/** * stage2_wp_range() - write protect stage2 memory region range * @kvm: The KVM pointer * @addr: Start address of range * @end: End address of range */ static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end) { pgd_t *pgd; phys_addr_t next; pgd = kvm->arch.pgd + kvm_pgd_index(addr); do { /* * Release kvm_mmu_lock periodically if the memory region is * large. Otherwise, we may see kernel panics with * CONFIG_DETECT_HUNG_TASK, CONFIG_LOCKUP_DETECTOR, * CONFIG_LOCKDEP. Additionally, holding the lock too long * will also starve other vCPUs. */ if (need_resched() || spin_needbreak(&kvm->mmu_lock)) cond_resched_lock(&kvm->mmu_lock); next = kvm_pgd_addr_end(addr, end); if (pgd_present(*pgd)) stage2_wp_puds(pgd, addr, next); } while (pgd++, addr = next, addr != end); }
int jbd2_log_do_checkpoint(journal_t *journal) { transaction_t *transaction; tid_t this_tid; int result; jbd_debug(1, "Start checkpoint\n"); result = jbd2_cleanup_journal_tail(journal); trace_jbd2_checkpoint(journal, result); jbd_debug(1, "cleanup_journal_tail returned %d\n", result); if (result <= 0) return result; result = 0; spin_lock(&journal->j_list_lock); if (!journal->j_checkpoint_transactions) goto out; transaction = journal->j_checkpoint_transactions; if (transaction->t_chp_stats.cs_chp_time == 0) transaction->t_chp_stats.cs_chp_time = jiffies; this_tid = transaction->t_tid; restart: if (journal->j_checkpoint_transactions == transaction && transaction->t_tid == this_tid) { int batch_count = 0; struct journal_head *jh; int retry = 0, err; while (!retry && transaction->t_checkpoint_list) { jh = transaction->t_checkpoint_list; retry = __process_buffer(journal, jh, &batch_count, transaction); if (retry < 0 && !result) result = retry; if (!retry && (need_resched() || spin_needbreak(&journal->j_list_lock))) { spin_unlock(&journal->j_list_lock); retry = 1; break; } } if (batch_count) { if (!retry) { spin_unlock(&journal->j_list_lock); retry = 1; } __flush_batch(journal, &batch_count); } if (retry) { spin_lock(&journal->j_list_lock); goto restart; } err = __wait_cp_io(journal, transaction); if (!result) result = err; } out: spin_unlock(&journal->j_list_lock); if (result < 0) jbd2_journal_abort(journal, result); else result = jbd2_cleanup_journal_tail(journal); return (result < 0) ? result : 0; }
/* * Submit all the data buffers to disk */ static int journal_submit_data_buffers(journal_t *journal, transaction_t *commit_transaction, int write_op) { struct journal_head *jh; struct buffer_head *bh; int locked; int bufs = 0; struct buffer_head **wbuf = journal->j_wbuf; int err = 0; /* * Whenever we unlock the journal and sleep, things can get added * onto ->t_sync_datalist, so we have to keep looping back to * write_out_data until we *know* that the list is empty. * * Cleanup any flushed data buffers from the data list. Even in * abort mode, we want to flush this out as soon as possible. */ write_out_data: cond_resched(); spin_lock(&journal->j_list_lock); while (commit_transaction->t_sync_datalist) { jh = commit_transaction->t_sync_datalist; bh = jh2bh(jh); locked = 0; /* Get reference just to make sure buffer does not disappear * when we are forced to drop various locks */ get_bh(bh); /* If the buffer is dirty, we need to submit IO and hence * we need the buffer lock. We try to lock the buffer without * blocking. If we fail, we need to drop j_list_lock and do * blocking lock_buffer(). */ if (buffer_dirty(bh)) { if (!trylock_buffer(bh)) { BUFFER_TRACE(bh, "needs blocking lock"); spin_unlock(&journal->j_list_lock); trace_jbd_do_submit_data(journal, commit_transaction); /* Write out all data to prevent deadlocks */ journal_do_submit_data(wbuf, bufs, write_op); bufs = 0; lock_buffer(bh); spin_lock(&journal->j_list_lock); } locked = 1; } /* We have to get bh_state lock. Again out of order, sigh. */ if (!inverted_lock(journal, bh)) { jbd_lock_bh_state(bh); spin_lock(&journal->j_list_lock); } /* Someone already cleaned up the buffer? */ if (!buffer_jbd(bh) || bh2jh(bh) != jh || jh->b_transaction != commit_transaction || jh->b_jlist != BJ_SyncData) { jbd_unlock_bh_state(bh); if (locked) unlock_buffer(bh); BUFFER_TRACE(bh, "already cleaned up"); release_data_buffer(bh); continue; } if (locked && test_clear_buffer_dirty(bh)) { BUFFER_TRACE(bh, "needs writeout, adding to array"); wbuf[bufs++] = bh; __journal_file_buffer(jh, commit_transaction, BJ_Locked); jbd_unlock_bh_state(bh); if (bufs == journal->j_wbufsize) { spin_unlock(&journal->j_list_lock); trace_jbd_do_submit_data(journal, commit_transaction); journal_do_submit_data(wbuf, bufs, write_op); bufs = 0; goto write_out_data; } } else if (!locked && buffer_locked(bh)) { __journal_file_buffer(jh, commit_transaction, BJ_Locked); jbd_unlock_bh_state(bh); put_bh(bh); } else { BUFFER_TRACE(bh, "writeout complete: unfile"); if (unlikely(!buffer_uptodate(bh))) err = -EIO; __journal_unfile_buffer(jh); jbd_unlock_bh_state(bh); if (locked) unlock_buffer(bh); release_data_buffer(bh); } if (need_resched() || spin_needbreak(&journal->j_list_lock)) { spin_unlock(&journal->j_list_lock); goto write_out_data; } } spin_unlock(&journal->j_list_lock); trace_jbd_do_submit_data(journal, commit_transaction); journal_do_submit_data(wbuf, bufs, write_op); return err; }
/* * Perform an actual checkpoint. We take the first transaction on the * list of transactions to be checkpointed and send all its buffers * to disk. We submit larger chunks of data at once. * * The journal should be locked before calling this function. * Called with j_checkpoint_mutex held. */ int jbd2_log_do_checkpoint(journal_t *journal) { struct journal_head *jh; struct buffer_head *bh; transaction_t *transaction; tid_t this_tid; int result, batch_count = 0; jbd_debug(1, "Start checkpoint\n"); /* * First thing: if there are any transactions in the log which * don't need checkpointing, just eliminate them from the * journal straight away. */ result = jbd2_cleanup_journal_tail(journal); trace_jbd2_checkpoint(journal, result); jbd_debug(1, "cleanup_journal_tail returned %d\n", result); if (result <= 0) return result; /* * OK, we need to start writing disk blocks. Take one transaction * and write it. */ result = 0; spin_lock(&journal->j_list_lock); if (!journal->j_checkpoint_transactions) goto out; transaction = journal->j_checkpoint_transactions; if (transaction->t_chp_stats.cs_chp_time == 0) transaction->t_chp_stats.cs_chp_time = jiffies; this_tid = transaction->t_tid; restart: /* * If someone cleaned up this transaction while we slept, we're * done (maybe it's a new transaction, but it fell at the same * address). */ if (journal->j_checkpoint_transactions != transaction || transaction->t_tid != this_tid) goto out; /* checkpoint all of the transaction's buffers */ while (transaction->t_checkpoint_list) { jh = transaction->t_checkpoint_list; bh = jh2bh(jh); if (buffer_locked(bh)) { spin_unlock(&journal->j_list_lock); get_bh(bh); wait_on_buffer(bh); /* the journal_head may have gone by now */ BUFFER_TRACE(bh, "brelse"); __brelse(bh); goto retry; } if (jh->b_transaction != NULL) { transaction_t *t = jh->b_transaction; tid_t tid = t->t_tid; transaction->t_chp_stats.cs_forced_to_close++; spin_unlock(&journal->j_list_lock); if (unlikely(journal->j_flags & JBD2_UNMOUNT)) /* * The journal thread is dead; so * starting and waiting for a commit * to finish will cause us to wait for * a _very_ long time. */ printk(KERN_ERR "JBD2: %s: Waiting for Godot: block %llu\n", journal->j_devname, (unsigned long long) bh->b_blocknr); jbd2_log_start_commit(journal, tid); jbd2_log_wait_commit(journal, tid); goto retry; } if (!buffer_dirty(bh)) { if (unlikely(buffer_write_io_error(bh)) && !result) result = -EIO; BUFFER_TRACE(bh, "remove from checkpoint"); if (__jbd2_journal_remove_checkpoint(jh)) /* The transaction was released; we're done */ goto out; continue; } /* * Important: we are about to write the buffer, and * possibly block, while still holding the journal * lock. We cannot afford to let the transaction * logic start messing around with this buffer before * we write it to disk, as that would break * recoverability. */ BUFFER_TRACE(bh, "queue"); get_bh(bh); J_ASSERT_BH(bh, !buffer_jwrite(bh)); journal->j_chkpt_bhs[batch_count++] = bh; __buffer_relink_io(jh); transaction->t_chp_stats.cs_written++; if ((batch_count == JBD2_NR_BATCH) || need_resched() || spin_needbreak(&journal->j_list_lock)) goto unlock_and_flush; } if (batch_count) { unlock_and_flush: spin_unlock(&journal->j_list_lock); retry: if (batch_count) __flush_batch(journal, &batch_count); spin_lock(&journal->j_list_lock); goto restart; } /* * Now we issued all of the transaction's buffers, let's deal * with the buffers that are out for I/O. */ restart2: /* Did somebody clean up the transaction in the meanwhile? */ if (journal->j_checkpoint_transactions != transaction || transaction->t_tid != this_tid) goto out; while (transaction->t_checkpoint_io_list) { jh = transaction->t_checkpoint_io_list; bh = jh2bh(jh); if (buffer_locked(bh)) { spin_unlock(&journal->j_list_lock); get_bh(bh); wait_on_buffer(bh); /* the journal_head may have gone by now */ BUFFER_TRACE(bh, "brelse"); __brelse(bh); spin_lock(&journal->j_list_lock); goto restart2; } if (unlikely(buffer_write_io_error(bh)) && !result) result = -EIO; /* * Now in whatever state the buffer currently is, we * know that it has been written out and so we can * drop it from the list */ if (__jbd2_journal_remove_checkpoint(jh)) break; } out: spin_unlock(&journal->j_list_lock); if (result < 0) jbd2_journal_abort(journal, result); else result = jbd2_cleanup_journal_tail(journal); return (result < 0) ? result : 0; }
/* * Perform an actual checkpoint. We take the first transaction on the * list of transactions to be checkpointed and send all its buffers * to disk. We submit larger chunks of data at once. * * The journal should be locked before calling this function. * Called with j_checkpoint_mutex held. */ int jbd2_log_do_checkpoint(journal_t *journal) { transaction_t *transaction; tid_t this_tid; int result; jbd_debug(1, "Start checkpoint\n"); /* * First thing: if there are any transactions in the log which * don't need checkpointing, just eliminate them from the * journal straight away. */ result = jbd2_cleanup_journal_tail(journal); trace_jbd2_checkpoint(journal, result); jbd_debug(1, "cleanup_journal_tail returned %d\n", result); if (result <= 0) return result; /* * OK, we need to start writing disk blocks. Take one transaction * and write it. */ result = 0; spin_lock(&journal->j_list_lock); if (!journal->j_checkpoint_transactions) goto out; transaction = journal->j_checkpoint_transactions; if (transaction->t_chp_stats.cs_chp_time == 0) transaction->t_chp_stats.cs_chp_time = jiffies; this_tid = transaction->t_tid; restart: /* * If someone cleaned up this transaction while we slept, we're * done (maybe it's a new transaction, but it fell at the same * address). */ if (journal->j_checkpoint_transactions == transaction && transaction->t_tid == this_tid) { int batch_count = 0; struct journal_head *jh; int retry = 0, err; while (!retry && transaction->t_checkpoint_list) { jh = transaction->t_checkpoint_list; retry = __process_buffer(journal, jh, &batch_count, transaction); if (retry < 0 && !result) result = retry; if (!retry && (need_resched() || spin_needbreak(&journal->j_list_lock))) { spin_unlock(&journal->j_list_lock); retry = 1; break; } } if (batch_count) { if (!retry) { spin_unlock(&journal->j_list_lock); retry = 1; } __flush_batch(journal, &batch_count); } if (retry) { spin_lock(&journal->j_list_lock); goto restart; } /* * Now we have cleaned up the first transaction's checkpoint * list. Let's clean up the second one */ err = __wait_cp_io(journal, transaction); if (!result) result = err; } out: spin_unlock(&journal->j_list_lock); if (result < 0) jbd2_journal_abort(journal, result); else result = jbd2_cleanup_journal_tail(journal); return (result < 0) ? result : 0; }