!(flags & AT_EXECVE_CHECK);
retval = bprm_mm_init(bprm); if (!retval) return bprm;
out_free: free_bprm(bprm); return ERR_PTR(retval);}
DEFINE_CLASS(bprm, struct linux_binprm *, if (!IS_ERR(_T)) free_bprm(_T), alloc_bprm(fd, name, flags), int fd, struct filename *name, int flags)
int bprm_change_interp(const char *interp, struct linux_binprm *bprm){ /* If a binfmt changed the interp, free it first. */ if (bprm->interp != bprm->filename) kfree(bprm->interp); bprm->interp = kstrdup(interp, GFP_KERNEL); if (!bprm->interp) return -ENOMEM; return 0;}EXPORT_SYMBOL(bprm_change_interp);
/* * determine how safe it is to execute the proposed program * - the caller must hold ->cred_guard_mutex to protect against * PTRACE_ATTACH or seccomp thread-sync */static void check_unsafe_exec(struct linux_binprm *bprm){ struct task_struct *p = current, *t; unsigned n_fs;
if (p->ptrace) bprm->unsafe |= LSM_UNSAFE_PTRACE;
/* * This isn't strictly necessary, but it makes it harder for LSMs to * mess up. */ if (task_no_new_privs(current)) bprm->unsafe |= LSM_UNSAFE_NO_NEW_PRIVS;
/* * If another task is sharing our fs, we cannot safely * suid exec because the differently privileged task * will be able to manipulate the current directory, etc. * It would be nice to force an unshare instead... * * Otherwise we set fs->in_exec = 1 to deny clone(CLONE_FS) * from another sub-thread until de_thread() succeeds, this * state is protected by cred_guard_mutex we hold. */ n_fs = 1; read_seqlock_excl(&p->fs->seq); rcu_read_lock(); for_other_threads(p, t) { if (t->fs == p->fs) n_fs++; } rcu_read_unlock();
/* "users" and "in_exec" locked for copy_fs() */ if (p->fs->users > n_fs) bprm->unsafe |= LSM_UNSAFE_SHARE; else p->fs->in_exec = 1; read_sequnlock_excl(&p->fs->seq);}
static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file){ /* Handle suid and sgid on files */ struct mnt_idmap *idmap; struct inode *inode = file_inode(file); unsigned int mode; vfsuid_t vfsuid; vfsgid_t vfsgid; int err;
if (!mnt_may_suid(file->f_path.mnt)) return;
if (task_no_new_privs(current)) return;
mode = READ_ONCE(inode->i_mode); if (!(mode & (S_ISUID|S_ISGID))) return;
idmap = file_mnt_idmap(file);
/* Be careful if suid/sgid is set */ inode_lock(inode);
/* Atomically reload and check mode/uid/gid now that lock held. */ mode = inode->i_mode; vfsuid = i_uid_into_vfsuid(idmap, inode); vfsgid = i_gid_into_vfsgid(idmap, inode); err = inode_permission(idmap, inode, MAY_EXEC); inode_unlock(inode);
/* Did the exec bit vanish out from under us? Give up. */ if (err) return;
/* We ignore suid/sgid if there are no mappings for them in the ns */ if (!vfsuid_has_mapping(bprm->cred->user_ns, vfsuid) || !vfsgid_has_mapping(bprm->cred->user_ns, vfsgid)) return;
if (mode & S_ISUID) { bprm->per_clear |= PER_CLEAR_ON_SETID; bprm->cred->euid = vfsuid_into_kuid(vfsuid); }
if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { bprm->per_clear |= PER_CLEAR_ON_SETID; bprm->cred->egid = vfsgid_into_kgid(vfsgid); }}
/* * Compute brpm->cred based upon the final binary. */static int bprm_creds_from_file(struct linux_binprm *bprm){ /* Compute creds based on which file? */ struct file *file = bprm->execfd_creds ? bprm->executable : bprm->file;
bprm_fill_uid(bprm, file); return security_bprm_creds_from_file(bprm, file);}
/* * Fill the binprm structure from the inode. * Read the first BINPRM_BUF_SIZE bytes * * This may be called multiple times for binary chains (scripts for example). */static int prepare_binprm(struct linux_binprm *bprm){ loff_t pos = 0;
memset(bprm->buf, 0, BINPRM_BUF_SIZE); return kernel_read(bprm->file, bprm->buf, BINPRM_BUF_SIZE, &pos);}
/* * Arguments are '\0' separated strings found at the location bprm->p * points to; chop off the first by relocating brpm->p to right after * the first '\0' encountered. */int remove_arg_zero(struct linux_binprm *bprm){ unsigned long offset; char *kaddr; struct page *page;
if (!bprm->argc) return 0;
do { offset = bprm->p & ~PAGE_MASK; page = get_arg_page(bprm, bprm->p, 0); if (!page) return -EFAULT; kaddr = kmap_local_page(page);
for (; offset < PAGE_SIZE && kaddr[offset]; offset++, bprm->p++) ;
kunmap_local(kaddr); put_arg_page(page); } while (offset == PAGE_SIZE);
bprm->p++; bprm->argc--;
return 0;}EXPORT_SYMBOL(remove_arg_zero);
/* * cycle the list of binary formats handler, until one recognizes the image */static int search_binary_handler(struct linux_binprm *bprm){ struct linux_binfmt *fmt; int retval;
retval = prepare_binprm(bprm); if (retval < 0) return retval;
retval = security_bprm_check(bprm); if (retval) return retval;
read_lock(&binfmt_lock); list_for_each_entry(fmt, &formats, lh) { if (!try_module_get(fmt->module)) continue; read_unlock(&binfmt_lock);
retval = fmt->load_binary(bprm);
read_lock(&binfmt_lock); put_binfmt(fmt); if (bprm->point_of_no_return || (retval != -ENOEXEC)) { read_unlock(&binfmt_lock); return retval; } } read_unlock(&binfmt_lock);
return -ENOEXEC;}
/* binfmt handlers will call back into begin_new_exec() on success. */static int exec_binprm(struct linux_binprm *bprm){ pid_t old_pid, old_vpid; int ret, depth;
/* Need to fetch pid before load_binary changes it */ old_pid = current->pid; rcu_read_lock(); old_vpid = task_pid_nr_ns(current, task_active_pid_ns(current->parent)); rcu_read_unlock();
/* This allows 5 levels of binfmt rewrites before failing hard. */ for (depth = 0;; depth++) { struct file *exec; if (depth > 5) return -ELOOP;
ret = search_binary_handler(bprm); if (ret < 0) return ret; if (!bprm->interpreter) break;
exec = bprm->file; bprm->file = bprm->interpreter; bprm->interpreter = NULL;
exe_file_allow_write_access(exec); if (unlikely(bprm->have_execfd)) { if (bprm->executable) { fput(exec); return -ENOEXEC; } bprm->executable = exec; } else fput(exec); }
audit_bprm(bprm); trace_sched_process_exec(current, old_pid, bprm); ptrace_event(PTRACE_EVENT_EXEC, old_vpid); proc_exec_connector(current); return 0;}
static int bprm_execve(struct linux_binprm *bprm){ int retval;
retval = prepare_bprm_creds(bprm); if (retval) return retval;
/* * Check for unsafe execution states before exec_binprm(), which * will call back into begin_new_exec(), into bprm_creds_from_file(), * where setuid-ness is evaluated. */ check_unsafe_exec(bprm); current->in_execve = 1; sched_mm_cid_before_execve(current);
sched_exec();
/* Set the unchanging part of bprm->cred */ retval = security_bprm_creds_for_exec(bprm); if (retval || bprm->is_check) goto out;
retval = exec_binprm(bprm); if (retval < 0) goto out;
sched_mm_cid_after_execve(current); rseq_execve(current); /* execve succeeded */ current->in_execve = 0; user_events_execve(current); acct_update_integrals(current); task_numa_free(current, false); return retval;
out: /* * If past the point of no return ensure the code never * returns to the userspace process. Use an existing fatal * signal if present otherwise terminate the process with * SIGSEGV. */ if (bprm->point_of_no_return && !fatal_signal_pending(current)) force_fatal_sig(SIGSEGV);
sched_mm_cid_after_execve(current); rseq_force_update(); current->in_execve = 0;
return retval;}
static int do_execveat_common(int fd, struct filename *filename, struct user_arg_ptr argv, struct user_arg_ptr envp, int flags){ int retval;
/* * We move the actual failure in case of RLIMIT_NPROC excess from * set*uid() to execve() because too many poorly written programs * don't check setuid() return code. Here we additionally recheck * whether NPROC limit is still exceeded. */ if ((current->flags & PF_NPROC_EXCEEDED) && is_rlimit_overlimit(current_ucounts(), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) return -EAGAIN;
/* We're below the limit (still or again), so we don't want to make * further execve() calls fail. */ current->flags &= ~PF_NPROC_EXCEEDED;
CLASS(bprm, bprm)(fd, filename, flags); if (IS_ERR(bprm)) return PTR_ERR(bprm);
retval = count(argv, MAX_ARG_STRINGS); if (retval < 0) return retval; bprm->argc = retval;
retval = count(envp, MAX_ARG_STRINGS); if (retval < 0) return retval; bprm->envc = retval;
retval = bprm_stack_limits(bprm); if (retval < 0) return retval;
retval = copy_string_kernel(bprm->filename, bprm); if (retval < 0) return retval; bprm->exec = bprm->p;
retval = copy_strings(bprm->envc, envp, bprm); if (retval < 0) return retval;
retval = copy_strings(bprm->argc, argv, bprm); if (retval < 0) return retval;
/* * When argv is empty, add an empty string ("") as argv[0] to * ensure confused userspace programs that start processing * from argv[1] won't end up walking envp. See also * bprm_stack_limits(). */ if (bprm->argc == 0) { retval = copy_string_kernel("", bprm); if (retval < 0) return retval; bprm->argc = 1;
pr_warn_once("process '%s' launched '%s' with NULL argv: empty string added\n", current->comm, bprm->filename); }
return bprm_execve(bprm);}
int kernel_execve(const char *kernel_filename, const char *const *argv, const char *const *envp){ int retval;
/* It is non-sense for kernel threads to call execve */ if (WARN_ON_ONCE(current->flags & PF_KTHREAD)) return -EINVAL;
CLASS(filename_kernel, filename)(kernel_filename); CLASS(bprm, bprm)(AT_FDCWD, filename, 0); if (IS_ERR(bprm)) return PTR_ERR(bprm);
retval = count_strings_kernel(argv); if (WARN_ON_ONCE(retval == 0)) return -EINVAL; if (retval < 0) return retval; bprm->argc = retval;
retval = count_strings_kernel(envp); if (retval < 0) return retval; bprm->envc = retval;
retval = bprm_stack_limits(bprm); if (retval < 0) return retval;
retval = copy_string_kernel(bprm->filename, bprm); if (retval < 0) return retval; bprm->exec = bprm->p;
retval = copy_strings_kernel(bprm->envc, envp, bprm); if (retval < 0) return retval;
retval = copy_strings_kernel(bprm->argc, argv, bprm); if (retval < 0) return retval;
return bprm_execve(bprm);}
void set_binfmt(struct linux_binfmt *new){ struct mm_struct *mm = current->mm;
if (mm->binfmt) module_put(mm->binfmt->module);
mm->binfmt = new; if (new) __module_get(new->module);}EXPORT_SYMBOL(set_binfmt);
static inline struct user_arg_ptr native_arg(const char __user *const __user *p){ return (struct user_arg_ptr){.ptr.native = p};}
SYSCALL_DEFINE3(execve, const char __user *, filename, const char __user *const __user *, argv, const char __user *const __user *, envp){ CLASS(filename, name)(filename); return do_execveat_common(AT_FDCWD, name, native_arg(argv), native_arg(envp), 0);}
SYSCALL_DEFINE5(execveat, int, fd, const char __user *, filename, const char __user *const __user *, argv, const char __user *const __user *, envp, int, flags){ CLASS(filename_uflags, name)(filename, flags); return do_execveat_common(fd, name, native_arg(argv), native_arg(envp), flags);}
#ifdef CONFIG_COMPAT
static inline struct user_arg_ptr compat_arg(const compat_uptr_t __user *p){ return (struct user_arg_ptr){.is_compat = true, .ptr.compat = p};}
COMPAT_SYSCALL_DEFINE3(execve, const char __user *, filename, const compat_uptr_t __user *, argv, const compat_uptr_t __user *, envp){ CLASS(filename, name)(filename); return do_execveat_common(AT_FDCWD, name, compat_arg(argv), compat_arg(envp), 0);}
COMPAT_SYSCALL_DEFINE5(execveat, int, fd, const char __user *, filename, const compat_uptr_t __user *, argv, const compat_uptr_t __user *, envp, int, flags){ CLASS(filename_uflags, name)(filename, flags); return do_execveat_common(fd, name, compat_arg(argv), compat_arg(envp), flags);}#endif
#ifdef CONFIG_SYSCTL
static int proc_dointvec_minmax_coredump(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos){ int error, old = READ_ONCE(suid_dumpable);
error = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (!error && write && (old != READ_ONCE(suid_dumpable))) validate_coredump_safety(); return error;}
static const struct ctl_table fs_exec_sysctls[] = { { .procname = "suid_dumpable", .data = &suid_dumpable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax_coredump, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, },};
static int __init init_fs_exec_sysctls(void){ register_sysctl_init("fs", fs_exec_sysctls); return 0;}
fs_initcall(init_fs_exec_sysctls);#endif /* CONFIG_SYSCTL */
#ifdef CONFIG_EXEC_KUNIT_TEST#include "tests/exec_kunit.c"#endif