/* * JFFS2 -- Journalling Flash File System, Version 2. * * Copyright © 2001-2007 Red Hat, Inc. * * Created by David Woodhouse * * For licensing information, see the file 'LICENCE' in this directory. * */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include #include #include #include #include #include #include #include "nodelist.h" static void jffs2_obsolete_node_frag(struct jffs2_sb_info *c, struct jffs2_node_frag *this); void jffs2_add_fd_to_list(struct jffs2_sb_info *c, struct jffs2_full_dirent *new, struct jffs2_full_dirent **list) { struct jffs2_full_dirent **prev = list; dbg_dentlist("add dirent \"%s\", ino #%u\n", new->name, new->ino); while ((*prev) && (*prev)->nhash <= new->nhash) { if ((*prev)->nhash == new->nhash && !strcmp((*prev)->name, new->name)) { /* Duplicate. Free one */ if (new->version < (*prev)->version) { dbg_dentlist("Eep! Marking new dirent node obsolete, old is \"%s\", ino #%u\n", (*prev)->name, (*prev)->ino); jffs2_mark_node_obsolete(c, new->raw); jffs2_free_full_dirent(new); } else { dbg_dentlist("marking old dirent \"%s\", ino #%u obsolete\n", (*prev)->name, (*prev)->ino); new->next = (*prev)->next; /* It may have been a 'placeholder' deletion dirent, if jffs2_can_mark_obsolete() (see jffs2_do_unlink()) */ if ((*prev)->raw) jffs2_mark_node_obsolete(c, ((*prev)->raw)); jffs2_free_full_dirent(*prev); *prev = new; } return; } prev = &((*prev)->next); } new->next = *prev; *prev = new; } uint32_t jffs2_truncate_fragtree(struct jffs2_sb_info *c, struct rb_root *list, uint32_t size) { struct jffs2_node_frag *frag = jffs2_lookup_node_frag(list, size); dbg_fragtree("truncating fragtree to 0x%08x bytes\n", size); /* We know frag->ofs <= size. That's what lookup does for us */ if (frag && frag->ofs != size) { if (frag->ofs+frag->size > size) { frag->size = size - frag->ofs; } frag = frag_next(frag); } while (frag && frag->ofs >= size) { struct jffs2_node_frag *next = frag_next(frag); frag_erase(frag, list); jffs2_obsolete_node_frag(c, frag); frag = next; } if (size == 0) return 0; frag = frag_last(list); /* Sanity check for truncation to longer than we started with... */ if (!frag) return 0; if (frag->ofs + frag->size < size) return frag->ofs + frag->size; /* If the last fragment starts at the RAM page boundary, it is * REF_PRISTINE irrespective of its size. */ if (frag->node && (frag->ofs & (PAGE_CACHE_SIZE - 1)) == 0) { dbg_fragtree2("marking the last fragment 0x%08x-0x%08x REF_PRISTINE.\n", frag->ofs, frag->ofs + frag->size); frag->node->raw->flash_offset = ref_offset(frag->node->raw) | REF_PRISTINE; } return size; } static void jffs2_obsolete_node_frag(struct jffs2_sb_info *c, struct jffs2_node_frag *this) { if (this->node) { this->node->frags--; if (!this->node->frags) { /* The node has no valid frags left. It's totally obsoleted */ dbg_fragtree2("marking old node @0x%08x (0x%04x-0x%04x) obsolete\n", ref_offset(this->node->raw), this->node->ofs, this->node->ofs+this->node->size); jffs2_mark_node_obsolete(c, this->node->raw); jffs2_free_full_dnode(this->node); } else { dbg_fragtree2("marking old node @0x%08x (0x%04x-0x%04x) REF_NORMAL. frags is %d\n", ref_offset(this->node->raw), this->node->ofs, this->node->ofs+this->node->size, this->node->frags); mark_ref_normal(this->node->raw); } } jffs2_free_node_frag(this); } static void jffs2_fragtree_insert(struct jffs2_node_frag *newfrag, struct jffs2_node_frag *base) { struct rb_node *parent = &base->rb; struct rb_node **link = &parent; dbg_fragtree2("insert frag (0x%04x-0x%04x)\n", newfrag->ofs, newfrag->ofs + newfrag->size); while (*link) { parent = *link; base = rb_entry(parent, struct jffs2_node_frag, rb); if (newfrag->ofs > base->ofs) link = &base->rb.rb_right; else if (newfrag->ofs < base->ofs) link = &base->rb.rb_left; else { JFFS2_ERROR("duplicate frag at %08x (%p,%p)\n", newfrag->ofs, newfrag, base); BUG(); } } rb_link_node(&newfrag->rb, &base->rb, link); } /* * Allocate and initializes a new fragment. */ static struct jffs2_node_frag * new_fragment(struct jffs2_full_dnode *fn, uint32_t ofs, uint32_t size) { struct jffs2_node_frag *newfrag; newfrag = jffs2_alloc_node_frag(); if (likely(newfrag)) { newfrag->ofs = ofs; newfrag->size = size; newfrag->node = fn; } else { JFFS2_ERROR("cannot allocate a jffs2_node_frag object\n"); } return newfrag; } /* * Called when there is no overlapping fragment exist. Inserts a hole before the new * fragment and inserts the new fragment to the fragtree. */ static int no_overlapping_node(struct jffs2_sb_info *c, struct rb_root *root, struct jffs2_node_frag *newfrag, struct jffs2_node_frag *this, uint32_t lastend) { if (lastend < newfrag->node->ofs) { /* put a hole in before the new fragment */ struct jffs2_node_frag *holefrag; holefrag= new_fragment(NULL, lastend, newfrag->node->ofs - lastend); if (unlikely(!holefrag)) { jffs2_free_node_frag(newfrag); return -ENOMEM; } if (this) { /* By definition, the 'this' node has no right-hand child, because there are no frags with offset greater than it. So that's where we want to put the hole */ dbg_fragtree2("add hole frag %#04x-%#04x on the right of the new frag.\n", holefrag->ofs, holefrag->ofs + holefrag->size); rb_link_node(&holefrag->rb, &this->rb, &this->rb.rb_right); } else { dbg_fragtree2("Add hole frag %#04x-%#04x to the root of the tree.\n", holefrag->ofs, holefrag->ofs + holefrag->size); rb_link_node(&holefrag->rb, NULL, &root->rb_node); } rb_insert_color(&holefrag->rb, root); this = holefrag; } if (this) { /* By definition, the 'this' node has no right-hand child, because there are no frags with offset greater than it. So that's where we want to put new fragment */ dbg_fragtree2("add the new node at the right\n"); rb_link_node(&newfrag->rb, &this->rb, &this->rb.rb_right); } else { dbg_fragtree2("insert the new node at the root of the tree\n"); rb_link_node(&newfrag->rb, NULL, &root->rb_node); } rb_insert_color(&newfrag->rb, root); return 0; } /* Doesn't set inode->i_size */ static int jffs2_add_frag_to_fragtree(struct jffs2_sb_info *c, struct rb_root *root, struct jffs2_node_frag *newfrag) { struct jffs2_node_frag *this; uint32_t lastend; /* Skip all the nodes which are completed before this one starts */ this = jffs2_lookup_node_frag(root, newfrag->node->ofs); if (this) { dbg_fragtree2("lookup gave frag 0x%04x-0x%04x; phys 0x%08x (*%p)\n", this->ofs, this->ofs+this->size, this->node?(ref_offset(this->node->raw)):0xffffffff, this); lastend = this->ofs + this->size; } else { dbg_fragtree2("lookup gave no frag\n"); lastend = 0; } /* See if we ran off the end of the fragtree */ if (lastend <= newfrag->ofs) { /* We did */ /* Check if 'this' node was on the same page as the new node. If so, both 'this' and the new node get marked REF_NORMAL so the GC can take a look. */ if (lastend && (lastend-1) >> PAGE_CACHE_SHIFT == newfrag->ofs >> PAGE_CACHE_SHIFT) { if (this->node) mark_ref_normal(this->node->raw); mark_ref_normal(newfrag->node->raw); } return no_overlapping_node(c, root, newfrag, this, lastend); } if (this->node) dbg_fragtree2("dealing with frag %u-%u, phys %#08x(%d).\n", this->ofs, this->ofs + this->size, ref_offset(this->node->raw), ref_flags(this->node->raw)); else dbg_fragtree2("dealing with hole frag %u-%u.\n", this->ofs, this->ofs + this->size); /* OK. 'this' is pointing at the first frag that newfrag->ofs at least partially obsoletes, * - i.e. newfrag->ofs < this->ofs+this->size && newfrag->ofs >= this->ofs */ if (newfrag->ofs > this->ofs) { /* This node isn't completely obsoleted. The start of it remains valid */ /* Mark the new node and the partially covered node REF_NORMAL -- let the GC take a look at them */ mark_ref_normal(newfrag->node->raw); if (this->node) mark_ref_normal(this->node->raw); if (this->ofs + this->size > newfrag->ofs + newfrag->size) { /* The new node splits 'this' frag into two */ struct jffs2_node_frag *newfrag2; if (this->node) dbg_fragtree2("split old frag 0x%04x-0x%04x, phys 0x%08x\n", this->ofs, this->ofs+this->size, ref_offset(this->node->raw)); else dbg_fragtree2("split old hole frag 0x%04x-0x%04x\n", this->ofs, this->ofs+this->size); /* New second frag pointing to this's node */ newfrag2 = new_fragment(this->node, newfrag->ofs + newfrag->size, this->ofs + this->size - newfrag->ofs - newfrag->size); if (unlikely(!newfrag2)) return -ENOMEM; if (this->node) this->node->frags++; /* Adjust size of original 'this' */ this->size = newfrag->ofs - this->ofs; /* Now, we know there's no node with offset greater than this->ofs but smaller than newfrag2->ofs or newfrag->ofs, for obvious reasons. So we can do a tree insert from 'this' to insert newfrag, and a tree insert from newfrag to insert newfrag2. */ jffs2_fragtree_insert(newfrag, this); rb_insert_color(&newfrag->rb, root); jffs2_fragtree_insert(newfrag2, newfrag); rb_insert_color(&newfrag2->rb, root); return 0; } /* New node just reduces 'this' frag in size, doesn't split it */ this->size = newfrag->ofs - this->ofs; /* Again, we know it lives down here in the tree */ jffs2_fragtree_insert(newfrag, this); rb_insert_color(&newfrag->rb, root); } else { /* New frag starts at the same point as 'this' used to. Replace it in the tree without doing a delete and insertion */ dbg_fragtree2("inserting newfrag (*%p),%d-%d in before 'this' (*%p),%d-%d\n", newfrag, newfrag->ofs, newfrag->ofs+newfrag->size, this, this->ofs, this->ofs+this->size); rb_replace_node(&this->rb, &newfrag->rb, root); if (newfrag->ofs + newfrag->size >= this->ofs+this->size) { dbg_fragtree2("obsoleting node frag %p (%x-%x)\n", this, this->ofs, this->ofs+this->size); jffs2_obsolete_node_frag(c, this); } else { this->ofs += newfrag->size; this->size -= newfrag->size; jffs2_fragtree_insert(this, newfrag); rb_insert_color(&this->rb, root); return 0; } } /* OK, now we have newfrag added in the correct place in the tree, but frag_next(newfrag) may be a fragment which is overlapped by it */ while ((this = frag_next(newfrag)) && newfrag->ofs + newfrag->size >= this->ofs + this->size) { /* 'this' frag is obsoleted completely. */ dbg_fragtree2("obsoleting node frag %p (%x-%x) and removing from tree\n", this, this->ofs, this->ofs+this->size); rb_erase(&this->rb, root); jffs2_obsolete_node_frag(c, this); } /* Now we're pointing at the first frag which isn't totally obsoleted by the new frag */ if (!this || newfrag->ofs + newfrag->size == this->ofs) return 0; /* Still some overlap but we don't need to move it in the tree */ this->size = (this->ofs + this->size) - (newfrag->ofs + newfrag->size); this->ofs = newfrag->ofs + newfrag->size; /* And mark them REF_NORMAL so the GC takes a look at them */ if (this->node) mark_ref_normal(this->node->raw); mark_ref_normal(newfrag->node->raw); return 0; } /* * Given an inode, probably with existing tree of fragments, add the new node * to the fragment tree. */ int jffs2_add_full_dnode_to_inode(struct jffs2_sb_info *c, struct jffs2_inode_info *f, struct jffs2_full_dnode *fn) { int ret; struct jffs2_node_frag *newfrag; if (unlikely(!fn->size)) return 0; newfrag = new_fragment(fn, fn->ofs, fn->size); if (unlikely(!newfrag)) return -ENOMEM; newfrag->node->frags = 1; dbg_fragtree("adding node %#04x-%#04x @0x%08x on flash, newfrag *%p\n", fn->ofs, fn->ofs+fn->size, ref_offset(fn->raw), newfrag); ret = jffs2_add_frag_to_fragtree(c, &f->fragtree, newfrag); if (unlikely(ret)) return ret; /* If we now share a page with other nodes, mark either previous or next node REF_NORMAL, as appropriate. */ if (newfrag->ofs & (PAGE_CACHE_SIZE-1)) { struct jffs2_node_frag *prev = frag_prev(newfrag); mark_ref_normal(fn->raw); /* If we don't start at zero there's _always_ a previous */ if (prev->node) mark_ref_normal(prev->node->raw); } if ((newfrag->ofs+newfrag->size) & (PAGE_CACHE_SIZE-1)) { struct jffs2_node_frag *next = frag_next(newfrag); if (next) { mark_ref_normal(fn->raw); if (next->node) mark_ref_normal(next->node->raw); } } jffs2_dbg_fragtree_paranoia_check_nolock(f); return 0; } void jffs2_set_inocache_state(struct jffs2_sb_info *c, struct jffs2_inode_cache *ic, int state) { spin_lock(&c->inocache_lock); ic->state = state; wake_up(&c->inocache_wq); spin_unlock(&c->inocache_lock); } /* During mount, this needs no locking. During normal operation, its callers want to do other stuff while still holding the inocache_lock. Rather than introducing special case get_ino_cache functions or callbacks, we just let the caller do the locking itself. */ struct jffs2_inode_cache *jffs2_get_ino_cache(struct jffs2_sb_info *c, uint32_t ino) { struct jffs2_inode_cache *ret; ret = c->inocache_list[ino % c->inocache_hashsize]; while (ret && ret->ino < ino) { ret = ret->next; } if (ret && ret->ino != ino) ret = NULL; return ret; } void jffs2_add_ino_cache (struct jffs2_sb_info *c, struct jffs2_inode_cache *new) { struct jffs2_inode_cache **prev; spin_lock(&c->inocache_lock); if (!new->ino) new->ino = ++c->highest_ino; dbg_inocache("add %p (ino #%u)\n", new, new->ino); prev = &c->inocache_list[new->ino % c->inocache_hashsize]; while ((*prev) && (*prev)->ino < new->ino) { prev = &(*prev)->next; } new->next = *prev; *prev = new; spin_unlock(&c->inocache_lock); } void jffs2_del_ino_cache(struct jffs2_sb_info *c, struct jffs2_inode_cache *old) { struct jffs2_inode_cache **prev; #ifdef CONFIG_JFFS2_FS_XATTR BUG_ON(old->xref); #endif dbg_inocache("del %p (ino #%u)\n", old, old->ino); spin_lock(&c->inocache_lock); prev = &c->inocache_list[old->ino % c->inocache_hashsize]; while ((*prev) && (*prev)->ino < old->ino) { prev = &(*prev)->next; } if ((*prev) == old) { *prev = old->next; } /* Free it now unless it's in READING or CLEARING state, which are the transitions upon read_inode() and clear_inode(). The rest of the time we know nobody else is looking at it, and if it's held by read_inode() or clear_inode() they'll free it for themselves. */ if (old->state != INO_STATE_READING && old->state != INO_STATE_CLEARING) jffs2_free_inode_cache(old); spin_unlock(&c->inocache_lock); } void jffs2_free_ino_caches(struct jffs2_sb_info *c) { int i; struct jffs2_inode_cache *this, *next; for (i=0; i < c->inocache_hashsize; i++) { this = c->inocache_list[i]; while (this) { next = this->next; jffs2_xattr_free_inode(c, this); jffs2_free_inode_cache(this); this = next; } c->inocache_list[i] = NULL; } } void jffs2_free_raw_node_refs(struct jffs2_sb_info *c) { int i; struct jffs2_raw_node_ref *this, *next; for (i=0; inr_blocks; i++) { this = c->blocks[i].first_node; while (this) { if (this[REFS_PER_BLOCK].flash_offset == REF_LINK_NODE) next = this[REFS_PER_BLOCK].next_in_ino; else next = NULL; jffs2_free_refblock(this); this = next; } c->blocks[i].first_node = c->blocks[i].last_node = NULL; } } struct jffs2_node_frag *jffs2_lookup_node_frag(struct rb_root *fragtree, uint32_t offset) { /* The common case in lookup is that there will be a node which precisely matches. So we go looking for that first */ struct rb_node *next; struct jffs2_node_frag *prev = NULL; struct jffs2_node_frag *frag = NULL; dbg_fragtree2("root %p, offset %d\n", fragtree, offset); next = fragtree->rb_node; while(next) { frag = rb_entry(next, struct jffs2_node_frag, rb); if (frag->ofs + frag->size <= offset) { /* Remember the closest smaller match on the way down */ if (!prev || frag->ofs > prev->ofs) prev = frag; next = frag->rb.rb_right; } else if (frag->ofs > offset) { next = frag->rb.rb_left; } else { return frag; } } /* Exact match not found. Go back up looking at each parent, and return the closest smaller one */ if (prev) dbg_fragtree2("no match. Returning frag %#04x-%#04x, closest previous\n", prev->ofs, prev->ofs+prev->size); else dbg_fragtree2("returning NULL, empty fragtree\n"); return prev; } /* Pass 'c' argument to indicate that nodes should be marked obsolete as they're killed. */ void jffs2_kill_fragtree(struct rb_root *root, struct jffs2_sb_info *c) { struct jffs2_node_frag *frag; struct jffs2_node_frag *parent; if (!root->rb_node) return; dbg_fragtree("killing\n"); frag = (rb_entry(root->rb_node, struct jffs2_node_frag, rb)); while(frag) { if (frag->rb.rb_left) { frag = frag_left(frag); continue; } if (frag->rb.rb_right) { frag = frag_right(frag); continue; } if (frag->node && !(--frag->node->frags)) { /* Not a hole, and it's the final remaining frag of this node. Free the node */ if (c) jffs2_mark_node_obsolete(c, frag->node->raw); jffs2_free_full_dnode(frag->node); } parent = frag_parent(frag); if (parent) { if (frag_left(parent) == frag) parent->rb.rb_left = NULL; else parent->rb.rb_right = NULL; } jffs2_free_node_frag(frag); frag = parent; cond_resched(); } } struct jffs2_raw_node_ref *jffs2_link_node_ref(struct jffs2_sb_info *c, struct jffs2_eraseblock *jeb, uint32_t ofs, uint32_t len, struct jffs2_inode_cache *ic) { struct jffs2_raw_node_ref *ref; BUG_ON(!jeb->allocated_refs); jeb->allocated_refs--; ref = jeb->last_node; dbg_noderef("Last node at %p is (%08x,%p)\n", ref, ref->flash_offset, ref->next_in_ino); while (ref->flash_offset != REF_EMPTY_NODE) { if (ref->flash_offset == REF_LINK_NODE) ref = ref->next_in_ino; else ref++; } dbg_noderef("New ref is %p (%08x becomes %08x,%p) len 0x%x\n", ref, ref->flash_offset, ofs, ref->next_in_ino, len); ref->flash_offset = ofs; if (!jeb->first_node) { jeb->first_node = ref; BUG_ON(ref_offset(ref) != jeb->offset); } else if (unlikely(ref_offset(ref) != jeb->offset + c->sector_size - jeb->free_size)) { uint32_t last_len = ref_totlen(c, jeb, jeb->last_node); JFFS2_ERROR("Adding new ref %p at (0x%08x-0x%08x) not immediately after previous (0x%08x-0x%08x)\n", ref, ref_offset(ref), ref_offset(ref)+len, ref_offset(jeb->last_node), ref_offset(jeb->last_node)+last_len); BUG(); } jeb->last_node = ref; if (ic) { ref->next_in_ino = ic->nodes; ic->nodes = ref; } else { ref->next_in_ino = NULL; } switch(ref_flags(ref)) { case REF_UNCHECKED: c->unchecked_size += len; jeb->unchecked_size += len; break; case REF_NORMAL: case REF_PRISTINE: c->used_size += len; jeb->used_size += len; break; case REF_OBSOLETE: c->dirty_size += len; jeb->dirty_size += len; break; } c->free_size -= len; jeb->free_size -= len; #ifdef TEST_TOTLEN /* Set (and test) __totlen field... for now */ ref->__totlen = len; ref_totlen(c, jeb, ref); #endif return ref; } /* No locking, no reservation of 'ref'. Do not use on a live file system */ int jffs2_scan_dirty_space(struct jffs2_sb_info *c, struct jffs2_eraseblock *jeb, uint32_t size) { if (!size) return 0; if (unlikely(size > jeb->free_size)) { pr_crit("Dirty space 0x%x larger then free_size 0x%x (wasted 0x%x)\n", size, jeb->free_size, jeb->wasted_size); BUG(); } /* REF_EMPTY_NODE is !obsolete, so that works OK */ if (jeb->last_node && ref_obsolete(jeb->last_node)) { #ifdef TEST_TOTLEN jeb->last_node->__totlen += size; #endif c->dirty_size += size; c->free_size -= size; jeb->dirty_size += size; jeb->free_size -= size; } else { uint32_t ofs = jeb->offset + c->sector_size - jeb->free_size; ofs |= REF_OBSOLETE; jffs2_link_node_ref(c, jeb, ofs, size, NULL); } return 0; } /* Calculate totlen from surrounding nodes or eraseblock */ static inline uint32_t __ref_totlen(struct jffs2_sb_info *c, struct jffs2_eraseblock *jeb, struct jffs2_raw_node_ref *ref) { uint32_t ref_end; struct jffs2_raw_node_ref *next_ref = ref_next(ref); if (next_ref) ref_end = ref_offset(next_ref); else { if (!jeb) jeb = &c->blocks[ref->flash_offset / c->sector_size]; /* Last node in block. Use free_space */ if (unlikely(ref != jeb->last_node)) { pr_crit("ref %p @0x%08x is not jeb->last_node (%p @0x%08x)\n", ref, ref_offset(ref), jeb->last_node, jeb->last_node ? ref_offset(jeb->last_node) : 0); BUG(); } ref_end = jeb->offset + c->sector_size - jeb->free_size; } return ref_end - ref_offset(ref); } uint32_t __jffs2_ref_totlen(struct jffs2_sb_info *c, struct jffs2_eraseblock *jeb, struct jffs2_raw_node_ref *ref) { uint32_t ret; ret = __ref_totlen(c, jeb, ref); #ifdef TEST_TOTLEN if (unlikely(ret != ref->__totlen)) { if (!jeb) jeb = &c->blocks[ref->flash_offset / c->sector_size]; pr_crit("Totlen for ref at %p (0x%08x-0x%08x) miscalculated as 0x%x instead of %x\n", ref, ref_offset(ref), ref_offset(ref) + ref->__totlen, ret, ref->__totlen); if (ref_next(ref)) { pr_crit("next %p (0x%08x-0x%08x)\n", ref_next(ref), ref_offset(ref_next(ref)), ref_offset(ref_next(ref)) + ref->__totlen); } else pr_crit("No next ref. jeb->last_node is %p\n", jeb->last_node); pr_crit("jeb->wasted_size %x, dirty_size %x, used_size %x, free_size %x\n", jeb->wasted_size, jeb->dirty_size, jeb->used_size, jeb->free_size); #if defined(JFFS2_DBG_DUMPS) || defined(JFFS2_DBG_PARANOIA_CHECKS) __jffs2_dbg_dump_node_refs_nolock(c, jeb); #endif WARN_ON(1); ret = ref->__totlen; } #endif /* TEST_TOTLEN */ return ret; } #n548'>548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 
/*
 * Copyright (C) 2008, 2009 Intel Corporation
 * Authors: Andi Kleen, Fengguang Wu
 *
 * This software may be redistributed and/or modified under the terms of
 * the GNU General Public License ("GPL") version 2 only as published by the
 * Free Software Foundation.
 *
 * High level machine check handler. Handles pages reported by the
 * hardware as being corrupted usually due to a multi-bit ECC memory or cache
 * failure.
 * 
 * In addition there is a "soft offline" entry point that allows stop using
 * not-yet-corrupted-by-suspicious pages without killing anything.
 *
 * Handles page cache pages in various states.	The tricky part
 * here is that we can access any page asynchronously in respect to 
 * other VM users, because memory failures could happen anytime and 
 * anywhere. This could violate some of their assumptions. This is why 
 * this code has to be extremely careful. Generally it tries to use 
 * normal locking rules, as in get the standard locks, even if that means 
 * the error handling takes potentially a long time.
 *
 * It can be very tempting to add handling for obscure cases here.
 * In general any code for handling new cases should only be added iff:
 * - You know how to test it.
 * - You have a test that can be added to mce-test
 *   https://git.kernel.org/cgit/utils/cpu/mce/mce-test.git/
 * - The case actually shows up as a frequent (top 10) page state in
 *   tools/vm/page-types when running a real workload.
 * 
 * There are several operations here with exponential complexity because
 * of unsuitable VM data structures. For example the operation to map back 
 * from RMAP chains to processes has to walk the complete process list and 
 * has non linear complexity with the number. But since memory corruptions
 * are rare we hope to get away with this. This avoids impacting the core 
 * VM.
 */
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/page-flags.h>
#include <linux/kernel-page-flags.h>
#include <linux/sched.h>
#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/export.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/backing-dev.h>
#include <linux/migrate.h>
#include <linux/page-isolation.h>
#include <linux/suspend.h>
#include <linux/slab.h>
#include <linux/swapops.h>
#include <linux/hugetlb.h>
#include <linux/memory_hotplug.h>
#include <linux/mm_inline.h>
#include <linux/kfifo.h>
#include <linux/ratelimit.h>
#include "internal.h"
#include "ras/ras_event.h"

int sysctl_memory_failure_early_kill __read_mostly = 0;

int sysctl_memory_failure_recovery __read_mostly = 1;

atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);

#if defined(CONFIG_HWPOISON_INJECT) || defined(CONFIG_HWPOISON_INJECT_MODULE)

u32 hwpoison_filter_enable = 0;
u32 hwpoison_filter_dev_major = ~0U;
u32 hwpoison_filter_dev_minor = ~0U;
u64 hwpoison_filter_flags_mask;
u64 hwpoison_filter_flags_value;
EXPORT_SYMBOL_GPL(hwpoison_filter_enable);
EXPORT_SYMBOL_GPL(hwpoison_filter_dev_major);
EXPORT_SYMBOL_GPL(hwpoison_filter_dev_minor);
EXPORT_SYMBOL_GPL(hwpoison_filter_flags_mask);
EXPORT_SYMBOL_GPL(hwpoison_filter_flags_value);

static int hwpoison_filter_dev(struct page *p)
{
	struct address_space *mapping;
	dev_t dev;

	if (hwpoison_filter_dev_major == ~0U &&
	    hwpoison_filter_dev_minor == ~0U)
		return 0;

	/*
	 * page_mapping() does not accept slab pages.
	 */
	if (PageSlab(p))
		return -EINVAL;

	mapping = page_mapping(p);
	if (mapping == NULL || mapping->host == NULL)
		return -EINVAL;

	dev = mapping->host->i_sb->s_dev;
	if (hwpoison_filter_dev_major != ~0U &&
	    hwpoison_filter_dev_major != MAJOR(dev))
		return -EINVAL;
	if (hwpoison_filter_dev_minor != ~0U &&
	    hwpoison_filter_dev_minor != MINOR(dev))
		return -EINVAL;

	return 0;
}

static int hwpoison_filter_flags(struct page *p)
{
	if (!hwpoison_filter_flags_mask)
		return 0;

	if ((stable_page_flags(p) & hwpoison_filter_flags_mask) ==
				    hwpoison_filter_flags_value)
		return 0;
	else
		return -EINVAL;
}

/*
 * This allows stress tests to limit test scope to a collection of tasks
 * by putting them under some memcg. This prevents killing unrelated/important
 * processes such as /sbin/init. Note that the target task may share clean
 * pages with init (eg. libc text), which is harmless. If the target task
 * share _dirty_ pages with another task B, the test scheme must make sure B
 * is also included in the memcg. At last, due to race conditions this filter
 * can only guarantee that the page either belongs to the memcg tasks, or is
 * a freed page.
 */
#ifdef CONFIG_MEMCG
u64 hwpoison_filter_memcg;
EXPORT_SYMBOL_GPL(hwpoison_filter_memcg);
static int hwpoison_filter_task(struct page *p)
{
	if (!hwpoison_filter_memcg)
		return 0;

	if (page_cgroup_ino(p) != hwpoison_filter_memcg)
		return -EINVAL;

	return 0;
}
#else
static int hwpoison_filter_task(struct page *p) { return 0; }
#endif

int hwpoison_filter(struct page *p)
{
	if (!hwpoison_filter_enable)
		return 0;

	if (hwpoison_filter_dev(p))
		return -EINVAL;

	if (hwpoison_filter_flags(p))
		return -EINVAL;

	if (hwpoison_filter_task(p))
		return -EINVAL;

	return 0;
}
#else
int hwpoison_filter(struct page *p)
{
	return 0;
}
#endif

EXPORT_SYMBOL_GPL(hwpoison_filter);

/*
 * Send all the processes who have the page mapped a signal.
 * ``action optional'' if they are not immediately affected by the error
 * ``action required'' if error happened in current execution context
 */
static int kill_proc(struct task_struct *t, unsigned long addr, int trapno,
			unsigned long pfn, struct page *page, int flags)
{
	struct siginfo si;
	int ret;

	pr_err("Memory failure: %#lx: Killing %s:%d due to hardware memory corruption\n",
		pfn, t->comm, t->pid);
	si.si_signo = SIGBUS;
	si.si_errno = 0;
	si.si_addr = (void *)addr;
#ifdef __ARCH_SI_TRAPNO
	si.si_trapno = trapno;
#endif
	si.si_addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT;

	if ((flags & MF_ACTION_REQUIRED) && t->mm == current->mm) {
		si.si_code = BUS_MCEERR_AR;
		ret = force_sig_info(SIGBUS, &si, current);
	} else {
		/*
		 * Don't use force here, it's convenient if the signal
		 * can be temporarily blocked.
		 * This could cause a loop when the user sets SIGBUS
		 * to SIG_IGN, but hopefully no one will do that?
		 */
		si.si_code = BUS_MCEERR_AO;
		ret = send_sig_info(SIGBUS, &si, t);  /* synchronous? */
	}
	if (ret < 0)
		pr_info("Memory failure: Error sending signal to %s:%d: %d\n",
			t->comm, t->pid, ret);
	return ret;
}

/*
 * When a unknown page type is encountered drain as many buffers as possible
 * in the hope to turn the page into a LRU or free page, which we can handle.
 */
void shake_page(struct page *p, int access)
{
	if (!PageSlab(p)) {
		lru_add_drain_all();
		if (PageLRU(p))
			return;
		drain_all_pages(page_zone(p));
		if (PageLRU(p) || is_free_buddy_page(p))
			return;
	}

	/*
	 * Only call shrink_node_slabs here (which would also shrink
	 * other caches) if access is not potentially fatal.
	 */
	if (access)
		drop_slab_node(page_to_nid(p));
}
EXPORT_SYMBOL_GPL(shake_page);

/*
 * Kill all processes that have a poisoned page mapped and then isolate
 * the page.
 *
 * General strategy:
 * Find all processes having the page mapped and kill them.
 * But we keep a page reference around so that the page is not
 * actually freed yet.
 * Then stash the page away
 *
 * There's no convenient way to get back to mapped processes
 * from the VMAs. So do a brute-force search over all
 * running processes.
 *
 * Remember that machine checks are not common (or rather
 * if they are common you have other problems), so this shouldn't
 * be a performance issue.
 *
 * Also there are some races possible while we get from the
 * error detection to actually handle it.
 */

struct to_kill {
	struct list_head nd;
	struct task_struct *tsk;
	unsigned long addr;
	char addr_valid;
};

/*
 * Failure handling: if we can't find or can't kill a process there's
 * not much we can do.	We just print a message and ignore otherwise.
 */

/*
 * Schedule a process for later kill.
 * Uses GFP_ATOMIC allocations to avoid potential recursions in the VM.
 * TBD would GFP_NOIO be enough?
 */
static void add_to_kill(struct task_struct *tsk, struct page *p,
		       struct vm_area_struct *vma,
		       struct list_head *to_kill,
		       struct to_kill **tkc)
{
	struct to_kill *tk;

	if (*tkc) {
		tk = *tkc;
		*tkc = NULL;
	} else {
		tk = kmalloc(sizeof(struct to_kill), GFP_ATOMIC);
		if (!tk) {
			pr_err("Memory failure: Out of memory while machine check handling\n");
			return;
		}
	}
	tk->addr = page_address_in_vma(p, vma);
	tk->addr_valid = 1;

	/*
	 * In theory we don't have to kill when the page was
	 * munmaped. But it could be also a mremap. Since that's
	 * likely very rare kill anyways just out of paranoia, but use
	 * a SIGKILL because the error is not contained anymore.
	 */
	if (tk->addr == -EFAULT) {
		pr_info("Memory failure: Unable to find user space address %lx in %s\n",
			page_to_pfn(p), tsk->comm);
		tk->addr_valid = 0;
	}
	get_task_struct(tsk);
	tk->tsk = tsk;
	list_add_tail(&tk->nd, to_kill);
}

/*
 * Kill the processes that have been collected earlier.
 *
 * Only do anything when DOIT is set, otherwise just free the list
 * (this is used for clean pages which do not need killing)
 * Also when FAIL is set do a force kill because something went
 * wrong earlier.
 */
static void kill_procs(struct list_head *to_kill, int forcekill, int trapno,
			  int fail, struct page *page, unsigned long pfn,
			  int flags)
{
	struct to_kill *tk, *next;

	list_for_each_entry_safe (tk, next, to_kill, nd) {
		if (forcekill) {
			/*
			 * In case something went wrong with munmapping
			 * make sure the process doesn't catch the
			 * signal and then access the memory. Just kill it.
			 */
			if (fail || tk->addr_valid == 0) {
				pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n",
				       pfn, tk->tsk->comm, tk->tsk->pid);
				force_sig(SIGKILL, tk->tsk);
			}

			/*
			 * In theory the process could have mapped
			 * something else on the address in-between. We could
			 * check for that, but we need to tell the
			 * process anyways.
			 */
			else if (kill_proc(tk->tsk, tk->addr, trapno,
					      pfn, page, flags) < 0)
				pr_err("Memory failure: %#lx: Cannot send advisory machine check signal to %s:%d\n",
				       pfn, tk->tsk->comm, tk->tsk->pid);
		}
		put_task_struct(tk->tsk);
		kfree(tk);
	}
}

/*
 * Find a dedicated thread which is supposed to handle SIGBUS(BUS_MCEERR_AO)
 * on behalf of the thread group. Return task_struct of the (first found)
 * dedicated thread if found, and return NULL otherwise.
 *
 * We already hold read_lock(&tasklist_lock) in the caller, so we don't
 * have to call rcu_read_lock/unlock() in this function.
 */
static struct task_struct *find_early_kill_thread(struct task_struct *tsk)
{
	struct task_struct *t;

	for_each_thread(tsk, t)
		if ((t->flags & PF_MCE_PROCESS) && (t->flags & PF_MCE_EARLY))
			return t;
	return NULL;
}

/*
 * Determine whether a given process is "early kill" process which expects
 * to be signaled when some page under the process is hwpoisoned.
 * Return task_struct of the dedicated thread (main thread unless explicitly
 * specified) if the process is "early kill," and otherwise returns NULL.
 */
static struct task_struct *task_early_kill(struct task_struct *tsk,
					   int force_early)
{
	struct task_struct *t;
	if (!tsk->mm)
		return NULL;
	if (force_early)
		return tsk;
	t = find_early_kill_thread(tsk);
	if (t)
		return t;
	if (sysctl_memory_failure_early_kill)
		return tsk;
	return NULL;
}

/*
 * Collect processes when the error hit an anonymous page.
 */
static void collect_procs_anon(struct page *page, struct list_head *to_kill,
			      struct to_kill **tkc, int force_early)
{
	struct vm_area_struct *vma;
	struct task_struct *tsk;
	struct anon_vma *av;
	pgoff_t pgoff;

	av = page_lock_anon_vma_read(page);
	if (av == NULL)	/* Not actually mapped anymore */
		return;

	pgoff = page_to_pgoff(page);
	read_lock(&tasklist_lock);
	for_each_process (tsk) {
		struct anon_vma_chain *vmac;
		struct task_struct *t = task_early_kill(tsk, force_early);

		if (!t)
			continue;
		anon_vma_interval_tree_foreach(vmac, &av->rb_root,
					       pgoff, pgoff) {
			vma = vmac->vma;
			if (!page_mapped_in_vma(page, vma))
				continue;
			if (vma->vm_mm == t->mm)
				add_to_kill(t, page, vma, to_kill, tkc);
		}
	}
	read_unlock(&tasklist_lock);
	page_unlock_anon_vma_read(av);
}

/*
 * Collect processes when the error hit a file mapped page.
 */
static void collect_procs_file(struct page *page, struct list_head *to_kill,
			      struct to_kill **tkc, int force_early)
{
	struct vm_area_struct *vma;
	struct task_struct *tsk;
	struct address_space *mapping = page->mapping;

	i_mmap_lock_read(mapping);
	read_lock(&tasklist_lock);
	for_each_process(tsk) {
		pgoff_t pgoff = page_to_pgoff(page);
		struct task_struct *t = task_early_kill(tsk, force_early);

		if (!t)
			continue;
		vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff,
				      pgoff) {
			/*
			 * Send early kill signal to tasks where a vma covers
			 * the page but the corrupted page is not necessarily
			 * mapped it in its pte.
			 * Assume applications who requested early kill want
			 * to be informed of all such data corruptions.
			 */
			if (vma->vm_mm == t->mm)
				add_to_kill(t, page, vma, to_kill, tkc);
		}
	}
	read_unlock(&tasklist_lock);
	i_mmap_unlock_read(mapping);
}

/*
 * Collect the processes who have the corrupted page mapped to kill.
 * This is done in two steps for locking reasons.
 * First preallocate one tokill structure outside the spin locks,
 * so that we can kill at least one process reasonably reliable.
 */
static void collect_procs(struct page *page, struct list_head *tokill,
				int force_early)
{
	struct to_kill *tk;

	if (!page->mapping)
		return;

	tk = kmalloc(sizeof(struct to_kill), GFP_NOIO);
	if (!tk)
		return;
	if (PageAnon(page))
		collect_procs_anon(page, tokill, &tk, force_early);
	else
		collect_procs_file(page, tokill, &tk, force_early);
	kfree(tk);
}

static const char *action_name[] = {
	[MF_IGNORED] = "Ignored",
	[MF_FAILED] = "Failed",
	[MF_DELAYED] = "Delayed",
	[MF_RECOVERED] = "Recovered",
};

static const char * const action_page_types[] = {
	[MF_MSG_KERNEL]			= "reserved kernel page",
	[MF_MSG_KERNEL_HIGH_ORDER]	= "high-order kernel page",
	[MF_MSG_SLAB]			= "kernel slab page",
	[MF_MSG_DIFFERENT_COMPOUND]	= "different compound page after locking",
	[MF_MSG_POISONED_HUGE]		= "huge page already hardware poisoned",
	[MF_MSG_HUGE]			= "huge page",
	[MF_MSG_FREE_HUGE]		= "free huge page",
	[MF_MSG_UNMAP_FAILED]		= "unmapping failed page",
	[MF_MSG_DIRTY_SWAPCACHE]	= "dirty swapcache page",
	[MF_MSG_CLEAN_SWAPCACHE]	= "clean swapcache page",
	[MF_MSG_DIRTY_MLOCKED_LRU]	= "dirty mlocked LRU page",
	[MF_MSG_CLEAN_MLOCKED_LRU]	= "clean mlocked LRU page",
	[MF_MSG_DIRTY_UNEVICTABLE_LRU]	= "dirty unevictable LRU page",
	[MF_MSG_CLEAN_UNEVICTABLE_LRU]	= "clean unevictable LRU page",
	[MF_MSG_DIRTY_LRU]		= "dirty LRU page",
	[MF_MSG_CLEAN_LRU]		= "clean LRU page",
	[MF_MSG_TRUNCATED_LRU]		= "already truncated LRU page",
	[MF_MSG_BUDDY]			= "free buddy page",
	[MF_MSG_BUDDY_2ND]		= "free buddy page (2nd try)",
	[MF_MSG_UNKNOWN]		= "unknown page",
};

/*
 * XXX: It is possible that a page is isolated from LRU cache,
 * and then kept in swap cache or failed to remove from page cache.
 * The page count will stop it from being freed by unpoison.
 * Stress tests should be aware of this memory leak problem.
 */
static int delete_from_lru_cache(struct page *p)
{
	if (!isolate_lru_page(p)) {
		/*
		 * Clear sensible page flags, so that the buddy system won't
		 * complain when the page is unpoison-and-freed.
		 */
		ClearPageActive(p);
		ClearPageUnevictable(p);
		/*
		 * drop the page count elevated by isolate_lru_page()
		 */
		put_page(p);
		return 0;
	}
	return -EIO;
}

/*
 * Error hit kernel page.
 * Do nothing, try to be lucky and not touch this instead. For a few cases we
 * could be more sophisticated.
 */
static int me_kernel(struct page *p, unsigned long pfn)
{
	return MF_IGNORED;
}

/*
 * Page in unknown state. Do nothing.
 */
static int me_unknown(struct page *p, unsigned long pfn)
{
	pr_err("Memory failure: %#lx: Unknown page state\n", pfn);
	return MF_FAILED;
}

/*
 * Clean (or cleaned) page cache page.
 */
static int me_pagecache_clean(struct page *p, unsigned long pfn)
{
	int err;
	int ret = MF_FAILED;
	struct address_space *mapping;

	delete_from_lru_cache(p);

	/*
	 * For anonymous pages we're done the only reference left
	 * should be the one m_f() holds.
	 */
	if (PageAnon(p))
		return MF_RECOVERED;

	/*
	 * Now truncate the page in the page cache. This is really
	 * more like a "temporary hole punch"
	 * Don't do this for block devices when someone else
	 * has a reference, because it could be file system metadata
	 * and that's not safe to truncate.
	 */
	mapping = page_mapping(p);
	if (!mapping) {
		/*
		 * Page has been teared down in the meanwhile
		 */
		return MF_FAILED;
	}

	/*
	 * Truncation is a bit tricky. Enable it per file system for now.
	 *
	 * Open: to take i_mutex or not for this? Right now we don't.
	 */
	if (mapping->a_ops->error_remove_page) {
		err = mapping->a_ops->error_remove_page(mapping, p);
		if (err != 0) {
			pr_info("Memory failure: %#lx: Failed to punch page: %d\n",
				pfn, err);
		} else if (page_has_private(p) &&
				!try_to_release_page(p, GFP_NOIO)) {
			pr_info("Memory failure: %#lx: failed to release buffers\n",
				pfn);
		} else {
			ret = MF_RECOVERED;
		}
	} else {
		/*
		 * If the file system doesn't support it just invalidate
		 * This fails on dirty or anything with private pages
		 */
		if (invalidate_inode_page(p))
			ret = MF_RECOVERED;
		else
			pr_info("Memory failure: %#lx: Failed to invalidate\n",
				pfn);
	}
	return ret;
}

/*
 * Dirty pagecache page
 * Issues: when the error hit a hole page the error is not properly
 * propagated.
 */
static int me_pagecache_dirty(struct page *p, unsigned long pfn)
{
	struct address_space *mapping = page_mapping(p);

	SetPageError(p);
	/* TBD: print more information about the file. */
	if (mapping) {
		/*
		 * IO error will be reported by write(), fsync(), etc.
		 * who check the mapping.
		 * This way the application knows that something went
		 * wrong with its dirty file data.
		 *
		 * There's one open issue:
		 *
		 * The EIO will be only reported on the next IO
		 * operation and then cleared through the IO map.
		 * Normally Linux has two mechanisms to pass IO error
		 * first through the AS_EIO flag in the address space
		 * and then through the PageError flag in the page.
		 * Since we drop pages on memory failure handling the
		 * only mechanism open to use is through AS_AIO.
		 *
		 * This has the disadvantage that it gets cleared on
		 * the first operation that returns an error, while
		 * the PageError bit is more sticky and only cleared
		 * when the page is reread or dropped.  If an
		 * application assumes it will always get error on
		 * fsync, but does other operations on the fd before
		 * and the page is dropped between then the error
		 * will not be properly reported.
		 *
		 * This can already happen even without hwpoisoned
		 * pages: first on metadata IO errors (which only
		 * report through AS_EIO) or when the page is dropped
		 * at the wrong time.
		 *
		 * So right now we assume that the application DTRT on
		 * the first EIO, but we're not worse than other parts
		 * of the kernel.
		 */
		mapping_set_error(mapping, EIO);
	}

	return me_pagecache_clean(p, pfn);
}

/*
 * Clean and dirty swap cache.
 *
 * Dirty swap cache page is tricky to handle. The page could live both in page
 * cache and swap cache(ie. page is freshly swapped in). So it could be
 * referenced concurrently by 2 types of PTEs:
 * normal PTEs and swap PTEs. We try to handle them consistently by calling
 * try_to_unmap(TTU_IGNORE_HWPOISON) to convert the normal PTEs to swap PTEs,
 * and then
 *      - clear dirty bit to prevent IO
 *      - remove from LRU
 *      - but keep in the swap cache, so that when we return to it on
 *        a later page fault, we know the application is accessing
 *        corrupted data and shall be killed (we installed simple
 *        interception code in do_swap_page to catch it).
 *
 * Clean swap cache pages can be directly isolated. A later page fault will
 * bring in the known good data from disk.
 */
static int me_swapcache_dirty(struct page *p, unsigned long pfn)
{
	ClearPageDirty(p);
	/* Trigger EIO in shmem: */
	ClearPageUptodate(p);

	if (!delete_from_lru_cache(p))
		return MF_DELAYED;
	else
		return MF_FAILED;
}

static int me_swapcache_clean(struct page *p, unsigned long pfn)
{
	delete_from_swap_cache(p);

	if (!delete_from_lru_cache(p))
		return MF_RECOVERED;
	else
		return MF_FAILED;
}

/*
 * Huge pages. Needs work.
 * Issues:
 * - Error on hugepage is contained in hugepage unit (not in raw page unit.)
 *   To narrow down kill region to one page, we need to break up pmd.
 */
static int me_huge_page(struct page *p, unsigned long pfn)
{
	int res = 0;
	struct page *hpage = compound_head(p);

	if (!PageHuge(hpage))
		return MF_DELAYED;

	/*
	 * We can safely recover from error on free or reserved (i.e.
	 * not in-use) hugepage by dequeuing it from freelist.
	 * To check whether a hugepage is in-use or not, we can't use
	 * page->lru because it can be used in other hugepage operations,
	 * such as __unmap_hugepage_range() and gather_surplus_pages().
	 * So instead we use page_mapping() and PageAnon().
	 */
	if (!(page_mapping(hpage) || PageAnon(hpage))) {
		res = dequeue_hwpoisoned_huge_page(hpage);
		if (!res)
			return MF_RECOVERED;
	}
	return MF_DELAYED;
}

/*
 * Various page states we can handle.
 *
 * A page state is defined by its current page->flags bits.
 * The table matches them in order and calls the right handler.
 *
 * This is quite tricky because we can access page at any time
 * in its live cycle, so all accesses have to be extremely careful.
 *
 * This is not complete. More states could be added.
 * For any missing state don't attempt recovery.
 */

#define dirty		(1UL << PG_dirty)
#define sc		((1UL << PG_swapcache) | (1UL << PG_swapbacked))
#define unevict		(1UL << PG_unevictable)
#define mlock		(1UL << PG_mlocked)
#define writeback	(1UL << PG_writeback)
#define lru		(1UL << PG_lru)
#define head		(1UL << PG_head)
#define slab		(1UL << PG_slab)
#define reserved	(1UL << PG_reserved)

static struct page_state {
	unsigned long mask;
	unsigned long res;
	enum mf_action_page_type type;
	int (*action)(struct page *p, unsigned long pfn);
} error_states[] = {
	{ reserved,	reserved,	MF_MSG_KERNEL,	me_kernel },
	/*
	 * free pages are specially detected outside this table:
	 * PG_buddy pages only make a small fraction of all free pages.
	 */

	/*
	 * Could in theory check if slab page is free or if we can drop
	 * currently unused objects without touching them. But just
	 * treat it as standard kernel for now.
	 */
	{ slab,		slab,		MF_MSG_SLAB,	me_kernel },

	{ head,		head,		MF_MSG_HUGE,		me_huge_page },

	{ sc|dirty,	sc|dirty,	MF_MSG_DIRTY_SWAPCACHE,	me_swapcache_dirty },
	{ sc|dirty,	sc,		MF_MSG_CLEAN_SWAPCACHE,	me_swapcache_clean },

	{ mlock|dirty,	mlock|dirty,	MF_MSG_DIRTY_MLOCKED_LRU,	me_pagecache_dirty },
	{ mlock|dirty,	mlock,		MF_MSG_CLEAN_MLOCKED_LRU,	me_pagecache_clean },

	{ unevict|dirty, unevict|dirty,	MF_MSG_DIRTY_UNEVICTABLE_LRU,	me_pagecache_dirty },
	{ unevict|dirty, unevict,	MF_MSG_CLEAN_UNEVICTABLE_LRU,	me_pagecache_clean },

	{ lru|dirty,	lru|dirty,	MF_MSG_DIRTY_LRU,	me_pagecache_dirty },
	{ lru|dirty,	lru,		MF_MSG_CLEAN_LRU,	me_pagecache_clean },

	/*
	 * Catchall entry: must be at end.
	 */
	{ 0,		0,		MF_MSG_UNKNOWN,	me_unknown },
};

#undef dirty
#undef sc
#undef unevict
#undef mlock
#undef writeback
#undef lru
#undef head
#undef slab
#undef reserved

/*
 * "Dirty/Clean" indication is not 100% accurate due to the possibility of
 * setting PG_dirty outside page lock. See also comment above set_page_dirty().
 */
static void action_result(unsigned long pfn, enum mf_action_page_type type,
			  enum mf_result result)
{
	trace_memory_failure_event(pfn, type, result);

	pr_err("Memory failure: %#lx: recovery action for %s: %s\n",
		pfn, action_page_types[type], action_name[result]);
}

static int page_action(struct page_state *ps, struct page *p,
			unsigned long pfn)
{
	int result;
	int count;

	result = ps->action(p, pfn);

	count = page_count(p) - 1;
	if (ps->action == me_swapcache_dirty && result == MF_DELAYED)
		count--;
	if (count != 0) {
		pr_err("Memory failure: %#lx: %s still referenced by %d users\n",
		       pfn, action_page_types[ps->type], count);
		result = MF_FAILED;
	}
	action_result(pfn, ps->type, result);

	/* Could do more checks here if page looks ok */
	/*
	 * Could adjust zone counters here to correct for the missing page.
	 */

	return (result == MF_RECOVERED || result == MF_DELAYED) ? 0 : -EBUSY;
}

/**
 * get_hwpoison_page() - Get refcount for memory error handling:
 * @page:	raw error page (hit by memory error)
 *
 * Return: return 0 if failed to grab the refcount, otherwise true (some
 * non-zero value.)
 */
int get_hwpoison_page(struct page *page)
{
	struct page *head = compound_head(page);

	if (!PageHuge(head) && PageTransHuge(head)) {
		/*
		 * Non anonymous thp exists only in allocation/free time. We
		 * can't handle such a case correctly, so let's give it up.
		 * This should be better than triggering BUG_ON when kernel
		 * tries to touch the "partially handled" page.
		 */
		if (!PageAnon(head)) {
			pr_err("Memory failure: %#lx: non anonymous thp\n",
				page_to_pfn(page));
			return 0;
		}
	}

	if (get_page_unless_zero(head)) {
		if (head == compound_head(page))
			return 1;

		pr_info("Memory failure: %#lx cannot catch tail\n",
			page_to_pfn(page));
		put_page(head);
	}

	return 0;
}
EXPORT_SYMBOL_GPL(get_hwpoison_page);

/*
 * Do all that is necessary to remove user space mappings. Unmap
 * the pages and send SIGBUS to the processes if the data was dirty.
 */
static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
				  int trapno, int flags, struct page **hpagep)
{
	enum ttu_flags ttu = TTU_UNMAP | TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS;
	struct address_space *mapping;
	LIST_HEAD(tokill);
	int ret;
	int kill = 1, forcekill;
	struct page *hpage = *hpagep;

	/*
	 * Here we are interested only in user-mapped pages, so skip any
	 * other types of pages.
	 */
	if (PageReserved(p) || PageSlab(p))
		return SWAP_SUCCESS;
	if (!(PageLRU(hpage) || PageHuge(p)))
		return SWAP_SUCCESS;

	/*
	 * This check implies we don't kill processes if their pages
	 * are in the swap cache early. Those are always late kills.
	 */
	if (!page_mapped(hpage))
		return SWAP_SUCCESS;

	if (PageKsm(p)) {
		pr_err("Memory failure: %#lx: can't handle KSM pages.\n", pfn);
		return SWAP_FAIL;
	}

	if (PageSwapCache(p)) {
		pr_err("Memory failure: %#lx: keeping poisoned page in swap cache\n",
			pfn);
		ttu |= TTU_IGNORE_HWPOISON;
	}

	/*
	 * Propagate the dirty bit from PTEs to struct page first, because we
	 * need this to decide if we should kill or just drop the page.
	 * XXX: the dirty test could be racy: set_page_dirty() may not always
	 * be called inside page lock (it's recommended but not enforced).
	 */
	mapping = page_mapping(hpage);
	if (!(flags & MF_MUST_KILL) && !PageDirty(hpage) && mapping &&
	    mapping_cap_writeback_dirty(mapping)) {
		if (page_mkclean(hpage)) {
			SetPageDirty(hpage);
		} else {
			kill = 0;
			ttu |= TTU_IGNORE_HWPOISON;
			pr_info("Memory failure: %#lx: corrupted page was clean: dropped without side effects\n",
				pfn);
		}
	}

	/*
	 * First collect all the processes that have the page
	 * mapped in dirty form.  This has to be done before try_to_unmap,
	 * because ttu takes the rmap data structures down.
	 *
	 * Error handling: We ignore errors here because
	 * there's nothing that can be done.
	 */
	if (kill)
		collect_procs(hpage, &tokill, flags & MF_ACTION_REQUIRED);

	ret = try_to_unmap(hpage, ttu);
	if (ret != SWAP_SUCCESS)
		pr_err("Memory failure: %#lx: failed to unmap page (mapcount=%d)\n",
		       pfn, page_mapcount(hpage));

	/*
	 * Now that the dirty bit has been propagated to the
	 * struct page and all unmaps done we can decide if
	 * killing is needed or not.  Only kill when the page
	 * was dirty or the process is not restartable,
	 * otherwise the tokill list is merely
	 * freed.  When there was a problem unmapping earlier
	 * use a more force-full uncatchable kill to prevent
	 * any accesses to the poisoned memory.
	 */
	forcekill = PageDirty(hpage) || (flags & MF_MUST_KILL);
	kill_procs(&tokill, forcekill, trapno,
		      ret != SWAP_SUCCESS, p, pfn, flags);

	return ret;
}

static void set_page_hwpoison_huge_page(struct page *hpage)
{
	int i;
	int nr_pages = 1 << compound_order(hpage);
	for (i = 0; i < nr_pages; i++)
		SetPageHWPoison(hpage + i);
}

static void clear_page_hwpoison_huge_page(struct page *hpage)
{
	int i;
	int nr_pages = 1 << compound_order(hpage);
	for (i = 0; i < nr_pages; i++)
		ClearPageHWPoison(hpage + i);
}

/**
 * memory_failure - Handle memory failure of a page.
 * @pfn: Page Number of the corrupted page
 * @trapno: Trap number reported in the signal to user space.
 * @flags: fine tune action taken
 *
 * This function is called by the low level machine check code
 * of an architecture when it detects hardware memory corruption
 * of a page. It tries its best to recover, which includes
 * dropping pages, killing processes etc.
 *
 * The function is primarily of use for corruptions that
 * happen outside the current execution context (e.g. when
 * detected by a background scrubber)
 *
 * Must run in process context (e.g. a work queue) with interrupts
 * enabled and no spinlocks hold.
 */
int memory_failure(unsigned long pfn, int trapno, int flags)