The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y
git checkout FETCH_HEAD
git cherry-pick -x b6f3f28f604ba3de4724ad82bea6adb1300c0b5f
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023071117-convene-mockup-27f2@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From b6f3f28f604ba3de4724ad82bea6adb1300c0b5f Mon Sep 17 00:00:00 2001
From: Michael Schmitz <schmitzmic(a)gmail.com>
Date: Wed, 21 Jun 2023 08:17:25 +1200
Subject: [PATCH] block: add overflow checks for Amiga partition support
The Amiga partition parser module uses signed int for partition sector
address and count, which will overflow for disks larger than 1 TB.
Use u64 as type for sector address and size to allow using disks up to
2 TB without LBD support, and disks larger than 2 TB with LBD. The RBD
format allows to specify disk sizes up to 2^128 bytes (though native
OS limitations reduce this somewhat, to max 2^68 bytes), so check for
u64 overflow carefully to protect against overflowing sector_t.
Bail out if sector addresses overflow 32 bits on kernels without LBD
support.
This bug was reported originally in 2012, and the fix was created by
the RDB author, Joanne Dow <jdow(a)earthlink.net>. A patch had been
discussed and reviewed on linux-m68k at that time but never officially
submitted (now resubmitted as patch 1 in this series).
This patch adds additional error checking and warning messages.
Reported-by: Martin Steigerwald <Martin(a)lichtvoll.de>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=43511
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Message-ID: <201206192146.09327.Martin(a)lichtvoll.de>
Cc: <stable(a)vger.kernel.org> # 5.2
Signed-off-by: Michael Schmitz <schmitzmic(a)gmail.com>
Reviewed-by: Geert Uytterhoeven <geert(a)linux-m68k.org>
Reviewed-by: Christoph Hellwig <hch(a)infradead.org>
Link: https://lore.kernel.org/r/20230620201725.7020-4-schmitzmic@gmail.com
Signed-off-by: Jens Axboe <axboe(a)kernel.dk>
diff --git a/block/partitions/amiga.c b/block/partitions/amiga.c
index 85c5c79aae48..ed222b9c901b 100644
--- a/block/partitions/amiga.c
+++ b/block/partitions/amiga.c
@@ -11,10 +11,18 @@
#define pr_fmt(fmt) fmt
#include <linux/types.h>
+#include <linux/mm_types.h>
+#include <linux/overflow.h>
#include <linux/affs_hardblocks.h>
#include "check.h"
+/* magic offsets in partition DosEnvVec */
+#define NR_HD 3
+#define NR_SECT 5
+#define LO_CYL 9
+#define HI_CYL 10
+
static __inline__ u32
checksum_block(__be32 *m, int size)
{
@@ -31,9 +39,12 @@ int amiga_partition(struct parsed_partitions *state)
unsigned char *data;
struct RigidDiskBlock *rdb;
struct PartitionBlock *pb;
- sector_t start_sect, nr_sects;
- int blk, part, res = 0;
- int blksize = 1; /* Multiplier for disk block size */
+ u64 start_sect, nr_sects;
+ sector_t blk, end_sect;
+ u32 cylblk; /* rdb_CylBlocks = nr_heads*sect_per_track */
+ u32 nr_hd, nr_sect, lo_cyl, hi_cyl;
+ int part, res = 0;
+ unsigned int blksize = 1; /* Multiplier for disk block size */
int slot = 1;
for (blk = 0; ; blk++, put_dev_sector(sect)) {
@@ -41,7 +52,7 @@ int amiga_partition(struct parsed_partitions *state)
goto rdb_done;
data = read_part_sector(state, blk, §);
if (!data) {
- pr_err("Dev %s: unable to read RDB block %d\n",
+ pr_err("Dev %s: unable to read RDB block %llu\n",
state->disk->disk_name, blk);
res = -1;
goto rdb_done;
@@ -58,12 +69,12 @@ int amiga_partition(struct parsed_partitions *state)
*(__be32 *)(data+0xdc) = 0;
if (checksum_block((__be32 *)data,
be32_to_cpu(rdb->rdb_SummedLongs) & 0x7F)==0) {
- pr_err("Trashed word at 0xd0 in block %d ignored in checksum calculation\n",
+ pr_err("Trashed word at 0xd0 in block %llu ignored in checksum calculation\n",
blk);
break;
}
- pr_err("Dev %s: RDB in block %d has bad checksum\n",
+ pr_err("Dev %s: RDB in block %llu has bad checksum\n",
state->disk->disk_name, blk);
}
@@ -80,10 +91,15 @@ int amiga_partition(struct parsed_partitions *state)
blk = be32_to_cpu(rdb->rdb_PartitionList);
put_dev_sector(sect);
for (part = 1; blk>0 && part<=16; part++, put_dev_sector(sect)) {
- blk *= blksize; /* Read in terms partition table understands */
+ /* Read in terms partition table understands */
+ if (check_mul_overflow(blk, (sector_t) blksize, &blk)) {
+ pr_err("Dev %s: overflow calculating partition block %llu! Skipping partitions %u and beyond\n",
+ state->disk->disk_name, blk, part);
+ break;
+ }
data = read_part_sector(state, blk, §);
if (!data) {
- pr_err("Dev %s: unable to read partition block %d\n",
+ pr_err("Dev %s: unable to read partition block %llu\n",
state->disk->disk_name, blk);
res = -1;
goto rdb_done;
@@ -95,19 +111,70 @@ int amiga_partition(struct parsed_partitions *state)
if (checksum_block((__be32 *)pb, be32_to_cpu(pb->pb_SummedLongs) & 0x7F) != 0 )
continue;
- /* Tell Kernel about it */
+ /* RDB gives us more than enough rope to hang ourselves with,
+ * many times over (2^128 bytes if all fields max out).
+ * Some careful checks are in order, so check for potential
+ * overflows.
+ * We are multiplying four 32 bit numbers to one sector_t!
+ */
+
+ nr_hd = be32_to_cpu(pb->pb_Environment[NR_HD]);
+ nr_sect = be32_to_cpu(pb->pb_Environment[NR_SECT]);
+
+ /* CylBlocks is total number of blocks per cylinder */
+ if (check_mul_overflow(nr_hd, nr_sect, &cylblk)) {
+ pr_err("Dev %s: heads*sects %u overflows u32, skipping partition!\n",
+ state->disk->disk_name, cylblk);
+ continue;
+ }
+
+ /* check for consistency with RDB defined CylBlocks */
+ if (cylblk > be32_to_cpu(rdb->rdb_CylBlocks)) {
+ pr_warn("Dev %s: cylblk %u > rdb_CylBlocks %u!\n",
+ state->disk->disk_name, cylblk,
+ be32_to_cpu(rdb->rdb_CylBlocks));
+ }
+
+ /* RDB allows for variable logical block size -
+ * normalize to 512 byte blocks and check result.
+ */
+
+ if (check_mul_overflow(cylblk, blksize, &cylblk)) {
+ pr_err("Dev %s: partition %u bytes per cyl. overflows u32, skipping partition!\n",
+ state->disk->disk_name, part);
+ continue;
+ }
+
+ /* Calculate partition start and end. Limit of 32 bit on cylblk
+ * guarantees no overflow occurs if LBD support is enabled.
+ */
+
+ lo_cyl = be32_to_cpu(pb->pb_Environment[LO_CYL]);
+ start_sect = ((u64) lo_cyl * cylblk);
+
+ hi_cyl = be32_to_cpu(pb->pb_Environment[HI_CYL]);
+ nr_sects = (((u64) hi_cyl - lo_cyl + 1) * cylblk);
- nr_sects = ((sector_t)be32_to_cpu(pb->pb_Environment[10]) + 1 -
- be32_to_cpu(pb->pb_Environment[9])) *
- be32_to_cpu(pb->pb_Environment[3]) *
- be32_to_cpu(pb->pb_Environment[5]) *
- blksize;
if (!nr_sects)
continue;
- start_sect = (sector_t)be32_to_cpu(pb->pb_Environment[9]) *
- be32_to_cpu(pb->pb_Environment[3]) *
- be32_to_cpu(pb->pb_Environment[5]) *
- blksize;
+
+ /* Warn user if partition end overflows u32 (AmigaDOS limit) */
+
+ if ((start_sect + nr_sects) > UINT_MAX) {
+ pr_warn("Dev %s: partition %u (%llu-%llu) needs 64 bit device support!\n",
+ state->disk->disk_name, part,
+ start_sect, start_sect + nr_sects);
+ }
+
+ if (check_add_overflow(start_sect, nr_sects, &end_sect)) {
+ pr_err("Dev %s: partition %u (%llu-%llu) needs LBD device support, skipping partition!\n",
+ state->disk->disk_name, part,
+ start_sect, end_sect);
+ continue;
+ }
+
+ /* Tell Kernel about it */
+
put_partition(state,slot++,start_sect,nr_sects);
{
/* Be even more informative to aid mounting */
The patch below does not apply to the 6.1-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y
git checkout FETCH_HEAD
git cherry-pick -x 8a796565cec3601071cbbd27d6304e202019d014
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023071620-litigate-debunk-939a@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
8a796565cec3 ("io_uring: Use io_schedule* in cqring wait")
d33a39e57768 ("io_uring: keep timeout in io_wait_queue")
46ae7eef44f6 ("io_uring: optimise non-timeout waiting")
846072f16eed ("io_uring: mimimise io_cqring_wait_schedule")
3fcf19d592d5 ("io_uring: parse check_cq out of wq waiting")
12521a5d5cb7 ("io_uring: fix CQ waiting timeout handling")
52ea806ad983 ("io_uring: finish waiting before flushing overflow entries")
35d90f95cfa7 ("io_uring: include task_work run after scheduling in wait for events")
1b346e4aa8e7 ("io_uring: don't check overflow flush failures")
a85381d8326d ("io_uring: skip overflow CQE posting for dying ring")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 8a796565cec3601071cbbd27d6304e202019d014 Mon Sep 17 00:00:00 2001
From: Andres Freund <andres(a)anarazel.de>
Date: Fri, 7 Jul 2023 09:20:07 -0700
Subject: [PATCH] io_uring: Use io_schedule* in cqring wait
I observed poor performance of io_uring compared to synchronous IO. That
turns out to be caused by deeper CPU idle states entered with io_uring,
due to io_uring using plain schedule(), whereas synchronous IO uses
io_schedule().
The losses due to this are substantial. On my cascade lake workstation,
t/io_uring from the fio repository e.g. yields regressions between 20%
and 40% with the following command:
./t/io_uring -r 5 -X0 -d 1 -s 1 -c 1 -p 0 -S$use_sync -R 0 /mnt/t2/fio/write.0.0
This is repeatable with different filesystems, using raw block devices
and using different block devices.
Use io_schedule_prepare() / io_schedule_finish() in
io_cqring_wait_schedule() to address the difference.
After that using io_uring is on par or surpassing synchronous IO (using
registered files etc makes it reliably win, but arguably is a less fair
comparison).
There are other calls to schedule() in io_uring/, but none immediately
jump out to be similarly situated, so I did not touch them. Similarly,
it's possible that mutex_lock_io() should be used, but it's not clear if
there are cases where that matters.
Cc: stable(a)vger.kernel.org # 5.10+
Cc: Pavel Begunkov <asml.silence(a)gmail.com>
Cc: io-uring(a)vger.kernel.org
Cc: linux-kernel(a)vger.kernel.org
Signed-off-by: Andres Freund <andres(a)anarazel.de>
Link: https://lore.kernel.org/r/20230707162007.194068-1-andres@anarazel.de
[axboe: minor style fixup]
Signed-off-by: Jens Axboe <axboe(a)kernel.dk>
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index e8096d502a7c..7505de2428e0 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -2489,6 +2489,8 @@ int io_run_task_work_sig(struct io_ring_ctx *ctx)
static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
struct io_wait_queue *iowq)
{
+ int token, ret;
+
if (unlikely(READ_ONCE(ctx->check_cq)))
return 1;
if (unlikely(!llist_empty(&ctx->work_llist)))
@@ -2499,11 +2501,20 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
return -EINTR;
if (unlikely(io_should_wake(iowq)))
return 0;
+
+ /*
+ * Use io_schedule_prepare/finish, so cpufreq can take into account
+ * that the task is waiting for IO - turns out to be important for low
+ * QD IO.
+ */
+ token = io_schedule_prepare();
+ ret = 0;
if (iowq->timeout == KTIME_MAX)
schedule();
else if (!schedule_hrtimeout(&iowq->timeout, HRTIMER_MODE_ABS))
- return -ETIME;
- return 0;
+ ret = -ETIME;
+ io_schedule_finish(token);
+ return ret;
}
/*