From: Kailang Yang kailang@realtek.com

commit 69ea4c9d02b7947cdd612335a61cc1a02e544ccd upstream.

This was the ALC283 depop procedure. Maybe this procedure wasn't suitable with new codec. So, let us remove it. But HP 15z-fc000 must do 3k pull low. If it reboot with plugged headset, it will have errors show don't find codec error messages. Run 3k pull low will solve issues. So, let AMD chipset will run this for workarround.

Fixes: 5aec98913095 ("ALSA: hda/realtek - ALC236 headset MIC recording issue") Signed-off-by: Kailang Yang kailang@realtek.com Cc: stable@vger.kernel.org Reported-by: Joseph C. Sible josephcsible@gmail.com Closes: https://lore.kernel.org/r/CABpewhE4REgn9RJZduuEU6Z_ijXNeQWnrxO1tg70Gkw=F8qNY... Link: https://lore.kernel.org/r/4678992299664babac4403d9978e7ba7@realtek.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/pci/hda/patch_realtek.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

--- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -122,6 +122,7 @@ struct alc_spec { unsigned int ultra_low_power:1; unsigned int has_hs_key:1; unsigned int no_internal_mic_pin:1; + unsigned int en_3kpull_low:1;

/* for PLL fix */ hda_nid_t pll_nid; @@ -3622,6 +3623,7 @@ static void alc256_shutup(struct hda_cod if (!hp_pin) hp_pin = 0x21;

+ alc_update_coefex_idx(codec, 0x57, 0x04, 0x0007, 0x1); /* Low power */ hp_pin_sense = snd_hda_jack_detect(codec, hp_pin);

if (hp_pin_sense) @@ -3638,8 +3640,7 @@ static void alc256_shutup(struct hda_cod /* If disable 3k pulldown control for alc257, the Mic detection will not work correctly * when booting with headset plugged. So skip setting it for the codec alc257 */ - if (codec->core.vendor_id != 0x10ec0236 && - codec->core.vendor_id != 0x10ec0257) + if (spec->en_3kpull_low) alc_update_coef_idx(codec, 0x46, 0, 3 << 12);

if (!spec->no_shutup_pins) @@ -10599,6 +10600,8 @@ static int patch_alc269(struct hda_codec spec->shutup = alc256_shutup; spec->init_hook = alc256_init; spec->gen.mixer_nid = 0; /* ALC256 does not have any loopback mixer path */ + if (codec->bus->pci->vendor == PCI_VENDOR_ID_AMD) + spec->en_3kpull_low = true; break; case 0x10ec0257: spec->codec_variant = ALC269_TYPE_ALC257;

From: Luka Guzenko l.guzenko@web.de

commit 0659400f18c0e6c0c69d74fe5d09e7f6fbbd52a2 upstream.

The HP Laptop 15s-eq2xxx uses ALC236 codec and controls the mute LED using COEF 0x07 index 1. No existing quirk covers this configuration. Adds a new quirk and enables it for the device.

Signed-off-by: Luka Guzenko l.guzenko@web.de Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230718161241.393181-1-l.guzenko@web.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/pci/hda/patch_realtek.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+)

--- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4624,6 +4624,21 @@ static void alc236_fixup_hp_mute_led_coe } }

+static void alc236_fixup_hp_mute_led_coefbit2(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + struct alc_spec *spec = codec->spec; + + if (action == HDA_FIXUP_ACT_PRE_PROBE) { + spec->mute_led_polarity = 0; + spec->mute_led_coef.idx = 0x07; + spec->mute_led_coef.mask = 1; + spec->mute_led_coef.on = 1; + spec->mute_led_coef.off = 0; + snd_hda_gen_add_mute_led_cdev(codec, coef_mute_led_set); + } +} + /* turn on/off mic-mute LED per capture hook by coef bit */ static int coef_micmute_led_set(struct led_classdev *led_cdev, enum led_brightness brightness) @@ -7134,6 +7149,7 @@ enum { ALC285_FIXUP_HP_GPIO_LED, ALC285_FIXUP_HP_MUTE_LED, ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED, + ALC236_FIXUP_HP_MUTE_LED_COEFBIT2, ALC236_FIXUP_HP_GPIO_LED, ALC236_FIXUP_HP_MUTE_LED, ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF, @@ -8557,6 +8573,10 @@ static const struct hda_fixup alc269_fix .type = HDA_FIXUP_FUNC, .v.func = alc285_fixup_hp_spectre_x360_mute_led, }, + [ALC236_FIXUP_HP_MUTE_LED_COEFBIT2] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc236_fixup_hp_mute_led_coefbit2, + }, [ALC236_FIXUP_HP_GPIO_LED] = { .type = HDA_FIXUP_FUNC, .v.func = alc236_fixup_hp_gpio_led, @@ -9441,6 +9461,7 @@ static const struct snd_pci_quirk alc269 SND_PCI_QUIRK(0x103c, 0x886d, "HP ZBook Fury 17.3 Inch G8 Mobile Workstation PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x8870, "HP ZBook Fury 15.6 Inch G8 Mobile Workstation PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x8873, "HP ZBook Studio 15.6 Inch G8 Mobile Workstation PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), + SND_PCI_QUIRK(0x103c, 0x887a, "HP Laptop 15s-eq2xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x888d, "HP ZBook Power 15.6 inch G8 Mobile Workstation PC", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8895, "HP EliteBook 855 G8 Notebook PC", ALC285_FIXUP_HP_SPEAKERS_MICMUTE_LED), SND_PCI_QUIRK(0x103c, 0x8896, "HP EliteBook 855 G8 Notebook PC", ALC285_FIXUP_HP_MUTE_LED),

From: Liam R. Howlett Liam.Howlett@oracle.com

commit ef5c3de5211b5a3a8102b25aa83eb4cde65ac2fd upstream.

Internal node counting was altered and the 64 bit test was updated, however the 32bit test was missed.

Restore the 32bit test to a functional state.

Link: https://lore.kernel.org/linux-mm/CAMuHMdV4T53fOw7VPoBgPR7fP6RYqf=CBhD_y_vOg5... Link: https://lkml.kernel.org/r/20230712173916.168805-2-Liam.Howlett@oracle.com Fixes: 541e06b772c1 ("maple_tree: remove GFP_ZERO from kmem_cache_alloc() and kmem_cache_alloc_bulk()") Signed-off-by: Liam R. Howlett Liam.Howlett@oracle.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/radix-tree/maple.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -181,9 +181,9 @@ static noinline void check_new_node(stru e = i - 1; } else { if (i >= 4) - e = i - 4; - else if (i == 3) - e = i - 2; + e = i - 3; + else if (i >= 1) + e = i - 1; else e = 0; }

From: Georg Müller georgmueller@gmx.net

commit 56cbeacf143530576905623ac72ae0964f3293a6 upstream.

This patch adds a test to validate that 'perf probe' works for binaries where DWARF info is split into multiple CUs

Signed-off-by: Georg Müller georgmueller@gmx.net Acked-by: Masami Hiramatsu (Google) mhiramat@kernel.org Cc: Adrian Hunter adrian.hunter@intel.com Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Ian Rogers irogers@google.com Cc: Ingo Molnar mingo@redhat.com Cc: Jiri Olsa jolsa@kernel.org Cc: Mark Rutland mark.rutland@arm.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: regressions@lists.linux.dev Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230628084551.1860532-5-georgmueller@gmx.net Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/perf/tests/shell/test_uprobe_from_different_cu.sh | 77 ++++++++++++++++ 1 file changed, 77 insertions(+) create mode 100755 tools/perf/tests/shell/test_uprobe_from_different_cu.sh

--- /dev/null +++ b/tools/perf/tests/shell/test_uprobe_from_different_cu.sh @@ -0,0 +1,77 @@ +#!/bin/bash +# test perf probe of function from different CU +# SPDX-License-Identifier: GPL-2.0 + +set -e + +temp_dir=$(mktemp -d /tmp/perf-uprobe-different-cu-sh.XXXXXXXXXX) + +cleanup() +{ + trap - EXIT TERM INT + if [[ "${temp_dir}" =~ ^/tmp/perf-uprobe-different-cu-sh.*$ ]]; then + echo "--- Cleaning up ---" + perf probe -x ${temp_dir}/testfile -d foo + rm -f "${temp_dir}/"* + rmdir "${temp_dir}" + fi +} + +trap_cleanup() +{ + cleanup + exit 1 +} + +trap trap_cleanup EXIT TERM INT + +cat > ${temp_dir}/testfile-foo.h << EOF +struct t +{ + int *p; + int c; +}; + +extern int foo (int i, struct t *t); +EOF + +cat > ${temp_dir}/testfile-foo.c << EOF +#include "testfile-foo.h" + +int +foo (int i, struct t *t) +{ + int j, res = 0; + for (j = 0; j < i && j < t->c; j++) + res += t->p[j]; + + return res; +} +EOF + +cat > ${temp_dir}/testfile-main.c << EOF +#include "testfile-foo.h" + +static struct t g; + +int +main (int argc, char **argv) +{ + int i; + int j[argc]; + g.c = argc; + g.p = j; + for (i = 0; i < argc; i++) + j[i] = (int) argv[i][0]; + return foo (3, &g); +} +EOF + +gcc -g -Og -flto -c ${temp_dir}/testfile-foo.c -o ${temp_dir}/testfile-foo.o +gcc -g -Og -c ${temp_dir}/testfile-main.c -o ${temp_dir}/testfile-main.o +gcc -g -Og -o ${temp_dir}/testfile ${temp_dir}/testfile-foo.o ${temp_dir}/testfile-main.o + +perf probe -x ${temp_dir}/testfile --funcs foo +perf probe -x ${temp_dir}/testfile foo + +cleanup

From: Miklos Szeredi mszeredi@redhat.com

commit a9d1c4c6df0e568207907c04aed9e7beb1294c42 upstream.

If the LOOKUP request triggered from fuse_dentry_revalidate() is interrupted, then the dentry will be invalidated, possibly resulting in submounts being unmounted.

Reported-by: Xu Rongbo xurongbo@baidu.com Closes: https://lore.kernel.org/all/CAJfpegswN_CJJ6C3RZiaK6rpFmNyWmXfaEpnQUJ42KCwNF5... Fixes: 9e6268db496a ("[PATCH] FUSE - read-write operations") Cc: stable@vger.kernel.org Signed-off-by: Miklos Szeredi mszeredi@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/fuse/dir.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -258,7 +258,7 @@ static int fuse_dentry_revalidate(struct spin_unlock(&fi->lock); } kfree(forget); - if (ret == -ENOMEM) + if (ret == -ENOMEM || ret == -EINTR) goto out; if (ret || fuse_invalid_attr(&outarg.attr) || fuse_stale_inode(inode, outarg.generation, &outarg.attr))

From: Josef Bacik josef@toxicpanda.com

commit 17b17fcd6d446b95904a6929c40012ee7f0afc0c upstream.

While trying to get the subpage blocksize tests running, I hit the following panic on generic/476

assertion failed: PagePrivate(page) && page->private, in fs/btrfs/subpage.c:229 kernel BUG at fs/btrfs/subpage.c:229! Internal error: Oops - BUG: 00000000f2000800 [#1] SMP CPU: 1 PID: 1453 Comm: fsstress Not tainted 6.4.0-rc7+ #12 Hardware name: QEMU KVM Virtual Machine, BIOS edk2-20230301gitf80f052277c8-26.fc38 03/01/2023 pstate: 61400005 (nZCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--) pc : btrfs_subpage_assert+0xbc/0xf0 lr : btrfs_subpage_assert+0xbc/0xf0 Call trace: btrfs_subpage_assert+0xbc/0xf0 btrfs_subpage_clear_checked+0x38/0xc0 btrfs_page_clear_checked+0x48/0x98 btrfs_truncate_block+0x5d0/0x6a8 btrfs_cont_expand+0x5c/0x528 btrfs_write_check.isra.0+0xf8/0x150 btrfs_buffered_write+0xb4/0x760 btrfs_do_write_iter+0x2f8/0x4b0 btrfs_file_write_iter+0x1c/0x30 do_iter_readv_writev+0xc8/0x158 do_iter_write+0x9c/0x210 vfs_iter_write+0x24/0x40 iter_file_splice_write+0x224/0x390 direct_splice_actor+0x38/0x68 splice_direct_to_actor+0x12c/0x260 do_splice_direct+0x90/0xe8 generic_copy_file_range+0x50/0x90 vfs_copy_file_range+0x29c/0x470 __arm64_sys_copy_file_range+0xcc/0x498 invoke_syscall.constprop.0+0x80/0xd8 do_el0_svc+0x6c/0x168 el0_svc+0x50/0x1b0 el0t_64_sync_handler+0x114/0x120 el0t_64_sync+0x194/0x198

This happens because during btrfs_cont_expand we'll get a page, set it as mapped, and if it's not Uptodate we'll read it. However between the read and re-locking the page we could have called release_folio() on the page, but left the page in the file mapping. release_folio() can clear the page private, and thus further down we blow up when we go to modify the subpage bits.

Fix this by putting the set_page_extent_mapped() after the read. This is safe because read_folio() will call set_page_extent_mapped() before it does the read, and then if we clear page private but leave it on the mapping we're completely safe re-setting set_page_extent_mapped(). With this patch I can now run generic/476 without panicing.

CC: stable@vger.kernel.org # 6.1+ Reviewed-by: Christoph Hellwig hch@lst.de Signed-off-by: Josef Bacik josef@toxicpanda.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/btrfs/inode.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-)

--- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4913,9 +4913,6 @@ again: ret = -ENOMEM; goto out; } - ret = set_page_extent_mapped(page); - if (ret < 0) - goto out_unlock;

if (!PageUptodate(page)) { ret = btrfs_read_folio(NULL, page_folio(page)); @@ -4930,6 +4927,17 @@ again: goto out_unlock; } } + + /* + * We unlock the page after the io is completed and then re-lock it + * above. release_folio() could have come in between that and cleared + * PagePrivate(), but left the page in the mapping. Set the page mapped + * here to make sure it's properly set for the subpage stuff. + */ + ret = set_page_extent_mapped(page); + if (ret < 0) + goto out_unlock; + wait_on_page_writeback(page);

lock_extent(io_tree, block_start, block_end, &cached_state);

From: Miklos Szeredi mszeredi@redhat.com

commit 6a567e920fd0451bf29abc418df96c3365925770 upstream.

Fuse shouldn't return ENOSYS from its ioctl implementation. If userspace responds with ENOSYS it should be translated to ENOTTY.

There are two ways to return an error from the IOCTL request:

- fuse_out_header.error - fuse_ioctl_out.result

Commit 02c0cab8e734 ("fuse: ioctl: translate ENOSYS") already fixed this issue for the first case, but missed the second case. This patch fixes the second case.

Reported-by: Jonathan Katz jkatz@eitmlabs.org Closes: https://lore.kernel.org/all/CALKgVmcC1VUV_gJVq70n--omMJZUb4HSh_FqvLTHgNBc+HC... Fixes: 02c0cab8e734 ("fuse: ioctl: translate ENOSYS") Cc: stable@vger.kernel.org Signed-off-by: Miklos Szeredi mszeredi@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/fuse/ioctl.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-)

--- a/fs/fuse/ioctl.c +++ b/fs/fuse/ioctl.c @@ -9,14 +9,23 @@ #include <linux/compat.h> #include <linux/fileattr.h>

-static ssize_t fuse_send_ioctl(struct fuse_mount *fm, struct fuse_args *args) +static ssize_t fuse_send_ioctl(struct fuse_mount *fm, struct fuse_args *args, + struct fuse_ioctl_out *outarg) { - ssize_t ret = fuse_simple_request(fm, args); + ssize_t ret; + + args->out_args[0].size = sizeof(*outarg); + args->out_args[0].value = outarg; + + ret = fuse_simple_request(fm, args);

/* Translate ENOSYS, which shouldn't be returned from fs */ if (ret == -ENOSYS) ret = -ENOTTY;

+ if (ret >= 0 && outarg->result == -ENOSYS) + outarg->result = -ENOTTY; + return ret; }

@@ -264,13 +273,11 @@ long fuse_do_ioctl(struct file *file, un }

ap.args.out_numargs = 2; - ap.args.out_args[0].size = sizeof(outarg); - ap.args.out_args[0].value = &outarg; ap.args.out_args[1].size = out_size; ap.args.out_pages = true; ap.args.out_argvar = true;

- transferred = fuse_send_ioctl(fm, &ap.args); + transferred = fuse_send_ioctl(fm, &ap.args, &outarg); err = transferred; if (transferred < 0) goto out; @@ -399,12 +406,10 @@ static int fuse_priv_ioctl(struct inode args.in_args[1].size = inarg.in_size; args.in_args[1].value = ptr; args.out_numargs = 2; - args.out_args[0].size = sizeof(outarg); - args.out_args[0].value = &outarg; args.out_args[1].size = inarg.out_size; args.out_args[1].value = ptr;

- err = fuse_send_ioctl(fm, &args); + err = fuse_send_ioctl(fm, &args, &outarg); if (!err) { if (outarg.result < 0) err = outarg.result;

From: Matthieu Baerts matthieu.baerts@tessares.net

commit fda05798c22a354efde09a76bdfc276b2d591829 upstream.

When looking for something else in LKFT reports [1], I noticed that the TC selftest ended with a timeout error:

not ok 1 selftests: tc-testing: tdc.sh # TIMEOUT 45 seconds

The timeout had been introduced 3 years ago, see the Fixes commit below.

This timeout is only in place when executing the selftests via the kselftests runner scripts. I guess this is not what most TC devs are using and nobody noticed the issue before.

The new timeout is set to 15 minutes as suggested by Pedro [2]. It looks like it is plenty more time than what it takes in "normal" conditions.

Fixes: 852c8cbf34d3 ("selftests/kselftest/runner.sh: Add 45 second timeout per test") Cc: stable@vger.kernel.org Link: https://qa-reports.linaro.org/lkft/linux-next-master/build/next-20230711/tes... [1] Link: https://lore.kernel.org/netdev/0e061d4a-9a23-9f58-3b35-d8919de332d7@tessares... [2] Suggested-by: Pedro Tammela pctammela@mojatatu.com Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Reviewed-by: Zhengchao Shao shaozhengchao@huawei.com Link: https://lore.kernel.org/r/20230713-tc-selftests-lkft-v1-1-1eb4fd3a96e7@tessa... Acked-by: Jamal Hadi Salim jhs@mojatatu.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/tc-testing/settings | 1 + 1 file changed, 1 insertion(+) create mode 100644 tools/testing/selftests/tc-testing/settings

--- /dev/null +++ b/tools/testing/selftests/tc-testing/settings @@ -0,0 +1 @@ +timeout=900

From: Mark Brown broonie@kernel.org

commit bc64734825c59e18a27ac266b07e14944c111fd8 upstream.

When problems were noticed with the register address not being taken into account when limiting raw transfers with I2C devices we fixed this in the core. Unfortunately it has subsequently been realised that a lot of buses were relying on the prior behaviour, partly due to unclear documentation not making it obvious what was intended in the core. This is all more involved to fix than is sensible for a fix commit so let's just drop the original fixes, a separate commit will fix the originally observed problem in an I2C specific way

Fixes: 3981514180c9 ("regmap: Account for register length when chunking") Fixes: c8e796895e23 ("regmap: spi-avmm: Fix regmap_bus max_raw_write") Signed-off-by: Mark Brown broonie@kernel.org Reviewed-by: Xu Yilun yilun.xu@intel.com Cc: stable@kernel.org Link: https://lore.kernel.org/r/20230712-regmap-max-transfer-v1-1-80e2aed22e83@ker... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/base/regmap/regmap-spi-avmm.c | 2 +- drivers/base/regmap/regmap.c | 6 ++---- 2 files changed, 3 insertions(+), 5 deletions(-)

--- a/drivers/base/regmap/regmap-spi-avmm.c +++ b/drivers/base/regmap/regmap-spi-avmm.c @@ -660,7 +660,7 @@ static const struct regmap_bus regmap_sp .reg_format_endian_default = REGMAP_ENDIAN_NATIVE, .val_format_endian_default = REGMAP_ENDIAN_NATIVE, .max_raw_read = SPI_AVMM_VAL_SIZE * MAX_READ_CNT, - .max_raw_write = SPI_AVMM_REG_SIZE + SPI_AVMM_VAL_SIZE * MAX_WRITE_CNT, + .max_raw_write = SPI_AVMM_VAL_SIZE * MAX_WRITE_CNT, .free_context = spi_avmm_bridge_ctx_free, };

--- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -2064,8 +2064,6 @@ int _regmap_raw_write(struct regmap *map size_t val_count = val_len / val_bytes; size_t chunk_count, chunk_bytes; size_t chunk_regs = val_count; - size_t max_data = map->max_raw_write - map->format.reg_bytes - - map->format.pad_bytes; int ret, i;

if (!val_count) @@ -2073,8 +2071,8 @@ int _regmap_raw_write(struct regmap *map

if (map->use_single_write) chunk_regs = 1; - else if (map->max_raw_write && val_len > max_data) - chunk_regs = max_data / val_bytes; + else if (map->max_raw_write && val_len > map->max_raw_write) + chunk_regs = map->max_raw_write / val_bytes;

chunk_count = val_count / chunk_regs; chunk_bytes = chunk_regs * val_bytes;

From: Mark Brown broonie@kernel.org

commit 0c9d2eb5e94792fe64019008a04d4df5e57625af upstream.

The SMBus I2C buses have limits on the size of transfers they can do but do not factor in the register length meaning we may try to do a transfer longer than our length limit, the core will not take care of this. Future changes will factor this out into the core but there are a number of users that assume current behaviour so let's just do something conservative here.

This does not take account padding bits but practically speaking these are very rarely if ever used on I2C buses given that they generally run slowly enough to mean there's no issue.

Cc: stable@kernel.org Signed-off-by: Mark Brown broonie@kernel.org Reviewed-by: Xu Yilun yilun.xu@intel.com Link: https://lore.kernel.org/r/20230712-regmap-max-transfer-v1-2-80e2aed22e83@ker... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/base/regmap/regmap-i2c.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/drivers/base/regmap/regmap-i2c.c +++ b/drivers/base/regmap/regmap-i2c.c @@ -242,8 +242,8 @@ static int regmap_i2c_smbus_i2c_read(voi static const struct regmap_bus regmap_i2c_smbus_i2c_block = { .write = regmap_i2c_smbus_i2c_write, .read = regmap_i2c_smbus_i2c_read, - .max_raw_read = I2C_SMBUS_BLOCK_MAX, - .max_raw_write = I2C_SMBUS_BLOCK_MAX, + .max_raw_read = I2C_SMBUS_BLOCK_MAX - 1, + .max_raw_write = I2C_SMBUS_BLOCK_MAX - 1, };

static int regmap_i2c_smbus_i2c_write_reg16(void *context, const void *data, @@ -299,8 +299,8 @@ static int regmap_i2c_smbus_i2c_read_reg static const struct regmap_bus regmap_i2c_smbus_i2c_block_reg16 = { .write = regmap_i2c_smbus_i2c_write_reg16, .read = regmap_i2c_smbus_i2c_read_reg16, - .max_raw_read = I2C_SMBUS_BLOCK_MAX, - .max_raw_write = I2C_SMBUS_BLOCK_MAX, + .max_raw_read = I2C_SMBUS_BLOCK_MAX - 2, + .max_raw_write = I2C_SMBUS_BLOCK_MAX - 2, };

static const struct regmap_bus *regmap_get_i2c_bus(struct i2c_client *i2c,

From: Fedor Ross fedor.ross@ifm.com

commit 9efa1a5407e81265ea502cab83be4de503decc49 upstream.

The mcp251xfd controller needs an idle bus to enter 'Normal CAN 2.0 mode' or . The maximum length of a CAN frame is 736 bits (64 data bytes, CAN-FD, EFF mode, worst case bit stuffing and interframe spacing). For low bit rates like 10 kbit/s the arbitrarily chosen MCP251XFD_POLL_TIMEOUT_US of 1 ms is too small.

Otherwise during polling for the CAN controller to enter 'Normal CAN 2.0 mode' the timeout limit is exceeded and the configuration fails with:

| $ ip link set dev can1 up type can bitrate 10000 | [ 731.911072] mcp251xfd spi2.1 can1: Controller failed to enter mode CAN 2.0 Mode (6) and stays in Configuration Mode (4) (con=0x068b0760, osc=0x00000468). | [ 731.927192] mcp251xfd spi2.1 can1: CRC read error at address 0x0e0c (length=4, data=00 00 00 00, CRC=0x0000) retrying. | [ 731.938101] A link change request failed with some changes committed already. Interface can1 may have been left with an inconsistent configuration, please check. | RTNETLINK answers: Connection timed out

Make MCP251XFD_POLL_TIMEOUT_US timeout calculation dynamic. Use maximum of 1ms and bit time of 1 full 64 data bytes CAN-FD frame in EFF mode, worst case bit stuffing and interframe spacing at the current bit rate.

For easier backporting define the macro MCP251XFD_FRAME_LEN_MAX_BITS that holds the max frame length in bits, which is 736. This can be replaced by can_frame_bits(true, true, true, true, CANFD_MAX_DLEN) in a cleanup patch later.

Fixes: 55e5b97f003e8 ("can: mcp25xxfd: add driver for Microchip MCP25xxFD SPI CAN") Signed-off-by: Fedor Ross fedor.ross@ifm.com Signed-off-by: Marek Vasut marex@denx.de Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/20230717-mcp251xfd-fix-increase-poll-timeout-v5-... Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c | 10 ++++++++-- drivers/net/can/spi/mcp251xfd/mcp251xfd.h | 1 + 2 files changed, 9 insertions(+), 2 deletions(-)

--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c @@ -227,6 +227,8 @@ static int __mcp251xfd_chip_set_mode(const struct mcp251xfd_priv *priv, const u8 mode_req, bool nowait) { + const struct can_bittiming *bt = &priv->can.bittiming; + unsigned long timeout_us = MCP251XFD_POLL_TIMEOUT_US; u32 con = 0, con_reqop, osc = 0; u8 mode; int err; @@ -246,12 +248,16 @@ __mcp251xfd_chip_set_mode(const struct m if (mode_req == MCP251XFD_REG_CON_MODE_SLEEP || nowait) return 0;

+ if (bt->bitrate) + timeout_us = max_t(unsigned long, timeout_us, + MCP251XFD_FRAME_LEN_MAX_BITS * USEC_PER_SEC / + bt->bitrate); + err = regmap_read_poll_timeout(priv->map_reg, MCP251XFD_REG_CON, con, !mcp251xfd_reg_invalid(con) && FIELD_GET(MCP251XFD_REG_CON_OPMOD_MASK, con) == mode_req, - MCP251XFD_POLL_SLEEP_US, - MCP251XFD_POLL_TIMEOUT_US); + MCP251XFD_POLL_SLEEP_US, timeout_us); if (err != -ETIMEDOUT && err != -EBADMSG) return err;

--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h @@ -387,6 +387,7 @@ static_assert(MCP251XFD_TIMESTAMP_WORK_D #define MCP251XFD_OSC_STAB_TIMEOUT_US (10 * MCP251XFD_OSC_STAB_SLEEP_US) #define MCP251XFD_POLL_SLEEP_US (10) #define MCP251XFD_POLL_TIMEOUT_US (USEC_PER_MSEC) +#define MCP251XFD_FRAME_LEN_MAX_BITS (736)

/* Misc */ #define MCP251XFD_NAPI_WEIGHT 32

From: Marc Kleine-Budde mkl@pengutronix.de

commit 2603be9e8167ddc7bea95dcfab9ffc33414215aa upstream.

The gs_usb driver handles USB devices with more than 1 CAN channel. The RX path for all channels share the same bulk endpoint (the transmitted bulk data encodes the channel number). These per-device resources are allocated and submitted by the first opened channel.

During this allocation, the resources are either released immediately in case of a failure or the URBs are anchored. All anchored URBs are finally killed with gs_usb_disconnect().

Currently, gs_can_open() returns with an error if the allocation of a URB or a buffer fails. However, if usb_submit_urb() fails, the driver continues with the URBs submitted so far, even if no URBs were successfully submitted.

Treat every error as fatal and free all allocated resources immediately.

Switch to goto-style error handling, to prepare the driver for more per-device resource allocation.

Cc: stable@vger.kernel.org Cc: John Whittington git@jbrengineering.co.uk Link: https://lore.kernel.org/all/20230716-gs_usb-fix-time-stamp-counter-v1-1-9017... Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/can/usb/gs_usb.c | 31 ++++++++++++++++++++++--------- 1 file changed, 22 insertions(+), 9 deletions(-)

--- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -833,6 +833,7 @@ static int gs_can_open(struct net_device .mode = cpu_to_le32(GS_CAN_MODE_START), }; struct gs_host_frame *hf; + struct urb *urb = NULL; u32 ctrlmode; u32 flags = 0; int rc, i; @@ -858,13 +859,14 @@ static int gs_can_open(struct net_device

if (!parent->active_channels) { for (i = 0; i < GS_MAX_RX_URBS; i++) { - struct urb *urb; u8 *buf;

/* alloc rx urb */ urb = usb_alloc_urb(0, GFP_KERNEL); - if (!urb) - return -ENOMEM; + if (!urb) { + rc = -ENOMEM; + goto out_usb_kill_anchored_urbs; + }

/* alloc rx buffer */ buf = kmalloc(dev->parent->hf_size_rx, @@ -872,8 +874,8 @@ static int gs_can_open(struct net_device if (!buf) { netdev_err(netdev, "No memory left for USB buffer\n"); - usb_free_urb(urb); - return -ENOMEM; + rc = -ENOMEM; + goto out_usb_free_urb; }

/* fill, anchor, and submit rx urb */ @@ -896,9 +898,7 @@ static int gs_can_open(struct net_device netdev_err(netdev, "usb_submit failed (err=%d)\n", rc);

- usb_unanchor_urb(urb); - usb_free_urb(urb); - break; + goto out_usb_unanchor_urb; }

/* Drop reference, @@ -944,7 +944,8 @@ static int gs_can_open(struct net_device if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) gs_usb_timestamp_stop(dev); dev->can.state = CAN_STATE_STOPPED; - return rc; + + goto out_usb_kill_anchored_urbs; }

parent->active_channels++; @@ -952,6 +953,18 @@ static int gs_can_open(struct net_device netif_start_queue(netdev);

return 0; + +out_usb_unanchor_urb: + usb_unanchor_urb(urb); +out_usb_free_urb: + usb_free_urb(urb); +out_usb_kill_anchored_urbs: + if (!parent->active_channels) + usb_kill_anchored_urbs(&dev->tx_submitted); + + close_candev(netdev); + + return rc; }

static int gs_can_close(struct net_device *netdev)

From: Ville Syrjälä ville.syrjala@linux.intel.com

commit 05abb3be91d8788328231ee02973ab3d47f5e3d2 upstream.

Currently dma_resv_get_fences() will leak the previously allocated array if the fence iteration got restarted and the krealloc_array() fails.

Free the old array by hand, and make sure we still clear the returned *fences so the caller won't end up accessing freed memory. Some (but not all) of the callers of dma_resv_get_fences() seem to still trawl through the array even when dma_resv_get_fences() failed. And let's zero out *num_fences as well for good measure.

Cc: Sumit Semwal sumit.semwal@linaro.org Cc: Christian König christian.koenig@amd.com Cc: linux-media@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Cc: linaro-mm-sig@lists.linaro.org Fixes: d3c80698c9f5 ("dma-buf: use new iterator in dma_resv_get_fences v3") Signed-off-by: Ville Syrjälä ville.syrjala@linux.intel.com Reviewed-by: Christian König christian.koenig@amd.com Cc: stable@vger.kernel.org Link: https://patchwork.freedesktop.org/patch/msgid/20230713194745.1751-1-ville.sy... Signed-off-by: Christian König christian.koenig@amd.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/dma-buf/dma-resv.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-)

--- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -566,6 +566,7 @@ int dma_resv_get_fences(struct dma_resv dma_resv_for_each_fence_unlocked(&cursor, fence) {

if (dma_resv_iter_is_restarted(&cursor)) { + struct dma_fence **new_fences; unsigned int count;

while (*num_fences) @@ -574,13 +575,17 @@ int dma_resv_get_fences(struct dma_resv count = cursor.num_fences + 1;

/* Eventually re-allocate the array */ - *fences = krealloc_array(*fences, count, - sizeof(void *), - GFP_KERNEL); - if (count && !*fences) { + new_fences = krealloc_array(*fences, count, + sizeof(void *), + GFP_KERNEL); + if (count && !new_fences) { + kfree(*fences); + *fences = NULL; + *num_fences = 0; dma_resv_iter_end(&cursor); return -ENOMEM; } + *fences = new_fences; }

(*fences)[(*num_fences)++] = dma_fence_get(fence);

From: Alex Deucher alexander.deucher@amd.com

commit a4eb11824170d742531998f4ebd1c6a18b63db47 upstream.

Use average gfxclock for consistency with other dGPUs.

Reviewed-by: Kenneth Feng kenneth.feng@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Cc: stable@vger.kernel.org # 6.1.x Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index f6599c00a6fd..0cda3b276f61 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -1927,12 +1927,16 @@ static int sienna_cichlid_read_sensor(struct smu_context *smu, *size = 4; break; case AMDGPU_PP_SENSOR_GFX_MCLK: - ret = sienna_cichlid_get_current_clk_freq_by_table(smu, SMU_UCLK, (uint32_t *)data); + ret = sienna_cichlid_get_smu_metrics_data(smu, + METRICS_CURR_UCLK, + (uint32_t *)data); *(uint32_t *)data *= 100; *size = 4; break; case AMDGPU_PP_SENSOR_GFX_SCLK: - ret = sienna_cichlid_get_current_clk_freq_by_table(smu, SMU_GFXCLK, (uint32_t *)data); + ret = sienna_cichlid_get_smu_metrics_data(smu, + METRICS_AVERAGE_GFXCLK, + (uint32_t *)data); *(uint32_t *)data *= 100; *size = 4; break;

From: Jocelyn Falempe jfalempe@redhat.com

commit c2a88e8bdf5f6239948d75283d0ae7e0c7945b03 upstream.

dmt_mode is allocated and never freed in this function. It was found with the ast driver, but most drivers using generic fbdev setup are probably affected.

This fixes the following kmemleak report: backtrace: [<00000000b391296d>] drm_mode_duplicate+0x45/0x220 [drm] [<00000000e45bb5b3>] drm_client_target_cloned.constprop.0+0x27b/0x480 [drm] [<00000000ed2d3a37>] drm_client_modeset_probe+0x6bd/0xf50 [drm] [<0000000010e5cc9d>] __drm_fb_helper_initial_config_and_unlock+0xb4/0x2c0 [drm_kms_helper] [<00000000909f82ca>] drm_fbdev_client_hotplug+0x2bc/0x4d0 [drm_kms_helper] [<00000000063a69aa>] drm_client_register+0x169/0x240 [drm] [<00000000a8c61525>] ast_pci_probe+0x142/0x190 [ast] [<00000000987f19bb>] local_pci_probe+0xdc/0x180 [<000000004fca231b>] work_for_cpu_fn+0x4e/0xa0 [<0000000000b85301>] process_one_work+0x8b7/0x1540 [<000000003375b17c>] worker_thread+0x70a/0xed0 [<00000000b0d43cd9>] kthread+0x29f/0x340 [<000000008d770833>] ret_from_fork+0x1f/0x30 unreferenced object 0xff11000333089a00 (size 128):

cc: stable@vger.kernel.org Fixes: 1d42bbc8f7f9 ("drm/fbdev: fix cloning on fbcon") Reported-by: Zhang Yi yizhan@redhat.com Signed-off-by: Jocelyn Falempe jfalempe@redhat.com Reviewed-by: Javier Martinez Canillas javierm@redhat.com Reviewed-by: Thomas Zimmermann tzimmermann@suse.de Link: https://patchwork.freedesktop.org/patch/msgid/20230711092203.68157-2-jfalemp... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/drm_client_modeset.c | 5 +++++ 1 file changed, 5 insertions(+)

--- a/drivers/gpu/drm/drm_client_modeset.c +++ b/drivers/gpu/drm/drm_client_modeset.c @@ -315,6 +315,9 @@ static bool drm_client_target_cloned(str can_clone = true; dmt_mode = drm_mode_find_dmt(dev, 1024, 768, 60, false);

+ if (!dmt_mode) + goto fail; + for (i = 0; i < connector_count; i++) { if (!enabled[i]) continue; @@ -330,11 +333,13 @@ static bool drm_client_target_cloned(str if (!modes[i]) can_clone = false; } + kfree(dmt_mode);

if (can_clone) { DRM_DEBUG_KMS("can clone using 1024x768\n"); return true; } +fail: DRM_INFO("kms: can't enable cloning when we probably wanted to.\n"); return false; }

From: Simon Ser contact@emersion.fr

commit 1ca67aba8d11c2849d395013e1fdce02918d5657 upstream.

Up until now, amdgpu was silently degrading to vsync when user-space requested an async flip but the hardware didn't support it.

The hardware doesn't support immediate flips when the update changes the FB pitch, the DCC state, the rotation, enables or disables CRTCs or planes, etc. This is reflected in the dm_crtc_state.update_type field: UPDATE_TYPE_FAST means that immediate flip is supported.

Silently degrading async flips to vsync is not the expected behavior from a uAPI point-of-view. Xorg expects async flips to fail if unsupported, to be able to fall back to a blit. i915 already behaves this way.

This patch aligns amdgpu with uAPI expectations and returns a failure when an async flip is not possible.

Signed-off-by: Simon Ser contact@emersion.fr Reviewed-by: André Almeida andrealmeid@igalia.com Reviewed-by: Alex Deucher alexander.deucher@amd.com Reviewed-by: Harry Wentland harry.wentland@amd.com Signed-off-by: André Almeida andrealmeid@igalia.com Signed-off-by: Hamza Mahfooz hamza.mahfooz@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 8 ++++++++ drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c | 12 ++++++++++++ 2 files changed, 20 insertions(+)

--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -7757,7 +7757,15 @@ static void amdgpu_dm_commit_planes(stru * Only allow immediate flips for fast updates that don't * change memory domain, FB pitch, DCC state, rotation or * mirroring. + * + * dm_crtc_helper_atomic_check() only accepts async flips with + * fast updates. */ + if (crtc->state->async_flip && + acrtc_state->update_type != UPDATE_TYPE_FAST) + drm_warn_once(state->dev, + "[PLANE:%d:%s] async flip with non-fast update\n", + plane->base.id, plane->name); bundle->flip_addrs[planes_count].flip_immediate = crtc->state->async_flip && acrtc_state->update_type == UPDATE_TYPE_FAST && --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c @@ -406,6 +406,18 @@ static int dm_crtc_helper_atomic_check(s return -EINVAL; }

+ /* + * Only allow async flips for fast updates that don't change the FB + * pitch, the DCC state, rotation, etc. + */ + if (crtc_state->async_flip && + dm_crtc_state->update_type != UPDATE_TYPE_FAST) { + drm_dbg_atomic(crtc->dev, + "[CRTC:%d:%s] async flips are only supported for fast updates\n", + crtc->base.id, crtc->name); + return -EINVAL; + } + /* In some use cases, like reset, no stream is attached */ if (!dm_crtc_state->stream) return 0;

From: Taimur Hassan syed.hassan@amd.com

commit 5a25cefc0920088bb9afafeb80ad3dcd84fe278b upstream.

[Why & How] If there is no TG allocation we can dereference a NULL pointer when checking if the TG is enabled.

Cc: Mario Limonciello mario.limonciello@amd.com Cc: Alex Deucher alexander.deucher@amd.com Cc: stable@vger.kernel.org Reviewed-by: Nicholas Kazlauskas nicholas.kazlauskas@amd.com Acked-by: Alan Liu haoping.liu@amd.com Signed-off-by: Taimur Hassan syed.hassan@amd.com Tested-by: Daniel Wheeler daniel.wheeler@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -3293,7 +3293,8 @@ void dcn10_wait_for_mpcc_disconnect( if (pipe_ctx->stream_res.opp->mpcc_disconnect_pending[mpcc_inst]) { struct hubp *hubp = get_hubp_by_inst(res_pool, mpcc_inst);

- if (pipe_ctx->stream_res.tg->funcs->is_tg_enabled(pipe_ctx->stream_res.tg)) + if (pipe_ctx->stream_res.tg && + pipe_ctx->stream_res.tg->funcs->is_tg_enabled(pipe_ctx->stream_res.tg)) res_pool->mpc->funcs->wait_for_idle(res_pool->mpc, mpcc_inst); pipe_ctx->stream_res.opp->mpcc_disconnect_pending[mpcc_inst] = false; hubp->funcs->set_blank(hubp, true);

From: Matus Gajdos matuszpd@gmail.com

commit 269f399dc19f0e5c51711c3ba3bd06e0ef6ef403 upstream.

Otherwise bit clock remains running writing invalid data to the DAC.

Signed-off-by: Matus Gajdos matuszpd@gmail.com Acked-by: Shengjiu Wang shengjiu.wang@gmail.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230712124934.32232-1-matuszpd@gmail.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/soc/fsl/fsl_sai.c | 2 +- sound/soc/fsl/fsl_sai.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-)

--- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -719,7 +719,7 @@ static void fsl_sai_config_disable(struc u32 xcsr, count = 100;

regmap_update_bits(sai->regmap, FSL_SAI_xCSR(tx, ofs), - FSL_SAI_CSR_TERE, 0); + FSL_SAI_CSR_TERE | FSL_SAI_CSR_BCE, 0);

/* TERE will remain set till the end of current frame */ do { --- a/sound/soc/fsl/fsl_sai.h +++ b/sound/soc/fsl/fsl_sai.h @@ -91,6 +91,7 @@ /* SAI Transmit/Receive Control Register */ #define FSL_SAI_CSR_TERE BIT(31) #define FSL_SAI_CSR_SE BIT(30) +#define FSL_SAI_CSR_BCE BIT(28) #define FSL_SAI_CSR_FR BIT(25) #define FSL_SAI_CSR_SR BIT(24) #define FSL_SAI_CSR_xF_SHIFT 16

From: Sheetal sheetal@nvidia.com

commit 6dfe70be0b0dec0f9297811501bec26c05fd96ad upstream.

Byte mask for channel-1 of stream-1 is not getting enabled and this causes failures during ADX use cases. This happens because the byte map value 0 matches the byte map array and put() callback returns without enabling the corresponding bits in the byte mask.

ADX supports 4 output streams and each stream can have a maximum of 16 channels. Each byte in the input frame is uniquely mapped to a byte in one of these 4 outputs. This mapping is done with the help of byte map array via user space control setting. The byte map array size in the driver is 16 and each array element is of size 4 bytes. This corresponds to 64 byte map values.

Each byte in the byte map array can have any value between 0 to 255 to enable the corresponding bits in the byte mask. The value 256 is used as a way to disable the byte map. However the byte map array element cannot store this value. The put() callback disables the byte mask for 256 value and byte map value is reset to 0 for this case. This causes problems during subsequent runs since put() callback, for value of 0, just returns without enabling the byte mask. In short, the problem is coming because 0 and 256 control values are stored as 0 in the byte map array.

Right now fix the put() callback by actually looking at the byte mask array state to identify if any change is needed and update the fields accordingly. The get() callback needs an update as well to return the correct control value that user has set before. Note that when user set 256, the value is stored as 0 and byte mask is disabled. So byte mask state is used to either return 256 or the value from byte map array.

Given above, this looks bit complicated and all this happens because the byte map array is tightly packed and cannot actually store the 256 value. Right now the priority is to fix the existing failure and a TODO item is put to improve this logic.

Fixes: 3c97881b8c8a ("ASoC: tegra: Fix kcontrol put callback in ADX") Cc: stable@vger.kernel.org Signed-off-by: Sheetal sheetal@nvidia.com Reviewed-by: Mohan Kumar D mkumard@nvidia.com Reviewed-by: Sameer Pujar spujar@nvidia.com Link: https://lore.kernel.org/r/1688015537-31682-3-git-send-email-spujar@nvidia.co... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/soc/tegra/tegra210_adx.c | 34 ++++++++++++++++++++++------------ 1 file changed, 22 insertions(+), 12 deletions(-)

diff --git a/sound/soc/tegra/tegra210_adx.c b/sound/soc/tegra/tegra210_adx.c index bd0b10c70c4c..7d003f0c8d0f 100644 --- a/sound/soc/tegra/tegra210_adx.c +++ b/sound/soc/tegra/tegra210_adx.c @@ -2,7 +2,7 @@ // // tegra210_adx.c - Tegra210 ADX driver // -// Copyright (c) 2021 NVIDIA CORPORATION. All rights reserved. +// Copyright (c) 2021-2023 NVIDIA CORPORATION. All rights reserved.

#include <linux/clk.h> #include <linux/device.h> @@ -175,10 +175,20 @@ static int tegra210_adx_get_byte_map(struct snd_kcontrol *kcontrol, mc = (struct soc_mixer_control *)kcontrol->private_value; enabled = adx->byte_mask[mc->reg / 32] & (1 << (mc->reg % 32));

+ /* + * TODO: Simplify this logic to just return from bytes_map[] + * + * Presently below is required since bytes_map[] is + * tightly packed and cannot store the control value of 256. + * Byte mask state is used to know if 256 needs to be returned. + * Note that for control value of 256, the put() call stores 0 + * in the bytes_map[] and disables the corresponding bit in + * byte_mask[]. + */ if (enabled) ucontrol->value.integer.value[0] = bytes_map[mc->reg]; else - ucontrol->value.integer.value[0] = 0; + ucontrol->value.integer.value[0] = 256;

return 0; } @@ -192,19 +202,19 @@ static int tegra210_adx_put_byte_map(struct snd_kcontrol *kcontrol, int value = ucontrol->value.integer.value[0]; struct soc_mixer_control *mc = (struct soc_mixer_control *)kcontrol->private_value; + unsigned int mask_val = adx->byte_mask[mc->reg / 32];

- if (value == bytes_map[mc->reg]) + if (value >= 0 && value <= 255) + mask_val |= (1 << (mc->reg % 32)); + else + mask_val &= ~(1 << (mc->reg % 32)); + + if (mask_val == adx->byte_mask[mc->reg / 32]) return 0;

- if (value >= 0 && value <= 255) { - /* update byte map and enable slot */ - bytes_map[mc->reg] = value; - adx->byte_mask[mc->reg / 32] |= (1 << (mc->reg % 32)); - } else { - /* reset byte map and disable slot */ - bytes_map[mc->reg] = 0; - adx->byte_mask[mc->reg / 32] &= ~(1 << (mc->reg % 32)); - } + /* Update byte map and slot */ + bytes_map[mc->reg] = value % 256; + adx->byte_mask[mc->reg / 32] = mask_val;

return 1; }

From: Thomas Petazzoni thomas.petazzoni@bootlin.com

commit e51df4f81b02bcdd828a04de7c1eb6a92988b61e upstream.

In commit 2cb1e0259f50 ("ASoC: cs42l51: re-hook of_match_table pointer"), 9 years ago, some random guy fixed the cs42l51 after it was split into a core part and an I2C part to properly match based on a Device Tree compatible string.

However, the fix in this commit is wrong: the MODULE_DEVICE_TABLE(of, ....) is in the core part of the driver, not the I2C part. Therefore, automatic module loading based on module.alias, based on matching with the DT compatible string, loads the core part of the driver, but not the I2C part. And threfore, the i2c_driver is not registered, and the codec is not known to the system, nor matched with a DT node with the corresponding compatible string.

In order to fix that, we move the MODULE_DEVICE_TABLE(of, ...) into the I2C part of the driver. The cs42l51_of_match[] array is also moved as well, as it is not possible to have this definition in one file, and the MODULE_DEVICE_TABLE(of, ...) invocation in another file, due to how MODULE_DEVICE_TABLE works.

Thanks to this commit, the I2C part of the driver now properly autoloads, and thanks to its dependency on the core part, the core part gets autoloaded as well, resulting in a functional sound card without having to manually load kernel modules.

Fixes: 2cb1e0259f50 ("ASoC: cs42l51: re-hook of_match_table pointer") Cc: stable@vger.kernel.org Signed-off-by: Thomas Petazzoni thomas.petazzoni@bootlin.com Link: https://lore.kernel.org/r/20230713112112.778576-1-thomas.petazzoni@bootlin.c... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/soc/codecs/cs42l51-i2c.c | 6 ++++++ sound/soc/codecs/cs42l51.c | 7 ------- sound/soc/codecs/cs42l51.h | 1 - 3 files changed, 6 insertions(+), 8 deletions(-)

--- a/sound/soc/codecs/cs42l51-i2c.c +++ b/sound/soc/codecs/cs42l51-i2c.c @@ -19,6 +19,12 @@ static struct i2c_device_id cs42l51_i2c_ }; MODULE_DEVICE_TABLE(i2c, cs42l51_i2c_id);

+const struct of_device_id cs42l51_of_match[] = { + { .compatible = "cirrus,cs42l51", }, + { } +}; +MODULE_DEVICE_TABLE(of, cs42l51_of_match); + static int cs42l51_i2c_probe(struct i2c_client *i2c) { struct regmap_config config; --- a/sound/soc/codecs/cs42l51.c +++ b/sound/soc/codecs/cs42l51.c @@ -826,13 +826,6 @@ int __maybe_unused cs42l51_resume(struct } EXPORT_SYMBOL_GPL(cs42l51_resume);

-const struct of_device_id cs42l51_of_match[] = { - { .compatible = "cirrus,cs42l51", }, - { } -}; -MODULE_DEVICE_TABLE(of, cs42l51_of_match); -EXPORT_SYMBOL_GPL(cs42l51_of_match); - MODULE_AUTHOR("Arnaud Patard arnaud.patard@rtp-net.org"); MODULE_DESCRIPTION("Cirrus Logic CS42L51 ALSA SoC Codec Driver"); MODULE_LICENSE("GPL"); --- a/sound/soc/codecs/cs42l51.h +++ b/sound/soc/codecs/cs42l51.h @@ -16,7 +16,6 @@ int cs42l51_probe(struct device *dev, st void cs42l51_remove(struct device *dev); int __maybe_unused cs42l51_suspend(struct device *dev); int __maybe_unused cs42l51_resume(struct device *dev); -extern const struct of_device_id cs42l51_of_match[];

#define CS42L51_CHIP_ID 0x1B #define CS42L51_CHIP_REV_A 0x00

From: Johan Hovold johan+linaro@kernel.org

commit a5475829adcc600bc69ee9ff7c9e3e43fb4f8d30 upstream.

The MBHC resources must be released on component probe failure and removal so can not be tied to the lifetime of the component device.

This is specifically needed to allow probe deferrals of the sound card which otherwise fails when reprobing the codec component:

snd-sc8280xp sound: ASoC: failed to instantiate card -517 genirq: Flags mismatch irq 299. 00002001 (mbhc sw intr) vs. 00002001 (mbhc sw intr) wcd938x_codec audio-codec: Failed to request mbhc interrupts -16 wcd938x_codec audio-codec: mbhc initialization failed wcd938x_codec audio-codec: ASoC: error at snd_soc_component_probe on audio-codec: -16 snd-sc8280xp sound: ASoC: failed to instantiate card -16

Fixes: 0e5c9e7ff899 ("ASoC: codecs: wcd: add multi button Headset detection support") Cc: stable@vger.kernel.org # 5.14 Cc: Srinivas Kandagatla srinivas.kandagatla@linaro.org Signed-off-by: Johan Hovold johan+linaro@kernel.org Reviewed-by: Srinivas Kandagatla srinivas.kandagatla@linaro.org Link: https://lore.kernel.org/r/20230705123018.30903-7-johan+linaro@kernel.org Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/soc/codecs/wcd-mbhc-v2.c | 57 +++++++++++++++++++++++++++++------------ 1 file changed, 41 insertions(+), 16 deletions(-)

--- a/sound/soc/codecs/wcd-mbhc-v2.c +++ b/sound/soc/codecs/wcd-mbhc-v2.c @@ -1454,7 +1454,7 @@ struct wcd_mbhc *wcd_mbhc_init(struct sn return ERR_PTR(-EINVAL); }

- mbhc = devm_kzalloc(dev, sizeof(*mbhc), GFP_KERNEL); + mbhc = kzalloc(sizeof(*mbhc), GFP_KERNEL); if (!mbhc) return ERR_PTR(-ENOMEM);

@@ -1474,61 +1474,76 @@ struct wcd_mbhc *wcd_mbhc_init(struct sn

INIT_WORK(&mbhc->correct_plug_swch, wcd_correct_swch_plug);

- ret = devm_request_threaded_irq(dev, mbhc->intr_ids->mbhc_sw_intr, NULL, + ret = request_threaded_irq(mbhc->intr_ids->mbhc_sw_intr, NULL, wcd_mbhc_mech_plug_detect_irq, IRQF_ONESHOT | IRQF_TRIGGER_RISING, "mbhc sw intr", mbhc); if (ret) - goto err; + goto err_free_mbhc;

- ret = devm_request_threaded_irq(dev, mbhc->intr_ids->mbhc_btn_press_intr, NULL, + ret = request_threaded_irq(mbhc->intr_ids->mbhc_btn_press_intr, NULL, wcd_mbhc_btn_press_handler, IRQF_ONESHOT | IRQF_TRIGGER_RISING, "Button Press detect", mbhc); if (ret) - goto err; + goto err_free_sw_intr;

- ret = devm_request_threaded_irq(dev, mbhc->intr_ids->mbhc_btn_release_intr, NULL, + ret = request_threaded_irq(mbhc->intr_ids->mbhc_btn_release_intr, NULL, wcd_mbhc_btn_release_handler, IRQF_ONESHOT | IRQF_TRIGGER_RISING, "Button Release detect", mbhc); if (ret) - goto err; + goto err_free_btn_press_intr;

- ret = devm_request_threaded_irq(dev, mbhc->intr_ids->mbhc_hs_ins_intr, NULL, + ret = request_threaded_irq(mbhc->intr_ids->mbhc_hs_ins_intr, NULL, wcd_mbhc_adc_hs_ins_irq, IRQF_ONESHOT | IRQF_TRIGGER_RISING, "Elect Insert", mbhc); if (ret) - goto err; + goto err_free_btn_release_intr;

disable_irq_nosync(mbhc->intr_ids->mbhc_hs_ins_intr);

- ret = devm_request_threaded_irq(dev, mbhc->intr_ids->mbhc_hs_rem_intr, NULL, + ret = request_threaded_irq(mbhc->intr_ids->mbhc_hs_rem_intr, NULL, wcd_mbhc_adc_hs_rem_irq, IRQF_ONESHOT | IRQF_TRIGGER_RISING, "Elect Remove", mbhc); if (ret) - goto err; + goto err_free_hs_ins_intr;

disable_irq_nosync(mbhc->intr_ids->mbhc_hs_rem_intr);

- ret = devm_request_threaded_irq(dev, mbhc->intr_ids->hph_left_ocp, NULL, + ret = request_threaded_irq(mbhc->intr_ids->hph_left_ocp, NULL, wcd_mbhc_hphl_ocp_irq, IRQF_ONESHOT | IRQF_TRIGGER_RISING, "HPH_L OCP detect", mbhc); if (ret) - goto err; + goto err_free_hs_rem_intr;

- ret = devm_request_threaded_irq(dev, mbhc->intr_ids->hph_right_ocp, NULL, + ret = request_threaded_irq(mbhc->intr_ids->hph_right_ocp, NULL, wcd_mbhc_hphr_ocp_irq, IRQF_ONESHOT | IRQF_TRIGGER_RISING, "HPH_R OCP detect", mbhc); if (ret) - goto err; + goto err_free_hph_left_ocp;

return mbhc; -err: + +err_free_hph_left_ocp: + free_irq(mbhc->intr_ids->hph_left_ocp, mbhc); +err_free_hs_rem_intr: + free_irq(mbhc->intr_ids->mbhc_hs_rem_intr, mbhc); +err_free_hs_ins_intr: + free_irq(mbhc->intr_ids->mbhc_hs_ins_intr, mbhc); +err_free_btn_release_intr: + free_irq(mbhc->intr_ids->mbhc_btn_release_intr, mbhc); +err_free_btn_press_intr: + free_irq(mbhc->intr_ids->mbhc_btn_press_intr, mbhc); +err_free_sw_intr: + free_irq(mbhc->intr_ids->mbhc_sw_intr, mbhc); +err_free_mbhc: + kfree(mbhc); + dev_err(dev, "Failed to request mbhc interrupts %d\n", ret);

return ERR_PTR(ret); @@ -1537,9 +1552,19 @@ EXPORT_SYMBOL(wcd_mbhc_init);

void wcd_mbhc_deinit(struct wcd_mbhc *mbhc) { + free_irq(mbhc->intr_ids->hph_right_ocp, mbhc); + free_irq(mbhc->intr_ids->hph_left_ocp, mbhc); + free_irq(mbhc->intr_ids->mbhc_hs_rem_intr, mbhc); + free_irq(mbhc->intr_ids->mbhc_hs_ins_intr, mbhc); + free_irq(mbhc->intr_ids->mbhc_btn_release_intr, mbhc); + free_irq(mbhc->intr_ids->mbhc_btn_press_intr, mbhc); + free_irq(mbhc->intr_ids->mbhc_sw_intr, mbhc); + mutex_lock(&mbhc->lock); wcd_cancel_hs_detect_plug(mbhc, &mbhc->correct_plug_swch); mutex_unlock(&mbhc->lock); + + kfree(mbhc); } EXPORT_SYMBOL(wcd_mbhc_deinit);

From: Sheetal sheetal@nvidia.com

commit 49bd7b08149417a30aa7d92c8c85b3518de44a76 upstream.

Byte mask for channel-1 of stream-1 is not getting enabled and this causes failures during AMX use cases. This happens because the byte map value 0 matches the byte map array and put() callback returns without enabling the corresponding bits in the byte mask.

AMX supports 4 input streams and each stream can take a maximum of 16 channels. Each byte in the output frame is uniquely mapped to a byte in one of these 4 inputs. This mapping is done with the help of byte map array via user space control setting. The byte map array size in the driver is 16 and each array element is of size 4 bytes. This corresponds to 64 byte map values.

Each byte in the byte map array can have any value between 0 to 255 to enable the corresponding bits in the byte mask. The value 256 is used as a way to disable the byte map. However the byte map array element cannot store this value. The put() callback disables the byte mask for 256 value and byte map value is reset to 0 for this case. This causes problems during subsequent runs since put() callback, for value of 0, just returns without enabling the byte mask. In short, the problem is coming because 0 and 256 control values are stored as 0 in the byte map array.

Right now fix the put() callback by actually looking at the byte mask array state to identify if any change is needed and update the fields accordingly. The get() callback needs an update as well to return the correct control value that user has set before. Note that when user sets 256, the value is stored as 0 and byte mask is disabled. So byte mask state is used to either return 256 or the value from byte map array.

Given above, this looks bit complicated and all this happens because the byte map array is tightly packed and cannot actually store the 256 value. Right now the priority is to fix the existing failure and a TODO item is put to improve this logic.

Fixes: 8db78ace1ba8 ("ASoC: tegra: Fix kcontrol put callback in AMX") Cc: stable@vger.kernel.org Signed-off-by: Sheetal sheetal@nvidia.com Reviewed-by: Mohan Kumar D mkumard@nvidia.com Reviewed-by: Sameer Pujar spujar@nvidia.com Link: https://lore.kernel.org/r/1688015537-31682-2-git-send-email-spujar@nvidia.co... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/soc/tegra/tegra210_amx.c | 40 ++++++++++++++++++++++------------------ 1 file changed, 22 insertions(+), 18 deletions(-)

--- a/sound/soc/tegra/tegra210_amx.c +++ b/sound/soc/tegra/tegra210_amx.c @@ -2,7 +2,7 @@ // // tegra210_amx.c - Tegra210 AMX driver // -// Copyright (c) 2021 NVIDIA CORPORATION. All rights reserved. +// Copyright (c) 2021-2023 NVIDIA CORPORATION. All rights reserved.

#include <linux/clk.h> #include <linux/device.h> @@ -203,10 +203,20 @@ static int tegra210_amx_get_byte_map(str else enabled = amx->byte_mask[0] & (1 << reg);

+ /* + * TODO: Simplify this logic to just return from bytes_map[] + * + * Presently below is required since bytes_map[] is + * tightly packed and cannot store the control value of 256. + * Byte mask state is used to know if 256 needs to be returned. + * Note that for control value of 256, the put() call stores 0 + * in the bytes_map[] and disables the corresponding bit in + * byte_mask[]. + */ if (enabled) ucontrol->value.integer.value[0] = bytes_map[reg]; else - ucontrol->value.integer.value[0] = 0; + ucontrol->value.integer.value[0] = 256;

return 0; } @@ -221,25 +231,19 @@ static int tegra210_amx_put_byte_map(str unsigned char *bytes_map = (unsigned char *)&amx->map; int reg = mc->reg; int value = ucontrol->value.integer.value[0]; + unsigned int mask_val = amx->byte_mask[reg / 32];

- if (value == bytes_map[reg]) + if (value >= 0 && value <= 255) + mask_val |= (1 << (reg % 32)); + else + mask_val &= ~(1 << (reg % 32)); + + if (mask_val == amx->byte_mask[reg / 32]) return 0;

- if (value >= 0 && value <= 255) { - /* Update byte map and enable slot */ - bytes_map[reg] = value; - if (reg > 31) - amx->byte_mask[1] |= (1 << (reg - 32)); - else - amx->byte_mask[0] |= (1 << reg); - } else { - /* Reset byte map and disable slot */ - bytes_map[reg] = 0; - if (reg > 31) - amx->byte_mask[1] &= ~(1 << (reg - 32)); - else - amx->byte_mask[0] &= ~(1 << reg); - } + /* Update byte map and slot */ + bytes_map[reg] = value % 256; + amx->byte_mask[reg / 32] = mask_val;

return 1; }

From: Johan Hovold johan+linaro@kernel.org

commit 7dfae2631bfbdebecd35fe7b472ab3cc95c9ed66 upstream.

MBHC initialisation can fail so add the missing error handling to avoid dereferencing an error pointer when later configuring the jack:

Unable to handle kernel paging request at virtual address fffffffffffffff8

pc : wcd_mbhc_start+0x28/0x380 [snd_soc_wcd_mbhc] lr : wcd938x_codec_set_jack+0x28/0x48 [snd_soc_wcd938x]

Call trace: wcd_mbhc_start+0x28/0x380 [snd_soc_wcd_mbhc] wcd938x_codec_set_jack+0x28/0x48 [snd_soc_wcd938x] snd_soc_component_set_jack+0x28/0x8c [snd_soc_core] qcom_snd_wcd_jack_setup+0x7c/0x19c [snd_soc_qcom_common] sc8280xp_snd_init+0x20/0x2c [snd_soc_sc8280xp] snd_soc_link_init+0x28/0x90 [snd_soc_core] snd_soc_bind_card+0x628/0xbfc [snd_soc_core] snd_soc_register_card+0xec/0x104 [snd_soc_core] devm_snd_soc_register_card+0x4c/0xa4 [snd_soc_core] sc8280xp_platform_probe+0xf0/0x108 [snd_soc_sc8280xp]

Fixes: bcee7ed09b8e ("ASoC: codecs: wcd938x: add Multi Button Headset Control support") Cc: stable@vger.kernel.org # 5.15 Cc: Srinivas Kandagatla srinivas.kandagatla@linaro.org Signed-off-by: Johan Hovold johan+linaro@kernel.org Link: https://lore.kernel.org/r/20230703124701.11734-1-johan+linaro@kernel.org Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/soc/codecs/wcd938x.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/sound/soc/codecs/wcd938x.c +++ b/sound/soc/codecs/wcd938x.c @@ -2625,6 +2625,8 @@ static int wcd938x_mbhc_init(struct snd_ WCD938X_IRQ_HPHR_OCP_INT);

wcd938x->wcd_mbhc = wcd_mbhc_init(component, &mbhc_cb, intr_ids, wcd_mbhc_fields, true); + if (IS_ERR(wcd938x->wcd_mbhc)) + return PTR_ERR(wcd938x->wcd_mbhc);

snd_soc_add_component_controls(component, impedance_detect_controls, ARRAY_SIZE(impedance_detect_controls));

From: Johan Hovold johan+linaro@kernel.org

commit 85a61b1ce461a3f62f1019e5e6423c393c542bff upstream.

Make sure to resume the codec and soundwire device before trying to read the codec variant and configure the device during component probe.

This specifically avoids interpreting (a masked and shifted) -EBUSY errno as the variant:

wcd938x_codec audio-codec: ASoC: error at soc_component_read_no_lock on audio-codec for register: [0x000034b0] -16

when the soundwire device happens to be suspended, which in turn prevents some headphone controls from being registered.

Fixes: 8d78602aa87a ("ASoC: codecs: wcd938x: add basic driver") Cc: stable@vger.kernel.org # 5.14 Cc: Srinivas Kandagatla srinivas.kandagatla@linaro.org Reported-by: Steev Klimaszewski steev@kali.org Signed-off-by: Johan Hovold johan+linaro@kernel.org Link: https://lore.kernel.org/r/20230630120318.6571-1-johan+linaro@kernel.org Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/soc/codecs/wcd938x.c | 6 ++++++ 1 file changed, 6 insertions(+)

--- a/sound/soc/codecs/wcd938x.c +++ b/sound/soc/codecs/wcd938x.c @@ -3095,6 +3095,10 @@ static int wcd938x_soc_codec_probe(struc

snd_soc_component_init_regmap(component, wcd938x->regmap);

+ ret = pm_runtime_resume_and_get(dev); + if (ret < 0) + return ret; + wcd938x->variant = snd_soc_component_read_field(component, WCD938X_DIGITAL_EFUSE_REG_0, WCD938X_ID_MASK); @@ -3112,6 +3116,8 @@ static int wcd938x_soc_codec_probe(struc (WCD938X_DIGITAL_INTR_LEVEL_0 + i), 0); }

+ pm_runtime_put(dev); + wcd938x->hphr_pdm_wd_int = regmap_irq_get_virq(wcd938x->irq_chip, WCD938X_IRQ_HPHR_PDM_WD_INT); wcd938x->hphl_pdm_wd_int = regmap_irq_get_virq(wcd938x->irq_chip,

From: Eric Whitney enwlinux@gmail.com

commit 6909cf5c4101214f4305a62d582a5b93c7e1eb9a upstream.

When run on a file system where the inline_data feature has been enabled, xfstests generic/269, generic/270, and generic/476 cause ext4 to emit error messages indicating that inline directory entries are corrupted. This occurs because the inline offset used to locate inline directory entries in the inode body is not updated when an xattr in that shared region is deleted and the region is shifted in memory to recover the space it occupied. If the deleted xattr precedes the system.data attribute, which points to the inline directory entries, that attribute will be moved further up in the region. The inline offset continues to point to whatever is located in system.data's former location, with unfortunate effects when used to access directory entries or (presumably) inline data in the inode body.

Cc: stable@kernel.org Signed-off-by: Eric Whitney enwlinux@gmail.com Link: https://lore.kernel.org/r/20230522181520.1570360-1-enwlinux@gmail.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ext4/xattr.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+)

--- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1732,6 +1732,20 @@ static int ext4_xattr_set_entry(struct e memmove(here, (void *)here + size, (void *)last - (void *)here + sizeof(__u32)); memset(last, 0, size); + + /* + * Update i_inline_off - moved ibody region might contain + * system.data attribute. Handling a failure here won't + * cause other complications for setting an xattr. + */ + if (!is_block && ext4_has_inline_data(inode)) { + ret = ext4_find_inline_data_nolock(inode); + if (ret) { + ext4_warning_inode(inode, + "unable to update i_inline_off"); + goto out; + } + } } else if (s->not_found) { /* Insert new name. */ size_t size = EXT4_XATTR_LEN(name_len);

[ Upstream commit 8cabf83c7aa54530e699be56249fb44f9505c4f3 ]

There is no apparent reason for the massive code duplication.

Signed-off-by: Oswald Buddenhagen oswald.buddenhagen@gmx.de Link: https://lore.kernel.org/r/20230510173917.3073107-3-oswald.buddenhagen@gmx.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/pci/emu10k1/emufx.c | 112 +++------------------------------------------- 1 file changed, 9 insertions(+), 103 deletions(-)

--- a/sound/pci/emu10k1/emufx.c +++ b/sound/pci/emu10k1/emufx.c @@ -1563,14 +1563,8 @@ A_OP(icode, &ptr, iMAC0, A_GPR(var), A_G gpr += 2;

/* Master volume (will be renamed later) */ - A_OP(icode, &ptr, iMAC0, A_GPR(playback+0+SND_EMU10K1_PLAYBACK_CHANNELS), A_C_00000000, A_GPR(gpr), A_GPR(playback+0+SND_EMU10K1_PLAYBACK_CHANNELS)); - A_OP(icode, &ptr, iMAC0, A_GPR(playback+1+SND_EMU10K1_PLAYBACK_CHANNELS), A_C_00000000, A_GPR(gpr), A_GPR(playback+1+SND_EMU10K1_PLAYBACK_CHANNELS)); - A_OP(icode, &ptr, iMAC0, A_GPR(playback+2+SND_EMU10K1_PLAYBACK_CHANNELS), A_C_00000000, A_GPR(gpr), A_GPR(playback+2+SND_EMU10K1_PLAYBACK_CHANNELS)); - A_OP(icode, &ptr, iMAC0, A_GPR(playback+3+SND_EMU10K1_PLAYBACK_CHANNELS), A_C_00000000, A_GPR(gpr), A_GPR(playback+3+SND_EMU10K1_PLAYBACK_CHANNELS)); - A_OP(icode, &ptr, iMAC0, A_GPR(playback+4+SND_EMU10K1_PLAYBACK_CHANNELS), A_C_00000000, A_GPR(gpr), A_GPR(playback+4+SND_EMU10K1_PLAYBACK_CHANNELS)); - A_OP(icode, &ptr, iMAC0, A_GPR(playback+5+SND_EMU10K1_PLAYBACK_CHANNELS), A_C_00000000, A_GPR(gpr), A_GPR(playback+5+SND_EMU10K1_PLAYBACK_CHANNELS)); - A_OP(icode, &ptr, iMAC0, A_GPR(playback+6+SND_EMU10K1_PLAYBACK_CHANNELS), A_C_00000000, A_GPR(gpr), A_GPR(playback+6+SND_EMU10K1_PLAYBACK_CHANNELS)); - A_OP(icode, &ptr, iMAC0, A_GPR(playback+7+SND_EMU10K1_PLAYBACK_CHANNELS), A_C_00000000, A_GPR(gpr), A_GPR(playback+7+SND_EMU10K1_PLAYBACK_CHANNELS)); + for (z = 0; z < 8; z++) + A_OP(icode, &ptr, iMAC0, A_GPR(playback+z+SND_EMU10K1_PLAYBACK_CHANNELS), A_C_00000000, A_GPR(gpr), A_GPR(playback+z+SND_EMU10K1_PLAYBACK_CHANNELS)); snd_emu10k1_init_mono_control(&controls[nctl++], "Wave Master Playback Volume", gpr, 0); gpr += 2;

@@ -1654,102 +1648,14 @@ A_OP(icode, &ptr, iMAC0, A_GPR(var), A_G dev_dbg(emu->card->dev, "emufx.c: gpr=0x%x, tmp=0x%x\n", gpr, tmp); */ - /* For the EMU1010: How to get 32bit values from the DSP. High 16bits into L, low 16bits into R. */ - /* A_P16VIN(0) is delayed by one sample, - * so all other A_P16VIN channels will need to also be delayed - */ - /* Left ADC in. 1 of 2 */ snd_emu10k1_audigy_dsp_convert_32_to_2x16( icode, &ptr, tmp, bit_shifter16, A_P16VIN(0x0), A_FXBUS2(0) ); - /* Right ADC in 1 of 2 */ - gpr_map[gpr++] = 0x00000000; - /* Delaying by one sample: instead of copying the input - * value A_P16VIN to output A_FXBUS2 as in the first channel, - * we use an auxiliary register, delaying the value by one - * sample - */ - snd_emu10k1_audigy_dsp_convert_32_to_2x16( icode, &ptr, tmp, bit_shifter16, A_GPR(gpr - 1), A_FXBUS2(2) ); - A_OP(icode, &ptr, iACC3, A_GPR(gpr - 1), A_P16VIN(0x1), A_C_00000000, A_C_00000000); - gpr_map[gpr++] = 0x00000000; - snd_emu10k1_audigy_dsp_convert_32_to_2x16( icode, &ptr, tmp, bit_shifter16, A_GPR(gpr - 1), A_FXBUS2(4) ); - A_OP(icode, &ptr, iACC3, A_GPR(gpr - 1), A_P16VIN(0x2), A_C_00000000, A_C_00000000); - gpr_map[gpr++] = 0x00000000; - snd_emu10k1_audigy_dsp_convert_32_to_2x16( icode, &ptr, tmp, bit_shifter16, A_GPR(gpr - 1), A_FXBUS2(6) ); - A_OP(icode, &ptr, iACC3, A_GPR(gpr - 1), A_P16VIN(0x3), A_C_00000000, A_C_00000000); - /* For 96kHz mode */ - /* Left ADC in. 2 of 2 */ - gpr_map[gpr++] = 0x00000000; - snd_emu10k1_audigy_dsp_convert_32_to_2x16( icode, &ptr, tmp, bit_shifter16, A_GPR(gpr - 1), A_FXBUS2(0x8) ); - A_OP(icode, &ptr, iACC3, A_GPR(gpr - 1), A_P16VIN(0x4), A_C_00000000, A_C_00000000); - /* Right ADC in 2 of 2 */ - gpr_map[gpr++] = 0x00000000; - snd_emu10k1_audigy_dsp_convert_32_to_2x16( icode, &ptr, tmp, bit_shifter16, A_GPR(gpr - 1), A_FXBUS2(0xa) ); - A_OP(icode, &ptr, iACC3, A_GPR(gpr - 1), A_P16VIN(0x5), A_C_00000000, A_C_00000000); - gpr_map[gpr++] = 0x00000000; - snd_emu10k1_audigy_dsp_convert_32_to_2x16( icode, &ptr, tmp, bit_shifter16, A_GPR(gpr - 1), A_FXBUS2(0xc) ); - A_OP(icode, &ptr, iACC3, A_GPR(gpr - 1), A_P16VIN(0x6), A_C_00000000, A_C_00000000); - gpr_map[gpr++] = 0x00000000; - snd_emu10k1_audigy_dsp_convert_32_to_2x16( icode, &ptr, tmp, bit_shifter16, A_GPR(gpr - 1), A_FXBUS2(0xe) ); - A_OP(icode, &ptr, iACC3, A_GPR(gpr - 1), A_P16VIN(0x7), A_C_00000000, A_C_00000000); - /* Pavel Hofman - we still have voices, A_FXBUS2s, and - * A_P16VINs available - - * let's add 8 more capture channels - total of 16 - */ - gpr_map[gpr++] = 0x00000000; - snd_emu10k1_audigy_dsp_convert_32_to_2x16(icode, &ptr, tmp, - bit_shifter16, - A_GPR(gpr - 1), - A_FXBUS2(0x10)); - A_OP(icode, &ptr, iACC3, A_GPR(gpr - 1), A_P16VIN(0x8), - A_C_00000000, A_C_00000000); - gpr_map[gpr++] = 0x00000000; - snd_emu10k1_audigy_dsp_convert_32_to_2x16(icode, &ptr, tmp, - bit_shifter16, - A_GPR(gpr - 1), - A_FXBUS2(0x12)); - A_OP(icode, &ptr, iACC3, A_GPR(gpr - 1), A_P16VIN(0x9), - A_C_00000000, A_C_00000000); - gpr_map[gpr++] = 0x00000000; - snd_emu10k1_audigy_dsp_convert_32_to_2x16(icode, &ptr, tmp, - bit_shifter16, - A_GPR(gpr - 1), - A_FXBUS2(0x14)); - A_OP(icode, &ptr, iACC3, A_GPR(gpr - 1), A_P16VIN(0xa), - A_C_00000000, A_C_00000000); - gpr_map[gpr++] = 0x00000000; - snd_emu10k1_audigy_dsp_convert_32_to_2x16(icode, &ptr, tmp, - bit_shifter16, - A_GPR(gpr - 1), - A_FXBUS2(0x16)); - A_OP(icode, &ptr, iACC3, A_GPR(gpr - 1), A_P16VIN(0xb), - A_C_00000000, A_C_00000000); - gpr_map[gpr++] = 0x00000000; - snd_emu10k1_audigy_dsp_convert_32_to_2x16(icode, &ptr, tmp, - bit_shifter16, - A_GPR(gpr - 1), - A_FXBUS2(0x18)); - A_OP(icode, &ptr, iACC3, A_GPR(gpr - 1), A_P16VIN(0xc), - A_C_00000000, A_C_00000000); - gpr_map[gpr++] = 0x00000000; - snd_emu10k1_audigy_dsp_convert_32_to_2x16(icode, &ptr, tmp, - bit_shifter16, - A_GPR(gpr - 1), - A_FXBUS2(0x1a)); - A_OP(icode, &ptr, iACC3, A_GPR(gpr - 1), A_P16VIN(0xd), - A_C_00000000, A_C_00000000); - gpr_map[gpr++] = 0x00000000; - snd_emu10k1_audigy_dsp_convert_32_to_2x16(icode, &ptr, tmp, - bit_shifter16, - A_GPR(gpr - 1), - A_FXBUS2(0x1c)); - A_OP(icode, &ptr, iACC3, A_GPR(gpr - 1), A_P16VIN(0xe), - A_C_00000000, A_C_00000000); - gpr_map[gpr++] = 0x00000000; - snd_emu10k1_audigy_dsp_convert_32_to_2x16(icode, &ptr, tmp, - bit_shifter16, - A_GPR(gpr - 1), - A_FXBUS2(0x1e)); - A_OP(icode, &ptr, iACC3, A_GPR(gpr - 1), A_P16VIN(0xf), - A_C_00000000, A_C_00000000); + /* A_P16VIN(0) is delayed by one sample, so all other A_P16VIN channels + * will need to also be delayed; we use an auxiliary register for that. */ + for (z = 1; z < 0x10; z++) { + snd_emu10k1_audigy_dsp_convert_32_to_2x16( icode, &ptr, tmp, bit_shifter16, A_GPR(gpr), A_FXBUS2(z * 2) ); + A_OP(icode, &ptr, iACC3, A_GPR(gpr), A_P16VIN(z), A_C_00000000, A_C_00000000); + gpr_map[gpr++] = 0x00000000; + } }

#if 0

[ Upstream commit d6a95db3c7ad160bc16b89e36449705309b52bcb ]

There's issue as follows when do fault injection: WARNING: CPU: 1 PID: 14870 at include/linux/quotaops.h:51 dquot_disable+0x13b7/0x18c0 Modules linked in: CPU: 1 PID: 14870 Comm: fsconfig Not tainted 6.3.0-next-20230505-00006-g5107a9c821af-dirty #541 RIP: 0010:dquot_disable+0x13b7/0x18c0 RSP: 0018:ffffc9000acc79e0 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff88825e41b980 RDX: 0000000000000000 RSI: ffff88825e41b980 RDI: 0000000000000002 RBP: ffff888179f68000 R08: ffffffff82087ca7 R09: 0000000000000000 R10: 0000000000000001 R11: ffffed102f3ed026 R12: ffff888179f68130 R13: ffff888179f68110 R14: dffffc0000000000 R15: ffff888179f68118 FS: 00007f450a073740(0000) GS:ffff88882fc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffe96f2efd8 CR3: 000000025c8ad000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> dquot_load_quota_sb+0xd53/0x1060 dquot_resume+0x172/0x230 ext4_reconfigure+0x1dc6/0x27b0 reconfigure_super+0x515/0xa90 __x64_sys_fsconfig+0xb19/0xd20 do_syscall_64+0x39/0xb0 entry_SYSCALL_64_after_hwframe+0x63/0xcd

Above issue may happens as follows: ProcessA ProcessB ProcessC sys_fsconfig vfs_fsconfig_locked reconfigure_super ext4_remount dquot_suspend -> suspend all type quota

sys_fsconfig vfs_fsconfig_locked reconfigure_super ext4_remount dquot_resume ret = dquot_load_quota_sb add_dquot_ref do_open -> open file O_RDWR vfs_open do_dentry_open get_write_access atomic_inc_unless_negative(&inode->i_writecount) ext4_file_open dquot_file_open dquot_initialize __dquot_initialize dqget atomic_inc(&dquot->dq_count);

__dquot_initialize __dquot_initialize dqget if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) ext4_acquire_dquot -> Return error DQ_ACTIVE_B flag isn't set dquot_disable invalidate_dquots if (atomic_read(&dquot->dq_count)) dqgrab WARN_ON_ONCE(!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) -> Trigger warning

In the above scenario, 'dquot->dq_flags' has no DQ_ACTIVE_B is normal when dqgrab(). To solve above issue just replace the dqgrab() use in invalidate_dquots() with atomic_inc(&dquot->dq_count).

Signed-off-by: Ye Bin yebin10@huawei.com Signed-off-by: Jan Kara jack@suse.cz Message-Id: 20230605140731.2427629-3-yebin10@huawei.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/quota/dquot.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -555,7 +555,7 @@ restart: continue; /* Wait for dquot users */ if (atomic_read(&dquot->dq_count)) { - dqgrab(dquot); + atomic_inc(&dquot->dq_count); spin_unlock(&dq_list_lock); /* * Once dqput() wakes us up, we know it's time to free

[ Upstream commit f723edb8a532cd26e1ff0a2b271d73762d48f762 ]

Porting overlayfs to the new amount api I started experiencing random crashes that couldn't be explained easily. So after much debugging and reasoning it became clear that struct ovl_entry requires the point to struct vfsmount to be the first member and of type struct vfsmount.

During the port I added a new member at the beginning of struct ovl_entry which broke all over the place in the form of random crashes and cache corruptions. While there's a comment in ovl_free_fs() to the effect of "Hack! Reuse ofs->layers as a vfsmount array before freeing it" there's no such comment on struct ovl_entry which makes this easy to trip over.

Add a comment and two static asserts for both the offset and the type of pointer in struct ovl_entry.

Signed-off-by: Christian Brauner brauner@kernel.org Signed-off-by: Amir Goldstein amir73il@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/overlayfs/ovl_entry.h | 9 +++++++++ 1 file changed, 9 insertions(+)

--- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -32,6 +32,7 @@ struct ovl_sb { };

struct ovl_layer { + /* ovl_free_fs() relies on @mnt being the first member! */ struct vfsmount *mnt; /* Trap in ovl inode cache */ struct inode *trap; @@ -42,6 +43,14 @@ struct ovl_layer { int fsid; };

+/* + * ovl_free_fs() relies on @mnt being the first member when unmounting + * the private mounts created for each layer. Let's check both the + * offset and type. + */ +static_assert(offsetof(struct ovl_layer, mnt) == 0); +static_assert(__same_type(typeof_member(struct ovl_layer, mnt), struct vfsmount *)); + struct ovl_path { const struct ovl_layer *layer; struct dentry *dentry;

[ Upstream commit 4e302336d5ca1767a06beee7596a72d3bdc8d983 ]

Syzkaller reported the following issue:

UBSAN: array-index-out-of-bounds in fs/jfs/jfs_dmap.c:1965:6 index -84 is out of range for type 's8[341]' (aka 'signed char[341]') CPU: 1 PID: 4995 Comm: syz-executor146 Not tainted 6.4.0-rc6-syzkaller-00037-gb6dad5178cea #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/27/2023 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1e7/0x2d0 lib/dump_stack.c:106 ubsan_epilogue lib/ubsan.c:217 [inline] __ubsan_handle_out_of_bounds+0x11c/0x150 lib/ubsan.c:348 dbAllocDmapLev+0x3e5/0x430 fs/jfs/jfs_dmap.c:1965 dbAllocCtl+0x113/0x920 fs/jfs/jfs_dmap.c:1809 dbAllocAG+0x28f/0x10b0 fs/jfs/jfs_dmap.c:1350 dbAlloc+0x658/0xca0 fs/jfs/jfs_dmap.c:874 dtSplitUp fs/jfs/jfs_dtree.c:974 [inline] dtInsert+0xda7/0x6b00 fs/jfs/jfs_dtree.c:863 jfs_create+0x7b6/0xbb0 fs/jfs/namei.c:137 lookup_open fs/namei.c:3492 [inline] open_last_lookups fs/namei.c:3560 [inline] path_openat+0x13df/0x3170 fs/namei.c:3788 do_filp_open+0x234/0x490 fs/namei.c:3818 do_sys_openat2+0x13f/0x500 fs/open.c:1356 do_sys_open fs/open.c:1372 [inline] __do_sys_openat fs/open.c:1388 [inline] __se_sys_openat fs/open.c:1383 [inline] __x64_sys_openat+0x247/0x290 fs/open.c:1383 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f1f4e33f7e9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 51 14 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffc21129578 EFLAGS: 00000246 ORIG_RAX: 0000000000000101 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f1f4e33f7e9 RDX: 000000000000275a RSI: 0000000020000040 RDI: 00000000ffffff9c RBP: 00007f1f4e2ff080 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f1f4e2ff110 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 </TASK>

The bug occurs when the dbAllocDmapLev()function attempts to access dp->tree.stree[leafidx + LEAFIND] while the leafidx value is negative.

To rectify this, the patch introduces a safeguard within the dbAllocDmapLev() function. A check has been added to verify if leafidx is negative. If it is, the function immediately returns an I/O error, preventing any further execution that could potentially cause harm.

Tested via syzbot.

Reported-by: syzbot+853a6f4dfa3cf37d3aea@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=ae2f5a27a07ae44b0f17 Signed-off-by: Yogesh yogi.kernel@gmail.com Signed-off-by: Dave Kleikamp dave.kleikamp@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/jfs/jfs_dmap.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -1959,6 +1959,9 @@ dbAllocDmapLev(struct bmap * bmp, if (dbFindLeaf((dmtree_t *) & dp->tree, l2nb, &leafidx)) return -ENOSPC;

+ if (leafidx < 0) + return -EIO; + /* determine the block number within the file system corresponding * to the leaf at which free space was found. */

[ Upstream commit 47cfdc338d674d38f4b2f22b7612cc6a2763ba27 ]

Syzkaller reported an issue where txBegin may be called on a superblock in a read-only mounted filesystem which leads to NULL pointer deref. This could be solved by checking if the filesystem is read-only before calling txBegin, and returning with appropiate error code.

Reported-By: syzbot+f1faa20eec55e0c8644c@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=be7e52c50c5182cc09a09ea6fc456446b2039de...

Signed-off-by: Immad Mir mirimmad17@gmail.com Signed-off-by: Dave Kleikamp dave.kleikamp@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/jfs/namei.c | 5 +++++ 1 file changed, 5 insertions(+)

--- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -799,6 +799,11 @@ static int jfs_link(struct dentry *old_d if (rc) goto out;

+ if (isReadOnly(ip)) { + jfs_error(ip->i_sb, "read-only filesystem\n"); + return -EROFS; + } + tid = txBegin(ip->i_sb, 0);

mutex_lock_nested(&JFS_IP(dir)->commit_mutex, COMMIT_MUTEX_PARENT);

From: Hans de Goede hdegoede@redhat.com

[ Upstream commit 23d28cc0444be3f694eb986cd653b6888b78431d ]

The Dell Studio 1569 predates Windows 8, so it defaults to using acpi_video# for backlight control, but this is non functional on this model.

Add a DMI quirk to use the native intel_backlight interface which does work properly.

Reported-by: raycekarneal raycekarneal@gmail.com Signed-off-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/video_detect.c | 8 ++++++++ 1 file changed, 8 insertions(+)

--- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -512,6 +512,14 @@ static const struct dmi_system_id video_ }, { .callback = video_detect_force_native, + /* Dell Studio 1569 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Studio 1569"), + }, + }, + { + .callback = video_detect_force_native, /* Acer Aspire 3830TG */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Acer"),

From: Paul E. McKenney paulmck@kernel.org

[ Upstream commit 9146eb25495ea8bfb5010192e61e3ed5805ce9ef ]

The per-CPU rcu_data structure's ->cpu_no_qs.b.exp field is updated only on the instance corresponding to the current CPU, but can be read more widely. Unmarked accesses are OK from the corresponding CPU, but only if interrupts are disabled, given that interrupt handlers can and do modify this field.

Unfortunately, although the load from rcu_preempt_deferred_qs() is always carried out from the corresponding CPU, interrupts are not necessarily disabled. This commit therefore upgrades this load to READ_ONCE.

Similarly, the diagnostic access from synchronize_rcu_expedited_wait() might run with interrupts disabled and from some other CPU. This commit therefore marks this load with data_race().

Finally, the C-language access in rcu_preempt_ctxt_queue() is OK as is because interrupts are disabled and this load is always from the corresponding CPU. This commit adds a comment giving the rationale for this access being safe.

This data race was reported by KCSAN. Not appropriate for backporting due to failure being unlikely.

Signed-off-by: Paul E. McKenney paulmck@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/rcu/tree_exp.h | 2 +- kernel/rcu/tree_plugin.h | 4 +++- 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index e25321dbb068e..aa3ec3c3b9f75 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -641,7 +641,7 @@ static void synchronize_rcu_expedited_wait(void) "O."[!!cpu_online(cpu)], "o."[!!(rdp->grpmask & rnp->expmaskinit)], "N."[!!(rdp->grpmask & rnp->expmaskinitnext)], - "D."[!!(rdp->cpu_no_qs.b.exp)]); + "D."[!!data_race(rdp->cpu_no_qs.b.exp)]); } } pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n", diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index e3142ee35fc6a..044026abfdd7f 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -257,6 +257,8 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) * GP should not be able to end until we report, so there should be * no need to check for a subsequent expedited GP. (Though we are * still in a quiescent state in any case.) + * + * Interrupts are disabled, so ->cpu_no_qs.b.exp cannot change. */ if (blkd_state & RCU_EXP_BLKD && rdp->cpu_no_qs.b.exp) rcu_report_exp_rdp(rdp); @@ -941,7 +943,7 @@ notrace void rcu_preempt_deferred_qs(struct task_struct *t) { struct rcu_data *rdp = this_cpu_ptr(&rcu_data);

- if (rdp->cpu_no_qs.b.exp) + if (READ_ONCE(rdp->cpu_no_qs.b.exp)) rcu_report_exp_rdp(rdp); }

From: Maxime Bizon mbizon@freebox.fr

[ Upstream commit e2ceb1de2f83aafd8003f0b72dfd4b7441e97d14 ]

Because of what seems to be a typo, a 6Ghz-only phy for which the BDF does not allow the 7115Mhz channel will fail to register:

WARNING: CPU: 2 PID: 106 at net/wireless/core.c:907 wiphy_register+0x914/0x954 Modules linked in: ath11k_pci sbsa_gwdt CPU: 2 PID: 106 Comm: kworker/u8:5 Not tainted 6.3.0-rc7-next-20230418-00549-g1e096a17625a-dirty #9 Hardware name: Freebox V7R Board (DT) Workqueue: ath11k_qmi_driver_event ath11k_qmi_driver_event_work pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : wiphy_register+0x914/0x954 lr : ieee80211_register_hw+0x67c/0xc10 sp : ffffff800b123aa0 x29: ffffff800b123aa0 x28: 0000000000000000 x27: 0000000000000000 x26: 0000000000000000 x25: 0000000000000006 x24: ffffffc008d51418 x23: ffffffc008cb0838 x22: ffffff80176c2460 x21: 0000000000000168 x20: ffffff80176c0000 x19: ffffff80176c03e0 x18: 0000000000000014 x17: 00000000cbef338c x16: 00000000d2a26f21 x15: 00000000ad6bb85f x14: 0000000000000020 x13: 0000000000000020 x12: 00000000ffffffbd x11: 0000000000000208 x10: 00000000fffffdf7 x9 : ffffffc009394718 x8 : ffffff80176c0528 x7 : 000000007fffffff x6 : 0000000000000006 x5 : 0000000000000005 x4 : ffffff800b304284 x3 : ffffff800b304284 x2 : ffffff800b304d98 x1 : 0000000000000000 x0 : 0000000000000000 Call trace: wiphy_register+0x914/0x954 ieee80211_register_hw+0x67c/0xc10 ath11k_mac_register+0x7c4/0xe10 ath11k_core_qmi_firmware_ready+0x1f4/0x570 ath11k_qmi_driver_event_work+0x198/0x590 process_one_work+0x1b8/0x328 worker_thread+0x6c/0x414 kthread+0x100/0x104 ret_from_fork+0x10/0x20 ---[ end trace 0000000000000000 ]--- ath11k_pci 0002:01:00.0: ieee80211 registration failed: -22 ath11k_pci 0002:01:00.0: failed register the radio with mac80211: -22 ath11k_pci 0002:01:00.0: failed to create pdev core: -22

Signed-off-by: Maxime Bizon mbizon@freebox.fr Signed-off-by: Kalle Valo quic_kvalo@quicinc.com Link: https://lore.kernel.org/r/20230421145445.2612280-1-mbizon@freebox.fr Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/ath/ath11k/mac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index ef7617802491e..b19d44b3f5dfb 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -8715,7 +8715,7 @@ static int ath11k_mac_setup_channels_rates(struct ath11k *ar, }

if (supported_bands & WMI_HOST_WLAN_5G_CAP) { - if (reg_cap->high_5ghz_chan >= ATH11K_MAX_6G_FREQ) { + if (reg_cap->high_5ghz_chan >= ATH11K_MIN_6G_FREQ) { channels = kmemdup(ath11k_6ghz_channels, sizeof(ath11k_6ghz_channels), GFP_KERNEL); if (!channels) {

From: Martin KaFai Lau martin.lau@kernel.org

[ Upstream commit ee9fd0ac3017c4313be91a220a9ac4c99dde7ad4 ]

KCSAN reported a data-race when accessing node->ref. Although node->ref does not have to be accurate, take this chance to use a more common READ_ONCE() and WRITE_ONCE() pattern instead of data_race().

There is an existing bpf_lru_node_is_ref() and bpf_lru_node_set_ref(). This patch also adds bpf_lru_node_clear_ref() to do the WRITE_ONCE(node->ref, 0) also.

================================================================== BUG: KCSAN: data-race in __bpf_lru_list_rotate / __htab_lru_percpu_map_update_elem

write to 0xffff888137038deb of 1 bytes by task 11240 on cpu 1: __bpf_lru_node_move kernel/bpf/bpf_lru_list.c:113 [inline] __bpf_lru_list_rotate_active kernel/bpf/bpf_lru_list.c:149 [inline] __bpf_lru_list_rotate+0x1bf/0x750 kernel/bpf/bpf_lru_list.c:240 bpf_lru_list_pop_free_to_local kernel/bpf/bpf_lru_list.c:329 [inline] bpf_common_lru_pop_free kernel/bpf/bpf_lru_list.c:447 [inline] bpf_lru_pop_free+0x638/0xe20 kernel/bpf/bpf_lru_list.c:499 prealloc_lru_pop kernel/bpf/hashtab.c:290 [inline] __htab_lru_percpu_map_update_elem+0xe7/0x820 kernel/bpf/hashtab.c:1316 bpf_percpu_hash_update+0x5e/0x90 kernel/bpf/hashtab.c:2313 bpf_map_update_value+0x2a9/0x370 kernel/bpf/syscall.c:200 generic_map_update_batch+0x3ae/0x4f0 kernel/bpf/syscall.c:1687 bpf_map_do_batch+0x2d9/0x3d0 kernel/bpf/syscall.c:4534 __sys_bpf+0x338/0x810 __do_sys_bpf kernel/bpf/syscall.c:5096 [inline] __se_sys_bpf kernel/bpf/syscall.c:5094 [inline] __x64_sys_bpf+0x43/0x50 kernel/bpf/syscall.c:5094 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd

read to 0xffff888137038deb of 1 bytes by task 11241 on cpu 0: bpf_lru_node_set_ref kernel/bpf/bpf_lru_list.h:70 [inline] __htab_lru_percpu_map_update_elem+0x2f1/0x820 kernel/bpf/hashtab.c:1332 bpf_percpu_hash_update+0x5e/0x90 kernel/bpf/hashtab.c:2313 bpf_map_update_value+0x2a9/0x370 kernel/bpf/syscall.c:200 generic_map_update_batch+0x3ae/0x4f0 kernel/bpf/syscall.c:1687 bpf_map_do_batch+0x2d9/0x3d0 kernel/bpf/syscall.c:4534 __sys_bpf+0x338/0x810 __do_sys_bpf kernel/bpf/syscall.c:5096 [inline] __se_sys_bpf kernel/bpf/syscall.c:5094 [inline] __x64_sys_bpf+0x43/0x50 kernel/bpf/syscall.c:5094 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd

value changed: 0x01 -> 0x00

Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 11241 Comm: syz-executor.3 Not tainted 6.3.0-rc7-syzkaller-00136-g6a66fdd29ea1 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/30/2023 ==================================================================

Reported-by: syzbot+ebe648a84e8784763f82@syzkaller.appspotmail.com Signed-off-by: Martin KaFai Lau martin.lau@kernel.org Acked-by: Yonghong Song yhs@fb.com Link: https://lore.kernel.org/r/20230511043748.1384166-1-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov ast@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/bpf/bpf_lru_list.c | 21 +++++++++++++-------- kernel/bpf/bpf_lru_list.h | 7 ++----- 2 files changed, 15 insertions(+), 13 deletions(-)

diff --git a/kernel/bpf/bpf_lru_list.c b/kernel/bpf/bpf_lru_list.c index d99e89f113c43..3dabdd137d102 100644 --- a/kernel/bpf/bpf_lru_list.c +++ b/kernel/bpf/bpf_lru_list.c @@ -41,7 +41,12 @@ static struct list_head *local_pending_list(struct bpf_lru_locallist *loc_l) /* bpf_lru_node helpers */ static bool bpf_lru_node_is_ref(const struct bpf_lru_node *node) { - return node->ref; + return READ_ONCE(node->ref); +} + +static void bpf_lru_node_clear_ref(struct bpf_lru_node *node) +{ + WRITE_ONCE(node->ref, 0); }

static void bpf_lru_list_count_inc(struct bpf_lru_list *l, @@ -89,7 +94,7 @@ static void __bpf_lru_node_move_in(struct bpf_lru_list *l,

bpf_lru_list_count_inc(l, tgt_type); node->type = tgt_type; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_move(&node->list, &l->lists[tgt_type]); }

@@ -110,7 +115,7 @@ static void __bpf_lru_node_move(struct bpf_lru_list *l, bpf_lru_list_count_inc(l, tgt_type); node->type = tgt_type; } - node->ref = 0; + bpf_lru_node_clear_ref(node);

/* If the moving node is the next_inactive_rotation candidate, * move the next_inactive_rotation pointer also. @@ -353,7 +358,7 @@ static void __local_list_add_pending(struct bpf_lru *lru, *(u32 *)((void *)node + lru->hash_offset) = hash; node->cpu = cpu; node->type = BPF_LRU_LOCAL_LIST_T_PENDING; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_add(&node->list, local_pending_list(loc_l)); }

@@ -419,7 +424,7 @@ static struct bpf_lru_node *bpf_percpu_lru_pop_free(struct bpf_lru *lru, if (!list_empty(free_list)) { node = list_first_entry(free_list, struct bpf_lru_node, list); *(u32 *)((void *)node + lru->hash_offset) = hash; - node->ref = 0; + bpf_lru_node_clear_ref(node); __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_INACTIVE); }

@@ -522,7 +527,7 @@ static void bpf_common_lru_push_free(struct bpf_lru *lru, }

node->type = BPF_LRU_LOCAL_LIST_T_FREE; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_move(&node->list, local_free_list(loc_l));

raw_spin_unlock_irqrestore(&loc_l->lock, flags); @@ -568,7 +573,7 @@ static void bpf_common_lru_populate(struct bpf_lru *lru, void *buf,

node = (struct bpf_lru_node *)(buf + node_offset); node->type = BPF_LRU_LIST_T_FREE; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]); buf += elem_size; } @@ -594,7 +599,7 @@ static void bpf_percpu_lru_populate(struct bpf_lru *lru, void *buf, node = (struct bpf_lru_node *)(buf + node_offset); node->cpu = cpu; node->type = BPF_LRU_LIST_T_FREE; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]); i++; buf += elem_size; diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h index 4ea227c9c1ade..8f3c8b2b4490e 100644 --- a/kernel/bpf/bpf_lru_list.h +++ b/kernel/bpf/bpf_lru_list.h @@ -64,11 +64,8 @@ struct bpf_lru {

static inline void bpf_lru_node_set_ref(struct bpf_lru_node *node) { - /* ref is an approximation on access frequency. It does not - * have to be very accurate. Hence, no protection is used. - */ - if (!node->ref) - node->ref = 1; + if (!READ_ONCE(node->ref)) + WRITE_ONCE(node->ref, 1); }

int bpf_lru_init(struct bpf_lru *lru, bool percpu, u32 hash_offset,

From: Wen Gong quic_wgong@quicinc.com

[ Upstream commit 88ca89202f8e8afb5225eb5244d79cd67c15d744 ]

Sometimes board-2.bin does not have the regdb data which matched the parameters such as vendor, device, subsystem-vendor, subsystem-device and etc. Add default regdb data with 'bus=%s' into board-2.bin for WCN6855, then ath11k use 'bus=pci' to search regdb data in board-2.bin for WCN6855.

kernel: [ 122.515808] ath11k_pci 0000:03:00.0: boot using board name 'bus=pci,vendor=17cb,device=1103,subsystem-vendor=17cb,subsystem-device=3374,qmi-chip-id=2,qmi-board-id=262' kernel: [ 122.517240] ath11k_pci 0000:03:00.0: boot firmware request ath11k/WCN6855/hw2.0/board-2.bin size 6179564 kernel: [ 122.517280] ath11k_pci 0000:03:00.0: failed to fetch regdb data for bus=pci,vendor=17cb,device=1103,subsystem-vendor=17cb,subsystem-device=3374,qmi-chip-id=2,qmi-board-id=262 from ath11k/WCN6855/hw2.0/board-2.bin kernel: [ 122.517464] ath11k_pci 0000:03:00.0: boot using board name 'bus=pci' kernel: [ 122.518901] ath11k_pci 0000:03:00.0: boot firmware request ath11k/WCN6855/hw2.0/board-2.bin size 6179564 kernel: [ 122.518915] ath11k_pci 0000:03:00.0: board name kernel: [ 122.518917] ath11k_pci 0000:03:00.0: 00000000: 62 75 73 3d 70 63 69 bus=pci kernel: [ 122.518918] ath11k_pci 0000:03:00.0: boot found match regdb data for name 'bus=pci' kernel: [ 122.518920] ath11k_pci 0000:03:00.0: boot found regdb data for 'bus=pci' kernel: [ 122.518921] ath11k_pci 0000:03:00.0: fetched regdb

Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3

Signed-off-by: Wen Gong quic_wgong@quicinc.com Signed-off-by: Kalle Valo quic_kvalo@quicinc.com Link: https://lore.kernel.org/r/20230517133959.8224-1-quic_wgong@quicinc.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/ath/ath11k/core.c | 53 +++++++++++++++++++------- 1 file changed, 40 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c index b99180bc81723..893fefadbba96 100644 --- a/drivers/net/wireless/ath/ath11k/core.c +++ b/drivers/net/wireless/ath/ath11k/core.c @@ -870,7 +870,8 @@ int ath11k_core_check_dt(struct ath11k_base *ab) }

static int __ath11k_core_create_board_name(struct ath11k_base *ab, char *name, - size_t name_len, bool with_variant) + size_t name_len, bool with_variant, + bool bus_type_mode) { /* strlen(',variant=') + strlen(ab->qmi.target.bdf_ext) */ char variant[9 + ATH11K_QMI_BDF_EXT_STR_LENGTH] = { 0 }; @@ -881,15 +882,20 @@ static int __ath11k_core_create_board_name(struct ath11k_base *ab, char *name,

switch (ab->id.bdf_search) { case ATH11K_BDF_SEARCH_BUS_AND_BOARD: - scnprintf(name, name_len, - "bus=%s,vendor=%04x,device=%04x,subsystem-vendor=%04x,subsystem-device=%04x,qmi-chip-id=%d,qmi-board-id=%d%s", - ath11k_bus_str(ab->hif.bus), - ab->id.vendor, ab->id.device, - ab->id.subsystem_vendor, - ab->id.subsystem_device, - ab->qmi.target.chip_id, - ab->qmi.target.board_id, - variant); + if (bus_type_mode) + scnprintf(name, name_len, + "bus=%s", + ath11k_bus_str(ab->hif.bus)); + else + scnprintf(name, name_len, + "bus=%s,vendor=%04x,device=%04x,subsystem-vendor=%04x,subsystem-device=%04x,qmi-chip-id=%d,qmi-board-id=%d%s", + ath11k_bus_str(ab->hif.bus), + ab->id.vendor, ab->id.device, + ab->id.subsystem_vendor, + ab->id.subsystem_device, + ab->qmi.target.chip_id, + ab->qmi.target.board_id, + variant); break; default: scnprintf(name, name_len, @@ -908,13 +914,19 @@ static int __ath11k_core_create_board_name(struct ath11k_base *ab, char *name, static int ath11k_core_create_board_name(struct ath11k_base *ab, char *name, size_t name_len) { - return __ath11k_core_create_board_name(ab, name, name_len, true); + return __ath11k_core_create_board_name(ab, name, name_len, true, false); }

static int ath11k_core_create_fallback_board_name(struct ath11k_base *ab, char *name, size_t name_len) { - return __ath11k_core_create_board_name(ab, name, name_len, false); + return __ath11k_core_create_board_name(ab, name, name_len, false, false); +} + +static int ath11k_core_create_bus_type_board_name(struct ath11k_base *ab, char *name, + size_t name_len) +{ + return __ath11k_core_create_board_name(ab, name, name_len, false, true); }

const struct firmware *ath11k_core_firmware_request(struct ath11k_base *ab, @@ -1218,7 +1230,7 @@ int ath11k_core_fetch_bdf(struct ath11k_base *ab, struct ath11k_board_data *bd)

int ath11k_core_fetch_regdb(struct ath11k_base *ab, struct ath11k_board_data *bd) { - char boardname[BOARD_NAME_SIZE]; + char boardname[BOARD_NAME_SIZE], default_boardname[BOARD_NAME_SIZE]; int ret;

ret = ath11k_core_create_board_name(ab, boardname, BOARD_NAME_SIZE); @@ -1235,6 +1247,21 @@ int ath11k_core_fetch_regdb(struct ath11k_base *ab, struct ath11k_board_data *bd if (!ret) goto exit;

+ ret = ath11k_core_create_bus_type_board_name(ab, default_boardname, + BOARD_NAME_SIZE); + if (ret) { + ath11k_dbg(ab, ATH11K_DBG_BOOT, + "failed to create default board name for regdb: %d", ret); + goto exit; + } + + ret = ath11k_core_fetch_board_data_api_n(ab, bd, default_boardname, + ATH11K_BD_IE_REGDB, + ATH11K_BD_IE_REGDB_NAME, + ATH11K_BD_IE_REGDB_DATA); + if (!ret) + goto exit; + ret = ath11k_core_fetch_board_data_api_1(ab, bd, ATH11K_REGDB_FILE_NAME); if (ret) ath11k_dbg(ab, ATH11K_DBG_BOOT, "failed to fetch %s from %s\n",

From: Abe Kohandel abe.kohandel@intel.com

[ Upstream commit 0760d5d0e9f0c0e2200a0323a61d1995bb745dee ]

The Intel Mount Evans SoC's Integrated Management Complex uses the SPI controller for access to a NOR SPI FLASH. However, the SoC doesn't provide a mechanism to override the native chip select signal.

This driver doesn't use DMA for memory operations when a chip select override is not provided due to the native chip select timing behavior. As a result no DMA configuration is done for the controller and this configuration is not tested.

The controller also has an errata where a full TX FIFO can result in data corruption. The suggested workaround is to never completely fill the FIFO. The TX FIFO has a size of 32 so the fifo_len is set to 31.

Signed-off-by: Abe Kohandel abe.kohandel@intel.com Reviewed-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Link: https://lore.kernel.org/r/20230606145402.474866-2-abe.kohandel@intel.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/spi/spi-dw-mmio.c | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+)

diff --git a/drivers/spi/spi-dw-mmio.c b/drivers/spi/spi-dw-mmio.c index 26c40ea6dd129..7e8478ad74e55 100644 --- a/drivers/spi/spi-dw-mmio.c +++ b/drivers/spi/spi-dw-mmio.c @@ -222,6 +222,31 @@ static int dw_spi_intel_init(struct platform_device *pdev, return 0; }

+/* + * The Intel Mount Evans SoC's Integrated Management Complex uses the + * SPI controller for access to a NOR SPI FLASH. However, the SoC doesn't + * provide a mechanism to override the native chip select signal. + * + * This driver doesn't use DMA for memory operations when a chip select + * override is not provided due to the native chip select timing behavior. + * As a result no DMA configuration is done for the controller and this + * configuration is not tested. + */ +static int dw_spi_mountevans_imc_init(struct platform_device *pdev, + struct dw_spi_mmio *dwsmmio) +{ + /* + * The Intel Mount Evans SoC's Integrated Management Complex DW + * apb_ssi_v4.02a controller has an errata where a full TX FIFO can + * result in data corruption. The suggested workaround is to never + * completely fill the FIFO. The TX FIFO has a size of 32 so the + * fifo_len is set to 31. + */ + dwsmmio->dws.fifo_len = 31; + + return 0; +} + static int dw_spi_canaan_k210_init(struct platform_device *pdev, struct dw_spi_mmio *dwsmmio) { @@ -350,6 +375,10 @@ static const struct of_device_id dw_spi_mmio_of_match[] = { { .compatible = "snps,dwc-ssi-1.01a", .data = dw_spi_hssi_init}, { .compatible = "intel,keembay-ssi", .data = dw_spi_intel_init}, { .compatible = "intel,thunderbay-ssi", .data = dw_spi_intel_init}, + { + .compatible = "intel,mountevans-imc-ssi", + .data = dw_spi_mountevans_imc_init, + }, { .compatible = "microchip,sparx5-spi", dw_spi_mscc_sparx5_init}, { .compatible = "canaan,k210-spi", dw_spi_canaan_k210_init}, { /* end of table */}

From: Jisheng Zhang jszhang@kernel.org

[ Upstream commit 18da174d865a87d47d2f33f5b0a322efcf067728 ]

Implement 64 bit per cpu stats to fix the overflow of netdev->stats on 32 bit platforms. To simplify the code, we use net core pcpu_sw_netstats infrastructure. One small drawback is some memory overhead because litex uses just one queue, but we allocate the counters per cpu.

Signed-off-by: Jisheng Zhang jszhang@kernel.org Reviewed-by: Simon Horman simon.horman@corigine.com Acked-by: Gabriel Somlo gsomlo@gmail.com Link: https://lore.kernel.org/r/20230614162035.300-1-jszhang@kernel.org Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/litex/litex_liteeth.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/litex/litex_liteeth.c b/drivers/net/ethernet/litex/litex_liteeth.c index 35f24e0f09349..ffa96059079c6 100644 --- a/drivers/net/ethernet/litex/litex_liteeth.c +++ b/drivers/net/ethernet/litex/litex_liteeth.c @@ -78,8 +78,7 @@ static int liteeth_rx(struct net_device *netdev) memcpy_fromio(data, priv->rx_base + rx_slot * priv->slot_size, len); skb->protocol = eth_type_trans(skb, netdev);

- netdev->stats.rx_packets++; - netdev->stats.rx_bytes += len; + dev_sw_netstats_rx_add(netdev, len);

return netif_rx(skb);

@@ -185,8 +184,7 @@ static netdev_tx_t liteeth_start_xmit(struct sk_buff *skb, litex_write16(priv->base + LITEETH_READER_LENGTH, skb->len); litex_write8(priv->base + LITEETH_READER_START, 1);

- netdev->stats.tx_bytes += skb->len; - netdev->stats.tx_packets++; + dev_sw_netstats_tx_add(netdev, 1, skb->len);

priv->tx_slot = (priv->tx_slot + 1) % priv->num_tx_slots; dev_kfree_skb_any(skb); @@ -194,9 +192,17 @@ static netdev_tx_t liteeth_start_xmit(struct sk_buff *skb, return NETDEV_TX_OK; }

+static void +liteeth_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) +{ + netdev_stats_to_stats64(stats, &netdev->stats); + dev_fetch_sw_netstats(stats, netdev->tstats); +} + static const struct net_device_ops liteeth_netdev_ops = { .ndo_open = liteeth_open, .ndo_stop = liteeth_stop, + .ndo_get_stats64 = liteeth_get_stats64, .ndo_start_xmit = liteeth_start_xmit, };

@@ -242,6 +248,11 @@ static int liteeth_probe(struct platform_device *pdev) priv->netdev = netdev; priv->dev = &pdev->dev;

+ netdev->tstats = devm_netdev_alloc_pcpu_stats(&pdev->dev, + struct pcpu_sw_netstats); + if (!netdev->tstats) + return -ENOMEM; + irq = platform_get_irq(pdev, 0); if (irq < 0) return irq;

From: Gustavo A. R. Silva gustavoars@kernel.org

[ Upstream commit 71e7552c90db2a2767f5c17c7ec72296b0d92061 ]

-Wstringop-overflow is legitimately warning us about extra_size pontentially being zero at some point, hence potenially ending up _allocating_ zero bytes of memory for extra pointer and then trying to access such object in a call to copy_from_user().

Fix this by adding a sanity check to ensure we never end up trying to allocate zero bytes of data for extra pointer, before continue executing the rest of the code in the function.

Address the following -Wstringop-overflow warning seen when built m68k architecture with allyesconfig configuration: from net/wireless/wext-core.c:11: In function '_copy_from_user', inlined from 'copy_from_user' at include/linux/uaccess.h:183:7, inlined from 'ioctl_standard_iw_point' at net/wireless/wext-core.c:825:7: arch/m68k/include/asm/string.h:48:25: warning: '__builtin_memset' writing 1 or more bytes into a region of size 0 overflows the destination [-Wstringop-overflow=] 48 | #define memset(d, c, n) __builtin_memset(d, c, n) | ^~~~~~~~~~~~~~~~~~~~~~~~~ include/linux/uaccess.h:153:17: note: in expansion of macro 'memset' 153 | memset(to + (n - res), 0, res); | ^~~~~~ In function 'kmalloc', inlined from 'kzalloc' at include/linux/slab.h:694:9, inlined from 'ioctl_standard_iw_point' at net/wireless/wext-core.c:819:10: include/linux/slab.h:577:16: note: at offset 1 into destination object of size 0 allocated by '__kmalloc' 577 | return __kmalloc(size, flags); | ^~~~~~~~~~~~~~~~~~~~~~

This help with the ongoing efforts to globally enable -Wstringop-overflow.

Link: https://github.com/KSPP/linux/issues/315 Signed-off-by: Gustavo A. R. Silva gustavoars@kernel.org Reviewed-by: Simon Horman simon.horman@corigine.com Link: https://lore.kernel.org/r/ZItSlzvIpjdjNfd8@work Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/wireless/wext-core.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index fe8765c4075d3..8a4b85f96a13a 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -799,6 +799,12 @@ static int ioctl_standard_iw_point(struct iw_point *iwp, unsigned int cmd, } }

+ /* Sanity-check to ensure we never end up _allocating_ zero + * bytes of data for extra. + */ + if (extra_size <= 0) + return -EFAULT; + /* kzalloc() ensures NULL-termination for essid_compat. */ extra = kzalloc(extra_size, GFP_KERNEL); if (!extra)

From: Johannes Berg johannes.berg@intel.com

[ Upstream commit 1a528ab1da324d078ec60283c34c17848580df24 ]

Roee reported various hard-to-debug crashes with pings in EHT aggregation scenarios. Enabling KASAN showed that we access the BAID allocation out of bounds, and looking at the code a bit shows that since the reorder buffer entry (struct iwl_mvm_reorder_buf_entry) is 128 bytes if debug such as lockdep is enabled, then staring from an agg size 512 we overflow the size calculation, and allocate a much smaller structure than we should, causing slab corruption once we initialize this.

Fix this by simply using u32 instead of u16.

Reported-by: Roee Goldfiner roee.h.goldfiner@intel.com Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Gregory Greenman gregory.greenman@intel.com Link: https://lore.kernel.org/r/20230620125813.f428c856030d.I2c2bb808e945adb71bc15... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/intel/iwlwifi/mvm/sta.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index 013aca70c3d3b..6b52afcf02721 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -2738,7 +2738,7 @@ int iwl_mvm_sta_rx_agg(struct iwl_mvm *mvm, struct ieee80211_sta *sta, }

if (iwl_mvm_has_new_rx_api(mvm) && start) { - u16 reorder_buf_size = buf_size * sizeof(baid_data->entries[0]); + u32 reorder_buf_size = buf_size * sizeof(baid_data->entries[0]);

/* sparse doesn't like the __align() so don't check */ #ifndef __CHECKER__

From: Ying Hsu yinghsu@chromium.org

[ Upstream commit 004d25060c78fc31f66da0fa439c544dda1ac9d5 ]

In a setup where a Thunderbolt hub connects to Ethernet and a display through USB Type-C, users may experience a hung task timeout when they remove the cable between the PC and the Thunderbolt hub. This is because the igb_down function is called multiple times when the Thunderbolt hub is unplugged. For example, the igb_io_error_detected triggers the first call, and the igb_remove triggers the second call. The second call to igb_down will block at napi_synchronize. Here's the call trace: __schedule+0x3b0/0xddb ? __mod_timer+0x164/0x5d3 schedule+0x44/0xa8 schedule_timeout+0xb2/0x2a4 ? run_local_timers+0x4e/0x4e msleep+0x31/0x38 igb_down+0x12c/0x22a [igb 6615058754948bfde0bf01429257eb59f13030d4] __igb_close+0x6f/0x9c [igb 6615058754948bfde0bf01429257eb59f13030d4] igb_close+0x23/0x2b [igb 6615058754948bfde0bf01429257eb59f13030d4] __dev_close_many+0x95/0xec dev_close_many+0x6e/0x103 unregister_netdevice_many+0x105/0x5b1 unregister_netdevice_queue+0xc2/0x10d unregister_netdev+0x1c/0x23 igb_remove+0xa7/0x11c [igb 6615058754948bfde0bf01429257eb59f13030d4] pci_device_remove+0x3f/0x9c device_release_driver_internal+0xfe/0x1b4 pci_stop_bus_device+0x5b/0x7f pci_stop_bus_device+0x30/0x7f pci_stop_bus_device+0x30/0x7f pci_stop_and_remove_bus_device+0x12/0x19 pciehp_unconfigure_device+0x76/0xe9 pciehp_disable_slot+0x6e/0x131 pciehp_handle_presence_or_link_change+0x7a/0x3f7 pciehp_ist+0xbe/0x194 irq_thread_fn+0x22/0x4d ? irq_thread+0x1fd/0x1fd irq_thread+0x17b/0x1fd ? irq_forced_thread_fn+0x5f/0x5f kthread+0x142/0x153 ? __irq_get_irqchip_state+0x46/0x46 ? kthread_associate_blkcg+0x71/0x71 ret_from_fork+0x1f/0x30

In this case, igb_io_error_detected detaches the network interface and requests a PCIE slot reset, however, the PCIE reset callback is not being invoked and thus the Ethernet connection breaks down. As the PCIE error in this case is a non-fatal one, requesting a slot reset can be avoided. This patch fixes the task hung issue and preserves Ethernet connection by ignoring non-fatal PCIE errors.

Signed-off-by: Ying Hsu yinghsu@chromium.org Tested-by: Pucha Himasekhar Reddy himasekharx.reddy.pucha@intel.com (A Contingent worker at Intel) Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Reviewed-by: Simon Horman simon.horman@corigine.com Link: https://lore.kernel.org/r/20230620174732.4145155-1-anthony.l.nguyen@intel.co... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/igb/igb_main.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 18ffbc892f86c..3e0444354632d 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -9585,6 +9585,11 @@ static pci_ers_result_t igb_io_error_detected(struct pci_dev *pdev, struct net_device *netdev = pci_get_drvdata(pdev); struct igb_adapter *adapter = netdev_priv(netdev);

+ if (state == pci_channel_io_normal) { + dev_warn(&pdev->dev, "Non-correctable non-fatal error reported.\n"); + return PCI_ERS_RESULT_CAN_RECOVER; + } + netif_device_detach(netdev);

if (state == pci_channel_io_perm_failure)

From: Vijendar Mukunda Vijendar.Mukunda@amd.com

[ Upstream commit 85aeab362201cf52c34cd429e4f6c75a0b42f9a3 ]

For invalid dai id, instead of returning -EINVAL return bytes count as zero in acp_get_byte_count() function.

Fixes: 623621a9f9e1 ("ASoC: amd: Add common framework to support I2S on ACP SOC")

Signed-off-by: Vijendar Mukunda Vijendar.Mukunda@amd.com Link: https://lore.kernel.org/r/20230626105356.2580125-6-Vijendar.Mukunda@amd.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/amd/acp/amd.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/sound/soc/amd/acp/amd.h b/sound/soc/amd/acp/amd.h index 5f2119f422715..12a176a50fd6e 100644 --- a/sound/soc/amd/acp/amd.h +++ b/sound/soc/amd/acp/amd.h @@ -173,7 +173,7 @@ int snd_amd_acp_find_config(struct pci_dev *pci);

static inline u64 acp_get_byte_count(struct acp_dev_data *adata, int dai_id, int direction) { - u64 byte_count, low = 0, high = 0; + u64 byte_count = 0, low = 0, high = 0;

if (direction == SNDRV_PCM_STREAM_PLAYBACK) { switch (dai_id) { @@ -191,7 +191,7 @@ static inline u64 acp_get_byte_count(struct acp_dev_data *adata, int dai_id, int break; default: dev_err(adata->dev, "Invalid dai id %x\n", dai_id); - return -EINVAL; + goto POINTER_RETURN_BYTES; } } else { switch (dai_id) { @@ -213,12 +213,13 @@ static inline u64 acp_get_byte_count(struct acp_dev_data *adata, int dai_id, int break; default: dev_err(adata->dev, "Invalid dai id %x\n", dai_id); - return -EINVAL; + goto POINTER_RETURN_BYTES; } } /* Get 64 bit value from two 32 bit registers */ byte_count = (high << 32) | low;

+POINTER_RETURN_BYTES: return byte_count; }

From: Srinivas Kandagatla srinivas.kandagatla@linaro.org

[ Upstream commit c03226ba15fe3c42d13907ec7d8536396602557b ]

dB range for HPHL and HPHR gains are from +6dB to -30dB in steps of 1.5dB with register values range from 0 to 24.

Current code maps these dB ranges incorrectly, fix them to allow proper volume setting.

Fixes: e8ba1e05bdc0 ("ASoC: codecs: wcd938x: add basic controls") Signed-off-by: Srinivas Kandagatla srinivas.kandagatla@linaro.org Link: https://lore.kernel.org/r/20230705125723.40464-1-srinivas.kandagatla@linaro.... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/codecs/wcd938x.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/sound/soc/codecs/wcd938x.c b/sound/soc/codecs/wcd938x.c index 7715040383840..2316481c2541b 100644 --- a/sound/soc/codecs/wcd938x.c +++ b/sound/soc/codecs/wcd938x.c @@ -210,7 +210,7 @@ struct wcd938x_priv { };

static const SNDRV_CTL_TLVD_DECLARE_DB_MINMAX(ear_pa_gain, 600, -1800); -static const SNDRV_CTL_TLVD_DECLARE_DB_MINMAX(line_gain, 600, -3000); +static const DECLARE_TLV_DB_SCALE(line_gain, -3000, 150, -3000); static const SNDRV_CTL_TLVD_DECLARE_DB_MINMAX(analog_gain, 0, 3000);

struct wcd938x_mbhc_zdet_param { @@ -2662,8 +2662,8 @@ static const struct snd_kcontrol_new wcd938x_snd_controls[] = { wcd938x_get_swr_port, wcd938x_set_swr_port), SOC_SINGLE_EXT("DSD_R Switch", WCD938X_DSD_R, 0, 1, 0, wcd938x_get_swr_port, wcd938x_set_swr_port), - SOC_SINGLE_TLV("HPHL Volume", WCD938X_HPH_L_EN, 0, 0x18, 0, line_gain), - SOC_SINGLE_TLV("HPHR Volume", WCD938X_HPH_R_EN, 0, 0x18, 0, line_gain), + SOC_SINGLE_TLV("HPHL Volume", WCD938X_HPH_L_EN, 0, 0x18, 1, line_gain), + SOC_SINGLE_TLV("HPHR Volume", WCD938X_HPH_R_EN, 0, 0x18, 1, line_gain), WCD938X_EAR_PA_GAIN_TLV("EAR_PA Volume", WCD938X_ANA_EAR_COMPANDER_CTL, 2, 0x10, 0, ear_pa_gain), SOC_SINGLE_EXT("ADC1 Switch", WCD938X_ADC1, 1, 1, 0,

From: Miaohe Lin linmiaohe@huawei.com

[ Upstream commit ae2ad293d6be143ad223f5f947cca07bcbe42595 ]

When checking whether a recently used CPU can be a potential idle candidate, recent_used_cpu should be used to test p->cpus_ptr as p->recent_used_cpu is not equal to recent_used_cpu and candidate decision is made based on recent_used_cpu here.

Fixes: 89aafd67f28c ("sched/fair: Use prev instead of new target as recent_used_cpu") Signed-off-by: Miaohe Lin linmiaohe@huawei.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Phil Auld pauld@redhat.com Acked-by: Mel Gorman mgorman@suse.de Link: https://lore.kernel.org/r/20230620080747.359122-1-linmiaohe@huawei.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/sched/fair.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 57d39de0962d7..5e5aea2360a87 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6935,7 +6935,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) recent_used_cpu != target && cpus_share_cache(recent_used_cpu, target) && (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) && - cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) && + cpumask_test_cpu(recent_used_cpu, p->cpus_ptr) && asym_fits_cpu(task_util, util_min, util_max, recent_used_cpu)) { return recent_used_cpu; }

From: Domenico Cerasuolo cerasuolodomenico@gmail.com

[ Upstream commit 7fab21fa0d000a0ea32d73ce8eec68557c6c268b ]

Move a few functions up in the file to avoid forward declaration needed in the patch implementing unprivileged PSI triggers.

Suggested-by: Johannes Weiner hannes@cmpxchg.org Signed-off-by: Domenico Cerasuolo cerasuolodomenico@gmail.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Acked-by: Johannes Weiner hannes@cmpxchg.org Link: https://lore.kernel.org/r/20230330105418.77061-2-cerasuolodomenico@gmail.com Stable-dep-of: aff037078eca ("sched/psi: use kernfs polling functions for PSI trigger polling") Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/sched/psi.c | 196 ++++++++++++++++++++++----------------------- 1 file changed, 98 insertions(+), 98 deletions(-)

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 02e011cabe917..fe9269f1d2a46 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -384,92 +384,6 @@ static void collect_percpu_times(struct psi_group *group, *pchanged_states = changed_states; }

-static u64 update_averages(struct psi_group *group, u64 now) -{ - unsigned long missed_periods = 0; - u64 expires, period; - u64 avg_next_update; - int s; - - /* avgX= */ - expires = group->avg_next_update; - if (now - expires >= psi_period) - missed_periods = div_u64(now - expires, psi_period); - - /* - * The periodic clock tick can get delayed for various - * reasons, especially on loaded systems. To avoid clock - * drift, we schedule the clock in fixed psi_period intervals. - * But the deltas we sample out of the per-cpu buckets above - * are based on the actual time elapsing between clock ticks. - */ - avg_next_update = expires + ((1 + missed_periods) * psi_period); - period = now - (group->avg_last_update + (missed_periods * psi_period)); - group->avg_last_update = now; - - for (s = 0; s < NR_PSI_STATES - 1; s++) { - u32 sample; - - sample = group->total[PSI_AVGS][s] - group->avg_total[s]; - /* - * Due to the lockless sampling of the time buckets, - * recorded time deltas can slip into the next period, - * which under full pressure can result in samples in - * excess of the period length. - * - * We don't want to report non-sensical pressures in - * excess of 100%, nor do we want to drop such events - * on the floor. Instead we punt any overage into the - * future until pressure subsides. By doing this we - * don't underreport the occurring pressure curve, we - * just report it delayed by one period length. - * - * The error isn't cumulative. As soon as another - * delta slips from a period P to P+1, by definition - * it frees up its time T in P. - */ - if (sample > period) - sample = period; - group->avg_total[s] += sample; - calc_avgs(group->avg[s], missed_periods, sample, period); - } - - return avg_next_update; -} - -static void psi_avgs_work(struct work_struct *work) -{ - struct delayed_work *dwork; - struct psi_group *group; - u32 changed_states; - u64 now; - - dwork = to_delayed_work(work); - group = container_of(dwork, struct psi_group, avgs_work); - - mutex_lock(&group->avgs_lock); - - now = sched_clock(); - - collect_percpu_times(group, PSI_AVGS, &changed_states); - /* - * If there is task activity, periodically fold the per-cpu - * times and feed samples into the running averages. If things - * are idle and there is no data to process, stop the clock. - * Once restarted, we'll catch up the running averages in one - * go - see calc_avgs() and missed_periods. - */ - if (now >= group->avg_next_update) - group->avg_next_update = update_averages(group, now); - - if (changed_states & PSI_STATE_RESCHEDULE) { - schedule_delayed_work(dwork, nsecs_to_jiffies( - group->avg_next_update - now) + 1); - } - - mutex_unlock(&group->avgs_lock); -} - /* Trigger tracking window manipulations */ static void window_reset(struct psi_window *win, u64 now, u64 value, u64 prev_growth) @@ -516,18 +430,6 @@ static u64 window_update(struct psi_window *win, u64 now, u64 value) return growth; }

-static void init_triggers(struct psi_group *group, u64 now) -{ - struct psi_trigger *t; - - list_for_each_entry(t, &group->triggers, node) - window_reset(&t->win, now, - group->total[PSI_POLL][t->state], 0); - memcpy(group->polling_total, group->total[PSI_POLL], - sizeof(group->polling_total)); - group->polling_next_update = now + group->poll_min_period; -} - static u64 update_triggers(struct psi_group *group, u64 now) { struct psi_trigger *t; @@ -590,6 +492,104 @@ static u64 update_triggers(struct psi_group *group, u64 now) return now + group->poll_min_period; }

+static u64 update_averages(struct psi_group *group, u64 now) +{ + unsigned long missed_periods = 0; + u64 expires, period; + u64 avg_next_update; + int s; + + /* avgX= */ + expires = group->avg_next_update; + if (now - expires >= psi_period) + missed_periods = div_u64(now - expires, psi_period); + + /* + * The periodic clock tick can get delayed for various + * reasons, especially on loaded systems. To avoid clock + * drift, we schedule the clock in fixed psi_period intervals. + * But the deltas we sample out of the per-cpu buckets above + * are based on the actual time elapsing between clock ticks. + */ + avg_next_update = expires + ((1 + missed_periods) * psi_period); + period = now - (group->avg_last_update + (missed_periods * psi_period)); + group->avg_last_update = now; + + for (s = 0; s < NR_PSI_STATES - 1; s++) { + u32 sample; + + sample = group->total[PSI_AVGS][s] - group->avg_total[s]; + /* + * Due to the lockless sampling of the time buckets, + * recorded time deltas can slip into the next period, + * which under full pressure can result in samples in + * excess of the period length. + * + * We don't want to report non-sensical pressures in + * excess of 100%, nor do we want to drop such events + * on the floor. Instead we punt any overage into the + * future until pressure subsides. By doing this we + * don't underreport the occurring pressure curve, we + * just report it delayed by one period length. + * + * The error isn't cumulative. As soon as another + * delta slips from a period P to P+1, by definition + * it frees up its time T in P. + */ + if (sample > period) + sample = period; + group->avg_total[s] += sample; + calc_avgs(group->avg[s], missed_periods, sample, period); + } + + return avg_next_update; +} + +static void psi_avgs_work(struct work_struct *work) +{ + struct delayed_work *dwork; + struct psi_group *group; + u32 changed_states; + u64 now; + + dwork = to_delayed_work(work); + group = container_of(dwork, struct psi_group, avgs_work); + + mutex_lock(&group->avgs_lock); + + now = sched_clock(); + + collect_percpu_times(group, PSI_AVGS, &changed_states); + /* + * If there is task activity, periodically fold the per-cpu + * times and feed samples into the running averages. If things + * are idle and there is no data to process, stop the clock. + * Once restarted, we'll catch up the running averages in one + * go - see calc_avgs() and missed_periods. + */ + if (now >= group->avg_next_update) + group->avg_next_update = update_averages(group, now); + + if (changed_states & PSI_STATE_RESCHEDULE) { + schedule_delayed_work(dwork, nsecs_to_jiffies( + group->avg_next_update - now) + 1); + } + + mutex_unlock(&group->avgs_lock); +} + +static void init_triggers(struct psi_group *group, u64 now) +{ + struct psi_trigger *t; + + list_for_each_entry(t, &group->triggers, node) + window_reset(&t->win, now, + group->total[PSI_POLL][t->state], 0); + memcpy(group->polling_total, group->total[PSI_POLL], + sizeof(group->polling_total)); + group->polling_next_update = now + group->poll_min_period; +} + /* Schedule polling if it's not already scheduled or forced. */ static void psi_schedule_poll_work(struct psi_group *group, unsigned long delay, bool force)

From: Domenico Cerasuolo cerasuolodomenico@gmail.com

[ Upstream commit 4468fcae49f08e88fbbffe05b29496192df89991 ]

This change moves update_total flag out of update_triggers function, currently called only in psi_poll_work. In the next patch, update_triggers will be called also in psi_avgs_work, but the total update information is specific to psi_poll_work. Returning update_total value to the caller let us avoid differentiating the implementation of update_triggers for different aggregators.

Suggested-by: Johannes Weiner hannes@cmpxchg.org Signed-off-by: Domenico Cerasuolo cerasuolodomenico@gmail.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Acked-by: Johannes Weiner hannes@cmpxchg.org Link: https://lore.kernel.org/r/20230330105418.77061-4-cerasuolodomenico@gmail.com Stable-dep-of: aff037078eca ("sched/psi: use kernfs polling functions for PSI trigger polling") Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/sched/psi.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index a3d0b5cf797ab..f3df6a8ff493c 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -430,11 +430,11 @@ static u64 window_update(struct psi_window *win, u64 now, u64 value) return growth; }

-static u64 update_triggers(struct psi_group *group, u64 now) +static u64 update_triggers(struct psi_group *group, u64 now, bool *update_total) { struct psi_trigger *t; - bool update_total = false; u64 *total = group->total[PSI_POLL]; + *update_total = false;

/* * On subsequent updates, calculate growth deltas and let @@ -462,7 +462,7 @@ static u64 update_triggers(struct psi_group *group, u64 now) * been through all of them. Also remember to extend the * polling time if we see new stall activity. */ - update_total = true; + *update_total = true;

/* Calculate growth since last update */ growth = window_update(&t->win, now, total[t->state]); @@ -485,10 +485,6 @@ static u64 update_triggers(struct psi_group *group, u64 now) t->pending_event = false; }

- if (update_total) - memcpy(group->rtpoll_total, total, - sizeof(group->rtpoll_total)); - return now + group->rtpoll_min_period; }

@@ -622,6 +618,7 @@ static void psi_rtpoll_work(struct psi_group *group) { bool force_reschedule = false; u32 changed_states; + bool update_total; u64 now;

mutex_lock(&group->rtpoll_trigger_lock); @@ -686,8 +683,12 @@ static void psi_rtpoll_work(struct psi_group *group) goto out; }

- if (now >= group->rtpoll_next_update) - group->rtpoll_next_update = update_triggers(group, now); + if (now >= group->rtpoll_next_update) { + group->rtpoll_next_update = update_triggers(group, now, &update_total); + if (update_total) + memcpy(group->rtpoll_total, group->total[PSI_POLL], + sizeof(group->rtpoll_total)); + }

psi_schedule_rtpoll_work(group, nsecs_to_jiffies(group->rtpoll_next_update - now) + 1,

From: Suren Baghdasaryan surenb@google.com

[ Upstream commit aff037078ecaecf34a7c2afab1341815f90fba5e ]

Destroying psi trigger in cgroup_file_release causes UAF issues when a cgroup is removed from under a polling process. This is happening because cgroup removal causes a call to cgroup_file_release while the actual file is still alive. Destroying the trigger at this point would also destroy its waitqueue head and if there is still a polling process on that file accessing the waitqueue, it will step on the freed pointer:

do_select vfs_poll do_rmdir cgroup_rmdir kernfs_drain_open_files cgroup_file_release cgroup_pressure_release psi_trigger_destroy wake_up_pollfree(&t->event_wait) // vfs_poll is unblocked synchronize_rcu kfree(t) poll_freewait -> UAF access to the trigger's waitqueue head

Patch [1] fixed this issue for epoll() case using wake_up_pollfree(), however the same issue exists for synchronous poll() case. The root cause of this issue is that the lifecycles of the psi trigger's waitqueue and of the file associated with the trigger are different. Fix this by using kernfs_generic_poll function when polling on cgroup-specific psi triggers. It internally uses kernfs_open_node->poll waitqueue head with its lifecycle tied to the file's lifecycle. This also renders the fix in [1] obsolete, so revert it.

[1] commit c2dbe32d5db5 ("sched/psi: Fix use-after-free in ep_remove_wait_queue()")

Fixes: 0e94682b73bf ("psi: introduce psi monitor") Closes: https://lore.kernel.org/all/20230613062306.101831-1-lujialin4@huawei.com/ Reported-by: Lu Jialin lujialin4@huawei.com Signed-off-by: Suren Baghdasaryan surenb@google.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20230630005612.1014540-1-surenb@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/psi.h | 5 +++-- include/linux/psi_types.h | 3 +++ kernel/cgroup/cgroup.c | 2 +- kernel/sched/psi.c | 29 +++++++++++++++++++++-------- 4 files changed, 28 insertions(+), 11 deletions(-)

diff --git a/include/linux/psi.h b/include/linux/psi.h index ab26200c28033..e0745873e3f26 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -23,8 +23,9 @@ void psi_memstall_enter(unsigned long *flags); void psi_memstall_leave(unsigned long *flags);

int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); -struct psi_trigger *psi_trigger_create(struct psi_group *group, - char *buf, enum psi_res res, struct file *file); +struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, + enum psi_res res, struct file *file, + struct kernfs_open_file *of); void psi_trigger_destroy(struct psi_trigger *t);

__poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 040c089581c6c..f1fd3a8044e0e 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -137,6 +137,9 @@ struct psi_trigger { /* Wait queue for polling */ wait_queue_head_t event_wait;

+ /* Kernfs file for cgroup triggers */ + struct kernfs_open_file *of; + /* Pending event flag */ int event;

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index c35efae566a4b..73f11e4db3a4d 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3771,7 +3771,7 @@ static ssize_t pressure_write(struct kernfs_open_file *of, char *buf, }

psi = cgroup_psi(cgrp); - new = psi_trigger_create(psi, buf, res, of->file); + new = psi_trigger_create(psi, buf, res, of->file, of); if (IS_ERR(new)) { cgroup_put(cgrp); return PTR_ERR(new); diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index e072f6b31bf30..80d8c10e93638 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -494,8 +494,12 @@ static u64 update_triggers(struct psi_group *group, u64 now, bool *update_total, continue;

/* Generate an event */ - if (cmpxchg(&t->event, 0, 1) == 0) - wake_up_interruptible(&t->event_wait); + if (cmpxchg(&t->event, 0, 1) == 0) { + if (t->of) + kernfs_notify(t->of->kn); + else + wake_up_interruptible(&t->event_wait); + } t->last_event_time = now; /* Reset threshold breach flag once event got generated */ t->pending_event = false; @@ -1272,8 +1276,9 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) return 0; }

-struct psi_trigger *psi_trigger_create(struct psi_group *group, - char *buf, enum psi_res res, struct file *file) +struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, + enum psi_res res, struct file *file, + struct kernfs_open_file *of) { struct psi_trigger *t; enum psi_states state; @@ -1333,7 +1338,9 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,

t->event = 0; t->last_event_time = 0; - init_waitqueue_head(&t->event_wait); + t->of = of; + if (!of) + init_waitqueue_head(&t->event_wait); t->pending_event = false; t->aggregator = privileged ? PSI_POLL : PSI_AVGS;

@@ -1390,7 +1397,10 @@ void psi_trigger_destroy(struct psi_trigger *t) * being accessed later. Can happen if cgroup is deleted from under a * polling process. */ - wake_up_pollfree(&t->event_wait); + if (t->of) + kernfs_notify(t->of->kn); + else + wake_up_interruptible(&t->event_wait);

if (t->aggregator == PSI_AVGS) { mutex_lock(&group->avgs_lock); @@ -1462,7 +1472,10 @@ __poll_t psi_trigger_poll(void **trigger_ptr, if (!t) return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI;

- poll_wait(file, &t->event_wait, wait); + if (t->of) + kernfs_generic_poll(t->of, wait); + else + poll_wait(file, &t->event_wait, wait);

if (cmpxchg(&t->event, 1, 0) == 1) ret |= EPOLLPRI; @@ -1532,7 +1545,7 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf, return -EBUSY; }

- new = psi_trigger_create(&psi_system, buf, res, file); + new = psi_trigger_create(&psi_system, buf, res, file, NULL); if (IS_ERR(new)) { mutex_unlock(&seq->lock); return PTR_ERR(new);

From: Biju Das biju.das.jz@bp.renesas.com

[ Upstream commit bfc374a145ae133613e05b9b89be561f169cb58d ]

Currently, sd1 and sd0 have unique subnode names 'sd1_mux' and 'sd0_mux'. If we change these to non-unique subnode names such as 'mux' this can lead to the below conflict as the RZ/G2L pin control driver considers only the names of the subnodes.

pinctrl-rzg2l 11030000.pinctrl: pin P47_0 already requested by 11c00000.mmc; cannot claim for 11c10000.mmc pinctrl-rzg2l 11030000.pinctrl: pin-376 (11c10000.mmc) status -22 pinctrl-rzg2l 11030000.pinctrl: could not request pin 376 (P47_0) from group mux on device pinctrl-rzg2l renesas_sdhi_internal_dmac 11c10000.mmc: Error applying setting, reverse things back

Fix this by constructing unique names from the node names of both the pin control configuration node and its child node, where appropriate.

Based on the work done by Geert for the RZ/V2M pinctrl driver.

Fixes: c4c4637eb57f ("pinctrl: renesas: Add RZ/G2L pin and gpio controller driver") Signed-off-by: Biju Das biju.das.jz@bp.renesas.com Reviewed-by: Geert Uytterhoeven geert+renesas@glider.be Link: https://lore.kernel.org/r/20230704111858.215278-1-biju.das.jz@bp.renesas.com Signed-off-by: Geert Uytterhoeven geert+renesas@glider.be Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pinctrl/renesas/pinctrl-rzg2l.c | 28 ++++++++++++++++++------- 1 file changed, 20 insertions(+), 8 deletions(-)

diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c index ca6303fc41f98..fd11d28e5a1e4 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c +++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c @@ -246,6 +246,7 @@ static int rzg2l_map_add_config(struct pinctrl_map *map,

static int rzg2l_dt_subnode_to_map(struct pinctrl_dev *pctldev, struct device_node *np, + struct device_node *parent, struct pinctrl_map **map, unsigned int *num_maps, unsigned int *index) @@ -263,6 +264,7 @@ static int rzg2l_dt_subnode_to_map(struct pinctrl_dev *pctldev, struct property *prop; int ret, gsel, fsel; const char **pin_fn; + const char *name; const char *pin;

pinmux = of_find_property(np, "pinmux", NULL); @@ -346,8 +348,19 @@ static int rzg2l_dt_subnode_to_map(struct pinctrl_dev *pctldev, psel_val[i] = MUX_FUNC(value); }

+ if (parent) { + name = devm_kasprintf(pctrl->dev, GFP_KERNEL, "%pOFn.%pOFn", + parent, np); + if (!name) { + ret = -ENOMEM; + goto done; + } + } else { + name = np->name; + } + /* Register a single pin group listing all the pins we read from DT */ - gsel = pinctrl_generic_add_group(pctldev, np->name, pins, num_pinmux, NULL); + gsel = pinctrl_generic_add_group(pctldev, name, pins, num_pinmux, NULL); if (gsel < 0) { ret = gsel; goto done; @@ -357,17 +370,16 @@ static int rzg2l_dt_subnode_to_map(struct pinctrl_dev *pctldev, * Register a single group function where the 'data' is an array PSEL * register values read from DT. */ - pin_fn[0] = np->name; - fsel = pinmux_generic_add_function(pctldev, np->name, pin_fn, 1, - psel_val); + pin_fn[0] = name; + fsel = pinmux_generic_add_function(pctldev, name, pin_fn, 1, psel_val); if (fsel < 0) { ret = fsel; goto remove_group; }

maps[idx].type = PIN_MAP_TYPE_MUX_GROUP; - maps[idx].data.mux.group = np->name; - maps[idx].data.mux.function = np->name; + maps[idx].data.mux.group = name; + maps[idx].data.mux.function = name; idx++;

dev_dbg(pctrl->dev, "Parsed %pOF with %d pins\n", np, num_pinmux); @@ -414,7 +426,7 @@ static int rzg2l_dt_node_to_map(struct pinctrl_dev *pctldev, index = 0;

for_each_child_of_node(np, child) { - ret = rzg2l_dt_subnode_to_map(pctldev, child, map, + ret = rzg2l_dt_subnode_to_map(pctldev, child, np, map, num_maps, &index); if (ret < 0) { of_node_put(child); @@ -423,7 +435,7 @@ static int rzg2l_dt_node_to_map(struct pinctrl_dev *pctldev, }

if (*num_maps == 0) { - ret = rzg2l_dt_subnode_to_map(pctldev, np, map, + ret = rzg2l_dt_subnode_to_map(pctldev, np, NULL, map, num_maps, &index); if (ret < 0) goto done;

From: Martin Kaiser martin@kaiser.cx

[ Upstream commit 4e47382fbca916d7db95cbf9e2d7ca2e9d1ca3fe ]

Warn about invalid var->left_margin or var->right_margin. Their values are read from the device tree.

We store var->left_margin-3 and var->right_margin-1 in register fields. These fields should be >= 0.

Fixes: 7e8549bcee00 ("imxfb: Fix margin settings") Signed-off-by: Martin Kaiser martin@kaiser.cx Signed-off-by: Helge Deller deller@gmx.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/video/fbdev/imxfb.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/video/fbdev/imxfb.c b/drivers/video/fbdev/imxfb.c index 51fde1b2a7938..61731921011d5 100644 --- a/drivers/video/fbdev/imxfb.c +++ b/drivers/video/fbdev/imxfb.c @@ -613,10 +613,10 @@ static int imxfb_activate_var(struct fb_var_screeninfo *var, struct fb_info *inf if (var->hsync_len < 1 || var->hsync_len > 64) printk(KERN_ERR "%s: invalid hsync_len %d\n", info->fix.id, var->hsync_len); - if (var->left_margin > 255) + if (var->left_margin < 3 || var->left_margin > 255) printk(KERN_ERR "%s: invalid left_margin %d\n", info->fix.id, var->left_margin); - if (var->right_margin > 255) + if (var->right_margin < 1 || var->right_margin > 255) printk(KERN_ERR "%s: invalid right_margin %d\n", info->fix.id, var->right_margin); if (var->yres < 1 || var->yres > ymax_mask)

From: James Clark james.clark@arm.com

[ Upstream commit 1feece2780ac2f8de45177fe53979726cee4b3d1 ]

-L only specifies the search path for libraries directly provided in the link line with -l. Because -lopencsd isn't specified, it's only linked because it's a dependency of -lopencsd_c_api. Dependencies like this are resolved using the default system search paths or -rpath-link=... rather than -L. This means that compilation only works if OpenCSD is installed to the system rather than provided with the CSLIBS (-L) option.

This could be fixed by adding -Wl,-rpath-link=$(CSLIBS) but that is less conventional than just adding -lopencsd to the link line so that it uses -L. -lopencsd seems to have been removed in commit ed17b1914978eddb ("perf tools: Drop requirement for libstdc++.so for libopencsd check") because it was thought that there was a chance compilation would work even if it didn't exist, but I think that only applies to libstdc++ so there is no harm to add it back. libopencsd.so and libopencsd_c_api.so would always exist together.

Testing =======

The following scenarios now all work:

* Cross build with OpenCSD installed * Cross build using CSLIBS=... * Native build with OpenCSD installed * Native build using CSLIBS=... * Static cross build with OpenCSD installed * Static cross build with CSLIBS=...

Committer testing:

⬢[acme@toolbox perf-tools]$ alias m alias m='make -k BUILD_BPF_SKEL=1 CORESIGHT=1 O=/tmp/build/perf-tools -C tools/perf install-bin && git status && perf test python ; perf record -o /dev/null sleep 0.01 ; perf stat --null sleep 0.01' ⬢[acme@toolbox perf-tools]$ ldd ~/bin/perf | grep csd libopencsd_c_api.so.1 => /lib64/libopencsd_c_api.so.1 (0x00007fd49c44e000) libopencsd.so.1 => /lib64/libopencsd.so.1 (0x00007fd49bd56000) ⬢[acme@toolbox perf-tools]$ cat /etc/redhat-release Fedora release 36 (Thirty Six) ⬢[acme@toolbox perf-tools]$

Fixes: ed17b1914978eddb ("perf tools: Drop requirement for libstdc++.so for libopencsd check") Reported-by: Radhey Shyam Pandey radhey.shyam.pandey@amd.com Signed-off-by: James Clark james.clark@arm.com Tested-by: Arnaldo Carvalho de Melo acme@redhat.com Tested-by: Radhey Shyam Pandey radhey.shyam.pandey@amd.com Cc: Adrian Hunter adrian.hunter@intel.com Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Ian Rogers irogers@google.com Cc: Ingo Molnar mingo@redhat.com Cc: Jiri Olsa jolsa@kernel.org Cc: Mark Rutland mark.rutland@arm.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Uwe Kleine-König uwe@kleine-koenig.org Cc: coresight@lists.linaro.org Closes: https://lore.kernel.org/linux-arm-kernel/56905d7a-a91e-883a-b707-9d5f686ba5f... Link: https://lore.kernel.org/all/36cc4dc6-bf4b-1093-1c0a-876e368af183@kleine-koen... Link: https://lore.kernel.org/r/20230707154546.456720-1-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/Makefile.config | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 898226ea8cadc..fac6ba07eacdb 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -149,9 +149,9 @@ FEATURE_CHECK_LDFLAGS-libcrypto = -lcrypto ifdef CSINCLUDES LIBOPENCSD_CFLAGS := -I$(CSINCLUDES) endif -OPENCSDLIBS := -lopencsd_c_api +OPENCSDLIBS := -lopencsd_c_api -lopencsd ifeq ($(findstring -static,${LDFLAGS}),-static) - OPENCSDLIBS += -lopencsd -lstdc++ + OPENCSDLIBS += -lstdc++ endif ifdef CSLIBS LIBOPENCSD_LDFLAGS := -L$(CSLIBS)

From: Jaewon Kim jaewon02.kim@samsung.com

[ Upstream commit 9ec3c5517e22a12d2ff1b71e844f7913641460c6 ]

When SPI loopback transfer is performed, S3C64XX_SPI_MODE_SELF_LOOPBACK bit still remained. It works as loopback even if the next transfer is not spi loopback mode. If not SPI_LOOP, needs to clear S3C64XX_SPI_MODE_SELF_LOOPBACK bit.

Signed-off-by: Jaewon Kim jaewon02.kim@samsung.com Fixes: ffb7bcd3b27e ("spi: s3c64xx: support loopback mode") Reviewed-by: Chanho Park chanho61.park@samsung.com Link: https://lore.kernel.org/r/20230711082020.138165-1-jaewon02.kim@samsung.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/spi/spi-s3c64xx.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c index 71d324ec9a70a..1480df7b43b3f 100644 --- a/drivers/spi/spi-s3c64xx.c +++ b/drivers/spi/spi-s3c64xx.c @@ -668,6 +668,8 @@ static int s3c64xx_spi_config(struct s3c64xx_spi_driver_data *sdd)

if ((sdd->cur_mode & SPI_LOOP) && sdd->port_conf->has_loopback) val |= S3C64XX_SPI_MODE_SELF_LOOPBACK; + else + val &= ~S3C64XX_SPI_MODE_SELF_LOOPBACK;

writel(val, regs + S3C64XX_SPI_MODE_CFG);

From: Zhen Lei thunder.leizhen@huawei.com

[ Upstream commit 010a0aad39fccceba4a07d30d163158a39c704f3 ]

LLVM appends various suffixes for local functions and variables, suffixes observed: - foo.llvm.[0-9a-f]+ - foo.[0-9a-f]+

Therefore, when CONFIG_LTO_CLANG=y, kallsyms_lookup_name() needs to truncate the suffix of the symbol name before comparing the local function or variable name.

Old implementation code: - if (strcmp(namebuf, name) == 0) - return kallsyms_sym_address(i); - if (cleanup_symbol_name(namebuf) && strcmp(namebuf, name) == 0) - return kallsyms_sym_address(i);

The preceding process is traversed by address from low to high. That is, for those with the same name after the suffix is removed, the one with the smallest address is returned first. Therefore, when sorting in the tool, if the raw names are the same, they should be sorted by address in ascending order.

ASCII[.] = 2e ASCII[0-9] = 30,39 ASCII[A-Z] = 41,5a ASCII[_] = 5f ASCII[a-z] = 61,7a

According to the preceding ASCII code values, the following sorting result is strictly followed. --------------------------------- | main-key | sub-key | |---------------------------------| | | addr_lowest | | <name> | ... | | <name>.<suffix> | ... | | | addr_highest | |---------------------------------| | <name>?<others> | | //? is [_A-Za-z0-9] ---------------------------------

Signed-off-by: Zhen Lei thunder.leizhen@huawei.com Signed-off-by: Luis Chamberlain mcgrof@kernel.org Stable-dep-of: 8cc32a9bbf29 ("kallsyms: strip LTO-only suffixes from promoted global functions") Signed-off-by: Sasha Levin sashal@kernel.org --- scripts/kallsyms.c | 36 ++++++++++++++++++++++++++++++++++-- scripts/link-vmlinux.sh | 4 ++++ 2 files changed, 38 insertions(+), 2 deletions(-)

diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index dcb744a067e5e..67ef9aa14a770 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -78,6 +78,7 @@ static unsigned int table_size, table_cnt; static int all_symbols; static int absolute_percpu; static int base_relative; +static int lto_clang;

static int token_profit[0x10000];

@@ -89,7 +90,7 @@ static unsigned char best_table_len[256]; static void usage(void) { fprintf(stderr, "Usage: kallsyms [--all-symbols] [--absolute-percpu] " - "[--base-relative] in.map > out.S\n"); + "[--base-relative] [--lto-clang] in.map > out.S\n"); exit(1); }

@@ -411,6 +412,34 @@ static int symbol_absolute(const struct sym_entry *s) return s->percpu_absolute; }

+static char * s_name(char *buf) +{ + /* Skip the symbol type */ + return buf + 1; +} + +static void cleanup_symbol_name(char *s) +{ + char *p; + + if (!lto_clang) + return; + + /* + * ASCII[.] = 2e + * ASCII[0-9] = 30,39 + * ASCII[A-Z] = 41,5a + * ASCII[_] = 5f + * ASCII[a-z] = 61,7a + * + * As above, replacing '.' with '\0' does not affect the main sorting, + * but it helps us with subsorting. + */ + p = strchr(s, '.'); + if (p) + *p = '\0'; +} + static int compare_names(const void *a, const void *b) { int ret; @@ -421,7 +450,9 @@ static int compare_names(const void *a, const void *b)

expand_symbol(sa->sym, sa->len, sa_namebuf); expand_symbol(sb->sym, sb->len, sb_namebuf); - ret = strcmp(&sa_namebuf[1], &sb_namebuf[1]); + cleanup_symbol_name(s_name(sa_namebuf)); + cleanup_symbol_name(s_name(sb_namebuf)); + ret = strcmp(s_name(sa_namebuf), s_name(sb_namebuf)); if (!ret) { if (sa->addr > sb->addr) return 1; @@ -855,6 +886,7 @@ int main(int argc, char **argv) {"all-symbols", no_argument, &all_symbols, 1}, {"absolute-percpu", no_argument, &absolute_percpu, 1}, {"base-relative", no_argument, &base_relative, 1}, + {"lto-clang", no_argument, &lto_clang, 1}, {}, };

diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 918470d768e9c..32e573943cf03 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -156,6 +156,10 @@ kallsyms() kallsymopt="${kallsymopt} --base-relative" fi

+ if is_enabled CONFIG_LTO_CLANG; then + kallsymopt="${kallsymopt} --lto-clang" + fi + info KSYMS ${2} scripts/kallsyms ${kallsymopt} ${1} > ${2} }

From: Linus Walleij linus.walleij@linaro.org

[ Upstream commit 95ce158b6c93b28842b54b42ad1cb221b9844062 ]

I get sporadic timeouts from the driver when using the MV88E6352. Reading the status again after the loop fixes the problem: the operation is successful but goes undetected.

Some added prints show things like this:

[ 58.356209] mv88e6085 mdio_mux-0.1:00: Timeout while waiting for switch, addr 1b reg 0b, mask 8000, val 0000, data c000 [ 58.367487] mv88e6085 mdio_mux-0.1:00: Timeout waiting for ATU op 4000, fid 0001 (...) [ 61.826293] mv88e6085 mdio_mux-0.1:00: Timeout while waiting for switch, addr 1c reg 18, mask 8000, val 0000, data 9860 [ 61.837560] mv88e6085 mdio_mux-0.1:00: Timeout waiting for PHY command 1860 to complete

The reason is probably not the commands: I think those are mostly fine with the 50+50ms timeout, but the problem appears when OpenWrt brings up several interfaces in parallel on a system with 7 populated ports: if one of them take more than 50 ms and waits one or more of the others can get stuck on the mutex for the switch and then this can easily multiply.

As we sleep and wait, the function loop needs a final check after exiting the loop if we were successful.

Suggested-by: Andrew Lunn andrew@lunn.ch Cc: Tobias Waldekranz tobias@waldekranz.com Fixes: 35da1dfd9484 ("net: dsa: mv88e6xxx: Improve performance of busy bit polling") Signed-off-by: Linus Walleij linus.walleij@linaro.org Reviewed-by: Andrew Lunn andrew@lunn.ch Link: https://lore.kernel.org/r/20230712223405.861899-1-linus.walleij@linaro.org Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/dsa/mv88e6xxx/chip.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 4db1652015d1d..b69bd44ada1f2 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -109,6 +109,13 @@ int mv88e6xxx_wait_mask(struct mv88e6xxx_chip *chip, int addr, int reg, usleep_range(1000, 2000); }

+ err = mv88e6xxx_read(chip, addr, reg, &data); + if (err) + return err; + + if ((data & mask) == val) + return 0; + dev_err(chip->dev, "Timeout while waiting for switch\n"); return -ETIMEDOUT; }

From: Kuniyuki Iwashima kuniyu@amazon.com

[ Upstream commit 56a16035bb6effb37177867cea94c13a8382f745 ]

When we create an L2 loop on a bridge in netns, we will see packets storm even if STP is enabled.

# unshare -n # ip link add br0 type bridge # ip link add veth0 type veth peer name veth1 # ip link set veth0 master br0 up # ip link set veth1 master br0 up # ip link set br0 type bridge stp_state 1 # ip link set br0 up # sleep 30 # ip -s link show br0 2: br0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP mode DEFAULT group default qlen 1000 link/ether b6:61:98:1c:1c:b5 brd ff:ff:ff:ff:ff:ff RX: bytes packets errors dropped missed mcast 956553768 12861249 0 0 0 12861249 <-. Keep TX: bytes packets errors dropped carrier collsns | increasing 1027834 11951 0 0 0 0 <-' rapidly

This is because llc_rcv() drops all packets in non-root netns and BPDU is dropped.

Let's add extack warning when enabling STP in netns.

# unshare -n # ip link add br0 type bridge # ip link set br0 type bridge stp_state 1 Warning: bridge: STP does not work in non-root netns.

Note this commit will be reverted later when we namespacify the whole LLC infra.

Fixes: e730c15519d0 ("[NET]: Make packet reception network namespace safe") Suggested-by: Harry Coin hcoin@quietfountain.com Link: https://lore.kernel.org/netdev/0f531295-e289-022d-5add-5ceffa0df9bc@quietfou... Suggested-by: Ido Schimmel idosch@idosch.org Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Acked-by: Nikolay Aleksandrov razor@blackwall.org Reviewed-by: Ido Schimmel idosch@nvidia.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/bridge/br_stp_if.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 75204d36d7f90..b65962682771f 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -201,6 +201,9 @@ int br_stp_set_enabled(struct net_bridge *br, unsigned long val, { ASSERT_RTNL();

+ if (!net_eq(dev_net(br->dev), &init_net)) + NL_SET_ERR_MSG_MOD(extack, "STP does not work in non-root netns"); + if (br_mrp_enabled(br)) { NL_SET_ERR_MSG_MOD(extack, "STP can't be enabled if MRP is already enabled");

From: Shyam Prasad N nspmangalore@gmail.com

[ Upstream commit 69cba9d3c1284e0838ae408830a02c4a063104bc ]

When the number of responses with status of STATUS_IO_TIMEOUT exceeds a specified threshold (NUM_STATUS_IO_TIMEOUT), we reconnect the connection. But we do not return the mid, or the credits returned for the mid, or reduce the number of in-flight requests.

This bug could result in the server->in_flight count to go bad, and also cause a leak in the mids.

This change moves the check to a few lines below where the response is decrypted, even of the response is read from the transform header. This way, the code for returning the mids can be reused.

Also, the cifs_reconnect was reconnecting just the transport connection before. In case of multi-channel, this may not be what we want to do after several timeouts. Changed that to reconnect the session and the tree too.

Also renamed NUM_STATUS_IO_TIMEOUT to a more appropriate name MAX_STATUS_IO_TIMEOUT.

Fixes: 8e670f77c4a5 ("Handle STATUS_IO_TIMEOUT gracefully") Signed-off-by: Shyam Prasad N sprasad@microsoft.com Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/smb/client/connect.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-)

diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 935fe198a4baf..cbe08948baf4a 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -59,7 +59,7 @@ extern bool disable_legacy_dialects; #define TLINK_IDLE_EXPIRE (600 * HZ)

/* Drop the connection to not overload the server */ -#define NUM_STATUS_IO_TIMEOUT 5 +#define MAX_STATUS_IO_TIMEOUT 5

struct mount_ctx { struct cifs_sb_info *cifs_sb; @@ -1162,6 +1162,7 @@ cifs_demultiplex_thread(void *p) struct mid_q_entry *mids[MAX_COMPOUND]; char *bufs[MAX_COMPOUND]; unsigned int noreclaim_flag, num_io_timeout = 0; + bool pending_reconnect = false;

noreclaim_flag = memalloc_noreclaim_save(); cifs_dbg(FYI, "Demultiplex PID: %d\n", task_pid_nr(current)); @@ -1201,6 +1202,8 @@ cifs_demultiplex_thread(void *p) cifs_dbg(FYI, "RFC1002 header 0x%x\n", pdu_length); if (!is_smb_response(server, buf[0])) continue; + + pending_reconnect = false; next_pdu: server->pdu_size = pdu_length;

@@ -1258,10 +1261,13 @@ cifs_demultiplex_thread(void *p) if (server->ops->is_status_io_timeout && server->ops->is_status_io_timeout(buf)) { num_io_timeout++; - if (num_io_timeout > NUM_STATUS_IO_TIMEOUT) { - cifs_reconnect(server, false); + if (num_io_timeout > MAX_STATUS_IO_TIMEOUT) { + cifs_server_dbg(VFS, + "Number of request timeouts exceeded %d. Reconnecting", + MAX_STATUS_IO_TIMEOUT); + + pending_reconnect = true; num_io_timeout = 0; - continue; } }

@@ -1308,6 +1314,11 @@ cifs_demultiplex_thread(void *p) buf = server->smallbuf; goto next_pdu; } + + /* do this reconnect at the very end after processing all MIDs */ + if (pending_reconnect) + cifs_reconnect(server, true); + } /* end while !EXITING */

/* buffer usually freed in free_mid - need to free it here on exit */

From: Victor Nogueira victor@mojatatu.com

[ Upstream commit b3d0e0489430735e2e7626aa37e6462cdd136e9d ]

In case an error occurred after mall_set_parms executed successfully, we must undo the tcf_bind_filter call it issues.

Fix that by calling tcf_unbind_filter in err_replace_hw_filter label.

Fixes: ec2507d2a306 ("net/sched: cls_matchall: Fix error path") Signed-off-by: Victor Nogueira victor@mojatatu.com Acked-by: Jamal Hadi Salim jhs@mojatatu.com Reviewed-by: Pedro Tammela pctammela@mojatatu.com Reviewed-by: Simon Horman simon.horman@corigine.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/sched/cls_matchall.c | 35 ++++++++++++----------------------- 1 file changed, 12 insertions(+), 23 deletions(-)

diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 39a5d9c170def..43f8df5847414 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -157,26 +157,6 @@ static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = { [TCA_MATCHALL_FLAGS] = { .type = NLA_U32 }, };

-static int mall_set_parms(struct net *net, struct tcf_proto *tp, - struct cls_mall_head *head, - unsigned long base, struct nlattr **tb, - struct nlattr *est, u32 flags, u32 fl_flags, - struct netlink_ext_ack *extack) -{ - int err; - - err = tcf_exts_validate_ex(net, tp, tb, est, &head->exts, flags, - fl_flags, extack); - if (err < 0) - return err; - - if (tb[TCA_MATCHALL_CLASSID]) { - head->res.classid = nla_get_u32(tb[TCA_MATCHALL_CLASSID]); - tcf_bind_filter(tp, &head->res, base); - } - return 0; -} - static int mall_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, @@ -185,6 +165,7 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, { struct cls_mall_head *head = rtnl_dereference(tp->root); struct nlattr *tb[TCA_MATCHALL_MAX + 1]; + bool bound_to_filter = false; struct cls_mall_head *new; u32 userflags = 0; int err; @@ -224,11 +205,17 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, goto err_alloc_percpu; }

- err = mall_set_parms(net, tp, new, base, tb, tca[TCA_RATE], - flags, new->flags, extack); - if (err) + err = tcf_exts_validate_ex(net, tp, tb, tca[TCA_RATE], + &new->exts, flags, new->flags, extack); + if (err < 0) goto err_set_parms;

+ if (tb[TCA_MATCHALL_CLASSID]) { + new->res.classid = nla_get_u32(tb[TCA_MATCHALL_CLASSID]); + tcf_bind_filter(tp, &new->res, base); + bound_to_filter = true; + } + if (!tc_skip_hw(new->flags)) { err = mall_replace_hw_filter(tp, new, (unsigned long)new, extack); @@ -244,6 +231,8 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, return 0;

err_replace_hw_filter: + if (bound_to_filter) + tcf_unbind_filter(tp, &new->res); err_set_parms: free_percpu(new->pf); err_alloc_percpu:

From: Victor Nogueira victor@mojatatu.com

[ Upstream commit e8d3d78c19be0264a5692bed477c303523aead31 ]

In the case of an update, when TCA_U32_LINK is set, u32_set_parms will decrement the refcount of the ht_down (struct tc_u_hnode) pointer present in the older u32 filter which we are replacing. However, if u32_replace_hw_knode errors out, the update command fails and that ht_down pointer continues decremented. To fix that, when u32_replace_hw_knode fails, check if ht_down's refcount was decremented and undo the decrement.

Fixes: d34e3e181395 ("net: cls_u32: Add support for skip-sw flag to tc u32 classifier.") Signed-off-by: Victor Nogueira victor@mojatatu.com Acked-by: Jamal Hadi Salim jhs@mojatatu.com Reviewed-by: Pedro Tammela pctammela@mojatatu.com Reviewed-by: Simon Horman simon.horman@corigine.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/sched/cls_u32.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 7cfbcd5180841..1280736a7b92e 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -926,6 +926,13 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, if (err) { u32_unbind_filter(tp, new, tb);

+ if (tb[TCA_U32_LINK]) { + struct tc_u_hnode *ht_old; + + ht_old = rtnl_dereference(n->ht_down); + if (ht_old) + ht_old->refcnt++; + } __u32_destroy_key(new); return err; }

From: Oleksij Rempel o.rempel@pengutronix.de

[ Upstream commit f6636ff69ec4f2c94a5ee1d032b21cfe1e0a5678 ]

Move static MAC table operations to separate functions in order to reuse the code for add/del_fdb. This is needed to address kernel warnings caused by the lack of fdb add function support in the current driver.

Signed-off-by: Oleksij Rempel o.rempel@pengutronix.de Reviewed-by: Vladimir Oltean olteanv@gmail.com Signed-off-by: Paolo Abeni pabeni@redhat.com Stable-dep-of: 4bdf79d686b4 ("net: dsa: microchip: correct KSZ8795 static MAC table access") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/dsa/microchip/ksz8795.c | 34 +++++++++++++++++++---------- 1 file changed, 23 insertions(+), 11 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 22250ae222b5b..38fd9b8e0287a 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -926,8 +926,8 @@ int ksz8_fdb_dump(struct ksz_device *dev, int port, return ret; }

-int ksz8_mdb_add(struct ksz_device *dev, int port, - const struct switchdev_obj_port_mdb *mdb, struct dsa_db db) +static int ksz8_add_sta_mac(struct ksz_device *dev, int port, + const unsigned char *addr, u16 vid) { struct alu_struct alu; int index; @@ -937,8 +937,8 @@ int ksz8_mdb_add(struct ksz_device *dev, int port, for (index = 0; index < dev->info->num_statics; index++) { if (!ksz8_r_sta_mac_table(dev, index, &alu)) { /* Found one already in static MAC table. */ - if (!memcmp(alu.mac, mdb->addr, ETH_ALEN) && - alu.fid == mdb->vid) + if (!memcmp(alu.mac, addr, ETH_ALEN) && + alu.fid == vid) break; /* Remember the first empty entry. */ } else if (!empty) { @@ -954,23 +954,23 @@ int ksz8_mdb_add(struct ksz_device *dev, int port, if (index == dev->info->num_statics) { index = empty - 1; memset(&alu, 0, sizeof(alu)); - memcpy(alu.mac, mdb->addr, ETH_ALEN); + memcpy(alu.mac, addr, ETH_ALEN); alu.is_static = true; } alu.port_forward |= BIT(port); - if (mdb->vid) { + if (vid) { alu.is_use_fid = true;

/* Need a way to map VID to FID. */ - alu.fid = mdb->vid; + alu.fid = vid; } ksz8_w_sta_mac_table(dev, index, &alu);

return 0; }

-int ksz8_mdb_del(struct ksz_device *dev, int port, - const struct switchdev_obj_port_mdb *mdb, struct dsa_db db) +static int ksz8_del_sta_mac(struct ksz_device *dev, int port, + const unsigned char *addr, u16 vid) { struct alu_struct alu; int index; @@ -978,8 +978,8 @@ int ksz8_mdb_del(struct ksz_device *dev, int port, for (index = 0; index < dev->info->num_statics; index++) { if (!ksz8_r_sta_mac_table(dev, index, &alu)) { /* Found one already in static MAC table. */ - if (!memcmp(alu.mac, mdb->addr, ETH_ALEN) && - alu.fid == mdb->vid) + if (!memcmp(alu.mac, addr, ETH_ALEN) && + alu.fid == vid) break; } } @@ -998,6 +998,18 @@ int ksz8_mdb_del(struct ksz_device *dev, int port, return 0; }

+int ksz8_mdb_add(struct ksz_device *dev, int port, + const struct switchdev_obj_port_mdb *mdb, struct dsa_db db) +{ + return ksz8_add_sta_mac(dev, port, mdb->addr, mdb->vid); +} + +int ksz8_mdb_del(struct ksz_device *dev, int port, + const struct switchdev_obj_port_mdb *mdb, struct dsa_db db) +{ + return ksz8_del_sta_mac(dev, port, mdb->addr, mdb->vid); +} + int ksz8_port_vlan_filtering(struct ksz_device *dev, int port, bool flag, struct netlink_ext_ack *extack) {

From: Oleksij Rempel o.rempel@pengutronix.de

[ Upstream commit 559901b46810e82ba5321a5e789f994b65d3bc3d ]

Prepare for the next patch by ensuring that ksz8_r_sta_mac_table() does not use error codes for empty entries. This change will enable better handling of read/write errors in the upcoming patch.

Signed-off-by: Oleksij Rempel o.rempel@pengutronix.de Reviewed-by: Vladimir Oltean olteanv@gmail.com Signed-off-by: Paolo Abeni pabeni@redhat.com Stable-dep-of: 4bdf79d686b4 ("net: dsa: microchip: correct KSZ8795 static MAC table access") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/dsa/microchip/ksz8795.c | 87 +++++++++++++++++------------ 1 file changed, 50 insertions(+), 37 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index a2f67be66b97d..6639fae56da7f 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -407,7 +407,7 @@ int ksz8_r_dyn_mac_table(struct ksz_device *dev, u16 addr, u8 *mac_addr, }

static int ksz8_r_sta_mac_table(struct ksz_device *dev, u16 addr, - struct alu_struct *alu) + struct alu_struct *alu, bool *valid) { u32 data_hi, data_lo; const u8 *shifts; @@ -420,28 +420,32 @@ static int ksz8_r_sta_mac_table(struct ksz_device *dev, u16 addr, ksz8_r_table(dev, TABLE_STATIC_MAC, addr, &data); data_hi = data >> 32; data_lo = (u32)data; - if (data_hi & (masks[STATIC_MAC_TABLE_VALID] | - masks[STATIC_MAC_TABLE_OVERRIDE])) { - alu->mac[5] = (u8)data_lo; - alu->mac[4] = (u8)(data_lo >> 8); - alu->mac[3] = (u8)(data_lo >> 16); - alu->mac[2] = (u8)(data_lo >> 24); - alu->mac[1] = (u8)data_hi; - alu->mac[0] = (u8)(data_hi >> 8); - alu->port_forward = - (data_hi & masks[STATIC_MAC_TABLE_FWD_PORTS]) >> - shifts[STATIC_MAC_FWD_PORTS]; - alu->is_override = - (data_hi & masks[STATIC_MAC_TABLE_OVERRIDE]) ? 1 : 0; - data_hi >>= 1; - alu->is_static = true; - alu->is_use_fid = - (data_hi & masks[STATIC_MAC_TABLE_USE_FID]) ? 1 : 0; - alu->fid = (data_hi & masks[STATIC_MAC_TABLE_FID]) >> - shifts[STATIC_MAC_FID]; + + if (!(data_hi & (masks[STATIC_MAC_TABLE_VALID] | + masks[STATIC_MAC_TABLE_OVERRIDE]))) { + *valid = false; return 0; } - return -ENXIO; + + alu->mac[5] = (u8)data_lo; + alu->mac[4] = (u8)(data_lo >> 8); + alu->mac[3] = (u8)(data_lo >> 16); + alu->mac[2] = (u8)(data_lo >> 24); + alu->mac[1] = (u8)data_hi; + alu->mac[0] = (u8)(data_hi >> 8); + alu->port_forward = + (data_hi & masks[STATIC_MAC_TABLE_FWD_PORTS]) >> + shifts[STATIC_MAC_FWD_PORTS]; + alu->is_override = (data_hi & masks[STATIC_MAC_TABLE_OVERRIDE]) ? 1 : 0; + data_hi >>= 1; + alu->is_static = true; + alu->is_use_fid = (data_hi & masks[STATIC_MAC_TABLE_USE_FID]) ? 1 : 0; + alu->fid = (data_hi & masks[STATIC_MAC_TABLE_FID]) >> + shifts[STATIC_MAC_FID]; + + *valid = true; + + return 0; }

void ksz8_w_sta_mac_table(struct ksz_device *dev, u16 addr, @@ -930,20 +934,25 @@ static int ksz8_add_sta_mac(struct ksz_device *dev, int port, const unsigned char *addr, u16 vid) { struct alu_struct alu; - int index; + int index, ret; int empty = 0;

alu.port_forward = 0; for (index = 0; index < dev->info->num_statics; index++) { - if (!ksz8_r_sta_mac_table(dev, index, &alu)) { - /* Found one already in static MAC table. */ - if (!memcmp(alu.mac, addr, ETH_ALEN) && - alu.fid == vid) - break; - /* Remember the first empty entry. */ - } else if (!empty) { - empty = index + 1; + bool valid; + + ret = ksz8_r_sta_mac_table(dev, index, &alu, &valid); + if (ret) + return ret; + if (!valid) { + /* Remember the first empty entry. */ + if (!empty) + empty = index + 1; + continue; } + + if (!memcmp(alu.mac, addr, ETH_ALEN) && alu.fid == vid) + break; }

/* no available entry */ @@ -973,15 +982,19 @@ static int ksz8_del_sta_mac(struct ksz_device *dev, int port, const unsigned char *addr, u16 vid) { struct alu_struct alu; - int index; + int index, ret;

for (index = 0; index < dev->info->num_statics; index++) { - if (!ksz8_r_sta_mac_table(dev, index, &alu)) { - /* Found one already in static MAC table. */ - if (!memcmp(alu.mac, addr, ETH_ALEN) && - alu.fid == vid) - break; - } + bool valid; + + ret = ksz8_r_sta_mac_table(dev, index, &alu, &valid); + if (ret) + return ret; + if (!valid) + continue; + + if (!memcmp(alu.mac, addr, ETH_ALEN) && alu.fid == vid) + break; }

/* no available entry */

From: Ding Hui dinghui@sangfor.com.cn

[ Upstream commit 5f4fa1672d98fe99d2297b03add35346f1685d6b ]

We do netif_napi_add() for all allocated q_vectors[], but potentially do netif_napi_del() for part of them, then kfree q_vectors and leave invalid pointers at dev->napi_list.

Reproducer:

[root@host ~]# cat repro.sh #!/bin/bash

pf_dbsf="0000:41:00.0" vf0_dbsf="0000:41:02.0" g_pids=()

function do_set_numvf() { echo 2 >/sys/bus/pci/devices/${pf_dbsf}/sriov_numvfs sleep $((RANDOM%3+1)) echo 0 >/sys/bus/pci/devices/${pf_dbsf}/sriov_numvfs sleep $((RANDOM%3+1)) }

function do_set_channel() { local nic=$(ls -1 --indicator-style=none /sys/bus/pci/devices/${vf0_dbsf}/net/) [ -z "$nic" ] && { sleep $((RANDOM%3)) ; return 1; } ifconfig $nic 192.168.18.5 netmask 255.255.255.0 ifconfig $nic up ethtool -L $nic combined 1 ethtool -L $nic combined 4 sleep $((RANDOM%3)) }

function on_exit() { local pid for pid in "${g_pids[@]}"; do kill -0 "$pid" &>/dev/null && kill "$pid" &>/dev/null done g_pids=() }

trap "on_exit; exit" EXIT

while :; do do_set_numvf ; done & g_pids+=($!) while :; do do_set_channel ; done & g_pids+=($!)

wait

Result:

[ 4093.900222] ================================================================== [ 4093.900230] BUG: KASAN: use-after-free in free_netdev+0x308/0x390 [ 4093.900232] Read of size 8 at addr ffff88b4dc145640 by task repro.sh/6699 [ 4093.900233] [ 4093.900236] CPU: 10 PID: 6699 Comm: repro.sh Kdump: loaded Tainted: G O --------- -t - 4.18.0 #1 [ 4093.900238] Hardware name: Powerleader PR2008AL/H12DSi-N6, BIOS 2.0 04/09/2021 [ 4093.900239] Call Trace: [ 4093.900244] dump_stack+0x71/0xab [ 4093.900249] print_address_description+0x6b/0x290 [ 4093.900251] ? free_netdev+0x308/0x390 [ 4093.900252] kasan_report+0x14a/0x2b0 [ 4093.900254] free_netdev+0x308/0x390 [ 4093.900261] iavf_remove+0x825/0xd20 [iavf] [ 4093.900265] pci_device_remove+0xa8/0x1f0 [ 4093.900268] device_release_driver_internal+0x1c6/0x460 [ 4093.900271] pci_stop_bus_device+0x101/0x150 [ 4093.900273] pci_stop_and_remove_bus_device+0xe/0x20 [ 4093.900275] pci_iov_remove_virtfn+0x187/0x420 [ 4093.900277] ? pci_iov_add_virtfn+0xe10/0xe10 [ 4093.900278] ? pci_get_subsys+0x90/0x90 [ 4093.900280] sriov_disable+0xed/0x3e0 [ 4093.900282] ? bus_find_device+0x12d/0x1a0 [ 4093.900290] i40e_free_vfs+0x754/0x1210 [i40e] [ 4093.900298] ? i40e_reset_all_vfs+0x880/0x880 [i40e] [ 4093.900299] ? pci_get_device+0x7c/0x90 [ 4093.900300] ? pci_get_subsys+0x90/0x90 [ 4093.900306] ? pci_vfs_assigned.part.7+0x144/0x210 [ 4093.900309] ? __mutex_lock_slowpath+0x10/0x10 [ 4093.900315] i40e_pci_sriov_configure+0x1fa/0x2e0 [i40e] [ 4093.900318] sriov_numvfs_store+0x214/0x290 [ 4093.900320] ? sriov_totalvfs_show+0x30/0x30 [ 4093.900321] ? __mutex_lock_slowpath+0x10/0x10 [ 4093.900323] ? __check_object_size+0x15a/0x350 [ 4093.900326] kernfs_fop_write+0x280/0x3f0 [ 4093.900329] vfs_write+0x145/0x440 [ 4093.900330] ksys_write+0xab/0x160 [ 4093.900332] ? __ia32_sys_read+0xb0/0xb0 [ 4093.900334] ? fput_many+0x1a/0x120 [ 4093.900335] ? filp_close+0xf0/0x130 [ 4093.900338] do_syscall_64+0xa0/0x370 [ 4093.900339] ? page_fault+0x8/0x30 [ 4093.900341] entry_SYSCALL_64_after_hwframe+0x65/0xca [ 4093.900357] RIP: 0033:0x7f16ad4d22c0 [ 4093.900359] Code: 73 01 c3 48 8b 0d d8 cb 2c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d 89 24 2d 00 00 75 10 b8 01 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 fe dd 01 00 48 89 04 24 [ 4093.900360] RSP: 002b:00007ffd6491b7f8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 4093.900362] RAX: ffffffffffffffda RBX: 0000000000000002 RCX: 00007f16ad4d22c0 [ 4093.900363] RDX: 0000000000000002 RSI: 0000000001a41408 RDI: 0000000000000001 [ 4093.900364] RBP: 0000000001a41408 R08: 00007f16ad7a1780 R09: 00007f16ae1f2700 [ 4093.900364] R10: 0000000000000001 R11: 0000000000000246 R12: 0000000000000002 [ 4093.900365] R13: 0000000000000001 R14: 00007f16ad7a0620 R15: 0000000000000001 [ 4093.900367] [ 4093.900368] Allocated by task 820: [ 4093.900371] kasan_kmalloc+0xa6/0xd0 [ 4093.900373] __kmalloc+0xfb/0x200 [ 4093.900376] iavf_init_interrupt_scheme+0x63b/0x1320 [iavf] [ 4093.900380] iavf_watchdog_task+0x3d51/0x52c0 [iavf] [ 4093.900382] process_one_work+0x56a/0x11f0 [ 4093.900383] worker_thread+0x8f/0xf40 [ 4093.900384] kthread+0x2a0/0x390 [ 4093.900385] ret_from_fork+0x1f/0x40 [ 4093.900387] 0xffffffffffffffff [ 4093.900387] [ 4093.900388] Freed by task 6699: [ 4093.900390] __kasan_slab_free+0x137/0x190 [ 4093.900391] kfree+0x8b/0x1b0 [ 4093.900394] iavf_free_q_vectors+0x11d/0x1a0 [iavf] [ 4093.900397] iavf_remove+0x35a/0xd20 [iavf] [ 4093.900399] pci_device_remove+0xa8/0x1f0 [ 4093.900400] device_release_driver_internal+0x1c6/0x460 [ 4093.900401] pci_stop_bus_device+0x101/0x150 [ 4093.900402] pci_stop_and_remove_bus_device+0xe/0x20 [ 4093.900403] pci_iov_remove_virtfn+0x187/0x420 [ 4093.900404] sriov_disable+0xed/0x3e0 [ 4093.900409] i40e_free_vfs+0x754/0x1210 [i40e] [ 4093.900415] i40e_pci_sriov_configure+0x1fa/0x2e0 [i40e] [ 4093.900416] sriov_numvfs_store+0x214/0x290 [ 4093.900417] kernfs_fop_write+0x280/0x3f0 [ 4093.900418] vfs_write+0x145/0x440 [ 4093.900419] ksys_write+0xab/0x160 [ 4093.900420] do_syscall_64+0xa0/0x370 [ 4093.900421] entry_SYSCALL_64_after_hwframe+0x65/0xca [ 4093.900422] 0xffffffffffffffff [ 4093.900422] [ 4093.900424] The buggy address belongs to the object at ffff88b4dc144200 which belongs to the cache kmalloc-8k of size 8192 [ 4093.900425] The buggy address is located 5184 bytes inside of 8192-byte region [ffff88b4dc144200, ffff88b4dc146200) [ 4093.900425] The buggy address belongs to the page: [ 4093.900427] page:ffffea00d3705000 refcount:1 mapcount:0 mapping:ffff88bf04415c80 index:0x0 compound_mapcount: 0 [ 4093.900430] flags: 0x10000000008100(slab|head) [ 4093.900433] raw: 0010000000008100 dead000000000100 dead000000000200 ffff88bf04415c80 [ 4093.900434] raw: 0000000000000000 0000000000030003 00000001ffffffff 0000000000000000 [ 4093.900434] page dumped because: kasan: bad access detected [ 4093.900435] [ 4093.900435] Memory state around the buggy address: [ 4093.900436] ffff88b4dc145500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 4093.900437] ffff88b4dc145580: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 4093.900438] >ffff88b4dc145600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 4093.900438] ^ [ 4093.900439] ffff88b4dc145680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 4093.900440] ffff88b4dc145700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 4093.900440] ==================================================================

Although the patch #2 (of 2) can avoid the issue triggered by this repro.sh, there still are other potential risks that if num_active_queues is changed to less than allocated q_vectors[] by unexpected, the mismatched netif_napi_add/del() can also cause UAF.

Since we actually call netif_napi_add() for all allocated q_vectors unconditionally in iavf_alloc_q_vectors(), so we should fix it by letting netif_napi_del() match to netif_napi_add().

Fixes: 5eae00c57f5e ("i40evf: main driver core") Signed-off-by: Ding Hui dinghui@sangfor.com.cn Cc: Donglin Peng pengdonglin@sangfor.com.cn Cc: Huang Cun huangcun@sangfor.com.cn Reviewed-by: Simon Horman simon.horman@corigine.com Reviewed-by: Madhu Chittim madhu.chittim@intel.com Reviewed-by: Leon Romanovsky leonro@nvidia.com Tested-by: Rafal Romanowski rafal.romanowski@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/iavf/iavf_main.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 965d02d7ff80f..81676c3af4b36 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1840,19 +1840,16 @@ static int iavf_alloc_q_vectors(struct iavf_adapter *adapter) static void iavf_free_q_vectors(struct iavf_adapter *adapter) { int q_idx, num_q_vectors; - int napi_vectors;

if (!adapter->q_vectors) return;

num_q_vectors = adapter->num_msix_vectors - NONQ_VECS; - napi_vectors = adapter->num_active_queues;

for (q_idx = 0; q_idx < num_q_vectors; q_idx++) { struct iavf_q_vector *q_vector = &adapter->q_vectors[q_idx];

- if (q_idx < napi_vectors) - netif_napi_del(&q_vector->napi); + netif_napi_del(&q_vector->napi); } kfree(adapter->q_vectors); adapter->q_vectors = NULL;

From: Ahmed Zaki ahmed.zaki@intel.com

[ Upstream commit a77ed5c5b768e9649be240a2d864e5cd9c6a2015 ]

If the system tries to close the netdev while iavf_reset_task() is running, __LINK_STATE_START will be cleared and netif_running() will return false in iavf_reinit_interrupt_scheme(). This will result in iavf_free_traffic_irqs() not being called and a leak as follows:

[7632.489326] remove_proc_entry: removing non-empty directory 'irq/999', leaking at least 'iavf-enp24s0f0v0-TxRx-0' [7632.490214] WARNING: CPU: 0 PID: 10 at fs/proc/generic.c:718 remove_proc_entry+0x19b/0x1b0

is shown when pci_disable_msix() is later called. Fix by using the internal adapter state. The traffic IRQs will always exist if state == __IAVF_RUNNING.

Fixes: 5b36e8d04b44 ("i40evf: Enable VF to request an alternate queue allocation") Signed-off-by: Ahmed Zaki ahmed.zaki@intel.com Tested-by: Rafal Romanowski rafal.romanowski@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/iavf/iavf_main.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 81676c3af4b36..104de9a071449 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1941,15 +1941,16 @@ static void iavf_free_rss(struct iavf_adapter *adapter) /** * iavf_reinit_interrupt_scheme - Reallocate queues and vectors * @adapter: board private structure + * @running: true if adapter->state == __IAVF_RUNNING * * Returns 0 on success, negative on failure **/ -static int iavf_reinit_interrupt_scheme(struct iavf_adapter *adapter) +static int iavf_reinit_interrupt_scheme(struct iavf_adapter *adapter, bool running) { struct net_device *netdev = adapter->netdev; int err;

- if (netif_running(netdev)) + if (running) iavf_free_traffic_irqs(adapter); iavf_free_misc_irq(adapter); iavf_reset_interrupt_capability(adapter); @@ -3056,7 +3057,7 @@ static void iavf_reset_task(struct work_struct *work)

if ((adapter->flags & IAVF_FLAG_REINIT_MSIX_NEEDED) || (adapter->flags & IAVF_FLAG_REINIT_ITR_NEEDED)) { - err = iavf_reinit_interrupt_scheme(adapter); + err = iavf_reinit_interrupt_scheme(adapter, running); if (err) goto reset_err; }

From: Ahmed Zaki ahmed.zaki@intel.com

[ Upstream commit 7dcbdf29282fbcdb646dc785e8a57ed2c2fec8ba ]

When the user disables rxvlan offloading and then changes the number of channels, all VLAN ports are unable to receive traffic.

Changing the number of channels triggers a VFR reset. During re-init, when VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS is received, we do: 1 - set the IAVF_FLAG_SETUP_NETDEV_FEATURES flag 2 - call iavf_set_vlan_offload_features(adapter, 0, netdev->features);

The second step sends to the PF the __default__ features, in this case aq_required |= IAVF_FLAG_AQ_ENABLE_CTAG_VLAN_STRIPPING

While the first step forces the watchdog task to call netdev_update_features() -> iavf_set_features() -> iavf_set_vlan_offload_features(adapter, netdev->features, features). Since the user disabled the "rxvlan", this sets: aq_required |= IAVF_FLAG_AQ_DISABLE_CTAG_VLAN_STRIPPING

When we start processing the AQ commands, both flags are enabled. Since we process DISABLE_XTAG first then ENABLE_XTAG, this results in the PF enabling the rxvlan offload. This breaks all communications on the VLAN net devices.

Fix by removing the call to iavf_set_vlan_offload_features() (second step). Calling netdev_update_features() from watchdog task is enough for both init and reset paths.

Fixes: 7598f4b40bd6 ("iavf: Move netdev_update_features() into watchdog task") Signed-off-by: Ahmed Zaki ahmed.zaki@intel.com Tested-by: Rafal Romanowski rafal.romanowski@intel.com Reviewed-by: Leon Romanovsky leonro@nvidia.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Stable-dep-of: c2ed2403f12c ("iavf: Wait for reset in callbacks which trigger it") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/iavf/iavf_virtchnl.c | 5 ----- 1 file changed, 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 07d37402a0df5..7b34111fd4eb1 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -2238,11 +2238,6 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, iavf_process_config(adapter); adapter->flags |= IAVF_FLAG_SETUP_NETDEV_FEATURES;

- /* Request VLAN offload settings */ - if (VLAN_V2_ALLOWED(adapter)) - iavf_set_vlan_offload_features(adapter, 0, - netdev->features); - iavf_set_queue_vlan_tag_loc(adapter);

was_mac_changed = !ether_addr_equal(netdev->dev_addr,

From: Marcin Szycik marcin.szycik@linux.intel.com

[ Upstream commit c2ed2403f12c74a74a0091ed5d830e72c58406e8 ]

There was a fail when trying to add the interface to bonding right after changing the MTU on the interface. It was caused by bonding interface unable to open the interface due to interface being in __RESETTING state because of MTU change.

Add new reset_waitqueue to indicate that reset has finished.

Add waiting for reset to finish in callbacks which trigger hw reset: iavf_set_priv_flags(), iavf_change_mtu() and iavf_set_ringparam(). We use a 5000ms timeout period because on Hyper-V based systems, this operation takes around 3000-4000ms. In normal circumstances, it doesn't take more than 500ms to complete.

Add a function iavf_wait_for_reset() to reuse waiting for reset code and use it also in iavf_set_channels(), which already waits for reset. We don't use error handling in iavf_set_channels() as this could cause the device to be in incorrect state if the reset was scheduled but hit timeout or the waitng function was interrupted by a signal.

Fixes: 4e5e6b5d9d13 ("iavf: Fix return of set the new channel count") Signed-off-by: Marcin Szycik marcin.szycik@linux.intel.com Co-developed-by: Dawid Wesierski dawidx.wesierski@intel.com Signed-off-by: Dawid Wesierski dawidx.wesierski@intel.com Signed-off-by: Sylwester Dziedziuch sylwesterx.dziedziuch@intel.com Signed-off-by: Kamil Maziarz kamil.maziarz@intel.com Signed-off-by: Mateusz Palczewski mateusz.palczewski@intel.com Tested-by: Rafal Romanowski rafal.romanowski@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/iavf/iavf.h | 2 + .../net/ethernet/intel/iavf/iavf_ethtool.c | 31 ++++++----- drivers/net/ethernet/intel/iavf/iavf_main.c | 51 ++++++++++++++++++- .../net/ethernet/intel/iavf/iavf_virtchnl.c | 1 + 4 files changed, 68 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index a716ed6bb787d..2fe44e865d0a2 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -257,6 +257,7 @@ struct iavf_adapter { struct work_struct adminq_task; struct delayed_work client_task; wait_queue_head_t down_waitqueue; + wait_queue_head_t reset_waitqueue; wait_queue_head_t vc_waitqueue; struct iavf_q_vector *q_vectors; struct list_head vlan_filter_list; @@ -582,4 +583,5 @@ void iavf_add_adv_rss_cfg(struct iavf_adapter *adapter); void iavf_del_adv_rss_cfg(struct iavf_adapter *adapter); struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter, const u8 *macaddr); +int iavf_wait_for_reset(struct iavf_adapter *adapter); #endif /* _IAVF_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 4746ee517c75a..73219c5069290 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -484,6 +484,7 @@ static int iavf_set_priv_flags(struct net_device *netdev, u32 flags) { struct iavf_adapter *adapter = netdev_priv(netdev); u32 orig_flags, new_flags, changed_flags; + int ret = 0; u32 i;

orig_flags = READ_ONCE(adapter->flags); @@ -533,10 +534,13 @@ static int iavf_set_priv_flags(struct net_device *netdev, u32 flags) if (netif_running(netdev)) { adapter->flags |= IAVF_FLAG_RESET_NEEDED; queue_work(adapter->wq, &adapter->reset_task); + ret = iavf_wait_for_reset(adapter); + if (ret) + netdev_warn(netdev, "Changing private flags timeout or interrupted waiting for reset"); } }

- return 0; + return ret; }

/** @@ -627,6 +631,7 @@ static int iavf_set_ringparam(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); u32 new_rx_count, new_tx_count; + int ret = 0;

if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) return -EINVAL; @@ -673,9 +678,12 @@ static int iavf_set_ringparam(struct net_device *netdev, if (netif_running(netdev)) { adapter->flags |= IAVF_FLAG_RESET_NEEDED; queue_work(adapter->wq, &adapter->reset_task); + ret = iavf_wait_for_reset(adapter); + if (ret) + netdev_warn(netdev, "Changing ring parameters timeout or interrupted waiting for reset"); }

- return 0; + return ret; }

/** @@ -1830,7 +1838,7 @@ static int iavf_set_channels(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); u32 num_req = ch->combined_count; - int i; + int ret = 0;

if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && adapter->num_tc) { @@ -1854,20 +1862,11 @@ static int iavf_set_channels(struct net_device *netdev, adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED; iavf_schedule_reset(adapter);

- /* wait for the reset is done */ - for (i = 0; i < IAVF_RESET_WAIT_COMPLETE_COUNT; i++) { - msleep(IAVF_RESET_WAIT_MS); - if (adapter->flags & IAVF_FLAG_RESET_PENDING) - continue; - break; - } - if (i == IAVF_RESET_WAIT_COMPLETE_COUNT) { - adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; - adapter->num_req_queues = 0; - return -EOPNOTSUPP; - } + ret = iavf_wait_for_reset(adapter); + if (ret) + netdev_warn(netdev, "Changing channel count timeout or interrupted waiting for reset");

- return 0; + return ret; }

/** diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index d5b1dcfe0ccdd..c2739071149de 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -166,6 +166,45 @@ static struct iavf_adapter *iavf_pdev_to_adapter(struct pci_dev *pdev) return netdev_priv(pci_get_drvdata(pdev)); }

+/** + * iavf_is_reset_in_progress - Check if a reset is in progress + * @adapter: board private structure + */ +static bool iavf_is_reset_in_progress(struct iavf_adapter *adapter) +{ + if (adapter->state == __IAVF_RESETTING || + adapter->flags & (IAVF_FLAG_RESET_PENDING | + IAVF_FLAG_RESET_NEEDED)) + return true; + + return false; +} + +/** + * iavf_wait_for_reset - Wait for reset to finish. + * @adapter: board private structure + * + * Returns 0 if reset finished successfully, negative on timeout or interrupt. + */ +int iavf_wait_for_reset(struct iavf_adapter *adapter) +{ + int ret = wait_event_interruptible_timeout(adapter->reset_waitqueue, + !iavf_is_reset_in_progress(adapter), + msecs_to_jiffies(5000)); + + /* If ret < 0 then it means wait was interrupted. + * If ret == 0 then it means we got a timeout while waiting + * for reset to finish. + * If ret > 0 it means reset has finished. + */ + if (ret > 0) + return 0; + else if (ret < 0) + return -EINTR; + else + return -EBUSY; +} + /** * iavf_allocate_dma_mem_d - OS specific memory alloc for shared code * @hw: pointer to the HW structure @@ -3161,6 +3200,7 @@ static void iavf_reset_task(struct work_struct *work)

adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED;

+ wake_up(&adapter->reset_waitqueue); mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock);

@@ -4325,6 +4365,7 @@ static int iavf_close(struct net_device *netdev) static int iavf_change_mtu(struct net_device *netdev, int new_mtu) { struct iavf_adapter *adapter = netdev_priv(netdev); + int ret = 0;

netdev_dbg(netdev, "changing MTU from %d to %d\n", netdev->mtu, new_mtu); @@ -4337,9 +4378,14 @@ static int iavf_change_mtu(struct net_device *netdev, int new_mtu) if (netif_running(netdev)) { adapter->flags |= IAVF_FLAG_RESET_NEEDED; queue_work(adapter->wq, &adapter->reset_task); + ret = iavf_wait_for_reset(adapter); + if (ret < 0) + netdev_warn(netdev, "MTU change interrupted waiting for reset"); + else if (ret) + netdev_warn(netdev, "MTU change timed out waiting for reset"); }

- return 0; + return ret; }

#define NETIF_VLAN_OFFLOAD_FEATURES (NETIF_F_HW_VLAN_CTAG_RX | \ @@ -4942,6 +4988,9 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Setup the wait queue for indicating transition to down status */ init_waitqueue_head(&adapter->down_waitqueue);

+ /* Setup the wait queue for indicating transition to running state */ + init_waitqueue_head(&adapter->reset_waitqueue); + /* Setup the wait queue for indicating virtchannel events */ init_waitqueue_head(&adapter->vc_waitqueue);

diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 7b34111fd4eb1..eec7ac3b7f6ee 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -2285,6 +2285,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, case VIRTCHNL_OP_ENABLE_QUEUES: /* enable transmits */ iavf_irq_enable(adapter, true); + wake_up(&adapter->reset_waitqueue); adapter->flags &= ~IAVF_FLAG_QUEUES_DISABLED; break; case VIRTCHNL_OP_DISABLE_QUEUES:

From: Ahmed Zaki ahmed.zaki@intel.com

[ Upstream commit c34743daca0eb1dc855831a5210f0800a850088e ]

The reset task is currently scheduled from the watchdog or adminq tasks. First, all direct calls to schedule the reset task are replaced with the iavf_schedule_reset(), which is modified to accept the flag showing the type of reset.

To prevent the reset task from starting once iavf_remove() starts, we need to check the __IAVF_IN_REMOVE_TASK bit before we schedule it. This is now easily added to iavf_schedule_reset().

Finally, remove the check for IAVF_FLAG_RESET_NEEDED in the watchdog task. It is redundant since all callers who set the flag immediately schedules the reset task.

Fixes: 3ccd54ef44eb ("iavf: Fix init state closure on remove") Fixes: 14756b2ae265 ("iavf: Fix __IAVF_RESETTING state usage") Signed-off-by: Ahmed Zaki ahmed.zaki@intel.com Signed-off-by: Mateusz Palczewski mateusz.palczewski@intel.com Tested-by: Rafal Romanowski rafal.romanowski@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/iavf/iavf.h | 2 +- .../net/ethernet/intel/iavf/iavf_ethtool.c | 8 ++--- drivers/net/ethernet/intel/iavf/iavf_main.c | 32 +++++++------------ .../net/ethernet/intel/iavf/iavf_virtchnl.c | 3 +- 4 files changed, 16 insertions(+), 29 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 305675042fe55..543931c06bb17 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -520,7 +520,7 @@ int iavf_up(struct iavf_adapter *adapter); void iavf_down(struct iavf_adapter *adapter); int iavf_process_config(struct iavf_adapter *adapter); int iavf_parse_vf_resource_msg(struct iavf_adapter *adapter); -void iavf_schedule_reset(struct iavf_adapter *adapter); +void iavf_schedule_reset(struct iavf_adapter *adapter, u64 flags); void iavf_schedule_request_stats(struct iavf_adapter *adapter); void iavf_schedule_finish_config(struct iavf_adapter *adapter); void iavf_reset(struct iavf_adapter *adapter); diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 73219c5069290..fd6d6f6263f66 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -532,8 +532,7 @@ static int iavf_set_priv_flags(struct net_device *netdev, u32 flags) /* issue a reset to force legacy-rx change to take effect */ if (changed_flags & IAVF_FLAG_LEGACY_RX) { if (netif_running(netdev)) { - adapter->flags |= IAVF_FLAG_RESET_NEEDED; - queue_work(adapter->wq, &adapter->reset_task); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); ret = iavf_wait_for_reset(adapter); if (ret) netdev_warn(netdev, "Changing private flags timeout or interrupted waiting for reset"); @@ -676,8 +675,7 @@ static int iavf_set_ringparam(struct net_device *netdev, }

if (netif_running(netdev)) { - adapter->flags |= IAVF_FLAG_RESET_NEEDED; - queue_work(adapter->wq, &adapter->reset_task); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); ret = iavf_wait_for_reset(adapter); if (ret) netdev_warn(netdev, "Changing ring parameters timeout or interrupted waiting for reset"); @@ -1860,7 +1858,7 @@ static int iavf_set_channels(struct net_device *netdev,

adapter->num_req_queues = num_req; adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED; - iavf_schedule_reset(adapter); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED);

ret = iavf_wait_for_reset(adapter); if (ret) diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 0e201d690f0dd..c1f91c55e1ca7 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -309,12 +309,14 @@ static int iavf_lock_timeout(struct mutex *lock, unsigned int msecs) /** * iavf_schedule_reset - Set the flags and schedule a reset event * @adapter: board private structure + * @flags: IAVF_FLAG_RESET_PENDING or IAVF_FLAG_RESET_NEEDED **/ -void iavf_schedule_reset(struct iavf_adapter *adapter) +void iavf_schedule_reset(struct iavf_adapter *adapter, u64 flags) { - if (!(adapter->flags & - (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED))) { - adapter->flags |= IAVF_FLAG_RESET_NEEDED; + if (!test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section) && + !(adapter->flags & + (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED))) { + adapter->flags |= flags; queue_work(adapter->wq, &adapter->reset_task); } } @@ -342,7 +344,7 @@ static void iavf_tx_timeout(struct net_device *netdev, unsigned int txqueue) struct iavf_adapter *adapter = netdev_priv(netdev);

adapter->tx_timeout_count++; - iavf_schedule_reset(adapter); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); }

/** @@ -2490,7 +2492,7 @@ int iavf_parse_vf_resource_msg(struct iavf_adapter *adapter) adapter->vsi_res->num_queue_pairs); adapter->flags |= IAVF_FLAG_REINIT_MSIX_NEEDED; adapter->num_req_queues = adapter->vsi_res->num_queue_pairs; - iavf_schedule_reset(adapter); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED);

return -EAGAIN; } @@ -2787,14 +2789,6 @@ static void iavf_watchdog_task(struct work_struct *work) if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) iavf_change_state(adapter, __IAVF_COMM_FAILED);

- if (adapter->flags & IAVF_FLAG_RESET_NEEDED) { - adapter->aq_required = 0; - adapter->current_op = VIRTCHNL_OP_UNKNOWN; - mutex_unlock(&adapter->crit_lock); - queue_work(adapter->wq, &adapter->reset_task); - return; - } - switch (adapter->state) { case __IAVF_STARTUP: iavf_startup(adapter); @@ -2922,11 +2916,10 @@ static void iavf_watchdog_task(struct work_struct *work) /* check for hw reset */ reg_val = rd32(hw, IAVF_VF_ARQLEN1) & IAVF_VF_ARQLEN1_ARQENABLE_MASK; if (!reg_val) { - adapter->flags |= IAVF_FLAG_RESET_PENDING; adapter->aq_required = 0; adapter->current_op = VIRTCHNL_OP_UNKNOWN; dev_err(&adapter->pdev->dev, "Hardware reset detected\n"); - queue_work(adapter->wq, &adapter->reset_task); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_PENDING); mutex_unlock(&adapter->crit_lock); queue_delayed_work(adapter->wq, &adapter->watchdog_task, HZ * 2); @@ -3324,9 +3317,7 @@ static void iavf_adminq_task(struct work_struct *work) } while (pending); mutex_unlock(&adapter->crit_lock);

- if ((adapter->flags & - (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED)) || - adapter->state == __IAVF_RESETTING) + if (iavf_is_reset_in_progress(adapter)) goto freedom;

/* check for error indications */ @@ -4423,8 +4414,7 @@ static int iavf_change_mtu(struct net_device *netdev, int new_mtu) }

if (netif_running(netdev)) { - adapter->flags |= IAVF_FLAG_RESET_NEEDED; - queue_work(adapter->wq, &adapter->reset_task); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); ret = iavf_wait_for_reset(adapter); if (ret < 0) netdev_warn(netdev, "MTU change interrupted waiting for reset"); diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 35419673b6987..2fc8e60ef6afb 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -1961,9 +1961,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, case VIRTCHNL_EVENT_RESET_IMPENDING: dev_info(&adapter->pdev->dev, "Reset indication received from the PF\n"); if (!(adapter->flags & IAVF_FLAG_RESET_PENDING)) { - adapter->flags |= IAVF_FLAG_RESET_PENDING; dev_info(&adapter->pdev->dev, "Scheduling reset task\n"); - queue_work(adapter->wq, &adapter->reset_task); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_PENDING); } break; default:

From: Geetha sowjanya gakula@marvell.com

[ Upstream commit 8fcd7c7b3a38ab5e452f542fda8f7940e77e479a ]

Current driver enables backpressure for LBK interfaces. But these interfaces do not support this feature. Hence, this patch fixes the issue by skipping the backpressure configuration for these interfaces.

Fixes: 75f36270990c ("octeontx2-pf: Support to enable/disable pause frames via ethtool"). Signed-off-by: Geetha sowjanya gakula@marvell.com Signed-off-by: Sunil Goutham sgoutham@marvell.com Link: https://lore.kernel.org/r/20230716093741.28063-1-gakula@marvell.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index ed911d9946277..c236dba80ff1a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1452,8 +1452,9 @@ static int otx2_init_hw_resources(struct otx2_nic *pf) if (err) goto err_free_npa_lf;

- /* Enable backpressure */ - otx2_nix_config_bp(pf, true); + /* Enable backpressure for CGX mapped PF/VFs */ + if (!is_otx2_lbkvf(pf->pdev)) + otx2_nix_config_bp(pf, true);

/* Init Auras and pools used by NIX RQ, for free buffer ptrs */ err = otx2_rq_aura_pool_init(pf);

From: Kumar Kartikeya Dwivedi memxor@gmail.com

[ Upstream commit b5e9ad522c4ccd32d322877515cff8d47ed731b9 ]

While the check_max_stack_depth function explores call chains emanating from the main prog, which is typically enough to cover all possible call chains, it doesn't explore those rooted at async callbacks unless the async callback will have been directly called, since unlike non-async callbacks it skips their instruction exploration as they don't contribute to stack depth.

It could be the case that the async callback leads to a callchain which exceeds the stack depth, but this is never reachable while only exploring the entry point from main subprog. Hence, repeat the check for the main subprog *and* all async callbacks marked by the symbolic execution pass of the verifier, as execution of the program may begin at any of them.

Consider functions with following stack depths: main: 256 async: 256 foo: 256

main: rX = async bpf_timer_set_callback(...)

async: foo()

Here, async is not descended as it does not contribute to stack depth of main (since it is referenced using bpf_pseudo_func and not bpf_pseudo_call). However, when async is invoked asynchronously, it will end up breaching the MAX_BPF_STACK limit by calling foo.

Hence, in addition to main, we also need to explore call chains beginning at all async callback subprogs in a program.

Fixes: 7ddc80a476c2 ("bpf: Teach stack depth check about async callbacks.") Signed-off-by: Kumar Kartikeya Dwivedi memxor@gmail.com Link: https://lore.kernel.org/r/20230717161530.1238-3-memxor@gmail.com Signed-off-by: Alexei Starovoitov ast@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/bpf/verifier.c | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index fdba4086881b3..f25ce959fae64 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4288,16 +4288,17 @@ static int update_stack_depth(struct bpf_verifier_env *env, * Since recursion is prevented by check_cfg() this algorithm * only needs a local stack of MAX_CALL_FRAMES to remember callsites */ -static int check_max_stack_depth(struct bpf_verifier_env *env) +static int check_max_stack_depth_subprog(struct bpf_verifier_env *env, int idx) { - int depth = 0, frame = 0, idx = 0, i = 0, subprog_end; struct bpf_subprog_info *subprog = env->subprog_info; struct bpf_insn *insn = env->prog->insnsi; + int depth = 0, frame = 0, i, subprog_end; bool tail_call_reachable = false; int ret_insn[MAX_CALL_FRAMES]; int ret_prog[MAX_CALL_FRAMES]; int j;

+ i = subprog[idx].start; process_func: /* protect against potential stack overflow that might happen when * bpf2bpf calls get combined with tailcalls. Limit the caller's stack @@ -4398,6 +4399,22 @@ static int check_max_stack_depth(struct bpf_verifier_env *env) goto continue_func; }

+static int check_max_stack_depth(struct bpf_verifier_env *env) +{ + struct bpf_subprog_info *si = env->subprog_info; + int ret; + + for (int i = 0; i < env->subprog_cnt; i++) { + if (!i || si[i].is_async_cb) { + ret = check_max_stack_depth_subprog(env, i); + if (ret < 0) + return ret; + } + continue; + } + return 0; +} + #ifndef CONFIG_BPF_JIT_ALWAYS_ON static int get_callee_stack_depth(struct bpf_verifier_env *env, const struct bpf_insn *insn, int idx)

From: Kurt Kanzenbach kurt@linutronix.de

[ Upstream commit 95b681485563c64585de78662ee52d06b7fa47d9 ]

High XDP load triggers the netdev watchdog:

|NETDEV WATCHDOG: enp3s0 (igc): transmit queue 2 timed out

The reason is the Tx queue transmission start (txq->trans_start) is not updated in XDP code path. Therefore, add it for all XDP transmission functions.

Signed-off-by: Kurt Kanzenbach kurt@linutronix.de Tested-by: Naama Meir naamax.meir@linux.intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Stable-dep-of: 78adb4bcf99e ("igc: Prevent garbled TX queue with XDP ZEROCOPY") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/igc/igc_main.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 273941f90f066..ade4bde47c65a 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -2402,6 +2402,8 @@ static int igc_xdp_xmit_back(struct igc_adapter *adapter, struct xdp_buff *xdp) nq = txring_txq(ring);

__netif_tx_lock(nq, cpu); + /* Avoid transmit queue timeout since we share it with the slow path */ + txq_trans_cond_update(nq); res = igc_xdp_init_tx_descriptor(ring, xdpf); __netif_tx_unlock(nq); return res; @@ -2804,6 +2806,9 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring)

__netif_tx_lock(nq, cpu);

+ /* Avoid transmit queue timeout since we share it with the slow path */ + txq_trans_cond_update(nq); + budget = igc_desc_unused(ring);

while (xsk_tx_peek_desc(pool, &xdp_desc) && budget--) { @@ -6297,6 +6302,9 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames,

__netif_tx_lock(nq, cpu);

+ /* Avoid transmit queue timeout since we share it with the slow path */ + txq_trans_cond_update(nq); + drops = 0; for (i = 0; i < num_frames; i++) { int err;

From: Antoine Tenart atenart@kernel.org

[ Upstream commit c0a8966e2bc7d31f77a7246947ebc09c1ff06066 ]

When using IPv4/TCP, skb->hash comes from sk->sk_txhash except in TIME_WAIT and SYN_RECV where it's not set in the reply skb from ip_send_unicast_reply. Those packets will have a mismatched hash with others from the same flow as their hashes will be 0. IPv6 does not have the same issue as the hash is set from the socket txhash in those cases.

This commits sets the hash in the reply skb from ip_send_unicast_reply, which makes the IPv4 code behaving like IPv6.

Signed-off-by: Antoine Tenart atenart@kernel.org Reviewed-by: Eric Dumazet edumazet@google.com Signed-off-by: Paolo Abeni pabeni@redhat.com Stable-dep-of: 5e5265522a9a ("tcp: annotate data-races around tcp_rsk(req)->txhash") Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/ip.h | 2 +- net/ipv4/ip_output.c | 4 +++- net/ipv4/tcp_ipv4.c | 14 +++++++++----- 3 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h index acec504c469a0..83a1a9bc3ceb1 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -282,7 +282,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, const struct ip_options *sopt, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, - unsigned int len, u64 transmit_time); + unsigned int len, u64 transmit_time, u32 txhash);

#define IP_INC_STATS(net, field) SNMP_INC_STATS64((net)->mib.ip_statistics, field) #define __IP_INC_STATS(net, field) __SNMP_INC_STATS64((net)->mib.ip_statistics, field) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 2a07588265c70..7b4ab545c06e0 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1691,7 +1691,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, const struct ip_options *sopt, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, - unsigned int len, u64 transmit_time) + unsigned int len, u64 transmit_time, u32 txhash) { struct ip_options_data replyopts; struct ipcm_cookie ipc; @@ -1754,6 +1754,8 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, arg->csum)); nskb->ip_summed = CHECKSUM_NONE; nskb->mono_delivery_time = !!transmit_time; + if (txhash) + skb_set_hash(nskb, txhash, PKT_HASH_TYPE_L4); ip_push_pending_frames(sk, &fl4); } out: diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a7de5ba74e7f7..ef740983a1222 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -692,6 +692,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) u64 transmit_time = 0; struct sock *ctl_sk; struct net *net; + u32 txhash = 0;

/* Never send a reset in response to a reset. */ if (th->rst) @@ -829,6 +830,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) inet_twsk(sk)->tw_priority : sk->sk_priority; transmit_time = tcp_transmit_time(sk); xfrm_sk_clone_policy(ctl_sk, sk); + txhash = (sk->sk_state == TCP_TIME_WAIT) ? + inet_twsk(sk)->tw_txhash : sk->sk_txhash; } else { ctl_sk->sk_mark = 0; ctl_sk->sk_priority = 0; @@ -837,7 +840,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) skb, &TCP_SKB_CB(skb)->header.h4.opt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len, - transmit_time); + transmit_time, txhash);

xfrm_sk_free_policy(ctl_sk); sock_net_set(ctl_sk, &init_net); @@ -859,7 +862,7 @@ static void tcp_v4_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, - int reply_flags, u8 tos) + int reply_flags, u8 tos, u32 txhash) { const struct tcphdr *th = tcp_hdr(skb); struct { @@ -935,7 +938,7 @@ static void tcp_v4_send_ack(const struct sock *sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len, - transmit_time); + transmit_time, txhash);

sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); @@ -955,7 +958,8 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0, - tw->tw_tos + tw->tw_tos, + tw->tw_txhash );

inet_twsk_put(tw); @@ -988,7 +992,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, 0, tcp_md5_do_lookup(sk, l3index, addr, AF_INET), inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, - ip_hdr(skb)->tos); + ip_hdr(skb)->tos, tcp_rsk(req)->txhash); }

/*

From: Eric Dumazet edumazet@google.com

[ Upstream commit eba20811f32652bc1a52d5e7cc403859b86390d9 ]

TCP request sockets are lockless, tcp_rsk(req)->ts_recent can change while being read by another cpu as syzbot noticed.

This is harmless, but we should annotate the known races.

Note that tcp_check_req() changes req->ts_recent a bit early, we might change this in the future.

BUG: KCSAN: data-race in tcp_check_req / tcp_check_req

write to 0xffff88813c8afb84 of 4 bytes by interrupt on cpu 1: tcp_check_req+0x694/0xc70 net/ipv4/tcp_minisocks.c:762 tcp_v4_rcv+0x12db/0x1b70 net/ipv4/tcp_ipv4.c:2071 ip_protocol_deliver_rcu+0x356/0x6d0 net/ipv4/ip_input.c:205 ip_local_deliver_finish+0x13c/0x1a0 net/ipv4/ip_input.c:233 NF_HOOK include/linux/netfilter.h:303 [inline] ip_local_deliver+0xec/0x1c0 net/ipv4/ip_input.c:254 dst_input include/net/dst.h:468 [inline] ip_rcv_finish net/ipv4/ip_input.c:449 [inline] NF_HOOK include/linux/netfilter.h:303 [inline] ip_rcv+0x197/0x270 net/ipv4/ip_input.c:569 __netif_receive_skb_one_core net/core/dev.c:5493 [inline] __netif_receive_skb+0x90/0x1b0 net/core/dev.c:5607 process_backlog+0x21f/0x380 net/core/dev.c:5935 __napi_poll+0x60/0x3b0 net/core/dev.c:6498 napi_poll net/core/dev.c:6565 [inline] net_rx_action+0x32b/0x750 net/core/dev.c:6698 __do_softirq+0xc1/0x265 kernel/softirq.c:571 do_softirq+0x7e/0xb0 kernel/softirq.c:472 __local_bh_enable_ip+0x64/0x70 kernel/softirq.c:396 local_bh_enable+0x1f/0x20 include/linux/bottom_half.h:33 rcu_read_unlock_bh include/linux/rcupdate.h:843 [inline] __dev_queue_xmit+0xabb/0x1d10 net/core/dev.c:4271 dev_queue_xmit include/linux/netdevice.h:3088 [inline] neigh_hh_output include/net/neighbour.h:528 [inline] neigh_output include/net/neighbour.h:542 [inline] ip_finish_output2+0x700/0x840 net/ipv4/ip_output.c:229 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:317 NF_HOOK_COND include/linux/netfilter.h:292 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:431 dst_output include/net/dst.h:458 [inline] ip_local_out net/ipv4/ip_output.c:126 [inline] __ip_queue_xmit+0xa4d/0xa70 net/ipv4/ip_output.c:533 ip_queue_xmit+0x38/0x40 net/ipv4/ip_output.c:547 __tcp_transmit_skb+0x1194/0x16e0 net/ipv4/tcp_output.c:1399 tcp_transmit_skb net/ipv4/tcp_output.c:1417 [inline] tcp_write_xmit+0x13ff/0x2fd0 net/ipv4/tcp_output.c:2693 __tcp_push_pending_frames+0x6a/0x1a0 net/ipv4/tcp_output.c:2877 tcp_push_pending_frames include/net/tcp.h:1952 [inline] __tcp_sock_set_cork net/ipv4/tcp.c:3336 [inline] tcp_sock_set_cork+0xe8/0x100 net/ipv4/tcp.c:3343 rds_tcp_xmit_path_complete+0x3b/0x40 net/rds/tcp_send.c:52 rds_send_xmit+0xf8d/0x1420 net/rds/send.c:422 rds_send_worker+0x42/0x1d0 net/rds/threads.c:200 process_one_work+0x3e6/0x750 kernel/workqueue.c:2408 worker_thread+0x5f2/0xa10 kernel/workqueue.c:2555 kthread+0x1d7/0x210 kernel/kthread.c:379 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308

read to 0xffff88813c8afb84 of 4 bytes by interrupt on cpu 0: tcp_check_req+0x32a/0xc70 net/ipv4/tcp_minisocks.c:622 tcp_v4_rcv+0x12db/0x1b70 net/ipv4/tcp_ipv4.c:2071 ip_protocol_deliver_rcu+0x356/0x6d0 net/ipv4/ip_input.c:205 ip_local_deliver_finish+0x13c/0x1a0 net/ipv4/ip_input.c:233 NF_HOOK include/linux/netfilter.h:303 [inline] ip_local_deliver+0xec/0x1c0 net/ipv4/ip_input.c:254 dst_input include/net/dst.h:468 [inline] ip_rcv_finish net/ipv4/ip_input.c:449 [inline] NF_HOOK include/linux/netfilter.h:303 [inline] ip_rcv+0x197/0x270 net/ipv4/ip_input.c:569 __netif_receive_skb_one_core net/core/dev.c:5493 [inline] __netif_receive_skb+0x90/0x1b0 net/core/dev.c:5607 process_backlog+0x21f/0x380 net/core/dev.c:5935 __napi_poll+0x60/0x3b0 net/core/dev.c:6498 napi_poll net/core/dev.c:6565 [inline] net_rx_action+0x32b/0x750 net/core/dev.c:6698 __do_softirq+0xc1/0x265 kernel/softirq.c:571 run_ksoftirqd+0x17/0x20 kernel/softirq.c:939 smpboot_thread_fn+0x30a/0x4a0 kernel/smpboot.c:164 kthread+0x1d7/0x210 kernel/kthread.c:379 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308

value changed: 0x1cd237f1 -> 0x1cd237f2

Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Reviewed-by: Kuniyuki Iwashima kuniyu@amazon.com Link: https://lore.kernel.org/r/20230717144445.653164-3-edumazet@google.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/tcp_minisocks.c | 9 ++++++--- net/ipv4/tcp_output.c | 2 +- net/ipv6/tcp_ipv6.c | 2 +- 4 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index e5df50b3e23a0..d49a66b271d52 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -988,7 +988,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, - req->ts_recent, + READ_ONCE(req->ts_recent), 0, tcp_md5_do_lookup(sk, l3index, addr, AF_INET), inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index f281eab7fd125..42844d20da020 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -537,7 +537,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->max_window = newtp->snd_wnd;

if (newtp->rx_opt.tstamp_ok) { - newtp->rx_opt.ts_recent = req->ts_recent; + newtp->rx_opt.ts_recent = READ_ONCE(req->ts_recent); newtp->rx_opt.ts_recent_stamp = ktime_get_seconds(); newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED; } else { @@ -601,7 +601,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, tcp_parse_options(sock_net(sk), skb, &tmp_opt, 0, NULL);

if (tmp_opt.saw_tstamp) { - tmp_opt.ts_recent = req->ts_recent; + tmp_opt.ts_recent = READ_ONCE(req->ts_recent); if (tmp_opt.rcv_tsecr) tmp_opt.rcv_tsecr -= tcp_rsk(req)->ts_off; /* We do not store true stamp, but it is not required, @@ -740,8 +740,11 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,

/* In sequence, PAWS is OK. */

+ /* TODO: We probably should defer ts_recent change once + * we take ownership of @req. + */ if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt)) - req->ts_recent = tmp_opt.rcv_tsval; + WRITE_ONCE(req->ts_recent, tmp_opt.rcv_tsval);

if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) { /* Truncate SYN, it is out of window starting diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 693a29d3f43bd..26bd039f9296f 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -876,7 +876,7 @@ static unsigned int tcp_synack_options(const struct sock *sk, if (likely(ireq->tstamp_ok)) { opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp(skb) + tcp_rsk(req)->ts_off; - opts->tsecr = req->ts_recent; + opts->tsecr = READ_ONCE(req->ts_recent); remaining -= TCPOLEN_TSTAMP_ALIGNED; } if (likely(ireq->sack_ok)) { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 0dcb06a1fe044..d9253aa764fae 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1130,7 +1130,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, - req->ts_recent, sk->sk_bound_dev_if, + READ_ONCE(req->ts_recent), sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index), ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority, READ_ONCE(tcp_rsk(req)->txhash));

From: Yuanjun Gong ruc_gongyuanjun@163.com

[ Upstream commit 4258faa130be4ea43e5e2d839467da421b8ff274 ]

goto tx_err if an unexpected result is returned by pskb_tirm() in ip6erspan_tunnel_xmit().

Fixes: 5a963eb61b7c ("ip6_gre: Add ERSPAN native tunnel support") Signed-off-by: Yuanjun Gong ruc_gongyuanjun@163.com Reviewed-by: David Ahern dsahern@kernel.org Reviewed-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv6/ip6_gre.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 216b40ccadae0..d3fba7d8dec4e 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -977,7 +977,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, goto tx_err;

if (skb->len > dev->mtu + dev->hard_header_len) { - pskb_trim(skb, dev->mtu + dev->hard_header_len); + if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) + goto tx_err; truncate = true; }

From: Zhang Shurong zhang_shurong@foxmail.com

[ Upstream commit 4e88761f5f8c7869f15a2046b1a1116f4fab4ac8 ]

This func misses checking for platform_get_irq()'s call and may passes the negative error codes to request_irq(), which takes unsigned IRQ #, causing it to fail with -EINVAL, overriding an original error code.

Fix this by stop calling request_irq() with invalid IRQ #s.

Fixes: 1630d85a8312 ("au1200fb: fix hardcoded IRQ") Signed-off-by: Zhang Shurong zhang_shurong@foxmail.com Signed-off-by: Helge Deller deller@gmx.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/video/fbdev/au1200fb.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/video/fbdev/au1200fb.c b/drivers/video/fbdev/au1200fb.c index b6b22fa4a8a01..fd3ff398d234a 100644 --- a/drivers/video/fbdev/au1200fb.c +++ b/drivers/video/fbdev/au1200fb.c @@ -1732,6 +1732,9 @@ static int au1200fb_drv_probe(struct platform_device *dev)

/* Now hook interrupt too */ irq = platform_get_irq(dev, 0); + if (irq < 0) + return irq; + ret = request_irq(irq, au1200fb_handle_irq, IRQF_SHARED, "lcd", (void *)dev); if (ret) {

From: Vitaly Rodionov vitalyr@opensource.cirrus.com

[ Upstream commit f7b069cf08816252f494d193b9ecdff172bf9aa1 ]

Generic fixup for CS35L41 amplifies should not have vendor specific chained fixup. For ThinkPad laptops with led issue, we can just add specific fixup.

Fixes: a6ac60b36dade (ALSA: hda/realtek: Fix mute led issue on thinkpad with cs35l41 s-codec) Signed-off-by: Vitaly Rodionov vitalyr@opensource.cirrus.com Link: https://lore.kernel.org/r/20230720082022.13033-1-vitalyr@opensource.cirrus.c... Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/pci/hda/patch_realtek.c | 25 +++++++++++++++---------- 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 1a8ca119ffe45..cb34a62075b13 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7220,6 +7220,7 @@ enum { ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN, ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS, ALC236_FIXUP_DELL_DUAL_CODECS, + ALC287_FIXUP_CS35L41_I2C_2_THINKPAD_ACPI, };

/* A special fixup for Lenovo C940 and Yoga Duet 7; @@ -9090,8 +9091,6 @@ static const struct hda_fixup alc269_fixups[] = { [ALC287_FIXUP_CS35L41_I2C_2] = { .type = HDA_FIXUP_FUNC, .v.func = cs35l41_fixup_i2c_two, - .chained = true, - .chain_id = ALC269_FIXUP_THINKPAD_ACPI, }, [ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED] = { .type = HDA_FIXUP_FUNC, @@ -9228,6 +9227,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, }, + [ALC287_FIXUP_CS35L41_I2C_2_THINKPAD_ACPI] = { + .type = HDA_FIXUP_FUNC, + .v.func = cs35l41_fixup_i2c_two, + .chained = true, + .chain_id = ALC269_FIXUP_THINKPAD_ACPI, + }, };

static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -9750,14 +9755,14 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x22be, "Thinkpad X1 Carbon 8th", ALC285_FIXUP_THINKPAD_HEADSET_JACK), SND_PCI_QUIRK(0x17aa, 0x22c1, "Thinkpad P1 Gen 3", ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK), SND_PCI_QUIRK(0x17aa, 0x22c2, "Thinkpad X1 Extreme Gen 3", ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK), - SND_PCI_QUIRK(0x17aa, 0x22f1, "Thinkpad", ALC287_FIXUP_CS35L41_I2C_2), - SND_PCI_QUIRK(0x17aa, 0x22f2, "Thinkpad", ALC287_FIXUP_CS35L41_I2C_2), - SND_PCI_QUIRK(0x17aa, 0x22f3, "Thinkpad", ALC287_FIXUP_CS35L41_I2C_2), - SND_PCI_QUIRK(0x17aa, 0x2316, "Thinkpad P1 Gen 6", ALC287_FIXUP_CS35L41_I2C_2), - SND_PCI_QUIRK(0x17aa, 0x2317, "Thinkpad P1 Gen 6", ALC287_FIXUP_CS35L41_I2C_2), - SND_PCI_QUIRK(0x17aa, 0x2318, "Thinkpad Z13 Gen2", ALC287_FIXUP_CS35L41_I2C_2), - SND_PCI_QUIRK(0x17aa, 0x2319, "Thinkpad Z16 Gen2", ALC287_FIXUP_CS35L41_I2C_2), - SND_PCI_QUIRK(0x17aa, 0x231a, "Thinkpad Z16 Gen2", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x17aa, 0x22f1, "Thinkpad", ALC287_FIXUP_CS35L41_I2C_2_THINKPAD_ACPI), + SND_PCI_QUIRK(0x17aa, 0x22f2, "Thinkpad", ALC287_FIXUP_CS35L41_I2C_2_THINKPAD_ACPI), + SND_PCI_QUIRK(0x17aa, 0x22f3, "Thinkpad", ALC287_FIXUP_CS35L41_I2C_2_THINKPAD_ACPI), + SND_PCI_QUIRK(0x17aa, 0x2316, "Thinkpad P1 Gen 6", ALC287_FIXUP_CS35L41_I2C_2_THINKPAD_ACPI), + SND_PCI_QUIRK(0x17aa, 0x2317, "Thinkpad P1 Gen 6", ALC287_FIXUP_CS35L41_I2C_2_THINKPAD_ACPI), + SND_PCI_QUIRK(0x17aa, 0x2318, "Thinkpad Z13 Gen2", ALC287_FIXUP_CS35L41_I2C_2_THINKPAD_ACPI), + SND_PCI_QUIRK(0x17aa, 0x2319, "Thinkpad Z16 Gen2", ALC287_FIXUP_CS35L41_I2C_2_THINKPAD_ACPI), + SND_PCI_QUIRK(0x17aa, 0x231a, "Thinkpad Z16 Gen2", ALC287_FIXUP_CS35L41_I2C_2_THINKPAD_ACPI), SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),

From: Florian Westphal fw@strlen.de

[ Upstream commit 314c82841602a111c04a7210c21dc77e0d560242 ]

Can be called via nft set element list iteration, which may acquire rcu and/or bh read lock (depends on set type).

BUG: sleeping function called from invalid context at net/netfilter/nf_tables_api.c:3353 in_atomic(): 0, irqs_disabled(): 0, non_block: 0, pid: 1232, name: nft preempt_count: 0, expected: 0 RCU nest depth: 1, expected: 0 2 locks held by nft/1232: #0: ffff8881180e3ea8 (&nft_net->commit_mutex){+.+.}-{3:3}, at: nf_tables_valid_genid #1: ffffffff83f5f540 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire Call Trace: nft_chain_validate nft_lookup_validate_setelem nft_pipapo_walk nft_lookup_validate nft_chain_validate nft_immediate_validate nft_chain_validate nf_tables_validate nf_tables_abort

No choice but to move it to nf_tables_validate().

Fixes: 81ea01066741 ("netfilter: nf_tables: add rescheduling points during loop detection walks") Signed-off-by: Florian Westphal fw@strlen.de Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nf_tables_api.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 58f14e4ef63d4..0bb1cc7ed5e99 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3500,8 +3500,6 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) if (err < 0) return err; } - - cond_resched(); }

return 0; @@ -3525,6 +3523,8 @@ static int nft_table_validate(struct net *net, const struct nft_table *table) err = nft_chain_validate(&ctx, chain); if (err < 0) return err; + + cond_resched(); }

return 0;

From: Pablo Neira Ayuso pablo@netfilter.org

[ Upstream commit 751d460ccff3137212f47d876221534bf0490996 ]

Skip bound chain from netns release path, the rule that owns this chain releases these objects.

Fixes: d0e2c7de92c7 ("netfilter: nf_tables: add NFT_CHAIN_BINDING") Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Florian Westphal fw@strlen.de Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nf_tables_api.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 0bb1cc7ed5e99..f621c5e48747b 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -10398,6 +10398,9 @@ static void __nft_release_table(struct net *net, struct nft_table *table) ctx.family = table->family; ctx.table = table; list_for_each_entry(chain, &table->chains, list) { + if (nft_chain_is_bound(chain)) + continue; + ctx.chain = chain; list_for_each_entry_safe(rule, nr, &chain->rules, list) { list_del(&rule->list);

From: Pauli Virtanen pav@iki.fi

[ Upstream commit 195ef75e19287b4bc413da3e3e3722b030ac881e ]

hci_update_accept_list_sync iterates over hdev->pend_le_conns and hdev->pend_le_reports, and waits for controller events in the loop body, without holding hdev lock.

Meanwhile, these lists and the items may be modified e.g. by le_scan_cleanup. This can invalidate the list cursor or any other item in the list, resulting to invalid behavior (eg use-after-free).

Use RCU for the hci_conn_params action lists. Since the loop bodies in hci_sync block and we cannot use RCU or hdev->lock for the whole loop, copy list items first and then iterate on the copy. Only the flags field is written from elsewhere, so READ_ONCE/WRITE_ONCE should guarantee we read valid values.

Free params everywhere with hci_conn_params_free so the cleanup is guaranteed to be done properly.

This fixes the following, which can be triggered e.g. by BlueZ new mgmt-tester case "Add + Remove Device Nowait - Success", or by changing hci_le_set_cig_params to always return false, and running iso-tester:

================================================================== BUG: KASAN: slab-use-after-free in hci_update_passive_scan_sync (net/bluetooth/hci_sync.c:2536 net/bluetooth/hci_sync.c:2723 net/bluetooth/hci_sync.c:2841) Read of size 8 at addr ffff888001265018 by task kworker/u3:0/32

Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-1.fc38 04/01/2014 Workqueue: hci0 hci_cmd_sync_work Call Trace: <TASK> dump_stack_lvl (./arch/x86/include/asm/irqflags.h:134 lib/dump_stack.c:107) print_report (mm/kasan/report.c:320 mm/kasan/report.c:430) ? __virt_addr_valid (./include/linux/mmzone.h:1915 ./include/linux/mmzone.h:2011 arch/x86/mm/physaddr.c:65) ? hci_update_passive_scan_sync (net/bluetooth/hci_sync.c:2536 net/bluetooth/hci_sync.c:2723 net/bluetooth/hci_sync.c:2841) kasan_report (mm/kasan/report.c:538) ? hci_update_passive_scan_sync (net/bluetooth/hci_sync.c:2536 net/bluetooth/hci_sync.c:2723 net/bluetooth/hci_sync.c:2841) hci_update_passive_scan_sync (net/bluetooth/hci_sync.c:2536 net/bluetooth/hci_sync.c:2723 net/bluetooth/hci_sync.c:2841) ? __pfx_hci_update_passive_scan_sync (net/bluetooth/hci_sync.c:2780) ? mutex_lock (kernel/locking/mutex.c:282) ? __pfx_mutex_lock (kernel/locking/mutex.c:282) ? __pfx_mutex_unlock (kernel/locking/mutex.c:538) ? __pfx_update_passive_scan_sync (net/bluetooth/hci_sync.c:2861) hci_cmd_sync_work (net/bluetooth/hci_sync.c:306) process_one_work (./arch/x86/include/asm/preempt.h:27 kernel/workqueue.c:2399) worker_thread (./include/linux/list.h:292 kernel/workqueue.c:2538) ? __pfx_worker_thread (kernel/workqueue.c:2480) kthread (kernel/kthread.c:376) ? __pfx_kthread (kernel/kthread.c:331) ret_from_fork (arch/x86/entry/entry_64.S:314) </TASK>

Allocated by task 31: kasan_save_stack (mm/kasan/common.c:46) kasan_set_track (mm/kasan/common.c:52) __kasan_kmalloc (mm/kasan/common.c:374 mm/kasan/common.c:383) hci_conn_params_add (./include/linux/slab.h:580 ./include/linux/slab.h:720 net/bluetooth/hci_core.c:2277) hci_connect_le_scan (net/bluetooth/hci_conn.c:1419 net/bluetooth/hci_conn.c:1589) hci_connect_cis (net/bluetooth/hci_conn.c:2266) iso_connect_cis (net/bluetooth/iso.c:390) iso_sock_connect (net/bluetooth/iso.c:899) __sys_connect (net/socket.c:2003 net/socket.c:2020) __x64_sys_connect (net/socket.c:2027) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120)

Freed by task 15: kasan_save_stack (mm/kasan/common.c:46) kasan_set_track (mm/kasan/common.c:52) kasan_save_free_info (mm/kasan/generic.c:523) __kasan_slab_free (mm/kasan/common.c:238 mm/kasan/common.c:200 mm/kasan/common.c:244) __kmem_cache_free (mm/slub.c:1807 mm/slub.c:3787 mm/slub.c:3800) hci_conn_params_del (net/bluetooth/hci_core.c:2323) le_scan_cleanup (net/bluetooth/hci_conn.c:202) process_one_work (./arch/x86/include/asm/preempt.h:27 kernel/workqueue.c:2399) worker_thread (./include/linux/list.h:292 kernel/workqueue.c:2538) kthread (kernel/kthread.c:376) ret_from_fork (arch/x86/entry/entry_64.S:314) ==================================================================

Fixes: e8907f76544f ("Bluetooth: hci_sync: Make use of hci_cmd_sync_queue set 3") Signed-off-by: Pauli Virtanen pav@iki.fi Signed-off-by: Luiz Augusto von Dentz luiz.von.dentz@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/bluetooth/hci_core.h | 5 ++ net/bluetooth/hci_conn.c | 10 +-- net/bluetooth/hci_core.c | 38 ++++++++-- net/bluetooth/hci_event.c | 12 ++-- net/bluetooth/hci_sync.c | 117 ++++++++++++++++++++++++++++--- net/bluetooth/mgmt.c | 26 +++---- 6 files changed, 164 insertions(+), 44 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 84c5ce57eab69..ddbcbf9ccb2ce 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -807,6 +807,7 @@ struct hci_conn_params {

struct hci_conn *conn; bool explicit_connect; + /* Accessed without hdev->lock: */ hci_conn_flags_t flags; u8 privacy_mode; }; @@ -1536,7 +1537,11 @@ struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type); void hci_conn_params_del(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type); void hci_conn_params_clear_disabled(struct hci_dev *hdev); +void hci_conn_params_free(struct hci_conn_params *param);

+void hci_pend_le_list_del_init(struct hci_conn_params *param); +void hci_pend_le_list_add(struct hci_conn_params *param, + struct list_head *list); struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list, bdaddr_t *addr, u8 addr_type); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index fef09d2121384..61059571c8779 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -117,7 +117,7 @@ static void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) */ params->explicit_connect = false;

- list_del_init(&params->action); + hci_pend_le_list_del_init(params);

switch (params->auto_connect) { case HCI_AUTO_CONN_EXPLICIT: @@ -126,10 +126,10 @@ static void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) return; case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: - list_add(&params->action, &hdev->pend_le_conns); + hci_pend_le_list_add(params, &hdev->pend_le_conns); break; case HCI_AUTO_CONN_REPORT: - list_add(&params->action, &hdev->pend_le_reports); + hci_pend_le_list_add(params, &hdev->pend_le_reports); break; default: break; @@ -1398,8 +1398,8 @@ static int hci_explicit_conn_params_set(struct hci_dev *hdev, if (params->auto_connect == HCI_AUTO_CONN_DISABLED || params->auto_connect == HCI_AUTO_CONN_REPORT || params->auto_connect == HCI_AUTO_CONN_EXPLICIT) { - list_del_init(&params->action); - list_add(&params->action, &hdev->pend_le_conns); + hci_pend_le_list_del_init(params); + hci_pend_le_list_add(params, &hdev->pend_le_conns); }

params->explicit_connect = true; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index ca42129f8f91a..be0e6865b340f 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2249,21 +2249,45 @@ struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev, return NULL; }

-/* This function requires the caller holds hdev->lock */ +/* This function requires the caller holds hdev->lock or rcu_read_lock */ struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list, bdaddr_t *addr, u8 addr_type) { struct hci_conn_params *param;

- list_for_each_entry(param, list, action) { + rcu_read_lock(); + + list_for_each_entry_rcu(param, list, action) { if (bacmp(&param->addr, addr) == 0 && - param->addr_type == addr_type) + param->addr_type == addr_type) { + rcu_read_unlock(); return param; + } }

+ rcu_read_unlock(); + return NULL; }

+/* This function requires the caller holds hdev->lock */ +void hci_pend_le_list_del_init(struct hci_conn_params *param) +{ + if (list_empty(&param->action)) + return; + + list_del_rcu(&param->action); + synchronize_rcu(); + INIT_LIST_HEAD(&param->action); +} + +/* This function requires the caller holds hdev->lock */ +void hci_pend_le_list_add(struct hci_conn_params *param, + struct list_head *list) +{ + list_add_rcu(&param->action, list); +} + /* This function requires the caller holds hdev->lock */ struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) @@ -2297,14 +2321,15 @@ struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, return params; }

-static void hci_conn_params_free(struct hci_conn_params *params) +void hci_conn_params_free(struct hci_conn_params *params) { + hci_pend_le_list_del_init(params); + if (params->conn) { hci_conn_drop(params->conn); hci_conn_put(params->conn); }

- list_del(&params->action); list_del(&params->list); kfree(params); } @@ -2342,8 +2367,7 @@ void hci_conn_params_clear_disabled(struct hci_dev *hdev) continue; }

- list_del(&params->list); - kfree(params); + hci_conn_params_free(params); }

BT_DBG("All LE disabled connection parameters were removed"); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index b272cc1f36481..ec9b0612f2761 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1558,7 +1558,7 @@ static u8 hci_cc_le_set_privacy_mode(struct hci_dev *hdev, void *data,

params = hci_conn_params_lookup(hdev, &cp->bdaddr, cp->bdaddr_type); if (params) - params->privacy_mode = cp->mode; + WRITE_ONCE(params->privacy_mode, cp->mode);

hci_dev_unlock(hdev);

@@ -2809,8 +2809,8 @@ static void hci_cs_disconnect(struct hci_dev *hdev, u8 status)

case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: - list_del_init(&params->action); - list_add(&params->action, &hdev->pend_le_conns); + hci_pend_le_list_del_init(params); + hci_pend_le_list_add(params, &hdev->pend_le_conns); break;

default: @@ -3428,8 +3428,8 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, void *data,

case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: - list_del_init(&params->action); - list_add(&params->action, &hdev->pend_le_conns); + hci_pend_le_list_del_init(params); + hci_pend_le_list_add(params, &hdev->pend_le_conns); hci_update_passive_scan(hdev); break;

@@ -5952,7 +5952,7 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, params = hci_pend_le_action_lookup(&hdev->pend_le_conns, &conn->dst, conn->dst_type); if (params) { - list_del_init(&params->action); + hci_pend_le_list_del_init(params); if (params->conn) { hci_conn_drop(params->conn); hci_conn_put(params->conn); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 37131a36700a1..2ae038dfc39f7 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -2139,15 +2139,23 @@ static int hci_le_del_accept_list_sync(struct hci_dev *hdev, return 0; }

+struct conn_params { + bdaddr_t addr; + u8 addr_type; + hci_conn_flags_t flags; + u8 privacy_mode; +}; + /* Adds connection to resolve list if needed. * Setting params to NULL programs local hdev->irk */ static int hci_le_add_resolve_list_sync(struct hci_dev *hdev, - struct hci_conn_params *params) + struct conn_params *params) { struct hci_cp_le_add_to_resolv_list cp; struct smp_irk *irk; struct bdaddr_list_with_irk *entry; + struct hci_conn_params *p;

if (!use_ll_privacy(hdev)) return 0; @@ -2182,6 +2190,16 @@ static int hci_le_add_resolve_list_sync(struct hci_dev *hdev, /* Default privacy mode is always Network */ params->privacy_mode = HCI_NETWORK_PRIVACY;

+ rcu_read_lock(); + p = hci_pend_le_action_lookup(&hdev->pend_le_conns, + &params->addr, params->addr_type); + if (!p) + p = hci_pend_le_action_lookup(&hdev->pend_le_reports, + &params->addr, params->addr_type); + if (p) + WRITE_ONCE(p->privacy_mode, HCI_NETWORK_PRIVACY); + rcu_read_unlock(); + done: if (hci_dev_test_flag(hdev, HCI_PRIVACY)) memcpy(cp.local_irk, hdev->irk, 16); @@ -2194,7 +2212,7 @@ static int hci_le_add_resolve_list_sync(struct hci_dev *hdev,

/* Set Device Privacy Mode. */ static int hci_le_set_privacy_mode_sync(struct hci_dev *hdev, - struct hci_conn_params *params) + struct conn_params *params) { struct hci_cp_le_set_privacy_mode cp; struct smp_irk *irk; @@ -2219,6 +2237,8 @@ static int hci_le_set_privacy_mode_sync(struct hci_dev *hdev, bacpy(&cp.bdaddr, &irk->bdaddr); cp.mode = HCI_DEVICE_PRIVACY;

+ /* Note: params->privacy_mode is not updated since it is a copy */ + return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_PRIVACY_MODE, sizeof(cp), &cp, HCI_CMD_TIMEOUT); } @@ -2228,7 +2248,7 @@ static int hci_le_set_privacy_mode_sync(struct hci_dev *hdev, * properly set the privacy mode. */ static int hci_le_add_accept_list_sync(struct hci_dev *hdev, - struct hci_conn_params *params, + struct conn_params *params, u8 *num_entries) { struct hci_cp_le_add_to_accept_list cp; @@ -2426,6 +2446,52 @@ struct sk_buff *hci_read_local_oob_data_sync(struct hci_dev *hdev, return __hci_cmd_sync_sk(hdev, opcode, 0, NULL, 0, HCI_CMD_TIMEOUT, sk); }

+static struct conn_params *conn_params_copy(struct list_head *list, size_t *n) +{ + struct hci_conn_params *params; + struct conn_params *p; + size_t i; + + rcu_read_lock(); + + i = 0; + list_for_each_entry_rcu(params, list, action) + ++i; + *n = i; + + rcu_read_unlock(); + + p = kvcalloc(*n, sizeof(struct conn_params), GFP_KERNEL); + if (!p) + return NULL; + + rcu_read_lock(); + + i = 0; + list_for_each_entry_rcu(params, list, action) { + /* Racing adds are handled in next scan update */ + if (i >= *n) + break; + + /* No hdev->lock, but: addr, addr_type are immutable. + * privacy_mode is only written by us or in + * hci_cc_le_set_privacy_mode that we wait for. + * We should be idempotent so MGMT updating flags + * while we are processing is OK. + */ + bacpy(&p[i].addr, &params->addr); + p[i].addr_type = params->addr_type; + p[i].flags = READ_ONCE(params->flags); + p[i].privacy_mode = READ_ONCE(params->privacy_mode); + ++i; + } + + rcu_read_unlock(); + + *n = i; + return p; +} + /* Device must not be scanning when updating the accept list. * * Update is done using the following sequence: @@ -2445,11 +2511,12 @@ struct sk_buff *hci_read_local_oob_data_sync(struct hci_dev *hdev, */ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) { - struct hci_conn_params *params; + struct conn_params *params; struct bdaddr_list *b, *t; u8 num_entries = 0; bool pend_conn, pend_report; u8 filter_policy; + size_t i, n; int err;

/* Pause advertising if resolving list can be used as controllers @@ -2483,6 +2550,7 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) if (hci_conn_hash_lookup_le(hdev, &b->bdaddr, b->bdaddr_type)) continue;

+ /* Pointers not dereferenced, no locks needed */ pend_conn = hci_pend_le_action_lookup(&hdev->pend_le_conns, &b->bdaddr, b->bdaddr_type); @@ -2511,23 +2579,50 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) * available accept list entries in the controller, then * just abort and return filer policy value to not use the * accept list. + * + * The list and params may be mutated while we wait for events, + * so make a copy and iterate it. */ - list_for_each_entry(params, &hdev->pend_le_conns, action) { - err = hci_le_add_accept_list_sync(hdev, params, &num_entries); - if (err) + + params = conn_params_copy(&hdev->pend_le_conns, &n); + if (!params) { + err = -ENOMEM; + goto done; + } + + for (i = 0; i < n; ++i) { + err = hci_le_add_accept_list_sync(hdev, &params[i], + &num_entries); + if (err) { + kvfree(params); goto done; + } }

+ kvfree(params); + /* After adding all new pending connections, walk through * the list of pending reports and also add these to the * accept list if there is still space. Abort if space runs out. */ - list_for_each_entry(params, &hdev->pend_le_reports, action) { - err = hci_le_add_accept_list_sync(hdev, params, &num_entries); - if (err) + + params = conn_params_copy(&hdev->pend_le_reports, &n); + if (!params) { + err = -ENOMEM; + goto done; + } + + for (i = 0; i < n; ++i) { + err = hci_le_add_accept_list_sync(hdev, &params[i], + &num_entries); + if (err) { + kvfree(params); goto done; + } }

+ kvfree(params); + /* Use the allowlist unless the following conditions are all true: * - We are not currently suspending * - There are 1 or more ADV monitors registered and it's not offloaded @@ -4778,12 +4873,12 @@ static void hci_pend_le_actions_clear(struct hci_dev *hdev) struct hci_conn_params *p;

list_for_each_entry(p, &hdev->le_conn_params, list) { + hci_pend_le_list_del_init(p); if (p->conn) { hci_conn_drop(p->conn); hci_conn_put(p->conn); p->conn = NULL; } - list_del_init(&p->action); }

BT_DBG("All LE pending actions cleared"); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 815f2abe918ef..89c94f3e96bc3 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -1297,15 +1297,15 @@ static void restart_le_actions(struct hci_dev *hdev) /* Needed for AUTO_OFF case where might not "really" * have been powered off. */ - list_del_init(&p->action); + hci_pend_le_list_del_init(p);

switch (p->auto_connect) { case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: - list_add(&p->action, &hdev->pend_le_conns); + hci_pend_le_list_add(p, &hdev->pend_le_conns); break; case HCI_AUTO_CONN_REPORT: - list_add(&p->action, &hdev->pend_le_reports); + hci_pend_le_list_add(p, &hdev->pend_le_reports); break; default: break; @@ -5161,7 +5161,7 @@ static int set_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, goto unlock; }

- params->flags = current_flags; + WRITE_ONCE(params->flags, current_flags); status = MGMT_STATUS_SUCCESS;

/* Update passive scan if HCI_CONN_FLAG_DEVICE_PRIVACY @@ -7573,7 +7573,7 @@ static int hci_conn_params_set(struct hci_dev *hdev, bdaddr_t *addr, if (params->auto_connect == auto_connect) return 0;

- list_del_init(&params->action); + hci_pend_le_list_del_init(params);

switch (auto_connect) { case HCI_AUTO_CONN_DISABLED: @@ -7582,18 +7582,18 @@ static int hci_conn_params_set(struct hci_dev *hdev, bdaddr_t *addr, * connect to device, keep connecting. */ if (params->explicit_connect) - list_add(&params->action, &hdev->pend_le_conns); + hci_pend_le_list_add(params, &hdev->pend_le_conns); break; case HCI_AUTO_CONN_REPORT: if (params->explicit_connect) - list_add(&params->action, &hdev->pend_le_conns); + hci_pend_le_list_add(params, &hdev->pend_le_conns); else - list_add(&params->action, &hdev->pend_le_reports); + hci_pend_le_list_add(params, &hdev->pend_le_reports); break; case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: if (!is_connected(hdev, addr, addr_type)) - list_add(&params->action, &hdev->pend_le_conns); + hci_pend_le_list_add(params, &hdev->pend_le_conns); break; }

@@ -7816,9 +7816,7 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, goto unlock; }

- list_del(&params->action); - list_del(&params->list); - kfree(params); + hci_conn_params_free(params);

device_removed(sk, hdev, &cp->addr.bdaddr, cp->addr.type); } else { @@ -7849,9 +7847,7 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, p->auto_connect = HCI_AUTO_CONN_EXPLICIT; continue; } - list_del(&p->action); - list_del(&p->list); - kfree(p); + hci_conn_params_free(p); }

bt_dev_dbg(hdev, "All LE connection parameters were removed");

From: Pauli Virtanen pav@iki.fi

[ Upstream commit d40ae85ee62e3666f45bc61864b22121346f88ef ]

sk->sk_state indicates whether iso_pi(sk)->conn is valid. Operations that check/update sk_state and access conn should hold lock_sock, otherwise they can race.

The order of taking locks is hci_dev_lock > lock_sock > iso_conn_lock, which is how it is in connect/disconnect_cfm -> iso_conn_del -> iso_chan_del.

Fix locking in iso_connect_cis/bis and sendmsg/recvmsg to take lock_sock around updating sk_state and conn.

iso_conn_del must not occur during iso_connect_cis/bis, as it frees the iso_conn. Hold hdev->lock longer to prevent that.

This should not reintroduce the issue fixed in commit 241f51931c35 ("Bluetooth: ISO: Avoid circular locking dependency"), since the we acquire locks in order. We retain the fix in iso_sock_connect to release lock_sock before iso_connect_* acquires hdev->lock.

Similarly for commit 6a5ad251b7cd ("Bluetooth: ISO: Fix possible circular locking dependency"). We retain the fix in iso_conn_ready to not acquire iso_conn_lock before lock_sock.

iso_conn_add shall return iso_conn with valid hcon. Make it so also when reusing an old CIS connection waiting for disconnect timeout (see __iso_sock_close where conn->hcon is set to NULL).

Trace with iso_conn_del after iso_chan_add in iso_connect_cis: =============================================================== iso_sock_create:771: sock 00000000be9b69b7 iso_sock_init:693: sk 000000004dff667e iso_sock_bind:827: sk 000000004dff667e 70:1a:b8:98:ff:a2 type 1 iso_sock_setsockopt:1289: sk 000000004dff667e iso_sock_setsockopt:1289: sk 000000004dff667e iso_sock_setsockopt:1289: sk 000000004dff667e iso_sock_connect:875: sk 000000004dff667e iso_connect_cis:353: 70:1a:b8:98:ff:a2 -> 28:3d:c2:4a:7e:da hci_get_route:1199: 70:1a:b8:98:ff:a2 -> 28:3d:c2:4a:7e:da hci_conn_add:1005: hci0 dst 28:3d:c2:4a:7e:da iso_conn_add:140: hcon 000000007b65d182 conn 00000000daf8625e __iso_chan_add:214: conn 00000000daf8625e iso_connect_cfm:1700: hcon 000000007b65d182 bdaddr 28:3d:c2:4a:7e:da status 12 iso_conn_del:187: hcon 000000007b65d182 conn 00000000daf8625e, err 16 iso_sock_clear_timer:117: sock 000000004dff667e state 3 <Note: sk_state is BT_BOUND (3), so iso_connect_cis is still running at this point> iso_chan_del:153: sk 000000004dff667e, conn 00000000daf8625e, err 16 hci_conn_del:1151: hci0 hcon 000000007b65d182 handle 65535 hci_conn_unlink:1102: hci0: hcon 000000007b65d182 hci_chan_list_flush:2780: hcon 000000007b65d182 iso_sock_getsockopt:1376: sk 000000004dff667e iso_sock_getname:1070: sock 00000000be9b69b7, sk 000000004dff667e iso_sock_getname:1070: sock 00000000be9b69b7, sk 000000004dff667e iso_sock_getsockopt:1376: sk 000000004dff667e iso_sock_getname:1070: sock 00000000be9b69b7, sk 000000004dff667e iso_sock_getname:1070: sock 00000000be9b69b7, sk 000000004dff667e iso_sock_shutdown:1434: sock 00000000be9b69b7, sk 000000004dff667e, how 1 __iso_sock_close:632: sk 000000004dff667e state 5 socket 00000000be9b69b7 <Note: sk_state is BT_CONNECT (5), even though iso_chan_del sets BT_CLOSED (6). Only iso_connect_cis sets it to BT_CONNECT, so it must be that iso_chan_del occurred between iso_chan_add and end of iso_connect_cis.> BUG: kernel NULL pointer dereference, address: 0000000000000000 PGD 8000000006467067 P4D 8000000006467067 PUD 3f5f067 PMD 0 Oops: 0000 [#1] PREEMPT SMP PTI Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-1.fc38 04/01/2014 RIP: 0010:__iso_sock_close (net/bluetooth/iso.c:664) bluetooth ===============================================================

Trace with iso_conn_del before iso_chan_add in iso_connect_cis: =============================================================== iso_connect_cis:356: 70:1a:b8:98:ff:a2 -> 28:3d:c2:4a:7e:da ... iso_conn_add:140: hcon 0000000093bc551f conn 00000000768ae504 hci_dev_put:1487: hci0 orig refcnt 21 hci_event_packet:7607: hci0: event 0x0e hci_cmd_complete_evt:4231: hci0: opcode 0x2062 hci_cc_le_set_cig_params:3846: hci0: status 0x07 hci_sent_cmd_data:3107: hci0 opcode 0x2062 iso_connect_cfm:1703: hcon 0000000093bc551f bdaddr 28:3d:c2:4a:7e:da status 7 iso_conn_del:187: hcon 0000000093bc551f conn 00000000768ae504, err 12 hci_conn_del:1151: hci0 hcon 0000000093bc551f handle 65535 hci_conn_unlink:1102: hci0: hcon 0000000093bc551f hci_chan_list_flush:2780: hcon 0000000093bc551f __iso_chan_add:214: conn 00000000768ae504 <Note: this conn was already freed in iso_conn_del above> iso_sock_clear_timer:117: sock 0000000098323f95 state 3 general protection fault, probably for non-canonical address 0x30b29c630930aec8: 0000 [#1] PREEMPT SMP PTI CPU: 1 PID: 1920 Comm: bluetoothd Tainted: G E 6.3.0-rc7+ #4 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-1.fc38 04/01/2014 RIP: 0010:detach_if_pending+0x28/0xd0 Code: 90 90 0f 1f 44 00 00 48 8b 47 08 48 85 c0 0f 84 ad 00 00 00 55 89 d5 53 48 83 3f 00 48 89 fb 74 7d 66 90 48 8b 03 48 8b 53 08 <> RSP: 0018:ffffb90841a67d08 EFLAGS: 00010007 RAX: 0000000000000000 RBX: ffff9141bd5061b8 RCX: 0000000000000000 RDX: 30b29c630930aec8 RSI: ffff9141fdd21e80 RDI: ffff9141bd5061b8 RBP: 0000000000000001 R08: 0000000000000000 R09: ffffb90841a67b88 R10: 0000000000000003 R11: ffffffff8613f558 R12: ffff9141fdd21e80 R13: 0000000000000000 R14: ffff9141b5976010 R15: ffff914185755338 FS: 00007f45768bd840(0000) GS:ffff9141fdd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000619000424074 CR3: 0000000009f5e005 CR4: 0000000000170ee0 Call Trace: <TASK> timer_delete+0x48/0x80 try_to_grab_pending+0xdf/0x170 __cancel_work+0x37/0xb0 iso_connect_cis+0x141/0x400 [bluetooth] ===============================================================

Trace with NULL conn->hcon in state BT_CONNECT: =============================================================== __iso_sock_close:619: sk 00000000f7c71fc5 state 1 socket 00000000d90c5fe5 ... __iso_sock_close:619: sk 00000000f7c71fc5 state 8 socket 00000000d90c5fe5 iso_chan_del:153: sk 00000000f7c71fc5, conn 0000000022c03a7e, err 104 ... iso_sock_connect:862: sk 00000000129b56c3 iso_connect_cis:348: 70:1a:b8:98:ff:a2 -> 28:3d:c2:4a:7d:2a hci_get_route:1199: 70:1a:b8:98:ff:a2 -> 28:3d:c2:4a:7d:2a hci_dev_hold:1495: hci0 orig refcnt 19 __iso_chan_add:214: conn 0000000022c03a7e <Note: reusing old conn> iso_sock_clear_timer:117: sock 00000000129b56c3 state 3 ... iso_sock_ready:1485: sk 00000000129b56c3 ... iso_sock_sendmsg:1077: sock 00000000e5013966, sk 00000000129b56c3 BUG: kernel NULL pointer dereference, address: 00000000000006a8 PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 1 PID: 1403 Comm: wireplumber Tainted: G E 6.3.0-rc7+ #4 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-1.fc38 04/01/2014 RIP: 0010:iso_sock_sendmsg+0x63/0x2a0 [bluetooth] ===============================================================

Fixes: 241f51931c35 ("Bluetooth: ISO: Avoid circular locking dependency") Fixes: 6a5ad251b7cd ("Bluetooth: ISO: Fix possible circular locking dependency") Signed-off-by: Pauli Virtanen pav@iki.fi Signed-off-by: Luiz Augusto von Dentz luiz.von.dentz@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/bluetooth/iso.c | 53 ++++++++++++++++++++++++++------------------- 1 file changed, 31 insertions(+), 22 deletions(-)

diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index cb959e8eac185..699e4f400df29 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -116,8 +116,11 @@ static struct iso_conn *iso_conn_add(struct hci_conn *hcon) { struct iso_conn *conn = hcon->iso_data;

- if (conn) + if (conn) { + if (!conn->hcon) + conn->hcon = hcon; return conn; + }

conn = kzalloc(sizeof(*conn), GFP_KERNEL); if (!conn) @@ -285,14 +288,13 @@ static int iso_connect_bis(struct sock *sk) goto unlock; }

- hci_dev_unlock(hdev); - hci_dev_put(hdev); + lock_sock(sk);

err = iso_chan_add(conn, sk, NULL); - if (err) - return err; - - lock_sock(sk); + if (err) { + release_sock(sk); + goto unlock; + }

/* Update source addr of the socket */ bacpy(&iso_pi(sk)->src, &hcon->src); @@ -306,7 +308,6 @@ static int iso_connect_bis(struct sock *sk) }

release_sock(sk); - return err;

unlock: hci_dev_unlock(hdev); @@ -367,14 +368,13 @@ static int iso_connect_cis(struct sock *sk) goto unlock; }

- hci_dev_unlock(hdev); - hci_dev_put(hdev); + lock_sock(sk);

err = iso_chan_add(conn, sk, NULL); - if (err) - return err; - - lock_sock(sk); + if (err) { + release_sock(sk); + goto unlock; + }

/* Update source addr of the socket */ bacpy(&iso_pi(sk)->src, &hcon->src); @@ -391,7 +391,6 @@ static int iso_connect_cis(struct sock *sk) }

release_sock(sk); - return err;

unlock: hci_dev_unlock(hdev); @@ -1036,8 +1035,8 @@ static int iso_sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; - struct iso_conn *conn = iso_pi(sk)->conn; struct sk_buff *skb, **frag; + size_t mtu; int err;

BT_DBG("sock %p, sk %p", sock, sk); @@ -1049,11 +1048,18 @@ static int iso_sock_sendmsg(struct socket *sock, struct msghdr *msg, if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP;

- if (sk->sk_state != BT_CONNECTED) + lock_sock(sk); + + if (sk->sk_state != BT_CONNECTED) { + release_sock(sk); return -ENOTCONN; + } + + mtu = iso_pi(sk)->conn->hcon->hdev->iso_mtu; + + release_sock(sk);

- skb = bt_skb_sendmsg(sk, msg, len, conn->hcon->hdev->iso_mtu, - HCI_ISO_DATA_HDR_SIZE, 0); + skb = bt_skb_sendmsg(sk, msg, len, mtu, HCI_ISO_DATA_HDR_SIZE, 0); if (IS_ERR(skb)) return PTR_ERR(skb);

@@ -1066,8 +1072,7 @@ static int iso_sock_sendmsg(struct socket *sock, struct msghdr *msg, while (len) { struct sk_buff *tmp;

- tmp = bt_skb_sendmsg(sk, msg, len, conn->hcon->hdev->iso_mtu, - 0, 0); + tmp = bt_skb_sendmsg(sk, msg, len, mtu, 0, 0); if (IS_ERR(tmp)) { kfree_skb(skb); return PTR_ERR(tmp); @@ -1122,15 +1127,19 @@ static int iso_sock_recvmsg(struct socket *sock, struct msghdr *msg, BT_DBG("sk %p", sk);

if (test_and_clear_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { + lock_sock(sk); switch (sk->sk_state) { case BT_CONNECT2: - lock_sock(sk); iso_conn_defer_accept(pi->conn->hcon); sk->sk_state = BT_CONFIG; release_sock(sk); return 0; case BT_CONNECT: + release_sock(sk); return iso_connect_cis(sk); + default: + release_sock(sk); + break; } }

From: Eric Dumazet edumazet@google.com

[ Upstream commit 348b81b68b13ebd489a3e6a46aa1c384c731c919 ]

do_tcp_getsockopt() reads tp->tcp_tx_delay while another cpu might change its value.

Fixes: a842fe1425cb ("tcp: add optional per socket transmit delay") Signed-off-by: Eric Dumazet edumazet@google.com Link: https://lore.kernel.org/r/20230719212857.3943972-2-edumazet@google.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/tcp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0bd0be3c63d22..5e4bc80dc0ae5 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3780,7 +3780,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_TX_DELAY: if (val) tcp_enable_tx_delay(); - tp->tcp_tx_delay = val; + WRITE_ONCE(tp->tcp_tx_delay, val); break; default: err = -ENOPROTOOPT; @@ -4256,7 +4256,7 @@ int do_tcp_getsockopt(struct sock *sk, int level, break;

case TCP_TX_DELAY: - val = tp->tcp_tx_delay; + val = READ_ONCE(tp->tcp_tx_delay); break;

case TCP_TIMESTAMP:

From: Eric Dumazet edumazet@google.com

[ Upstream commit 4164245c76ff906c9086758e1c3f87082a7f5ef5 ]

do_tcp_getsockopt() reads tp->keepalive_time while another cpu might change its value.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet edumazet@google.com Link: https://lore.kernel.org/r/20230719212857.3943972-4-edumazet@google.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/tcp.h | 7 +++++-- net/ipv4/tcp.c | 3 ++- 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h index 5eedd476a38d7..397c248102415 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1519,9 +1519,12 @@ static inline int keepalive_intvl_when(const struct tcp_sock *tp) static inline int keepalive_time_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); + int val;

- return tp->keepalive_time ? : - READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time); + /* Paired with WRITE_ONCE() in tcp_sock_set_keepidle_locked() */ + val = READ_ONCE(tp->keepalive_time); + + return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time); }

static inline int keepalive_probes(const struct tcp_sock *tp) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3edf7a1c5cbd2..c0d7b226bca1a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3418,7 +3418,8 @@ int tcp_sock_set_keepidle_locked(struct sock *sk, int val) if (val < 1 || val > MAX_TCP_KEEPIDLE) return -EINVAL;

- tp->keepalive_time = val * HZ; + /* Paired with WRITE_ONCE() in keepalive_time_when() */ + WRITE_ONCE(tp->keepalive_time, val * HZ); if (sock_flag(sk, SOCK_KEEPOPEN) && !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { u32 elapsed = keepalive_time_elapsed(tp);

From: Eric Dumazet edumazet@google.com

[ Upstream commit 6e5e1de616bf5f3df1769abc9292191dfad9110a ]

do_tcp_getsockopt() reads tp->keepalive_probes while another cpu might change its value.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet edumazet@google.com Link: https://lore.kernel.org/r/20230719212857.3943972-6-edumazet@google.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/tcp.h | 9 +++++++-- net/ipv4/tcp.c | 5 +++-- 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h index f39c44cbdfe62..9733d8e4f10af 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1535,9 +1535,14 @@ static inline int keepalive_time_when(const struct tcp_sock *tp) static inline int keepalive_probes(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); + int val; + + /* Paired with WRITE_ONCE() in tcp_sock_set_keepcnt() + * and do_tcp_setsockopt(). + */ + val = READ_ONCE(tp->keepalive_probes);

- return tp->keepalive_probes ? : - READ_ONCE(net->ipv4.sysctl_tcp_keepalive_probes); + return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_probes); }

static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index d19cfeb78392d..7d75928ea0f9c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3463,7 +3463,8 @@ int tcp_sock_set_keepcnt(struct sock *sk, int val) return -EINVAL;

lock_sock(sk); - tcp_sk(sk)->keepalive_probes = val; + /* Paired with READ_ONCE() in keepalive_probes() */ + WRITE_ONCE(tcp_sk(sk)->keepalive_probes, val); release_sock(sk); return 0; } @@ -3671,7 +3672,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (val < 1 || val > MAX_TCP_KEEPCNT) err = -EINVAL; else - tp->keepalive_probes = val; + WRITE_ONCE(tp->keepalive_probes, val); break; case TCP_SYNCNT: if (val < 1 || val > MAX_TCP_SYNCNT)

From: Eric Dumazet edumazet@google.com

[ Upstream commit 9df5335ca974e688389c875546e5819778a80d59 ]

do_tcp_getsockopt() reads tp->linger2 while another cpu might change its value.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet edumazet@google.com Link: https://lore.kernel.org/r/20230719212857.3943972-8-edumazet@google.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/tcp.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index ffa9717293358..363535b6ece83 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3691,11 +3691,11 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,

case TCP_LINGER2: if (val < 0) - tp->linger2 = -1; + WRITE_ONCE(tp->linger2, -1); else if (val > TCP_FIN_TIMEOUT_MAX / HZ) - tp->linger2 = TCP_FIN_TIMEOUT_MAX; + WRITE_ONCE(tp->linger2, TCP_FIN_TIMEOUT_MAX); else - tp->linger2 = val * HZ; + WRITE_ONCE(tp->linger2, val * HZ); break;

case TCP_DEFER_ACCEPT: @@ -4099,7 +4099,7 @@ int do_tcp_getsockopt(struct sock *sk, int level, READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); break; case TCP_LINGER2: - val = tp->linger2; + val = READ_ONCE(tp->linger2); if (val >= 0) val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ; break;

From: Eric Dumazet edumazet@google.com

[ Upstream commit 1aeb87bc1440c5447a7fa2d6e3c2cca52cbd206b ]

tp->notsent_lowat can be read locklessly from do_tcp_getsockopt() and tcp_poll().

Fixes: c9bee3b7fdec ("tcp: TCP_NOTSENT_LOWAT socket option") Signed-off-by: Eric Dumazet edumazet@google.com Link: https://lore.kernel.org/r/20230719212857.3943972-10-edumazet@google.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/tcp.h | 6 +++++- net/ipv4/tcp.c | 4 ++-- 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h index 9733d8e4f10af..e9c8f88f47696 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2059,7 +2059,11 @@ void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr); static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); - return tp->notsent_lowat ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat); + u32 val; + + val = READ_ONCE(tp->notsent_lowat); + + return val ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat); }

bool tcp_stream_memory_free(const struct sock *sk, int wake); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index bc3ad48f92389..6f3a494b965ae 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3770,7 +3770,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, err = tcp_repair_set_window(tp, optval, optlen); break; case TCP_NOTSENT_LOWAT: - tp->notsent_lowat = val; + WRITE_ONCE(tp->notsent_lowat, val); sk->sk_write_space(sk); break; case TCP_INQ: @@ -4266,7 +4266,7 @@ int do_tcp_getsockopt(struct sock *sk, int level, val = tcp_time_stamp_raw() + READ_ONCE(tp->tsoffset); break; case TCP_NOTSENT_LOWAT: - val = tp->notsent_lowat; + val = READ_ONCE(tp->notsent_lowat); break; case TCP_INQ: val = tp->recvmsg_inq;