4.14.227-rc1 review

From: Jan Kara <[email protected]>

commit d176b1f62f242ab259ff665a26fbac69db1aecba upstream.

ext4_setup_system_zone() can fail. Handle the failure in ext4_remount().

---
 fs/ext4/super.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

@@ -5364,7 +5364,10 @@ static int ext4_remount(struct super_blo
 		ext4_register_li_request(sb, first_not_zeroed);
 	}
 
-	ext4_setup_system_zone(sb);
+	err = ext4_setup_system_zone(sb);
+	if (err)
+		goto restore_opts;
+
 	if (sbi->s_journal == NULL && !(old_sb_flags & MS_RDONLY))
 		ext4_commit_super(sb, 1);
 

From: Jiri Olsa <[email protected]>

commit fc8c0a99223367b071c83711259d754b6bb7a379 upstream.

bison deprecated the "%pure-parser" directive in favor of "%define api.pure full".

The api.pure got introduced in bison 2.3 (Oct 2007), so it seems safe to use it without any version check.

---
 tools/perf/util/expr.y         |    3 ++-
 tools/perf/util/parse-events.y |    2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)

@@ -10,7 +10,8 @@
 #define MAXIDLEN 256
 %}
 
-%pure-parser
+%define api.pure full
+
 %parse-param { double *final_val }
 %parse-param { struct parse_ctx *ctx }
 %parse-param { const char **pp }

@@ -1,4 +1,4 @@
-%pure-parser
+%define api.pure full
 %parse-param {void *_parse_state}
 %parse-param {void *scanner}
 %lex-param {void* scanner}

From: Arnaldo Carvalho de Melo <[email protected]>

commit 8feb8efef97a134933620071e0b6384cb3238b4e upstream.

As the namespace support code will use this, which is not available in some non _GNU_SOURCE libraries such as Android's bionic used in my container build tests (r12b and r15c at the moment).

---
 tools/build/Makefile.feature                    |    1 +
 tools/build/feature/Makefile                    |    4 ++++
 tools/build/feature/test-all.c                  |    5 +++++
 tools/build/feature/test-get_current_dir_name.c |   10 ++++++++++
 tools/perf/Makefile.config                      |    5 +++++
 tools/perf/util/Build                           |    1 +
 tools/perf/util/get_current_dir_name.c          |   18 ++++++++++++++++++
 tools/perf/util/util.h                          |    4 ++++
 8 files changed, 48 insertions(+)
 create mode 100644 tools/build/feature/test-get_current_dir_name.c
 create mode 100644 tools/perf/util/get_current_dir_name.c

@@ -33,6 +33,7 @@ FEATURE_TESTS_BASIC :=
         dwarf_getlocations              \
         fortify-source                  \
         sync-compare-and-swap           \
+        get_current_dir_name            \
         glibc                           \
         gtk2                            \
         gtk2-infobar                    \

@@ -7,6 +7,7 @@ FILES=
          test-dwarf_getlocations.bin            \
          test-fortify-source.bin                \
          test-sync-compare-and-swap.bin         \
+         test-get_current_dir_name.bin          \
          test-glibc.bin                         \
          test-gtk2.bin                          \
          test-gtk2-infobar.bin                  \

@@ -89,6 +90,9 @@ $(OUTPUT)test-bionic.bin:
 $(OUTPUT)test-libelf.bin:
 	$(BUILD) -lelf
 
+$(OUTPUT)test-get_current_dir_name.bin:
+	$(BUILD)
+
 $(OUTPUT)test-glibc.bin:
 	$(BUILD)
 

@@ -34,6 +34,10 @@
 # include "test-libelf-mmap.c"
 #undef main
 
+#define main main_test_get_current_dir_name
+# include "test-get_current_dir_name.c"
+#undef main
+
 #define main main_test_glibc
 # include "test-glibc.c"
 #undef main

@@ -166,6 +170,7 @@ int main(int argc, char *argv[])
 	main_test_hello();
 	main_test_libelf();
 	main_test_libelf_mmap();
+	main_test_get_current_dir_name();
 	main_test_glibc();
 	main_test_dwarf();
 	main_test_dwarf_getlocations();

@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <unistd.h>
+#include <stdlib.h>
+
+int main(void)
+{
+	free(get_current_dir_name());
+	return 0;
+}

@@ -281,6 +281,11 @@ ifndef NO_BIONIC
   endif
 endif
 
+ifeq ($(feature-get_current_dir_name), 1)
+  CFLAGS += -DHAVE_GET_CURRENT_DIR_NAME
+endif
+
+
 ifdef NO_LIBELF
   NO_DWARF := 1
   NO_DEMANGLE := 1

@@ -10,6 +10,7 @@ libperf-y += evlist.o
 libperf-y += evsel.o
 libperf-y += evsel_fprintf.o
 libperf-y += find_bit.o
+libperf-y += get_current_dir_name.o
 libperf-y += kallsyms.o
 libperf-y += levenshtein.o
 libperf-y += llvm-utils.o

@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <[email protected]>
+//
+#ifndef HAVE_GET_CURRENT_DIR_NAME
+#include "util.h"
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdlib.h>
+
+/* Android's 'bionic' library, for one, doesn't have this */
+
+char *get_current_dir_name(void)
+{
+	char pwd[PATH_MAX];
+
+	return getcwd(pwd, sizeof(pwd)) == NULL ? NULL : strdup(pwd);
+}
+#endif // HAVE_GET_CURRENT_DIR_NAME

@@ -57,6 +57,10 @@ int fetch_kernel_version(unsigned int *p
 
 const char *perf_tip(const char *dirpath);
 
+#ifndef HAVE_GET_CURRENT_DIR_NAME
+char *get_current_dir_name(void);
+#endif
+
 #ifndef HAVE_SCHED_GETCPU_SUPPORT
 int sched_getcpu(void);
 #endif

From: Arnaldo Carvalho de Melo <[email protected]>

commit 11c6cbe706f218a8dc7e1f962f12b3a52ddd33a9 upstream.

A new 'perf bench epoll' will use this, and to disable it for older systems, add a feature test for this API.

This is just a simple program that if successfully compiled, means that the feature is present, at least at the library level, in a build that sets the output directory to /tmp/build/perf (using O=/tmp/build/perf), we end up with:

  $ ls -la /tmp/build/perf/feature/test-eventfd*
  -rwxrwxr-x. 1 acme acme 8176 Nov 21 15:58 /tmp/build/perf/feature/test-eventfd.bin
  -rw-rw-r--. 1 acme acme  588 Nov 21 15:58 /tmp/build/perf/feature/test-eventfd.d
  -rw-rw-r--. 1 acme acme    0 Nov 21 15:58 /tmp/build/perf/feature/test-eventfd.make.output
  $ ldd /tmp/build/perf/feature/test-eventfd.bin
	  linux-vdso.so.1 (0x00007fff3bf3f000)
	  libc.so.6 => /lib64/libc.so.6 (0x00007fa984061000)
	  /lib64/ld-linux-x86-64.so.2 (0x00007fa984417000)
  $ grep eventfd -A 2 -B 2 /tmp/build/perf/FEATURE-DUMP
  feature-dwarf=1
  feature-dwarf_getlocations=1
  feature-eventfd=1
  feature-fortify-source=1
  feature-sync-compare-and-swap=1
  $

The main thing here is that in the end we'll have -DHAVE_EVENTFD in CFLAGS, and then the 'perf bench' entry needing that API can be selectively pruned.

---
 tools/build/Makefile.feature       |    1 +
 tools/build/feature/Makefile       |    4 ++++
 tools/build/feature/test-all.c     |    5 +++++
 tools/build/feature/test-eventfd.c |    9 +++++++++
 tools/perf/Makefile.config         |    5 ++++-
 5 files changed, 23 insertions(+), 1 deletion(-)
 create mode 100644 tools/build/feature/test-eventfd.c

@@ -31,6 +31,7 @@ FEATURE_TESTS_BASIC :=
         backtrace                       \
         dwarf                           \
         dwarf_getlocations              \
+        eventfd                         \
         fortify-source                  \
         sync-compare-and-swap           \
         get_current_dir_name            \

@@ -5,6 +5,7 @@ FILES=
          test-bionic.bin                        \
          test-dwarf.bin                         \
          test-dwarf_getlocations.bin            \
+         test-eventfd.bin                       \
          test-fortify-source.bin                \
          test-sync-compare-and-swap.bin         \
          test-get_current_dir_name.bin          \

@@ -90,6 +91,9 @@ $(OUTPUT)test-bionic.bin:
 $(OUTPUT)test-libelf.bin:
 	$(BUILD) -lelf
 
+$(OUTPUT)test-eventfd.bin:
+	$(BUILD)
+
 $(OUTPUT)test-get_current_dir_name.bin:
 	$(BUILD)
 

@@ -50,6 +50,10 @@
 # include "test-dwarf_getlocations.c"
 #undef main
 
+#define main main_test_eventfd
+# include "test-eventfd.c"
+#undef main
+
 #define main main_test_libelf_getphdrnum
 # include "test-libelf-getphdrnum.c"
 #undef main

@@ -174,6 +178,7 @@ int main(int argc, char *argv[])
 	main_test_glibc();
 	main_test_dwarf();
 	main_test_dwarf_getlocations();
+	main_test_eventfd();
 	main_test_libelf_getphdrnum();
 	main_test_libelf_gelf_getnote();
 	main_test_libelf_getshdrstrndx();

@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <[email protected]>
+
+#include <sys/eventfd.h>
+
+int main(void)
+{
+	return eventfd(0, EFD_NONBLOCK);
+}

@@ -281,11 +281,14 @@ ifndef NO_BIONIC
   endif
 endif
 
+ifeq ($(feature-eventfd), 1)
+  CFLAGS += -DHAVE_EVENTFD
+endif
+
 ifeq ($(feature-get_current_dir_name), 1)
   CFLAGS += -DHAVE_GET_CURRENT_DIR_NAME
 endif
 
-
 ifdef NO_LIBELF
   NO_DWARF := 1
   NO_DEMANGLE := 1

From: Arnaldo Carvalho de Melo <[email protected]>

commit 4541a8bb13a86e504416a13360c8dc64d2fd612a upstream.

Laura reported that the perf build failed in fedora when we got a glibc that provides gettid(), which I reproduced using fedora rawhide with the glibc-devel-2.29.9000-26.fc31.x86_64 package.

Add a feature check to avoid providing a gettid() helper in such systems.

On a fedora rawhide system with this patch applied we now get:

[root@7a5f55352234 perf]# grep gettid /tmp/build/perf/FEATURE-DUMP feature-gettid=1
[root@7a5f55352234 perf]# cat /tmp/build/perf/feature/test-gettid.make.output [root@7a5f55352234 perf]# ldd /tmp/build/perf/feature/test-gettid.bin

          linux-vdso.so.1 (0x00007ffc6b1f6000)
          libc.so.6 => /lib64/libc.so.6 (0x00007f04e0a74000)
          /lib64/ld-linux-x86-64.so.2 (0x00007f04e0c47000)
  [root@7a5f55352234 perf]# nm /tmp/build/perf/feature/test-gettid.bin | grep -w gettid
                   U gettid@@GLIBC_2.30

[root@7a5f55352234 perf]#

While on a fedora:29 system:

[acme@quaco perf]$ grep gettid /tmp/build/perf/FEATURE-DUMP
feature-gettid=0
[acme@quaco perf]$ cat /tmp/build/perf/feature/test-gettid.make.output
test-gettid.c: In function ‘main’:
test-gettid.c:8:9: error: implicit declaration of function ‘gettid’; did you mean ‘getgid’? [-Werror=implicit-function-declaration]

    return gettid();
           ^~~~~~
           getgid

cc1: all warnings being treated as errors
[acme@quaco perf]$

---
 tools/build/Makefile.feature      |    1 +
 tools/build/feature/Makefile      |    4 ++++
 tools/build/feature/test-all.c    |    5 +++++
 tools/build/feature/test-gettid.c |   11 +++++++++++
 tools/perf/Makefile.config        |    4 ++++
 tools/perf/jvmti/jvmti_agent.c    |    2 ++
 6 files changed, 27 insertions(+)
 create mode 100644 tools/build/feature/test-gettid.c

@@ -35,6 +35,7 @@ FEATURE_TESTS_BASIC :=
         fortify-source                  \
         sync-compare-and-swap           \
         get_current_dir_name            \
+        gettid				\
         glibc                           \
         gtk2                            \
         gtk2-infobar                    \

@@ -51,6 +51,7 @@ FILES=
          test-get_cpuid.bin                     \
          test-sdt.bin                           \
          test-cxx.bin                           \
+         test-gettid.bin			\
          test-jvmti.bin				\
          test-sched_getcpu.bin			\
          test-setns.bin

@@ -242,6 +243,9 @@ $(OUTPUT)test-sdt.bin:
 $(OUTPUT)test-cxx.bin:
 	$(BUILDXX) -std=gnu++11
 
+$(OUTPUT)test-gettid.bin:
+	$(BUILD)
+
 $(OUTPUT)test-jvmti.bin:
 	$(BUILD)
 

@@ -38,6 +38,10 @@
 # include "test-get_current_dir_name.c"
 #undef main
 
+#define main main_test_gettid
+# include "test-gettid.c"
+#undef main
+
 #define main main_test_glibc
 # include "test-glibc.c"
 #undef main

@@ -175,6 +179,7 @@ int main(int argc, char *argv[])
 	main_test_libelf();
 	main_test_libelf_mmap();
 	main_test_get_current_dir_name();
+	main_test_gettid();
 	main_test_glibc();
 	main_test_dwarf();
 	main_test_dwarf_getlocations();

@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2019, Red Hat Inc, Arnaldo Carvalho de Melo <[email protected]>
+#define _GNU_SOURCE
+#include <unistd.h>
+
+int main(void)
+{
+	return gettid();
+}
+
+#undef _GNU_SOURCE

@@ -289,6 +289,10 @@ ifeq ($(feature-get_current_dir_name), 1
   CFLAGS += -DHAVE_GET_CURRENT_DIR_NAME
 endif
 
+ifeq ($(feature-gettid), 1)
+  CFLAGS += -DHAVE_GETTID
+endif
+
 ifdef NO_LIBELF
   NO_DWARF := 1
   NO_DEMANGLE := 1

@@ -45,10 +45,12 @@
 static char jit_path[PATH_MAX];
 static void *marker_addr;
 
+#ifndef HAVE_GETTID
 static inline pid_t gettid(void)
 {
 	return (pid_t)syscall(__NR_gettid);
 }
+#endif
 
 static int get_e_machine(struct jitheader *hdr)
 {

From: Changbin Du <[email protected]>

commit 0ada120c883d4f1f6aafd01cf0fbb10d8bbba015 upstream.

libbfd has changed the bfd_section_* macros to inline functions bfd_section_<field> since 2019-09-18. See below two commits:
o http://www.sourceware.org/ml/gdb-cvs/2019-09/msg00064.html
o https://www.sourceware.org/ml/gdb-cvs/2019-09/msg00072.html

This fix make perf able to build with both old and new libbfd.

---
 tools/perf/util/srcline.c |   16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

@@ -139,16 +139,30 @@ static void find_address_in_section(bfd
 	bfd_vma pc, vma;
 	bfd_size_type size;
 	struct a2l_data *a2l = data;
+	flagword flags;
 
 	if (a2l->found)
 		return;
 
-	if ((bfd_get_section_flags(abfd, section) & SEC_ALLOC) == 0)
+#ifdef bfd_get_section_flags
+	flags = bfd_get_section_flags(abfd, section);
+#else
+	flags = bfd_section_flags(section);
+#endif
+	if ((flags & SEC_ALLOC) == 0)
 		return;
 
 	pc = a2l->addr;
+#ifdef bfd_get_section_vma
 	vma = bfd_get_section_vma(abfd, section);
+#else
+	vma = bfd_section_vma(section);
+#endif
+#ifdef bfd_get_section_size
 	size = bfd_get_section_size(section);
+#else
+	size = bfd_section_size(section);
+#endif
 
 	if (pc < vma || pc >= vma + size)
 		return;

From: Arnaldo Carvalho de Melo <[email protected]>

commit 25ab5abf5b141d7fd13eed506c7458aa04749c29 upstream.

As 'perf bench futex wake-parallel" will use this, which is not available in older systems such as versions of the android NDK used in my container build tests (r12b and r15c at the moment).

---
 tools/build/Makefile.feature               |    1 +
 tools/build/feature/Makefile               |    4 ++++
 tools/build/feature/test-all.c             |    5 +++++
 tools/build/feature/test-pthread-barrier.c |   12 ++++++++++++
 tools/perf/Makefile.config                 |    4 ++++
 5 files changed, 26 insertions(+)
 create mode 100644 tools/build/feature/test-pthread-barrier.c

@@ -59,6 +59,7 @@ FEATURE_TESTS_BASIC :=
         libunwind-arm                   \
         libunwind-aarch64               \
         pthread-attr-setaffinity-np     \
+        pthread-barrier     		\
         stackprotector-all              \
         timerfd                         \
         libdw-dwarf-unwind              \

@@ -39,6 +39,7 @@ FILES=
          test-libunwind-debug-frame-arm.bin     \
          test-libunwind-debug-frame-aarch64.bin \
          test-pthread-attr-setaffinity-np.bin   \
+         test-pthread-barrier.bin		\
          test-stackprotector-all.bin            \
          test-timerfd.bin                       \
          test-libdw-dwarf-unwind.bin            \

@@ -80,6 +81,9 @@ $(OUTPUT)test-hello.bin:
 $(OUTPUT)test-pthread-attr-setaffinity-np.bin:
 	$(BUILD) -D_GNU_SOURCE -lpthread
 
+$(OUTPUT)test-pthread-barrier.bin:
+	$(BUILD) -lpthread
+
 $(OUTPUT)test-stackprotector-all.bin:
 	$(BUILD) -fstack-protector-all
 

@@ -130,6 +130,10 @@
 # include "test-pthread-attr-setaffinity-np.c"
 #undef main
 
+#define main main_test_pthread_barrier
+# include "test-pthread-barrier.c"
+#undef main
+
 #define main main_test_sched_getcpu
 # include "test-sched_getcpu.c"
 #undef main

@@ -202,6 +206,7 @@ int main(int argc, char *argv[])
 	main_test_sync_compare_and_swap(argc, argv);
 	main_test_zlib();
 	main_test_pthread_attr_setaffinity_np();
+	main_test_pthread_barrier();
 	main_test_lzma();
 	main_test_get_cpuid();
 	main_test_bpf();

@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdint.h>
+#include <pthread.h>
+
+int main(void)
+{
+	pthread_barrier_t barrier;
+
+	pthread_barrier_init(&barrier, NULL, 1);
+	pthread_barrier_wait(&barrier);
+	return pthread_barrier_destroy(&barrier);
+}

@@ -272,6 +272,10 @@ ifeq ($(feature-pthread-attr-setaffinity
   CFLAGS += -DHAVE_PTHREAD_ATTR_SETAFFINITY_NP
 endif
 
+ifeq ($(feature-pthread-barrier), 1)
+  CFLAGS += -DHAVE_PTHREAD_BARRIER
+endif
+
 ifndef NO_BIONIC
   $(call feature_check,bionic)
   ifeq ($(feature-bionic), 1)

From: Filipe Manana <[email protected]>

commit dbcc7d57bffc0c8cac9dac11bec548597d59a6a5 upstream.

While resolving backreferences, as part of a logical ino ioctl call or fiemap, we can end up hitting a BUG_ON() when replaying tree mod log operations of a root, triggering a stack trace like the following:

  ------------[ cut here ]------------
  kernel BUG at fs/btrfs/ctree.c:1210!
  invalid opcode: 0000 [#1] SMP KASAN PTI
  CPU: 1 PID: 19054 Comm: crawl_335 Tainted: G        W         5.11.0-2d11c0084b02-misc-next+ #89
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014
  RIP: 0010:__tree_mod_log_rewind+0x3b1/0x3c0
  Code: 05 48 8d 74 10 (...)
  RSP: 0018:ffffc90001eb70b8 EFLAGS: 00010297
  RAX: 0000000000000000 RBX: ffff88812344e400 RCX: ffffffffb28933b6
  RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff88812344e42c
  RBP: ffffc90001eb7108 R08: 1ffff11020b60a20 R09: ffffed1020b60a20
  R10: ffff888105b050f9 R11: ffffed1020b60a1f R12: 00000000000000ee
  R13: ffff8880195520c0 R14: ffff8881bc958500 R15: ffff88812344e42c
  FS:  00007fd1955e8700(0000) GS:ffff8881f5600000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00007efdb7928718 CR3: 000000010103a006 CR4: 0000000000170ee0
  Call Trace:
   btrfs_search_old_slot+0x265/0x10d0
   ? lock_acquired+0xbb/0x600
   ? btrfs_search_slot+0x1090/0x1090
   ? free_extent_buffer.part.61+0xd7/0x140
   ? free_extent_buffer+0x13/0x20
   resolve_indirect_refs+0x3e9/0xfc0
   ? lock_downgrade+0x3d0/0x3d0
   ? __kasan_check_read+0x11/0x20
   ? add_prelim_ref.part.11+0x150/0x150
   ? lock_downgrade+0x3d0/0x3d0
   ? __kasan_check_read+0x11/0x20
   ? lock_acquired+0xbb/0x600
   ? __kasan_check_write+0x14/0x20
   ? do_raw_spin_unlock+0xa8/0x140
   ? rb_insert_color+0x30/0x360
   ? prelim_ref_insert+0x12d/0x430
   find_parent_nodes+0x5c3/0x1830
   ? resolve_indirect_refs+0xfc0/0xfc0
   ? lock_release+0xc8/0x620
   ? fs_reclaim_acquire+0x67/0xf0
   ? lock_acquire+0xc7/0x510
   ? lock_downgrade+0x3d0/0x3d0
   ? lockdep_hardirqs_on_prepare+0x160/0x210
   ? lock_release+0xc8/0x620
   ? fs_reclaim_acquire+0x67/0xf0
   ? lock_acquire+0xc7/0x510
   ? poison_range+0x38/0x40
   ? unpoison_range+0x14/0x40
   ? trace_hardirqs_on+0x55/0x120
   btrfs_find_all_roots_safe+0x142/0x1e0
   ? find_parent_nodes+0x1830/0x1830
   ? btrfs_inode_flags_to_xflags+0x50/0x50
   iterate_extent_inodes+0x20e/0x580
   ? tree_backref_for_extent+0x230/0x230
   ? lock_downgrade+0x3d0/0x3d0
   ? read_extent_buffer+0xdd/0x110
   ? lock_downgrade+0x3d0/0x3d0
   ? __kasan_check_read+0x11/0x20
   ? lock_acquired+0xbb/0x600
   ? __kasan_check_write+0x14/0x20
   ? _raw_spin_unlock+0x22/0x30
   ? __kasan_check_write+0x14/0x20
   iterate_inodes_from_logical+0x129/0x170
   ? iterate_inodes_from_logical+0x129/0x170
   ? btrfs_inode_flags_to_xflags+0x50/0x50
   ? iterate_extent_inodes+0x580/0x580
   ? __vmalloc_node+0x92/0xb0
   ? init_data_container+0x34/0xb0
   ? init_data_container+0x34/0xb0
   ? kvmalloc_node+0x60/0x80
   btrfs_ioctl_logical_to_ino+0x158/0x230
   btrfs_ioctl+0x205e/0x4040
   ? __might_sleep+0x71/0xe0
   ? btrfs_ioctl_get_supported_features+0x30/0x30
   ? getrusage+0x4b6/0x9c0
   ? __kasan_check_read+0x11/0x20
   ? lock_release+0xc8/0x620
   ? __might_fault+0x64/0xd0
   ? lock_acquire+0xc7/0x510
   ? lock_downgrade+0x3d0/0x3d0
   ? lockdep_hardirqs_on_prepare+0x210/0x210
   ? lockdep_hardirqs_on_prepare+0x210/0x210
   ? __kasan_check_read+0x11/0x20
   ? do_vfs_ioctl+0xfc/0x9d0
   ? ioctl_file_clone+0xe0/0xe0
   ? lock_downgrade+0x3d0/0x3d0
   ? lockdep_hardirqs_on_prepare+0x210/0x210
   ? __kasan_check_read+0x11/0x20
   ? lock_release+0xc8/0x620
   ? __task_pid_nr_ns+0xd3/0x250
   ? lock_acquire+0xc7/0x510
   ? __fget_files+0x160/0x230
   ? __fget_light+0xf2/0x110
   __x64_sys_ioctl+0xc3/0x100
   do_syscall_64+0x37/0x80
   entry_SYSCALL_64_after_hwframe+0x44/0xa9
  RIP: 0033:0x7fd1976e2427
  Code: 00 00 90 48 8b 05 (...)
  RSP: 002b:00007fd1955e5cf8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
  RAX: ffffffffffffffda RBX: 00007fd1955e5f40 RCX: 00007fd1976e2427
  RDX: 00007fd1955e5f48 RSI: 00000000c038943b RDI: 0000000000000004
  RBP: 0000000001000000 R08: 0000000000000000 R09: 00007fd1955e6120
  R10: 0000557835366b00 R11: 0000000000000246 R12: 0000000000000004
  R13: 00007fd1955e5f48 R14: 00007fd1955e5f40 R15: 00007fd1955e5ef8
  Modules linked in:
  ---[ end trace ec8931a1c36e57be ]---

(gdb) l *(__tree_mod_log_rewind+0x3b1)
0xffffffff81893521 is in __tree_mod_log_rewind (fs/btrfs/ctree.c:1210).

  1205                     * the modification. as we're going backwards, we do the
  1206                     * opposite of each operation here.
  1207                     */

1208 switch (tm->op) {
1209 case MOD_LOG_KEY_REMOVE_WHILE_FREEING:
1210 BUG_ON(tm->slot < n);
1211 fallthrough;
1212 case MOD_LOG_KEY_REMOVE_WHILE_MOVING:
1213 case MOD_LOG_KEY_REMOVE:
1214 btrfs_set_node_key(eb, &tm->key, tm->slot);

Here's what happens to hit that BUG_ON():

1) We have one tree mod log user (through fiemap or the logical ino ioctl), with a sequence number of 1, so we have fs_info->tree_mod_seq == 1;

2) Another task is at ctree.c:balance_level() and we have eb X currently as the root of the tree, and we promote its single child, eb Y, as the new root.

Then, at ctree.c:balance_level(), we call:

      tree_mod_log_insert_root(eb X, eb Y, 1);

3) At tree_mod_log_insert_root() we create tree mod log elements for each slot of eb X, of operation type MOD_LOG_KEY_REMOVE_WHILE_FREEING each with a ->logical pointing to ebX->start. These are placed in an array named tm_list.
Lets assume there are N elements (N pointers in eb X);

4) Then, still at tree_mod_log_insert_root(), we create a tree mod log element of operation type MOD_LOG_ROOT_REPLACE, ->logical set to ebY->start, ->old_root.logical set to ebX->start, ->old_root.level set to the level of eb X and ->generation set to the generation of eb X;

5) Then tree_mod_log_insert_root() calls tree_mod_log_free_eb() with tm_list as argument. After that, tree_mod_log_free_eb() calls __tree_mod_log_insert() for each member of tm_list in reverse order, from highest slot in eb X, slot N - 1, to slot 0 of eb X;

6) __tree_mod_log_insert() sets the sequence number of each given tree mod log operation - it increments fs_info->tree_mod_seq and sets fs_info->tree_mod_seq as the sequence number of the given tree mod log operation.

This means that for the tm_list created at tree_mod_log_insert_root(), the element corresponding to slot 0 of eb X has the highest sequence number (1 + N), and the element corresponding to the last slot has the lowest sequence number (2);

7) Then, after inserting tm_list's elements into the tree mod log rbtree, the MOD_LOG_ROOT_REPLACE element is inserted, which gets the highest sequence number, which is N + 2;

8) Back to ctree.c:balance_level(), we free eb X by calling btrfs_free_tree_block() on it. Because eb X was created in the current transaction, has no other references and writeback did not happen for it, we add it back to the free space cache/tree;

9) Later some other task T allocates the metadata extent from eb X, since it is marked as free space in the space cache/tree, and uses it as a node for some other btree;

10) The tree mod log user task calls btrfs_search_old_slot(), which calls get_old_root(), and finally that calls __tree_mod_log_oldest_root() with time_seq == 1 and eb_root == eb Y;

11) First iteration of the while loop finds the tree mod log element with sequence number N + 2, for the logical address of eb Y and of type MOD_LOG_ROOT_REPLACE;

12) Because the operation type is MOD_LOG_ROOT_REPLACE, we don't break out

    of the loop, and set root_logical to point to tm->old_root.logical
    which corresponds to the logical address of eb X;

13) On the next iteration of the while loop, the call to tree_mod_log_search_oldest() returns the smallest tree mod log element for the logical address of eb X, which has a sequence number of 2, an operation type of MOD_LOG_KEY_REMOVE_WHILE_FREEING and corresponds to the old slot N - 1 of eb X (eb X had N items in it before being freed);

14) We then break out of the while loop and return the tree mod log operation of type MOD_LOG_ROOT_REPLACE (eb Y), and not the one for slot N - 1 of eb X, to get_old_root();

15) At get_old_root(), we process the MOD_LOG_ROOT_REPLACE operation and set "logical" to the logical address of eb X, which was the old root. We then call tree_mod_log_search() passing it the logical address of eb X and time_seq == 1;

16) Then before calling tree_mod_log_search(), task T adds a key to eb X, which results in adding a tree mod log operation of type MOD_LOG_KEY_ADD to the tree mod log - this is done at ctree.c:insert_ptr() - but after adding the tree mod log operation and before updating the number of items in eb X from 0 to 1...

17) The task at get_old_root() calls tree_mod_log_search() and gets the tree mod log operation of type MOD_LOG_KEY_ADD just added by task T. Then it enters the following if branch:

if (old_root && tm && tm->op != MOD_LOG_KEY_REMOVE_WHILE_FREEING) {
(...)
} (...)

Calls read_tree_block() for eb X, which gets a reference on eb X but does not lock it - task T has it locked.
Then it clones eb X while it has nritems set to 0 in its header, before task T sets nritems to 1 in eb X's header. From hereupon we use the clone of eb X which no other task has access to;

18) Then we call __tree_mod_log_rewind(), passing it the MOD_LOG_KEY_ADD mod log operation we just got from tree_mod_log_search() in the previous step and the cloned version of eb X;

19) At __tree_mod_log_rewind(), we set the local variable "n" to the number of items set in eb X's clone, which is 0. Then we enter the while loop, and in its first iteration we process the MOD_LOG_KEY_ADD operation, which just decrements "n" from 0 to (u32)-1, since "n" is declared with a type of u32. At the end of this iteration we call rb_next() to find the next tree mod log operation for eb X, that gives us the mod log operation of type MOD_LOG_KEY_REMOVE_WHILE_FREEING, for slot 0, with a sequence number of N + 1 (steps 3 to 6);

20) Then we go back to the top of the while loop and trigger the following

    BUG_ON():

        (...)
        switch (tm->op) {
        case MOD_LOG_KEY_REMOVE_WHILE_FREEING:
                 BUG_ON(tm->slot < n);
                 fallthrough;
        (...)

    Because "n" has a value of (u32)-1 (4294967295) and tm->slot is 0.

Fix this by taking a read lock on the extent buffer before cloning it at ctree.c:get_old_root(). This should be done regardless of the extent buffer having been freed and reused, as a concurrent task might be modifying it (while holding a write lock on it).

---
 fs/btrfs/ctree.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -1431,7 +1431,9 @@ get_old_root(struct btrfs_root *root, u6
 				   "failed to read tree block %llu from get_old_root",
 				   logical);
 		} else {
+			btrfs_tree_read_lock(old);
 			eb = btrfs_clone_extent_buffer(old);
+			btrfs_tree_read_unlock(old);
 			free_extent_buffer(old);
 		}
 	} else if (old_root) {

From: Joe Korty <[email protected]>

commit c7de87ff9dac5f396f62d584f3908f80ddc0e07b upstream.

[ This problem is in mainline, but only rt has the chops to be able to detect it. ]

Lockdep reports a circular lock dependency between serv->sv_lock and softirq_ctl.lock on system shutdown, when using a kernel built with CONFIG_PREEMPT_RT=y, and a nfs mount exists.

This is due to the definition of spin_lock_bh on rt:

	local_bh_disable();
	rt_spin_lock(lock);

which forces a softirq_ctl.lock -> serv->sv_lock dependency. This is not a problem as long as _every_ lock of serv->sv_lock is a:

	spin_lock_bh(&serv->sv_lock);

but there is one of the form:

	spin_lock(&serv->sv_lock);

This is what is causing the circular dependency splat. The spin_lock() grabs the lock without first grabbing softirq_ctl.lock via local_bh_disable. If later on in the critical region, someone does a local_bh_disable, we get a serv->sv_lock -> softirq_ctrl.lock dependency established. Deadlock.

Fix is to make serv->sv_lock be locked with spin_lock_bh everywhere, no exceptions.

[ OK ] Stopped target NFS client services.
Stopping Logout off all iSCSI sessions on shutdown... Stopping NFS server and services...

[  109.442380]
[  109.442385] ======================================================
[  109.442386] WARNING: possible circular locking dependency detected
[  109.442387] 5.10.16-rt30 #1 Not tainted
[  109.442389] ------------------------------------------------------
[  109.442390] nfsd/1032 is trying to acquire lock:
[  109.442392] ffff994237617f60 ((softirq_ctrl.lock).lock){+.+.}-{2:2}, at: __local_bh_disable_ip+0xd9/0x270
[  109.442405]
[  109.442405] but task is already holding lock:
[  109.442406] ffff994245cb00b0 (&serv->sv_lock){+.+.}-{0:0}, at: svc_close_list+0x1f/0x90
[  109.442415]
[  109.442415] which lock already depends on the new lock.
[  109.442415]
[  109.442416]
[  109.442416] the existing dependency chain (in reverse order) is:
[  109.442417]
[  109.442417] -> #1 (&serv->sv_lock){+.+.}-{0:0}:
[  109.442421]        rt_spin_lock+0x2b/0xc0
[  109.442428]        svc_add_new_perm_xprt+0x42/0xa0
[  109.442430]        svc_addsock+0x135/0x220
[  109.442434]        write_ports+0x4b3/0x620
[  109.442438]        nfsctl_transaction_write+0x45/0x80
[  109.442440]        vfs_write+0xff/0x420
[  109.442444]        ksys_write+0x4f/0xc0
[  109.442446]        do_syscall_64+0x33/0x40
[  109.442450]        entry_SYSCALL_64_after_hwframe+0x44/0xa9
[  109.442454]
[  109.442454] -> #0 ((softirq_ctrl.lock).lock){+.+.}-{2:2}:
[  109.442457]        __lock_acquire+0x1264/0x20b0
[  109.442463]        lock_acquire+0xc2/0x400
[  109.442466]        rt_spin_lock+0x2b/0xc0
[  109.442469]        __local_bh_disable_ip+0xd9/0x270
[  109.442471]        svc_xprt_do_enqueue+0xc0/0x4d0
[  109.442474]        svc_close_list+0x60/0x90
[  109.442476]        svc_close_net+0x49/0x1a0
[  109.442478]        svc_shutdown_net+0x12/0x40
[  109.442480]        nfsd_destroy+0xc5/0x180
[  109.442482]        nfsd+0x1bc/0x270
[  109.442483]        kthread+0x194/0x1b0
[  109.442487]        ret_from_fork+0x22/0x30
[  109.442492]
[  109.442492] other info that might help us debug this:
[  109.442492]
[  109.442493]  Possible unsafe locking scenario:
[  109.442493]
[  109.442493]        CPU0                    CPU1
[  109.442494]        ----                    ----
[  109.442495]   lock(&serv->sv_lock);
[  109.442496]                                lock((softirq_ctrl.lock).lock);
[  109.442498]                                lock(&serv->sv_lock);
[  109.442499]   lock((softirq_ctrl.lock).lock);
[  109.442501]
[  109.442501]  *** DEADLOCK ***
[  109.442501]
[  109.442501] 3 locks held by nfsd/1032:
[  109.442503]  #0: ffffffff93b49258 (nfsd_mutex){+.+.}-{3:3}, at: nfsd+0x19a/0x270
[  109.442508]  #1: ffff994245cb00b0 (&serv->sv_lock){+.+.}-{0:0}, at: svc_close_list+0x1f/0x90
[  109.442512]  #2: ffffffff93a81b20 (rcu_read_lock){....}-{1:2}, at: rt_spin_lock+0x5/0xc0
[  109.442518]
[  109.442518] stack backtrace:
[  109.442519] CPU: 0 PID: 1032 Comm: nfsd Not tainted 5.10.16-rt30 #1
[  109.442522] Hardware name: Supermicro X9DRL-3F/iF/X9DRL-3F/iF, BIOS 3.2 09/22/2015
[  109.442524] Call Trace:
[  109.442527]  dump_stack+0x77/0x97
[  109.442533]  check_noncircular+0xdc/0xf0
[  109.442546]  __lock_acquire+0x1264/0x20b0
[  109.442553]  lock_acquire+0xc2/0x400
[  109.442564]  rt_spin_lock+0x2b/0xc0
[  109.442570]  __local_bh_disable_ip+0xd9/0x270
[  109.442573]  svc_xprt_do_enqueue+0xc0/0x4d0
[  109.442577]  svc_close_list+0x60/0x90
[  109.442581]  svc_close_net+0x49/0x1a0
[  109.442585]  svc_shutdown_net+0x12/0x40
[  109.442588]  nfsd_destroy+0xc5/0x180
[  109.442590]  nfsd+0x1bc/0x270
[  109.442595]  kthread+0x194/0x1b0
[  109.442600]  ret_from_fork+0x22/0x30
[  109.518225] nfsd: last server has exited, flushing export cache
[  OK  ] Stopped NFSv4 ID-name mapping service.
[  OK  ] Stopped GSSAPI Proxy Daemon.
[  OK  ] Stopped NFS Mount Daemon.
[  OK  ] Stopped NFS status monitor for NFSv2/3 locking..

---
 net/sunrpc/svc_xprt.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -1106,7 +1106,7 @@ static int svc_close_list(struct svc_ser
 	struct svc_xprt *xprt;
 	int ret = 0;
 
-	spin_lock(&serv->sv_lock);
+	spin_lock_bh(&serv->sv_lock);
 	list_for_each_entry(xprt, xprt_list, xpt_list) {
 		if (xprt->xpt_net != net)
 			continue;

@@ -1114,7 +1114,7 @@ static int svc_close_list(struct svc_ser
 		set_bit(XPT_CLOSE, &xprt->xpt_flags);
 		svc_xprt_enqueue(xprt);
 	}
-	spin_unlock(&serv->sv_lock);
+	spin_unlock_bh(&serv->sv_lock);
 	return ret;
 }
 

From: Timo Rothenpieler <[email protected]>

commit 6820bf77864d5894ff67b5c00d7dba8f92011e3d upstream.

This brings it in line with the regular tcp backchannel, which also has all those timeouts disabled.

Prevents the backchannel from timing out, getting some async operations like server side copying getting stuck indefinitely on the client side.

---
 net/sunrpc/xprtrdma/svc_rdma_backchannel.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

@@ -321,9 +321,9 @@ xprt_setup_rdma_bc(struct xprt_create *a
 	xprt->timeout = &xprt_rdma_bc_timeout;
 	xprt_set_bound(xprt);
 	xprt_set_connected(xprt);
-	xprt->bind_timeout = RPCRDMA_BIND_TO;
-	xprt->reestablish_timeout = RPCRDMA_INIT_REEST_TO;
-	xprt->idle_timeout = RPCRDMA_IDLE_DISC_TO;
+	xprt->bind_timeout = 0;
+	xprt->reestablish_timeout = 0;
+	xprt->idle_timeout = 0;
 
 	xprt->prot = XPRT_TRANSPORT_BC_RDMA;
 	xprt->tsh_size = RPCRDMA_HDRLEN_MIN / sizeof(__be32);

This is the start of the stable review cycle for the 4.14.227 release. There are 43 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Wed, 24 Mar 2021 12:19:09 +0000. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

	https://www.kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.14.227-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-4.14.y
and the diffstat can be found below.

thanks,

greg k-h

-------------
Pseudo-Shortlog of commits:

Greg Kroah-Hartman <[email protected]>

    Linux 4.14.227-rc1

Thomas Gleixner <[email protected]>
genirq: Disable interrupts for force threaded handlers

Shijie Luo <[email protected]>
ext4: fix potential error in ext4_do_update_inode

zhangyi (F) <[email protected]>
ext4: do not try to set xattr into ea_inode if value is empty

zhangyi (F) <[email protected]>
ext4: find old entry again if failed to rename whiteout

Oleg Nesterov <[email protected]>
x86: Introduce TS_COMPAT_RESTART to fix get_nr_restart_syscall()

Oleg Nesterov <[email protected]>
x86: Move TS_COMPAT back to asm/thread_info.h

Oleg Nesterov <[email protected]>
kernel, fs: Introduce and use set_restart_fn() and arch_set_restart_data()

Thomas Gleixner <[email protected]>
x86/ioapic: Ignore IRQ2 again

Kan Liang <[email protected]>
perf/x86/intel: Fix a crash caused by zero PEBS status

Tyrel Datwyler <[email protected]>
PCI: rpadlpar: Fix potential drc_name corruption in store functions

Ye Xiang <[email protected]>
iio: hid-sensor-temperature: Fix issues of timestamp channel

Ye Xiang <[email protected]>
iio: hid-sensor-prox: Fix scale not correct issue

Ye Xiang <[email protected]>
iio: hid-sensor-humidity: Fix alignment issue of timestamp channel

Dinghao Liu <[email protected]>
iio: gyro: mpu3050: Fix error handling in mpu3050_trigger_handler

Dan Carpenter <[email protected]>

    iio: adis16400: Fix an error code in adis16400_initial_setup()

Jonathan Albrieux <[email protected]>
iio:adc:qcom-spmi-vadc: add default scale to LR_MUX2_BAT_ID channel

Jonathan Cameron <[email protected]>
iio:adc:stm32-adc: Add HAS_IOMEM dependency

Jim Lin <[email protected]>
usb: gadget: configfs: Fix KASAN use-after-free

Macpaul Lin <[email protected]>
USB: replace hardcode maximum usb string length by definition

Alan Stern <[email protected]>
usb-storage: Add quirk to defeat Kindle's automatic unload

Sagi Grimberg <[email protected]>
nvme-rdma: fix possible hang when failing to set io queues

Dan Carpenter <[email protected]>
scsi: lpfc: Fix some error codes in debugfs

Pavel Skripkin <[email protected]>
net/qrtr: fix __netdev_alloc_skb call

Daniel Kobras <[email protected]>
sunrpc: fix refcount leak for rpc auth modules

Timo Rothenpieler <[email protected]>
svcrdma: disable timeouts on rdma backchannel

Joe Korty <[email protected]>

    NFSD: Repair misuse of sv_lock in 5.10.16-rt30.

Sagi Grimberg <[email protected]>
nvmet: don't check iosqes,iocqes for discovery controllers

Filipe Manana <[email protected]>
btrfs: fix race when cloning extent buffer during rewind of an old root

Arnaldo Carvalho de Melo <[email protected]>
tools build feature: Check if pthread_barrier_t is available

Changbin Du <[email protected]>
perf: Make perf able to build with latest libbfd

Arnaldo Carvalho de Melo <[email protected]>
tools build: Check if gettid() is available before providing helper

Arnaldo Carvalho de Melo <[email protected]>
tools build feature: Check if eventfd() is available

Arnaldo Carvalho de Melo <[email protected]>
tools build feature: Check if get_current_dir_name() is available

Jiri Olsa <[email protected]>
perf tools: Use %define api.pure full instead of %pure-parser

Rafael J. Wysocki <[email protected]>
Revert "PM: runtime: Update device status before letting suppliers suspend"

Piotr Krysiuk <[email protected]>
bpf: Prohibit alu ops for pointer types not defining ptr_limit

Florian Fainelli <[email protected]>
net: dsa: b53: Support setting learning on port

Piotr Krysiuk <[email protected]>
bpf: Add sanity check for upper ptr_limit

Piotr Krysiuk <[email protected]>
bpf: Simplify alu_limit masking for pointer arithmetic

Piotr Krysiuk <[email protected]>
bpf: Fix off-by-one for area size in creating mask to left

Jan Kara <[email protected]>
ext4: check journal inode extents more carefully

Jan Kara <[email protected]>
ext4: don't allow overlapping system zones

Jan Kara <[email protected]>
ext4: handle error of ext4_setup_system_zone() on remount

-------------

Diffstat:

 Makefile                                         |  4 +-
 arch/x86/events/intel/ds.c                       |  2 +-
 arch/x86/include/asm/processor.h                 |  9 ---
 arch/x86/include/asm/thread_info.h               | 23 +++++++-
 arch/x86/kernel/apic/io_apic.c                   | 10 ++++
 arch/x86/kernel/signal.c                         | 24 +-------
 drivers/base/power/runtime.c                     | 62 +++++++++------------
 drivers/iio/adc/Kconfig                          |  1 +
 drivers/iio/adc/qcom-spmi-vadc.c                 |  2 +-
 drivers/iio/gyro/mpu3050-core.c                  |  2 +
 drivers/iio/humidity/hid-sensor-humidity.c       | 12 ++--
 drivers/iio/imu/adis16400_core.c                 |  3 +-
 drivers/iio/light/hid-sensor-prox.c              | 13 ++++-
 drivers/iio/temperature/hid-sensor-temperature.c | 14 +++--
 drivers/net/dsa/b53/b53_common.c                 | 20 +++++++
 drivers/net/dsa/b53/b53_regs.h                   |  1 +
 drivers/net/dsa/bcm_sf2.c                        |  5 ++
 drivers/net/dsa/bcm_sf2_regs.h                   |  2 +
 drivers/nvme/host/rdma.c                         |  7 ++-
 drivers/nvme/target/core.c                       | 17 +++++-
 drivers/pci/hotplug/rpadlpar_sysfs.c             | 14 ++---
 drivers/scsi/lpfc/lpfc_debugfs.c                 |  4 +-
 drivers/usb/gadget/composite.c                   |  4 +-
 drivers/usb/gadget/configfs.c                    | 16 ++++--
 drivers/usb/gadget/usbstring.c                   |  4 +-
 drivers/usb/storage/transport.c                  |  7 +++
 drivers/usb/storage/unusual_devs.h               | 12 ++++
 fs/btrfs/ctree.c                                 |  2 +
 fs/ext4/block_validity.c                         | 71 +++++++++++-------------
 fs/ext4/ext4.h                                   |  6 +-
 fs/ext4/extents.c                                | 16 ++----
 fs/ext4/indirect.c                               |  6 +-
 fs/ext4/inode.c                                  | 13 ++---
 fs/ext4/mballoc.c                                |  4 +-
 fs/ext4/namei.c                                  | 29 +++++++++-
 fs/ext4/super.c                                  |  5 +-
 fs/ext4/xattr.c                                  |  2 +-
 fs/select.c                                      | 10 ++--
 include/linux/thread_info.h                      | 13 +++++
 include/linux/usb_usual.h                        |  2 +
 include/uapi/linux/usb/ch9.h                     |  3 +
 kernel/bpf/verifier.c                            | 33 +++++++----
 kernel/futex.c                                   |  3 +-
 kernel/irq/manage.c                              |  4 ++
 kernel/time/alarmtimer.c                         |  2 +-
 kernel/time/hrtimer.c                            |  2 +-
 kernel/time/posix-cpu-timers.c                   |  2 +-
 net/qrtr/qrtr.c                                  |  2 +-
 net/sunrpc/svc.c                                 |  6 +-
 net/sunrpc/svc_xprt.c                            |  4 +-
 net/sunrpc/xprtrdma/svc_rdma_backchannel.c       |  6 +-
 tools/build/Makefile.feature                     |  4 ++
 tools/build/feature/Makefile                     | 16 ++++++
 tools/build/feature/test-all.c                   | 20 +++++++
 tools/build/feature/test-eventfd.c               |  9 +++
 tools/build/feature/test-get_current_dir_name.c  | 10 ++++
 tools/build/feature/test-gettid.c                | 11 ++++
 tools/build/feature/test-pthread-barrier.c       | 12 ++++
 tools/perf/Makefile.config                       | 16 ++++++
 tools/perf/jvmti/jvmti_agent.c                   |  2 +
 tools/perf/util/Build                            |  1 +
 tools/perf/util/expr.y                           |  3 +-
 tools/perf/util/get_current_dir_name.c           | 18 ++++++
 tools/perf/util/parse-events.y                   |  2 +-
 tools/perf/util/srcline.c                        | 16 +++++-
 tools/perf/util/util.h                           |  4 ++
 66 files changed, 469 insertions(+), 215 deletions(-)

From: Jan Kara <[email protected]>

commit bf9a379d0980e7413d94cb18dac73db2bfc5f470 upstream.

Currently, add_system_zone() just silently merges two added system zones that overlap. However the overlap should not happen and it generally suggests that some unrelated metadata overlap which indicates the fs is corrupted. We should have caught such problems earlier (e.g. in ext4_check_descriptors()) but add this check as another line of defense. In later patch we also use this for stricter checking of journal inode extent tree.

---
 fs/ext4/block_validity.c |   34 ++++++++++++----------------------
 1 file changed, 12 insertions(+), 22 deletions(-)

@@ -58,7 +58,7 @@ static int add_system_zone(struct ext4_s
 			   ext4_fsblk_t start_blk,
 			   unsigned int count)
 {
-	struct ext4_system_zone *new_entry = NULL, *entry;
+	struct ext4_system_zone *new_entry, *entry;
 	struct rb_node **n = &sbi->system_blks.rb_node, *node;
 	struct rb_node *parent = NULL, *new_node = NULL;
 

@@ -69,30 +69,20 @@ static int add_system_zone(struct ext4_s
 			n = &(*n)->rb_left;
 		else if (start_blk >= (entry->start_blk + entry->count))
 			n = &(*n)->rb_right;
-		else {
-			if (start_blk + count > (entry->start_blk +
-						 entry->count))
-				entry->count = (start_blk + count -
-						entry->start_blk);
-			new_node = *n;
-			new_entry = rb_entry(new_node, struct ext4_system_zone,
-					     node);
-			break;
-		}
+		else	/* Unexpected overlap of system zones. */
+			return -EFSCORRUPTED;
 	}
 
-	if (!new_entry) {
-		new_entry = kmem_cache_alloc(ext4_system_zone_cachep,
-					     GFP_KERNEL);
-		if (!new_entry)
-			return -ENOMEM;
-		new_entry->start_blk = start_blk;
-		new_entry->count = count;
-		new_node = &new_entry->node;
+	new_entry = kmem_cache_alloc(ext4_system_zone_cachep,
+				     GFP_KERNEL);
+	if (!new_entry)
+		return -ENOMEM;
+	new_entry->start_blk = start_blk;
+	new_entry->count = count;
+	new_node = &new_entry->node;
 
-		rb_link_node(new_node, parent, n);
-		rb_insert_color(new_node, &sbi->system_blks);
-	}
+	rb_link_node(new_node, parent, n);
+	rb_insert_color(new_node, &sbi->system_blks);
 
 	/* Can we merge to the left? */
 	node = rb_prev(new_node);

From: Piotr Krysiuk <[email protected]>

commit 10d2bb2e6b1d8c4576c56a748f697dbeb8388899 upstream.

retrieve_ptr_limit() computes the ptr_limit for registers with stack and map_value type. ptr_limit is the size of the memory area that is still valid / in-bounds from the point of the current position and direction of the operation (add / sub). This size will later be used for masking the operation such that attempting out-of-bounds access in the speculative domain is redirected to remain within the bounds of the current map value.

When masking to the right the size is correct, however, when masking to the left, the size is off-by-one which would lead to an incorrect mask and thus incorrect arithmetic operation in the non-speculative domain. Piotr found that if the resulting alu_limit value is zero, then the BPF_MOV32_IMM() from the fixup_bpf_calls() rewrite will end up loading 0xffffffff into AX instead of sign-extending to the full 64 bit range, and as a result, this allows abuse for executing speculatively out-of- bounds loads against 4GB window of address space and thus extracting the contents of kernel memory via side-channel.

---
 kernel/bpf/verifier.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -2035,13 +2035,13 @@ static int retrieve_ptr_limit(const stru
 	case PTR_TO_STACK:
 		off = ptr_reg->off + ptr_reg->var_off.value;
 		if (mask_to_left)
-			*ptr_limit = MAX_BPF_STACK + off;
+			*ptr_limit = MAX_BPF_STACK + off + 1;
 		else
 			*ptr_limit = -off;
 		return 0;
 	case PTR_TO_MAP_VALUE:
 		if (mask_to_left) {
-			*ptr_limit = ptr_reg->umax_value + ptr_reg->off;
+			*ptr_limit = ptr_reg->umax_value + ptr_reg->off + 1;
 		} else {
 			off = ptr_reg->smin_value + ptr_reg->off;
 			*ptr_limit = ptr_reg->map_ptr->value_size - off;

From: Piotr Krysiuk <[email protected]>

commit b5871dca250cd391885218b99cc015aca1a51aea upstream.

Instead of having the mov32 with aux->alu_limit - 1 immediate, move this operation to retrieve_ptr_limit() instead to simplify the logic and to allow for subsequent sanity boundary checks inside retrieve_ptr_limit(). This avoids in future that at the time of the verifier masking rewrite we'd run into an underflow which would not sign extend due to the nature of mov32 instruction.

---
 kernel/bpf/verifier.c |   10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

@@ -2035,16 +2035,16 @@ static int retrieve_ptr_limit(const stru
 	case PTR_TO_STACK:
 		off = ptr_reg->off + ptr_reg->var_off.value;
 		if (mask_to_left)
-			*ptr_limit = MAX_BPF_STACK + off + 1;
+			*ptr_limit = MAX_BPF_STACK + off;
 		else
-			*ptr_limit = -off;
+			*ptr_limit = -off - 1;
 		return 0;
 	case PTR_TO_MAP_VALUE:
 		if (mask_to_left) {
-			*ptr_limit = ptr_reg->umax_value + ptr_reg->off + 1;
+			*ptr_limit = ptr_reg->umax_value + ptr_reg->off;
 		} else {
 			off = ptr_reg->smin_value + ptr_reg->off;
-			*ptr_limit = ptr_reg->map_ptr->value_size - off;
+			*ptr_limit = ptr_reg->map_ptr->value_size - off - 1;
 		}
 		return 0;
 	default:

@@ -4802,7 +4802,7 @@ static int fixup_bpf_calls(struct bpf_ve
 			off_reg = issrc ? insn->src_reg : insn->dst_reg;
 			if (isneg)
 				*patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1);
-			*patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit - 1);
+			*patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit);
 			*patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg);
 			*patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg);
 			*patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0);

From: Piotr Krysiuk <[email protected]>

commit f232326f6966cf2a1d1db7bc917a4ce5f9f55f76 upstream.

The purpose of this patch is to streamline error propagation and in particular to propagate retrieve_ptr_limit() errors for pointer types that are not defining a ptr_limit such that register-based alu ops against these types can be rejected.

The main rationale is that a gap has been identified by Piotr in the existing protection against speculatively out-of-bounds loads, for example, in case of ctx pointers, unprivileged programs can still perform pointer arithmetic. This can be abused to execute speculatively out-of-bounds loads without restrictions and thus extract contents of kernel memory.

Fix this by rejecting unprivileged programs that attempt any pointer arithmetic on unprotected pointer types. The two affected ones are pointer to ctx as well as pointer to map. Field access to a modified ctx' pointer is rejected at a later point in time in the verifier, and 7c6967326267 ("bpf: Permit map_ptr arithmetic with opcode add and offset 0") only relevant for root-only use cases. Risk of unprivileged program breakage is considered very low.

---
 kernel/bpf/verifier.c |   16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

@@ -2104,6 +2104,7 @@ static int sanitize_ptr_alu(struct bpf_v
 	u32 alu_state, alu_limit;
 	struct bpf_reg_state tmp;
 	bool ret;
+	int err;
 
 	if (can_skip_alu_sanitation(env, insn))
 		return 0;

@@ -2119,10 +2120,13 @@ static int sanitize_ptr_alu(struct bpf_v
 	alu_state |= ptr_is_dst_reg ?
 		     BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;
 
-	if (retrieve_ptr_limit(ptr_reg, &alu_limit, opcode, off_is_neg))
-		return 0;
-	if (update_alu_sanitation_state(aux, alu_state, alu_limit))
-		return -EACCES;
+	err = retrieve_ptr_limit(ptr_reg, &alu_limit, opcode, off_is_neg);
+	if (err < 0)
+		return err;
+
+	err = update_alu_sanitation_state(aux, alu_state, alu_limit);
+	if (err < 0)
+		return err;
 do_sim:
 	/* Simulate and find potential out-of-bounds access under
 	 * speculative execution from truncation as a result of

@@ -2215,7 +2219,7 @@ static int adjust_ptr_min_max_vals(struc
 	case BPF_ADD:
 		ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0);
 		if (ret < 0) {
-			verbose("R%d tried to add from different maps or paths\n", dst);
+			verbose("R%d tried to add from different maps, paths, or prohibited types\n", dst);
 			return ret;
 		}
 		/* We can take a fixed offset as long as it doesn't overflow

@@ -2270,7 +2274,7 @@ static int adjust_ptr_min_max_vals(struc
 	case BPF_SUB:
 		ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0);
 		if (ret < 0) {
-			verbose("R%d tried to sub from different maps or paths\n", dst);
+			verbose("R%d tried to sub from different maps, paths, or prohibited types\n", dst);
 			return ret;
 		}
 		if (dst_reg == off_reg) {

From: Rafael J. Wysocki <[email protected]>

commit 0cab893f409c53634d0d818fa414641cbcdb0dab upstream.

Revert commit 44cc89f76464 ("PM: runtime: Update device status before letting suppliers suspend") that introduced a race condition into __rpm_callback() which allowed a concurrent rpm_resume() to run and resume the device prematurely after its status had been changed to RPM_SUSPENDED by __rpm_callback().

---
 drivers/base/power/runtime.c |   62 +++++++++++++++++--------------------------
 1 file changed, 25 insertions(+), 37 deletions(-)

@@ -306,22 +306,22 @@ static void rpm_put_suppliers(struct dev
 static int __rpm_callback(int (*cb)(struct device *), struct device *dev)
 	__releases(&dev->power.lock) __acquires(&dev->power.lock)
 {
-	bool use_links = dev->power.links_count > 0;
-	bool get = false;
 	int retval, idx;
-	bool put;
+	bool use_links = dev->power.links_count > 0;
 
 	if (dev->power.irq_safe) {
 		spin_unlock(&dev->power.lock);
-	} else if (!use_links) {
-		spin_unlock_irq(&dev->power.lock);
 	} else {
-		get = dev->power.runtime_status == RPM_RESUMING;
-
 		spin_unlock_irq(&dev->power.lock);
 
-		/* Resume suppliers if necessary. */
-		if (get) {
+		/*
+		 * Resume suppliers if necessary.
+		 *
+		 * The device's runtime PM status cannot change until this
+		 * routine returns, so it is safe to read the status outside of
+		 * the lock.
+		 */
+		if (use_links && dev->power.runtime_status == RPM_RESUMING) {
 			idx = device_links_read_lock();
 
 			retval = rpm_get_suppliers(dev);

@@ -336,36 +336,24 @@ static int __rpm_callback(int (*cb)(stru
 
 	if (dev->power.irq_safe) {
 		spin_lock(&dev->power.lock);
-		return retval;
-	}
-
-	spin_lock_irq(&dev->power.lock);
-
-	if (!use_links)
-		return retval;
-
-	/*
-	 * If the device is suspending and the callback has returned success,
-	 * drop the usage counters of the suppliers that have been reference
-	 * counted on its resume.
-	 *
-	 * Do that if the resume fails too.
-	 */
-	put = dev->power.runtime_status == RPM_SUSPENDING && !retval;
-	if (put)
-		__update_runtime_status(dev, RPM_SUSPENDED);
-	else
-		put = get && retval;
-
-	if (put) {
-		spin_unlock_irq(&dev->power.lock);
-
-		idx = device_links_read_lock();
+	} else {
+		/*
+		 * If the device is suspending and the callback has returned
+		 * success, drop the usage counters of the suppliers that have
+		 * been reference counted on its resume.
+		 *
+		 * Do that if resume fails too.
+		 */
+		if (use_links
+		    && ((dev->power.runtime_status == RPM_SUSPENDING && !retval)
+		    || (dev->power.runtime_status == RPM_RESUMING && retval))) {
+			idx = device_links_read_lock();
 
-fail:
-		rpm_put_suppliers(dev);
+ fail:
+			rpm_put_suppliers(dev);
 
-		device_links_read_unlock(idx);
+			device_links_read_unlock(idx);
+		}
 
 		spin_lock_irq(&dev->power.lock);
 	}

From: Pavel Skripkin <[email protected]>

commit 093b036aa94e01a0bea31a38d7f0ee28a2749023 upstream.

syzbot found WARNING in __alloc_pages_nodemask()[1] when order >= MAX_ORDER. It was caused by a huge length value passed from userspace to qrtr_tun_write_iter(), which tries to allocate skb. Since the value comes from the untrusted source there is no need to raise a warning in __alloc_pages_nodemask().

[1] WARNING in __alloc_pages_nodemask+0x5f8/0x730 mm/page_alloc.c:5014

Call Trace:
 __alloc_pages include/linux/gfp.h:511 [inline]
 __alloc_pages_node include/linux/gfp.h:524 [inline]
 alloc_pages_node include/linux/gfp.h:538 [inline]
 kmalloc_large_node+0x60/0x110 mm/slub.c:3999
 __kmalloc_node_track_caller+0x319/0x3f0 mm/slub.c:4496
 __kmalloc_reserve net/core/skbuff.c:150 [inline]
 __alloc_skb+0x4e4/0x5a0 net/core/skbuff.c:210
 __netdev_alloc_skb+0x70/0x400 net/core/skbuff.c:446
 netdev_alloc_skb include/linux/skbuff.h:2832 [inline]
 qrtr_endpoint_post+0x84/0x11b0 net/qrtr/qrtr.c:442
 qrtr_tun_write_iter+0x11f/0x1a0 net/qrtr/tun.c:98
 call_write_iter include/linux/fs.h:1901 [inline]
 new_sync_write+0x426/0x650 fs/read_write.c:518
 vfs_write+0x791/0xa30 fs/read_write.c:605
 ksys_write+0x12d/0x250 fs/read_write.c:658
 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

---
 net/qrtr/qrtr.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -235,7 +235,7 @@ int qrtr_endpoint_post(struct qrtr_endpo
 	if (dst != QRTR_PORT_CTRL && type != QRTR_TYPE_DATA)
 		return -EINVAL;
 
-	skb = netdev_alloc_skb(NULL, len);
+	skb = __netdev_alloc_skb(NULL, len, GFP_ATOMIC | __GFP_NOWARN);
 	if (!skb)
 		return -ENOMEM;
 

From: Dinghao Liu <[email protected]>

commit 6dbbbe4cfd398704b72b21c1d4a5d3807e909d60 upstream.

There is one regmap_bulk_read() call in mpu3050_trigger_handler that we have caught its return value bug lack further handling. Check and terminate the execution flow just like the other three regmap_bulk_read() calls in this function.

---
 drivers/iio/gyro/mpu3050-core.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -549,6 +549,8 @@ static irqreturn_t mpu3050_trigger_handl
 					       MPU3050_FIFO_R,
 					       &fifo_values[offset],
 					       toread);
+			if (ret)
+				goto out_trigger_unlock;
 
 			dev_dbg(mpu3050->dev,
 				"%04x %04x %04x %04x %04x\n",

From: Ye Xiang <[email protected]>

commit d68c592e02f6f49a88e705f13dfc1883432cf300 upstream.

Currently, the proxy sensor scale is zero because it just return the exponent directly. To fix this issue, this patch use hid_sensor_format_scale to process the scale first then return the output.

---
 drivers/iio/light/hid-sensor-prox.c |   13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

@@ -37,6 +37,9 @@ struct prox_state {
 	struct hid_sensor_common common_attributes;
 	struct hid_sensor_hub_attribute_info prox_attr;
 	u32 human_presence;
+	int scale_pre_decml;
+	int scale_post_decml;
+	int scale_precision;
 };
 
 /* Channel definitions */

@@ -107,8 +110,9 @@ static int prox_read_raw(struct iio_dev
 		ret_type = IIO_VAL_INT;
 		break;
 	case IIO_CHAN_INFO_SCALE:
-		*val = prox_state->prox_attr.units;
-		ret_type = IIO_VAL_INT;
+		*val = prox_state->scale_pre_decml;
+		*val2 = prox_state->scale_post_decml;
+		ret_type = prox_state->scale_precision;
 		break;
 	case IIO_CHAN_INFO_OFFSET:
 		*val = hid_sensor_convert_exponent(

@@ -249,6 +253,11 @@ static int prox_parse_report(struct plat
 			HID_USAGE_SENSOR_HUMAN_PRESENCE,
 			&st->common_attributes.sensitivity);
 
+	st->scale_precision = hid_sensor_format_scale(
+				hsdev->usage,
+				&st->prox_attr,
+				&st->scale_pre_decml, &st->scale_post_decml);
+
 	return ret;
 }
 

From: Ye Xiang <[email protected]>

commit 141e7633aa4d2838d1f6ad5c74cccc53547c16ac upstream.

This patch fixes 2 issues of timestamp channel:
1. This patch ensures that there is sufficient space and correct alignment for the timestamp.
2. Correct the timestamp channel scan index.

---
 drivers/iio/temperature/hid-sensor-temperature.c |   14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

@@ -28,7 +28,10 @@
 struct temperature_state {
 	struct hid_sensor_common common_attributes;
 	struct hid_sensor_hub_attribute_info temperature_attr;
-	s32 temperature_data;
+	struct {
+		s32 temperature_data;
+		u64 timestamp __aligned(8);
+	} scan;
 	int scale_pre_decml;
 	int scale_post_decml;
 	int scale_precision;

@@ -45,7 +48,7 @@ static const struct iio_chan_spec temper
 			BIT(IIO_CHAN_INFO_SAMP_FREQ) |
 			BIT(IIO_CHAN_INFO_HYSTERESIS),
 	},
-	IIO_CHAN_SOFT_TIMESTAMP(3),
+	IIO_CHAN_SOFT_TIMESTAMP(1),
 };
 
 /* Adjust channel real bits based on report descriptor */

@@ -137,9 +140,8 @@ static int temperature_proc_event(struct
 	struct temperature_state *temp_st = iio_priv(indio_dev);
 
 	if (atomic_read(&temp_st->common_attributes.data_ready))
-		iio_push_to_buffers_with_timestamp(indio_dev,
-				&temp_st->temperature_data,
-				iio_get_time_ns(indio_dev));
+		iio_push_to_buffers_with_timestamp(indio_dev, &temp_st->scan,
+						   iio_get_time_ns(indio_dev));
 
 	return 0;
 }

@@ -154,7 +156,7 @@ static int temperature_capture_sample(st
 
 	switch (usage_id) {
 	case HID_USAGE_SENSOR_DATA_ENVIRONMENTAL_TEMPERATURE:
-		temp_st->temperature_data = *(s32 *)raw_data;
+		temp_st->scan.temperature_data = *(s32 *)raw_data;
 		return 0;
 	default:
 		return -EINVAL;

From: Kan Liang <[email protected]>

commit d88d05a9e0b6d9356e97129d4ff9942d765f46ea upstream.

A repeatable crash can be triggered by the perf_fuzzer on some Haswell system.
https://lore.kernel.org/lkml/[email protected]/

For some old CPUs (HSW and earlier), the PEBS status in a PEBS record may be mistakenly set to 0. To minimize the impact of the defect, the commit was introduced to try to avoid dropping the PEBS record for some cases. It adds a check in the intel_pmu_drain_pebs_nhm(), and updates the local pebs_status accordingly. However, it doesn't correct the PEBS status in the PEBS record, which may trigger the crash, especially for the large PEBS.

It's possible that all the PEBS records in a large PEBS have the PEBS status 0. If so, the first get_next_pebs_record_by_bit() in the __intel_pmu_pebs_event() returns NULL. The at = NULL. Since it's a large PEBS, the 'count' parameter must > 1. The second get_next_pebs_record_by_bit() will crash.

Besides the local pebs_status, correct the PEBS status in the PEBS record as well.

---
 arch/x86/events/intel/ds.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1515,7 +1515,7 @@ static void intel_pmu_drain_pebs_nhm(str
 		 */
 		if (!pebs_status && cpuc->pebs_enabled &&
 			!(cpuc->pebs_enabled & (cpuc->pebs_enabled-1)))
-			pebs_status = cpuc->pebs_enabled;
+			pebs_status = p->status = cpuc->pebs_enabled;
 
 		bit = find_first_bit((unsigned long *)&pebs_status,
 					x86_pmu.max_pebs_events);

From: Thomas Gleixner <[email protected]>

commit a501b048a95b79e1e34f03cac3c87ff1e9f229ad upstream.

Vitaly ran into an issue with hotplugging CPU0 on an Amazon instance where the matrix allocator claimed to be out of vectors. He analyzed it down to the point that IRQ2, the PIC cascade interrupt, which is supposed to be not ever routed to the IO/APIC ended up having an interrupt vector assigned which got moved during unplug of CPU0.

The underlying issue is that IRQ2 for various reasons (see commit af174783b925 ("x86: I/O APIC: Never configure IRQ2" for details) is treated as a reserved system vector by the vector core code and is not accounted as a regular vector. The Amazon BIOS has an routing entry of pin2 to IRQ2 which causes the IO/APIC setup to claim that interrupt which is granted by the vector domain because there is no sanity check. As a consequence the allocation counter of CPU0 underflows which causes a subsequent unplug to fail with:

[ ... ] CPU 0 has 4294967295 vectors, 589 available. Cannot disable CPU

There is another sanity check missing in the matrix allocator, but the underlying root cause is that the IO/APIC code lost the IRQ2 ignore logic during the conversion to irqdomains.

For almost 6 years nobody complained about this wreckage, which might indicate that this requirement could be lifted, but for any system which actually has a PIC IRQ2 is unusable by design so any routing entry has no effect and the interrupt cannot be connected to a device anyway.

Due to that and due to history biased paranoia reasons restore the IRQ2 ignore logic and treat it as non existent despite a routing entry claiming otherwise.

---
 arch/x86/kernel/apic/io_apic.c |   10 ++++++++++
 1 file changed, 10 insertions(+)

@@ -1042,6 +1042,16 @@ static int mp_map_pin_to_irq(u32 gsi, in
 	if (idx >= 0 && test_bit(mp_irqs[idx].srcbus, mp_bus_not_pci)) {
 		irq = mp_irqs[idx].srcbusirq;
 		legacy = mp_is_legacy_irq(irq);
+		/*
+		 * IRQ2 is unusable for historical reasons on systems which
+		 * have a legacy PIC. See the comment vs. IRQ2 further down.
+		 *
+		 * If this gets removed at some point then the related code
+		 * in lapic_assign_system_vectors() needs to be adjusted as
+		 * well.
+		 */
+		if (legacy && irq == PIC_CASCADE_IR)
+			return -EINVAL;
 	}
 
 	mutex_lock(&ioapic_mutex);

From: Oleg Nesterov <[email protected]>

commit 5abbe51a526253b9f003e9a0a195638dc882d660 upstream.

Preparation for fixing get_nr_restart_syscall() on X86 for COMPAT.

Add a new helper which sets restart_block->fn and calls a dummy arch_set_restart_data() helper.

---
 fs/select.c                    |   10 ++++------
 include/linux/thread_info.h    |   13 +++++++++++++
 kernel/futex.c                 |    3 +--
 kernel/time/alarmtimer.c       |    2 +-
 kernel/time/hrtimer.c          |    2 +-
 kernel/time/posix-cpu-timers.c |    2 +-
 6 files changed, 21 insertions(+), 11 deletions(-)

@@ -1006,10 +1006,9 @@ static long do_restart_poll(struct resta
 
 	ret = do_sys_poll(ufds, nfds, to);
 
-	if (ret == -EINTR) {
-		restart_block->fn = do_restart_poll;
-		ret = -ERESTART_RESTARTBLOCK;
-	}
+	if (ret == -EINTR)
+		ret = set_restart_fn(restart_block, do_restart_poll);
+
 	return ret;
 }
 

@@ -1031,7 +1030,6 @@ SYSCALL_DEFINE3(poll, struct pollfd __us
 		struct restart_block *restart_block;
 
 		restart_block = &current->restart_block;
-		restart_block->fn = do_restart_poll;
 		restart_block->poll.ufds = ufds;
 		restart_block->poll.nfds = nfds;
 

@@ -1042,7 +1040,7 @@ SYSCALL_DEFINE3(poll, struct pollfd __us
 		} else
 			restart_block->poll.has_timeout = 0;
 
-		ret = -ERESTART_RESTARTBLOCK;
+		ret = set_restart_fn(restart_block, do_restart_poll);
 	}
 	return ret;
 }

@@ -11,6 +11,7 @@
 #include <linux/types.h>
 #include <linux/bug.h>
 #include <linux/restart_block.h>
+#include <linux/errno.h>
 
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 /*

@@ -39,6 +40,18 @@ enum {
 
 #ifdef __KERNEL__
 
+#ifndef arch_set_restart_data
+#define arch_set_restart_data(restart) do { } while (0)
+#endif
+
+static inline long set_restart_fn(struct restart_block *restart,
+					long (*fn)(struct restart_block *))
+{
+	restart->fn = fn;
+	arch_set_restart_data(restart);
+	return -ERESTART_RESTARTBLOCK;
+}
+
 #ifndef THREAD_ALIGN
 #define THREAD_ALIGN	THREAD_SIZE
 #endif

@@ -2875,14 +2875,13 @@ retry:
 		goto out;
 
 	restart = &current->restart_block;
-	restart->fn = futex_wait_restart;
 	restart->futex.uaddr = uaddr;
 	restart->futex.val = val;
 	restart->futex.time = *abs_time;
 	restart->futex.bitset = bitset;
 	restart->futex.flags = flags | FLAGS_HAS_TIMEOUT;
 
-	ret = -ERESTART_RESTARTBLOCK;
+	ret = set_restart_fn(restart, futex_wait_restart);
 
 out:
 	if (to) {

@@ -822,9 +822,9 @@ static int alarm_timer_nsleep(const cloc
 	if (flags == TIMER_ABSTIME)
 		return -ERESTARTNOHAND;
 
-	restart->fn = alarm_timer_nsleep_restart;
 	restart->nanosleep.clockid = type;
 	restart->nanosleep.expires = exp;
+	set_restart_fn(restart, alarm_timer_nsleep_restart);
 	return ret;
 }
 

@@ -1545,9 +1545,9 @@ long hrtimer_nanosleep(const struct time
 	}
 
 	restart = &current->restart_block;
-	restart->fn = hrtimer_nanosleep_restart;
 	restart->nanosleep.clockid = t.timer.base->clockid;
 	restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer);
+	set_restart_fn(restart, hrtimer_nanosleep_restart);
 out:
 	destroy_hrtimer_on_stack(&t.timer);
 	return ret;

@@ -1348,8 +1348,8 @@ static int posix_cpu_nsleep(const clocki
 		if (flags & TIMER_ABSTIME)
 			return -ERESTARTNOHAND;
 
-		restart_block->fn = posix_cpu_nsleep_restart;
 		restart_block->nanosleep.clockid = which_clock;
+		set_restart_fn(restart_block, posix_cpu_nsleep_restart);
 	}
 	return error;
 }

From: Oleg Nesterov <[email protected]>

commit 66c1b6d74cd7035e85c426f0af4aede19e805c8a upstream.

Move TS_COMPAT back to asm/thread_info.h, close to TS_I386_REGS_POKED.

It was moved to asm/processor.h by b9d989c7218a ("x86/asm: Move the thread_info::status field to thread_struct"), then later 37a8f7c38339 ("x86/asm: Move 'status' from thread_struct to thread_info") moved the 'status' field back but TS_COMPAT was forgotten.

Preparatory patch to fix the COMPAT case for get_nr_restart_syscall()

---
 arch/x86/include/asm/processor.h   |    9 ---------
 arch/x86/include/asm/thread_info.h |    9 +++++++++
 2 files changed, 9 insertions(+), 9 deletions(-)

@@ -512,15 +512,6 @@ struct thread_struct {
 };
 
 /*
- * Thread-synchronous status.
- *
- * This is different from the flags in that nobody else
- * ever touches our thread-synchronous status, so we don't
- * have to worry about atomic accesses.
- */
-#define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
-
-/*
  * Set IOPL bits in EFLAGS from given mask
  */
 static inline void native_set_iopl_mask(unsigned mask)

@@ -229,6 +229,15 @@ static inline int arch_within_stack_fram
 
 #endif
 
+/*
+ * Thread-synchronous status.
+ *
+ * This is different from the flags in that nobody else
+ * ever touches our thread-synchronous status, so we don't
+ * have to worry about atomic accesses.
+ */
+#define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
+
 #ifdef CONFIG_COMPAT
 #define TS_I386_REGS_POKED	0x0004	/* regs poked by 32-bit ptracer */
 #endif

From: Dan Carpenter <[email protected]>

commit 19f1bc7edf0f97186810e13a88f5b62069d89097 upstream.

If copy_from_user() or kstrtoull() fail then the correct behavior is to return a negative error code.

---
 drivers/scsi/lpfc/lpfc_debugfs.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -1753,7 +1753,7 @@ lpfc_debugfs_dif_err_write(struct file *
 	memset(dstbuf, 0, 33);
 	size = (nbytes < 32) ? nbytes : 32;
 	if (copy_from_user(dstbuf, buf, size))
-		return 0;
+		return -EFAULT;
 
 	if (dent == phba->debug_InjErrLBA) {
 		if ((buf[0] == 'o') && (buf[1] == 'f') && (buf[2] == 'f'))

@@ -1761,7 +1761,7 @@ lpfc_debugfs_dif_err_write(struct file *
 	}
 
 	if ((tmp == 0) && (kstrtoull(dstbuf, 0, &tmp)))
-		return 0;
+		return -EINVAL;
 
 	if (dent == phba->debug_writeGuard)
 		phba->lpfc_injerr_wgrd_cnt = (uint32_t)tmp;

From: Oleg Nesterov <[email protected]>

commit 8c150ba2fb5995c84a7a43848250d444a3329a7d upstream.

The comment in get_nr_restart_syscall() says:

* The problem is that we can get here when ptrace pokes
* syscall-like values into regs even if we're not in a syscall
* at all.

Yes, but if not in a syscall then the

	status & (TS_COMPAT|TS_I386_REGS_POKED)

check below can't really help:

- TS_COMPAT can't be set

- TS_I386_REGS_POKED is only set if regs->orig_ax was changed by 32bit debugger; and even in this case get_nr_restart_syscall() is only correct if the tracee is 32bit too.

Suppose that a 64bit debugger plays with a 32bit tracee and

* Tracee calls sleep(2) // TS_COMPAT is set
* User interrupts the tracee by CTRL-C after 1 sec and does "(gdb) call func()"
* gdb saves the regs by PTRACE_GETREGS
* does PTRACE_SETREGS to set %rip='func' and %orig_rax=-1
* PTRACE_CONT // TS_COMPAT is cleared
* func() hits int3.
* Debugger catches SIGTRAP.
* Restore original regs by PTRACE_SETREGS.
* PTRACE_CONT

get_nr_restart_syscall() wrongly returns __NR_restart_syscall==219, the tracee calls ia32_sys_call_table[219] == sys_madvise.

Add the sticky TS_COMPAT_RESTART flag which survives after return to user mode. It's going to be removed in the next step again by storing the information in the restart block. As a further cleanup it might be possible to remove also TS_I386_REGS_POKED with that.

Test-case:

  $ cvs -d :pserver:anoncvs:[email protected]:/cvs/systemtap co ptrace-tests
  $ gcc -o erestartsys-trap-debuggee ptrace-tests/tests/erestartsys-trap-debuggee.c --m32
  $ gcc -o erestartsys-trap-debugger ptrace-tests/tests/erestartsys-trap-debugger.c -lutil
  $ ./erestartsys-trap-debugger
  Unexpected: retval 1, errno 22
  erestartsys-trap-debugger: ptrace-tests/tests/erestartsys-trap-debugger.c:421

---
 arch/x86/include/asm/thread_info.h |   14 +++++++++++++-
 arch/x86/kernel/signal.c           |   24 +-----------------------
 2 files changed, 14 insertions(+), 24 deletions(-)

@@ -238,10 +238,22 @@ static inline int arch_within_stack_fram
  */
 #define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
 
+#ifndef __ASSEMBLY__
 #ifdef CONFIG_COMPAT
 #define TS_I386_REGS_POKED	0x0004	/* regs poked by 32-bit ptracer */
+#define TS_COMPAT_RESTART	0x0008
+
+#define arch_set_restart_data	arch_set_restart_data
+
+static inline void arch_set_restart_data(struct restart_block *restart)
+{
+	struct thread_info *ti = current_thread_info();
+	if (ti->status & TS_COMPAT)
+		ti->status |= TS_COMPAT_RESTART;
+	else
+		ti->status &= ~TS_COMPAT_RESTART;
+}
 #endif
-#ifndef __ASSEMBLY__
 
 #ifdef CONFIG_X86_32
 #define in_ia32_syscall() true

@@ -769,30 +769,8 @@ handle_signal(struct ksignal *ksig, stru
 
 static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs)
 {
-	/*
-	 * This function is fundamentally broken as currently
-	 * implemented.
-	 *
-	 * The idea is that we want to trigger a call to the
-	 * restart_block() syscall and that we want in_ia32_syscall(),
-	 * in_x32_syscall(), etc. to match whatever they were in the
-	 * syscall being restarted.  We assume that the syscall
-	 * instruction at (regs->ip - 2) matches whatever syscall
-	 * instruction we used to enter in the first place.
-	 *
-	 * The problem is that we can get here when ptrace pokes
-	 * syscall-like values into regs even if we're not in a syscall
-	 * at all.
-	 *
-	 * For now, we maintain historical behavior and guess based on
-	 * stored state.  We could do better by saving the actual
-	 * syscall arch in restart_block or (with caveats on x32) by
-	 * checking if regs->ip points to 'int $0x80'.  The current
-	 * behavior is incorrect if a tracer has a different bitness
-	 * than the tracee.
-	 */
 #ifdef CONFIG_IA32_EMULATION
-	if (current_thread_info()->status & (TS_COMPAT|TS_I386_REGS_POKED))
+	if (current_thread_info()->status & TS_COMPAT_RESTART)
 		return __NR_ia32_restart_syscall;
 #endif
 #ifdef CONFIG_X86_X32_ABI

From: zhangyi (F) <[email protected]>

commit b7ff91fd030dc9d72ed91b1aab36e445a003af4f upstream.

If we failed to add new entry on rename whiteout, we cannot reset the old->de entry directly, because the old->de could have moved from under us during make indexed dir. So find the old entry again before reset is needed, otherwise it may corrupt the filesystem as below.

/dev/sda: Entry '00000001' in ??? (12) has deleted/unused inode 15. CLEARED. /dev/sda: Unattached inode 75
/dev/sda: UNEXPECTED INCONSISTENCY; RUN fsck MANUALLY.

---
 fs/ext4/namei.c |   29 +++++++++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)

@@ -3445,6 +3445,31 @@ static int ext4_setent(handle_t *handle,
 	return 0;
 }
 
+static void ext4_resetent(handle_t *handle, struct ext4_renament *ent,
+			  unsigned ino, unsigned file_type)
+{
+	struct ext4_renament old = *ent;
+	int retval = 0;
+
+	/*
+	 * old->de could have moved from under us during make indexed dir,
+	 * so the old->de may no longer valid and need to find it again
+	 * before reset old inode info.
+	 */
+	old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL);
+	if (IS_ERR(old.bh))
+		retval = PTR_ERR(old.bh);
+	if (!old.bh)
+		retval = -ENOENT;
+	if (retval) {
+		ext4_std_error(old.dir->i_sb, retval);
+		return;
+	}
+
+	ext4_setent(handle, &old, ino, file_type);
+	brelse(old.bh);
+}
+
 static int ext4_find_delete_entry(handle_t *handle, struct inode *dir,
 				  const struct qstr *d_name)
 {

@@ -3754,8 +3779,8 @@ static int ext4_rename(struct inode *old
 end_rename:
 	if (whiteout) {
 		if (retval) {
-			ext4_setent(handle, &old,
-				old.inode->i_ino, old_file_type);
+			ext4_resetent(handle, &old,
+				      old.inode->i_ino, old_file_type);
 			drop_nlink(whiteout);
 		}
 		unlock_new_inode(whiteout);

From: zhangyi (F) <[email protected]>

commit 6b22489911b726eebbf169caee52fea52013fbdd upstream.

Syzbot report a warning that ext4 may create an empty ea_inode if set an empty extent attribute to a file on the file system which is no free blocks left.

  WARNING: CPU: 6 PID: 10667 at fs/ext4/xattr.c:1640 ext4_xattr_set_entry+0x10f8/0x1114 fs/ext4/xattr.c:1640
  ...
  Call trace:
   ext4_xattr_set_entry+0x10f8/0x1114 fs/ext4/xattr.c:1640
   ext4_xattr_block_set+0x1d0/0x1b1c fs/ext4/xattr.c:1942
   ext4_xattr_set_handle+0x8a0/0xf1c fs/ext4/xattr.c:2390
   ext4_xattr_set+0x120/0x1f0 fs/ext4/xattr.c:2491
   ext4_xattr_trusted_set+0x48/0x5c fs/ext4/xattr_trusted.c:37
   __vfs_setxattr+0x208/0x23c fs/xattr.c:177
  ...

Now, ext4 try to store extent attribute into an external inode if ext4_xattr_block_set() return -ENOSPC, but for the case of store an empty extent attribute, store the extent entry into the extent attribute block is enough. A simple reproduce below.

fallocate test.img -l 1M
mkfs.ext4 -F -b 2048 -O ea_inode test.img
mount test.img /mnt
dd if=/dev/zero of=/mnt/foo bs=2048 count=500
setfattr -n "user.test" /mnt/foo

---
 fs/ext4/xattr.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -2418,7 +2418,7 @@ retry_inode:
 				 * external inode if possible.
 				 */
 				if (ext4_has_feature_ea_inode(inode->i_sb) &&
-				    !i.in_inode) {
+				    i.value_len && !i.in_inode) {
 					i.in_inode = 1;
 					goto retry_inode;
 				}

From: Shijie Luo <[email protected]>

commit 7d8bd3c76da1d94b85e6c9b7007e20e980bfcfe6 upstream.

If set_large_file = 1 and errors occur in ext4_handle_dirty_metadata(), the error code will be overridden, go to out_brelse to avoid this situation.

---
 fs/ext4/inode.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

@@ -5130,7 +5130,7 @@ static int ext4_do_update_inode(handle_t
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct buffer_head *bh = iloc->bh;
 	struct super_block *sb = inode->i_sb;
-	int err = 0, rc, block;
+	int err = 0, block;
 	int need_datasync = 0, set_large_file = 0;
 	uid_t i_uid;
 	gid_t i_gid;

@@ -5240,9 +5240,9 @@ static int ext4_do_update_inode(handle_t
 					      bh->b_data);
 
 	BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
-	rc = ext4_handle_dirty_metadata(handle, NULL, bh);
-	if (!err)
-		err = rc;
+	err = ext4_handle_dirty_metadata(handle, NULL, bh);
+	if (err)
+		goto out_brelse;
 	ext4_clear_inode_state(inode, EXT4_STATE_NEW);
 	if (set_large_file) {
 		BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get write access");

From: Thomas Gleixner <[email protected]>

commit 81e2073c175b887398e5bca6c004efa89983f58d upstream.

With interrupt force threading all device interrupt handlers are invoked from kernel threads. Contrary to hard interrupt context the invocation only disables bottom halfs, but not interrupts. This was an oversight back then because any code like this will have an issue:

thread(irq_A)
irq_handler(A)

    spin_lock(&foo->lock);

interrupt(irq_B)
irq_handler(B)

    spin_lock(&foo->lock);

This has been triggered with networking (NAPI vs. hrtimers) and console drivers where printk() happens from an interrupt which interrupted the force threaded handler.

Now people noticed and started to change the spin_lock() in the handler to spin_lock_irqsave() which affects performance or add IRQF_NOTHREAD to the interrupt request which in turn breaks RT.

Fix the root cause and not the symptom and disable interrupts before invoking the force threaded handler which preserves the regular semantics and the usefulness of the interrupt force threading as a general debugging tool.

For not RT this is not changing much, except that during the execution of the threaded handler interrupts are delayed until the handler returns. Vs. scheduling and softirq processing there is no difference.

For RT kernels there is no issue.

---
 kernel/irq/manage.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -916,11 +916,15 @@ irq_forced_thread_fn(struct irq_desc *de
 	irqreturn_t ret;
 
 	local_bh_disable();
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT_BASE))
+		local_irq_disable();
 	ret = action->thread_fn(action->irq, action->dev_id);
 	if (ret == IRQ_HANDLED)
 		atomic_inc(&desc->threads_handled);
 
 	irq_finalize_oneshot(desc, action);
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT_BASE))
+		local_irq_enable();
 	local_bh_enable();
 	return ret;
 }

From: Sagi Grimberg <[email protected]>

[ Upstream commit c4c6df5fc84659690d4391d1fba155cd94185295 ]

We only setup io queues for nvme controllers, and it makes absolutely no sense to allow a controller (re)connect without any I/O queues. If we happen to fail setting the queue count for any reason, we should not allow this to be a successful reconnect as I/O has no chance in going through. Instead just fail and schedule another reconnect.

---
 drivers/nvme/host/rdma.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

index 564e457f1345..57e1c0dd63c4 100644
@@ -655,8 +655,11 @@ static int nvme_rdma_alloc_io_queues(struct nvme_rdma_ctrl *ctrl)
 		return ret;
 
 	ctrl->ctrl.queue_count = nr_io_queues + 1;
-	if (ctrl->ctrl.queue_count < 2)
-		return 0;
+	if (ctrl->ctrl.queue_count < 2) {
+		dev_err(ctrl->ctrl.device,
+			"unable to set any I/O queues\n");
+		return -ENOMEM;
+	}
 
 	dev_info(ctrl->ctrl.device,
 		"creating %d I/O queues.\n", nr_io_queues);

2.30.1

From: Alan Stern <[email protected]>

commit 546aa0e4ea6ed81b6c51baeebc4364542fa3f3a7 upstream.

Matthias reports that the Amazon Kindle automatically removes its emulated media if it doesn't receive another SCSI command within about one second after a SYNCHRONIZE CACHE. It does so even when the host has sent a PREVENT MEDIUM REMOVAL command. The reason for this behavior isn't clear, although it's not hard to make some guesses.

At any rate, the results can be unexpected for anyone who tries to access the Kindle in an unusual fashion, and in theory they can lead to data loss (for example, if one file is closed and synchronized while other files are still in the middle of being written).

To avoid such problems, this patch creates a new usb-storage quirks flag telling the driver always to issue a REQUEST SENSE following a SYNCHRONIZE CACHE command, and adds an unusual_devs entry for the Kindle with the flag set. This is sufficient to prevent the Kindle from doing its automatic unload, without interfering with proper operation.

Another possible way to deal with this would be to increase the frequency of TEST UNIT READY polling that the kernel normally carries out for removable-media storage devices. However that would increase the overall load on the system and it is not as reliable, because the user can override the polling interval. Changing the driver's behavior is safer and has minimal overhead.

---
 drivers/usb/storage/transport.c    |    7 +++++++
 drivers/usb/storage/unusual_devs.h |   12 ++++++++++++
 include/linux/usb_usual.h          |    2 ++
 3 files changed, 21 insertions(+)

@@ -667,6 +667,13 @@ void usb_stor_invoke_transport(struct sc
 		need_auto_sense = 1;
 	}
 
+	/* Some devices (Kindle) require another command after SYNC CACHE */
+	if ((us->fflags & US_FL_SENSE_AFTER_SYNC) &&
+			srb->cmnd[0] == SYNCHRONIZE_CACHE) {
+		usb_stor_dbg(us, "-- sense after SYNC CACHE\n");
+		need_auto_sense = 1;
+	}
+
 	/*
 	 * If we have a failure, we're going to do a REQUEST_SENSE 
 	 * automatically.  Note that we differentiate between a command

@@ -2231,6 +2231,18 @@ UNUSUAL_DEV( 0x1908, 0x3335, 0x0200, 0x0
 		US_FL_NO_READ_DISC_INFO ),
 
 /*
+ * Reported by Matthias Schwarzott <[email protected]>
+ * The Amazon Kindle treats SYNCHRONIZE CACHE as an indication that
+ * the host may be finished with it, and automatically ejects its
+ * emulated media unless it receives another command within one second.
+ */
+UNUSUAL_DEV( 0x1949, 0x0004, 0x0000, 0x9999,
+		"Amazon",
+		"Kindle",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_SENSE_AFTER_SYNC ),
+
+/*
  * Reported by Oliver Neukum <[email protected]>
  * This device morphes spontaneously into another device if the access
  * pattern of Windows isn't followed. Thus writable media would be dirty

@@ -86,6 +86,8 @@
 		/* lies about caching, so always sync */	\
 	US_FLAG(NO_SAME, 0x40000000)				\
 		/* Cannot handle WRITE_SAME */			\
+	US_FLAG(SENSE_AFTER_SYNC, 0x80000000)			\
+		/* Do REQUEST_SENSE after SYNCHRONIZE_CACHE */	\
 
 #define US_FLAG(name, value)	US_FL_##name = value ,
 enum { US_DO_ALL_FLAGS };

From: Macpaul Lin <[email protected]>

commit 81c7462883b0cc0a4eeef0687f80ad5b5baee5f6 upstream.

Replace hardcoded maximum USB string length (126 bytes) by definition "USB_MAX_STRING_LEN".

---
 drivers/usb/gadget/composite.c |    4 ++--
 drivers/usb/gadget/configfs.c  |    2 +-
 drivers/usb/gadget/usbstring.c |    4 ++--
 include/uapi/linux/usb/ch9.h   |    3 +++
 4 files changed, 8 insertions(+), 5 deletions(-)

@@ -1080,7 +1080,7 @@ static void collect_langs(struct usb_gad
 	while (*sp) {
 		s = *sp;
 		language = cpu_to_le16(s->language);
-		for (tmp = buf; *tmp && tmp < &buf[126]; tmp++) {
+		for (tmp = buf; *tmp && tmp < &buf[USB_MAX_STRING_LEN]; tmp++) {
 			if (*tmp == language)
 				goto repeat;
 		}

@@ -1155,7 +1155,7 @@ static int get_string(struct usb_composi
 			collect_langs(sp, s->wData);
 		}
 
-		for (len = 0; len <= 126 && s->wData[len]; len++)
+		for (len = 0; len <= USB_MAX_STRING_LEN && s->wData[len]; len++)
 			continue;
 		if (!len)
 			return -EINVAL;

@@ -114,7 +114,7 @@ static int usb_string_copy(const char *s
 	char *str;
 	char *copy = *s_copy;
 	ret = strlen(s);
-	if (ret > 126)
+	if (ret > USB_MAX_STRING_LEN)
 		return -EOVERFLOW;
 
 	str = kstrdup(s, GFP_KERNEL);

@@ -59,9 +59,9 @@ usb_gadget_get_string (struct usb_gadget
 		return -EINVAL;
 
 	/* string descriptors have length, tag, then UTF16-LE text */
-	len = min ((size_t) 126, strlen (s->s));
+	len = min((size_t)USB_MAX_STRING_LEN, strlen(s->s));
 	len = utf8s_to_utf16s(s->s, len, UTF16_LITTLE_ENDIAN,
-			(wchar_t *) &buf[2], 126);
+			(wchar_t *) &buf[2], USB_MAX_STRING_LEN);
 	if (len < 0)
 		return -EINVAL;
 	buf [0] = (len + 1) * 2;

@@ -360,6 +360,9 @@ struct usb_config_descriptor {
 
 /*-------------------------------------------------------------------------*/
 
+/* USB String descriptors can contain at most 126 characters. */
+#define USB_MAX_STRING_LEN	126
+
 /* USB_DT_STRING: String descriptor */
 struct usb_string_descriptor {
 	__u8  bLength;

From: Jim Lin <[email protected]>

commit 98f153a10da403ddd5e9d98a3c8c2bb54bb5a0b6 upstream.

When gadget is disconnected, running sequence is like this. . composite_disconnect
. Call trace:

  usb_string_copy+0xd0/0x128
  gadget_config_name_configuration_store+0x4
  gadget_config_name_attr_store+0x40/0x50
  configfs_write_file+0x198/0x1f4
  vfs_write+0x100/0x220
  SyS_write+0x58/0xa8

. configfs_composite_unbind
. configfs_composite_bind

In configfs_composite_bind, it has
"cn->strings.s = cn->configuration;"

When usb_string_copy is invoked. it would
allocate memory, copy input string, release previous pointed memory space, and use new allocated memory.

When gadget is connected, host sends down request to get information.

Call trace:
  usb_gadget_get_string+0xec/0x168
  lookup_string+0x64/0x98
  composite_setup+0xa34/0x1ee8

If gadget is disconnected and connected quickly, in the failed case, cn->configuration memory has been released by usb_string_copy kfree but configfs_composite_bind hasn't been run in time to assign new allocated "cn->configuration" pointer to "cn->strings.s".

When "strlen(s->s) of usb_gadget_get_string is being executed, the dangling memory is accessed, "BUG: KASAN: use-after-free" error occurs.

---
 drivers/usb/gadget/configfs.c |   14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

@@ -108,6 +108,8 @@ struct gadget_config_name {
 	struct list_head list;
 };
 
+#define USB_MAX_STRING_WITH_NULL_LEN	(USB_MAX_STRING_LEN+1)
+
 static int usb_string_copy(const char *s, char **s_copy)
 {
 	int ret;

@@ -117,12 +119,16 @@ static int usb_string_copy(const char *s
 	if (ret > USB_MAX_STRING_LEN)
 		return -EOVERFLOW;
 
-	str = kstrdup(s, GFP_KERNEL);
-	if (!str)
-		return -ENOMEM;
+	if (copy) {
+		str = copy;
+	} else {
+		str = kmalloc(USB_MAX_STRING_WITH_NULL_LEN, GFP_KERNEL);
+		if (!str)
+			return -ENOMEM;
+	}
+	strcpy(str, s);
 	if (str[ret - 1] == '\n')
 		str[ret - 1] = '\0';
-	kfree(copy);
 	*s_copy = str;
 	return 0;
 }

From: Jonathan Albrieux <[email protected]>

commit 7d200b283aa049fcda0d43dd6e03e9e783d2799c upstream.

Checking at both msm8909-pm8916.dtsi and msm8916.dtsi from downstream it is indicated that "batt_id" channel has to be scaled with the default function:

	chan@31 {
		label = "batt_id";
		reg = <0x31>;
		qcom,decimation = <0>;
		qcom,pre-div-channel-scaling = <0>;
		qcom,calibration-type = "ratiometric";
		qcom,scale-function = <0>;
		qcom,hw-settle-time = <0xb>;
		qcom,fast-avg-setup = <0>;
	};

Change LR_MUX2_BAT_ID scaling accordingly.

---
 drivers/iio/adc/qcom-spmi-vadc.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -607,7 +607,7 @@ static const struct vadc_channels vadc_c
 	VADC_CHAN_NO_SCALE(P_MUX16_1_3, 1)
 
 	VADC_CHAN_NO_SCALE(LR_MUX1_BAT_THERM, 0)
-	VADC_CHAN_NO_SCALE(LR_MUX2_BAT_ID, 0)
+	VADC_CHAN_VOLT(LR_MUX2_BAT_ID, 0, SCALE_DEFAULT)
 	VADC_CHAN_NO_SCALE(LR_MUX3_XO_THERM, 0)
 	VADC_CHAN_NO_SCALE(LR_MUX4_AMUX_THM1, 0)
 	VADC_CHAN_NO_SCALE(LR_MUX5_AMUX_THM2, 0)

From: Jan Kara <[email protected]>

commit ce9f24cccdc019229b70a5c15e2b09ad9c0ab5d1 upstream.

Currently, system zones just track ranges of block, that are "important" fs metadata (bitmaps, group descriptors, journal blocks, etc.). This however complicates how extent tree (or indirect blocks) can be checked for inodes that actually track such metadata - currently the journal inode but arguably we should be treating quota files or resize inode similarly. We cannot run __ext4_ext_check() on such metadata inodes when loading their extents as that would immediately trigger the validity checks and so we just hack around that and special-case the journal inode. This however leads to a situation that a journal inode which has extent tree of depth at least one can have invalid extent tree that gets unnoticed until ext4_cache_extents() crashes.

To overcome this limitation, track inode number each system zone belongs to (0 is used for zones not belonging to any inode). We can then verify inode number matches the expected one when verifying extent tree and thus avoid the false errors. With this there's no need to to special-case journal inode during extent tree checking anymore so remove it.

---
 fs/ext4/block_validity.c |   37 +++++++++++++++++++++----------------
 fs/ext4/ext4.h           |    6 +++---
 fs/ext4/extents.c        |   16 ++++++----------
 fs/ext4/indirect.c       |    6 ++----
 fs/ext4/inode.c          |    5 ++---
 fs/ext4/mballoc.c        |    4 ++--
 6 files changed, 36 insertions(+), 38 deletions(-)

@@ -24,6 +24,7 @@ struct ext4_system_zone {
 	struct rb_node	node;
 	ext4_fsblk_t	start_blk;
 	unsigned int	count;
+	u32		ino;
 };
 
 static struct kmem_cache *ext4_system_zone_cachep;

@@ -44,7 +45,8 @@ void ext4_exit_system_zone(void)
 static inline int can_merge(struct ext4_system_zone *entry1,
 		     struct ext4_system_zone *entry2)
 {
-	if ((entry1->start_blk + entry1->count) == entry2->start_blk)
+	if ((entry1->start_blk + entry1->count) == entry2->start_blk &&
+	    entry1->ino == entry2->ino)
 		return 1;
 	return 0;
 }

@@ -56,7 +58,7 @@ static inline int can_merge(struct ext4_
  */
 static int add_system_zone(struct ext4_sb_info *sbi,
 			   ext4_fsblk_t start_blk,
-			   unsigned int count)
+			   unsigned int count, u32 ino)
 {
 	struct ext4_system_zone *new_entry, *entry;
 	struct rb_node **n = &sbi->system_blks.rb_node, *node;

@@ -79,6 +81,7 @@ static int add_system_zone(struct ext4_s
 		return -ENOMEM;
 	new_entry->start_blk = start_blk;
 	new_entry->count = count;
+	new_entry->ino = ino;
 	new_node = &new_entry->node;
 
 	rb_link_node(new_node, parent, n);

@@ -154,16 +157,16 @@ static int ext4_protect_reserved_inode(s
 		if (n == 0) {
 			i++;
 		} else {
-			if (!ext4_data_block_valid(sbi, map.m_pblk, n)) {
-				ext4_error(sb, "blocks %llu-%llu from inode %u "
+			err = add_system_zone(sbi, map.m_pblk, n, ino);
+			if (err < 0) {
+				if (err == -EFSCORRUPTED) {
+					ext4_error(sb,
+					   "blocks %llu-%llu from inode %u "
 					   "overlap system zone", map.m_pblk,
 					   map.m_pblk + map.m_len - 1, ino);
-				err = -EFSCORRUPTED;
+				}
 				break;
 			}
-			err = add_system_zone(sbi, map.m_pblk, n);
-			if (err < 0)
-				break;
 			i += n;
 		}
 	}

@@ -192,16 +195,16 @@ int ext4_setup_system_zone(struct super_
 		if (ext4_bg_has_super(sb, i) &&
 		    ((i < 5) || ((i % flex_size) == 0)))
 			add_system_zone(sbi, ext4_group_first_block_no(sb, i),
-					ext4_bg_num_gdb(sb, i) + 1);
+					ext4_bg_num_gdb(sb, i) + 1, 0);
 		gdp = ext4_get_group_desc(sb, i, NULL);
-		ret = add_system_zone(sbi, ext4_block_bitmap(sb, gdp), 1);
+		ret = add_system_zone(sbi, ext4_block_bitmap(sb, gdp), 1, 0);
 		if (ret)
 			return ret;
-		ret = add_system_zone(sbi, ext4_inode_bitmap(sb, gdp), 1);
+		ret = add_system_zone(sbi, ext4_inode_bitmap(sb, gdp), 1, 0);
 		if (ret)
 			return ret;
 		ret = add_system_zone(sbi, ext4_inode_table(sb, gdp),
-				sbi->s_itb_per_group);
+				sbi->s_itb_per_group, 0);
 		if (ret)
 			return ret;
 	}

@@ -234,10 +237,11 @@ void ext4_release_system_zone(struct sup
  * start_blk+count) is valid; 0 if some part of the block region
  * overlaps with filesystem metadata blocks.
  */
-int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk,
-			  unsigned int count)
+int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk,
+			   unsigned int count)
 {
 	struct ext4_system_zone *entry;
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct rb_node *n = sbi->system_blks.rb_node;
 
 	if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) ||

@@ -253,6 +257,8 @@ int ext4_data_block_valid(struct ext4_sb
 		else if (start_blk >= (entry->start_blk + entry->count))
 			n = n->rb_right;
 		else {
+			if (entry->ino == inode->i_ino)
+				return 1;
 			sbi->s_es->s_last_error_block = cpu_to_le64(start_blk);
 			return 0;
 		}

@@ -275,8 +281,7 @@ int ext4_check_blockref(const char *func
 	while (bref < p+max) {
 		blk = le32_to_cpu(*bref++);
 		if (blk &&
-		    unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb),
-						    blk, 1))) {
+		    unlikely(!ext4_inode_block_valid(inode, blk, 1))) {
 			es->s_last_error_block = cpu_to_le64(blk);
 			ext4_error_inode(inode, function, line, blk,
 					 "invalid block");

@@ -3151,9 +3151,9 @@ extern void ext4_release_system_zone(str
 extern int ext4_setup_system_zone(struct super_block *sb);
 extern int __init ext4_init_system_zone(void);
 extern void ext4_exit_system_zone(void);
-extern int ext4_data_block_valid(struct ext4_sb_info *sbi,
-				 ext4_fsblk_t start_blk,
-				 unsigned int count);
+extern int ext4_inode_block_valid(struct inode *inode,
+				  ext4_fsblk_t start_blk,
+				  unsigned int count);
 extern int ext4_check_blockref(const char *, unsigned int,
 			       struct inode *, __le32 *, unsigned int);
 

@@ -389,7 +389,7 @@ static int ext4_valid_extent(struct inod
 	 */
 	if (lblock + len <= lblock)
 		return 0;
-	return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
+	return ext4_inode_block_valid(inode, block, len);
 }
 
 static int ext4_valid_extent_idx(struct inode *inode,

@@ -397,7 +397,7 @@ static int ext4_valid_extent_idx(struct
 {
 	ext4_fsblk_t block = ext4_idx_pblock(ext_idx);
 
-	return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, 1);
+	return ext4_inode_block_valid(inode, block, 1);
 }
 
 static int ext4_valid_extent_entries(struct inode *inode,

@@ -554,14 +554,10 @@ __read_extent_tree_block(const char *fun
 	}
 	if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE))
 		return bh;
-	if (!ext4_has_feature_journal(inode->i_sb) ||
-	    (inode->i_ino !=
-	     le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) {
-		err = __ext4_ext_check(function, line, inode,
-				       ext_block_hdr(bh), depth, pblk);
-		if (err)
-			goto errout;
-	}
+	err = __ext4_ext_check(function, line, inode,
+			       ext_block_hdr(bh), depth, pblk);
+	if (err)
+		goto errout;
 	set_buffer_verified(bh);
 	/*
 	 * If this is a leaf block, cache all of its entries

@@ -842,8 +842,7 @@ static int ext4_clear_blocks(handle_t *h
 	else if (ext4_should_journal_data(inode))
 		flags |= EXT4_FREE_BLOCKS_FORGET;
 
-	if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), block_to_free,
-				   count)) {
+	if (!ext4_inode_block_valid(inode, block_to_free, count)) {
 		EXT4_ERROR_INODE(inode, "attempt to clear invalid "
 				 "blocks %llu len %lu",
 				 (unsigned long long) block_to_free, count);

@@ -1005,8 +1004,7 @@ static void ext4_free_branches(handle_t
 			if (!nr)
 				continue;		/* A hole */
 
-			if (!ext4_data_block_valid(EXT4_SB(inode->i_sb),
-						   nr, 1)) {
+			if (!ext4_inode_block_valid(inode, nr, 1)) {
 				EXT4_ERROR_INODE(inode,
 						 "invalid indirect mapped "
 						 "block %lu (level %d)",

@@ -420,8 +420,7 @@ static int __check_block_validity(struct
 	    (inode->i_ino ==
 	     le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum)))
 		return 0;
-	if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk,
-				   map->m_len)) {
+	if (!ext4_inode_block_valid(inode, map->m_pblk, map->m_len)) {
 		ext4_error_inode(inode, func, line, map->m_pblk,
 				 "lblock %lu mapped to illegal pblock %llu "
 				 "(length %d)", (unsigned long) map->m_lblk,

@@ -4940,7 +4939,7 @@ struct inode *__ext4_iget(struct super_b
 
 	ret = 0;
 	if (ei->i_file_acl &&
-	    !ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) {
+	    !ext4_inode_block_valid(inode, ei->i_file_acl, 1)) {
 		ext4_error_inode(inode, function, line, 0,
 				 "iget: bad extended attribute block %llu",
 				 ei->i_file_acl);

@@ -3017,7 +3017,7 @@ ext4_mb_mark_diskspace_used(struct ext4_
 	block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex);
 
 	len = EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
-	if (!ext4_data_block_valid(sbi, block, len)) {
+	if (!ext4_inode_block_valid(ac->ac_inode, block, len)) {
 		ext4_error(sb, "Allocating blocks %llu-%llu which overlap "
 			   "fs metadata", block, block+len);
 		/* File system mounted not to panic on error

@@ -4783,7 +4783,7 @@ void ext4_free_blocks(handle_t *handle,
 
 	sbi = EXT4_SB(sb);
 	if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) &&
-	    !ext4_data_block_valid(sbi, block, count)) {
+	    !ext4_inode_block_valid(inode, block, count)) {
 		ext4_error(sb, "Freeing blocks not in datazone - "
 			   "block = %llu, count = %lu", block, count);
 		goto error_return;

From: Daniel Kobras <[email protected]>

commit f1442d6349a2e7bb7a6134791bdc26cb776c79af upstream.

If an auth module's accept op returns SVC_CLOSE, svc_process_common() enters a call path that does not call svc_authorise() before leaving the function, and thus leaks a reference on the auth module's refcount. Hence, make sure calls to svc_authenticate() and svc_authorise() are paired for all call paths, to make sure rpc auth modules can be unloaded.

---
 net/sunrpc/svc.c |    6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

@@ -1329,7 +1329,7 @@ svc_process_common(struct svc_rqst *rqst
 
  sendit:
 	if (svc_authorise(rqstp))
-		goto close;
+		goto close_xprt;
 	return 1;		/* Caller can now send it */
 
  dropit:

@@ -1338,6 +1338,8 @@ svc_process_common(struct svc_rqst *rqst
 	return 0;
 
  close:
+	svc_authorise(rqstp);
+close_xprt:
 	if (rqstp->rq_xprt && test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags))
 		svc_close_xprt(rqstp->rq_xprt);
 	dprintk("svc: svc_process close\n");

@@ -1346,7 +1348,7 @@ svc_process_common(struct svc_rqst *rqst
 err_short_len:
 	svc_printk(rqstp, "short len %zd, dropping request\n",
 			argv->iov_len);
-	goto close;
+	goto close_xprt;
 
 err_bad_rpc:
 	serv->sv_stats->rpcbadfmt++;

From: Jonathan Cameron <[email protected]>

commit 121875b28e3bd7519a675bf8ea2c2e793452c2bd upstream.

Seems that there are config combinations in which this driver gets enabled and hence selects the MFD, but with out HAS_IOMEM getting pulled in via some other route. MFD is entirely contained in an
if HAS_IOMEM block, leading to the build issue in this bugzilla.

https://bugzilla.kernel.org/show_bug.cgi?id=209889

---
 drivers/iio/adc/Kconfig |    1 +
 1 file changed, 1 insertion(+)

@@ -635,6 +635,7 @@ config STM32_ADC_CORE
 	depends on HAS_DMA
 	depends on OF
 	depends on REGULATOR
+	depends on HAS_IOMEM
 	select IIO_BUFFER
 	select MFD_STM32_TIMERS
 	select IIO_STM32_TIMER_TRIGGER

From: Dan Carpenter <[email protected]>

commit a71266e454b5df10d019b06f5ebacd579f76be28 upstream.

This is to silence a new Smatch warning:

drivers/iio/imu/adis16400.c:492 adis16400_initial_setup()
warn: sscanf doesn't return error codes

If the condition "if (st->variant->flags & ADIS16400_HAS_SLOW_MODE) {" is false then we return 1 instead of returning 0 and probe will fail.

---
 drivers/iio/imu/adis16400_core.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

@@ -288,8 +288,7 @@ static int adis16400_initial_setup(struc
 		if (ret)
 			goto err_ret;
 
-		ret = sscanf(indio_dev->name, "adis%u\n", &device_id);
-		if (ret != 1) {
+		if (sscanf(indio_dev->name, "adis%u\n", &device_id) != 1) {
 			ret = -EINVAL;
 			goto err_ret;
 		}

From: Piotr Krysiuk <[email protected]>

commit 1b1597e64e1a610c7a96710fc4717158e98a08b3 upstream.

Given we know the max possible value of ptr_limit at the time of retrieving the latter, add basic assertions, so that the verifier can bail out if anything looks odd and reject the program. Nothing triggered this so far, but it also does not hurt to have these.

---
 kernel/bpf/verifier.c |   11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

@@ -2029,24 +2029,29 @@ static int retrieve_ptr_limit(const stru
 {
 	bool mask_to_left = (opcode == BPF_ADD &&  off_is_neg) ||
 			    (opcode == BPF_SUB && !off_is_neg);
-	u32 off;
+	u32 off, max;
 
 	switch (ptr_reg->type) {
 	case PTR_TO_STACK:
+		/* Offset 0 is out-of-bounds, but acceptable start for the
+		 * left direction, see BPF_REG_FP.
+		 */
+		max = MAX_BPF_STACK + mask_to_left;
 		off = ptr_reg->off + ptr_reg->var_off.value;
 		if (mask_to_left)
 			*ptr_limit = MAX_BPF_STACK + off;
 		else
 			*ptr_limit = -off - 1;
-		return 0;
+		return *ptr_limit >= max ? -ERANGE : 0;
 	case PTR_TO_MAP_VALUE:
+		max = ptr_reg->map_ptr->value_size;
 		if (mask_to_left) {
 			*ptr_limit = ptr_reg->umax_value + ptr_reg->off;
 		} else {
 			off = ptr_reg->smin_value + ptr_reg->off;
 			*ptr_limit = ptr_reg->map_ptr->value_size - off - 1;
 		}
-		return 0;
+		return *ptr_limit >= max ? -ERANGE : 0;
 	default:
 		return -EINVAL;
 	}

From: Florian Fainelli <[email protected]>

commit f9b3827ee66cfcf297d0acd6ecf33653a5f297ef upstream.

Add support for being able to set the learning attribute on port, and make sure that the standalone ports start up with learning disabled.

We can remove the code in bcm_sf2 that configured the ports learning attribute because we want the standalone ports to have learning disabled by default and port 7 cannot be bridged, so its learning attribute will not change past its initial configuration.

---
 drivers/net/dsa/b53/b53_common.c |   20 ++++++++++++++++++++
 drivers/net/dsa/b53/b53_regs.h   |    1 +
 drivers/net/dsa/bcm_sf2.c        |    5 +++++
 drivers/net/dsa/bcm_sf2_regs.h   |    2 ++
 4 files changed, 28 insertions(+)

@@ -501,6 +501,19 @@ static void b53_imp_vlan_setup(struct ds
 	}
 }
 
+static void b53_port_set_learning(struct b53_device *dev, int port,
+				  bool learning)
+{
+	u16 reg;
+
+	b53_read16(dev, B53_CTRL_PAGE, B53_DIS_LEARNING, &reg);
+	if (learning)
+		reg &= ~BIT(port);
+	else
+		reg |= BIT(port);
+	b53_write16(dev, B53_CTRL_PAGE, B53_DIS_LEARNING, reg);
+}
+
 static int b53_enable_port(struct dsa_switch *ds, int port,
 			   struct phy_device *phy)
 {

@@ -508,6 +521,8 @@ static int b53_enable_port(struct dsa_sw
 	unsigned int cpu_port = dev->cpu_port;
 	u16 pvlan;
 
+	b53_port_set_learning(dev, port, false);
+
 	/* Clear the Rx and Tx disable bits and set to no spanning tree */
 	b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), 0);
 

@@ -551,6 +566,8 @@ static void b53_enable_cpu_port(struct b
 		    PORT_CTRL_RX_MCST_EN |
 		    PORT_CTRL_RX_UCST_EN;
 	b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(cpu_port), port_ctrl);
+
+	b53_port_set_learning(dev, cpu_port, false);
 }
 
 static void b53_enable_mib(struct b53_device *dev)

@@ -1342,6 +1359,8 @@ int b53_br_join(struct dsa_switch *ds, i
 	b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), pvlan);
 	dev->ports[port].vlan_ctl_mask = pvlan;
 
+	b53_port_set_learning(dev, port, true);
+
 	return 0;
 }
 EXPORT_SYMBOL(b53_br_join);

@@ -1392,6 +1411,7 @@ void b53_br_leave(struct dsa_switch *ds,
 		vl->untag |= BIT(port) | BIT(dev->cpu_port);
 		b53_set_vlan_entry(dev, pvid, vl);
 	}
+	b53_port_set_learning(dev, port, false);
 }
 EXPORT_SYMBOL(b53_br_leave);
 

@@ -112,6 +112,7 @@
 #define B53_UC_FLOOD_MASK		0x32
 #define B53_MC_FLOOD_MASK		0x34
 #define B53_IPMC_FLOOD_MASK		0x36
+#define B53_DIS_LEARNING		0x3c
 
 /*
  * Override Ports 0-7 State on devices with xMII interfaces (8 bit)

@@ -252,6 +252,11 @@ static int bcm_sf2_port_setup(struct dsa
 	reg &= ~P_TXQ_PSM_VDD(port);
 	core_writel(priv, reg, CORE_MEM_PSM_VDD_CTRL);
 
+	/* Disable learning */
+	reg = core_readl(priv, CORE_DIS_LEARN);
+	reg |= BIT(port);
+	core_writel(priv, reg, CORE_DIS_LEARN);
+
 	/* Enable Broadcom tags for that port if requested */
 	if (priv->brcm_tag_mask & BIT(port))
 		bcm_sf2_brcm_hdr_setup(priv, port);

@@ -150,6 +150,8 @@ enum bcm_sf2_reg_offs {
 #define CORE_SWITCH_CTRL		0x00088
 #define  MII_DUMB_FWDG_EN		(1 << 6)
 
+#define CORE_DIS_LEARN			0x000f0
+
 #define CORE_SFT_LRN_CTRL		0x000f8
 #define  SW_LEARN_CNTL(x)		(1 << (x))
 

From: Ye Xiang <[email protected]>

commit 37e89e574dc238a4ebe439543c5ab4fbb2f0311b upstream.

This patch ensures that, there is sufficient space and correct alignment for the timestamp.

---
 drivers/iio/humidity/hid-sensor-humidity.c |   12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

@@ -28,7 +28,10 @@
 struct hid_humidity_state {
 	struct hid_sensor_common common_attributes;
 	struct hid_sensor_hub_attribute_info humidity_attr;
-	s32 humidity_data;
+	struct {
+		s32 humidity_data;
+		u64 timestamp __aligned(8);
+	} scan;
 	int scale_pre_decml;
 	int scale_post_decml;
 	int scale_precision;

@@ -139,9 +142,8 @@ static int humidity_proc_event(struct hi
 	struct hid_humidity_state *humid_st = iio_priv(indio_dev);
 
 	if (atomic_read(&humid_st->common_attributes.data_ready))
-		iio_push_to_buffers_with_timestamp(indio_dev,
-					&humid_st->humidity_data,
-					iio_get_time_ns(indio_dev));
+		iio_push_to_buffers_with_timestamp(indio_dev, &humid_st->scan,
+						   iio_get_time_ns(indio_dev));
 
 	return 0;
 }

@@ -156,7 +158,7 @@ static int humidity_capture_sample(struc
 
 	switch (usage_id) {
 	case HID_USAGE_SENSOR_ATMOSPHERIC_HUMIDITY:
-		humid_st->humidity_data = *(s32 *)raw_data;
+		humid_st->scan.humidity_data = *(s32 *)raw_data;
 
 		return 0;
 	default:

From: Tyrel Datwyler <[email protected]>

commit cc7a0bb058b85ea03db87169c60c7cfdd5d34678 upstream.

Both add_slot_store() and remove_slot_store() try to fix up the drc_name copied from the store buffer by placing a NUL terminator at nbyte + 1 or in place of a '\n' if present. However, the static buffer that we copy the drc_name data into is not zeroed and can contain anything past the n-th byte.

This is problematic if a '\n' byte appears in that buffer after nbytes and the string copied into the store buffer was not NUL terminated to start with as the strchr() search for a '\n' byte will mark this incorrectly as the end of the drc_name string resulting in a drc_name string that contains garbage data after the n-th byte.

Additionally it will cause us to overwrite that '\n' byte on the stack with NUL, potentially corrupting data on the stack.

The following debugging shows an example of the drmgr utility writing "PHB 4543" to the add_slot sysfs attribute, but add_slot_store() logging a corrupted string value.

drmgr: drmgr: -c phb -a -s PHB 4543 -d 1
add_slot_store: drc_name = PHB 4543°|<82>!, rc = -19

Fix this by using strscpy() instead of memcpy() to ensure the string is NUL terminated when copied into the static drc_name buffer. Further, since the string is now NUL terminated the code only needs to change '\n' to '\0' when present.

---
 drivers/pci/hotplug/rpadlpar_sysfs.c |   14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

@@ -39,12 +39,11 @@ static ssize_t add_slot_store(struct kob
 	if (nbytes >= MAX_DRC_NAME_LEN)
 		return 0;
 
-	memcpy(drc_name, buf, nbytes);
+	strscpy(drc_name, buf, nbytes + 1);
 
 	end = strchr(drc_name, '\n');
-	if (!end)
-		end = &drc_name[nbytes];
-	*end = '\0';
+	if (end)
+		*end = '\0';
 
 	rc = dlpar_add_slot(drc_name);
 	if (rc)

@@ -70,12 +69,11 @@ static ssize_t remove_slot_store(struct
 	if (nbytes >= MAX_DRC_NAME_LEN)
 		return 0;
 
-	memcpy(drc_name, buf, nbytes);
+	strscpy(drc_name, buf, nbytes + 1);
 
 	end = strchr(drc_name, '\n');
-	if (!end)
-		end = &drc_name[nbytes];
-	*end = '\0';
+	if (end)
+		*end = '\0';
 
 	rc = dlpar_remove_slot(drc_name);
 	if (rc)

From: Sagi Grimberg <[email protected]>

commit d218a8a3003e84ab136e69a4e30dd4ec7dab2d22 upstream.

"Controller Configuration, these fields are defined as parameters to
configure an "I/O Controller (IOC)" and not to configure a "Discovery Controller (DC).

...
If the controller does not support I/O queues, then this field shall be read-only with a value of 0h

Just perform this check for I/O controllers.

---
 drivers/nvme/target/core.c |   17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

@@ -594,9 +594,20 @@ static void nvmet_start_ctrl(struct nvme
 {
 	lockdep_assert_held(&ctrl->lock);
 
-	if (nvmet_cc_iosqes(ctrl->cc) != NVME_NVM_IOSQES ||
-	    nvmet_cc_iocqes(ctrl->cc) != NVME_NVM_IOCQES ||
-	    nvmet_cc_mps(ctrl->cc) != 0 ||
+	/*
+	 * Only I/O controllers should verify iosqes,iocqes.
+	 * Strictly speaking, the spec says a discovery controller
+	 * should verify iosqes,iocqes are zeroed, however that
+	 * would break backwards compatibility, so don't enforce it.
+	 */
+	if (ctrl->subsys->type != NVME_NQN_DISC &&
+	    (nvmet_cc_iosqes(ctrl->cc) != NVME_NVM_IOSQES ||
+	     nvmet_cc_iocqes(ctrl->cc) != NVME_NVM_IOCQES)) {
+		ctrl->csts = NVME_CSTS_CFS;
+		return;
+	}
+
+	if (nvmet_cc_mps(ctrl->cc) != 0 ||
 	    nvmet_cc_ams(ctrl->cc) != 0 ||
 	    nvmet_cc_css(ctrl->cc) != 0) {
 		ctrl->csts = NVME_CSTS_CFS;

All tests passing for Tegra ...

Test results for stable-v4.14:

    8 builds:	8 pass, 0 fail
    16 boots:	16 pass, 0 fail
    34 tests:	34 pass, 0 fail

Linux version: 4.14.227-rc1-gdbfdb55a0970
Boards tested: tegra124-jetson-tk1, tegra20-ventana,

                tegra210-p2371-2180, tegra30-cardhu-a04

Jon

Build results:

	total: 168 pass: 168 fail: 0
Qemu test results:
	total: 406 pass: 406 fail: 0

Guenter

Results from Linaro’s test farm.
No regressions on arm64, arm, x86_64, and i386.

Summary
------------------------------------------------------------------------

kernel: 4.14.227-rc1
git: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git
git branch: linux-4.14.y
git commit: dbfdb55a0970570a02a8d7bb6abc2e4db71218c8
git describe: v4.14.226-44-gdbfdb55a0970
Test details: https://qa-reports.linaro.org/lkft/linux-stable-rc-linux-4.14.y/build/v4.14.226-44-gdbfdb55a0970

No regressions (compared to v4.14.226-8-g085047cda613)

No fixes (compared to v4.14.226-8-g085047cda613)

Ran 48680 total tests in the following environments and test suites.

Environments
--------------
- arm
- arm64
- dragonboard-410c - arm64
- hi6220-hikey - arm64
- i386
- juno-r2 - arm64
- juno-r2-compat
- juno-r2-kasan
- mips
- nxp-ls2088
- nxp-ls2088-64k_page_size
- powerpc
- qemu-arm-debug
- qemu-arm64-clang
- qemu-arm64-debug
- qemu-arm64-kasan
- qemu-i386-debug
- qemu-x86_64-clang
- qemu-x86_64-debug
- qemu-x86_64-kasan
- qemu_arm
- qemu_arm64
- qemu_arm64-compat
- qemu_i386
- qemu_x86_64
- qemu_x86_64-compat
- s390
- sparc
- x15 - arm
- x86_64
- x86-kasan
- x86_64

Test Suites
-----------
* build
* linux-log-parser
* install-android-platform-tools-r2600
* kselftest-
* kselftest-android
* kselftest-bpf
* kselftest-capabilities
* kselftest-cgroup
* kselftest-clone3
* kselftest-core
* kselftest-cpu-hotplug
* kselftest-cpufreq
* kselftest-intel_pstate
* kselftest-kvm
* kselftest-livepatch
* kselftest-lkdtm
* kselftest-net
* kselftest-netfilter
* kselftest-nsfs
* kselftest-ptrace
* kselftest-rseq
* kselftest-rtc
* kselftest-seccomp
* kselftest-sigaltstack
* kselftest-size
* kselftest-splice
* kselftest-static_keys
* kselftest-sync
* kselftest-sysctl
* kselftest-tc-testing
* kselftest-timens
* kselftest-timers
* kselftest-tmpfs
* kselftest-tpm2
* kselftest-user
* kselftest-zram
* libhugetlbfs
* ltp-cap_bounds-tests
* ltp-commands-tests
* ltp-containers-tests
* ltp-controllers-tests
* ltp-cpuhotplug-tests
* ltp-crypto-tests
* ltp-cve-tests
* ltp-dio-tests
* ltp-fcntl-locktests-tests
* ltp-filecaps-tests
* ltp-fs_bind-tests
* ltp-fs_perms_simple-tests
* ltp-fsx-tests
* ltp-hugetlb-tests
* ltp-io-tests
* ltp-ipc-tests
* ltp-math-tests
* ltp-mm-tests
* ltp-nptl-tests
* ltp-pty-tests
* ltp-sched-tests
* ltp-securebits-tests
* ltp-tracing-tests
* v4l2-compliance
* kselftest-efivarfs
* kselftest-filesystems
* kselftest-firmware
* kselftest-fpu
* kselftest-futex
* kselftest-gpio
* kselftest-ipc
* kselftest-ir
* kselftest-kcmp
* kselftest-lib
* kselftest-membarrier
* kselftest-memfd
* kselftest-memory-hotplug
* kselftest-mincore
* kselftest-mount
* kselftest-mqueue
* kselftest-openat2
* kselftest-pid_namespace
* kselftest-pidfd
* kselftest-proc
* kselftest-pstore
* kvm-unit-tests
* ltp-fs-tests
* network-basic-tests
* perf
* kselftest-kexec
* kselftest-vm
* kselftest-x86
* ltp-open-posix-tests
* ltp-syscalls-tests
* fwts
* rcutorture
* igt-gpu-tools
* ssuite
* kselftest-vsyscall-mode-native-
* kselftest-vsyscall-mode-none-

Linaro LKFT
https://lkft.linaro.org

Tested on x86 for 4.14.227-rc1,

Kernel repo:
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git
Branch: linux-4.14.y
Version: 4.14.227-rc1
Commit: dbfdb55a0970570a02a8d7bb6abc2e4db71218c8
Compiler: gcc version 7.3.0 (GCC)

x86:
--------------------------------------------------------------------
Testcase Result Summary:
total: 4667
passed: 4667
failed: 0
timeout: 0
--------------------------------------------------------------------