X-Git-Url: https://git.sesse.net/?a=blobdiff_plain;f=libbcachefs%2Ferror.c;h=655e3ba9bfd2c09f221011ae16c38ba9f101e6ff;hb=596ec1050d0ce55f5e2d38aa8cdcb46d92178140;hp=c2882c599896cc694c9e0180bf4abf4e90f05e0a;hpb=a104f0407b7f5de54972389ef10e11dd8c525a96;p=bcachefs-tools-debian

diff --git a/libbcachefs/error.c b/libbcachefs/error.c
index c2882c5..655e3ba 100644
--- a/libbcachefs/error.c
+++ b/libbcachefs/error.c
@@ -1,14 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "bcachefs.h"
 #include "error.h"
-#include "io.h"
 #include "super.h"
 
 #define FSCK_ERR_RATELIMIT_NR	10
 
 bool bch2_inconsistent_error(struct bch_fs *c)
 {
-	set_bit(BCH_FS_ERROR, &c->flags);
+	set_bit(BCH_FS_error, &c->flags);
 
 	switch (c->opts.errors) {
 	case BCH_ON_ERROR_continue:
@@ -27,11 +26,8 @@ bool bch2_inconsistent_error(struct bch_fs *c)
 
 void bch2_topology_error(struct bch_fs *c)
 {
-	if (!test_bit(BCH_FS_TOPOLOGY_REPAIR_DONE, &c->flags))
-		return;
-
-	set_bit(BCH_FS_TOPOLOGY_ERROR, &c->flags);
-	if (test_bit(BCH_FS_FSCK_DONE, &c->flags))
+	set_bit(BCH_FS_topology_error, &c->flags);
+	if (test_bit(BCH_FS_fsck_done, &c->flags))
 		bch2_inconsistent_error(c);
 }
 
@@ -60,50 +56,95 @@ void bch2_io_error_work(struct work_struct *work)
 	up_write(&c->state_lock);
 }
 
-void bch2_io_error(struct bch_dev *ca)
+void bch2_io_error(struct bch_dev *ca, enum bch_member_error_type type)
 {
+	atomic64_inc(&ca->errors[type]);
 	//queue_work(system_long_wq, &ca->io_error_work);
 }
 
+enum ask_yn {
+	YN_NO,
+	YN_YES,
+	YN_ALLNO,
+	YN_ALLYES,
+};
+
 #ifdef __KERNEL__
-#define ask_yn()	false
+#define bch2_fsck_ask_yn()	YN_NO
 #else
+
 #include "tools-util.h"
+
+enum ask_yn bch2_fsck_ask_yn(void)
+{
+	char *buf = NULL;
+	size_t buflen = 0;
+	bool ret;
+
+	while (true) {
+		fputs(" (y,n, or Y,N for all errors of this type) ", stdout);
+		fflush(stdout);
+
+		if (getline(&buf, &buflen, stdin) < 0)
+			die("error reading from standard input");
+
+		strim(buf);
+		if (strlen(buf) != 1)
+			continue;
+
+		switch (buf[0]) {
+		case 'n':
+			return YN_NO;
+		case 'y':
+			return YN_YES;
+		case 'N':
+			return YN_ALLNO;
+		case 'Y':
+			return YN_ALLYES;
+		}
+	}
+
+	free(buf);
+	return ret;
+}
+
 #endif
 
 static struct fsck_err_state *fsck_err_get(struct bch_fs *c, const char *fmt)
 {
 	struct fsck_err_state *s;
 
-	if (test_bit(BCH_FS_FSCK_DONE, &c->flags))
+	if (test_bit(BCH_FS_fsck_done, &c->flags))
 		return NULL;
 
-	list_for_each_entry(s, &c->fsck_errors, list)
+	list_for_each_entry(s, &c->fsck_error_msgs, list)
 		if (s->fmt == fmt) {
 			/*
 			 * move it to the head of the list: repeated fsck errors
 			 * are common
 			 */
-			list_move(&s->list, &c->fsck_errors);
+			list_move(&s->list, &c->fsck_error_msgs);
 			return s;
 		}
 
 	s = kzalloc(sizeof(*s), GFP_NOFS);
 	if (!s) {
-		if (!c->fsck_alloc_err)
+		if (!c->fsck_alloc_msgs_err)
 			bch_err(c, "kmalloc err, cannot ratelimit fsck errs");
-		c->fsck_alloc_err = true;
+		c->fsck_alloc_msgs_err = true;
 		return NULL;
 	}
 
 	INIT_LIST_HEAD(&s->list);
 	s->fmt = fmt;
-	s->buf = PRINTBUF;
-	list_add(&s->list, &c->fsck_errors);
+	list_add(&s->list, &c->fsck_error_msgs);
 	return s;
 }
 
-int bch2_fsck_err(struct bch_fs *c, unsigned flags, const char *fmt, ...)
+int bch2_fsck_err(struct bch_fs *c,
+		  enum bch_fsck_flags flags,
+		  enum bch_sb_error_id err,
+		  const char *fmt, ...)
 {
 	struct fsck_err_state *s = NULL;
 	va_list args;
@@ -111,9 +152,30 @@ int bch2_fsck_err(struct bch_fs *c, unsigned flags, const char *fmt, ...)
 	struct printbuf buf = PRINTBUF, *out = &buf;
 	int ret = -BCH_ERR_fsck_ignore;
 
-	mutex_lock(&c->fsck_error_lock);
+	bch2_sb_error_count(c, err);
+
+	va_start(args, fmt);
+	prt_vprintf(out, fmt, args);
+	va_end(args);
+
+	mutex_lock(&c->fsck_error_msgs_lock);
 	s = fsck_err_get(c, fmt);
 	if (s) {
+		/*
+		 * We may be called multiple times for the same error on
+		 * transaction restart - this memoizes instead of asking the user
+		 * multiple times for the same error:
+		 */
+		if (s->last_msg && !strcmp(buf.buf, s->last_msg)) {
+			ret = s->ret;
+			mutex_unlock(&c->fsck_error_msgs_lock);
+			printbuf_exit(&buf);
+			return ret;
+		}
+
+		kfree(s->last_msg);
+		s->last_msg = kstrdup(buf.buf, GFP_KERNEL);
+
 		if (c->opts.ratelimit_errors &&
 		    !(flags & FSCK_NO_RATELIMIT) &&
 		    s->nr >= FSCK_ERR_RATELIMIT_NR) {
@@ -123,8 +185,6 @@ int bch2_fsck_err(struct bch_fs *c, unsigned flags, const char *fmt, ...)
 				print = false;
 		}
 
-		printbuf_reset(&s->buf);
-		out = &s->buf;
 		s->nr++;
 	}
 
@@ -133,11 +193,7 @@ int bch2_fsck_err(struct bch_fs *c, unsigned flags, const char *fmt, ...)
 		prt_printf(out, bch2_log_msg(c, ""));
 #endif
 
-	va_start(args, fmt);
-	prt_vprintf(out, fmt, args);
-	va_end(args);
-
-	if (test_bit(BCH_FS_FSCK_DONE, &c->flags)) {
+	if (test_bit(BCH_FS_fsck_done, &c->flags)) {
 		if (c->opts.errors != BCH_ON_ERROR_continue ||
 		    !(flags & (FSCK_CAN_FIX|FSCK_CAN_IGNORE))) {
 			prt_str(out, ", shutting down");
@@ -150,18 +206,32 @@ int bch2_fsck_err(struct bch_fs *c, unsigned flags, const char *fmt, ...)
 			prt_str(out, ", continuing");
 			ret = -BCH_ERR_fsck_ignore;
 		}
-	} else if (c->opts.fix_errors == FSCK_OPT_EXIT) {
+	} else if (c->opts.fix_errors == FSCK_FIX_exit) {
 		prt_str(out, ", exiting");
 		ret = -BCH_ERR_fsck_errors_not_fixed;
 	} else if (flags & FSCK_CAN_FIX) {
-		if (c->opts.fix_errors == FSCK_OPT_ASK) {
+		int fix = s && s->fix
+			? s->fix
+			: c->opts.fix_errors;
+
+		if (fix == FSCK_FIX_ask) {
+			int ask;
+
 			prt_str(out, ": fix?");
 			bch2_print_string_as_lines(KERN_ERR, out->buf);
 			print = false;
-			ret = ask_yn()
+
+			ask = bch2_fsck_ask_yn();
+
+			if (ask >= YN_ALLNO && s)
+				s->fix = ask == YN_ALLNO
+					? FSCK_FIX_no
+					: FSCK_FIX_yes;
+
+			ret = ask & 1
 				? -BCH_ERR_fsck_fix
 				: -BCH_ERR_fsck_ignore;
-		} else if (c->opts.fix_errors == FSCK_OPT_YES ||
+		} else if (fix == FSCK_FIX_yes ||
 			   (c->opts.nochanges &&
 			    !(flags & FSCK_CAN_IGNORE))) {
 			prt_str(out, ", fixing");
@@ -176,21 +246,24 @@ int bch2_fsck_err(struct bch_fs *c, unsigned flags, const char *fmt, ...)
 	}
 
 	if (ret == -BCH_ERR_fsck_ignore &&
-	    (c->opts.fix_errors == FSCK_OPT_EXIT ||
+	    (c->opts.fix_errors == FSCK_FIX_exit ||
 	     !(flags & FSCK_CAN_IGNORE)))
 		ret = -BCH_ERR_fsck_errors_not_fixed;
 
 	if (print)
 		bch2_print_string_as_lines(KERN_ERR, out->buf);
 
-	if (!test_bit(BCH_FS_FSCK_DONE, &c->flags) &&
+	if (!test_bit(BCH_FS_fsck_done, &c->flags) &&
 	    (ret != -BCH_ERR_fsck_fix &&
 	     ret != -BCH_ERR_fsck_ignore))
 		bch_err(c, "Unable to continue, halting");
 	else if (suppressing)
 		bch_err(c, "Ratelimiting new instances of previous error");
 
-	mutex_unlock(&c->fsck_error_lock);
+	if (s)
+		s->ret = ret;
+
+	mutex_unlock(&c->fsck_error_msgs_lock);
 
 	printbuf_exit(&buf);
 
@@ -198,10 +271,10 @@ int bch2_fsck_err(struct bch_fs *c, unsigned flags, const char *fmt, ...)
 		bch2_inconsistent_error(c);
 
 	if (ret == -BCH_ERR_fsck_fix) {
-		set_bit(BCH_FS_ERRORS_FIXED, &c->flags);
+		set_bit(BCH_FS_errors_fixed, &c->flags);
 	} else {
-		set_bit(BCH_FS_ERRORS_NOT_FIXED, &c->flags);
-		set_bit(BCH_FS_ERROR, &c->flags);
+		set_bit(BCH_FS_errors_not_fixed, &c->flags);
+		set_bit(BCH_FS_error, &c->flags);
 	}
 
 	return ret;
@@ -211,16 +284,16 @@ void bch2_flush_fsck_errs(struct bch_fs *c)
 {
 	struct fsck_err_state *s, *n;
 
-	mutex_lock(&c->fsck_error_lock);
+	mutex_lock(&c->fsck_error_msgs_lock);
 
-	list_for_each_entry_safe(s, n, &c->fsck_errors, list) {
-		if (s->ratelimited)
-			bch_err(c, "Saw %llu errors like:\n    %s", s->nr, s->buf.buf);
+	list_for_each_entry_safe(s, n, &c->fsck_error_msgs, list) {
+		if (s->ratelimited && s->last_msg)
+			bch_err(c, "Saw %llu errors like:\n    %s", s->nr, s->last_msg);
 
 		list_del(&s->list);
-		printbuf_exit(&s->buf);
+		kfree(s->last_msg);
 		kfree(s);
 	}
 
-	mutex_unlock(&c->fsck_error_lock);
+	mutex_unlock(&c->fsck_error_msgs_lock);
 }