diff options
author | Stephen Rothwell <sfr@canb.auug.org.au> | 2020-07-20 18:29:44 +1000 |
---|---|---|
committer | Stephen Rothwell <sfr@canb.auug.org.au> | 2020-07-20 18:29:44 +1000 |
commit | 61c2dbfd4f3fb10e574f8779763900afb6d60ac6 (patch) | |
tree | ba3c722c12bb3726f6fc9587c4dea8c55642633c | |
parent | 9dfa5c1dcba0b1e2f06cbc3061d3e1ae5feaea15 (diff) | |
parent | d3a0b365954e5e4728b6a92b171e4659199c6db5 (diff) | |
download | linux-next-61c2dbfd4f3fb10e574f8779763900afb6d60ac6.tar.gz |
Merge branch 'akpm/master'
133 files changed, 669 insertions, 856 deletions
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index 86ee19c1dc15..2e156975f573 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -249,7 +249,7 @@ 316 common mlockall sys_mlockall 317 common munlockall sys_munlockall 318 common sysinfo sys_sysinfo -319 common _sysctl sys_sysctl +319 common _sysctl sys_ni_syscall # 320 was sys_idle 321 common oldumount sys_oldumount 322 common swapon sys_swapon @@ -482,3 +482,4 @@ 550 common watch_mount sys_watch_mount 551 common watch_sb sys_watch_sb 552 common fsinfo sys_fsinfo +553 common process_madvise sys_process_madvise diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index c2303a8c2b9f..09172f017efc 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -25,6 +25,7 @@ #include <linux/interrupt.h> #include <linux/extable.h> #include <linux/uaccess.h> +#include <linux/perf_event.h> extern void die_if_kernel(char *,struct pt_regs *,long, unsigned long *); @@ -116,6 +117,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr, #endif if (user_mode(regs)) flags |= FAULT_FLAG_USER; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); retry: mmap_read_lock(mm); vma = find_vma(mm, address); @@ -148,7 +150,7 @@ retry: /* If for any reason at all we couldn't handle the fault, make sure we exit gracefully rather than endlessly redo the fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) return; @@ -164,10 +166,6 @@ retry: } if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index 105420c23c8b..a1d2eea66bba 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -91,7 +91,7 @@ fault: goto fail; mmap_read_lock(current->mm); - ret = fixup_user_fault(current, current->mm, (unsigned long) uaddr, + ret = fixup_user_fault(current->mm, (unsigned long) uaddr, FAULT_FLAG_WRITE, NULL); mmap_read_unlock(current->mm); diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index 7287c793d1c9..f5657cb68e4f 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -105,6 +105,7 @@ void do_page_fault(unsigned long address, struct pt_regs *regs) if (write) flags |= FAULT_FLAG_WRITE; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); retry: mmap_read_lock(mm); @@ -130,7 +131,7 @@ retry: goto bad_area; } - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { @@ -155,22 +156,9 @@ bad_area: * Major/minor page fault accounting * (in case of retry we only land here once) */ - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); - - if (likely(!(fault & VM_FAULT_ERROR))) { - if (fault & VM_FAULT_MAJOR) { - tsk->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, - regs, address); - } else { - tsk->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, - regs, address); - } - + if (likely(!(fault & VM_FAULT_ERROR))) /* Normal return path: fault Handled Gracefully */ return; - } if (!user_mode(regs)) goto no_context; diff --git a/arch/arm/configs/am200epdkit_defconfig b/arch/arm/configs/am200epdkit_defconfig index f56ac394caf1..4e49d6cb2f62 100644 --- a/arch/arm/configs/am200epdkit_defconfig +++ b/arch/arm/configs/am200epdkit_defconfig @@ -3,7 +3,6 @@ CONFIG_LOCALVERSION="gum" CONFIG_SYSVIPC=y CONFIG_SYSFS_DEPRECATED_V2=y CONFIG_EXPERT=y -# CONFIG_SYSCTL_SYSCALL is not set # CONFIG_EPOLL is not set # CONFIG_SHMEM is not set # CONFIG_VM_EVENT_COUNTERS is not set diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index c6550eddfce1..efa402025031 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -202,7 +202,8 @@ static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma) static vm_fault_t __kprobes __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr, - unsigned int flags, struct task_struct *tsk) + unsigned int flags, struct task_struct *tsk, + struct pt_regs *regs) { struct vm_area_struct *vma; vm_fault_t fault; @@ -224,7 +225,7 @@ good_area: goto out; } - return handle_mm_fault(vma, addr & PAGE_MASK, flags); + return handle_mm_fault(vma, addr & PAGE_MASK, flags, regs); check_stack: /* Don't allow expansion below FIRST_USER_ADDRESS */ @@ -266,6 +267,8 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if ((fsr & FSR_WRITE) && !(fsr & FSR_CM)) flags |= FAULT_FLAG_WRITE; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); + /* * As per x86, we may deadlock here. However, since the kernel only * validly references user space from well defined areas of the code, @@ -290,7 +293,7 @@ retry: #endif } - fault = __do_page_fault(mm, addr, fsr, flags, tsk); + fault = __do_page_fault(mm, addr, fsr, flags, tsk, regs); /* If we need to retry but a fatal signal is pending, handle the * signal first. We do not need to release the mmap_lock because @@ -302,23 +305,7 @@ retry: return 0; } - /* - * Major/minor page fault accounting is only done on the - * initial attempt. If we go through a retry, it is extremely - * likely that the page will be found in page cache at that point. - */ - - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); if (!(fault & VM_FAULT_ERROR) && flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) { - tsk->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, - regs, addr); - } else { - tsk->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, - regs, addr); - } if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; goto retry; diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index 91b97d51acef..b166a5383a60 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -162,7 +162,7 @@ 146 common writev sys_writev 147 common getsid sys_getsid 148 common fdatasync sys_fdatasync -149 common _sysctl sys_sysctl +149 common _sysctl sys_ni_syscall 150 common mlock sys_mlock 151 common munlock sys_munlock 152 common mlockall sys_mlockall @@ -456,3 +456,4 @@ 440 common watch_mount sys_watch_mount 441 common watch_sb sys_watch_sb 442 common fsinfo sys_fsinfo +443 common process_madvise sys_process_madvise diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 949788f5ba40..d1f7d35f986e 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 443 +#define __NR_compat_syscalls 444 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 9822cc41915f..7d2ba5bd7e04 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -308,8 +308,8 @@ __SYSCALL(__NR_writev, compat_sys_writev) __SYSCALL(__NR_getsid, sys_getsid) #define __NR_fdatasync 148 __SYSCALL(__NR_fdatasync, sys_fdatasync) -#define __NR__sysctl 149 -__SYSCALL(__NR__sysctl, compat_sys_sysctl) + /* 149 was sys_sysctl */ +__SYSCALL(149, sys_ni_syscall) #define __NR_mlock 150 __SYSCALL(__NR_mlock, sys_mlock) #define __NR_munlock 151 @@ -893,6 +893,8 @@ __SYSCALL(__NR_watch_mount, sys_watch_mount) __SYSCALL(__NR_watch_sb, sys_watch_sb) #define __NR_fsinfo 442 __SYSCALL(__NR_fsinfo, sys_fsinfo) +#define __NR_process_madvise 443 +__SYSCALL(__NR_process_madvise, compat_sys_process_madvise) /* * Please add new compat syscalls above this comment and update diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index eb39504e390a..bd2aad4616ba 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -227,7 +227,7 @@ static int __access_remote_tags(struct task_struct *tsk, struct mm_struct *mm, void *maddr; struct page *page = NULL; - ret = get_user_pages_remote(tsk, mm, addr, 1, gup_flags, + ret = get_user_pages_remote(mm, addr, 1, gup_flags, &page, &vma, NULL); if (ret <= 0) break; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 5e832b3387f1..a3bd189602df 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -404,7 +404,8 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re #define VM_FAULT_BADACCESS 0x020000 static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr, - unsigned int mm_flags, unsigned long vm_flags) + unsigned int mm_flags, unsigned long vm_flags, + struct pt_regs *regs) { struct vm_area_struct *vma = find_vma(mm, addr); @@ -428,7 +429,7 @@ static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr, */ if (!(vma->vm_flags & vm_flags)) return VM_FAULT_BADACCESS; - return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags); + return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags, regs); } static bool is_el0_instruction_abort(unsigned int esr) @@ -450,7 +451,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, { const struct fault_info *inf; struct mm_struct *mm = current->mm; - vm_fault_t fault, major = 0; + vm_fault_t fault; unsigned long vm_flags = VM_ACCESS_FLAGS; unsigned int mm_flags = FAULT_FLAG_DEFAULT; @@ -516,8 +517,7 @@ retry: #endif } - fault = __do_page_fault(mm, addr, mm_flags, vm_flags); - major |= fault & VM_FAULT_MAJOR; + fault = __do_page_fault(mm, addr, mm_flags, vm_flags, regs); /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { @@ -538,25 +538,8 @@ retry: * Handle the "normal" (no error) case first. */ if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP | - VM_FAULT_BADACCESS)))) { - /* - * Major/minor page fault accounting is only done - * once. If we go through a retry, it is extremely - * likely that the page will be found in page cache at - * that point. - */ - if (major) { - current->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, - addr); - } else { - current->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, - addr); - } - + VM_FAULT_BADACCESS)))) return 0; - } /* * If we are in kernel mode at this point, we have no context to diff --git a/arch/csky/mm/fault.c b/arch/csky/mm/fault.c index 0b9cbf2cf6a9..c3f580714ee4 100644 --- a/arch/csky/mm/fault.c +++ b/arch/csky/mm/fault.c @@ -150,7 +150,8 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(vma, address, write ? FAULT_FLAG_WRITE : 0); + fault = handle_mm_fault(vma, address, write ? FAULT_FLAG_WRITE : 0, + regs); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; @@ -160,16 +161,6 @@ good_area: goto bad_area; BUG(); } - if (fault & VM_FAULT_MAJOR) { - tsk->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, - address); - } else { - tsk->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, - address); - } - mmap_read_unlock(mm); return; diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c index cd3808f96b93..ef32c5a84ff3 100644 --- a/arch/hexagon/mm/vm_fault.c +++ b/arch/hexagon/mm/vm_fault.c @@ -18,6 +18,7 @@ #include <linux/signal.h> #include <linux/extable.h> #include <linux/hardirq.h> +#include <linux/perf_event.h> /* * Decode of hardware exception sends us to one of several @@ -53,6 +54,8 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs) if (user_mode(regs)) flags |= FAULT_FLAG_USER; + + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); retry: mmap_read_lock(mm); vma = find_vma(mm, address); @@ -88,7 +91,7 @@ good_area: break; } - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) return; @@ -96,10 +99,6 @@ good_area: /* The most common case -- we are done. */ if (likely(!(fault & VM_FAULT_ERROR))) { if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; goto retry; diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index e6c9396811bb..71337e11f01c 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -135,7 +135,7 @@ 123 common writev sys_writev 124 common pread64 sys_pread64 125 common pwrite64 sys_pwrite64 -126 common _sysctl sys_sysctl +126 common _sysctl sys_ni_syscall 127 common mmap sys_mmap 128 common munmap sys_munmap 129 common mlock sys_mlock @@ -363,3 +363,4 @@ 440 common watch_mount sys_watch_mount 441 common watch_sb sys_watch_sb 442 common fsinfo sys_fsinfo +443 common process_madvise sys_process_madvise diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 3a4dec334cc5..cd9766d2b6e0 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -14,6 +14,7 @@ #include <linux/kdebug.h> #include <linux/prefetch.h> #include <linux/uaccess.h> +#include <linux/perf_event.h> #include <asm/processor.h> #include <asm/exception.h> @@ -105,6 +106,8 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re flags |= FAULT_FLAG_USER; if (mask & VM_WRITE) flags |= FAULT_FLAG_WRITE; + + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); retry: mmap_read_lock(mm); @@ -143,7 +146,7 @@ retry: * sure we exit gracefully rather than endlessly redo the * fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) return; @@ -166,10 +169,6 @@ retry: } if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index cc042ace0494..460fb0f9bb4b 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -156,7 +156,7 @@ 146 common writev sys_writev 147 common getsid sys_getsid 148 common fdatasync sys_fdatasync -149 common _sysctl sys_sysctl +149 common _sysctl sys_ni_syscall 150 common mlock sys_mlock 151 common munlock sys_munlock 152 common mlockall sys_mlockall @@ -442,3 +442,4 @@ 440 common watch_mount sys_watch_mount 441 common watch_sb sys_watch_sb 442 common fsinfo sys_fsinfo +443 common process_madvise sys_process_madvise diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index 508abb63da67..795f483b1050 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -12,6 +12,7 @@ #include <linux/interrupt.h> #include <linux/module.h> #include <linux/uaccess.h> +#include <linux/perf_event.h> #include <asm/setup.h> #include <asm/traps.h> @@ -84,6 +85,8 @@ int do_page_fault(struct pt_regs *regs, unsigned long address, if (user_mode(regs)) flags |= FAULT_FLAG_USER; + + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); retry: mmap_read_lock(mm); @@ -134,7 +137,7 @@ good_area: * the fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); pr_debug("handle_mm_fault returns %x\n", fault); if (fault_signal_pending(fault, regs)) @@ -150,16 +153,7 @@ good_area: BUG(); } - /* - * Major/minor page fault accounting is only done on the - * initial attempt. If we go through a retry, it is extremely - * likely that the page will be found in page cache at that point. - */ if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index a9f647b045f7..a95897a4ea76 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -156,7 +156,7 @@ 146 common writev sys_writev 147 common getsid sys_getsid 148 common fdatasync sys_fdatasync -149 common _sysctl sys_sysctl +149 common _sysctl sys_ni_syscall 150 common mlock sys_mlock 151 common munlock sys_munlock 152 common mlockall sys_mlockall @@ -448,3 +448,4 @@ 440 common watch_mount sys_watch_mount 441 common watch_sb sys_watch_sb 442 common fsinfo sys_fsinfo +443 common process_madvise sys_process_madvise diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index a2bfe587b491..b3fed2cecf84 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -28,6 +28,7 @@ #include <linux/mman.h> #include <linux/mm.h> #include <linux/interrupt.h> +#include <linux/perf_event.h> #include <asm/page.h> #include <asm/mmu.h> @@ -121,6 +122,8 @@ void do_page_fault(struct pt_regs *regs, unsigned long address, if (user_mode(regs)) flags |= FAULT_FLAG_USER; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); + /* When running in the kernel we expect faults to occur only to * addresses in user space. All other faults represent errors in the * kernel and should generate an OOPS. Unfortunately, in the case of an @@ -214,7 +217,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) return; @@ -230,10 +233,6 @@ good_area: } if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (unlikely(fault & VM_FAULT_MAJOR)) - current->maj_flt++; - else - current->min_flt++; if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/mips/configs/cu1000-neo_defconfig b/arch/mips/configs/cu1000-neo_defconfig index 6b471cdb16cf..e924c817f73d 100644 --- a/arch/mips/configs/cu1000-neo_defconfig +++ b/arch/mips/configs/cu1000-neo_defconfig @@ -17,7 +17,6 @@ CONFIG_CGROUP_CPUACCT=y CONFIG_NAMESPACES=y CONFIG_USER_NS=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y -CONFIG_SYSCTL_SYSCALL=y CONFIG_KALLSYMS_ALL=y CONFIG_EMBEDDED=y # CONFIG_VM_EVENT_COUNTERS is not set diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index bd15c759ad97..5ede2681f4e1 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -159,7 +159,7 @@ 149 n32 munlockall sys_munlockall 150 n32 vhangup sys_vhangup 151 n32 pivot_root sys_pivot_root -152 n32 _sysctl compat_sys_sysctl +152 n32 _sysctl sys_ni_syscall 153 n32 prctl sys_prctl 154 n32 adjtimex sys_adjtimex_time32 155 n32 setrlimit compat_sys_setrlimit @@ -381,3 +381,4 @@ 440 n32 watch_mount sys_watch_mount 441 n32 watch_sb sys_watch_sb 442 n32 fsinfo sys_fsinfo +443 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 b2b9538535e6..daa607c4afe6 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -159,7 +159,7 @@ 149 n64 munlockall sys_munlockall 150 n64 vhangup sys_vhangup 151 n64 pivot_root sys_pivot_root -152 n64 _sysctl sys_sysctl +152 n64 _sysctl sys_ni_syscall 153 n64 prctl sys_prctl 154 n64 adjtimex sys_adjtimex 155 n64 setrlimit sys_setrlimit @@ -357,3 +357,4 @@ 440 n64 watch_mount sys_watch_mount 441 n64 watch_sb sys_watch_sb 442 n64 fsinfo sys_fsinfo +443 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 bea3d6e34711..0dffd81fb345 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -164,7 +164,7 @@ 150 o32 unused150 sys_ni_syscall 151 o32 getsid sys_getsid 152 o32 fdatasync sys_fdatasync -153 o32 _sysctl sys_sysctl compat_sys_sysctl +153 o32 _sysctl sys_ni_syscall 154 o32 mlock sys_mlock 155 o32 munlock sys_munlock 156 o32 mlockall sys_mlockall @@ -430,3 +430,4 @@ 440 o32 watch_mount sys_watch_mount 441 o32 watch_sb sys_watch_sb 442 o32 fsinfo sys_fsinfo +443 o32 process_madvise sys_process_madvise compat_sys_process_madvise diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index 01b168a90434..7c871b14e74a 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -96,6 +96,8 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write, if (user_mode(regs)) flags |= FAULT_FLAG_USER; + + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); retry: mmap_read_lock(mm); vma = find_vma(mm, address); @@ -152,12 +154,11 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) return; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; @@ -168,15 +169,6 @@ good_area: BUG(); } if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) { - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, - regs, address); - tsk->maj_flt++; - } else { - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, - regs, address); - tsk->min_flt++; - } if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/nds32/mm/fault.c b/arch/nds32/mm/fault.c index 8fb73f6401a0..f02524eb6d56 100644 --- a/arch/nds32/mm/fault.c +++ b/arch/nds32/mm/fault.c @@ -121,6 +121,8 @@ void do_page_fault(unsigned long entry, unsigned long addr, if (unlikely(faulthandler_disabled() || !mm)) goto no_context; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); + /* * As per x86, we may deadlock here. However, since the kernel only * validly references user space from well defined areas of the code, @@ -206,7 +208,7 @@ good_area: * the fault. */ - fault = handle_mm_fault(vma, addr, flags); + fault = handle_mm_fault(vma, addr, flags, regs); /* * If we need to retry but a fatal signal is pending, handle the @@ -228,22 +230,7 @@ good_area: goto bad_area; } - /* - * Major/minor page fault accounting is only done on the initial - * attempt. If we go through a retry, it is extremely likely that the - * page will be found in page cache at that point. - */ - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) { - tsk->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, - 1, regs, addr); - } else { - tsk->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, - 1, regs, addr); - } if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c index 4112ef0e247e..9476feecf512 100644 --- a/arch/nios2/mm/fault.c +++ b/arch/nios2/mm/fault.c @@ -24,6 +24,7 @@ #include <linux/mm.h> #include <linux/extable.h> #include <linux/uaccess.h> +#include <linux/perf_event.h> #include <asm/mmu_context.h> #include <asm/traps.h> @@ -83,6 +84,8 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause, if (user_mode(regs)) flags |= FAULT_FLAG_USER; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); + if (!mmap_read_trylock(mm)) { if (!user_mode(regs) && !search_exception_tables(regs->ea)) goto bad_area_nosemaphore; @@ -131,7 +134,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) return; @@ -146,16 +149,7 @@ good_area: BUG(); } - /* - * Major/minor page fault accounting is only done on the - * initial attempt. If we go through a retry, it is extremely - * likely that the page will be found in page cache at that point. - */ if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index d2224ccca294..ca97d9baab51 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -15,6 +15,7 @@ #include <linux/interrupt.h> #include <linux/extable.h> #include <linux/sched/signal.h> +#include <linux/perf_event.h> #include <linux/uaccess.h> #include <asm/siginfo.h> @@ -103,6 +104,8 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address, if (in_interrupt() || !mm) goto no_context; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); + retry: mmap_read_lock(mm); vma = find_vma(mm, address); @@ -159,7 +162,7 @@ good_area: * the fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) return; @@ -176,10 +179,6 @@ good_area: if (flags & FAULT_FLAG_ALLOW_RETRY) { /*RGD modeled on Cris */ - if (fault & VM_FAULT_MAJOR) - tsk->maj_flt++; - else - tsk->min_flt++; if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index 43bbdce3237f..09ac0b4aac30 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -163,7 +163,7 @@ 146 common writev sys_writev compat_sys_writev 147 common getsid sys_getsid 148 common fdatasync sys_fdatasync -149 common _sysctl sys_sysctl compat_sys_sysctl +149 common _sysctl sys_ni_syscall 150 common mlock sys_mlock 151 common munlock sys_munlock 152 common mlockall sys_mlockall @@ -440,3 +440,4 @@ 440 common watch_mount sys_watch_mount 441 common watch_sb sys_watch_sb 442 common fsinfo sys_fsinfo +443 common process_madvise sys_process_madvise compat_sys_process_madvise diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 66ac0719bd49..4bfe2da9fbe3 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -18,6 +18,7 @@ #include <linux/extable.h> #include <linux/uaccess.h> #include <linux/hugetlb.h> +#include <linux/perf_event.h> #include <asm/traps.h> @@ -281,6 +282,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long code, acc_type = parisc_acctyp(code, regs->iir); if (acc_type & VM_WRITE) flags |= FAULT_FLAG_WRITE; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); retry: mmap_read_lock(mm); vma = find_vma_prev(mm, address, &prev_vma); @@ -302,7 +304,7 @@ good_area: * fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) return; @@ -323,10 +325,6 @@ good_area: BUG(); } if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; if (fault & VM_FAULT_RETRY) { /* * No need to mmap_read_unlock(mm) as we would diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 93355266885f..df783ec47ca4 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -197,7 +197,7 @@ 146 common writev sys_writev compat_sys_writev 147 common getsid sys_getsid 148 common fdatasync sys_fdatasync -149 nospu _sysctl sys_sysctl compat_sys_sysctl +149 nospu _sysctl sys_ni_syscall 150 common mlock sys_mlock 151 common munlock sys_munlock 152 common mlockall sys_mlockall @@ -532,3 +532,4 @@ 440 common watch_mount sys_watch_mount 441 common watch_sb sys_watch_sb 442 common fsinfo sys_fsinfo +443 common process_madvise sys_process_madvise compat_sys_process_madvise diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c index b83abbead4a2..8acd00178956 100644 --- a/arch/powerpc/mm/copro_fault.c +++ b/arch/powerpc/mm/copro_fault.c @@ -64,7 +64,7 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea, } ret = 0; - *flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0); + *flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0, NULL); if (unlikely(*flt & VM_FAULT_ERROR)) { if (*flt & VM_FAULT_OOM) { ret = -ENOMEM; @@ -76,11 +76,6 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea, BUG(); } - if (*flt & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; - out_unlock: mmap_read_unlock(mm); return ret; diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 641fc5f3d7dd..00259e9b452d 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -607,7 +607,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); major |= fault & VM_FAULT_MAJOR; @@ -633,14 +633,9 @@ good_area: /* * Major/minor page fault accounting. */ - if (major) { - current->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); + if (major) cmo_account_page_fault(); - } else { - current->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); - } + return 0; } NOKPROBE_SYMBOL(__do_page_fault); diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 5873835a3e6b..716d64e36f83 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -109,7 +109,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(vma, addr, flags); + fault = handle_mm_fault(vma, addr, flags, regs); /* * If we need to retry but a fatal signal is pending, handle the @@ -127,21 +127,7 @@ good_area: BUG(); } - /* - * Major/minor page fault accounting is only done on the - * initial attempt. If we go through a retry, it is extremely - * likely that the page will be found in page cache at that point. - */ if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) { - tsk->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, - 1, regs, addr); - } else { - tsk->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, - 1, regs, addr); - } if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index 621085153509..51c8a704a119 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -138,7 +138,7 @@ 146 common writev sys_writev compat_sys_writev 147 common getsid sys_getsid sys_getsid 148 common fdatasync sys_fdatasync sys_fdatasync -149 common _sysctl sys_sysctl compat_sys_sysctl +149 common _sysctl - - 150 common mlock sys_mlock sys_mlock 151 common munlock sys_munlock sys_munlock 152 common mlockall sys_mlockall sys_mlockall @@ -445,3 +445,4 @@ 440 common watch_mount sys_watch_mount sys_watch_mount 441 common watch_sb sys_watch_sb sys_watch_sb 442 common fsinfo sys_fsinfo sys_fsinfo +443 common process_madvise sys_process_madvise compat_sys_process_madvise diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 1608fd99bbee..2f177298c663 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -2768,7 +2768,7 @@ static struct page *get_map_page(struct kvm *kvm, u64 uaddr) struct page *page = NULL; mmap_read_lock(kvm->mm); - get_user_pages_remote(NULL, kvm->mm, uaddr, 1, FOLL_WRITE, + get_user_pages_remote(kvm->mm, uaddr, 1, FOLL_WRITE, &page, NULL, NULL); mmap_read_unlock(kvm->mm); return page; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 66da278a67fb..6b74b92c1a58 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1892,7 +1892,7 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) r = set_guest_storage_key(current->mm, hva, keys[i], 0); if (r) { - r = fixup_user_fault(current, current->mm, hva, + r = fixup_user_fault(current->mm, hva, FAULT_FLAG_WRITE, &unlocked); if (r) break; diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 2f721a923b54..cd74989ce0b0 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -273,7 +273,7 @@ retry: rc = get_guest_storage_key(current->mm, vmaddr, &key); if (rc) { - rc = fixup_user_fault(current, current->mm, vmaddr, + rc = fixup_user_fault(current->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked); if (!rc) { mmap_read_unlock(current->mm); @@ -319,7 +319,7 @@ retry: mmap_read_lock(current->mm); rc = reset_guest_reference_bit(current->mm, vmaddr); if (rc < 0) { - rc = fixup_user_fault(current, current->mm, vmaddr, + rc = fixup_user_fault(current->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked); if (!rc) { mmap_read_unlock(current->mm); @@ -390,7 +390,7 @@ static int handle_sske(struct kvm_vcpu *vcpu) m3 & SSKE_MC); if (rc < 0) { - rc = fixup_user_fault(current, current->mm, vmaddr, + rc = fixup_user_fault(current->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked); rc = !rc ? -EAGAIN : rc; } @@ -1094,7 +1094,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) rc = cond_set_guest_storage_key(current->mm, vmaddr, key, NULL, nq, mr, mc); if (rc < 0) { - rc = fixup_user_fault(current, current->mm, vmaddr, + rc = fixup_user_fault(current->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked); rc = !rc ? -EAGAIN : rc; } diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index d53c2e2ea1fd..9aa201df2e94 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -478,7 +478,7 @@ retry: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) { fault = VM_FAULT_SIGNAL; if (flags & FAULT_FLAG_RETRY_NOWAIT) @@ -488,21 +488,7 @@ retry: if (unlikely(fault & VM_FAULT_ERROR)) goto out_up; - /* - * Major/minor page fault accounting is only done on the - * initial attempt. If we go through a retry, it is extremely - * likely that the page will be found in page cache at that point. - */ if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) { - tsk->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, - regs, address); - } else { - tsk->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, - regs, address); - } if (fault & VM_FAULT_RETRY) { if (IS_ENABLED(CONFIG_PGSTE) && gmap && (flags & FAULT_FLAG_RETRY_NOWAIT)) { diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 190357ff86b3..8747487c50a8 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -649,7 +649,7 @@ retry: rc = vmaddr; goto out_up; } - if (fixup_user_fault(current, gmap->mm, vmaddr, fault_flags, + if (fixup_user_fault(gmap->mm, vmaddr, fault_flags, &unlocked)) { rc = -EFAULT; goto out_up; @@ -879,7 +879,7 @@ static int gmap_pte_op_fixup(struct gmap *gmap, unsigned long gaddr, BUG_ON(gmap_is_shadow(gmap)); fault_flags = (prot == PROT_WRITE) ? FAULT_FLAG_WRITE : 0; - if (fixup_user_fault(current, mm, vmaddr, fault_flags, &unlocked)) + if (fixup_user_fault(mm, vmaddr, fault_flags, &unlocked)) return -EFAULT; if (unlocked) /* lost mmap_lock, caller has to retry __gmap_translate */ diff --git a/arch/sh/configs/dreamcast_defconfig b/arch/sh/configs/dreamcast_defconfig index ae067e0b15e3..6a82c7b8ff32 100644 --- a/arch/sh/configs/dreamcast_defconfig +++ b/arch/sh/configs/dreamcast_defconfig @@ -1,7 +1,6 @@ CONFIG_SYSVIPC=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_LOG_BUF_SHIFT=14 -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_SLAB=y CONFIG_PROFILING=y CONFIG_MODULES=y diff --git a/arch/sh/configs/espt_defconfig b/arch/sh/configs/espt_defconfig index a5b865a75d22..9a988c347e9d 100644 --- a/arch/sh/configs/espt_defconfig +++ b/arch/sh/configs/espt_defconfig @@ -5,7 +5,6 @@ CONFIG_LOG_BUF_SHIFT=14 CONFIG_NAMESPACES=y CONFIG_UTS_NS=y CONFIG_IPC_NS=y -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_SLAB=y CONFIG_PROFILING=y CONFIG_OPROFILE=y diff --git a/arch/sh/configs/hp6xx_defconfig b/arch/sh/configs/hp6xx_defconfig index a92db6694ce2..70e6605d7f7e 100644 --- a/arch/sh/configs/hp6xx_defconfig +++ b/arch/sh/configs/hp6xx_defconfig @@ -3,7 +3,6 @@ CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_SLAB=y # CONFIG_BLK_DEV_BSG is not set CONFIG_CPU_SUBTYPE_SH7709=y diff --git a/arch/sh/configs/landisk_defconfig b/arch/sh/configs/landisk_defconfig index 567af752b1bb..ba6ec042606f 100644 --- a/arch/sh/configs/landisk_defconfig +++ b/arch/sh/configs/landisk_defconfig @@ -1,6 +1,5 @@ CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_KALLSYMS_EXTRA_PASS=y CONFIG_SLAB=y CONFIG_MODULES=y diff --git a/arch/sh/configs/lboxre2_defconfig b/arch/sh/configs/lboxre2_defconfig index 10f6d371ce2c..05e4ac6fed5f 100644 --- a/arch/sh/configs/lboxre2_defconfig +++ b/arch/sh/configs/lboxre2_defconfig @@ -1,6 +1,5 @@ CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_KALLSYMS_EXTRA_PASS=y CONFIG_SLAB=y CONFIG_MODULES=y diff --git a/arch/sh/configs/microdev_defconfig b/arch/sh/configs/microdev_defconfig index ed84d1303acf..c65667d00313 100644 --- a/arch/sh/configs/microdev_defconfig +++ b/arch/sh/configs/microdev_defconfig @@ -2,7 +2,6 @@ CONFIG_BSD_PROCESS_ACCT=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_SLAB=y # CONFIG_BLK_DEV_BSG is not set CONFIG_CPU_SUBTYPE_SH4_202=y diff --git a/arch/sh/configs/migor_defconfig b/arch/sh/configs/migor_defconfig index 37e9521a99e5..a24cf8cd2cea 100644 --- a/arch/sh/configs/migor_defconfig +++ b/arch/sh/configs/migor_defconfig @@ -4,7 +4,6 @@ CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_SLAB=y CONFIG_PROFILING=y CONFIG_OPROFILE=y diff --git a/arch/sh/configs/r7780mp_defconfig b/arch/sh/configs/r7780mp_defconfig index c97ec60cff27..e922659fdadb 100644 --- a/arch/sh/configs/r7780mp_defconfig +++ b/arch/sh/configs/r7780mp_defconfig @@ -3,7 +3,6 @@ CONFIG_BSD_PROCESS_ACCT=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 -# CONFIG_SYSCTL_SYSCALL is not set # CONFIG_FUTEX is not set # CONFIG_EPOLL is not set CONFIG_SLAB=y diff --git a/arch/sh/configs/r7785rp_defconfig b/arch/sh/configs/r7785rp_defconfig index 55fce65eb454..5978866358ec 100644 --- a/arch/sh/configs/r7785rp_defconfig +++ b/arch/sh/configs/r7785rp_defconfig @@ -7,7 +7,6 @@ CONFIG_RCU_TRACE=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_SLAB=y CONFIG_PROFILING=y CONFIG_OPROFILE=y diff --git a/arch/sh/configs/rts7751r2d1_defconfig b/arch/sh/configs/rts7751r2d1_defconfig index 6a3cfe08295f..fc9c22152b08 100644 --- a/arch/sh/configs/rts7751r2d1_defconfig +++ b/arch/sh/configs/rts7751r2d1_defconfig @@ -1,7 +1,6 @@ CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_SLAB=y CONFIG_PROFILING=y CONFIG_OPROFILE=y diff --git a/arch/sh/configs/rts7751r2dplus_defconfig b/arch/sh/configs/rts7751r2dplus_defconfig index 2b3d7d280672..ff3fd6787fd6 100644 --- a/arch/sh/configs/rts7751r2dplus_defconfig +++ b/arch/sh/configs/rts7751r2dplus_defconfig @@ -1,7 +1,6 @@ CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_SLAB=y CONFIG_PROFILING=y CONFIG_OPROFILE=y diff --git a/arch/sh/configs/se7206_defconfig b/arch/sh/configs/se7206_defconfig index 21a43f14ffac..ff5bb4489922 100644 --- a/arch/sh/configs/se7206_defconfig +++ b/arch/sh/configs/se7206_defconfig @@ -18,7 +18,6 @@ CONFIG_USER_NS=y CONFIG_PID_NS=y CONFIG_BLK_DEV_INITRD=y # CONFIG_UID16 is not set -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_KALLSYMS_ALL=y # CONFIG_ELF_CORE is not set # CONFIG_COMPAT_BRK is not set diff --git a/arch/sh/configs/se7343_defconfig b/arch/sh/configs/se7343_defconfig index 4e794e719a28..5d6c19338ebf 100644 --- a/arch/sh/configs/se7343_defconfig +++ b/arch/sh/configs/se7343_defconfig @@ -2,7 +2,6 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_LOG_BUF_SHIFT=14 -# CONFIG_SYSCTL_SYSCALL is not set # CONFIG_FUTEX is not set # CONFIG_EPOLL is not set # CONFIG_SHMEM is not set diff --git a/arch/sh/configs/se7619_defconfig b/arch/sh/configs/se7619_defconfig index 3264415a5931..71a672c30716 100644 --- a/arch/sh/configs/se7619_defconfig +++ b/arch/sh/configs/se7619_defconfig @@ -1,7 +1,6 @@ # CONFIG_LOCALVERSION_AUTO is not set CONFIG_LOG_BUF_SHIFT=14 # CONFIG_UID16 is not set -# CONFIG_SYSCTL_SYSCALL is not set # CONFIG_KALLSYMS is not set # CONFIG_HOTPLUG is not set # CONFIG_ELF_CORE is not set diff --git a/arch/sh/configs/se7705_defconfig b/arch/sh/configs/se7705_defconfig index 4496b94b7d88..ed00a6eeadf5 100644 --- a/arch/sh/configs/se7705_defconfig +++ b/arch/sh/configs/se7705_defconfig @@ -2,7 +2,6 @@ CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -# CONFIG_SYSCTL_SYSCALL is not set # CONFIG_KALLSYMS is not set # CONFIG_HOTPLUG is not set CONFIG_SLAB=y diff --git a/arch/sh/configs/se7750_defconfig b/arch/sh/configs/se7750_defconfig index b23f67542728..3f1c13799d79 100644 --- a/arch/sh/configs/se7750_defconfig +++ b/arch/sh/configs/se7750_defconfig @@ -5,7 +5,6 @@ CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -# CONFIG_SYSCTL_SYSCALL is not set # CONFIG_HOTPLUG is not set CONFIG_SLAB=y CONFIG_MODULES=y diff --git a/arch/sh/configs/se7751_defconfig b/arch/sh/configs/se7751_defconfig index 162343683937..4a024065bb75 100644 --- a/arch/sh/configs/se7751_defconfig +++ b/arch/sh/configs/se7751_defconfig @@ -3,7 +3,6 @@ CONFIG_BSD_PROCESS_ACCT=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -# CONFIG_SYSCTL_SYSCALL is not set # CONFIG_HOTPLUG is not set CONFIG_SLAB=y CONFIG_MODULES=y diff --git a/arch/sh/configs/secureedge5410_defconfig b/arch/sh/configs/secureedge5410_defconfig index 360592d63a2f..8422599cfb04 100644 --- a/arch/sh/configs/secureedge5410_defconfig +++ b/arch/sh/configs/secureedge5410_defconfig @@ -1,7 +1,6 @@ # CONFIG_SWAP is not set CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y -# CONFIG_SYSCTL_SYSCALL is not set # CONFIG_HOTPLUG is not set CONFIG_SLAB=y # CONFIG_BLK_DEV_BSG is not set diff --git a/arch/sh/configs/sh03_defconfig b/arch/sh/configs/sh03_defconfig index 87db9a84b5ec..f0073ed39947 100644 --- a/arch/sh/configs/sh03_defconfig +++ b/arch/sh/configs/sh03_defconfig @@ -3,7 +3,6 @@ CONFIG_POSIX_MQUEUE=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_SLAB=y CONFIG_PROFILING=y CONFIG_OPROFILE=m diff --git a/arch/sh/configs/sh7710voipgw_defconfig b/arch/sh/configs/sh7710voipgw_defconfig index 08426913c0e3..0d814770b07f 100644 --- a/arch/sh/configs/sh7710voipgw_defconfig +++ b/arch/sh/configs/sh7710voipgw_defconfig @@ -2,7 +2,6 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_LOG_BUF_SHIFT=14 -# CONFIG_SYSCTL_SYSCALL is not set # CONFIG_FUTEX is not set # CONFIG_EPOLL is not set # CONFIG_SHMEM is not set diff --git a/arch/sh/configs/sh7757lcr_defconfig b/arch/sh/configs/sh7757lcr_defconfig index d0933a9b9799..a2700ab165af 100644 --- a/arch/sh/configs/sh7757lcr_defconfig +++ b/arch/sh/configs/sh7757lcr_defconfig @@ -8,7 +8,6 @@ CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_KALLSYMS_ALL=y CONFIG_SLAB=y CONFIG_MODULES=y diff --git a/arch/sh/configs/sh7763rdp_defconfig b/arch/sh/configs/sh7763rdp_defconfig index d0a0aa74cecf..26c5fd02c87a 100644 --- a/arch/sh/configs/sh7763rdp_defconfig +++ b/arch/sh/configs/sh7763rdp_defconfig @@ -5,7 +5,6 @@ CONFIG_LOG_BUF_SHIFT=14 CONFIG_NAMESPACES=y CONFIG_UTS_NS=y CONFIG_IPC_NS=y -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_SLAB=y CONFIG_PROFILING=y CONFIG_OPROFILE=y diff --git a/arch/sh/configs/shmin_defconfig b/arch/sh/configs/shmin_defconfig index a27b129b93c5..c0b6f40d01cc 100644 --- a/arch/sh/configs/shmin_defconfig +++ b/arch/sh/configs/shmin_defconfig @@ -1,7 +1,6 @@ # CONFIG_SWAP is not set CONFIG_LOG_BUF_SHIFT=14 # CONFIG_UID16 is not set -# CONFIG_SYSCTL_SYSCALL is not set # CONFIG_KALLSYMS is not set # CONFIG_HOTPLUG is not set # CONFIG_BUG is not set diff --git a/arch/sh/configs/titan_defconfig b/arch/sh/configs/titan_defconfig index 4ec961ace688..ba887f1351be 100644 --- a/arch/sh/configs/titan_defconfig +++ b/arch/sh/configs/titan_defconfig @@ -6,7 +6,6 @@ CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=16 CONFIG_BLK_DEV_INITRD=y # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y diff --git a/arch/sh/include/asm/string_32.h b/arch/sh/include/asm/string_32.h index 3558b1d7123e..be3f9a08cbc9 100644 --- a/arch/sh/include/asm/string_32.h +++ b/arch/sh/include/asm/string_32.h @@ -28,32 +28,6 @@ static inline char *strcpy(char *__dest, const char *__src) return __xdest; } -#define __HAVE_ARCH_STRNCPY -static inline char *strncpy(char *__dest, const char *__src, size_t __n) -{ - register char *__xdest = __dest; - unsigned long __dummy; - - if (__n == 0) - return __xdest; - - __asm__ __volatile__( - "1:\n" - "mov.b @%1+, %2\n\t" - "mov.b %2, @%0\n\t" - "cmp/eq #0, %2\n\t" - "bt/s 2f\n\t" - " cmp/eq %5,%1\n\t" - "bf/s 1b\n\t" - " add #1, %0\n" - "2:" - : "=r" (__dest), "=r" (__src), "=&z" (__dummy) - : "0" (__dest), "1" (__src), "r" (__src+__n) - : "memory", "t"); - - return __xdest; -} - #define __HAVE_ARCH_STRCMP static inline int strcmp(const char *__cs, const char *__ct) { diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index 3a1230ce4878..792539111ed8 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -156,7 +156,7 @@ 146 common writev sys_writev 147 common getsid sys_getsid 148 common fdatasync sys_fdatasync -149 common _sysctl sys_sysctl +149 common _sysctl sys_ni_syscall 150 common mlock sys_mlock 151 common munlock sys_munlock 152 common mlockall sys_mlockall @@ -445,3 +445,4 @@ 440 common watch_mount sys_watch_mount 441 common watch_sb sys_watch_sb 442 common fsinfo sys_fsinfo +443 common process_madvise sys_process_madvise diff --git a/arch/sh/lib/delay.c b/arch/sh/lib/delay.c index 540e670dbafc..cccab21f3e56 100644 --- a/arch/sh/lib/delay.c +++ b/arch/sh/lib/delay.c @@ -42,6 +42,7 @@ inline void __const_udelay(unsigned long xloops) : "macl", "mach"); __delay(++xloops); } +EXPORT_SYMBOL(__delay); void __udelay(unsigned long usecs) { diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index fbe1f2fe9a8c..482668a2f6d3 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -482,22 +482,13 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (unlikely(fault & (VM_FAULT_RETRY | VM_FAULT_ERROR))) if (mm_fault_error(regs, error_code, address, fault)) return; if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) { - tsk->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, - regs, address); - } else { - tsk->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, - regs, address); - } if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index b98abce16ec4..4f8eebfcd07e 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -300,7 +300,7 @@ 249 64 nanosleep sys_nanosleep 250 32 mremap sys_mremap 250 64 mremap sys_64_mremap -251 common _sysctl sys_sysctl compat_sys_sysctl +251 common _sysctl sys_ni_syscall 252 common getsid sys_getsid 253 common fdatasync sys_fdatasync 254 32 nfsservctl sys_ni_syscall sys_nis_syscall @@ -488,3 +488,4 @@ 440 common watch_mount sys_watch_mount 441 common watch_sb sys_watch_sb 442 common fsinfo sys_fsinfo +443 common process_madvise sys_process_madvise compat_sys_process_madvise diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index cfef656eda0f..8071bfd72349 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -234,7 +234,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) return; @@ -250,15 +250,6 @@ good_area: } if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) { - current->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, - 1, regs, address); - } else { - current->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, - 1, regs, address); - } if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; @@ -410,7 +401,7 @@ good_area: if (!(vma->vm_flags & (VM_READ | VM_EXEC))) goto bad_area; } - switch (handle_mm_fault(vma, address, flags)) { + switch (handle_mm_fault(vma, address, flags, NULL)) { case VM_FAULT_SIGBUS: case VM_FAULT_OOM: goto do_sigbus; diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index a3806614e4dc..0a6bcc85fba7 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -422,7 +422,7 @@ good_area: goto bad_area; } - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) goto exit_exception; @@ -438,15 +438,6 @@ good_area: } if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) { - current->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, - 1, regs, address); - } else { - current->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, - 1, regs, address); - } if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 2b3afa354a90..ad12f78bda7e 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -71,7 +71,7 @@ good_area: do { vm_fault_t fault; - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, NULL); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) goto out_nosemaphore; @@ -88,10 +88,6 @@ good_area: BUG(); } if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index ea7c4aaa7043..29e49a70c99e 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -160,7 +160,7 @@ 146 i386 writev sys_writev compat_sys_writev 147 i386 getsid sys_getsid 148 i386 fdatasync sys_fdatasync -149 i386 _sysctl sys_sysctl compat_sys_sysctl +149 i386 _sysctl sys_ni_syscall 150 i386 mlock sys_mlock 151 i386 munlock sys_munlock 152 i386 mlockall sys_mlockall @@ -447,3 +447,4 @@ 440 i386 watch_mount sys_watch_mount 441 i386 watch_sb sys_watch_sb 442 i386 fsinfo sys_fsinfo +443 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 8756b396e3be..8f959d90338a 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -164,7 +164,7 @@ 153 common vhangup sys_vhangup 154 common modify_ldt sys_modify_ldt 155 common pivot_root sys_pivot_root -156 64 _sysctl sys_sysctl +156 64 _sysctl sys_ni_syscall 157 common prctl sys_prctl 158 common arch_prctl sys_arch_prctl 159 common adjtimex sys_adjtimex @@ -364,6 +364,7 @@ 440 common watch_mount sys_watch_mount 441 common watch_sb sys_watch_sb 442 common fsinfo sys_fsinfo +443 64 process_madvise sys_process_madvise # # x32-specific system call numbers start at 512 to avoid cache impact @@ -407,3 +408,4 @@ 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/x86/mm/fault.c b/arch/x86/mm/fault.c index 5709248f66af..877874a26597 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1139,7 +1139,7 @@ void do_user_addr_fault(struct pt_regs *regs, struct vm_area_struct *vma; struct task_struct *tsk; struct mm_struct *mm; - vm_fault_t fault, major = 0; + vm_fault_t fault; unsigned int flags = FAULT_FLAG_DEFAULT; tsk = current; @@ -1291,8 +1291,7 @@ good_area: * userland). The return to userland is identified whenever * FAULT_FLAG_USER|FAULT_FLAG_KILLABLE are both set in flags. */ - fault = handle_mm_fault(vma, address, flags); - major |= fault & VM_FAULT_MAJOR; + fault = handle_mm_fault(vma, address, flags, regs); /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { @@ -1319,18 +1318,6 @@ good_area: return; } - /* - * Major/minor page fault accounting. If any of the events - * returned VM_FAULT_MAJOR, we account it as a major fault. - */ - if (major) { - tsk->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); - } else { - tsk->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); - } - check_v8086_mode(regs, address, tsk); } NOKPROBE_SYMBOL(do_user_addr_fault); diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 216bf20f9fa4..173bd27f61dd 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -222,7 +222,7 @@ 204 common quotactl sys_quotactl # 205 was old nfsservctl 205 common nfsservctl sys_ni_syscall -206 common _sysctl sys_sysctl +206 common _sysctl sys_ni_syscall 207 common bdflush sys_bdflush 208 common uname sys_newuname 209 common sysinfo sys_sysinfo @@ -413,3 +413,4 @@ 440 common watch_mount sys_watch_mount 441 common watch_sb sys_watch_sb 442 common fsinfo sys_fsinfo +443 common process_madvise sys_process_madvise diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index c128dcc7c85b..7666408ce12a 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -72,6 +72,9 @@ void do_page_fault(struct pt_regs *regs) if (user_mode(regs)) flags |= FAULT_FLAG_USER; + + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); + retry: mmap_read_lock(mm); vma = find_vma(mm, address); @@ -107,7 +110,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) return; @@ -122,10 +125,6 @@ good_area: BUG(); } if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; @@ -139,12 +138,6 @@ good_area: } mmap_read_unlock(mm); - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); - if (flags & VM_FAULT_MAJOR) - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); - else - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); - return; /* Something tried to access memory that isn't in our memory map.. diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index e946032b13e4..2c2bf24140c9 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -469,7 +469,7 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work) locked = 1; } ret = pin_user_pages_remote - (work->task, mm, + (mm, obj->userptr.ptr + pinned * PAGE_SIZE, npages - pinned, flags, diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c index 5e32f61a2fe4..cc6b4befde7c 100644 --- a/drivers/infiniband/core/umem_odp.c +++ b/drivers/infiniband/core/umem_odp.c @@ -439,7 +439,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt, * complex (and doesn't gain us much performance in most use * cases). */ - npages = get_user_pages_remote(owning_process, owning_mm, + npages = get_user_pages_remote(owning_mm, user_virt, gup_num_pages, flags, local_page_list, NULL, NULL); mmap_read_unlock(owning_mm); diff --git a/drivers/iommu/amd/iommu_v2.c b/drivers/iommu/amd/iommu_v2.c index e4b025c5637c..c259108ab6dd 100644 --- a/drivers/iommu/amd/iommu_v2.c +++ b/drivers/iommu/amd/iommu_v2.c @@ -495,7 +495,7 @@ static void do_fault(struct work_struct *work) if (access_error(vma, fault)) goto out; - ret = handle_mm_fault(vma, address, flags); + ret = handle_mm_fault(vma, address, flags, NULL); out: mmap_read_unlock(mm); diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 6c87c807a0ab..5ae59a6ad681 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -872,7 +872,8 @@ static irqreturn_t prq_event_thread(int irq, void *d) goto invalid; ret = handle_mm_fault(vma, address, - req->wr_req ? FAULT_FLAG_WRITE : 0); + req->wr_req ? FAULT_FLAG_WRITE : 0, + NULL); if (ret & VM_FAULT_ERROR) goto invalid; diff --git a/drivers/sh/clk/cpg.c b/drivers/sh/clk/cpg.c index eeb028b9cdb3..a5cacfe24a42 100644 --- a/drivers/sh/clk/cpg.c +++ b/drivers/sh/clk/cpg.c @@ -36,36 +36,21 @@ static void sh_clk_write(int value, struct clk *clk) iowrite32(value, clk->mapped_reg); } -static unsigned int r8(const void __iomem *addr) -{ - return ioread8(addr); -} - -static unsigned int r16(const void __iomem *addr) -{ - return ioread16(addr); -} - -static unsigned int r32(const void __iomem *addr) -{ - return ioread32(addr); -} - static int sh_clk_mstp_enable(struct clk *clk) { sh_clk_write(sh_clk_read(clk) & ~(1 << clk->enable_bit), clk); if (clk->status_reg) { - unsigned int (*read)(const void __iomem *addr); + unsigned int (*read)(void __iomem *addr); int i; void __iomem *mapped_status = (phys_addr_t)clk->status_reg - (phys_addr_t)clk->enable_reg + clk->mapped_reg; if (clk->flags & CLK_ENABLE_REG_8BIT) - read = r8; + read = ioread8; else if (clk->flags & CLK_ENABLE_REG_16BIT) - read = r16; + read = ioread16; else - read = r32; + read = ioread32; for (i = 1000; (read(mapped_status) & (1 << clk->enable_bit)) && i; diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 5e556ac9102a..9d41105bfd01 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -425,7 +425,7 @@ static int follow_fault_pfn(struct vm_area_struct *vma, struct mm_struct *mm, if (ret) { bool unlocked = false; - ret = fixup_user_fault(NULL, mm, vaddr, + ret = fixup_user_fault(mm, vaddr, FAULT_FLAG_REMOTE | (write_fault ? FAULT_FLAG_WRITE : 0), &unlocked); @@ -453,7 +453,7 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr, flags |= FOLL_WRITE; mmap_read_lock(mm); - ret = pin_user_pages_remote(NULL, mm, vaddr, 1, flags | FOLL_LONGTERM, + ret = pin_user_pages_remote(mm, vaddr, 1, flags | FOLL_LONGTERM, page, NULL, NULL); if (ret == 1) { *pfn = page_to_pfn(page[0]); diff --git a/fs/exec.c b/fs/exec.c index e93baf5da1d2..dc35fe2f6b09 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -217,7 +217,7 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, * We are doing an exec(). 'current' is the process * doing the exec and bprm->mm is the new process's mm. */ - ret = get_user_pages_remote(current, bprm->mm, pos, 1, gup_flags, + ret = get_user_pages_remote(bprm->mm, pos, 1, gup_flags, &page, NULL, NULL); if (ret <= 0) return NULL; diff --git a/fs/io_uring.c b/fs/io_uring.c index ae83c8dcd5d5..f81d36d78594 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -3711,7 +3711,7 @@ 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/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 62febf06a1b2..5f96b76e5784 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -393,6 +393,7 @@ */ #ifndef RO_AFTER_INIT_DATA #define RO_AFTER_INIT_DATA \ + . = ALIGN(8); \ __start_ro_after_init = .; \ *(.data..ro_after_init) \ JUMP_TABLE_DATA \ diff --git a/include/linux/compat.h b/include/linux/compat.h index e90100c0de72..4b48b6c49637 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -827,6 +827,10 @@ 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 @@ -855,7 +859,6 @@ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u32); asmlinkage long compat_sys_recv(int fd, void __user *buf, compat_size_t len, unsigned flags); -asmlinkage long compat_sys_sysctl(struct compat_sysctl_args __user *args); /* obsolete: fs/readdir.c */ asmlinkage long compat_sys_old_readdir(unsigned int fd, diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 50650d0d01b9..6b9508dc31b4 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -10,6 +10,7 @@ #include <linux/list.h> #include <linux/kref.h> #include <linux/pgtable.h> +#include <linux/gfp.h> struct ctl_table; struct user_struct; @@ -504,9 +505,8 @@ struct huge_bootmem_page { struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve); -struct page *alloc_huge_page_node(struct hstate *h, int nid); struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, - nodemask_t *nmask); + nodemask_t *nmask, gfp_t gfp_mask); struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address); struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask, @@ -692,6 +692,25 @@ static inline bool hugepage_movable_supported(struct hstate *h) return true; } +/* Movability of hugepages depends on migration support. */ +static inline gfp_t htlb_alloc_mask(struct hstate *h) +{ + if (hugepage_movable_supported(h)) + return GFP_HIGHUSER_MOVABLE; + else + return GFP_HIGHUSER; +} + +static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) +{ + gfp_t modified_mask = htlb_alloc_mask(h); + + /* Some callers might want to enfoce node */ + modified_mask |= (gfp_mask & __GFP_THISNODE); + + return modified_mask; +} + static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { @@ -759,13 +778,9 @@ static inline struct page *alloc_huge_page(struct vm_area_struct *vma, return NULL; } -static inline struct page *alloc_huge_page_node(struct hstate *h, int nid) -{ - return NULL; -} - static inline struct page * -alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask) +alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, + nodemask_t *nmask, gfp_t gfp_mask) { return NULL; } @@ -878,6 +893,16 @@ static inline bool hugepage_movable_supported(struct hstate *h) return false; } +static inline gfp_t htlb_alloc_mask(struct hstate *h) +{ + return 0; +} + +static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) +{ + return 0; +} + static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 16b59f70a457..7f64e4c3ce42 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -630,7 +630,7 @@ unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, struct mem_cgroup_per_node *mz; mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); - return mz->lru_zone_size[zone_idx][lru]; + return READ_ONCE(mz->lru_zone_size[zone_idx][lru]); } void mem_cgroup_handle_over_high(void); diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 3e546cbf03dd..cc56f0d6c95b 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -10,6 +10,8 @@ typedef struct page *new_page_t(struct page *page, unsigned long private); typedef void free_page_t(struct page *page, unsigned long private); +struct migration_target_control; + /* * Return values from addresss_space_operations.migratepage(): * - negative errno on page migration failure; @@ -31,34 +33,6 @@ enum migrate_reason { /* In mm/debug.c; also keep sync with include/trace/events/migrate.h */ extern const char *migrate_reason_names[MR_TYPES]; -static inline struct page *new_page_nodemask(struct page *page, - int preferred_nid, nodemask_t *nodemask) -{ - gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL; - unsigned int order = 0; - struct page *new_page = NULL; - - if (PageHuge(page)) - return alloc_huge_page_nodemask(page_hstate(compound_head(page)), - preferred_nid, nodemask); - - if (PageTransHuge(page)) { - gfp_mask |= GFP_TRANSHUGE; - order = HPAGE_PMD_ORDER; - } - - if (PageHighMem(page) || (zone_idx(page_zone(page)) == ZONE_MOVABLE)) - gfp_mask |= __GFP_HIGHMEM; - - new_page = __alloc_pages_nodemask(gfp_mask, order, - preferred_nid, nodemask); - - if (new_page && PageTransHuge(new_page)) - prep_transhuge_page(new_page); - - return new_page; -} - #ifdef CONFIG_MIGRATION extern void putback_movable_pages(struct list_head *l); @@ -67,6 +41,7 @@ extern int migrate_page(struct address_space *mapping, enum migrate_mode mode); extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, unsigned long private, enum migrate_mode mode, int reason); +extern struct page *alloc_migration_target(struct page *page, unsigned long private); extern int isolate_movable_page(struct page *page, isolate_mode_t mode); extern void putback_movable_page(struct page *page); @@ -85,6 +60,9 @@ static inline int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, unsigned long private, enum migrate_mode mode, int reason) { return -ENOSYS; } +static inline struct page *alloc_migration_target(struct page *page, + unsigned long private) + { return NULL; } static inline int isolate_movable_page(struct page *page, isolate_mode_t mode) { return -EBUSY; } diff --git a/include/linux/mm.h b/include/linux/mm.h index 8098637889ea..9e3217cf6b3a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -39,6 +39,7 @@ struct file_ra_state; struct user_struct; struct writeback_control; struct bdi_writeback; +struct pt_regs; void init_mm_internals(void); @@ -1066,6 +1067,7 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); static inline enum zone_type page_zonenum(const struct page *page) { + ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT); return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; } @@ -1658,8 +1660,9 @@ int invalidate_inode_page(struct page *page); #ifdef CONFIG_MMU extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, - unsigned long address, unsigned int flags); -extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, + unsigned long address, unsigned int flags, + struct pt_regs *regs); +extern int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked); void unmap_mapping_pages(struct address_space *mapping, @@ -1668,14 +1671,14 @@ void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); #else static inline vm_fault_t handle_mm_fault(struct vm_area_struct *vma, - unsigned long address, unsigned int flags) + unsigned long address, unsigned int flags, + struct pt_regs *regs) { /* should never happen if there's no MMU */ BUG(); return VM_FAULT_SIGBUS; } -static inline int fixup_user_fault(struct task_struct *tsk, - struct mm_struct *mm, unsigned long address, +static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked) { /* should never happen if there's no MMU */ @@ -1701,11 +1704,11 @@ extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, extern int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags); -long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, +long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked); -long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, +long pin_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked); @@ -2546,7 +2549,8 @@ 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); static inline unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, 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 2ef60a4f05e0..efa61eb116b4 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -48,7 +48,6 @@ struct statfs; struct statfs64; struct statx; struct fsinfo_params; -struct __sysctl_args; struct sysinfo; struct timespec; struct __kernel_old_timeval; @@ -881,6 +880,8 @@ 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); @@ -1125,7 +1126,6 @@ asmlinkage long sys_send(int, void __user *, size_t, unsigned); asmlinkage long sys_bdflush(int func, long data); asmlinkage long sys_oldumount(char __user *name); asmlinkage long sys_uselib(const char __user *library); -asmlinkage long sys_sysctl(struct __sysctl_args __user *args); asmlinkage long sys_sysfs(int option, unsigned long arg1, unsigned long arg2); asmlinkage long sys_fork(void); diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 50bb7f383a1b..51298a4f4623 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -74,15 +74,13 @@ int proc_do_static_key(struct ctl_table *table, int write, void *buffer, * sysctl names can be mirrored automatically under /proc/sys. The * procname supplied controls /proc naming. * - * The table's mode will be honoured both for sys_sysctl(2) and - * proc-fs access. + * The table's mode will be honoured for proc-fs access. * * Leaf nodes in the sysctl tree will be represented by a single file * under /proc; non-leaf nodes will be represented by directories. A * null procname disables /proc mirroring at this node. * - * sysctl(2) can automatically manage read and write requests through - * the sysctl table. The data and maxlen fields of the ctl_table + * The data and maxlen fields of the ctl_table * struct enable minimal validation of the values being written to be * performed, and the mode field allows minimal authentication. * diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 25b1bdfb3e97..ed180cbf7118 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -865,9 +865,11 @@ __SYSCALL(__NR_watch_mount, sys_watch_mount) __SYSCALL(__NR_watch_sb, sys_watch_sb) #define __NR_fsinfo 442 __SYSCALL(__NR_fsinfo, sys_fsinfo) +#define __NR_process_madvise 443 +__SC_COMP(__NR_process_madvise, sys_process_madvise, compat_sys_process_madvise) #undef __NR_syscalls -#define __NR_syscalls 443 +#define __NR_syscalls 444 /* * 32 bit systems traditionally used different diff --git a/kernel/Makefile b/kernel/Makefile index 71b6bbccdea6..9abd0529d97c 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -5,7 +5,7 @@ obj-y = fork.o exec_domain.o panic.o \ cpu.o exit.o softirq.o resource.o \ - sysctl.o sysctl_binary.o capability.o ptrace.o user.o \ + sysctl.o capability.o ptrace.o user.o \ signal.o sys.o umh.o workqueue.o pid.o task_work.o \ extable.o params.o \ kthread.o sys_ni.o nsproxy.o \ diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index e84eb52b646b..f500204eb70d 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -376,7 +376,7 @@ __update_ref_ctr(struct mm_struct *mm, unsigned long vaddr, short d) if (!vaddr || !d) return -EINVAL; - ret = get_user_pages_remote(NULL, mm, vaddr, 1, + ret = get_user_pages_remote(mm, vaddr, 1, FOLL_WRITE, &page, &vma, NULL); if (unlikely(ret <= 0)) { /* @@ -477,7 +477,7 @@ retry: if (is_register) gup_flags |= FOLL_SPLIT_PMD; /* Read the page with vaddr into memory */ - ret = get_user_pages_remote(NULL, mm, vaddr, 1, gup_flags, + ret = get_user_pages_remote(mm, vaddr, 1, gup_flags, &old_page, &vma, NULL); if (ret <= 0) return ret; @@ -2029,7 +2029,7 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr) * but we treat this as a 'remote' access since it is * essentially a kernel access to the memory. */ - result = get_user_pages_remote(NULL, mm, vaddr, 1, FOLL_FORCE, &page, + result = get_user_pages_remote(mm, vaddr, 1, FOLL_FORCE, &page, NULL, NULL); if (result < 0) return result; diff --git a/kernel/exit.c b/kernel/exit.c index c2d2961576f2..e45091eae224 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/futex.c b/kernel/futex.c index 05e88562de68..d024fcef62e8 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -699,7 +699,7 @@ static int fault_in_user_writeable(u32 __user *uaddr) int ret; mmap_read_lock(mm); - ret = fixup_user_fault(current, mm, (unsigned long)uaddr, + ret = fixup_user_fault(mm, (unsigned long)uaddr, FAULT_FLAG_WRITE, NULL); mmap_read_unlock(mm); diff --git a/kernel/pid.c b/kernel/pid.c index da5aea5f04fa..de9d29c41d77 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 519317f3904c..c935c1819ba3 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -287,6 +287,8 @@ 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); @@ -371,7 +373,6 @@ COND_SYSCALL(socketcall); COND_SYSCALL_COMPAT(socketcall); /* compat syscalls for arm64, x86, ... */ -COND_SYSCALL_COMPAT(sysctl); COND_SYSCALL_COMPAT(fanotify_mark); /* x86 */ diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c deleted file mode 100644 index 7d550cc76a3b..000000000000 --- a/kernel/sysctl_binary.c +++ /dev/null @@ -1,171 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/stat.h> -#include <linux/sysctl.h> -#include "../fs/xfs/xfs_sysctl.h" -#include <linux/sunrpc/debug.h> -#include <linux/string.h> -#include <linux/syscalls.h> -#include <linux/namei.h> -#include <linux/mount.h> -#include <linux/fs.h> -#include <linux/nsproxy.h> -#include <linux/pid_namespace.h> -#include <linux/file.h> -#include <linux/ctype.h> -#include <linux/netdevice.h> -#include <linux/kernel.h> -#include <linux/uuid.h> -#include <linux/slab.h> -#include <linux/compat.h> - -static ssize_t binary_sysctl(const int *name, int nlen, - void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) -{ - return -ENOSYS; -} - -static void deprecated_sysctl_warning(const int *name, int nlen) -{ - int i; - - /* - * CTL_KERN/KERN_VERSION is used by older glibc and cannot - * ever go away. - */ - if (nlen >= 2 && name[0] == CTL_KERN && name[1] == KERN_VERSION) - return; - - if (printk_ratelimit()) { - printk(KERN_INFO - "warning: process `%s' used the deprecated sysctl " - "system call with ", current->comm); - for (i = 0; i < nlen; i++) - printk(KERN_CONT "%d.", name[i]); - printk(KERN_CONT "\n"); - } - return; -} - -#define WARN_ONCE_HASH_BITS 8 -#define WARN_ONCE_HASH_SIZE (1<<WARN_ONCE_HASH_BITS) - -static DECLARE_BITMAP(warn_once_bitmap, WARN_ONCE_HASH_SIZE); - -#define FNV32_OFFSET 2166136261U -#define FNV32_PRIME 0x01000193 - -/* - * Print each legacy sysctl (approximately) only once. - * To avoid making the tables non-const use a external - * hash-table instead. - * Worst case hash collision: 6, but very rarely. - * NOTE! We don't use the SMP-safe bit tests. We simply - * don't care enough. - */ -static void warn_on_bintable(const int *name, int nlen) -{ - int i; - u32 hash = FNV32_OFFSET; - - for (i = 0; i < nlen; i++) - hash = (hash ^ name[i]) * FNV32_PRIME; - hash %= WARN_ONCE_HASH_SIZE; - if (__test_and_set_bit(hash, warn_once_bitmap)) - return; - deprecated_sysctl_warning(name, nlen); -} - -static ssize_t do_sysctl(int __user *args_name, int nlen, - void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) -{ - int name[CTL_MAXNAME]; - int i; - - /* Check args->nlen. */ - if (nlen < 0 || nlen > CTL_MAXNAME) - return -ENOTDIR; - /* Read in the sysctl name for simplicity */ - for (i = 0; i < nlen; i++) - if (get_user(name[i], args_name + i)) - return -EFAULT; - - warn_on_bintable(name, nlen); - - return binary_sysctl(name, nlen, oldval, oldlen, newval, newlen); -} - -SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args) -{ - struct __sysctl_args tmp; - size_t oldlen = 0; - ssize_t result; - - if (copy_from_user(&tmp, args, sizeof(tmp))) - return -EFAULT; - - if (tmp.oldval && !tmp.oldlenp) - return -EFAULT; - - if (tmp.oldlenp && get_user(oldlen, tmp.oldlenp)) - return -EFAULT; - - result = do_sysctl(tmp.name, tmp.nlen, tmp.oldval, oldlen, - tmp.newval, tmp.newlen); - - if (result >= 0) { - oldlen = result; - result = 0; - } - - if (tmp.oldlenp && put_user(oldlen, tmp.oldlenp)) - return -EFAULT; - - return result; -} - - -#ifdef CONFIG_COMPAT - -struct compat_sysctl_args { - compat_uptr_t name; - int nlen; - compat_uptr_t oldval; - compat_uptr_t oldlenp; - compat_uptr_t newval; - compat_size_t newlen; - compat_ulong_t __unused[4]; -}; - -COMPAT_SYSCALL_DEFINE1(sysctl, struct compat_sysctl_args __user *, args) -{ - struct compat_sysctl_args tmp; - compat_size_t __user *compat_oldlenp; - size_t oldlen = 0; - ssize_t result; - - if (copy_from_user(&tmp, args, sizeof(tmp))) - return -EFAULT; - - if (tmp.oldval && !tmp.oldlenp) - return -EFAULT; - - compat_oldlenp = compat_ptr(tmp.oldlenp); - if (compat_oldlenp && get_user(oldlen, compat_oldlenp)) - return -EFAULT; - - result = do_sysctl(compat_ptr(tmp.name), tmp.nlen, - compat_ptr(tmp.oldval), oldlen, - compat_ptr(tmp.newval), tmp.newlen); - - if (result >= 0) { - oldlen = result; - result = 0; - } - - if (compat_oldlenp && put_user(oldlen, compat_oldlenp)) - return -EFAULT; - - return result; -} - -#endif /* CONFIG_COMPAT */ diff --git a/mm/filemap.c b/mm/filemap.c index 9d43acdba8aa..cf4bdf7803b6 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2425,6 +2425,7 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) struct address_space *mapping = file->f_mapping; struct file *fpin = NULL; pgoff_t offset = vmf->pgoff; + unsigned int mmap_miss; /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ) @@ -2440,14 +2441,15 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) } /* Avoid banging the cache line if not needed */ - if (ra->mmap_miss < MMAP_LOTSAMISS * 10) - ra->mmap_miss++; + mmap_miss = READ_ONCE(ra->mmap_miss); + if (mmap_miss < MMAP_LOTSAMISS * 10) + WRITE_ONCE(ra->mmap_miss, ++mmap_miss); /* * Do we miss much more than hit in this file? If so, * stop bothering with read-ahead. It will only hurt. */ - if (ra->mmap_miss > MMAP_LOTSAMISS) + if (mmap_miss > MMAP_LOTSAMISS) return fpin; /* @@ -2473,13 +2475,15 @@ static struct file *do_async_mmap_readahead(struct vm_fault *vmf, struct file_ra_state *ra = &file->f_ra; struct address_space *mapping = file->f_mapping; struct file *fpin = NULL; + unsigned int mmap_miss; pgoff_t offset = vmf->pgoff; /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages) return fpin; - if (ra->mmap_miss > 0) - ra->mmap_miss--; + mmap_miss = READ_ONCE(ra->mmap_miss); + if (mmap_miss) + WRITE_ONCE(ra->mmap_miss, --mmap_miss); if (PageReadahead(page)) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_async_readahead(mapping, ra, file, @@ -2645,6 +2649,7 @@ void filemap_map_pages(struct vm_fault *vmf, unsigned long max_idx; XA_STATE(xas, &mapping->i_pages, start_pgoff); struct page *page; + unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss); rcu_read_lock(); xas_for_each(&xas, page, end_pgoff) { @@ -2681,8 +2686,8 @@ void filemap_map_pages(struct vm_fault *vmf, if (page->index >= max_idx) goto unlock; - if (file->f_ra.mmap_miss > 0) - file->f_ra.mmap_miss--; + if (mmap_miss > 0) + mmap_miss--; vmf->address += (xas.xa_index - last_pgoff) << PAGE_SHIFT; if (vmf->pte) @@ -2702,6 +2707,7 @@ next: break; } rcu_read_unlock(); + WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss); } EXPORT_SYMBOL(filemap_map_pages); diff --git a/mm/frontswap.c b/mm/frontswap.c index 9d977b1fc016..2183a56c7874 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -61,16 +61,16 @@ static u64 frontswap_failed_stores; static u64 frontswap_invalidates; static inline void inc_frontswap_loads(void) { - frontswap_loads++; + data_race(frontswap_loads++); } static inline void inc_frontswap_succ_stores(void) { - frontswap_succ_stores++; + data_race(frontswap_succ_stores++); } static inline void inc_frontswap_failed_stores(void) { - frontswap_failed_stores++; + data_race(frontswap_failed_stores++); } static inline void inc_frontswap_invalidates(void) { - frontswap_invalidates++; + data_race(frontswap_invalidates++); } #else static inline void inc_frontswap_loads(void) { } @@ -859,7 +859,7 @@ unmap: * does not include FOLL_NOWAIT, the mmap_lock may be released. If it * is, *@locked will be set to 0 and -EBUSY returned. */ -static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma, +static int faultin_page(struct vm_area_struct *vma, unsigned long address, unsigned int *flags, int *locked) { unsigned int fault_flags = 0; @@ -884,7 +884,7 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma, fault_flags |= FAULT_FLAG_TRIED; } - ret = handle_mm_fault(vma, address, fault_flags); + ret = handle_mm_fault(vma, address, fault_flags, NULL); if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, *flags); @@ -893,13 +893,6 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma, BUG(); } - if (tsk) { - if (ret & VM_FAULT_MAJOR) - tsk->maj_flt++; - else - tsk->min_flt++; - } - if (ret & VM_FAULT_RETRY) { if (locked && !(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) *locked = 0; @@ -969,7 +962,6 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) /** * __get_user_pages() - pin user pages in memory - * @tsk: task_struct of target task * @mm: mm_struct of target mm * @start: starting user address * @nr_pages: number of pages from start to pin @@ -1028,7 +1020,7 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) * instead of __get_user_pages. __get_user_pages should be used only if * you need some special @gup_flags. */ -static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, +static long __get_user_pages(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked) @@ -1110,8 +1102,7 @@ retry: page = follow_page_mask(vma, start, foll_flags, &ctx); if (!page) { - ret = faultin_page(tsk, vma, start, &foll_flags, - locked); + ret = faultin_page(vma, start, &foll_flags, locked); switch (ret) { case 0: goto retry; @@ -1185,8 +1176,6 @@ static bool vma_permits_fault(struct vm_area_struct *vma, /** * fixup_user_fault() - manually resolve a user page fault - * @tsk: the task_struct to use for page fault accounting, or - * NULL if faults are not to be recorded. * @mm: mm_struct of target mm * @address: user address * @fault_flags:flags to pass down to handle_mm_fault() @@ -1214,7 +1203,7 @@ static bool vma_permits_fault(struct vm_area_struct *vma, * This function will not return with an unlocked mmap_lock. So it has not the * same semantics wrt the @mm->mmap_lock as does filemap_fault(). */ -int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, +int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked) { @@ -1238,7 +1227,7 @@ retry: fatal_signal_pending(current)) return -EINTR; - ret = handle_mm_fault(vma, address, fault_flags); + ret = handle_mm_fault(vma, address, fault_flags, NULL); major |= ret & VM_FAULT_MAJOR; if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, 0); @@ -1255,12 +1244,6 @@ retry: goto retry; } - if (tsk) { - if (major) - tsk->maj_flt++; - else - tsk->min_flt++; - } return 0; } EXPORT_SYMBOL_GPL(fixup_user_fault); @@ -1269,8 +1252,7 @@ EXPORT_SYMBOL_GPL(fixup_user_fault); * Please note that this function, unlike __get_user_pages will not * return 0 for nr_pages > 0 without FOLL_NOWAIT */ -static __always_inline long __get_user_pages_locked(struct task_struct *tsk, - struct mm_struct *mm, +static __always_inline long __get_user_pages_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, @@ -1303,7 +1285,7 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk, pages_done = 0; lock_dropped = false; for (;;) { - ret = __get_user_pages(tsk, mm, start, nr_pages, flags, pages, + ret = __get_user_pages(mm, start, nr_pages, flags, pages, vmas, locked); if (!locked) /* VM_FAULT_RETRY couldn't trigger, bypass */ @@ -1363,7 +1345,7 @@ retry: } *locked = 1; - ret = __get_user_pages(tsk, mm, start, 1, flags | FOLL_TRIED, + ret = __get_user_pages(mm, start, 1, flags | FOLL_TRIED, pages, NULL, locked); if (!*locked) { /* Continue to retry until we succeeded */ @@ -1449,7 +1431,7 @@ long populate_vma_page_range(struct vm_area_struct *vma, * We made sure addr is within a VMA, so the following will * not result in a stack expansion that recurses back here. */ - return __get_user_pages(current, mm, start, nr_pages, gup_flags, + return __get_user_pages(mm, start, nr_pages, gup_flags, NULL, NULL, locked); } @@ -1533,7 +1515,7 @@ struct page *get_dump_page(unsigned long addr) struct vm_area_struct *vma; struct page *page; - if (__get_user_pages(current, current->mm, addr, 1, + if (__get_user_pages(current->mm, addr, 1, FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma, NULL) < 1) return NULL; @@ -1542,8 +1524,7 @@ struct page *get_dump_page(unsigned long addr) } #endif /* CONFIG_ELF_CORE */ #else /* CONFIG_MMU */ -static long __get_user_pages_locked(struct task_struct *tsk, - struct mm_struct *mm, unsigned long start, +static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, struct vm_area_struct **vmas, int *locked, unsigned int foll_flags) @@ -1659,8 +1640,7 @@ static struct page *new_non_cma_page(struct page *page, unsigned long private) return __alloc_pages_node(nid, gfp_mask, 0); } -static long check_and_migrate_cma_pages(struct task_struct *tsk, - struct mm_struct *mm, +static long check_and_migrate_cma_pages(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, @@ -1734,7 +1714,7 @@ check_again: * again migrating any new CMA pages which we failed to isolate * earlier. */ - ret = __get_user_pages_locked(tsk, mm, start, nr_pages, + ret = __get_user_pages_locked(mm, start, nr_pages, pages, vmas, NULL, gup_flags); @@ -1748,8 +1728,7 @@ check_again: return ret; } #else -static long check_and_migrate_cma_pages(struct task_struct *tsk, - struct mm_struct *mm, +static long check_and_migrate_cma_pages(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, @@ -1764,8 +1743,7 @@ static long check_and_migrate_cma_pages(struct task_struct *tsk, * __gup_longterm_locked() is a wrapper for __get_user_pages_locked which * allows us to process the FOLL_LONGTERM flag. */ -static long __gup_longterm_locked(struct task_struct *tsk, - struct mm_struct *mm, +static long __gup_longterm_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, @@ -1790,7 +1768,7 @@ static long __gup_longterm_locked(struct task_struct *tsk, flags = memalloc_nocma_save(); } - rc = __get_user_pages_locked(tsk, mm, start, nr_pages, pages, + rc = __get_user_pages_locked(mm, start, nr_pages, pages, vmas_tmp, NULL, gup_flags); if (gup_flags & FOLL_LONGTERM) { @@ -1805,7 +1783,7 @@ static long __gup_longterm_locked(struct task_struct *tsk, goto out; } - rc = check_and_migrate_cma_pages(tsk, mm, start, rc, pages, + rc = check_and_migrate_cma_pages(mm, start, rc, pages, vmas_tmp, gup_flags); } @@ -1815,22 +1793,20 @@ out: return rc; } #else /* !CONFIG_FS_DAX && !CONFIG_CMA */ -static __always_inline long __gup_longterm_locked(struct task_struct *tsk, - struct mm_struct *mm, +static __always_inline long __gup_longterm_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, struct vm_area_struct **vmas, unsigned int flags) { - return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas, + return __get_user_pages_locked(mm, start, nr_pages, pages, vmas, NULL, flags); } #endif /* CONFIG_FS_DAX || CONFIG_CMA */ #ifdef CONFIG_MMU -static long __get_user_pages_remote(struct task_struct *tsk, - struct mm_struct *mm, +static long __get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked) @@ -1849,20 +1825,18 @@ static long __get_user_pages_remote(struct task_struct *tsk, * This will check the vmas (even if our vmas arg is NULL) * and return -ENOTSUPP if DAX isn't allowed in this case: */ - return __gup_longterm_locked(tsk, mm, start, nr_pages, pages, + return __gup_longterm_locked(mm, start, nr_pages, pages, vmas, gup_flags | FOLL_TOUCH | FOLL_REMOTE); } - return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas, + return __get_user_pages_locked(mm, start, nr_pages, pages, vmas, locked, gup_flags | FOLL_TOUCH | FOLL_REMOTE); } /** * get_user_pages_remote() - pin user pages in memory - * @tsk: the task_struct to use for page fault accounting, or - * NULL if faults are not to be recorded. * @mm: mm_struct of target mm * @start: starting user address * @nr_pages: number of pages from start to pin @@ -1921,7 +1895,7 @@ static long __get_user_pages_remote(struct task_struct *tsk, * should use get_user_pages_remote because it cannot pass * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault. */ -long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, +long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked) @@ -1933,13 +1907,13 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, if (WARN_ON_ONCE(gup_flags & FOLL_PIN)) return -EINVAL; - return __get_user_pages_remote(tsk, mm, start, nr_pages, gup_flags, + return __get_user_pages_remote(mm, start, nr_pages, gup_flags, pages, vmas, locked); } EXPORT_SYMBOL(get_user_pages_remote); #else /* CONFIG_MMU */ -long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, +long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked) @@ -1947,8 +1921,7 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, return 0; } -static long __get_user_pages_remote(struct task_struct *tsk, - struct mm_struct *mm, +static long __get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked) @@ -1968,11 +1941,10 @@ static long __get_user_pages_remote(struct task_struct *tsk, * @vmas: array of pointers to vmas corresponding to each page. * Or NULL if the caller does not require them. * - * This is the same as get_user_pages_remote(), just with a - * less-flexible calling convention where we assume that the task - * and mm being operated on are the current task's and don't allow - * passing of a locked parameter. We also obviously don't pass - * FOLL_REMOTE in here. + * This is the same as get_user_pages_remote(), just with a less-flexible + * calling convention where we assume that the mm being operated on belongs to + * the current task, and doesn't allow passing of a locked parameter. We also + * obviously don't pass FOLL_REMOTE in here. */ long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, @@ -1985,7 +1957,7 @@ long get_user_pages(unsigned long start, unsigned long nr_pages, if (WARN_ON_ONCE(gup_flags & FOLL_PIN)) return -EINVAL; - return __gup_longterm_locked(current, current->mm, start, nr_pages, + return __gup_longterm_locked(current->mm, start, nr_pages, pages, vmas, gup_flags | FOLL_TOUCH); } EXPORT_SYMBOL(get_user_pages); @@ -1995,7 +1967,7 @@ EXPORT_SYMBOL(get_user_pages); * * mmap_read_lock(mm); * do_something() - * get_user_pages(tsk, mm, ..., pages, NULL); + * get_user_pages(mm, ..., pages, NULL); * mmap_read_unlock(mm); * * to: @@ -2003,7 +1975,7 @@ EXPORT_SYMBOL(get_user_pages); * int locked = 1; * mmap_read_lock(mm); * do_something() - * get_user_pages_locked(tsk, mm, ..., pages, &locked); + * get_user_pages_locked(mm, ..., pages, &locked); * if (locked) * mmap_read_unlock(mm); * @@ -2041,7 +2013,7 @@ long get_user_pages_locked(unsigned long start, unsigned long nr_pages, if (WARN_ON_ONCE(gup_flags & FOLL_PIN)) return -EINVAL; - return __get_user_pages_locked(current, current->mm, start, nr_pages, + return __get_user_pages_locked(current->mm, start, nr_pages, pages, NULL, locked, gup_flags | FOLL_TOUCH); } @@ -2051,12 +2023,12 @@ EXPORT_SYMBOL(get_user_pages_locked); * get_user_pages_unlocked() is suitable to replace the form: * * mmap_read_lock(mm); - * get_user_pages(tsk, mm, ..., pages, NULL); + * get_user_pages(mm, ..., pages, NULL); * mmap_read_unlock(mm); * * with: * - * get_user_pages_unlocked(tsk, mm, ..., pages); + * get_user_pages_unlocked(mm, ..., pages); * * It is functionally equivalent to get_user_pages_fast so * get_user_pages_fast should be used instead if specific gup_flags @@ -2079,7 +2051,7 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, return -EINVAL; mmap_read_lock(mm); - ret = __get_user_pages_locked(current, mm, start, nr_pages, pages, NULL, + ret = __get_user_pages_locked(mm, start, nr_pages, pages, NULL, &locked, gup_flags | FOLL_TOUCH); if (locked) mmap_read_unlock(mm); @@ -2724,7 +2696,7 @@ static int __gup_longterm_unlocked(unsigned long start, int nr_pages, */ if (gup_flags & FOLL_LONGTERM) { mmap_read_lock(current->mm); - ret = __gup_longterm_locked(current, current->mm, + ret = __gup_longterm_locked(current->mm, start, nr_pages, pages, NULL, gup_flags); mmap_read_unlock(current->mm); @@ -2967,10 +2939,8 @@ int pin_user_pages_fast_only(unsigned long start, int nr_pages, EXPORT_SYMBOL_GPL(pin_user_pages_fast_only); /** - * pin_user_pages_remote() - pin pages of a remote process (task != current) + * pin_user_pages_remote() - pin pages of a remote process * - * @tsk: the task_struct to use for page fault accounting, or - * NULL if faults are not to be recorded. * @mm: mm_struct of target mm * @start: starting user address * @nr_pages: number of pages from start to pin @@ -2991,7 +2961,7 @@ EXPORT_SYMBOL_GPL(pin_user_pages_fast_only); * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for details. */ -long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, +long pin_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked) @@ -3001,7 +2971,7 @@ long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, return -EINVAL; gup_flags |= FOLL_PIN; - return __get_user_pages_remote(tsk, mm, start, nr_pages, gup_flags, + return __get_user_pages_remote(mm, start, nr_pages, gup_flags, pages, vmas, locked); } EXPORT_SYMBOL(pin_user_pages_remote); @@ -3033,7 +3003,7 @@ long pin_user_pages(unsigned long start, unsigned long nr_pages, return -EINVAL; gup_flags |= FOLL_PIN; - return __gup_longterm_locked(current, current->mm, start, nr_pages, + return __gup_longterm_locked(current->mm, start, nr_pages, pages, vmas, gup_flags); } EXPORT_SYMBOL(pin_user_pages); @@ -3078,7 +3048,7 @@ long pin_user_pages_locked(unsigned long start, unsigned long nr_pages, return -EINVAL; gup_flags |= FOLL_PIN; - return __get_user_pages_locked(current, current->mm, start, nr_pages, + return __get_user_pages_locked(current->mm, start, nr_pages, pages, NULL, locked, gup_flags | FOLL_TOUCH); } @@ -75,7 +75,8 @@ static int hmm_vma_fault(unsigned long addr, unsigned long end, } for (; addr < end; addr += PAGE_SIZE) - if (handle_mm_fault(vma, addr, fault_flags) & VM_FAULT_ERROR) + if (handle_mm_fault(vma, addr, fault_flags, NULL) & + VM_FAULT_ERROR) return -EFAULT; return -EBUSY; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 0da89305a555..589c330df4db 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1092,15 +1092,6 @@ retry_cpuset: return NULL; } -/* Movability of hugepages depends on migration support. */ -static inline gfp_t htlb_alloc_mask(struct hstate *h) -{ - if (hugepage_movable_supported(h)) - return GFP_HIGHUSER_MOVABLE; - else - return GFP_HIGHUSER; -} - static struct page *dequeue_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address, int avoid_reserve, @@ -2022,31 +2013,9 @@ struct page *alloc_buddy_huge_page_with_mpol(struct hstate *h, } /* page migration callback function */ -struct page *alloc_huge_page_node(struct hstate *h, int nid) -{ - gfp_t gfp_mask = htlb_alloc_mask(h); - struct page *page = NULL; - - if (nid != NUMA_NO_NODE) - gfp_mask |= __GFP_THISNODE; - - spin_lock(&hugetlb_lock); - if (h->free_huge_pages - h->resv_huge_pages > 0) - page = dequeue_huge_page_nodemask(h, gfp_mask, nid, NULL); - spin_unlock(&hugetlb_lock); - - if (!page) - page = alloc_migrate_huge_page(h, gfp_mask, nid, NULL); - - return page; -} - -/* page migration callback function */ struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, - nodemask_t *nmask) + nodemask_t *nmask, gfp_t gfp_mask) { - gfp_t gfp_mask = htlb_alloc_mask(h); - spin_lock(&hugetlb_lock); if (h->free_huge_pages - h->resv_huge_pages > 0) { struct page *page; @@ -2074,7 +2043,7 @@ struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, gfp_mask = htlb_alloc_mask(h); node = huge_node(vma, address, gfp_mask, &mpol, &nodemask); - page = alloc_huge_page_nodemask(h, node, nodemask); + page = alloc_huge_page_nodemask(h, node, nodemask, gfp_mask); mpol_cond_put(mpol); return page; diff --git a/mm/internal.h b/mm/internal.h index dd14c5311d7f..10c677655912 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -613,5 +613,11 @@ static inline bool is_migrate_highatomic_page(struct page *page) } void setup_zone_pageset(struct zone *zone); -extern struct page *alloc_new_node_page(struct page *page, unsigned long node); + +struct migration_target_control { + int nid; /* preferred node id */ + nodemask_t *nmask; + gfp_t gfp_mask; +}; + #endif /* __MM_INTERNAL_H */ diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 29a684a4656a..4e644dc074b1 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1169,8 +1169,10 @@ static bool update_checksum(struct kmemleak_object *object) u32 old_csum = object->checksum; kasan_disable_current(); + kcsan_disable_current(); object->checksum = crc32(0, (void *)object->pointer, object->size); kasan_enable_current(); + kcsan_enable_current(); return object->checksum != old_csum; } @@ -480,7 +480,8 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr) break; if (PageKsm(page)) ret = handle_mm_fault(vma, addr, - FAULT_FLAG_WRITE | FAULT_FLAG_REMOTE); + FAULT_FLAG_WRITE | FAULT_FLAG_REMOTE, + NULL); else ret = VM_FAULT_WRITE; put_page(page); diff --git a/mm/list_lru.c b/mm/list_lru.c index e825804b3928..5aa6e44bc2ae 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -180,7 +180,7 @@ unsigned long list_lru_count_one(struct list_lru *lru, rcu_read_lock(); l = list_lru_from_memcg_idx(nlru, memcg_cache_id(memcg)); - count = l->nr_items; + count = READ_ONCE(l->nr_items); rcu_read_unlock(); return count; diff --git a/mm/madvise.c b/mm/madvise.c index 1fe2e55c0a9b..7b5ca96108cd 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -17,17 +17,20 @@ #include <linux/falloc.h> #include <linux/fadvise.h> #include <linux/sched.h> +#include <linux/sched/mm.h> #include <linux/ksm.h> #include <linux/fs.h> #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 +39,7 @@ struct madvise_walk_private { struct mmu_gather *tlb; bool pageout; + struct task_struct *target_task; }; /* @@ -255,6 +259,7 @@ 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; @@ -289,12 +294,12 @@ static long madvise_willneed(struct vm_area_struct *vma, */ *prev = NULL; /* tell sys_madvise we drop mmap_lock */ get_file(file); - mmap_read_unlock(current->mm); + mmap_read_unlock(mm); offset = (loff_t)(start - vma->vm_start) + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED); fput(file); - mmap_read_lock(current->mm); + mmap_read_lock(mm); return 0; } @@ -315,6 +320,10 @@ 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 +485,14 @@ 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 +500,8 @@ 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 +514,21 @@ 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 +552,8 @@ 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 +569,7 @@ 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 +698,6 @@ 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 +777,8 @@ 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 +786,8 @@ 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 +841,7 @@ 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 +869,13 @@ 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 +944,8 @@ 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 +954,9 @@ 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 +1003,18 @@ 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 +1062,11 @@ 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 +1081,8 @@ 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 +1120,7 @@ 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 +1135,12 @@ 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 +1148,7 @@ 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 +1173,8 @@ 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 +1186,122 @@ 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 7359164c3fe9..9523515be997 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1659,13 +1659,6 @@ int unpoison_memory(unsigned long pfn) } EXPORT_SYMBOL(unpoison_memory); -static struct page *new_page(struct page *p, unsigned long private) -{ - int nid = page_to_nid(p); - - return new_page_nodemask(p, nid, &node_states[N_MEMORY]); -} - /* * Safely get reference count of an arbitrary page. * Returns 0 for a free page, -EIO for a zero refcount page @@ -1770,6 +1763,10 @@ static int __soft_offline_page(struct page *page) const char *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 @@ -1806,8 +1803,8 @@ 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) { page_handle_poison(page, true, true, huge); } else { diff --git a/mm/memory.c b/mm/memory.c index 9ffbe8fa08e6..45e1dc0547ba 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -71,6 +71,8 @@ #include <linux/dax.h> #include <linux/oom.h> #include <linux/numa.h> +#include <linux/perf_event.h> +#include <linux/ptrace.h> #include <trace/events/kmem.h> @@ -3127,8 +3129,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (!page) { struct swap_info_struct *si = swp_swap_info(entry); - if (si->flags & SWP_SYNCHRONOUS_IO && - __swap_count(entry) == 1) { + if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && + __swap_count(entry) == 1) { /* skip swapcache */ page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); @@ -4366,6 +4368,67 @@ retry_pud: return handle_pte_fault(&vmf); } +/** + * mm_account_fault - Do page fault accountings + * + * @regs: the pt_regs struct pointer. When set to NULL, will skip accounting + * of perf event counters, but we'll still do the per-task accounting to + * the task who triggered this page fault. + * @address: the faulted address. + * @flags: the fault flags. + * @ret: the fault retcode. + * + * This will take care of most of the page fault accountings. Meanwhile, it + * will also include the PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] perf counter + * updates. However note that the handling of PERF_COUNT_SW_PAGE_FAULTS should + * still be in per-arch page fault handlers at the entry of page fault. + */ +static inline void mm_account_fault(struct pt_regs *regs, + unsigned long address, unsigned int flags, + vm_fault_t ret) +{ + bool major; + + /* + * We don't do accounting for some specific faults: + * + * - Unsuccessful faults (e.g. when the address wasn't valid). That + * includes arch_vma_access_permitted() failing before reaching here. + * So this is not a "this many hardware page faults" counter. We + * should use the hw profiling for that. + * + * - Incomplete faults (VM_FAULT_RETRY). They will only be counted + * once they're completed. + */ + if (ret & (VM_FAULT_ERROR | VM_FAULT_RETRY)) + return; + + /* + * We define the fault as a major fault when the final successful fault + * is VM_FAULT_MAJOR, or if it retried (which implies that we couldn't + * handle it immediately previously). + */ + major = (ret & VM_FAULT_MAJOR) || (flags & FAULT_FLAG_TRIED); + + if (major) + current->maj_flt++; + else + current->min_flt++; + + /* + * If the fault is done for GUP, regs will be NULL. We only do the + * accounting for the per thread fault counters who triggered the + * fault, and we skip the perf event updates. + */ + if (!regs) + return; + + if (major) + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); + else + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); +} + /* * By the time we get here, we already hold the mm semaphore * @@ -4373,7 +4436,7 @@ retry_pud: * return value. See filemap_fault() and __lock_page_or_retry(). */ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, - unsigned int flags) + unsigned int flags, struct pt_regs *regs) { vm_fault_t ret; @@ -4414,6 +4477,8 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, mem_cgroup_oom_synchronize(false); } + mm_account_fault(regs, address, flags, ret); + return ret; } EXPORT_SYMBOL_GPL(handle_mm_fault); @@ -4687,7 +4752,7 @@ int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, void *maddr; struct page *page = NULL; - ret = get_user_pages_remote(tsk, mm, addr, 1, + ret = get_user_pages_remote(mm, addr, 1, gup_flags, &page, &vma, NULL); if (ret <= 0) { #ifndef CONFIG_HAVE_IOREMAP_PROT diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 0204de3f9601..dcdf3271f87e 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1275,23 +1275,6 @@ found: return 0; } -static struct page *new_node_page(struct page *page, unsigned long private) -{ - int nid = page_to_nid(page); - nodemask_t nmask = node_states[N_MEMORY]; - - /* - * 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(nid, nmask); - if (nodes_empty(nmask)) - node_set(nid, nmask); - - return new_page_nodemask(page, nid, &nmask); -} - static int do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) { @@ -1351,9 +1334,28 @@ 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/mempolicy.c b/mm/mempolicy.c index dabcee8630f2..93fcfc1f2fa2 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1065,27 +1065,6 @@ static int migrate_page_add(struct page *page, struct list_head *pagelist, return 0; } -/* page allocation callback for NUMA node migration */ -struct page *alloc_new_node_page(struct page *page, unsigned long node) -{ - if (PageHuge(page)) - return alloc_huge_page_node(page_hstate(compound_head(page)), - node); - else if (PageTransHuge(page)) { - struct page *thp; - - thp = alloc_pages_node(node, - (GFP_TRANSHUGE | __GFP_THISNODE), - HPAGE_PMD_ORDER); - if (!thp) - return NULL; - prep_transhuge_page(thp); - return thp; - } else - return __alloc_pages_node(node, GFP_HIGHUSER_MOVABLE | - __GFP_THISNODE, 0); -} - /* * Migrate pages from one node to a target node. * Returns error or the number of pages not migrated. @@ -1096,6 +1075,10 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, nodemask_t nmask; LIST_HEAD(pagelist); int err = 0; + struct migration_target_control mtc = { + .nid = dest, + .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, + }; nodes_clear(nmask); node_set(source, nmask); @@ -1110,8 +1093,8 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, flags | MPOL_MF_DISCONTIG_OK, &pagelist); if (!list_empty(&pagelist)) { - err = migrate_pages(&pagelist, alloc_new_node_page, NULL, dest, - MIGRATE_SYNC, MR_SYSCALL); + err = migrate_pages(&pagelist, alloc_migration_target, NULL, + (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL); if (err) putback_movable_pages(&pagelist); } diff --git a/mm/mempool.c b/mm/mempool.c index 85efab3da720..79bff63ecf27 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -489,7 +489,7 @@ void mempool_free(void *element, mempool_t *pool) * ensures that there will be frees which return elements to the * pool waking up the waiters. */ - if (unlikely(pool->curr_nr < pool->min_nr)) { + if (unlikely(READ_ONCE(pool->curr_nr) < pool->min_nr)) { spin_lock_irqsave(&pool->lock, flags); if (likely(pool->curr_nr < pool->min_nr)) { add_element(pool, element); diff --git a/mm/migrate.c b/mm/migrate.c index de0f3662c605..c23378169762 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1533,6 +1533,49 @@ out: return rc; } +struct page *alloc_migration_target(struct page *page, unsigned long private) +{ + struct migration_target_control *mtc; + gfp_t gfp_mask; + unsigned int order = 0; + struct page *new_page = NULL; + int nid; + int zidx; + + mtc = (struct migration_target_control *)private; + gfp_mask = mtc->gfp_mask; + nid = mtc->nid; + if (nid == NUMA_NO_NODE) + nid = page_to_nid(page); + + if (PageHuge(page)) { + struct hstate *h = page_hstate(compound_head(page)); + + gfp_mask = htlb_modify_alloc_mask(h, gfp_mask); + return alloc_huge_page_nodemask(h, nid, mtc->nmask, gfp_mask); + } + + if (PageTransHuge(page)) { + /* + * clear __GFP_RECLAIM to make the migration callback + * consistent with regular THP allocations. + */ + gfp_mask &= ~__GFP_RECLAIM; + gfp_mask |= GFP_TRANSHUGE; + order = HPAGE_PMD_ORDER; + } + zidx = zone_idx(page_zone(page)); + if (is_highmem_idx(zidx) || zidx == ZONE_MOVABLE) + gfp_mask |= __GFP_HIGHMEM; + + new_page = __alloc_pages_nodemask(gfp_mask, order, nid, mtc->nmask); + + if (new_page && PageTransHuge(new_page)) + prep_transhuge_page(new_page); + + return new_page; +} + #ifdef CONFIG_NUMA static int store_status(int __user *status, int start, int value, int nr) @@ -1550,9 +1593,13 @@ static int do_move_pages_to_node(struct mm_struct *mm, struct list_head *pagelist, int node) { int err; + struct migration_target_control mtc = { + .nid = node, + .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, + }; - err = migrate_pages(pagelist, alloc_new_node_page, NULL, node, - MIGRATE_SYNC, MR_SYSCALL); + err = migrate_pages(pagelist, alloc_migration_target, NULL, + (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL); if (err) putback_movable_pages(pagelist); return err; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6f4056cf7384..b31f310c2545 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8349,6 +8349,10 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, unsigned long pfn = start; unsigned int tries = 0; int ret = 0; + struct migration_target_control mtc = { + .nid = zone_to_nid(cc->zone), + .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, + }; migrate_prep(); @@ -8375,8 +8379,8 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, &cc->migratepages); cc->nr_migratepages -= nr_reclaimed; - ret = migrate_pages(&cc->migratepages, alloc_migrate_target, - NULL, 0, cc->mode, MR_CONTIG_RANGE); + ret = migrate_pages(&cc->migratepages, alloc_migration_target, + NULL, (unsigned long)&mtc, cc->mode, MR_CONTIG_RANGE); } if (ret < 0) { putback_movable_pages(&cc->migratepages); diff --git a/mm/page_counter.c b/mm/page_counter.c index c56db2d5e159..e3a205275a0b 100644 --- a/mm/page_counter.c +++ b/mm/page_counter.c @@ -77,8 +77,8 @@ void page_counter_charge(struct page_counter *counter, unsigned long nr_pages) * This is indeed racy, but we can live with some * inaccuracy in the watermark. */ - if (new > c->watermark) - c->watermark = new; + if (new > READ_ONCE(c->watermark)) + WRITE_ONCE(c->watermark, new); } } @@ -119,9 +119,10 @@ bool page_counter_try_charge(struct page_counter *counter, propagate_protected_usage(counter, new); /* * This is racy, but we can live with some - * inaccuracy in the failcnt. + * inaccuracy in the failcnt which is only used + * to report stats. */ - c->failcnt++; + data_race(c->failcnt++); *fail = c; goto failed; } @@ -130,8 +131,8 @@ bool page_counter_try_charge(struct page_counter *counter, * Just like with failcnt, we can live with some * inaccuracy in the watermark. */ - if (new > c->watermark) - c->watermark = new; + if (new > READ_ONCE(c->watermark)) + WRITE_ONCE(c->watermark, new); } return true; diff --git a/mm/page_io.c b/mm/page_io.c index eaaecb75a8c5..739cb5b458dc 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -85,7 +85,7 @@ static void swap_slot_free_notify(struct page *page) return; sis = page_swap_info(page); - if (!(sis->flags & SWP_BLKDEV)) + if (data_race(!(sis->flags & SWP_BLKDEV))) return; /* @@ -312,7 +312,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, struct swap_info_struct *sis = page_swap_info(page); VM_BUG_ON_PAGE(!PageSwapCache(page), page); - if (sis->flags & SWP_FS) { + if (data_race(sis->flags & SWP_FS)) { struct kiocb kiocb; struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; @@ -403,7 +403,7 @@ int swap_readpage(struct page *page, bool synchronous) goto out; } - if (sis->flags & SWP_FS) { + if (data_race(sis->flags & SWP_FS)) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; @@ -465,7 +465,7 @@ int swap_set_page_dirty(struct page *page) { struct swap_info_struct *sis = page_swap_info(page); - if (sis->flags & SWP_FS) { + if (data_race(sis->flags & SWP_FS)) { struct address_space *mapping = sis->swap_file->f_mapping; VM_BUG_ON_PAGE(!PageSwapCache(page), page); diff --git a/mm/page_isolation.c b/mm/page_isolation.c index f6d07c5f0d34..242c03121d73 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -306,8 +306,3 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, return pfn < end_pfn ? -EBUSY : 0; } - -struct page *alloc_migrate_target(struct page *page, unsigned long private) -{ - return new_page_nodemask(page, numa_node_id(), &node_states[N_MEMORY]); -} diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index cc85ce81914a..29c052099aff 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -105,7 +105,7 @@ static int process_vm_rw_single_vec(unsigned long addr, * current/current->mm */ mmap_read_lock(mm); - pinned_pages = pin_user_pages_remote(task, mm, pa, pinned_pages, + pinned_pages = pin_user_pages_remote(mm, pa, pinned_pages, flags, process_pages, NULL, &locked); if (locked) diff --git a/mm/rmap.c b/mm/rmap.c index c56fab5826c1..b970353c06ed 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -672,7 +672,7 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) */ void flush_tlb_batched_pending(struct mm_struct *mm) { - if (mm->tlb_flush_batched) { + if (data_race(mm->tlb_flush_batched)) { flush_tlb_mm(mm); /* diff --git a/mm/swap.c b/mm/swap.c index 28ab40041b47..587be74a68de 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -631,7 +631,8 @@ void lru_add_drain_cpu(int cpu) __pagevec_lru_add(pvec); pvec = &per_cpu(lru_rotate.pvec, cpu); - if (pagevec_count(pvec)) { + /* Disabling interrupts below acts as a compiler barrier. */ + if (data_race(pagevec_count(pvec))) { unsigned long flags; /* No harm done if a racing interrupt already did this */ @@ -792,7 +793,7 @@ void lru_add_drain_all(void) struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); if (pagevec_count(&per_cpu(lru_pvecs.lru_add, cpu)) || - pagevec_count(&per_cpu(lru_rotate.pvec, cpu)) || + data_race(pagevec_count(&per_cpu(lru_rotate.pvec, cpu))) || pagevec_count(&per_cpu(lru_pvecs.lru_deactivate_file, cpu)) || pagevec_count(&per_cpu(lru_pvecs.lru_deactivate, cpu)) || pagevec_count(&per_cpu(lru_pvecs.lru_lazyfree, cpu)) || diff --git a/mm/swap_state.c b/mm/swap_state.c index 1983be226b1c..66e750f361ed 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -57,8 +57,8 @@ static bool enable_vma_readahead __read_mostly = true; #define GET_SWAP_RA_VAL(vma) \ (atomic_long_read(&(vma)->swap_readahead_info) ? : 4) -#define INC_CACHE_INFO(x) do { swap_cache_info.x++; } while (0) -#define ADD_CACHE_INFO(x, nr) do { swap_cache_info.x += (nr); } while (0) +#define INC_CACHE_INFO(x) data_race(swap_cache_info.x++) +#define ADD_CACHE_INFO(x, nr) data_race(swap_cache_info.x += (nr)) static struct { unsigned long add_total; diff --git a/mm/swapfile.c b/mm/swapfile.c index 7d22347264e6..7b0974f0fcc4 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -672,7 +672,7 @@ static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, if (offset == si->lowest_bit) si->lowest_bit += nr_entries; if (end == si->highest_bit) - si->highest_bit -= nr_entries; + WRITE_ONCE(si->highest_bit, si->highest_bit - nr_entries); si->inuse_pages += nr_entries; if (si->inuse_pages == si->pages) { si->lowest_bit = si->max; @@ -704,7 +704,7 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset, if (end > si->highest_bit) { bool was_full = !si->highest_bit; - si->highest_bit = end; + WRITE_ONCE(si->highest_bit, end); if (was_full && (si->flags & SWP_WRITEOK)) add_to_avail_list(si); } @@ -869,7 +869,7 @@ checks: else goto done; } - si->swap_map[offset] = usage; + WRITE_ONCE(si->swap_map[offset], usage); inc_cluster_info_page(si, si->cluster_info, offset); unlock_cluster(ci); @@ -928,12 +928,13 @@ done: scan: spin_unlock(&si->lock); - while (++offset <= si->highest_bit) { - if (!si->swap_map[offset]) { + while (++offset <= READ_ONCE(si->highest_bit)) { + if (data_race(!si->swap_map[offset])) { spin_lock(&si->lock); goto checks; } - if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { + if (vm_swap_full() && + READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { spin_lock(&si->lock); goto checks; } @@ -945,11 +946,12 @@ scan: } offset = si->lowest_bit; while (offset < scan_base) { - if (!si->swap_map[offset]) { + if (data_race(!si->swap_map[offset])) { spin_lock(&si->lock); goto checks; } - if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { + if (vm_swap_full() && + READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { spin_lock(&si->lock); goto checks; } @@ -1148,7 +1150,7 @@ static struct swap_info_struct *__swap_info_get(swp_entry_t entry) p = swp_swap_info(entry); if (!p) goto bad_nofile; - if (!(p->flags & SWP_USED)) + if (data_race(!(p->flags & SWP_USED))) goto bad_device; offset = swp_offset(entry); if (offset >= p->max) @@ -1174,7 +1176,7 @@ static struct swap_info_struct *_swap_info_get(swp_entry_t entry) p = __swap_info_get(entry); if (!p) goto out; - if (!p->swap_map[swp_offset(entry)]) + if (data_race(!p->swap_map[swp_offset(entry)])) goto bad_free; return p; @@ -1243,7 +1245,10 @@ static unsigned char __swap_entry_free_locked(struct swap_info_struct *p, } usage = count | has_cache; - p->swap_map[offset] = usage ? : SWAP_HAS_CACHE; + if (usage) + WRITE_ONCE(p->swap_map[offset], usage); + else + WRITE_ONCE(p->swap_map[offset], SWAP_HAS_CACHE); return usage; } @@ -1295,7 +1300,7 @@ struct swap_info_struct *get_swap_device(swp_entry_t entry) goto bad_nofile; rcu_read_lock(); - if (!(si->flags & SWP_VALID)) + if (data_race(!(si->flags & SWP_VALID))) goto unlock_out; offset = swp_offset(entry); if (offset >= si->max) @@ -3484,7 +3489,7 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage) } else err = -ENOENT; /* unused swap entry */ - p->swap_map[offset] = count | has_cache; + WRITE_ONCE(p->swap_map[offset], count | has_cache); unlock_out: unlock_cluster_or_swap_info(p, ci); diff --git a/scripts/deprecated_terms.txt b/scripts/deprecated_terms.txt index 4512ef5d5ffa..1be27a24187b 100644 --- a/scripts/deprecated_terms.txt +++ b/scripts/deprecated_terms.txt @@ -3,5 +3,8 @@ # The format of each line is: # deprecated||suggested # -blacklist||denylist -whitelist||allowlist +blacklist||(denylist|blocklist) +# For other alternatives of 'slave', Please refer to +# Documentation/process/coding-style.rst +slave||(secondary|target|...) +whitelist||(allowlist|passlist) diff --git a/security/tomoyo/domain.c b/security/tomoyo/domain.c index 7869d6a9980b..afe5e68ede77 100644 --- a/security/tomoyo/domain.c +++ b/security/tomoyo/domain.c @@ -914,7 +914,7 @@ bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos, * (represented by bprm). 'current' is the process doing * the execve(). */ - if (get_user_pages_remote(current, bprm->mm, pos, 1, + if (get_user_pages_remote(bprm->mm, pos, 1, FOLL_FORCE, &page, NULL, NULL) <= 0) return false; #else diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 35b61bfc1b1a..6d29d9a6bc60 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -193,7 +193,7 @@ 146 common writev sys_writev compat_sys_writev 147 common getsid sys_getsid 148 common fdatasync sys_fdatasync -149 nospu _sysctl sys_sysctl compat_sys_sysctl +149 nospu _sysctl sys_ni_syscall 150 common mlock sys_mlock 151 common munlock sys_munlock 152 common mlockall sys_mlockall diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index b38d48464368..29144b79a49d 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -138,7 +138,7 @@ 146 common writev sys_writev compat_sys_writev 147 common getsid sys_getsid sys_getsid 148 common fdatasync sys_fdatasync sys_fdatasync -149 common _sysctl sys_sysctl compat_sys_sysctl +149 common _sysctl - - 150 common mlock sys_mlock compat_sys_mlock 151 common munlock sys_munlock compat_sys_munlock 152 common mlockall sys_mlockall sys_mlockall diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 78847b32e137..d1c42227b857 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -164,7 +164,7 @@ 153 common vhangup sys_vhangup 154 common modify_ldt sys_modify_ldt 155 common pivot_root sys_pivot_root -156 64 _sysctl sys_sysctl +156 64 _sysctl sys_ni_syscall 157 common prctl sys_prctl 158 common arch_prctl sys_arch_prctl 159 common adjtimex sys_adjtimex diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 390f758d5a27..dd777688d14a 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -61,7 +61,7 @@ static void async_pf_execute(struct work_struct *work) * access remotely. */ mmap_read_lock(mm); - get_user_pages_remote(NULL, mm, addr, 1, FOLL_WRITE, NULL, NULL, + get_user_pages_remote(mm, addr, 1, FOLL_WRITE, NULL, NULL, &locked); if (locked) mmap_read_unlock(mm); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 2c2c0254c2d8..737666db02de 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1893,7 +1893,7 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma, * not call the fault handler, so do it here. */ bool unlocked = false; - r = fixup_user_fault(current, current->mm, addr, + r = fixup_user_fault(current->mm, addr, (write_fault ? FAULT_FLAG_WRITE : 0), &unlocked); if (unlocked) |