LU-13669 llite: make readahead aware of hints

[fs/lustre-release.git] / lustre / llite / llite_mmap.c

diff --git a/lustre/llite/llite_mmap.c b/lustre/llite/llite_mmap.c
index f3fd0a2..8ac6698 100644 (file)
--- a/lustre/llite/llite_mmap.c
+++ b/lustre/llite/llite_mmap.c
@@ -76,13 +76,11 @@ struct vm_area_struct *our_vma(struct mm_struct *mm, unsigned long addr,
  * \param env - corespondent lu_env to processing
  * \param vma - virtual memory area addressed to page fault
  * \param index - page index corespondent to fault.
- * \parm ra_flags - vma readahead flags.
  *
  * \return error codes from cl_io_init.
  */
 static struct cl_io *
-ll_fault_io_init(struct lu_env *env, struct vm_area_struct *vma,
-                pgoff_t index, unsigned long *ra_flags)
+ll_fault_io_init(struct lu_env *env, struct vm_area_struct *vma, pgoff_t index)
 {
        struct file            *file = vma->vm_file;
        struct inode           *inode = file_inode(file);
@@ -91,30 +89,27 @@ ll_fault_io_init(struct lu_env *env, struct vm_area_struct *vma,
        int                     rc;
        ENTRY;
 
-        if (ll_file_nolock(file))
-                RETURN(ERR_PTR(-EOPNOTSUPP));
+       if (ll_file_nolock(file))
+               RETURN(ERR_PTR(-EOPNOTSUPP));
 
 restart:
        io = vvp_env_thread_io(env);
-        io->ci_obj = ll_i2info(inode)->lli_clob;
-        LASSERT(io->ci_obj != NULL);
-
-        fio = &io->u.ci_fault;
-        fio->ft_index      = index;
-        fio->ft_executable = vma->vm_flags&VM_EXEC;
-
-        /*
-         * disable VM_SEQ_READ and use VM_RAND_READ to make sure that
-         * the kernel will not read other pages not covered by ldlm in
-         * filemap_nopage. we do our readahead in ll_readpage.
-         */
-        if (ra_flags != NULL)
-                *ra_flags = vma->vm_flags & (VM_RAND_READ|VM_SEQ_READ);
-        vma->vm_flags &= ~VM_SEQ_READ;
-        vma->vm_flags |= VM_RAND_READ;
-
-        CDEBUG(D_MMAP, "vm_flags: %lx (%lu %d)\n", vma->vm_flags,
-               fio->ft_index, fio->ft_executable);
+       io->ci_obj = ll_i2info(inode)->lli_clob;
+       LASSERT(io->ci_obj != NULL);
+
+       fio = &io->u.ci_fault;
+       fio->ft_index = index;
+       fio->ft_executable = vma->vm_flags & VM_EXEC;
+
+       CDEBUG(D_MMAP,
+              DFID": vma=%p start=%#lx end=%#lx vm_flags=%#lx idx=%lu\n",
+              PFID(&ll_i2info(inode)->lli_fid), vma, vma->vm_start,
+              vma->vm_end, vma->vm_flags, fio->ft_index);
+
+       if (vma->vm_flags & VM_SEQ_READ)
+               io->ci_seq_read = 1;
+       else if (vma->vm_flags & VM_RAND_READ)
+               io->ci_rand_read = 1;
 
        rc = cl_io_init(env, io, CIT_FAULT, io->ci_obj);
        if (rc == 0) {
@@ -158,7 +153,7 @@ static int ll_page_mkwrite0(struct vm_area_struct *vma, struct page *vmpage,
        if (IS_ERR(env))
                RETURN(PTR_ERR(env));
 
-       io = ll_fault_io_init(env, vma, vmpage->index, NULL);
+       io = ll_fault_io_init(env, vma, vmpage->index);
        if (IS_ERR(io))
                GOTO(out, result = PTR_ERR(io));
 
@@ -268,7 +263,6 @@ static vm_fault_t ll_fault0(struct vm_area_struct *vma, struct vm_fault *vmf)
        struct cl_io            *io;
        struct vvp_io           *vio = NULL;
        struct page             *vmpage;
-       unsigned long            ra_flags;
        int                      result = 0;
        int                      fault_ret = 0;
        __u16                    refcheck;
@@ -280,23 +274,29 @@ static vm_fault_t ll_fault0(struct vm_area_struct *vma, struct vm_fault *vmf)
 
        if (ll_sbi_has_fast_read(ll_i2sbi(file_inode(vma->vm_file)))) {
                /* do fast fault */
+               bool has_retry = vmf->flags & FAULT_FLAG_RETRY_NOWAIT;
+
+               /* To avoid loops, instruct downstream to not drop mmap_sem */
+               vmf->flags |= FAULT_FLAG_RETRY_NOWAIT;
                ll_cl_add(vma->vm_file, env, NULL, LCC_MMAP);
                fault_ret = ll_filemap_fault(vma, vmf);
                ll_cl_remove(vma->vm_file, env);
+               if (!has_retry)
+                       vmf->flags &= ~FAULT_FLAG_RETRY_NOWAIT;
 
                /* - If there is no error, then the page was found in cache and
                 *   uptodate;
                 * - If VM_FAULT_RETRY is set, the page existed but failed to
-                *   lock. It will return to kernel and retry;
+                *   lock. We will try slow path to avoid loops.
                 * - Otherwise, it should try normal fault under DLM lock. */
-               if ((fault_ret & VM_FAULT_RETRY) ||
+               if (!(fault_ret & VM_FAULT_RETRY) &&
                    !(fault_ret & VM_FAULT_ERROR))
                        GOTO(out, result = 0);
 
                fault_ret = 0;
        }
 
-       io = ll_fault_io_init(env, vma, vmf->pgoff, &ra_flags);
+       io = ll_fault_io_init(env, vma, vmf->pgoff);
        if (IS_ERR(io))
                GOTO(out, result = PTR_ERR(io));
 
@@ -329,8 +329,6 @@ static vm_fault_t ll_fault0(struct vm_area_struct *vma, struct vm_fault *vmf)
         }
        cl_io_fini(env, io);
 
-       vma->vm_flags |= ra_flags;
-
 out:
        cl_env_put(env, &refcheck);
        if (result != 0 && !(fault_ret & VM_FAULT_RETRY))
@@ -359,6 +357,10 @@ static vm_fault_t ll_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
        if (cached)
                goto out;
 
+       CDEBUG(D_MMAP, DFID": vma=%p start=%#lx end=%#lx vm_flags=%#lx\n",
+              PFID(&ll_i2info(file_inode(vma->vm_file))->lli_fid),
+              vma, vma->vm_start, vma->vm_end, vma->vm_flags);
+
        /* Only SIGKILL and SIGTERM is allowed for fault/nopage/mkwrite
         * so that it can be killed by admin but not cause segfault by
         * other signals.
@@ -369,6 +371,7 @@ static vm_fault_t ll_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
        /* make sure offset is not a negative number */
        if (vmf->pgoff > (MAX_LFS_FILESIZE >> PAGE_SHIFT))
                return VM_FAULT_SIGBUS;
+
 restart:
        result = ll_fault0(vma, vmf);
        if (vmf->page &&
@@ -541,6 +544,10 @@ int ll_file_mmap(struct file *file, struct vm_area_struct * vma)
        int rc;
 
        ENTRY;
+       CDEBUG(D_VFSTRACE | D_MMAP,
+              "VFS_Op: fid="DFID" vma=%p start=%#lx end=%#lx vm_flags=%#lx\n",
+              PFID(&ll_i2info(inode)->lli_fid),
+              vma, vma->vm_start, vma->vm_end, vma->vm_flags);
 
        if (ll_file_nolock(file))
                RETURN(-EOPNOTSUPP);