Merge "Revert "mm: memory: reduce fault_around_bytes"" (e1b61ad2) · Commits · e / devices / android_kernel_fairphone_FP3

arch/arm64/Kconfig

+1 −0

Original line number	Diff line number	Diff line
		@@ -129,6 +129,7 @@ config ARM64
		select SPARSE_IRQ
		select SYSCTL_EXCEPTION_TRACE
		select THREAD_INFO_IN_TASK
		select ARCH_SUPPORTS_SPECULATIVE_PAGE_FAULT
		help
		ARM 64-bit (AArch64) Linux support.

arch/arm64/mm/fault.c

+45 −24

Original line number	Diff line number	Diff line
		@@ -253,14 +253,12 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re
		#define VM_FAULT_BADMAP 0x010000
		#define VM_FAULT_BADACCESS 0x020000

		static int __do_page_fault(struct mm_struct *mm, unsigned long addr,
		static int __do_page_fault(struct vm_area_struct *vma, unsigned long addr,
		unsigned int mm_flags, unsigned long vm_flags,
		struct task_struct *tsk)
		{
		struct vm_area_struct *vma;
		int fault;

		vma = find_vma(mm, addr);
		fault = VM_FAULT_BADMAP;
		if (unlikely(!vma))
		goto out;
		@@ -318,6 +316,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
		int fault, sig, code;
		unsigned long vm_flags = VM_READ \| VM_WRITE;
		unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY \| FAULT_FLAG_KILLABLE;
		struct vm_area_struct *vma = NULL;

		if (notify_page_fault(regs, esr))
		return 0;
		@@ -355,6 +354,14 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
		die("Accessing user space memory outside uaccess.h routines", regs, esr);
		}

		/*
		* let's try a speculative page fault without grabbing the
		* mmap_sem.
		*/
		fault = handle_speculative_fault(mm, addr, mm_flags, &vma);
		if (fault != VM_FAULT_RETRY)
		goto done;

		/*
		* As per x86, we may deadlock here. However, since the kernel only
		* validly references user space from well defined areas of the code,
		@@ -377,19 +384,44 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
		#endif
		}

		fault = __do_page_fault(mm, addr, mm_flags, vm_flags, tsk);
		if (!vma \|\| !can_reuse_spf_vma(vma, addr))
		vma = find_vma(mm, addr);

		fault = __do_page_fault(vma, addr, mm_flags, vm_flags, tsk);
		if (fault & VM_FAULT_RETRY) {
		/*
		* If we need to retry but a fatal signal is pending, handle the
		* signal first. We do not need to release the mmap_sem because it
		* would already be released in __lock_page_or_retry in mm/filemap.c.
		* signal first. We do not need to release the mmap_sem because
		* it would already be released in __lock_page_or_retry in
		* mm/filemap.c.
		*/
		if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {

		if (fatal_signal_pending(current)) {
		if (!user_mode(regs))
		goto no_context;
		return 0;
		}

		/*
		* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk of
		* starvation.
		*/
		if (mm_flags & FAULT_FLAG_ALLOW_RETRY) {
		mm_flags &= ~FAULT_FLAG_ALLOW_RETRY;
		mm_flags \|= FAULT_FLAG_TRIED;

		/*
		* Do not try to reuse this vma and fetch it
		* again since we will release the mmap_sem.
		*/
		vma = NULL;
		goto retry;
		}
		}

		up_read(&mm->mmap_sem);
		done:

		/*
		* Major/minor page fault accounting is only done on the initial
		* attempt. If we go through a retry, it is extremely likely that the
		@@ -407,19 +439,8 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs,
		addr);
		}
		if (fault & VM_FAULT_RETRY) {
		/*
		* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk of
		* starvation.
		*/
		mm_flags &= ~FAULT_FLAG_ALLOW_RETRY;
		mm_flags \|= FAULT_FLAG_TRIED;
		goto retry;
		}
		}

		up_read(&mm->mmap_sem);

		/*
		* Handle the "normal" case first - VM_FAULT_MAJOR
		*/

fs/exec.c

+1 −1

Original line number	Diff line number	Diff line
		@@ -306,7 +306,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
		vma->vm_start = vma->vm_end - PAGE_SIZE;
		vma->vm_flags = VM_SOFTDIRTY \| VM_STACK_FLAGS \| VM_STACK_INCOMPLETE_SETUP;
		vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
		INIT_LIST_HEAD(&vma->anon_vma_chain);
		INIT_VMA(vma);

		err = insert_vm_struct(mm, vma);
		if (err)

fs/proc/task_mmu.c

+4 −1

Original line number	Diff line number	Diff line
		@@ -1123,8 +1123,11 @@ static ssize_t clear_refs_write(struct file file, const char __user buf,
		goto out_mm;
		}
		for (vma = mm->mmap; vma; vma = vma->vm_next) {
		vma->vm_flags &= ~VM_SOFTDIRTY;
		vm_write_begin(vma);
		WRITE_ONCE(vma->vm_flags,
		vma->vm_flags & ~VM_SOFTDIRTY);
		vma_set_page_prot(vma);
		vm_write_end(vma);
		}
		downgrade_write(&mm->mmap_sem);
		break;

fs/userfaultfd.c

+9 −3

Original line number	Diff line number	Diff line
		@@ -499,8 +499,10 @@ static int userfaultfd_release(struct inode inode, struct file file)
		vma = prev;
		else
		prev = vma;
		vma->vm_flags = new_flags;
		vm_write_begin(vma);
		WRITE_ONCE(vma->vm_flags, new_flags);
		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
		vm_write_end(vma);
		}
		up_write(&mm->mmap_sem);
		mmput(mm);
		@@ -895,8 +897,10 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
		* the next vma was merged into the current one and
		* the current one has not been updated yet.
		*/
		vma->vm_flags = new_flags;
		vm_write_begin(vma);
		WRITE_ONCE(vma->vm_flags, new_flags);
		vma->vm_userfaultfd_ctx.ctx = ctx;
		vm_write_end(vma);

		skip:
		prev = vma;
		@@ -1033,8 +1037,10 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
		* the next vma was merged into the current one and
		* the current one has not been updated yet.
		*/
		vma->vm_flags = new_flags;
		vm_write_begin(vma);
		WRITE_ONCE(vma->vm_flags, new_flags);
		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
		vm_write_end(vma);

		skip:
		prev = vma;