diff options
34 files changed, 342 insertions, 132 deletions
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index 805d2ca50b4d..160cb7c46db0 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -480,3 +480,4 @@ 548 common pidfd_getfd sys_pidfd_getfd 549 common faccessat2 sys_faccessat2 550 common watch_mount sys_watch_mount +551 common process_madvise sys_process_madvise diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index 974d25b28316..3d3a3fe6931e 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -454,3 +454,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common watch_mount sys_watch_mount +441 common process_madvise sys_process_madvise diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index b3b2019f8d16..86a9d7b3eabe 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -38,7 +38,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) -#define __NR_compat_syscalls 441 +#define __NR_compat_syscalls 442 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 30e0cb686071..66ef92fce655 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -889,6 +889,8 @@ __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd) __SYSCALL(__NR_faccessat2, sys_faccessat2) #define __NR_watch_mount 440 __SYSCALL(__NR_watch_mount, sys_watch_mount) +#define __NR_process_madvise 441 +__SYSCALL(__NR_process_madvise, compat_sys_process_madvise) /* * Please add new compat syscalls above this comment and update diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index 1a8df6669eee..18d6008b151f 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -41,7 +41,7 @@ obj-y += esi_stub.o # must be in kernel proper endif obj-$(CONFIG_INTEL_IOMMU) += pci-dma.o -obj-$(CONFIG_BINFMT_ELF) += elfcore.o +obj-$(CONFIG_ELF_CORE) += elfcore.o # fp_emulate() expects f2-f5,f16-f31 to contain the user-level state. CFLAGS_traps.o += -mfixed-range=f2-f5,f16-f31 diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index f27af175bc75..7e30a024062b 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -361,3 +361,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common watch_mount sys_watch_mount +441 common process_madvise sys_process_madvise diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 25db9c8e412e..3b237088ef9c 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -440,3 +440,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common watch_mount sys_watch_mount +441 common process_madvise sys_process_madvise diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index e74adc19b288..fbbe9ad06f14 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -446,3 +446,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common watch_mount sys_watch_mount +441 common process_madvise sys_process_madvise diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 4f51890c8eeb..78f47e63b4ca 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -379,3 +379,4 @@ 438 n32 pidfd_getfd sys_pidfd_getfd 439 n32 faccessat2 sys_faccessat2 440 n32 watch_mount sys_watch_mount +441 n32 process_madvise compat_sys_process_madvise diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index 97969b679f80..0a55d89056b1 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -355,3 +355,4 @@ 438 n64 pidfd_getfd sys_pidfd_getfd 439 n64 faccessat2 sys_faccessat2 440 n64 watch_mount sys_watch_mount +441 n64 process_madvise sys_process_madvise diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 608922cddddb..97d3a1a2fed5 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -428,3 +428,4 @@ 438 o32 pidfd_getfd sys_pidfd_getfd 439 o32 faccessat2 sys_faccessat2 440 o32 watch_mount sys_watch_mount +441 o32 process_madvise sys_process_madvise compat_sys_process_madvise diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index 714e5359e259..0f5c48c48d7c 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -438,3 +438,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common watch_mount sys_watch_mount +441 common process_madvise sys_process_madvise compat_sys_process_madvise diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 07c1ab563b78..5bf7f0281fa3 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -530,3 +530,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common watch_mount sys_watch_mount +441 common process_madvise sys_process_madvise compat_sys_process_madvise diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index 957a776b8646..d90b1e05de6b 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -443,3 +443,4 @@ 438 common pidfd_getfd sys_pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 sys_faccessat2 440 common watch_mount sys_watch_mount sys_watch_mount +441 common process_madvise sys_process_madvise compat_sys_process_madvise diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index 6de03fe8c589..17147784ac47 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -443,3 +443,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common watch_mount sys_watch_mount +441 common process_madvise sys_process_madvise diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index a14b56b56dbd..42e1e69fae4c 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -486,3 +486,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common watch_mount sys_watch_mount +441 common process_madvise sys_process_madvise compat_sys_process_madvise diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index d7577fece9eb..4cfdf5755ab5 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -19,6 +19,7 @@ CONFIG_CGROUP_CPUACCT=y CONFIG_BLK_DEV_INITRD=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y +# CONFIG_64BIT is not set CONFIG_SMP=y CONFIG_X86_GENERIC=y CONFIG_HPET_TIMER=y diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 54560f3035f7..ece9aa3f7775 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -445,3 +445,4 @@ 438 i386 pidfd_getfd sys_pidfd_getfd 439 i386 faccessat2 sys_faccessat2 440 i386 watch_mount sys_watch_mount +441 i386 process_madvise sys_process_madvise compat_sys_process_madvise diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index f08845dbfaa1..ca94ba5cfe78 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -362,6 +362,7 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common watch_mount sys_watch_mount +441 64 process_madvise sys_process_madvise # # x32-specific system call numbers start at 512 to avoid cache impact @@ -405,3 +406,4 @@ 545 x32 execveat compat_sys_execveat 546 x32 preadv2 compat_sys_preadv64v2 547 x32 pwritev2 compat_sys_pwritev64v2 +548 x32 process_madvise compat_sys_process_madvise diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index de025a07d958..3e65f24adfe1 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -411,3 +411,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common watch_mount sys_watch_mount +441 common process_madvise sys_process_madvise diff --git a/fs/io_uring.c b/fs/io_uring.c index c66a5139dd4d..e9022798290d 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -3845,7 +3845,7 @@ static int io_madvise(struct io_kiocb *req, bool force_nonblock) if (force_nonblock) return -EAGAIN; - ret = do_madvise(ma->addr, ma->len, ma->advice); + ret = do_madvise(NULL, current->mm, ma->addr, ma->len, ma->advice); if (ret < 0) req_set_fail_links(req); io_req_complete(req, ret); diff --git a/include/linux/compat.h b/include/linux/compat.h index b354ce58966e..c24a355fdcbc 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -823,6 +823,10 @@ asmlinkage long compat_sys_pwritev64v2(unsigned long fd, unsigned long vlen, loff_t pos, rwf_t flags); #endif +asmlinkage ssize_t compat_sys_process_madvise(compat_int_t pidfd, + const struct compat_iovec __user *vec, + compat_ulong_t vlen, compat_int_t behavior, + compat_uint_t flags); /* * Deprecated system calls which are still defined in diff --git a/include/linux/mm.h b/include/linux/mm.h index 517751310dd2..e6708977c34b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2570,7 +2570,8 @@ extern int __do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf, bool downgrade); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); -extern int do_madvise(unsigned long start, size_t len_in, int behavior); +extern int do_madvise(struct task_struct *target_task, struct mm_struct *mm, + unsigned long start, size_t len_in, int behavior); #ifdef CONFIG_MMU extern int __mm_populate(unsigned long addr, unsigned long len, diff --git a/include/linux/pid.h b/include/linux/pid.h index 176d6cf80e7c..86e0e7cb7872 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -77,6 +77,7 @@ extern const struct file_operations pidfd_fops; struct file; extern struct pid *pidfd_pid(const struct file *file); +struct pid *pidfd_get_pid(unsigned int fd); static inline struct pid *get_pid(struct pid *pid) { diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 2ba46d811fe8..a32fba5b9617 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -879,6 +879,8 @@ asmlinkage long sys_munlockall(void); asmlinkage long sys_mincore(unsigned long start, size_t len, unsigned char __user * vec); asmlinkage long sys_madvise(unsigned long start, size_t len, int behavior); +asmlinkage long sys_process_madvise(int pidfd, const struct iovec __user *vec, + unsigned long vlen, int behavior, unsigned int flags); asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size, unsigned long prot, unsigned long pgoff, unsigned long flags); diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index b9285f261a9e..153704771cf6 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -861,9 +861,11 @@ __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd) __SYSCALL(__NR_faccessat2, sys_faccessat2) #define __NR_watch_mount 440 __SYSCALL(__NR_watch_mount, sys_watch_mount) +#define __NR_process_madvise 441 +__SC_COMP(__NR_process_madvise, sys_process_madvise, compat_sys_process_madvise) #undef __NR_syscalls -#define __NR_syscalls 441 +#define __NR_syscalls 442 /* * 32 bit systems traditionally used different diff --git a/kernel/exit.c b/kernel/exit.c index 733e80f334e7..62912406d74a 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1474,23 +1474,6 @@ end: return retval; } -static struct pid *pidfd_get_pid(unsigned int fd) -{ - struct fd f; - struct pid *pid; - - f = fdget(fd); - if (!f.file) - return ERR_PTR(-EBADF); - - pid = pidfd_pid(f.file); - if (!IS_ERR(pid)) - get_pid(pid); - - fdput(f); - return pid; -} - static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop, int options, struct rusage *ru) { diff --git a/kernel/pid.c b/kernel/pid.c index 2b97bedc1d9f..54e153ec6b74 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -519,6 +519,23 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns) return idr_get_next(&ns->idr, &nr); } +struct pid *pidfd_get_pid(unsigned int fd) +{ + struct fd f; + struct pid *pid; + + f = fdget(fd); + if (!f.file) + return ERR_PTR(-EBADF); + + pid = pidfd_pid(f.file); + if (!IS_ERR(pid)) + get_pid(pid); + + fdput(f); + return pid; +} + /** * pidfd_create() - Create a new pid file descriptor. * diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 66e05c695842..e060454b8bb5 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -283,6 +283,8 @@ COND_SYSCALL(mlockall); COND_SYSCALL(munlockall); COND_SYSCALL(mincore); COND_SYSCALL(madvise); +COND_SYSCALL(process_madvise); +COND_SYSCALL_COMPAT(process_madvise); COND_SYSCALL(remap_file_pages); COND_SYSCALL(mbind); COND_SYSCALL_COMPAT(mbind); diff --git a/mm/madvise.c b/mm/madvise.c index 12c3195b0fa5..e32e7efbba0f 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -22,12 +22,14 @@ #include <linux/file.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> +#include <linux/compat.h> #include <linux/pagewalk.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/shmem_fs.h> #include <linux/mmu_notifier.h> #include <linux/sched/mm.h> +#include <linux/uio.h> #include <asm/tlb.h> @@ -36,6 +38,7 @@ struct madvise_walk_private { struct mmu_gather *tlb; bool pageout; + struct task_struct *target_task; }; /* @@ -255,6 +258,7 @@ static long madvise_willneed(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end) { + struct mm_struct *mm = vma->vm_mm; struct file *file = vma->vm_file; loff_t offset; @@ -291,10 +295,10 @@ static long madvise_willneed(struct vm_area_struct *vma, get_file(file); offset = (loff_t)(start - vma->vm_start) + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); - mmap_read_unlock(current->mm); + mmap_read_unlock(mm); vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED); fput(file); - mmap_read_lock(current->mm); + mmap_read_lock(mm); return 0; } @@ -315,6 +319,10 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, if (fatal_signal_pending(current)) return -EINTR; + if (private->target_task && + fatal_signal_pending(private->target_task)) + return -EINTR; + #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (pmd_trans_huge(*pmd)) { pmd_t orig_pmd; @@ -476,12 +484,14 @@ static const struct mm_walk_ops cold_walk_ops = { }; static void madvise_cold_page_range(struct mmu_gather *tlb, + struct task_struct *task, struct vm_area_struct *vma, unsigned long addr, unsigned long end) { struct madvise_walk_private walk_private = { .pageout = false, .tlb = tlb, + .target_task = task, }; tlb_start_vma(tlb, vma); @@ -489,7 +499,8 @@ static void madvise_cold_page_range(struct mmu_gather *tlb, tlb_end_vma(tlb, vma); } -static long madvise_cold(struct vm_area_struct *vma, +static long madvise_cold(struct task_struct *task, + struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start_addr, unsigned long end_addr) { @@ -502,19 +513,21 @@ static long madvise_cold(struct vm_area_struct *vma, lru_add_drain(); tlb_gather_mmu(&tlb, mm, start_addr, end_addr); - madvise_cold_page_range(&tlb, vma, start_addr, end_addr); + madvise_cold_page_range(&tlb, task, vma, start_addr, end_addr); tlb_finish_mmu(&tlb, start_addr, end_addr); return 0; } static void madvise_pageout_page_range(struct mmu_gather *tlb, + struct task_struct *task, struct vm_area_struct *vma, unsigned long addr, unsigned long end) { struct madvise_walk_private walk_private = { .pageout = true, .tlb = tlb, + .target_task = task, }; tlb_start_vma(tlb, vma); @@ -538,7 +551,8 @@ static inline bool can_do_pageout(struct vm_area_struct *vma) inode_permission(file_inode(vma->vm_file), MAY_WRITE) == 0; } -static long madvise_pageout(struct vm_area_struct *vma, +static long madvise_pageout(struct task_struct *task, + struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start_addr, unsigned long end_addr) { @@ -554,7 +568,7 @@ static long madvise_pageout(struct vm_area_struct *vma, lru_add_drain(); tlb_gather_mmu(&tlb, mm, start_addr, end_addr); - madvise_pageout_page_range(&tlb, vma, start_addr, end_addr); + madvise_pageout_page_range(&tlb, task, vma, start_addr, end_addr); tlb_finish_mmu(&tlb, start_addr, end_addr); return 0; @@ -683,7 +697,6 @@ out: if (nr_swap) { if (current->mm == mm) sync_mm_rss(mm); - add_mm_counter(mm, MM_SWAPENTS, nr_swap); } arch_leave_lazy_mmu_mode(); @@ -763,6 +776,8 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, unsigned long start, unsigned long end, int behavior) { + struct mm_struct *mm = vma->vm_mm; + *prev = vma; if (!can_madv_lru_vma(vma)) return -EINVAL; @@ -770,8 +785,8 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, if (!userfaultfd_remove(vma, start, end)) { *prev = NULL; /* mmap_lock has been dropped, prev is stale */ - mmap_read_lock(current->mm); - vma = find_vma(current->mm, start); + mmap_read_lock(mm); + vma = find_vma(mm, start); if (!vma) return -ENOMEM; if (start < vma->vm_start) { @@ -825,6 +840,7 @@ static long madvise_remove(struct vm_area_struct *vma, loff_t offset; int error; struct file *f; + struct mm_struct *mm = vma->vm_mm; *prev = NULL; /* tell sys_madvise we drop mmap_lock */ @@ -852,13 +868,13 @@ static long madvise_remove(struct vm_area_struct *vma, get_file(f); if (userfaultfd_remove(vma, start, end)) { /* mmap_lock was not released by userfaultfd_remove() */ - mmap_read_unlock(current->mm); + mmap_read_unlock(mm); } error = vfs_fallocate(f, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, offset, end - start); fput(f); - mmap_read_lock(current->mm); + mmap_read_lock(mm); return error; } @@ -927,7 +943,8 @@ static int madvise_inject_error(int behavior, #endif static long -madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, +madvise_vma(struct task_struct *task, struct vm_area_struct *vma, + struct vm_area_struct **prev, unsigned long start, unsigned long end, int behavior) { switch (behavior) { @@ -936,9 +953,9 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, case MADV_WILLNEED: return madvise_willneed(vma, prev, start, end); case MADV_COLD: - return madvise_cold(vma, prev, start, end); + return madvise_cold(task, vma, prev, start, end); case MADV_PAGEOUT: - return madvise_pageout(vma, prev, start, end); + return madvise_pageout(task, vma, prev, start, end); case MADV_FREE: case MADV_DONTNEED: return madvise_dontneed_free(vma, prev, start, end, behavior); @@ -985,6 +1002,18 @@ madvise_behavior_valid(int behavior) } } +static bool +process_madvise_behavior_valid(int behavior) +{ + switch (behavior) { + case MADV_COLD: + case MADV_PAGEOUT: + return true; + default: + return false; + } +} + /* * The madvise(2) system call. * @@ -1032,6 +1061,11 @@ madvise_behavior_valid(int behavior) * MADV_DONTDUMP - the application wants to prevent pages in the given range * from being included in its core dump. * MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump. + * MADV_COLD - the application is not expected to use this memory soon, + * deactivate pages in this range so that they can be reclaimed + * easily if memory pressure hanppens. + * MADV_PAGEOUT - the application is not expected to use this memory soon, + * page out the pages in this range immediately. * * return values: * zero - success @@ -1046,7 +1080,8 @@ madvise_behavior_valid(int behavior) * -EBADF - map exists, but area maps something that isn't a file. * -EAGAIN - a kernel resource was temporarily unavailable. */ -int do_madvise(unsigned long start, size_t len_in, int behavior) +int do_madvise(struct task_struct *target_task, struct mm_struct *mm, + unsigned long start, size_t len_in, int behavior) { unsigned long end, tmp; struct vm_area_struct *vma, *prev; @@ -1084,7 +1119,7 @@ int do_madvise(unsigned long start, size_t len_in, int behavior) write = madvise_need_mmap_write(behavior); if (write) { - if (mmap_write_lock_killable(current->mm)) + if (mmap_write_lock_killable(mm)) return -EINTR; /* @@ -1099,12 +1134,12 @@ int do_madvise(unsigned long start, size_t len_in, int behavior) * but for now we have the mmget_still_valid() * model. */ - if (!mmget_still_valid(current->mm)) { - mmap_write_unlock(current->mm); + if (!mmget_still_valid(mm)) { + mmap_write_unlock(mm); return -EINTR; } } else { - mmap_read_lock(current->mm); + mmap_read_lock(mm); } /* @@ -1112,7 +1147,7 @@ int do_madvise(unsigned long start, size_t len_in, int behavior) * ranges, just ignore them, but return -ENOMEM at the end. * - different from the way of handling in mlock etc. */ - vma = find_vma_prev(current->mm, start, &prev); + vma = find_vma_prev(mm, start, &prev); if (vma && start > vma->vm_start) prev = vma; @@ -1137,7 +1172,8 @@ int do_madvise(unsigned long start, size_t len_in, int behavior) tmp = end; /* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */ - error = madvise_vma(vma, &prev, start, tmp, behavior); + error = madvise_vma(target_task, vma, &prev, + start, tmp, behavior); if (error) goto out; start = tmp; @@ -1149,19 +1185,122 @@ int do_madvise(unsigned long start, size_t len_in, int behavior) if (prev) vma = prev->vm_next; else /* madvise_remove dropped mmap_lock */ - vma = find_vma(current->mm, start); + vma = find_vma(mm, start); } out: blk_finish_plug(&plug); if (write) - mmap_write_unlock(current->mm); + mmap_write_unlock(mm); else - mmap_read_unlock(current->mm); + mmap_read_unlock(mm); return error; } SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) { - return do_madvise(start, len_in, behavior); + return do_madvise(current, current->mm, start, len_in, behavior); } + +static int process_madvise_vec(struct task_struct *target_task, + struct mm_struct *mm, struct iov_iter *iter, int behavior) +{ + struct iovec iovec; + int ret = 0; + + while (iov_iter_count(iter)) { + iovec = iov_iter_iovec(iter); + ret = do_madvise(target_task, mm, (unsigned long)iovec.iov_base, + iovec.iov_len, behavior); + if (ret < 0) + break; + iov_iter_advance(iter, iovec.iov_len); + } + + return ret; +} + +static ssize_t do_process_madvise(int pidfd, struct iov_iter *iter, + int behavior, unsigned int flags) +{ + ssize_t ret; + struct pid *pid; + struct task_struct *task; + struct mm_struct *mm; + size_t total_len = iov_iter_count(iter); + + if (flags != 0) + return -EINVAL; + + pid = pidfd_get_pid(pidfd); + if (IS_ERR(pid)) + return PTR_ERR(pid); + + task = get_pid_task(pid, PIDTYPE_PID); + if (!task) { + ret = -ESRCH; + goto put_pid; + } + + if (task->mm != current->mm && + !process_madvise_behavior_valid(behavior)) { + ret = -EINVAL; + goto release_task; + } + + mm = mm_access(task, PTRACE_MODE_ATTACH_FSCREDS); + if (IS_ERR_OR_NULL(mm)) { + ret = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH; + goto release_task; + } + + ret = process_madvise_vec(task, mm, iter, behavior); + if (ret >= 0) + ret = total_len - iov_iter_count(iter); + + mmput(mm); +release_task: + put_task_struct(task); +put_pid: + put_pid(pid); + return ret; +} + +SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec, + unsigned long, vlen, int, behavior, unsigned int, flags) +{ + ssize_t ret; + struct iovec iovstack[UIO_FASTIOV]; + struct iovec *iov = iovstack; + struct iov_iter iter; + + ret = import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); + if (ret >= 0) { + ret = do_process_madvise(pidfd, &iter, behavior, flags); + kfree(iov); + } + return ret; +} + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE5(process_madvise, compat_int_t, pidfd, + const struct compat_iovec __user *, vec, + compat_ulong_t, vlen, + compat_int_t, behavior, + compat_uint_t, flags) + +{ + ssize_t ret; + struct iovec iovstack[UIO_FASTIOV]; + struct iovec *iov = iovstack; + struct iov_iter iter; + + ret = compat_import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack), + &iov, &iter); + if (ret >= 0) { + ret = do_process_madvise(pidfd, &iter, behavior, flags); + kfree(iov); + } + return ret; +} +#endif diff --git a/mm/memory-failure.c b/mm/memory-failure.c index f56cda87f03e..696505f56910 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1677,16 +1677,6 @@ int unpoison_memory(unsigned long pfn) } EXPORT_SYMBOL(unpoison_memory); -static struct page *new_page(struct page *p, unsigned long private) -{ - struct migration_target_control mtc = { - .nid = page_to_nid(p), - .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, - }; - - return alloc_migration_target(p, (unsigned long)&mtc); -} - /* * Safely get reference count of an arbitrary page. * Returns 0 for a free page, -EIO for a zero refcount page @@ -1801,6 +1791,10 @@ static int __soft_offline_page(struct page *page) char const *msg_page[] = {"page", "hugepage"}; bool huge = PageHuge(page); LIST_HEAD(pagelist); + struct migration_target_control mtc = { + .nid = NUMA_NO_NODE, + .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, + }; /* * Check PageHWPoison again inside page lock because PageHWPoison @@ -1837,8 +1831,8 @@ static int __soft_offline_page(struct page *page) } if (isolate_page(hpage, &pagelist)) { - ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, - MIGRATE_SYNC, MR_MEMORY_FAILURE); + ret = migrate_pages(&pagelist, alloc_migration_target, NULL, + (unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_FAILURE); if (!ret) { bool release = !huge; diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 7a129e1170d7..7562c29eebb3 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1286,27 +1286,6 @@ found: return 0; } -static struct page *new_node_page(struct page *page, unsigned long private) -{ - nodemask_t nmask = node_states[N_MEMORY]; - struct migration_target_control mtc = { - .nid = page_to_nid(page), - .nmask = &nmask, - .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, - }; - - /* - * try to allocate from a different node but reuse this node if there - * are no other online nodes to be used (e.g. we are offlining a part - * of the only existing node) - */ - node_clear(mtc.nid, nmask); - if (nodes_empty(nmask)) - node_set(mtc.nid, nmask); - - return alloc_migration_target(page, (unsigned long)&mtc); -} - static int do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) { @@ -1366,9 +1345,28 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) put_page(page); } if (!list_empty(&source)) { - /* Allocate a new page from the nearest neighbor node */ - ret = migrate_pages(&source, new_node_page, NULL, 0, - MIGRATE_SYNC, MR_MEMORY_HOTPLUG); + nodemask_t nmask = node_states[N_MEMORY]; + struct migration_target_control mtc = { + .nmask = &nmask, + .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, + }; + + /* + * We have checked that migration range is on a single zone so + * we can use the nid of the first page to all the others. + */ + mtc.nid = page_to_nid(list_first_entry(&source, struct page, lru)); + + /* + * try to allocate from a different node but reuse this node + * if there are no other online nodes to be used (e.g. we are + * offlining a part of the only existing node) + */ + node_clear(mtc.nid, nmask); + if (nodes_empty(nmask)) + node_set(mtc.nid, nmask); + ret = migrate_pages(&source, alloc_migration_target, NULL, + (unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_HOTPLUG); if (ret) { list_for_each_entry(page, &source, lru) { pr_warn("migrating pfn %lx failed ret:%d ", diff --git a/mm/migrate.c b/mm/migrate.c index 4dcb1f6b320b..0b945c8031be 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1864,33 +1864,27 @@ static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages, return nr_pages ? -EFAULT : 0; } -/* - * Move a list of pages in the address space of the currently executing - * process. - */ -static int kernel_move_pages(pid_t pid, unsigned long nr_pages, - const void __user * __user *pages, - const int __user *nodes, - int __user *status, int flags) +static struct mm_struct *find_mm_struct(pid_t pid, nodemask_t *mem_nodes) { struct task_struct *task; struct mm_struct *mm; - int err; - nodemask_t task_nodes; - - /* Check flags */ - if (flags & ~(MPOL_MF_MOVE|MPOL_MF_MOVE_ALL)) - return -EINVAL; - if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE)) - return -EPERM; + /* + * There is no need to check if current process has the right to modify + * the specified process when they are same. + */ + if (!pid) { + mmget(current->mm); + *mem_nodes = cpuset_mems_allowed(current); + return current->mm; + } /* Find the mm_struct */ rcu_read_lock(); - task = pid ? find_task_by_vpid(pid) : current; + task = find_task_by_vpid(pid); if (!task) { rcu_read_unlock(); - return -ESRCH; + return ERR_PTR(-ESRCH); } get_task_struct(task); @@ -1900,22 +1894,47 @@ static int kernel_move_pages(pid_t pid, unsigned long nr_pages, */ if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) { rcu_read_unlock(); - err = -EPERM; + mm = ERR_PTR(-EPERM); goto out; } rcu_read_unlock(); - err = security_task_movememory(task); - if (err) + mm = ERR_PTR(security_task_movememory(task)); + if (IS_ERR(mm)) goto out; - - task_nodes = cpuset_mems_allowed(task); + *mem_nodes = cpuset_mems_allowed(task); mm = get_task_mm(task); +out: put_task_struct(task); - if (!mm) + mm = ERR_PTR(-EINVAL); + return mm; +} + +/* + * Move a list of pages in the address space of the currently executing + * process. + */ +static int kernel_move_pages(pid_t pid, unsigned long nr_pages, + const void __user * __user *pages, + const int __user *nodes, + int __user *status, int flags) +{ + struct mm_struct *mm; + int err; + nodemask_t task_nodes; + + /* Check flags */ + if (flags & ~(MPOL_MF_MOVE|MPOL_MF_MOVE_ALL)) return -EINVAL; + if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE)) + return -EPERM; + + mm = find_mm_struct(pid, &task_nodes); + if (IS_ERR(mm)) + return PTR_ERR(mm); + if (nodes) err = do_pages_move(mm, task_nodes, nr_pages, pages, nodes, status, flags); @@ -1924,10 +1943,6 @@ static int kernel_move_pages(pid_t pid, unsigned long nr_pages, mmput(mm); return err; - -out: - put_task_struct(task); - return err; } SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages, diff --git a/mm/mmap.c b/mm/mmap.c index 76e97b26581b..fe8d088f1487 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -558,6 +558,50 @@ static int find_vma_links(struct mm_struct *mm, unsigned long addr, return 0; } +/* + * vma_next() - Get the next VMA. + * @mm: The mm_struct. + * @vma: The current vma. + * + * If @vma is NULL, return the first vma in the mm. + * + * Returns: The next VMA after @vma. + */ +static inline struct vm_area_struct *vma_next(struct mm_struct *mm, + struct vm_area_struct *vma) +{ + if (!vma) + return mm->mmap; + + return vma->vm_next; +} + +/* + * munmap_vma_range() - munmap VMAs that overlap a range. + * @mm: The mm struct + * @start: The start of the range. + * @len: The length of the range. + * @pprev: pointer to the pointer that will be set to previous vm_area_struct + * @rb_link: the rb_node + * @rb_parent: the parent rb_node + * + * Find all the vm_area_struct that overlap from @start to + * @end and munmap them. Set @pprev to the previous vm_area_struct. + * + * Returns: -ENOMEM on munmap failure or 0 on success. + */ +static inline int +munmap_vma_range(struct mm_struct *mm, unsigned long start, unsigned long len, + struct vm_area_struct **pprev, struct rb_node ***link, + struct rb_node **parent, struct list_head *uf) +{ + + while (find_vma_links(mm, start, start + len, pprev, link, parent)) + if (do_munmap(mm, start, len, uf)) + return -ENOMEM; + + return 0; +} static unsigned long count_vma_pages_range(struct mm_struct *mm, unsigned long addr, unsigned long end) { @@ -1129,10 +1173,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, if (vm_flags & VM_SPECIAL) return NULL; - if (prev) - next = prev->vm_next; - else - next = mm->mmap; + next = vma_next(mm, prev); area = next; if (area && area->vm_end == end) /* cases 6, 7, 8 */ next = next->vm_next; @@ -1708,13 +1749,9 @@ unsigned long mmap_region(struct file *file, unsigned long addr, return -ENOMEM; } - /* Clear old maps */ - while (find_vma_links(mm, addr, addr + len, &prev, &rb_link, - &rb_parent)) { - if (do_munmap(mm, addr, len, uf)) - return -ENOMEM; - } - + /* Clear old maps, set up prev, rb_link, rb_parent, and uf */ + if (munmap_vma_range(mm, addr, len, &prev, &rb_link, &rb_parent, uf)) + return -ENOMEM; /* * Private writable mapping: check memory availability */ @@ -2638,7 +2675,7 @@ static void unmap_region(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, unsigned long start, unsigned long end) { - struct vm_area_struct *next = prev ? prev->vm_next : mm->mmap; + struct vm_area_struct *next = vma_next(mm, prev); struct mmu_gather tlb; lru_add_drain(); @@ -2837,7 +2874,7 @@ int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len, if (error) return error; } - vma = prev ? prev->vm_next : mm->mmap; + vma = vma_next(mm, prev); if (unlikely(uf)) { /* @@ -3055,14 +3092,9 @@ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long fla if (error) return error; - /* - * Clear old maps. this also does some error checking for us - */ - while (find_vma_links(mm, addr, addr + len, &prev, &rb_link, - &rb_parent)) { - if (do_munmap(mm, addr, len, uf)) - return -ENOMEM; - } + /* Clear old maps, set up prev, rb_link, rb_parent, and uf */ + if (munmap_vma_range(mm, addr, len, &prev, &rb_link, &rb_parent, uf)) + return -ENOMEM; /* Check against address space limits *after* clearing old maps... */ if (!may_expand_vm(mm, flags, len >> PAGE_SHIFT)) |