[PATCH AUTOSEL 4.19 012/192] sysctl: handle overflow for file-max

[PATCH AUTOSEL 4.19 012/192] sysctl: handle overflow for file-max

[Sasha Levin]

From: Christian Brauner <christian@brauner.io>

[ Upstream commit 32a5ad9c22852e6bd9e74bdec5934ef9d1480bc5 ]

Currently, when writing

  echo 18446744073709551616 > /proc/sys/fs/file-max

/proc/sys/fs/file-max will overflow and be set to 0.  That quickly
crashes the system.

This commit sets the max and min value for file-max.  The max value is
set to long int.  Any higher value cannot currently be used as the
percpu counters are long ints and not unsigned integers.

Note that the file-max value is ultimately parsed via
__do_proc_doulongvec_minmax().  This function does not report error when
min or max are exceeded.  Which means if a value largen that long int is
written userspace will not receive an error instead the old value will be
kept.  There is an argument to be made that this should be changed and
__do_proc_doulongvec_minmax() should return an error when a dedicated min
or max value are exceeded.  However this has the potential to break
userspace so let's defer this to an RFC patch.

Link: http://lkml.kernel.org/r/20190107222700.15954-3-christian@brauner.io
Signed-off-by: Christian Brauner <christian@brauner.io>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Dominik Brodowski <linux@dominikbrodowski.net>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Joe Lawrence <joe.lawrence@redhat.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Waiman Long <longman@redhat.com>
[christian@brauner.io: v4]
  Link: http://lkml.kernel.org/r/20190210203943.8227-3-christian@brauner.io
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/sysctl.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 3b86acd5de4e..9e22660153ff 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -126,6 +126,7 @@ static int __maybe_unused one = 1;
 static int __maybe_unused two = 2;
 static int __maybe_unused four = 4;
 static unsigned long one_ul = 1;
+static unsigned long long_max = LONG_MAX;
 static int one_hundred = 100;
 static int one_thousand = 1000;
 #ifdef CONFIG_PRINTK
@@ -1695,6 +1696,8 @@ static struct ctl_table fs_table[] = {
 		.maxlen		= sizeof(files_stat.max_files),
 		.mode		= 0644,
 		.proc_handler	= proc_doulongvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &long_max,
 	},
 	{
 		.procname	= "nr_open",
-- 
2.19.1

[PATCH AUTOSEL 4.19 033/192] fs/file.c: initialize init_files.resize_wait

[Sasha Levin]

From: Shuriyc Chu <sureeju@gmail.com>

[ Upstream commit 5704a06810682683355624923547b41540e2801a ]

(Taken from https://bugzilla.kernel.org/show_bug.cgi?id=200647)

'get_unused_fd_flags' in kthread cause kernel crash.  It works fine on
4.1, but causes crash after get 64 fds.  It also cause crash on
ubuntu1404/1604/1804, centos7.5, and the crash messages are almost the
same.

The crash message on centos7.5 shows below:

  start fd 61
  start fd 62
  start fd 63
  BUG: unable to handle kernel NULL pointer dereference at           (null)
  IP: __wake_up_common+0x2e/0x90
  PGD 0
  Oops: 0000 [#1] SMP
  Modules linked in: test(OE) xt_CHECKSUM iptable_mangle ipt_MASQUERADE nf_nat_masquerade_ipv4 iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack ipt_REJECT nf_reject_ipv4 tun bridge stp llc ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter devlink sunrpc kvm_intel kvm irqbypass crc32_pclmul ghash_clmulni_intel aesni_intel lrw gf128mul glue_helper ablk_helper cryptd sg ppdev pcspkr virtio_balloon parport_pc parport i2c_piix4 joydev ip_tables xfs libcrc32c sr_mod cdrom sd_mod crc_t10dif crct10dif_generic ata_generic pata_acpi virtio_scsi virtio_console virtio_net cirrus drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm crct10dif_pclmul crct10dif_common crc32c_intel drm ata_piix serio_raw libata virtio_pci virtio_ring i2c_core
   virtio floppy dm_mirror dm_region_hash dm_log dm_mod
  CPU: 2 PID: 1820 Comm: test_fd Kdump: loaded Tainted: G           OE  ------------   3.10.0-862.3.3.el7.x86_64 #1
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.10.2-0-g5f4c7b1-prebuilt.qemu-project.org 04/01/2014
  task: ffff8e92b9431fa0 ti: ffff8e94247a0000 task.ti: ffff8e94247a0000
  RIP: 0010:__wake_up_common+0x2e/0x90
  RSP: 0018:ffff8e94247a2d18  EFLAGS: 00010086
  RAX: 0000000000000000 RBX: ffffffff9d09daa0 RCX: 0000000000000000
  RDX: 0000000000000000 RSI: 0000000000000003 RDI: ffffffff9d09daa0
  RBP: ffff8e94247a2d50 R08: 0000000000000000 R09: ffff8e92b95dfda8
  R10: 0000000000000000 R11: 0000000000000000 R12: ffffffff9d09daa8
  R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000000003
  FS:  0000000000000000(0000) GS:ffff8e9434e80000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 0000000000000000 CR3: 000000017c686000 CR4: 00000000000207e0
  Call Trace:
    __wake_up+0x39/0x50
    expand_files+0x131/0x250
    __alloc_fd+0x47/0x170
    get_unused_fd_flags+0x30/0x40
    test_fd+0x12a/0x1c0 [test]
    kthread+0xd1/0xe0
    ret_from_fork_nospec_begin+0x21/0x21
  Code: 66 90 55 48 89 e5 41 57 41 89 f7 41 56 41 89 ce 41 55 41 54 49 89 fc 49 83 c4 08 53 48 83 ec 10 48 8b 47 08 89 55 cc 4c 89 45 d0 <48> 8b 08 49 39 c4 48 8d 78 e8 4c 8d 69 e8 75 08 eb 3b 4c 89 ef
  RIP   __wake_up_common+0x2e/0x90
   RSP <ffff8e94247a2d18>
  CR2: 0000000000000000

This issue exists since CentOS 7.5 3.10.0-862 and CentOS 7.4
(3.10.0-693.21.1 ) is ok.  Root cause: the item 'resize_wait' is not
initialized before being used.

Reported-by: Richard Zhang <zhang.zijian@h3c.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/file.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/file.c b/fs/file.c
index 7ffd6e9d103d..780d29e58847 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -457,6 +457,7 @@ struct files_struct init_files = {
 		.full_fds_bits	= init_files.full_fds_bits_init,
 	},
 	.file_lock	= __SPIN_LOCK_UNLOCKED(init_files.file_lock),
+	.resize_wait	= __WAIT_QUEUE_HEAD_INITIALIZER(init_files.resize_wait),
 };
 
 static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start)
-- 
2.19.1

[PATCH AUTOSEL 4.19 040/192] fs: Make splice() and tee() take into account O_NONBLOCK flag on pipes

[Sasha Levin]

From: Slavomir Kaslev <kaslevs@vmware.com>

[ Upstream commit ee5e001196d1345b8fee25925ff5f1d67936081e ]

The current implementation of splice() and tee() ignores O_NONBLOCK set
on pipe file descriptors and checks only the SPLICE_F_NONBLOCK flag for
blocking on pipe arguments.  This is inconsistent since splice()-ing
from/to non-pipe file descriptors does take O_NONBLOCK into
consideration.

Fix this by promoting O_NONBLOCK, when set on a pipe, to
SPLICE_F_NONBLOCK.

Some context for how the current implementation of splice() leads to
inconsistent behavior.  In the ongoing work[1] to add VM tracing
capability to trace-cmd we stream tracing data over named FIFOs or
vsockets from guests back to the host.

When we receive SIGINT from user to stop tracing, we set O_NONBLOCK on
the input file descriptor and set SPLICE_F_NONBLOCK for the next call to
splice().  If splice() was blocked waiting on data from the input FIFO,
after SIGINT splice() restarts with the same arguments (no
SPLICE_F_NONBLOCK) and blocks again instead of returning -EAGAIN when no
data is available.

This differs from the splice() behavior when reading from a vsocket or
when we're doing a traditional read()/write() loop (trace-cmd's
--nosplice argument).

With this patch applied we get the same behavior in all situations after
setting O_NONBLOCK which also matches the behavior of doing a
read()/write() loop instead of splice().

This change does have potential of breaking users who don't expect
EAGAIN from splice() when SPLICE_F_NONBLOCK is not set.  OTOH programs
that set O_NONBLOCK and don't anticipate EAGAIN are arguably buggy[2].

 [1] https://github.com/skaslev/trace-cmd/tree/vsock
 [2] https://github.com/torvalds/linux/blob/d47e3da1759230e394096fd742aad423c291ba48/fs/read_write.c#L1425

Signed-off-by: Slavomir Kaslev <kaslevs@vmware.com>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/splice.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/fs/splice.c b/fs/splice.c
index 29e92b506394..7769181aa1a6 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1119,6 +1119,9 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 		if (ipipe == opipe)
 			return -EINVAL;
 
+		if ((in->f_flags | out->f_flags) & O_NONBLOCK)
+			flags |= SPLICE_F_NONBLOCK;
+
 		return splice_pipe_to_pipe(ipipe, opipe, len, flags);
 	}
 
@@ -1144,6 +1147,9 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 		if (unlikely(ret < 0))
 			return ret;
 
+		if (in->f_flags & O_NONBLOCK)
+			flags |= SPLICE_F_NONBLOCK;
+
 		file_start_write(out);
 		ret = do_splice_from(ipipe, out, &offset, len, flags);
 		file_end_write(out);
@@ -1168,6 +1174,9 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 			offset = in->f_pos;
 		}
 
+		if (out->f_flags & O_NONBLOCK)
+			flags |= SPLICE_F_NONBLOCK;
+
 		pipe_lock(opipe);
 		ret = wait_for_space(opipe, flags);
 		if (!ret)
@@ -1717,6 +1726,9 @@ static long do_tee(struct file *in, struct file *out, size_t len,
 	 * copying the data.
 	 */
 	if (ipipe && opipe && ipipe != opipe) {
+		if ((in->f_flags | out->f_flags) & O_NONBLOCK)
+			flags |= SPLICE_F_NONBLOCK;
+
 		/*
 		 * Keep going, unless we encounter an error. The ipipe/opipe
 		 * ordering doesn't really matter.
-- 
2.19.1

[PATCH AUTOSEL 4.19 044/192] fs: fix guard_bio_eod to check for real EOD errors

[Sasha Levin]

From: Carlos Maiolino <cmaiolino@redhat.com>

[ Upstream commit dce30ca9e3b676fb288c33c1f4725a0621361185 ]

guard_bio_eod() can truncate a segment in bio to allow it to do IO on
odd last sectors of a device.

It already checks if the IO starts past EOD, but it does not consider
the possibility of an IO request starting within device boundaries can
contain more than one segment past EOD.

In such cases, truncated_bytes can be bigger than PAGE_SIZE, and will
underflow bvec->bv_len.

Fix this by checking if truncated_bytes is lower than PAGE_SIZE.

This situation has been found on filesystems such as isofs and vfat,
which doesn't check the device size before mount, if the device is
smaller than the filesystem itself, a readahead on such filesystem,
which spans EOD, can trigger this situation, leading a call to
zero_user() with a wrong size possibly corrupting memory.

I didn't see any crash, or didn't let the system run long enough to
check if memory corruption will be hit somewhere, but adding
instrumentation to guard_bio_end() to check truncated_bytes size, was
enough to see the error.

The following script can trigger the error.

MNT=/mnt
IMG=./DISK.img
DEV=/dev/loop0

mkfs.vfat $IMG
mount $IMG $MNT
cp -R /etc $MNT &> /dev/null
umount $MNT

losetup -D

losetup --find --show --sizelimit 16247280 $IMG
mount $DEV $MNT

find $MNT -type f -exec cat {} + >/dev/null

Kudos to Eric Sandeen for coming up with the reproducer above

Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/buffer.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/fs/buffer.c b/fs/buffer.c
index c083c4b3c1e7..a550e0d8e965 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -3027,6 +3027,13 @@ void guard_bio_eod(int op, struct bio *bio)
 	/* Uhhuh. We've got a bio that straddles the device size! */
 	truncated_bytes = bio->bi_iter.bi_size - (maxsector << 9);
 
+	/*
+	 * The bio contains more than one segment which spans EOD, just return
+	 * and let IO layer turn it into an EIO
+	 */
+	if (truncated_bytes > bvec->bv_len)
+		return;
+
 	/* Truncate the bio.. */
 	bio->bi_iter.bi_size -= truncated_bytes;
 	bvec->bv_len -= truncated_bytes;
-- 
2.19.1

[PATCH AUTOSEL 4.19 094/192] vfs: fix preadv64v2 and pwritev64v2 compat syscalls with offset == -1

[Sasha Levin]

From: Aurelien Jarno <aurelien@aurel32.net>

[ Upstream commit cc4b1242d7e3b42eed73881fc749944146493e4f ]

The preadv2 and pwritev2 syscalls are supposed to emulate the readv and
writev syscalls when offset == -1. Therefore the compat code should
check for offset before calling do_compat_preadv64 and
do_compat_pwritev64. This is the case for the preadv2 and pwritev2
syscalls, but handling of offset == -1 is missing in their 64-bit
equivalent.

This patch fixes that, calling do_compat_readv and do_compat_writev when
offset == -1. This fixes the following glibc tests on x32:
 - misc/tst-preadvwritev2
 - misc/tst-preadvwritev64v2

Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: H.J. Lu <hjl.tools@gmail.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/read_write.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/fs/read_write.c b/fs/read_write.c
index 8a2737f0d61d..562974a0616c 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1241,6 +1241,9 @@ COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd,
 		const struct compat_iovec __user *,vec,
 		unsigned long, vlen, loff_t, pos, rwf_t, flags)
 {
+	if (pos == -1)
+		return do_compat_readv(fd, vec, vlen, flags);
+
 	return do_compat_preadv64(fd, vec, vlen, pos, flags);
 }
 #endif
@@ -1347,6 +1350,9 @@ COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd,
 		const struct compat_iovec __user *,vec,
 		unsigned long, vlen, loff_t, pos, rwf_t, flags)
 {
+	if (pos == -1)
+		return do_compat_writev(fd, vec, vlen, flags);
+
 	return do_compat_pwritev64(fd, vec, vlen, pos, flags);
 }
 #endif
-- 
2.19.1

[PATCH AUTOSEL 4.19 117/192] genirq: Avoid summation loops for /proc/stat

[Sasha Levin]

From: Thomas Gleixner <tglx@linutronix.de>

[ Upstream commit 1136b0728969901a091f0471968b2b76ed14d9ad ]

Waiman reported that on large systems with a large amount of interrupts the
readout of /proc/stat takes a long time to sum up the interrupt
statistics. In principle this is not a problem. but for unknown reasons
some enterprise quality software reads /proc/stat with a high frequency.

The reason for this is that interrupt statistics are accounted per cpu. So
the /proc/stat logic has to sum up the interrupt stats for each interrupt.

This can be largely avoided for interrupts which are not marked as
'PER_CPU' interrupts by simply adding a per interrupt summation counter
which is incremented along with the per interrupt per cpu counter.

The PER_CPU interrupts need to avoid that and use only per cpu accounting
because they share the interrupt number and the interrupt descriptor and
concurrent updates would conflict or require unwanted synchronization.

Reported-by: Waiman Long <longman@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Waiman Long <longman@redhat.com>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: linux-fsdevel@vger.kernel.org
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: Daniel Colascione <dancol@google.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Link: https://lkml.kernel.org/r/20190208135020.925487496@linutronix.de

8<-------------

v2: Undo the unintentional layout change of struct irq_desc.

 include/linux/irqdesc.h |    1 +
 kernel/irq/chip.c       |   12 ++++++++++--
 kernel/irq/internals.h  |    8 +++++++-
 kernel/irq/irqdesc.c    |    7 ++++++-
 4 files changed, 24 insertions(+), 4 deletions(-)

Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/linux/irqdesc.h |  1 +
 kernel/irq/chip.c       | 12 ++++++++++--
 kernel/irq/internals.h  |  8 +++++++-
 kernel/irq/irqdesc.c    |  7 ++++++-
 4 files changed, 24 insertions(+), 4 deletions(-)

diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index dd1e40ddac7d..875c41b23f20 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -65,6 +65,7 @@ struct irq_desc {
 	unsigned int		core_internal_state__do_not_mess_with_it;
 	unsigned int		depth;		/* nested irq disables */
 	unsigned int		wake_depth;	/* nested wake enables */
+	unsigned int		tot_count;
 	unsigned int		irq_count;	/* For detecting broken IRQs */
 	unsigned long		last_unhandled;	/* Aging timer for unhandled count */
 	unsigned int		irqs_unhandled;
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index a2b3d9de999c..811009ebacd4 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -855,7 +855,11 @@ void handle_percpu_irq(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 
-	kstat_incr_irqs_this_cpu(desc);
+	/*
+	 * PER CPU interrupts are not serialized. Do not touch
+	 * desc->tot_count.
+	 */
+	__kstat_incr_irqs_this_cpu(desc);
 
 	if (chip->irq_ack)
 		chip->irq_ack(&desc->irq_data);
@@ -884,7 +888,11 @@ void handle_percpu_devid_irq(struct irq_desc *desc)
 	unsigned int irq = irq_desc_get_irq(desc);
 	irqreturn_t res;
 
-	kstat_incr_irqs_this_cpu(desc);
+	/*
+	 * PER CPU interrupts are not serialized. Do not touch
+	 * desc->tot_count.
+	 */
+	__kstat_incr_irqs_this_cpu(desc);
 
 	if (chip->irq_ack)
 		chip->irq_ack(&desc->irq_data);
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index ca6afa267070..e74e7eea76cf 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -242,12 +242,18 @@ static inline void irq_state_set_masked(struct irq_desc *desc)
 
 #undef __irqd_to_state
 
-static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc)
+static inline void __kstat_incr_irqs_this_cpu(struct irq_desc *desc)
 {
 	__this_cpu_inc(*desc->kstat_irqs);
 	__this_cpu_inc(kstat.irqs_sum);
 }
 
+static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc)
+{
+	__kstat_incr_irqs_this_cpu(desc);
+	desc->tot_count++;
+}
+
 static inline int irq_desc_get_node(struct irq_desc *desc)
 {
 	return irq_common_data_get_node(&desc->irq_common_data);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 578d0e5f1b5b..ba454cba4069 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -119,6 +119,7 @@ static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node,
 	desc->depth = 1;
 	desc->irq_count = 0;
 	desc->irqs_unhandled = 0;
+	desc->tot_count = 0;
 	desc->name = NULL;
 	desc->owner = owner;
 	for_each_possible_cpu(cpu)
@@ -915,11 +916,15 @@ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
 unsigned int kstat_irqs(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
-	int cpu;
 	unsigned int sum = 0;
+	int cpu;
 
 	if (!desc || !desc->kstat_irqs)
 		return 0;
+	if (!irq_settings_is_per_cpu_devid(desc) &&
+	    !irq_settings_is_per_cpu(desc))
+	    return desc->tot_count;
+
 	for_each_possible_cpu(cpu)
 		sum += *per_cpu_ptr(desc->kstat_irqs, cpu);
 	return sum;
-- 
2.19.1