5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Qu Wenruo wqu@suse.com

[ Upstream commit 7f72f50547b7af4ddf985b07fc56600a4deba281 ]

[BUG] Syzbot reported several warning triggered inside lookup_inline_extent_backref().

[CAUSE] As usual, the reproducer doesn't reliably trigger locally here, but at least we know the WARN_ON() is triggered when an inline backref can not be found, and it can only be triggered when @insert is true. (I.e. inserting a new inline backref, which means the backref should already exist)

[ENHANCEMENT] After the WARN_ON(), dump all the parameters and the extent tree leaf to help debug.

Link: https://syzkaller.appspot.com/bug?extid=d6f9ff86c1d804ba2bc6 Signed-off-by: Qu Wenruo wqu@suse.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/btrfs/extent-tree.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 9cdf50e2484e1..4d2f25ebe3048 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -857,6 +857,11 @@ int lookup_inline_extent_backref(struct btrfs_trans_handle *trans, err = -ENOENT; goto out; } else if (WARN_ON(ret)) { + btrfs_print_leaf(path->nodes[0]); + btrfs_err(fs_info, +"extent item not found for insert, bytenr %llu num_bytes %llu parent %llu root_objectid %llu owner %llu offset %llu", + bytenr, num_bytes, parent, root_objectid, owner, + offset); err = -EIO; goto out; }

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Abhishek Mainkar abmainkar@nvidia.com

[ Upstream commit 3a21ffdbc825e0919db9da0e27ee5ff2cc8a863e ]

ACPICA commit 90310989a0790032f5a0140741ff09b545af4bc5

According to the ACPI specification 19.6.134, no argument is required to be passed for ASL Timer instruction. For taking care of no argument, AML_NO_OPERAND_RESOLVE flag is added to ASL Timer instruction opcode.

When ASL timer instruction interpreted by ACPI interpreter, getting error. After adding AML_NO_OPERAND_RESOLVE flag to ASL Timer instruction opcode, issue is not observed.

============================================================= UBSAN: array-index-out-of-bounds in acpica/dswexec.c:401:12 index -1 is out of range for type 'union acpi_operand_object *[9]' CPU: 37 PID: 1678 Comm: cat Not tainted 6.0.0-dev-th500-6.0.y-1+bcf8c46459e407-generic-64k HW name: NVIDIA BIOS v1.1.1-d7acbfc-dirty 12/19/2022 Call trace: dump_backtrace+0xe0/0x130 show_stack+0x20/0x60 dump_stack_lvl+0x68/0x84 dump_stack+0x18/0x34 ubsan_epilogue+0x10/0x50 __ubsan_handle_out_of_bounds+0x80/0x90 acpi_ds_exec_end_op+0x1bc/0x6d8 acpi_ps_parse_loop+0x57c/0x618 acpi_ps_parse_aml+0x1e0/0x4b4 acpi_ps_execute_method+0x24c/0x2b8 acpi_ns_evaluate+0x3a8/0x4bc acpi_evaluate_object+0x15c/0x37c acpi_evaluate_integer+0x54/0x15c show_power+0x8c/0x12c [acpi_power_meter]

Link: https://github.com/acpica/acpica/commit/90310989 Signed-off-by: Abhishek Mainkar abmainkar@nvidia.com Signed-off-by: Bob Moore robert.moore@intel.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/acpica/psopcode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/acpi/acpica/psopcode.c b/drivers/acpi/acpica/psopcode.c index 28af49263ebfa..62957cba30f61 100644 --- a/drivers/acpi/acpica/psopcode.c +++ b/drivers/acpi/acpica/psopcode.c @@ -603,7 +603,7 @@ const struct acpi_opcode_info acpi_gbl_aml_op_info[AML_NUM_OPCODES] = {

/* 7E */ ACPI_OP("Timer", ARGP_TIMER_OP, ARGI_TIMER_OP, ACPI_TYPE_ANY, AML_CLASS_EXECUTE, AML_TYPE_EXEC_0A_0T_1R, - AML_FLAGS_EXEC_0A_0T_1R), + AML_FLAGS_EXEC_0A_0T_1R | AML_NO_OPERAND_RESOLVE),

/* ACPI 5.0 opcodes */

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Zqiang qiang.zhang1211@gmail.com

[ Upstream commit e60c122a1614b4f65b29a7bef9d83b9fd30e937a ]

The rcuscale.holdoff module parameter can be used to delay the start of rcu_scale_writer() kthread. However, the hung-task timeout will trigger when the timeout specified by rcuscale.holdoff is greater than hung_task_timeout_secs:

runqemu kvm nographic slirp qemuparams="-smp 4 -m 2048M" bootparams="rcuscale.shutdown=0 rcuscale.holdoff=300"

[ 247.071753] INFO: task rcu_scale_write:59 blocked for more than 122 seconds. [ 247.072529] Not tainted 6.4.0-rc1-00134-gb9ed6de8d4ff #7 [ 247.073400] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 247.074331] task:rcu_scale_write state:D stack:30144 pid:59 ppid:2 flags:0x00004000 [ 247.075346] Call Trace: [ 247.075660] <TASK> [ 247.075965] __schedule+0x635/0x1280 [ 247.076448] ? __pfx___schedule+0x10/0x10 [ 247.076967] ? schedule_timeout+0x2dc/0x4d0 [ 247.077471] ? __pfx_lock_release+0x10/0x10 [ 247.078018] ? enqueue_timer+0xe2/0x220 [ 247.078522] schedule+0x84/0x120 [ 247.078957] schedule_timeout+0x2e1/0x4d0 [ 247.079447] ? __pfx_schedule_timeout+0x10/0x10 [ 247.080032] ? __pfx_rcu_scale_writer+0x10/0x10 [ 247.080591] ? __pfx_process_timeout+0x10/0x10 [ 247.081163] ? __pfx_sched_set_fifo_low+0x10/0x10 [ 247.081760] ? __pfx_rcu_scale_writer+0x10/0x10 [ 247.082287] rcu_scale_writer+0x6b1/0x7f0 [ 247.082773] ? mark_held_locks+0x29/0xa0 [ 247.083252] ? __pfx_rcu_scale_writer+0x10/0x10 [ 247.083865] ? __pfx_rcu_scale_writer+0x10/0x10 [ 247.084412] kthread+0x179/0x1c0 [ 247.084759] ? __pfx_kthread+0x10/0x10 [ 247.085098] ret_from_fork+0x2c/0x50 [ 247.085433] </TASK>

This commit therefore replaces schedule_timeout_uninterruptible() with schedule_timeout_idle().

Signed-off-by: Zqiang qiang.zhang1211@gmail.com Signed-off-by: Paul E. McKenney paulmck@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/rcu/rcuscale.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c index 6c05365ed80fc..3b9783eda6796 100644 --- a/kernel/rcu/rcuscale.c +++ b/kernel/rcu/rcuscale.c @@ -372,7 +372,7 @@ rcu_scale_writer(void *arg) sched_set_fifo_low(current);

if (holdoff) - schedule_timeout_uninterruptible(holdoff * HZ); + schedule_timeout_idle(holdoff * HZ);

/* * Wait until rcu_end_inkernel_boot() is called for normal GP tests

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Jiri Slaby (SUSE) jirislaby@kernel.org

[ Upstream commit 96b709be183c56293933ef45b8b75f8af268c6de ]

The Lenovo Ideapad Z470 predates Windows 8, so it defaults to using acpi_video for backlight control. But this is not functional on this model.

Add a DMI quirk to use the native backlight interface which works.

Link: https://bugzilla.suse.com/show_bug.cgi?id=1208724 Signed-off-by: Jiri Slaby (SUSE) jirislaby@kernel.org Reviewed-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 | 9 +++++++++ 1 file changed, 9 insertions(+)

diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index b02d381e78483..28e816be4753e 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -307,6 +307,15 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "Lenovo IdeaPad S405"), }, }, + { + /* https://bugzilla.suse.com/show_bug.cgi?id=1208724 */ + .callback = video_detect_force_native, + /* Lenovo Ideapad Z470 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "IdeaPad Z470"), + }, + }, { /* https://bugzilla.redhat.com/show_bug.cgi?id=1187004 */ .callback = video_detect_force_native,

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Hans de Goede hdegoede@redhat.com

[ Upstream commit 8cf04bb321f036dd2e523e993897e0789bd5265c ]

Linux defaults to picking the non-working ACPI video backlight interface on the Apple iMac12,1 and iMac12,2.

Add a DMI quirk to pick the working native radeon_bl0 interface instead.

Link: https://gitlab.freedesktop.org/drm/amd/-/issues/1838 Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2753 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 | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+)

diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 28e816be4753e..a5cb9e1d48bcc 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -357,6 +357,24 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "iMac11,3"), }, }, + { + /* https://gitlab.freedesktop.org/drm/amd/-/issues/1838 */ + .callback = video_detect_force_native, + /* Apple iMac12,1 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "iMac12,1"), + }, + }, + { + /* https://gitlab.freedesktop.org/drm/amd/-/issues/2753 */ + .callback = video_detect_force_native, + /* Apple iMac12,2 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "iMac12,2"), + }, + }, { /* https://bugzilla.redhat.com/show_bug.cgi?id=1217249 */ .callback = video_detect_force_native,

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Jiri Pirko jiri@nvidia.com

[ Upstream commit 633d76ad01ad0321a1ace3e5cc4fed06753d7ac4 ]

The checks in question were introduced by: commit 6b4db2e528f6 ("devlink: Fix use-after-free after a failed reload"). That fixed an issue of reload with mlxsw driver.

Back then, that was a valid fix, because there was a limitation in place that prevented drivers from registering/unregistering params when devlink instance was registered.

It was possible to do the fix differently by changing drivers to register/unregister params in appropriate places making sure the ops operate only on memory which is allocated and initialized. But that, as a dependency, would require to remove the limitation mentioned above.

Eventually, this limitation was lifted by: commit 1d18bb1a4ddd ("devlink: allow registering parameters after the instance")

Also, the alternative fix (which also fixed another issue) was done by: commit 74cbc3c03c82 ("mlxsw: spectrum_acl_tcam: Move devlink param to TCAM code").

Therefore, the checks are no longer relevant. Each driver should make sure to have the params registered only when the memory the ops are working with is allocated and initialized.

So remove the checks.

Signed-off-by: Jiri Pirko jiri@nvidia.com Reviewed-by: Ido Schimmel idosch@nvidia.com Reviewed-by: Jakub Kicinski kuba@kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/core/devlink.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/devlink.c b/net/core/devlink.c index 00c6944ed6342..38666dde89340 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -3620,7 +3620,7 @@ static int devlink_param_get(struct devlink *devlink, const struct devlink_param *param, struct devlink_param_gset_ctx *ctx) { - if (!param->get || devlink->reload_failed) + if (!param->get) return -EOPNOTSUPP; return param->get(devlink, param->id, ctx); } @@ -3629,7 +3629,7 @@ static int devlink_param_set(struct devlink *devlink, const struct devlink_param *param, struct devlink_param_gset_ctx *ctx) { - if (!param->set || devlink->reload_failed) + if (!param->set) return -EOPNOTSUPP; return param->set(devlink, param->id, ctx); }

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Dmitry Antipov dmantipov@yandex.ru

[ Upstream commit 810e41cebb6c6e394f2068f839e1a3fc745a5dcc ]

When compiling with gcc 13.1 and CONFIG_FORTIFY_SOURCE=y, I've noticed the following:

In function ‘fortify_memcpy_chk’, inlined from ‘ath_tx_complete_aggr’ at drivers/net/wireless/ath/ath9k/xmit.c:556:4, inlined from ‘ath_tx_process_buffer’ at drivers/net/wireless/ath/ath9k/xmit.c:773:3: ./include/linux/fortify-string.h:529:25: warning: call to ‘__read_overflow2_field’ declared with attribute warning: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Wattribute-warning] 529 | __read_overflow2_field(q_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

In function ‘fortify_memcpy_chk’, inlined from ‘ath_tx_count_frames’ at drivers/net/wireless/ath/ath9k/xmit.c:473:3, inlined from ‘ath_tx_complete_aggr’ at drivers/net/wireless/ath/ath9k/xmit.c:572:2, inlined from ‘ath_tx_process_buffer’ at drivers/net/wireless/ath/ath9k/xmit.c:773:3: ./include/linux/fortify-string.h:529:25: warning: call to ‘__read_overflow2_field’ declared with attribute warning: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Wattribute-warning] 529 | __read_overflow2_field(q_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

In both cases, the compiler complains on:

memcpy(ba, &ts->ba_low, WME_BA_BMP_SIZE >> 3);

which is the legal way to copy both 'ba_low' and following 'ba_high' members of 'struct ath_tx_status' at once (that is, issue one 8-byte 'memcpy()' for two 4-byte fields). Since the fortification logic seems interprets this trick as an attempt to overread 4-byte 'ba_low', silence relevant warnings by using the convenient 'struct_group()' quirk.

Suggested-by: Johannes Berg johannes@sipsolutions.net Signed-off-by: Dmitry Antipov dmantipov@yandex.ru Acked-by: Toke Høiland-Jørgensen toke@toke.dk Signed-off-by: Kalle Valo quic_kvalo@quicinc.com Link: https://lore.kernel.org/r/20230620080855.396851-2-dmantipov@yandex.ru Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/ath/ath9k/mac.h | 6 ++++-- drivers/net/wireless/ath/ath9k/xmit.c | 4 ++-- 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/mac.h b/drivers/net/wireless/ath/ath9k/mac.h index fd6aa49adadfe..9b00e77a6fc3c 100644 --- a/drivers/net/wireless/ath/ath9k/mac.h +++ b/drivers/net/wireless/ath/ath9k/mac.h @@ -113,8 +113,10 @@ struct ath_tx_status { u8 qid; u16 desc_id; u8 tid; - u32 ba_low; - u32 ba_high; + struct_group(ba, + u32 ba_low; + u32 ba_high; + ); u32 evm0; u32 evm1; u32 evm2; diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c index 6555abf02f18b..84c68aefc171a 100644 --- a/drivers/net/wireless/ath/ath9k/xmit.c +++ b/drivers/net/wireless/ath/ath9k/xmit.c @@ -421,7 +421,7 @@ static void ath_tx_count_frames(struct ath_softc *sc, struct ath_buf *bf, isaggr = bf_isaggr(bf); if (isaggr) { seq_st = ts->ts_seqnum; - memcpy(ba, &ts->ba_low, WME_BA_BMP_SIZE >> 3); + memcpy(ba, &ts->ba, WME_BA_BMP_SIZE >> 3); }

while (bf) { @@ -504,7 +504,7 @@ static void ath_tx_complete_aggr(struct ath_softc *sc, struct ath_txq *txq, if (isaggr && txok) { if (ts->ts_flags & ATH9K_TX_BA) { seq_st = ts->ts_seqnum; - memcpy(ba, &ts->ba_low, WME_BA_BMP_SIZE >> 3); + memcpy(ba, &ts->ba, WME_BA_BMP_SIZE >> 3); } else { /* * AR5416 can become deaf/mute when BA

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Dmitry Antipov dmantipov@yandex.ru

[ Upstream commit dcce94b80a954a8968ff29fafcfb066d6197fa9a ]

When compiling with gcc 13.1 and CONFIG_FORTIFY_SOURCE=y, I've noticed the following:

In function ‘fortify_memcpy_chk’, inlined from ‘mwifiex_construct_tdls_action_frame’ at drivers/net/wireless/marvell/mwifiex/tdls.c:765:3, inlined from ‘mwifiex_send_tdls_action_frame’ at drivers/net/wireless/marvell/mwifiex/tdls.c:856:6: ./include/linux/fortify-string.h:529:25: warning: call to ‘__read_overflow2_field’ declared with attribute warning: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Wattribute-warning] 529 | __read_overflow2_field(q_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

The compiler actually complains on:

memmove(pos + ETH_ALEN, &mgmt->u.action.category, sizeof(mgmt->u.action.u.tdls_discover_resp));

and it happens because the fortification logic interprets this as an attempt to overread 1-byte 'u.action.category' member of 'struct ieee80211_mgmt'. To silence this warning, it's enough to pass an address of 'u.action' itself instead of an address of its first member.

This also fixes an improper usage of 'sizeof()'. Since 'skb' is extended with 'sizeof(mgmt->u.action.u.tdls_discover_resp) + 1' bytes (where 1 is actually 'sizeof(mgmt->u.action.category)'), I assume that the same number of bytes should be copied.

Suggested-by: Brian Norris briannorris@chromium.org Signed-off-by: Dmitry Antipov dmantipov@yandex.ru Reviewed-by: Brian Norris briannorris@chromium.org Signed-off-by: Kalle Valo kvalo@kernel.org Link: https://lore.kernel.org/r/20230629085115.180499-2-dmantipov@yandex.ru Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/marvell/mwifiex/tdls.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/tdls.c b/drivers/net/wireless/marvell/mwifiex/tdls.c index 97bb87c3676bb..6c60621b6cccb 100644 --- a/drivers/net/wireless/marvell/mwifiex/tdls.c +++ b/drivers/net/wireless/marvell/mwifiex/tdls.c @@ -735,6 +735,7 @@ mwifiex_construct_tdls_action_frame(struct mwifiex_private *priv, int ret; u16 capab; struct ieee80211_ht_cap *ht_cap; + unsigned int extra; u8 radio, *pos;

capab = priv->curr_bss_params.bss_descriptor.cap_info_bitmap; @@ -753,7 +754,10 @@ mwifiex_construct_tdls_action_frame(struct mwifiex_private *priv,

switch (action_code) { case WLAN_PUB_ACTION_TDLS_DISCOVER_RES: - skb_put(skb, sizeof(mgmt->u.action.u.tdls_discover_resp) + 1); + /* See the layout of 'struct ieee80211_mgmt'. */ + extra = sizeof(mgmt->u.action.u.tdls_discover_resp) + + sizeof(mgmt->u.action.category); + skb_put(skb, extra); mgmt->u.action.category = WLAN_CATEGORY_PUBLIC; mgmt->u.action.u.tdls_discover_resp.action_code = WLAN_PUB_ACTION_TDLS_DISCOVER_RES; @@ -762,8 +766,7 @@ mwifiex_construct_tdls_action_frame(struct mwifiex_private *priv, mgmt->u.action.u.tdls_discover_resp.capability = cpu_to_le16(capab); /* move back for addr4 */ - memmove(pos + ETH_ALEN, &mgmt->u.action.category, - sizeof(mgmt->u.action.u.tdls_discover_resp)); + memmove(pos + ETH_ALEN, &mgmt->u.action, extra); /* init address 4 */ eth_broadcast_addr(pos);

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Mark O'Donovan shiftee@posteo.net

[ Upstream commit 9e47a758b70167c9301d2b44d2569f86c7796f2d ]

During NVMeTCP Authentication a controller can trigger a kernel oops by specifying the 8192 bit Diffie Hellman group and passing a correctly sized, but zeroed Diffie Hellamn value. mpi_cmp_ui() was detecting this if the second parameter was 0, but 1 is passed from dh_is_pubkey_valid(). This causes the null pointer u->d to be dereferenced towards the end of mpi_cmp_ui()

Signed-off-by: Mark O'Donovan shiftee@posteo.net Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Sasha Levin sashal@kernel.org --- lib/mpi/mpi-cmp.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/lib/mpi/mpi-cmp.c b/lib/mpi/mpi-cmp.c index c4cfa3ff05818..0835b6213235e 100644 --- a/lib/mpi/mpi-cmp.c +++ b/lib/mpi/mpi-cmp.c @@ -25,8 +25,12 @@ int mpi_cmp_ui(MPI u, unsigned long v) mpi_limb_t limb = v;

mpi_normalize(u); - if (!u->nlimbs && !limb) - return 0; + if (u->nlimbs == 0) { + if (v == 0) + return 0; + else + return -1; + } if (u->sign) return -1; if (u->nlimbs > 1)

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Giulio Benetti giulio.benetti@benettiengineering.com

[ Upstream commit 5ae4b0d8875caa44946e579420c7fd5740d58653 ]

Errata ERR010450 only shows up if voltage is 1.8V, but if the device is supplied by 3v3 the errata can be ignored. So let's check for if quirk SDHCI_QUIRK2_NO_1_8_V is defined or not before limiting the frequency.

Cc: Jim Reinhart jimr@tekvox.com Cc: James Autry jautry@tekvox.com Cc: Matthew Maron matthewm@tekvox.com Signed-off-by: Giulio Benetti giulio.benetti@benettiengineering.com Acked-by: Haibo Chen haibo.chen@nxp.com Acked-by: Adrian Hunter adrian.hunter@intel.com Link: https://lore.kernel.org/r/20230811214853.8623-1-giulio.benetti@benettiengine... Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/mmc/host/sdhci-esdhc-imx.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index 70f388f83485c..b030f657e2534 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -166,8 +166,8 @@ #define ESDHC_FLAG_HS400 BIT(9) /* * The IP has errata ERR010450 - * uSDHC: Due to the I/O timing limit, for SDR mode, SD card clock can't - * exceed 150MHz, for DDR mode, SD card clock can't exceed 45MHz. + * uSDHC: At 1.8V due to the I/O timing limit, for SDR mode, SD card + * clock can't exceed 150MHz, for DDR mode, SD card clock can't exceed 45MHz. */ #define ESDHC_FLAG_ERR010450 BIT(10) /* The IP supports HS400ES mode */ @@ -873,7 +873,8 @@ static inline void esdhc_pltfm_set_clock(struct sdhci_host *host, | ESDHC_CLOCK_MASK); sdhci_writel(host, temp, ESDHC_SYSTEM_CONTROL);

- if (imx_data->socdata->flags & ESDHC_FLAG_ERR010450) { + if ((imx_data->socdata->flags & ESDHC_FLAG_ERR010450) && + (!(host->quirks2 & SDHCI_QUIRK2_NO_1_8_V))) { unsigned int max_clock;

max_clock = imx_data->is_ddr ? 45000000 : 150000000;

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: GONG, Ruiqi gongruiqi1@huawei.com

[ Upstream commit a7ed3465daa240bdf01a5420f64336fee879c09d ]

When compiling with gcc 13 and CONFIG_FORTIFY_SOURCE=y, the following warning appears:

In function ‘fortify_memcpy_chk’, inlined from ‘size_entry_mwt’ at net/bridge/netfilter/ebtables.c:2118:2: ./include/linux/fortify-string.h:592:25: error: call to ‘__read_overflow2_field’ declared with attribute warning: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Werror=attribute-warning] 592 | __read_overflow2_field(q_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

The compiler is complaining:

memcpy(&offsets[1], &entry->watchers_offset, sizeof(offsets) - sizeof(offsets[0]));

where memcpy reads beyong &entry->watchers_offset to copy {watchers,target,next}_offset altogether into offsets[]. Silence the warning by wrapping these three up via struct_group().

Signed-off-by: GONG, Ruiqi gongruiqi1@huawei.com Reviewed-by: Gustavo A. R. Silva gustavoars@kernel.org Reviewed-by: Kees Cook keescook@chromium.org Signed-off-by: Florian Westphal fw@strlen.de Signed-off-by: Sasha Levin sashal@kernel.org --- include/uapi/linux/netfilter_bridge/ebtables.h | 14 ++++++++------ net/bridge/netfilter/ebtables.c | 3 +-- 2 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/include/uapi/linux/netfilter_bridge/ebtables.h b/include/uapi/linux/netfilter_bridge/ebtables.h index a494cf43a7552..b0caad82b6937 100644 --- a/include/uapi/linux/netfilter_bridge/ebtables.h +++ b/include/uapi/linux/netfilter_bridge/ebtables.h @@ -182,12 +182,14 @@ struct ebt_entry { unsigned char sourcemsk[ETH_ALEN]; unsigned char destmac[ETH_ALEN]; unsigned char destmsk[ETH_ALEN]; - /* sizeof ebt_entry + matches */ - unsigned int watchers_offset; - /* sizeof ebt_entry + matches + watchers */ - unsigned int target_offset; - /* sizeof ebt_entry + matches + watchers + target */ - unsigned int next_offset; + __struct_group(/* no tag */, offsets, /* no attrs */, + /* sizeof ebt_entry + matches */ + unsigned int watchers_offset; + /* sizeof ebt_entry + matches + watchers */ + unsigned int target_offset; + /* sizeof ebt_entry + matches + watchers + target */ + unsigned int next_offset; + ); unsigned char elems[0] __attribute__ ((aligned (__alignof__(struct ebt_replace)))); };

diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 8335b7e4bcf6f..bab14186f9ad5 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -2001,8 +2001,7 @@ static int size_entry_mwt(const struct ebt_entry *entry, const unsigned char *ba return ret;

offsets[0] = sizeof(struct ebt_entry); /* matches come first */ - memcpy(&offsets[1], &entry->watchers_offset, - sizeof(offsets) - sizeof(offsets[0])); + memcpy(&offsets[1], &entry->offsets, sizeof(entry->offsets));

if (state->buf_kern_start) { buf_start = state->buf_kern_start + state->buf_kern_offset;

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Hao Luo haoluo@google.com

[ Upstream commit 29d67fdebc42af6466d1909c60fdd1ef4f3e5240 ]

I hit a memory leak when testing bpf_program__set_attach_target(). Basically, set_attach_target() may allocate btf_vmlinux, for example, when setting attach target for bpf_iter programs. But btf_vmlinux is freed only in bpf_object_load(), which means if we only open bpf object but not load it, setting attach target may leak btf_vmlinux.

So let's free btf_vmlinux in bpf_object__close() anyway.

Signed-off-by: Hao Luo haoluo@google.com Signed-off-by: Andrii Nakryiko andrii@kernel.org Link: https://lore.kernel.org/bpf/20230822193840.1509809-1-haoluo@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/lib/bpf/libbpf.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 015ed8253f739..44646c5286fbe 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -7962,6 +7962,7 @@ void bpf_object__close(struct bpf_object *obj) bpf_object__elf_finish(obj); bpf_object__unload(obj); btf__free(obj->btf); + btf__free(obj->btf_vmlinux); btf_ext__free(obj->btf_ext);

for (i = 0; i < obj->nr_maps; i++)

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Rong Tao rongtao@cestc.cn

[ Upstream commit 910e230d5f1bb72c54532e94fbb1705095c7bab6 ]

Macro symbol_put() is defined as __symbol_put(__stringify(x))

ksym_name = "jiffies" symbol_put(ksym_name)

will be resolved as

__symbol_put("ksym_name")

which is clearly wrong. So symbol_put must be replaced with __symbol_put.

When we uninstall hw_breakpoint.ko (rmmod), a kernel bug occurs with the following error:

[11381.854152] kernel BUG at kernel/module/main.c:779! [11381.854159] invalid opcode: 0000 [#2] PREEMPT SMP PTI [11381.854163] CPU: 8 PID: 59623 Comm: rmmod Tainted: G D OE 6.2.9-200.fc37.x86_64 #1 [11381.854167] Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./B360M-HDV, BIOS P3.20 10/23/2018 [11381.854169] RIP: 0010:__symbol_put+0xa2/0xb0 [11381.854175] Code: 00 e8 92 d2 f7 ff 65 8b 05 c3 2f e6 78 85 c0 74 1b 48 8b 44 24 30 65 48 2b 04 25 28 00 00 00 75 12 48 83 c4 38 c3 cc cc cc cc <0f> 0b 0f 1f 44 00 00 eb de e8 c0 df d8 00 90 90 90 90 90 90 90 90 [11381.854178] RSP: 0018:ffffad8ec6ae7dd0 EFLAGS: 00010246 [11381.854181] RAX: 0000000000000000 RBX: ffffffffc1fd1240 RCX: 000000000000000c [11381.854184] RDX: 000000000000006b RSI: ffffffffc02bf7c7 RDI: ffffffffc1fd001c [11381.854186] RBP: 000055a38b76e7c8 R08: ffffffff871ccfe0 R09: 0000000000000000 [11381.854188] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 [11381.854190] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 [11381.854192] FS: 00007fbf7c62c740(0000) GS:ffff8c5badc00000(0000) knlGS:0000000000000000 [11381.854195] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [11381.854197] CR2: 000055a38b7793f8 CR3: 0000000363e1e001 CR4: 00000000003726e0 [11381.854200] DR0: ffffffffb3407980 DR1: 0000000000000000 DR2: 0000000000000000 [11381.854202] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [11381.854204] Call Trace: [11381.854207] <TASK> [11381.854212] s_module_exit+0xc/0xff0 [symbol_getput] [11381.854219] __do_sys_delete_module.constprop.0+0x198/0x2f0 [11381.854225] do_syscall_64+0x58/0x80 [11381.854231] ? exit_to_user_mode_prepare+0x180/0x1f0 [11381.854237] ? syscall_exit_to_user_mode+0x17/0x40 [11381.854241] ? do_syscall_64+0x67/0x80 [11381.854245] ? syscall_exit_to_user_mode+0x17/0x40 [11381.854248] ? do_syscall_64+0x67/0x80 [11381.854252] ? exc_page_fault+0x70/0x170 [11381.854256] entry_SYSCALL_64_after_hwframe+0x72/0xdc

Signed-off-by: Rong Tao rongtao@cestc.cn Reviewed-by: Petr Mladek pmladek@suse.com Signed-off-by: Luis Chamberlain mcgrof@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- samples/hw_breakpoint/data_breakpoint.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/samples/hw_breakpoint/data_breakpoint.c b/samples/hw_breakpoint/data_breakpoint.c index 418c46fe5ffc3..9debd128b2ab8 100644 --- a/samples/hw_breakpoint/data_breakpoint.c +++ b/samples/hw_breakpoint/data_breakpoint.c @@ -70,7 +70,7 @@ static int __init hw_break_module_init(void) static void __exit hw_break_module_exit(void) { unregister_wide_hw_breakpoint(sample_hbp); - symbol_put(ksym_name); + __symbol_put(ksym_name); printk(KERN_INFO "HW Breakpoint for %s write uninstalled\n", ksym_name); }

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Tuo Li islituo@gmail.com

[ Upstream commit 2e63972a2de14482d0eae1a03a73e379f1c3f44c ]

The variable crtc->state->event is often protected by the lock crtc->dev->event_lock when is accessed. However, it is accessed as a condition of an if statement in exynos_drm_crtc_atomic_disable() without holding the lock:

if (crtc->state->event && !crtc->state->active)

However, if crtc->state->event is changed to NULL by another thread right after the conditions of the if statement is checked to be true, a null-pointer dereference can occur in drm_crtc_send_vblank_event():

e->pipe = pipe;

To fix this possible null-pointer dereference caused by data race, the spin lock coverage is extended to protect the if statement as well as the function call to drm_crtc_send_vblank_event().

Reported-by: BassCheck bass@buaa.edu.cn Link: https://sites.google.com/view/basscheck/home Signed-off-by: Tuo Li islituo@gmail.com Reviewed-by: Krzysztof Kozlowski krzysztof.kozlowski@linaro.org Added relevant link. Signed-off-by: Inki Dae inki.dae@samsung.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/exynos/exynos_drm_crtc.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c index 1c03485676efa..de9fadccf22e5 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c @@ -39,13 +39,12 @@ static void exynos_drm_crtc_atomic_disable(struct drm_crtc *crtc, if (exynos_crtc->ops->atomic_disable) exynos_crtc->ops->atomic_disable(exynos_crtc);

+ spin_lock_irq(&crtc->dev->event_lock); if (crtc->state->event && !crtc->state->active) { - spin_lock_irq(&crtc->dev->event_lock); drm_crtc_send_vblank_event(crtc, crtc->state->event); - spin_unlock_irq(&crtc->dev->event_lock); - crtc->state->event = NULL; } + spin_unlock_irq(&crtc->dev->event_lock); }

static int exynos_crtc_atomic_check(struct drm_crtc *crtc,

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Zhang Shurong zhang_shurong@foxmail.com

[ Upstream commit 8b0472b50bcf0f19a5119b00a53b63579c8e1e4d ]

If rddev->raid_disk is greater than mddev->raid_disks, there will be an out-of-bounds in raid1_remove_disk(). We have already found similar reports as follows:

1) commit d17f744e883b ("md-raid10: fix KASAN warning") 2) commit 1ebc2cec0b7d ("dm raid: fix KASAN warning in raid5_remove_disk")

Fix this bug by checking whether the "number" variable is valid.

Signed-off-by: Zhang Shurong zhang_shurong@foxmail.com Reviewed-by: Yu Kuai yukuai3@huawei.com Link: https://lore.kernel.org/r/tencent_0D24426FAC6A21B69AC0C03CE4143A508F09@qq.co... Signed-off-by: Song Liu song@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/md/raid1.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 6b5cc3f59fb39..25be491c1a6ac 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1791,6 +1791,10 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev) struct r1conf *conf = mddev->private; int err = 0; int number = rdev->raid_disk; + + if (unlikely(number >= conf->raid_disks)) + goto abort; + struct raid1_info *p = conf->mirrors + number;

if (rdev != p->rdev)

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Andrew Kanner andrew.kanner@gmail.com

[ Upstream commit cade5397e5461295f3cb87880534b6a07cafa427 ]

Syzkaller reported the following issue: ================================================================== BUG: KASAN: double-free in slab_free mm/slub.c:3787 [inline] BUG: KASAN: double-free in __kmem_cache_free+0x71/0x110 mm/slub.c:3800 Free of addr ffff888086408000 by task syz-executor.4/12750 [...] Call Trace: <TASK> [...] kasan_report_invalid_free+0xac/0xd0 mm/kasan/report.c:482 ____kasan_slab_free+0xfb/0x120 kasan_slab_free include/linux/kasan.h:177 [inline] slab_free_hook mm/slub.c:1781 [inline] slab_free_freelist_hook+0x12e/0x1a0 mm/slub.c:1807 slab_free mm/slub.c:3787 [inline] __kmem_cache_free+0x71/0x110 mm/slub.c:3800 dbUnmount+0xf4/0x110 fs/jfs/jfs_dmap.c:264 jfs_umount+0x248/0x3b0 fs/jfs/jfs_umount.c:87 jfs_put_super+0x86/0x190 fs/jfs/super.c:194 generic_shutdown_super+0x130/0x310 fs/super.c:492 kill_block_super+0x79/0xd0 fs/super.c:1386 deactivate_locked_super+0xa7/0xf0 fs/super.c:332 cleanup_mnt+0x494/0x520 fs/namespace.c:1291 task_work_run+0x243/0x300 kernel/task_work.c:179 resume_user_mode_work include/linux/resume_user_mode.h:49 [inline] exit_to_user_mode_loop+0x124/0x150 kernel/entry/common.c:171 exit_to_user_mode_prepare+0xb2/0x140 kernel/entry/common.c:203 __syscall_exit_to_user_mode_work kernel/entry/common.c:285 [inline] syscall_exit_to_user_mode+0x26/0x60 kernel/entry/common.c:296 do_syscall_64+0x49/0xb0 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x63/0xcd [...] </TASK>

Allocated by task 13352: kasan_save_stack mm/kasan/common.c:45 [inline] kasan_set_track+0x3d/0x60 mm/kasan/common.c:52 ____kasan_kmalloc mm/kasan/common.c:371 [inline] __kasan_kmalloc+0x97/0xb0 mm/kasan/common.c:380 kmalloc include/linux/slab.h:580 [inline] dbMount+0x54/0x980 fs/jfs/jfs_dmap.c:164 jfs_mount+0x1dd/0x830 fs/jfs/jfs_mount.c:121 jfs_fill_super+0x590/0xc50 fs/jfs/super.c:556 mount_bdev+0x26c/0x3a0 fs/super.c:1359 legacy_get_tree+0xea/0x180 fs/fs_context.c:610 vfs_get_tree+0x88/0x270 fs/super.c:1489 do_new_mount+0x289/0xad0 fs/namespace.c:3145 do_mount fs/namespace.c:3488 [inline] __do_sys_mount fs/namespace.c:3697 [inline] __se_sys_mount+0x2d3/0x3c0 fs/namespace.c:3674 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd

Freed by task 13352: kasan_save_stack mm/kasan/common.c:45 [inline] kasan_set_track+0x3d/0x60 mm/kasan/common.c:52 kasan_save_free_info+0x27/0x40 mm/kasan/generic.c:518 ____kasan_slab_free+0xd6/0x120 mm/kasan/common.c:236 kasan_slab_free include/linux/kasan.h:177 [inline] slab_free_hook mm/slub.c:1781 [inline] slab_free_freelist_hook+0x12e/0x1a0 mm/slub.c:1807 slab_free mm/slub.c:3787 [inline] __kmem_cache_free+0x71/0x110 mm/slub.c:3800 dbUnmount+0xf4/0x110 fs/jfs/jfs_dmap.c:264 jfs_mount_rw+0x545/0x740 fs/jfs/jfs_mount.c:247 jfs_remount+0x3db/0x710 fs/jfs/super.c:454 reconfigure_super+0x3bc/0x7b0 fs/super.c:935 vfs_fsconfig_locked fs/fsopen.c:254 [inline] __do_sys_fsconfig fs/fsopen.c:439 [inline] __se_sys_fsconfig+0xad5/0x1060 fs/fsopen.c:314 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd [...]

JFS_SBI(ipbmap->i_sb)->bmap wasn't set to NULL after kfree() in dbUnmount().

Syzkaller uses faultinject to reproduce this KASAN double-free warning. The issue is triggered if either diMount() or dbMount() fail in jfs_remount(), since diUnmount() or dbUnmount() already happened in such a case - they will do double-free on next execution: jfs_umount or jfs_remount.

Tested on both upstream and jfs-next by syzkaller.

Reported-and-tested-by: syzbot+6a93efb725385bc4b2e9@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/000000000000471f2d05f1ce8bad@google.com/T/ Link: https://syzkaller.appspot.com/bug?extid=6a93efb725385bc4b2e9 Signed-off-by: Andrew Kanner andrew.kanner@gmail.com Signed-off-by: Dave Kleikamp dave.kleikamp@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/jfs/jfs_dmap.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index cef3303d94995..a9c078fc2302a 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -269,6 +269,7 @@ int dbUnmount(struct inode *ipbmap, int mounterror)

/* free the memory for the in-memory bmap. */ kfree(bmp); + JFS_SBI(ipbmap->i_sb)->bmap = NULL;

return (0); }

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: ruanjinjie ruanjinjie@huawei.com

[ Upstream commit afda85b963c12947e298ad85d757e333aa40fd74 ]

If device_register() returns error in ibmebus_bus_init(), name of kobject which is allocated in dev_set_name() called in device_add() is leaked.

As comment of device_add() says, it should call put_device() to drop the reference count that was set in device_initialize() when it fails, so the name can be freed in kobject_cleanup().

Signed-off-by: ruanjinjie ruanjinjie@huawei.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://msgid.link/20221110011929.3709774-1-ruanjinjie@huawei.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/platforms/pseries/ibmebus.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c index 8c6e509f69675..c3cc010e9cc45 100644 --- a/arch/powerpc/platforms/pseries/ibmebus.c +++ b/arch/powerpc/platforms/pseries/ibmebus.c @@ -451,6 +451,7 @@ static int __init ibmebus_bus_init(void) if (err) { printk(KERN_WARNING "%s: device_register returned %i\n", __func__, err); + put_device(&ibmebus_bus_device); bus_unregister(&ibmebus_bus_type);

return err;

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Zhang Shurong zhang_shurong@foxmail.com

[ Upstream commit 5ae544d94abc8ff77b1b9bf8774def3fa5689b5b ]

In dw2102_i2c_transfer, msg is controlled by user. When msg[i].buf is null and msg[i].len is zero, former checks on msg[i].buf would be passed. Malicious data finally reach dw2102_i2c_transfer. If accessing msg[i].buf[0] without sanity check, null ptr deref would happen. We add check on msg[i].len to prevent crash.

Similar commit: commit 950e252cb469 ("[media] dw2102: limit messages to buffer size")

Signed-off-by: Zhang Shurong zhang_shurong@foxmail.com Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/usb/dvb-usb/dw2102.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+)

diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c index 3c4ac998d040f..2290f132a82c8 100644 --- a/drivers/media/usb/dvb-usb/dw2102.c +++ b/drivers/media/usb/dvb-usb/dw2102.c @@ -128,6 +128,10 @@ static int dw2102_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[],

switch (num) { case 2: + if (msg[0].len < 1) { + num = -EOPNOTSUPP; + break; + } /* read stv0299 register */ value = msg[0].buf[0];/* register */ for (i = 0; i < msg[1].len; i++) { @@ -139,6 +143,10 @@ static int dw2102_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[], case 1: switch (msg[0].addr) { case 0x68: + if (msg[0].len < 2) { + num = -EOPNOTSUPP; + break; + } /* write to stv0299 register */ buf6[0] = 0x2a; buf6[1] = msg[0].buf[0]; @@ -148,6 +156,10 @@ static int dw2102_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[], break; case 0x60: if (msg[0].flags == 0) { + if (msg[0].len < 4) { + num = -EOPNOTSUPP; + break; + } /* write to tuner pll */ buf6[0] = 0x2c; buf6[1] = 5; @@ -159,6 +171,10 @@ static int dw2102_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[], dw210x_op_rw(d->udev, 0xb2, 0, 0, buf6, 7, DW210X_WRITE_MSG); } else { + if (msg[0].len < 1) { + num = -EOPNOTSUPP; + break; + } /* read from tuner */ dw210x_op_rw(d->udev, 0xb5, 0, 0, buf6, 1, DW210X_READ_MSG); @@ -166,12 +182,20 @@ static int dw2102_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[], } break; case (DW2102_RC_QUERY): + if (msg[0].len < 2) { + num = -EOPNOTSUPP; + break; + } dw210x_op_rw(d->udev, 0xb8, 0, 0, buf6, 2, DW210X_READ_MSG); msg[0].buf[0] = buf6[0]; msg[0].buf[1] = buf6[1]; break; case (DW2102_VOLTAGE_CTRL): + if (msg[0].len < 1) { + num = -EOPNOTSUPP; + break; + } buf6[0] = 0x30; buf6[1] = msg[0].buf[0]; dw210x_op_rw(d->udev, 0xb2, 0, 0,

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Zhang Shurong zhang_shurong@foxmail.com

[ Upstream commit c30411266fd67ea3c02a05c157231654d5a3bdc9 ]

In anysee_master_xfer, msg is controlled by user. When msg[i].buf is null and msg[i].len is zero, former checks on msg[i].buf would be passed. Malicious data finally reach anysee_master_xfer. If accessing msg[i].buf[0] without sanity check, null ptr deref would happen. We add check on msg[i].len to prevent crash.

Similar commit: commit 0ed554fd769a ("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()")

Signed-off-by: Zhang Shurong zhang_shurong@foxmail.com Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl [hverkuil: add spaces around +] Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/usb/dvb-usb-v2/anysee.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/usb/dvb-usb-v2/anysee.c b/drivers/media/usb/dvb-usb-v2/anysee.c index 89a1b204b90c3..3dacf3914d75b 100644 --- a/drivers/media/usb/dvb-usb-v2/anysee.c +++ b/drivers/media/usb/dvb-usb-v2/anysee.c @@ -202,7 +202,7 @@ static int anysee_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msg,

while (i < num) { if (num > i + 1 && (msg[i+1].flags & I2C_M_RD)) { - if (msg[i].len > 2 || msg[i+1].len > 60) { + if (msg[i].len != 2 || msg[i + 1].len > 60) { ret = -EOPNOTSUPP; break; }

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Zhang Shurong zhang_shurong@foxmail.com

[ Upstream commit b97719a66970601cd3151a3e2020f4454a1c4ff6 ]

In gl861_i2c_master_xfer, msg is controlled by user. When msg[i].buf is null and msg[i].len is zero, former checks on msg[i].buf would be passed. Malicious data finally reach gl861_i2c_master_xfer. If accessing msg[i].buf[0] without sanity check, null ptr deref would happen. We add check on msg[i].len to prevent crash.

Similar commit: commit 0ed554fd769a ("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()")

Signed-off-by: Zhang Shurong zhang_shurong@foxmail.com Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/usb/dvb-usb-v2/gl861.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/usb/dvb-usb-v2/gl861.c b/drivers/media/usb/dvb-usb-v2/gl861.c index 0c434259c36f1..c71e7b93476de 100644 --- a/drivers/media/usb/dvb-usb-v2/gl861.c +++ b/drivers/media/usb/dvb-usb-v2/gl861.c @@ -120,7 +120,7 @@ static int gl861_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], } else if (num == 2 && !(msg[0].flags & I2C_M_RD) && (msg[1].flags & I2C_M_RD)) { /* I2C write + read */ - if (msg[0].len > 1 || msg[1].len > sizeof(ctx->buf)) { + if (msg[0].len != 1 || msg[1].len > sizeof(ctx->buf)) { ret = -EOPNOTSUPP; goto err; }

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Hans Verkuil hverkuil-cisco@xs4all.nl

[ Upstream commit 2e1796fd4904fdd6062a8e4589778ea899ea0c8d ]

It was completely unnecessary to use BUG in buffer_prepare(). Just replace it with an error return. This also fixes a smatch warning:

drivers/media/pci/cx23885/cx23885-video.c:422 buffer_prepare() error: uninitialized symbol 'ret'.

Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/pci/cx23885/cx23885-video.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/pci/cx23885/cx23885-video.c b/drivers/media/pci/cx23885/cx23885-video.c index a380e0920a21f..86e3bb5903712 100644 --- a/drivers/media/pci/cx23885/cx23885-video.c +++ b/drivers/media/pci/cx23885/cx23885-video.c @@ -412,7 +412,7 @@ static int buffer_prepare(struct vb2_buffer *vb) dev->height >> 1); break; default: - BUG(); + return -EINVAL; /* should not happen */ } dprintk(2, "[%p/%d] buffer_init - %dx%d %dbpp 0x%08x - dma=0x%08lx\n", buf, buf->vb.vb2_buf.index,

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Konstantin Shelekhin k.shelekhin@yadro.com

[ Upstream commit 801f287c93ff95582b0a2d2163f12870a2f076d4 ]

The function lio_target_nacl_info_show() uses sprintf() in a loop to print details for every iSCSI connection in a session without checking for the buffer length. With enough iSCSI connections it's possible to overflow the buffer provided by configfs and corrupt the memory.

This patch replaces sprintf() with sysfs_emit_at() that checks for buffer boundries.

Signed-off-by: Konstantin Shelekhin k.shelekhin@yadro.com Link: https://lore.kernel.org/r/20230722152657.168859-2-k.shelekhin@yadro.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/target/iscsi/iscsi_target_configfs.c | 54 ++++++++++---------- 1 file changed, 27 insertions(+), 27 deletions(-)

diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index 0fa1d57b26fa8..3cd671bbb9a41 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -508,102 +508,102 @@ static ssize_t lio_target_nacl_info_show(struct config_item *item, char *page) spin_lock_bh(&se_nacl->nacl_sess_lock); se_sess = se_nacl->nacl_sess; if (!se_sess) { - rb += sprintf(page+rb, "No active iSCSI Session for Initiator" + rb += sysfs_emit_at(page, rb, "No active iSCSI Session for Initiator" " Endpoint: %s\n", se_nacl->initiatorname); } else { sess = se_sess->fabric_sess_ptr;

- rb += sprintf(page+rb, "InitiatorName: %s\n", + rb += sysfs_emit_at(page, rb, "InitiatorName: %s\n", sess->sess_ops->InitiatorName); - rb += sprintf(page+rb, "InitiatorAlias: %s\n", + rb += sysfs_emit_at(page, rb, "InitiatorAlias: %s\n", sess->sess_ops->InitiatorAlias);

- rb += sprintf(page+rb, + rb += sysfs_emit_at(page, rb, "LIO Session ID: %u ISID: 0x%6ph TSIH: %hu ", sess->sid, sess->isid, sess->tsih); - rb += sprintf(page+rb, "SessionType: %s\n", + rb += sysfs_emit_at(page, rb, "SessionType: %s\n", (sess->sess_ops->SessionType) ? "Discovery" : "Normal"); - rb += sprintf(page+rb, "Session State: "); + rb += sysfs_emit_at(page, rb, "Session State: "); switch (sess->session_state) { case TARG_SESS_STATE_FREE: - rb += sprintf(page+rb, "TARG_SESS_FREE\n"); + rb += sysfs_emit_at(page, rb, "TARG_SESS_FREE\n"); break; case TARG_SESS_STATE_ACTIVE: - rb += sprintf(page+rb, "TARG_SESS_STATE_ACTIVE\n"); + rb += sysfs_emit_at(page, rb, "TARG_SESS_STATE_ACTIVE\n"); break; case TARG_SESS_STATE_LOGGED_IN: - rb += sprintf(page+rb, "TARG_SESS_STATE_LOGGED_IN\n"); + rb += sysfs_emit_at(page, rb, "TARG_SESS_STATE_LOGGED_IN\n"); break; case TARG_SESS_STATE_FAILED: - rb += sprintf(page+rb, "TARG_SESS_STATE_FAILED\n"); + rb += sysfs_emit_at(page, rb, "TARG_SESS_STATE_FAILED\n"); break; case TARG_SESS_STATE_IN_CONTINUE: - rb += sprintf(page+rb, "TARG_SESS_STATE_IN_CONTINUE\n"); + rb += sysfs_emit_at(page, rb, "TARG_SESS_STATE_IN_CONTINUE\n"); break; default: - rb += sprintf(page+rb, "ERROR: Unknown Session" + rb += sysfs_emit_at(page, rb, "ERROR: Unknown Session" " State!\n"); break; }

- rb += sprintf(page+rb, "---------------------[iSCSI Session" + rb += sysfs_emit_at(page, rb, "---------------------[iSCSI Session" " Values]-----------------------\n"); - rb += sprintf(page+rb, " CmdSN/WR : CmdSN/WC : ExpCmdSN" + rb += sysfs_emit_at(page, rb, " CmdSN/WR : CmdSN/WC : ExpCmdSN" " : MaxCmdSN : ITT : TTT\n"); max_cmd_sn = (u32) atomic_read(&sess->max_cmd_sn); - rb += sprintf(page+rb, " 0x%08x 0x%08x 0x%08x 0x%08x" + rb += sysfs_emit_at(page, rb, " 0x%08x 0x%08x 0x%08x 0x%08x" " 0x%08x 0x%08x\n", sess->cmdsn_window, (max_cmd_sn - sess->exp_cmd_sn) + 1, sess->exp_cmd_sn, max_cmd_sn, sess->init_task_tag, sess->targ_xfer_tag); - rb += sprintf(page+rb, "----------------------[iSCSI" + rb += sysfs_emit_at(page, rb, "----------------------[iSCSI" " Connections]-------------------------\n");

spin_lock(&sess->conn_lock); list_for_each_entry(conn, &sess->sess_conn_list, conn_list) { - rb += sprintf(page+rb, "CID: %hu Connection" + rb += sysfs_emit_at(page, rb, "CID: %hu Connection" " State: ", conn->cid); switch (conn->conn_state) { case TARG_CONN_STATE_FREE: - rb += sprintf(page+rb, + rb += sysfs_emit_at(page, rb, "TARG_CONN_STATE_FREE\n"); break; case TARG_CONN_STATE_XPT_UP: - rb += sprintf(page+rb, + rb += sysfs_emit_at(page, rb, "TARG_CONN_STATE_XPT_UP\n"); break; case TARG_CONN_STATE_IN_LOGIN: - rb += sprintf(page+rb, + rb += sysfs_emit_at(page, rb, "TARG_CONN_STATE_IN_LOGIN\n"); break; case TARG_CONN_STATE_LOGGED_IN: - rb += sprintf(page+rb, + rb += sysfs_emit_at(page, rb, "TARG_CONN_STATE_LOGGED_IN\n"); break; case TARG_CONN_STATE_IN_LOGOUT: - rb += sprintf(page+rb, + rb += sysfs_emit_at(page, rb, "TARG_CONN_STATE_IN_LOGOUT\n"); break; case TARG_CONN_STATE_LOGOUT_REQUESTED: - rb += sprintf(page+rb, + rb += sysfs_emit_at(page, rb, "TARG_CONN_STATE_LOGOUT_REQUESTED\n"); break; case TARG_CONN_STATE_CLEANUP_WAIT: - rb += sprintf(page+rb, + rb += sysfs_emit_at(page, rb, "TARG_CONN_STATE_CLEANUP_WAIT\n"); break; default: - rb += sprintf(page+rb, + rb += sysfs_emit_at(page, rb, "ERROR: Unknown Connection State!\n"); break; }

- rb += sprintf(page+rb, " Address %pISc %s", &conn->login_sockaddr, + rb += sysfs_emit_at(page, rb, " Address %pISc %s", &conn->login_sockaddr, (conn->network_transport == ISCSI_TCP) ? "TCP" : "SCTP"); - rb += sprintf(page+rb, " StatSN: 0x%08x\n", + rb += sysfs_emit_at(page, rb, " StatSN: 0x%08x\n", conn->stat_sn); } spin_unlock(&sess->conn_lock);

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Sakari Ailus sakari.ailus@linux.intel.com

[ Upstream commit 9d7531be3085a8f013cf173ccc4e72e3cf493538 ]

Initialise timing struct in cio2_hw_init() to zero in order to avoid a compiler warning. The warning was a false positive.

Reported-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Sakari Ailus sakari.ailus@linux.intel.com Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/pci/intel/ipu3/ipu3-cio2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/pci/intel/ipu3/ipu3-cio2.c b/drivers/media/pci/intel/ipu3/ipu3-cio2.c index d6838c8ebd7e8..f8dca47904766 100644 --- a/drivers/media/pci/intel/ipu3/ipu3-cio2.c +++ b/drivers/media/pci/intel/ipu3/ipu3-cio2.c @@ -355,7 +355,7 @@ static int cio2_hw_init(struct cio2_device *cio2, struct cio2_queue *q) void __iomem *const base = cio2->base; u8 lanes, csi2bus = q->csi2.port; u8 sensor_vc = SENSOR_VIR_CH_DFLT; - struct cio2_csi2_timing timing; + struct cio2_csi2_timing timing = { 0 }; int i, r;

fmt = cio2_find_format(NULL, &q->subdev_fmt.code);

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Rob Clark robdclark@chromium.org

[ Upstream commit af42269c3523492d71ebbe11fefae2653e9cdc78 ]

For cases where icc_bw_set() can be called in callbaths that could deadlock against shrinker/reclaim, such as runpm resume, we need to decouple the icc locking. Introduce a new icc_bw_lock for cases where we need to serialize bw aggregation and update to decouple that from paths that require memory allocation such as node/link creation/ destruction.

Fixes this lockdep splat:

====================================================== WARNING: possible circular locking dependency detected 6.2.0-rc8-debug+ #554 Not tainted ------------------------------------------------------ ring0/132 is trying to acquire lock: ffffff80871916d0 (&gmu->lock){+.+.}-{3:3}, at: a6xx_pm_resume+0xf0/0x234

but task is already holding lock: ffffffdb5aee57e8 (dma_fence_map){++++}-{0:0}, at: msm_job_run+0x68/0x150

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #4 (dma_fence_map){++++}-{0:0}: __dma_fence_might_wait+0x74/0xc0 dma_resv_lockdep+0x1f4/0x2f4 do_one_initcall+0x104/0x2bc kernel_init_freeable+0x344/0x34c kernel_init+0x30/0x134 ret_from_fork+0x10/0x20

-> #3 (mmu_notifier_invalidate_range_start){+.+.}-{0:0}: fs_reclaim_acquire+0x80/0xa8 slab_pre_alloc_hook.constprop.0+0x40/0x25c __kmem_cache_alloc_node+0x60/0x1cc __kmalloc+0xd8/0x100 topology_parse_cpu_capacity+0x8c/0x178 get_cpu_for_node+0x88/0xc4 parse_cluster+0x1b0/0x28c parse_cluster+0x8c/0x28c init_cpu_topology+0x168/0x188 smp_prepare_cpus+0x24/0xf8 kernel_init_freeable+0x18c/0x34c kernel_init+0x30/0x134 ret_from_fork+0x10/0x20

-> #2 (fs_reclaim){+.+.}-{0:0}: __fs_reclaim_acquire+0x3c/0x48 fs_reclaim_acquire+0x54/0xa8 slab_pre_alloc_hook.constprop.0+0x40/0x25c __kmem_cache_alloc_node+0x60/0x1cc __kmalloc+0xd8/0x100 kzalloc.constprop.0+0x14/0x20 icc_node_create_nolock+0x4c/0xc4 icc_node_create+0x38/0x58 qcom_icc_rpmh_probe+0x1b8/0x248 platform_probe+0x70/0xc4 really_probe+0x158/0x290 __driver_probe_device+0xc8/0xe0 driver_probe_device+0x44/0x100 __driver_attach+0xf8/0x108 bus_for_each_dev+0x78/0xc4 driver_attach+0x2c/0x38 bus_add_driver+0xd0/0x1d8 driver_register+0xbc/0xf8 __platform_driver_register+0x30/0x3c qnoc_driver_init+0x24/0x30 do_one_initcall+0x104/0x2bc kernel_init_freeable+0x344/0x34c kernel_init+0x30/0x134 ret_from_fork+0x10/0x20

-> #1 (icc_lock){+.+.}-{3:3}: __mutex_lock+0xcc/0x3c8 mutex_lock_nested+0x30/0x44 icc_set_bw+0x88/0x2b4 _set_opp_bw+0x8c/0xd8 _set_opp+0x19c/0x300 dev_pm_opp_set_opp+0x84/0x94 a6xx_gmu_resume+0x18c/0x804 a6xx_pm_resume+0xf8/0x234 adreno_runtime_resume+0x2c/0x38 pm_generic_runtime_resume+0x30/0x44 __rpm_callback+0x15c/0x174 rpm_callback+0x78/0x7c rpm_resume+0x318/0x524 __pm_runtime_resume+0x78/0xbc adreno_load_gpu+0xc4/0x17c msm_open+0x50/0x120 drm_file_alloc+0x17c/0x228 drm_open_helper+0x74/0x118 drm_open+0xa0/0x144 drm_stub_open+0xd4/0xe4 chrdev_open+0x1b8/0x1e4 do_dentry_open+0x2f8/0x38c vfs_open+0x34/0x40 path_openat+0x64c/0x7b4 do_filp_open+0x54/0xc4 do_sys_openat2+0x9c/0x100 do_sys_open+0x50/0x7c __arm64_sys_openat+0x28/0x34 invoke_syscall+0x8c/0x128 el0_svc_common.constprop.0+0xa0/0x11c do_el0_svc+0xac/0xbc el0_svc+0x48/0xa0 el0t_64_sync_handler+0xac/0x13c el0t_64_sync+0x190/0x194

-> #0 (&gmu->lock){+.+.}-{3:3}: __lock_acquire+0xe00/0x1060 lock_acquire+0x1e0/0x2f8 __mutex_lock+0xcc/0x3c8 mutex_lock_nested+0x30/0x44 a6xx_pm_resume+0xf0/0x234 adreno_runtime_resume+0x2c/0x38 pm_generic_runtime_resume+0x30/0x44 __rpm_callback+0x15c/0x174 rpm_callback+0x78/0x7c rpm_resume+0x318/0x524 __pm_runtime_resume+0x78/0xbc pm_runtime_get_sync.isra.0+0x14/0x20 msm_gpu_submit+0x58/0x178 msm_job_run+0x78/0x150 drm_sched_main+0x290/0x370 kthread+0xf0/0x100 ret_from_fork+0x10/0x20

other info that might help us debug this:

Chain exists of: &gmu->lock --> mmu_notifier_invalidate_range_start --> dma_fence_map

Possible unsafe locking scenario:

CPU0 CPU1 ---- ---- lock(dma_fence_map); lock(mmu_notifier_invalidate_range_start); lock(dma_fence_map); lock(&gmu->lock);

*** DEADLOCK ***

2 locks held by ring0/132: #0: ffffff8087191170 (&gpu->lock){+.+.}-{3:3}, at: msm_job_run+0x64/0x150 #1: ffffffdb5aee57e8 (dma_fence_map){++++}-{0:0}, at: msm_job_run+0x68/0x150

stack backtrace: CPU: 7 PID: 132 Comm: ring0 Not tainted 6.2.0-rc8-debug+ #554 Hardware name: Google Lazor (rev1 - 2) with LTE (DT) Call trace: dump_backtrace.part.0+0xb4/0xf8 show_stack+0x20/0x38 dump_stack_lvl+0x9c/0xd0 dump_stack+0x18/0x34 print_circular_bug+0x1b4/0x1f0 check_noncircular+0x78/0xac __lock_acquire+0xe00/0x1060 lock_acquire+0x1e0/0x2f8 __mutex_lock+0xcc/0x3c8 mutex_lock_nested+0x30/0x44 a6xx_pm_resume+0xf0/0x234 adreno_runtime_resume+0x2c/0x38 pm_generic_runtime_resume+0x30/0x44 __rpm_callback+0x15c/0x174 rpm_callback+0x78/0x7c rpm_resume+0x318/0x524 __pm_runtime_resume+0x78/0xbc pm_runtime_get_sync.isra.0+0x14/0x20 msm_gpu_submit+0x58/0x178 msm_job_run+0x78/0x150 drm_sched_main+0x290/0x370 kthread+0xf0/0x100 ret_from_fork+0x10/0x20

Signed-off-by: Rob Clark robdclark@chromium.org Link: https://lore.kernel.org/r/20230807171148.210181-7-robdclark@gmail.com Signed-off-by: Georgi Djakov djakov@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/interconnect/core.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 7db6d0fc6ec2e..64d8dcdc41fd8 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -29,6 +29,7 @@ static LIST_HEAD(icc_providers); static int providers_count; static bool synced_state; static DEFINE_MUTEX(icc_lock); +static DEFINE_MUTEX(icc_bw_lock); static struct dentry *icc_debugfs_dir;

static void icc_summary_show_one(struct seq_file *s, struct icc_node *n) @@ -632,7 +633,7 @@ int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw) if (WARN_ON(IS_ERR(path) || !path->num_nodes)) return -EINVAL;

- mutex_lock(&icc_lock); + mutex_lock(&icc_bw_lock);

old_avg = path->reqs[0].avg_bw; old_peak = path->reqs[0].peak_bw; @@ -664,7 +665,7 @@ int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw) apply_constraints(path); }

- mutex_unlock(&icc_lock); + mutex_unlock(&icc_bw_lock);

trace_icc_set_bw_end(path, ret);

@@ -964,6 +965,7 @@ EXPORT_SYMBOL_GPL(icc_link_destroy); void icc_node_add(struct icc_node *node, struct icc_provider *provider) { mutex_lock(&icc_lock); + mutex_lock(&icc_bw_lock);

node->provider = provider; list_add_tail(&node->node_list, &provider->nodes); @@ -989,6 +991,7 @@ void icc_node_add(struct icc_node *node, struct icc_provider *provider) node->avg_bw = 0; node->peak_bw = 0;

+ mutex_unlock(&icc_bw_lock); mutex_unlock(&icc_lock); } EXPORT_SYMBOL_GPL(icc_node_add); @@ -1115,6 +1118,7 @@ void icc_sync_state(struct device *dev) return;

mutex_lock(&icc_lock); + mutex_lock(&icc_bw_lock); synced_state = true; list_for_each_entry(p, &icc_providers, provider_list) { dev_dbg(p->dev, "interconnect provider is in synced state\n");

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: William Zhang william.zhang@broadcom.com

[ Upstream commit 2ec2839a9062db8a592525a3fdabd42dcd9a3a9b ]

v7.2 controller has different ECC level field size and shift in the acc control register than its predecessor and successor controller. It needs to be set specifically.

Fixes: decba6d47869 ("mtd: brcmnand: Add v7.2 controller support") Signed-off-by: William Zhang william.zhang@broadcom.com Reviewed-by: Florian Fainelli florian.fainelli@broadcom.com Cc: stable@vger.kernel.org Signed-off-by: Miquel Raynal miquel.raynal@bootlin.com Link: https://lore.kernel.org/linux-mtd/20230706182909.79151-2-william.zhang@broad... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/mtd/nand/raw/brcmnand/brcmnand.c | 74 +++++++++++++----------- 1 file changed, 41 insertions(+), 33 deletions(-)

diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c index 9ef58194d3a04..11d706ff30dd0 100644 --- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c +++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c @@ -268,6 +268,7 @@ struct brcmnand_controller { const unsigned int *page_sizes; unsigned int page_size_shift; unsigned int max_oob; + u32 ecc_level_shift; u32 features;

/* for low-power standby/resume only */ @@ -592,6 +593,34 @@ enum { INTFC_CTLR_READY = BIT(31), };

+/*********************************************************************** + * NAND ACC CONTROL bitfield + * + * Some bits have remained constant throughout hardware revision, while + * others have shifted around. + ***********************************************************************/ + +/* Constant for all versions (where supported) */ +enum { + /* See BRCMNAND_HAS_CACHE_MODE */ + ACC_CONTROL_CACHE_MODE = BIT(22), + + /* See BRCMNAND_HAS_PREFETCH */ + ACC_CONTROL_PREFETCH = BIT(23), + + ACC_CONTROL_PAGE_HIT = BIT(24), + ACC_CONTROL_WR_PREEMPT = BIT(25), + ACC_CONTROL_PARTIAL_PAGE = BIT(26), + ACC_CONTROL_RD_ERASED = BIT(27), + ACC_CONTROL_FAST_PGM_RDIN = BIT(28), + ACC_CONTROL_WR_ECC = BIT(30), + ACC_CONTROL_RD_ECC = BIT(31), +}; + +#define ACC_CONTROL_ECC_SHIFT 16 +/* Only for v7.2 */ +#define ACC_CONTROL_ECC_EXT_SHIFT 13 + static inline bool brcmnand_non_mmio_ops(struct brcmnand_controller *ctrl) { return static_branch_unlikely(&brcmnand_soc_has_ops_key); @@ -729,6 +758,12 @@ static int brcmnand_revision_init(struct brcmnand_controller *ctrl) else if (of_property_read_bool(ctrl->dev->of_node, "brcm,nand-has-wp")) ctrl->features |= BRCMNAND_HAS_WP;

+ /* v7.2 has different ecc level shift in the acc register */ + if (ctrl->nand_version == 0x0702) + ctrl->ecc_level_shift = ACC_CONTROL_ECC_EXT_SHIFT; + else + ctrl->ecc_level_shift = ACC_CONTROL_ECC_SHIFT; + return 0; }

@@ -917,30 +952,6 @@ static inline int brcmnand_cmd_shift(struct brcmnand_controller *ctrl) return 0; }

-/*********************************************************************** - * NAND ACC CONTROL bitfield - * - * Some bits have remained constant throughout hardware revision, while - * others have shifted around. - ***********************************************************************/ - -/* Constant for all versions (where supported) */ -enum { - /* See BRCMNAND_HAS_CACHE_MODE */ - ACC_CONTROL_CACHE_MODE = BIT(22), - - /* See BRCMNAND_HAS_PREFETCH */ - ACC_CONTROL_PREFETCH = BIT(23), - - ACC_CONTROL_PAGE_HIT = BIT(24), - ACC_CONTROL_WR_PREEMPT = BIT(25), - ACC_CONTROL_PARTIAL_PAGE = BIT(26), - ACC_CONTROL_RD_ERASED = BIT(27), - ACC_CONTROL_FAST_PGM_RDIN = BIT(28), - ACC_CONTROL_WR_ECC = BIT(30), - ACC_CONTROL_RD_ECC = BIT(31), -}; - static inline u32 brcmnand_spare_area_mask(struct brcmnand_controller *ctrl) { if (ctrl->nand_version == 0x0702) @@ -953,18 +964,15 @@ static inline u32 brcmnand_spare_area_mask(struct brcmnand_controller *ctrl) return GENMASK(4, 0); }

-#define NAND_ACC_CONTROL_ECC_SHIFT 16 -#define NAND_ACC_CONTROL_ECC_EXT_SHIFT 13 - static inline u32 brcmnand_ecc_level_mask(struct brcmnand_controller *ctrl) { u32 mask = (ctrl->nand_version >= 0x0600) ? 0x1f : 0x0f;

- mask <<= NAND_ACC_CONTROL_ECC_SHIFT; + mask <<= ACC_CONTROL_ECC_SHIFT;

/* v7.2 includes additional ECC levels */ - if (ctrl->nand_version >= 0x0702) - mask |= 0x7 << NAND_ACC_CONTROL_ECC_EXT_SHIFT; + if (ctrl->nand_version == 0x0702) + mask |= 0x7 << ACC_CONTROL_ECC_EXT_SHIFT;

return mask; } @@ -978,8 +986,8 @@ static void brcmnand_set_ecc_enabled(struct brcmnand_host *host, int en)

if (en) { acc_control |= ecc_flags; /* enable RD/WR ECC */ - acc_control |= host->hwcfg.ecc_level - << NAND_ACC_CONTROL_ECC_SHIFT; + acc_control &= ~brcmnand_ecc_level_mask(ctrl); + acc_control |= host->hwcfg.ecc_level << ctrl->ecc_level_shift; } else { acc_control &= ~ecc_flags; /* disable RD/WR ECC */ acc_control &= ~brcmnand_ecc_level_mask(ctrl); @@ -2533,7 +2541,7 @@ static int brcmnand_set_cfg(struct brcmnand_host *host, tmp &= ~brcmnand_ecc_level_mask(ctrl); tmp &= ~brcmnand_spare_area_mask(ctrl); if (ctrl->nand_version >= 0x0302) { - tmp |= cfg->ecc_level << NAND_ACC_CONTROL_ECC_SHIFT; + tmp |= cfg->ecc_level << ctrl->ecc_level_shift; tmp |= cfg->spare_area_size; } nand_writereg(ctrl, acc_control_offs, tmp);

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Ian Rogers irogers@google.com

[ Upstream commit 0d1c50ac488ebdaeeaea8ed5069f8d435fd485ed ]

Some distributions, like debian, don't link perf with libbfd. Add a build flag to make this configuration buildable and testable.

This was inspired by:

https://lore.kernel.org/linux-perf-users/20210910102307.2055484-1-tonyg@leas...

Signed-off-by: Ian Rogers irogers@google.com Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Jiri Olsa jolsa@redhat.com Cc: Mark Rutland mark.rutland@arm.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: tony garnock-jones tonyg@leastfixedpoint.com Link: http://lore.kernel.org/lkml/20210910225756.729087-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Stable-dep-of: 7822a8913f4c ("perf build: Update build rule for generated files") Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/Makefile.config | 47 ++++++++++++++++++++------------------ 1 file changed, 25 insertions(+), 22 deletions(-)

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 3e7706c251e9e..89905b4e93091 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -824,33 +824,36 @@ else endif endif

-ifeq ($(feature-libbfd), 1) - EXTLIBS += -lbfd -lopcodes -else - # we are on a system that requires -liberty and (maybe) -lz - # to link against -lbfd; test each case individually here - - # call all detections now so we get correct - # status in VF output - $(call feature_check,libbfd-liberty) - $(call feature_check,libbfd-liberty-z)

- ifeq ($(feature-libbfd-liberty), 1) - EXTLIBS += -lbfd -lopcodes -liberty - FEATURE_CHECK_LDFLAGS-disassembler-four-args += -liberty -ldl +ifndef NO_LIBBFD + ifeq ($(feature-libbfd), 1) + EXTLIBS += -lbfd -lopcodes else - ifeq ($(feature-libbfd-liberty-z), 1) - EXTLIBS += -lbfd -lopcodes -liberty -lz - FEATURE_CHECK_LDFLAGS-disassembler-four-args += -liberty -lz -ldl + # we are on a system that requires -liberty and (maybe) -lz + # to link against -lbfd; test each case individually here + + # call all detections now so we get correct + # status in VF output + $(call feature_check,libbfd-liberty) + $(call feature_check,libbfd-liberty-z) + + ifeq ($(feature-libbfd-liberty), 1) + EXTLIBS += -lbfd -lopcodes -liberty + FEATURE_CHECK_LDFLAGS-disassembler-four-args += -liberty -ldl + else + ifeq ($(feature-libbfd-liberty-z), 1) + EXTLIBS += -lbfd -lopcodes -liberty -lz + FEATURE_CHECK_LDFLAGS-disassembler-four-args += -liberty -lz -ldl + endif endif + $(call feature_check,disassembler-four-args) endif - $(call feature_check,disassembler-four-args) -endif

-ifeq ($(feature-libbfd-buildid), 1) - CFLAGS += -DHAVE_LIBBFD_BUILDID_SUPPORT -else - msg := $(warning Old version of libbfd/binutils things like PE executable profiling will not be available); + ifeq ($(feature-libbfd-buildid), 1) + CFLAGS += -DHAVE_LIBBFD_BUILDID_SUPPORT + else + msg := $(warning Old version of libbfd/binutils things like PE executable profiling will not be available); + endif endif

ifdef NO_DEMANGLE

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Namhyung Kim namhyung@kernel.org

[ Upstream commit 7822a8913f4c51c7d1aff793b525d60c3384fb5b ]

The bison and flex generate C files from the source (.y and .l) files. When O= option is used, they are saved in a separate directory but the default build rule assumes the .C files are in the source directory. So it might read invalid file if there are generated files from an old version. The same is true for the pmu-events files.

For example, the following command would cause a build failure:

$ git checkout v6.3 $ make -C tools/perf # build in the same directory

$ git checkout v6.5-rc2 $ mkdir build # create a build directory $ make -C tools/perf O=build # build in a different directory but it # refers files in the source directory

Let's update the build rule to specify those cases explicitly to depend on the files in the output directory.

Note that it's not a complete fix and it needs the next patch for the include path too.

Fixes: 80eeb67fe577aa76 ("perf jevents: Program to convert JSON file") Signed-off-by: Namhyung Kim namhyung@kernel.org Cc: Adrian Hunter adrian.hunter@intel.com Cc: Andi Kleen ak@linux.intel.com Cc: Anup Sharma anupnewsmail@gmail.com Cc: Ian Rogers irogers@google.com Cc: Ingo Molnar mingo@kernel.org Cc: Jiri Olsa jolsa@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230728022447.1323563-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/build/Makefile.build | 10 ++++++++++ tools/perf/pmu-events/Build | 6 ++++++ 2 files changed, 16 insertions(+)

diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build index cd72016c3cfa7..5a727094ae832 100644 --- a/tools/build/Makefile.build +++ b/tools/build/Makefile.build @@ -116,6 +116,16 @@ $(OUTPUT)%.s: %.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_s_c)

+# bison and flex files are generated in the OUTPUT directory +# so it needs a separate rule to depend on them properly +$(OUTPUT)%-bison.o: $(OUTPUT)%-bison.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,$(host)cc_o_c) + +$(OUTPUT)%-flex.o: $(OUTPUT)%-flex.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,$(host)cc_o_c) + # Gather build data: # obj-y - list of build objects # subdir-y - list of directories to nest diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build index 5ec5ce8c31bab..ea8c41f9c7398 100644 --- a/tools/perf/pmu-events/Build +++ b/tools/perf/pmu-events/Build @@ -25,3 +25,9 @@ $(OUTPUT)pmu-events/pmu-events.c: $(JSON) $(JSON_TEST) $(JEVENTS_PY) $(call rule_mkdir) $(Q)$(call echo-cmd,gen)$(PYTHON) $(JEVENTS_PY) $(SRCARCH) pmu-events/arch $@ endif + +# pmu-events.c file is generated in the OUTPUT directory so it needs a +# separate rule to depend on it properly +$(OUTPUT)pmu-events/pmu-events.o: $(PMU_EVENTS_C) + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c)

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Anand Jain anand.jain@oracle.com

[ Upstream commit 4844c3664a72d36cc79752cb651c78860b14c240 ]

In some cases, we need to read the FSID from the superblock when the metadata_uuid is not set, and otherwise, read the metadata_uuid. So, add a helper.

Reviewed-by: Johannes Thumshirn johannes.thumshirn@wdc.com Tested-by: Guilherme G. Piccoli gpiccoli@igalia.com Signed-off-by: Anand Jain anand.jain@oracle.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Stable-dep-of: 6bfe3959b0e7 ("btrfs: compare the correct fsid/metadata_uuid in btrfs_validate_super") Signed-off-by: Sasha Levin sashal@kernel.org --- fs/btrfs/volumes.c | 8 ++++++++ fs/btrfs/volumes.h | 1 + 2 files changed, 9 insertions(+)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index b798586263ebb..86c50e0570a5e 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -718,6 +718,14 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, return -EINVAL; }

+u8 *btrfs_sb_fsid_ptr(struct btrfs_super_block *sb) +{ + bool has_metadata_uuid = (btrfs_super_incompat_flags(sb) & + BTRFS_FEATURE_INCOMPAT_METADATA_UUID); + + return has_metadata_uuid ? sb->metadata_uuid : sb->fsid; +} + /* * Handle scanned device having its CHANGING_FSID_V2 flag set and the fs_devices * being created with a disk that has already completed its fsid change. Such diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 2463aeb34ab55..b2046e92b9143 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -581,5 +581,6 @@ const char *btrfs_bg_type_to_raid_name(u64 flags); int btrfs_verify_dev_extents(struct btrfs_fs_info *fs_info);

bool btrfs_pinned_by_swapfile(struct btrfs_fs_info *fs_info, void *ptr); +u8 *btrfs_sb_fsid_ptr(struct btrfs_super_block *sb);

#endif

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Jinjie Ruan ruanjinjie@huawei.com

[ Upstream commit 7583028d359db3cd0072badcc576b4f9455fd27a ]

The timeout arg of usb_bulk_msg() is ms already, which has been converted to jiffies by msecs_to_jiffies() in usb_start_wait_urb(). So fix the usage by removing the redundant msecs_to_jiffies() in the macros.

And as Hans suggested, also remove msecs_to_jiffies() for the IDLE_TIMEOUT macro to make it consistent here and so change IDLE_TIMEOUT to msecs_to_jiffies(IDLE_TIMEOUT) where it is used.

Fixes: e4f86e437164 ("drm: Add Grain Media GM12U320 driver v2") Signed-off-by: Jinjie Ruan ruanjinjie@huawei.com Suggested-by: Hans de Goede hdegoede@redhat.com Reviewed-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Thomas Zimmermann tzimmermann@suse.de Link: https://patchwork.freedesktop.org/patch/msgid/20230904021421.1663892-1-ruanj... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/tiny/gm12u320.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/tiny/gm12u320.c b/drivers/gpu/drm/tiny/gm12u320.c index 0f5d1e598d75f..1656f3ee0b193 100644 --- a/drivers/gpu/drm/tiny/gm12u320.c +++ b/drivers/gpu/drm/tiny/gm12u320.c @@ -67,10 +67,10 @@ MODULE_PARM_DESC(eco_mode, "Turn on Eco mode (less bright, more silent)"); #define READ_STATUS_SIZE 13 #define MISC_VALUE_SIZE 4

-#define CMD_TIMEOUT msecs_to_jiffies(200) -#define DATA_TIMEOUT msecs_to_jiffies(1000) -#define IDLE_TIMEOUT msecs_to_jiffies(2000) -#define FIRST_FRAME_TIMEOUT msecs_to_jiffies(2000) +#define CMD_TIMEOUT 200 +#define DATA_TIMEOUT 1000 +#define IDLE_TIMEOUT 2000 +#define FIRST_FRAME_TIMEOUT 2000

#define MISC_REQ_GET_SET_ECO_A 0xff #define MISC_REQ_GET_SET_ECO_B 0x35 @@ -399,7 +399,7 @@ static void gm12u320_fb_update_work(struct work_struct *work) * switches back to showing its logo. */ queue_delayed_work(system_long_wq, &gm12u320->fb_update.work, - IDLE_TIMEOUT); + msecs_to_jiffies(IDLE_TIMEOUT));

return; err:

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Masami Hiramatsu (Google) mhiramat@kernel.org

[ Upstream commit 7e021da80f48582171029714f8a487347f29dddb ]

Fix to unmount the tracefs if the ftracetest mounted it for recovering system environment. If the tracefs is already mounted, this does nothing.

Suggested-by: Mark Brown broonie@kernel.org Link: https://lore.kernel.org/all/29fce076-746c-4650-8358-b4e0fa215cf7@sirena.org.... Fixes: cbd965bde74c ("ftrace/selftests: Return the skip code when tracing directory not configured in kernel") Signed-off-by: Masami Hiramatsu (Google) mhiramat@kernel.org Reviewed-by: Steven Rostedt (Google) rostedt@goodmis.org Reviewed-by: Mark Brown broonie@kernel.org Signed-off-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/ftrace/ftracetest | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index 8ec1922e974eb..55314cd197ab9 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -30,6 +30,9 @@ err_ret=1 # kselftest skip code is 4 err_skip=4

+# umount required +UMOUNT_DIR="" + # cgroup RT scheduling prevents chrt commands from succeeding, which # induces failures in test wakeup tests. Disable for the duration of # the tests. @@ -44,6 +47,9 @@ setup() {

cleanup() { echo $sched_rt_runtime_orig > $sched_rt_runtime + if [ -n "${UMOUNT_DIR}" ]; then + umount ${UMOUNT_DIR} ||: + fi }

errexit() { # message @@ -155,11 +161,13 @@ if [ -z "$TRACING_DIR" ]; then mount -t tracefs nodev /sys/kernel/tracing || errexit "Failed to mount /sys/kernel/tracing" TRACING_DIR="/sys/kernel/tracing" + UMOUNT_DIR=${TRACING_DIR} # If debugfs exists, then so does /sys/kernel/debug elif [ -d "/sys/kernel/debug" ]; then mount -t debugfs nodev /sys/kernel/debug || errexit "Failed to mount /sys/kernel/debug" TRACING_DIR="/sys/kernel/debug/tracing" + UMOUNT_DIR=${TRACING_DIR} else err_ret=$err_skip errexit "debugfs and tracefs are not configured in this kernel"

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Kirill A. Shutemov kirill.shutemov@linux.intel.com

[ Upstream commit f530ee95b72e77b09c141c4b1a4b94d1199ffbd9 ]

The decompressor has a hard limit on the number of page tables it can allocate. This limit is defined at compile-time and will cause boot failure if it is reached.

The kernel is very strict and calculates the limit precisely for the worst-case scenario based on the current configuration. However, it is easy to forget to adjust the limit when a new use-case arises. The worst-case scenario is rarely encountered during sanity checks.

In the case of enabling 5-level paging, a use-case was overlooked. The limit needs to be increased by one to accommodate the additional level. This oversight went unnoticed until Aaron attempted to run the kernel via kexec with 5-level paging and unaccepted memory enabled.

Update wost-case calculations to include 5-level paging.

To address this issue, let's allocate some extra space for page tables. 128K should be sufficient for any use-case. The logic can be simplified by using a single value for all kernel configurations.

[ Also add a warning, should this memory run low - by Dave Hansen. ]

Fixes: 34bbb0009f3b ("x86/boot/compressed: Enable 5-level paging during decompression stage") Reported-by: Aaron Lu aaron.lu@intel.com Signed-off-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Signed-off-by: Ingo Molnar mingo@kernel.org Link: https://lore.kernel.org/r/20230915070221.10266-1-kirill.shutemov@linux.intel... Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/boot/compressed/ident_map_64.c | 8 +++++ arch/x86/include/asm/boot.h | 45 +++++++++++++++++-------- 2 files changed, 39 insertions(+), 14 deletions(-)

diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index 39b2eded7bc2b..f4a2e6d373b29 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -67,6 +67,14 @@ static void *alloc_pgt_page(void *context) return NULL; }

+ /* Consumed more tables than expected? */ + if (pages->pgt_buf_offset == BOOT_PGT_SIZE_WARN) { + debug_putstr("pgt_buf running low in " __FILE__ "\n"); + debug_putstr("Need to raise BOOT_PGT_SIZE?\n"); + debug_putaddr(pages->pgt_buf_offset); + debug_putaddr(pages->pgt_buf_size); + } + entry = pages->pgt_buf + pages->pgt_buf_offset; pages->pgt_buf_offset += PAGE_SIZE;

diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index 9191280d9ea31..215d37f7dde8a 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -40,23 +40,40 @@ #ifdef CONFIG_X86_64 # define BOOT_STACK_SIZE 0x4000

+/* + * Used by decompressor's startup_32() to allocate page tables for identity + * mapping of the 4G of RAM in 4-level paging mode: + * - 1 level4 table; + * - 1 level3 table; + * - 4 level2 table that maps everything with 2M pages; + * + * The additional level5 table needed for 5-level paging is allocated from + * trampoline_32bit memory. + */ # define BOOT_INIT_PGT_SIZE (6*4096) -# ifdef CONFIG_RANDOMIZE_BASE + /* - * Assuming all cross the 512GB boundary: - * 1 page for level4 - * (2+2)*4 pages for kernel, param, cmd_line, and randomized kernel - * 2 pages for first 2M (video RAM: CONFIG_X86_VERBOSE_BOOTUP). - * Total is 19 pages. + * Total number of page tables kernel_add_identity_map() can allocate, + * including page tables consumed by startup_32(). + * + * Worst-case scenario: + * - 5-level paging needs 1 level5 table; + * - KASLR needs to map kernel, boot_params, cmdline and randomized kernel, + * assuming all of them cross 256T boundary: + * + 4*2 level4 table; + * + 4*2 level3 table; + * + 4*2 level2 table; + * - X86_VERBOSE_BOOTUP needs to map the first 2M (video RAM): + * + 1 level4 table; + * + 1 level3 table; + * + 1 level2 table; + * Total: 28 tables + * + * Add 4 spare table in case decompressor touches anything beyond what is + * accounted above. Warn if it happens. */ -# ifdef CONFIG_X86_VERBOSE_BOOTUP -# define BOOT_PGT_SIZE (19*4096) -# else /* !CONFIG_X86_VERBOSE_BOOTUP */ -# define BOOT_PGT_SIZE (17*4096) -# endif -# else /* !CONFIG_RANDOMIZE_BASE */ -# define BOOT_PGT_SIZE BOOT_INIT_PGT_SIZE -# endif +# define BOOT_PGT_SIZE_WARN (28*4096) +# define BOOT_PGT_SIZE (32*4096)

#else /* !CONFIG_X86_64 */ # define BOOT_STACK_SIZE 0x1000

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Nigel Croxon ncroxon@redhat.com

[ Upstream commit df203da47f4428bc286fc99318936416253a321c ]

There is a compile error when this commit is added: md: raid1: fix potential OOB in raid1_remove_disk()

drivers/md/raid1.c: In function 'raid1_remove_disk': drivers/md/raid1.c:1844:9: error: ISO C90 forbids mixed declarations and code [-Werror=declaration-after-statement] 1844 |         struct raid1_info *p = conf->mirrors + number;     |         ^~~~~~

That's because the new code was inserted before the struct. The change is move the struct command above this commit.

Fixes: 8b0472b50bcf ("md: raid1: fix potential OOB in raid1_remove_disk()") Signed-off-by: Nigel Croxon ncroxon@redhat.com Signed-off-by: Song Liu song@kernel.org Link: https://lore.kernel.org/r/46d929d0-2aab-4cf2-b2bf-338963e8ba5a@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/md/raid1.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 25be491c1a6ac..3619db7e382a0 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1791,12 +1791,11 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev) struct r1conf *conf = mddev->private; int err = 0; int number = rdev->raid_disk; + struct raid1_info *p = conf->mirrors + number;

if (unlikely(number >= conf->raid_disks)) goto abort;

- struct raid1_info *p = conf->mirrors + number; - if (rdev != p->rdev) p = conf->mirrors + conf->raid_disks + number;

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Amir Goldstein amir73il@gmail.com

commit 724768a39374d35b70eaeae8dd87048a2ec7ae8e upstream.

ovl_{read,write}_iter() always call fdput(real) to put one or zero refcounts of the real file, but for aio, whether it was submitted or not, ovl_aio_put() also calls fdput(), which is not balanced. This is only a problem in the less common case when FDPUT_FPUT flag is set.

To fix the problem use get_file() to take file refcount and use fput() instead of fdput() in ovl_aio_put().

Fixes: 2406a307ac7d ("ovl: implement async IO routines") Cc: stable@vger.kernel.org # v5.6 Reviewed-by: Miklos Szeredi miklos@szeredi.hu Signed-off-by: Amir Goldstein amir73il@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/overlayfs/file.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-)

--- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -19,7 +19,6 @@ struct ovl_aio_req { struct kiocb iocb; refcount_t ref; struct kiocb *orig_iocb; - struct fd fd; };

static struct kmem_cache *ovl_aio_request_cachep; @@ -261,7 +260,7 @@ static rwf_t ovl_iocb_to_rwf(int ifl) static inline void ovl_aio_put(struct ovl_aio_req *aio_req) { if (refcount_dec_and_test(&aio_req->ref)) { - fdput(aio_req->fd); + fput(aio_req->iocb.ki_filp); kmem_cache_free(ovl_aio_request_cachep, aio_req); } } @@ -327,10 +326,9 @@ static ssize_t ovl_read_iter(struct kioc if (!aio_req) goto out;

- aio_req->fd = real; real.flags = 0; aio_req->orig_iocb = iocb; - kiocb_clone(&aio_req->iocb, iocb, real.file); + kiocb_clone(&aio_req->iocb, iocb, get_file(real.file)); aio_req->iocb.ki_complete = ovl_aio_rw_complete; refcount_set(&aio_req->ref, 2); ret = vfs_iocb_iter_read(real.file, &aio_req->iocb, iter); @@ -399,10 +397,9 @@ static ssize_t ovl_write_iter(struct kio /* Pacify lockdep, same trick as done in aio_write() */ __sb_writers_release(file_inode(real.file)->i_sb, SB_FREEZE_WRITE); - aio_req->fd = real; real.flags = 0; aio_req->orig_iocb = iocb; - kiocb_clone(&aio_req->iocb, iocb, real.file); + kiocb_clone(&aio_req->iocb, iocb, get_file(real.file)); aio_req->iocb.ki_flags = ifl; aio_req->iocb.ki_complete = ovl_aio_rw_complete; refcount_set(&aio_req->ref, 2);

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Filipe Manana fdmanana@suse.com

commit ee34a82e890a7babb5585daf1a6dd7d4d1cf142a upstream.

During the ino lookup ioctl we can end up calling btrfs_iget() to get an inode reference while we are holding on a root's btree. If btrfs_iget() needs to lookup the inode from the root's btree, because it's not currently loaded in memory, then it will need to lock another or the same path in the same root btree. This may result in a deadlock and trigger the following lockdep splat:

WARNING: possible circular locking dependency detected 6.5.0-rc7-syzkaller-00004-gf7757129e3de #0 Not tainted ------------------------------------------------------ syz-executor277/5012 is trying to acquire lock: ffff88802df41710 (btrfs-tree-01){++++}-{3:3}, at: __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136

but task is already holding lock: ffff88802df418e8 (btrfs-tree-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #1 (btrfs-tree-00){++++}-{3:3}: down_read_nested+0x49/0x2f0 kernel/locking/rwsem.c:1645 __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136 btrfs_search_slot+0x13a4/0x2f80 fs/btrfs/ctree.c:2302 btrfs_init_root_free_objectid+0x148/0x320 fs/btrfs/disk-io.c:4955 btrfs_init_fs_root fs/btrfs/disk-io.c:1128 [inline] btrfs_get_root_ref+0x5ae/0xae0 fs/btrfs/disk-io.c:1338 btrfs_get_fs_root fs/btrfs/disk-io.c:1390 [inline] open_ctree+0x29c8/0x3030 fs/btrfs/disk-io.c:3494 btrfs_fill_super+0x1c7/0x2f0 fs/btrfs/super.c:1154 btrfs_mount_root+0x7e0/0x910 fs/btrfs/super.c:1519 legacy_get_tree+0xef/0x190 fs/fs_context.c:611 vfs_get_tree+0x8c/0x270 fs/super.c:1519 fc_mount fs/namespace.c:1112 [inline] vfs_kern_mount+0xbc/0x150 fs/namespace.c:1142 btrfs_mount+0x39f/0xb50 fs/btrfs/super.c:1579 legacy_get_tree+0xef/0x190 fs/fs_context.c:611 vfs_get_tree+0x8c/0x270 fs/super.c:1519 do_new_mount+0x28f/0xae0 fs/namespace.c:3335 do_mount fs/namespace.c:3675 [inline] __do_sys_mount fs/namespace.c:3884 [inline] __se_sys_mount+0x2d9/0x3c0 fs/namespace.c:3861 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

-> #0 (btrfs-tree-01){++++}-{3:3}: check_prev_add kernel/locking/lockdep.c:3142 [inline] check_prevs_add kernel/locking/lockdep.c:3261 [inline] validate_chain kernel/locking/lockdep.c:3876 [inline] __lock_acquire+0x39ff/0x7f70 kernel/locking/lockdep.c:5144 lock_acquire+0x1e3/0x520 kernel/locking/lockdep.c:5761 down_read_nested+0x49/0x2f0 kernel/locking/rwsem.c:1645 __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136 btrfs_tree_read_lock fs/btrfs/locking.c:142 [inline] btrfs_read_lock_root_node+0x292/0x3c0 fs/btrfs/locking.c:281 btrfs_search_slot_get_root fs/btrfs/ctree.c:1832 [inline] btrfs_search_slot+0x4ff/0x2f80 fs/btrfs/ctree.c:2154 btrfs_lookup_inode+0xdc/0x480 fs/btrfs/inode-item.c:412 btrfs_read_locked_inode fs/btrfs/inode.c:3892 [inline] btrfs_iget_path+0x2d9/0x1520 fs/btrfs/inode.c:5716 btrfs_search_path_in_tree_user fs/btrfs/ioctl.c:1961 [inline] btrfs_ioctl_ino_lookup_user+0x77a/0xf50 fs/btrfs/ioctl.c:2105 btrfs_ioctl+0xb0b/0xd40 fs/btrfs/ioctl.c:4683 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl+0xf8/0x170 fs/ioctl.c:856 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

other info that might help us debug this:

Possible unsafe locking scenario:

CPU0 CPU1 ---- ---- rlock(btrfs-tree-00); lock(btrfs-tree-01); lock(btrfs-tree-00); rlock(btrfs-tree-01);

*** DEADLOCK ***

1 lock held by syz-executor277/5012: #0: ffff88802df418e8 (btrfs-tree-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136

stack backtrace: CPU: 1 PID: 5012 Comm: syz-executor277 Not tainted 6.5.0-rc7-syzkaller-00004-gf7757129e3de #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1e7/0x2d0 lib/dump_stack.c:106 check_noncircular+0x375/0x4a0 kernel/locking/lockdep.c:2195 check_prev_add kernel/locking/lockdep.c:3142 [inline] check_prevs_add kernel/locking/lockdep.c:3261 [inline] validate_chain kernel/locking/lockdep.c:3876 [inline] __lock_acquire+0x39ff/0x7f70 kernel/locking/lockdep.c:5144 lock_acquire+0x1e3/0x520 kernel/locking/lockdep.c:5761 down_read_nested+0x49/0x2f0 kernel/locking/rwsem.c:1645 __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136 btrfs_tree_read_lock fs/btrfs/locking.c:142 [inline] btrfs_read_lock_root_node+0x292/0x3c0 fs/btrfs/locking.c:281 btrfs_search_slot_get_root fs/btrfs/ctree.c:1832 [inline] btrfs_search_slot+0x4ff/0x2f80 fs/btrfs/ctree.c:2154 btrfs_lookup_inode+0xdc/0x480 fs/btrfs/inode-item.c:412 btrfs_read_locked_inode fs/btrfs/inode.c:3892 [inline] btrfs_iget_path+0x2d9/0x1520 fs/btrfs/inode.c:5716 btrfs_search_path_in_tree_user fs/btrfs/ioctl.c:1961 [inline] btrfs_ioctl_ino_lookup_user+0x77a/0xf50 fs/btrfs/ioctl.c:2105 btrfs_ioctl+0xb0b/0xd40 fs/btrfs/ioctl.c:4683 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl+0xf8/0x170 fs/ioctl.c:856 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: 0033:0x7f0bec94ea39

Fix this simply by releasing the path before calling btrfs_iget() as at point we don't need the path anymore.

Reported-by: syzbot+bf66ad948981797d2f1d@syzkaller.appspotmail.com Link: https://lore.kernel.org/linux-btrfs/00000000000045fa140603c4a969@google.com/ Fixes: 23d0b79dfaed ("btrfs: Add unprivileged version of ino_lookup ioctl") CC: stable@vger.kernel.org # 4.19+ Reviewed-by: Josef Bacik josef@toxicpanda.com Signed-off-by: Filipe Manana fdmanana@suse.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/btrfs/ioctl.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

--- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2550,6 +2550,13 @@ static int btrfs_search_path_in_tree_use goto out_put; }

+ /* + * We don't need the path anymore, so release it and + * avoid deadlocks and lockdep warnings in case + * btrfs_iget() needs to lookup the inode from its root + * btree and lock the same leaf. + */ + btrfs_release_path(path); temp_inode = btrfs_iget(sb, key2.objectid, root); if (IS_ERR(temp_inode)) { ret = PTR_ERR(temp_inode); @@ -2569,7 +2576,6 @@ static int btrfs_search_path_in_tree_use goto out_put; }

- btrfs_release_path(path); key.objectid = key.offset; key.offset = (u64)-1; dirid = key.objectid;

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Jamal Hadi Salim jhs@mojatatu.com

commit 265b4da82dbf5df04bee5a5d46b7474b1aaf326a upstream.

The rsvp classifier has served us well for about a quarter of a century but has has not been getting much maintenance attention due to lack of known users.

Signed-off-by: Jamal Hadi Salim jhs@mojatatu.com Acked-by: Jiri Pirko jiri@nvidia.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Kyle Zeng zengyhkyle@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/sched/Kconfig | 28 - net/sched/Makefile | 2 net/sched/cls_rsvp.c | 24 - net/sched/cls_rsvp.h | 777 -------------------------------------------------- net/sched/cls_rsvp6.c | 24 - 5 files changed, 855 deletions(-)

--- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -548,34 +548,6 @@ config CLS_U32_MARK help Say Y here to be able to use netfilter marks as u32 key.

-config NET_CLS_RSVP - tristate "IPv4 Resource Reservation Protocol (RSVP)" - select NET_CLS - help - The Resource Reservation Protocol (RSVP) permits end systems to - request a minimum and maximum data flow rate for a connection; this - is important for real time data such as streaming sound or video. - - Say Y here if you want to be able to classify outgoing packets based - on their RSVP requests. - - To compile this code as a module, choose M here: the - module will be called cls_rsvp. - -config NET_CLS_RSVP6 - tristate "IPv6 Resource Reservation Protocol (RSVP6)" - select NET_CLS - help - The Resource Reservation Protocol (RSVP) permits end systems to - request a minimum and maximum data flow rate for a connection; this - is important for real time data such as streaming sound or video. - - Say Y here if you want to be able to classify outgoing packets based - on their RSVP requests and you are using the IPv6 protocol. - - To compile this code as a module, choose M here: the - module will be called cls_rsvp6. - config NET_CLS_FLOW tristate "Flow classifier" select NET_CLS --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -68,8 +68,6 @@ obj-$(CONFIG_NET_SCH_TAPRIO) += sch_tapr obj-$(CONFIG_NET_CLS_U32) += cls_u32.o obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o obj-$(CONFIG_NET_CLS_FW) += cls_fw.o -obj-$(CONFIG_NET_CLS_RSVP) += cls_rsvp.o -obj-$(CONFIG_NET_CLS_RSVP6) += cls_rsvp6.o obj-$(CONFIG_NET_CLS_BASIC) += cls_basic.o obj-$(CONFIG_NET_CLS_FLOW) += cls_flow.o obj-$(CONFIG_NET_CLS_CGROUP) += cls_cgroup.o --- a/net/sched/cls_rsvp.c +++ /dev/null @@ -1,24 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * net/sched/cls_rsvp.c Special RSVP packet classifier for IPv4. - * - * Authors: Alexey Kuznetsov, kuznet@ms2.inr.ac.ru - */ - -#include <linux/module.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/skbuff.h> -#include <net/ip.h> -#include <net/netlink.h> -#include <net/act_api.h> -#include <net/pkt_cls.h> - -#define RSVP_DST_LEN 1 -#define RSVP_ID "rsvp" -#define RSVP_OPS cls_rsvp_ops - -#include "cls_rsvp.h" -MODULE_LICENSE("GPL"); --- a/net/sched/cls_rsvp.h +++ /dev/null @@ -1,777 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * net/sched/cls_rsvp.h Template file for RSVPv[46] classifiers. - * - * Authors: Alexey Kuznetsov, kuznet@ms2.inr.ac.ru - */ - -/* - Comparing to general packet classification problem, - RSVP needs only sevaral relatively simple rules: - - * (dst, protocol) are always specified, - so that we are able to hash them. - * src may be exact, or may be wildcard, so that - we can keep a hash table plus one wildcard entry. - * source port (or flow label) is important only if src is given. - - IMPLEMENTATION. - - We use a two level hash table: The top level is keyed by - destination address and protocol ID, every bucket contains a list - of "rsvp sessions", identified by destination address, protocol and - DPI(="Destination Port ID"): triple (key, mask, offset). - - Every bucket has a smaller hash table keyed by source address - (cf. RSVP flowspec) and one wildcard entry for wildcard reservations. - Every bucket is again a list of "RSVP flows", selected by - source address and SPI(="Source Port ID" here rather than - "security parameter index"): triple (key, mask, offset). - - - NOTE 1. All the packets with IPv6 extension headers (but AH and ESP) - and all fragmented packets go to the best-effort traffic class. - - - NOTE 2. Two "port id"'s seems to be redundant, rfc2207 requires - only one "Generalized Port Identifier". So that for classic - ah, esp (and udp,tcp) both *pi should coincide or one of them - should be wildcard. - - At first sight, this redundancy is just a waste of CPU - resources. But DPI and SPI add the possibility to assign different - priorities to GPIs. Look also at note 4 about tunnels below. - - - NOTE 3. One complication is the case of tunneled packets. - We implement it as following: if the first lookup - matches a special session with "tunnelhdr" value not zero, - flowid doesn't contain the true flow ID, but the tunnel ID (1...255). - In this case, we pull tunnelhdr bytes and restart lookup - with tunnel ID added to the list of keys. Simple and stupid 8)8) - It's enough for PIMREG and IPIP. - - - NOTE 4. Two GPIs make it possible to parse even GRE packets. - F.e. DPI can select ETH_P_IP (and necessary flags to make - tunnelhdr correct) in GRE protocol field and SPI matches - GRE key. Is it not nice? 8)8) - - - Well, as result, despite its simplicity, we get a pretty - powerful classification engine. */ - - -struct rsvp_head { - u32 tmap[256/32]; - u32 hgenerator; - u8 tgenerator; - struct rsvp_session __rcu *ht[256]; - struct rcu_head rcu; -}; - -struct rsvp_session { - struct rsvp_session __rcu *next; - __be32 dst[RSVP_DST_LEN]; - struct tc_rsvp_gpi dpi; - u8 protocol; - u8 tunnelid; - /* 16 (src,sport) hash slots, and one wildcard source slot */ - struct rsvp_filter __rcu *ht[16 + 1]; - struct rcu_head rcu; -}; - - -struct rsvp_filter { - struct rsvp_filter __rcu *next; - __be32 src[RSVP_DST_LEN]; - struct tc_rsvp_gpi spi; - u8 tunnelhdr; - - struct tcf_result res; - struct tcf_exts exts; - - u32 handle; - struct rsvp_session *sess; - struct rcu_work rwork; -}; - -static inline unsigned int hash_dst(__be32 *dst, u8 protocol, u8 tunnelid) -{ - unsigned int h = (__force __u32)dst[RSVP_DST_LEN - 1]; - - h ^= h>>16; - h ^= h>>8; - return (h ^ protocol ^ tunnelid) & 0xFF; -} - -static inline unsigned int hash_src(__be32 *src) -{ - unsigned int h = (__force __u32)src[RSVP_DST_LEN-1]; - - h ^= h>>16; - h ^= h>>8; - h ^= h>>4; - return h & 0xF; -} - -#define RSVP_APPLY_RESULT() \ -{ \ - int r = tcf_exts_exec(skb, &f->exts, res); \ - if (r < 0) \ - continue; \ - else if (r > 0) \ - return r; \ -} - -static int rsvp_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res) -{ - struct rsvp_head *head = rcu_dereference_bh(tp->root); - struct rsvp_session *s; - struct rsvp_filter *f; - unsigned int h1, h2; - __be32 *dst, *src; - u8 protocol; - u8 tunnelid = 0; - u8 *xprt; -#if RSVP_DST_LEN == 4 - struct ipv6hdr *nhptr; - - if (!pskb_network_may_pull(skb, sizeof(*nhptr))) - return -1; - nhptr = ipv6_hdr(skb); -#else - struct iphdr *nhptr; - - if (!pskb_network_may_pull(skb, sizeof(*nhptr))) - return -1; - nhptr = ip_hdr(skb); -#endif -restart: - -#if RSVP_DST_LEN == 4 - src = &nhptr->saddr.s6_addr32[0]; - dst = &nhptr->daddr.s6_addr32[0]; - protocol = nhptr->nexthdr; - xprt = ((u8 *)nhptr) + sizeof(struct ipv6hdr); -#else - src = &nhptr->saddr; - dst = &nhptr->daddr; - protocol = nhptr->protocol; - xprt = ((u8 *)nhptr) + (nhptr->ihl<<2); - if (ip_is_fragment(nhptr)) - return -1; -#endif - - h1 = hash_dst(dst, protocol, tunnelid); - h2 = hash_src(src); - - for (s = rcu_dereference_bh(head->ht[h1]); s; - s = rcu_dereference_bh(s->next)) { - if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN - 1] && - protocol == s->protocol && - !(s->dpi.mask & - (*(u32 *)(xprt + s->dpi.offset) ^ s->dpi.key)) && -#if RSVP_DST_LEN == 4 - dst[0] == s->dst[0] && - dst[1] == s->dst[1] && - dst[2] == s->dst[2] && -#endif - tunnelid == s->tunnelid) { - - for (f = rcu_dereference_bh(s->ht[h2]); f; - f = rcu_dereference_bh(f->next)) { - if (src[RSVP_DST_LEN-1] == f->src[RSVP_DST_LEN - 1] && - !(f->spi.mask & (*(u32 *)(xprt + f->spi.offset) ^ f->spi.key)) -#if RSVP_DST_LEN == 4 - && - src[0] == f->src[0] && - src[1] == f->src[1] && - src[2] == f->src[2] -#endif - ) { - *res = f->res; - RSVP_APPLY_RESULT(); - -matched: - if (f->tunnelhdr == 0) - return 0; - - tunnelid = f->res.classid; - nhptr = (void *)(xprt + f->tunnelhdr - sizeof(*nhptr)); - goto restart; - } - } - - /* And wildcard bucket... */ - for (f = rcu_dereference_bh(s->ht[16]); f; - f = rcu_dereference_bh(f->next)) { - *res = f->res; - RSVP_APPLY_RESULT(); - goto matched; - } - return -1; - } - } - return -1; -} - -static void rsvp_replace(struct tcf_proto *tp, struct rsvp_filter *n, u32 h) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - struct rsvp_session *s; - struct rsvp_filter __rcu **ins; - struct rsvp_filter *pins; - unsigned int h1 = h & 0xFF; - unsigned int h2 = (h >> 8) & 0xFF; - - for (s = rtnl_dereference(head->ht[h1]); s; - s = rtnl_dereference(s->next)) { - for (ins = &s->ht[h2], pins = rtnl_dereference(*ins); ; - ins = &pins->next, pins = rtnl_dereference(*ins)) { - if (pins->handle == h) { - RCU_INIT_POINTER(n->next, pins->next); - rcu_assign_pointer(*ins, n); - return; - } - } - } - - /* Something went wrong if we are trying to replace a non-existant - * node. Mind as well halt instead of silently failing. - */ - BUG_ON(1); -} - -static void *rsvp_get(struct tcf_proto *tp, u32 handle) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - struct rsvp_session *s; - struct rsvp_filter *f; - unsigned int h1 = handle & 0xFF; - unsigned int h2 = (handle >> 8) & 0xFF; - - if (h2 > 16) - return NULL; - - for (s = rtnl_dereference(head->ht[h1]); s; - s = rtnl_dereference(s->next)) { - for (f = rtnl_dereference(s->ht[h2]); f; - f = rtnl_dereference(f->next)) { - if (f->handle == handle) - return f; - } - } - return NULL; -} - -static int rsvp_init(struct tcf_proto *tp) -{ - struct rsvp_head *data; - - data = kzalloc(sizeof(struct rsvp_head), GFP_KERNEL); - if (data) { - rcu_assign_pointer(tp->root, data); - return 0; - } - return -ENOBUFS; -} - -static void __rsvp_delete_filter(struct rsvp_filter *f) -{ - tcf_exts_destroy(&f->exts); - tcf_exts_put_net(&f->exts); - kfree(f); -} - -static void rsvp_delete_filter_work(struct work_struct *work) -{ - struct rsvp_filter *f = container_of(to_rcu_work(work), - struct rsvp_filter, - rwork); - rtnl_lock(); - __rsvp_delete_filter(f); - rtnl_unlock(); -} - -static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f) -{ - tcf_unbind_filter(tp, &f->res); - /* all classifiers are required to call tcf_exts_destroy() after rcu - * grace period, since converted-to-rcu actions are relying on that - * in cleanup() callback - */ - if (tcf_exts_get_net(&f->exts)) - tcf_queue_work(&f->rwork, rsvp_delete_filter_work); - else - __rsvp_delete_filter(f); -} - -static void rsvp_destroy(struct tcf_proto *tp, bool rtnl_held, - struct netlink_ext_ack *extack) -{ - struct rsvp_head *data = rtnl_dereference(tp->root); - int h1, h2; - - if (data == NULL) - return; - - for (h1 = 0; h1 < 256; h1++) { - struct rsvp_session *s; - - while ((s = rtnl_dereference(data->ht[h1])) != NULL) { - RCU_INIT_POINTER(data->ht[h1], s->next); - - for (h2 = 0; h2 <= 16; h2++) { - struct rsvp_filter *f; - - while ((f = rtnl_dereference(s->ht[h2])) != NULL) { - rcu_assign_pointer(s->ht[h2], f->next); - rsvp_delete_filter(tp, f); - } - } - kfree_rcu(s, rcu); - } - } - kfree_rcu(data, rcu); -} - -static int rsvp_delete(struct tcf_proto *tp, void *arg, bool *last, - bool rtnl_held, struct netlink_ext_ack *extack) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - struct rsvp_filter *nfp, *f = arg; - struct rsvp_filter __rcu **fp; - unsigned int h = f->handle; - struct rsvp_session __rcu **sp; - struct rsvp_session *nsp, *s = f->sess; - int i, h1; - - fp = &s->ht[(h >> 8) & 0xFF]; - for (nfp = rtnl_dereference(*fp); nfp; - fp = &nfp->next, nfp = rtnl_dereference(*fp)) { - if (nfp == f) { - RCU_INIT_POINTER(*fp, f->next); - rsvp_delete_filter(tp, f); - - /* Strip tree */ - - for (i = 0; i <= 16; i++) - if (s->ht[i]) - goto out; - - /* OK, session has no flows */ - sp = &head->ht[h & 0xFF]; - for (nsp = rtnl_dereference(*sp); nsp; - sp = &nsp->next, nsp = rtnl_dereference(*sp)) { - if (nsp == s) { - RCU_INIT_POINTER(*sp, s->next); - kfree_rcu(s, rcu); - goto out; - } - } - - break; - } - } - -out: - *last = true; - for (h1 = 0; h1 < 256; h1++) { - if (rcu_access_pointer(head->ht[h1])) { - *last = false; - break; - } - } - - return 0; -} - -static unsigned int gen_handle(struct tcf_proto *tp, unsigned salt) -{ - struct rsvp_head *data = rtnl_dereference(tp->root); - int i = 0xFFFF; - - while (i-- > 0) { - u32 h; - - if ((data->hgenerator += 0x10000) == 0) - data->hgenerator = 0x10000; - h = data->hgenerator|salt; - if (!rsvp_get(tp, h)) - return h; - } - return 0; -} - -static int tunnel_bts(struct rsvp_head *data) -{ - int n = data->tgenerator >> 5; - u32 b = 1 << (data->tgenerator & 0x1F); - - if (data->tmap[n] & b) - return 0; - data->tmap[n] |= b; - return 1; -} - -static void tunnel_recycle(struct rsvp_head *data) -{ - struct rsvp_session __rcu **sht = data->ht; - u32 tmap[256/32]; - int h1, h2; - - memset(tmap, 0, sizeof(tmap)); - - for (h1 = 0; h1 < 256; h1++) { - struct rsvp_session *s; - for (s = rtnl_dereference(sht[h1]); s; - s = rtnl_dereference(s->next)) { - for (h2 = 0; h2 <= 16; h2++) { - struct rsvp_filter *f; - - for (f = rtnl_dereference(s->ht[h2]); f; - f = rtnl_dereference(f->next)) { - if (f->tunnelhdr == 0) - continue; - data->tgenerator = f->res.classid; - tunnel_bts(data); - } - } - } - } - - memcpy(data->tmap, tmap, sizeof(tmap)); -} - -static u32 gen_tunnel(struct rsvp_head *data) -{ - int i, k; - - for (k = 0; k < 2; k++) { - for (i = 255; i > 0; i--) { - if (++data->tgenerator == 0) - data->tgenerator = 1; - if (tunnel_bts(data)) - return data->tgenerator; - } - tunnel_recycle(data); - } - return 0; -} - -static const struct nla_policy rsvp_policy[TCA_RSVP_MAX + 1] = { - [TCA_RSVP_CLASSID] = { .type = NLA_U32 }, - [TCA_RSVP_DST] = { .len = RSVP_DST_LEN * sizeof(u32) }, - [TCA_RSVP_SRC] = { .len = RSVP_DST_LEN * sizeof(u32) }, - [TCA_RSVP_PINFO] = { .len = sizeof(struct tc_rsvp_pinfo) }, -}; - -static int rsvp_change(struct net *net, struct sk_buff *in_skb, - struct tcf_proto *tp, unsigned long base, - u32 handle, - struct nlattr **tca, - void **arg, bool ovr, bool rtnl_held, - struct netlink_ext_ack *extack) -{ - struct rsvp_head *data = rtnl_dereference(tp->root); - struct rsvp_filter *f, *nfp; - struct rsvp_filter __rcu **fp; - struct rsvp_session *nsp, *s; - struct rsvp_session __rcu **sp; - struct tc_rsvp_pinfo *pinfo = NULL; - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_RSVP_MAX + 1]; - struct tcf_exts e; - unsigned int h1, h2; - __be32 *dst; - int err; - - if (opt == NULL) - return handle ? -EINVAL : 0; - - err = nla_parse_nested_deprecated(tb, TCA_RSVP_MAX, opt, rsvp_policy, - NULL); - if (err < 0) - return err; - - err = tcf_exts_init(&e, net, TCA_RSVP_ACT, TCA_RSVP_POLICE); - if (err < 0) - return err; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr, true, - extack); - if (err < 0) - goto errout2; - - f = *arg; - if (f) { - /* Node exists: adjust only classid */ - struct rsvp_filter *n; - - if (f->handle != handle && handle) - goto errout2; - - n = kmemdup(f, sizeof(*f), GFP_KERNEL); - if (!n) { - err = -ENOMEM; - goto errout2; - } - - err = tcf_exts_init(&n->exts, net, TCA_RSVP_ACT, - TCA_RSVP_POLICE); - if (err < 0) { - kfree(n); - goto errout2; - } - - if (tb[TCA_RSVP_CLASSID]) { - n->res.classid = nla_get_u32(tb[TCA_RSVP_CLASSID]); - tcf_bind_filter(tp, &n->res, base); - } - - tcf_exts_change(&n->exts, &e); - rsvp_replace(tp, n, handle); - return 0; - } - - /* Now more serious part... */ - err = -EINVAL; - if (handle) - goto errout2; - if (tb[TCA_RSVP_DST] == NULL) - goto errout2; - - err = -ENOBUFS; - f = kzalloc(sizeof(struct rsvp_filter), GFP_KERNEL); - if (f == NULL) - goto errout2; - - err = tcf_exts_init(&f->exts, net, TCA_RSVP_ACT, TCA_RSVP_POLICE); - if (err < 0) - goto errout; - h2 = 16; - if (tb[TCA_RSVP_SRC]) { - memcpy(f->src, nla_data(tb[TCA_RSVP_SRC]), sizeof(f->src)); - h2 = hash_src(f->src); - } - if (tb[TCA_RSVP_PINFO]) { - pinfo = nla_data(tb[TCA_RSVP_PINFO]); - f->spi = pinfo->spi; - f->tunnelhdr = pinfo->tunnelhdr; - } - if (tb[TCA_RSVP_CLASSID]) - f->res.classid = nla_get_u32(tb[TCA_RSVP_CLASSID]); - - dst = nla_data(tb[TCA_RSVP_DST]); - h1 = hash_dst(dst, pinfo ? pinfo->protocol : 0, pinfo ? pinfo->tunnelid : 0); - - err = -ENOMEM; - if ((f->handle = gen_handle(tp, h1 | (h2<<8))) == 0) - goto errout; - - if (f->tunnelhdr) { - err = -EINVAL; - if (f->res.classid > 255) - goto errout; - - err = -ENOMEM; - if (f->res.classid == 0 && - (f->res.classid = gen_tunnel(data)) == 0) - goto errout; - } - - for (sp = &data->ht[h1]; - (s = rtnl_dereference(*sp)) != NULL; - sp = &s->next) { - if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN-1] && - pinfo && pinfo->protocol == s->protocol && - memcmp(&pinfo->dpi, &s->dpi, sizeof(s->dpi)) == 0 && -#if RSVP_DST_LEN == 4 - dst[0] == s->dst[0] && - dst[1] == s->dst[1] && - dst[2] == s->dst[2] && -#endif - pinfo->tunnelid == s->tunnelid) { - -insert: - /* OK, we found appropriate session */ - - fp = &s->ht[h2]; - - f->sess = s; - if (f->tunnelhdr == 0) - tcf_bind_filter(tp, &f->res, base); - - tcf_exts_change(&f->exts, &e); - - fp = &s->ht[h2]; - for (nfp = rtnl_dereference(*fp); nfp; - fp = &nfp->next, nfp = rtnl_dereference(*fp)) { - __u32 mask = nfp->spi.mask & f->spi.mask; - - if (mask != f->spi.mask) - break; - } - RCU_INIT_POINTER(f->next, nfp); - rcu_assign_pointer(*fp, f); - - *arg = f; - return 0; - } - } - - /* No session found. Create new one. */ - - err = -ENOBUFS; - s = kzalloc(sizeof(struct rsvp_session), GFP_KERNEL); - if (s == NULL) - goto errout; - memcpy(s->dst, dst, sizeof(s->dst)); - - if (pinfo) { - s->dpi = pinfo->dpi; - s->protocol = pinfo->protocol; - s->tunnelid = pinfo->tunnelid; - } - sp = &data->ht[h1]; - for (nsp = rtnl_dereference(*sp); nsp; - sp = &nsp->next, nsp = rtnl_dereference(*sp)) { - if ((nsp->dpi.mask & s->dpi.mask) != s->dpi.mask) - break; - } - RCU_INIT_POINTER(s->next, nsp); - rcu_assign_pointer(*sp, s); - - goto insert; - -errout: - tcf_exts_destroy(&f->exts); - kfree(f); -errout2: - tcf_exts_destroy(&e); - return err; -} - -static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg, - bool rtnl_held) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - unsigned int h, h1; - - if (arg->stop) - return; - - for (h = 0; h < 256; h++) { - struct rsvp_session *s; - - for (s = rtnl_dereference(head->ht[h]); s; - s = rtnl_dereference(s->next)) { - for (h1 = 0; h1 <= 16; h1++) { - struct rsvp_filter *f; - - for (f = rtnl_dereference(s->ht[h1]); f; - f = rtnl_dereference(f->next)) { - if (arg->count < arg->skip) { - arg->count++; - continue; - } - if (arg->fn(tp, f, arg) < 0) { - arg->stop = 1; - return; - } - arg->count++; - } - } - } - } -} - -static int rsvp_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) -{ - struct rsvp_filter *f = fh; - struct rsvp_session *s; - struct nlattr *nest; - struct tc_rsvp_pinfo pinfo; - - if (f == NULL) - return skb->len; - s = f->sess; - - t->tcm_handle = f->handle; - - nest = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - - if (nla_put(skb, TCA_RSVP_DST, sizeof(s->dst), &s->dst)) - goto nla_put_failure; - pinfo.dpi = s->dpi; - pinfo.spi = f->spi; - pinfo.protocol = s->protocol; - pinfo.tunnelid = s->tunnelid; - pinfo.tunnelhdr = f->tunnelhdr; - pinfo.pad = 0; - if (nla_put(skb, TCA_RSVP_PINFO, sizeof(pinfo), &pinfo)) - goto nla_put_failure; - if (f->res.classid && - nla_put_u32(skb, TCA_RSVP_CLASSID, f->res.classid)) - goto nla_put_failure; - if (((f->handle >> 8) & 0xFF) != 16 && - nla_put(skb, TCA_RSVP_SRC, sizeof(f->src), f->src)) - goto nla_put_failure; - - if (tcf_exts_dump(skb, &f->exts) < 0) - goto nla_put_failure; - - nla_nest_end(skb, nest); - - if (tcf_exts_dump_stats(skb, &f->exts) < 0) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} - -static void rsvp_bind_class(void *fh, u32 classid, unsigned long cl, void *q, - unsigned long base) -{ - struct rsvp_filter *f = fh; - - if (f && f->res.classid == classid) { - if (cl) - __tcf_bind_filter(q, &f->res, base); - else - __tcf_unbind_filter(q, &f->res); - } -} - -static struct tcf_proto_ops RSVP_OPS __read_mostly = { - .kind = RSVP_ID, - .classify = rsvp_classify, - .init = rsvp_init, - .destroy = rsvp_destroy, - .get = rsvp_get, - .change = rsvp_change, - .delete = rsvp_delete, - .walk = rsvp_walk, - .dump = rsvp_dump, - .bind_class = rsvp_bind_class, - .owner = THIS_MODULE, -}; - -static int __init init_rsvp(void) -{ - return register_tcf_proto_ops(&RSVP_OPS); -} - -static void __exit exit_rsvp(void) -{ - unregister_tcf_proto_ops(&RSVP_OPS); -} - -module_init(init_rsvp) -module_exit(exit_rsvp) --- a/net/sched/cls_rsvp6.c +++ /dev/null @@ -1,24 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * net/sched/cls_rsvp6.c Special RSVP packet classifier for IPv6. - * - * Authors: Alexey Kuznetsov, kuznet@ms2.inr.ac.ru - */ - -#include <linux/module.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/ipv6.h> -#include <linux/skbuff.h> -#include <net/act_api.h> -#include <net/pkt_cls.h> -#include <net/netlink.h> - -#define RSVP_DST_LEN 4 -#define RSVP_ID "rsvp6" -#define RSVP_OPS cls_rsvp6_ops - -#include "cls_rsvp.h" -MODULE_LICENSE("GPL");

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Kent Overstreet kent.overstreet@gmail.com

commit 3644e2d2dda78e21edd8f5415b6d7ab03f5f54f3 upstream.

If iter->count is 0 and iocb->ki_pos is page aligned, this causes nr_pages to be 0.

Then in generic_file_buffered_read_get_pages() find_get_pages_contig() returns 0 - because we asked for 0 pages, so we call generic_file_buffered_read_no_cached_page() which attempts to add a page to the page cache, which fails with -EEXIST, and then we loop. Oops...

Signed-off-by: Kent Overstreet kent.overstreet@gmail.com Reported-by: Jens Axboe axboe@kernel.dk Reviewed-by: Jens Axboe axboe@kernel.dk Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Suraj Jitindar Singh surajjs@amazon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/filemap.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/mm/filemap.c +++ b/mm/filemap.c @@ -2203,6 +2203,9 @@ ssize_t generic_file_buffered_read(struc

if (unlikely(*ppos >= inode->i_sb->s_maxbytes)) return 0; + if (unlikely(!iov_iter_count(iter))) + return 0; + iov_iter_truncate(iter, inode->i_sb->s_maxbytes);

index = *ppos >> PAGE_SHIFT;

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Steven Rostedt (Google) rostedt@goodmis.org

commit 9b37febc578b2e1ad76a105aab11d00af5ec3d27 upstream.

The current_trace updates the trace array tracer. For an instance, if the file is opened and the instance is deleted, reading or writing to the file will cause a use after free.

Up the ref count of the trace array when current_trace is opened.

Link: https://lkml.kernel.org/r/20230907024803.877687227@goodmis.org Link: https://lore.kernel.org/all/1cb3aee2-19af-c472-e265-05176fe9bd84@huawei.com/

Cc: stable@vger.kernel.org Cc: Masami Hiramatsu mhiramat@kernel.org Cc: Mark Rutland mark.rutland@arm.com Cc: Andrew Morton akpm@linux-foundation.org Cc: Zheng Yejian zhengyejian1@huawei.com Fixes: 8530dec63e7b4 ("tracing: Add tracing_check_open_get_tr()") Tested-by: Linux Kernel Functional Testing lkft@linaro.org Tested-by: Naresh Kamboju naresh.kamboju@linaro.org Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/trace/trace.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7324,10 +7324,11 @@ static const struct file_operations trac #endif

static const struct file_operations set_tracer_fops = { - .open = tracing_open_generic, + .open = tracing_open_generic_tr, .read = tracing_set_trace_read, .write = tracing_set_trace_write, .llseek = generic_file_llseek, + .release = tracing_release_generic_tr, };

static const struct file_operations tracing_pipe_fops = {

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Jeff Layton jlayton@kernel.org

commit fdd2630a7398191e84822612e589062063bd4f3d upstream.

nfsd sends the transposed directory change info in the RENAME reply. The source directory is in save_fh and the target is in current_fh.

Reported-by: Zhi Li yieli@redhat.com Reported-by: Benjamin Coddington bcodding@redhat.com Closes: https://bugzilla.redhat.com/show_bug.cgi?id=2218844 Signed-off-by: Jeff Layton jlayton@kernel.org Cc: stable@vger.kernel.org Signed-off-by: Chuck Lever chuck.lever@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/nfsd/nfs4proc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -881,8 +881,8 @@ nfsd4_rename(struct svc_rqst *rqstp, str rename->rn_tname, rename->rn_tnamelen); if (status) return status; - set_change_info(&rename->rn_sinfo, &cstate->current_fh); - set_change_info(&rename->rn_tinfo, &cstate->save_fh); + set_change_info(&rename->rn_sinfo, &cstate->save_fh); + set_change_info(&rename->rn_tinfo, &cstate->current_fh); return nfs_ok; }

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Tommy Huang tommy_huang@aspeedtech.com

commit fee465150b458351b6d9b9f66084f3cc3022b88b upstream.

Reset the i2c controller when an i2c transfer timeout occurs. The remaining interrupts and device should be reset to avoid unpredictable controller behavior.

Fixes: 2e57b7cebb98 ("i2c: aspeed: Add multi-master use case support") Cc: stable@vger.kernel.org # v5.1+ Signed-off-by: Tommy Huang tommy_huang@aspeedtech.com Reviewed-by: Andi Shyti andi.shyti@kernel.org Signed-off-by: Wolfram Sang wsa@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/i2c/busses/i2c-aspeed.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

--- a/drivers/i2c/busses/i2c-aspeed.c +++ b/drivers/i2c/busses/i2c-aspeed.c @@ -693,13 +693,16 @@ static int aspeed_i2c_master_xfer(struct

if (time_left == 0) { /* - * If timed out and bus is still busy in a multi master - * environment, attempt recovery at here. + * In a multi-master setup, if a timeout occurs, attempt + * recovery. But if the bus is idle, we still need to reset the + * i2c controller to clear the remaining interrupts. */ if (bus->multi_master && (readl(bus->base + ASPEED_I2C_CMD_REG) & ASPEED_I2CD_BUS_BUSY_STS)) aspeed_i2c_recover_bus(bus); + else + aspeed_i2c_reset(bus);

/* * If timed out and the state is still pending, drop the pending

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Junxiao Bi junxiao.bi@oracle.com

commit 0b0747d507bffb827e40fc0f9fb5883fffc23477 upstream.

The following processes run into a deadlock. CPU 41 was waiting for CPU 29 to handle a CSD request while holding spinlock "crashdump_lock", but CPU 29 was hung by that spinlock with IRQs disabled.

PID: 17360 TASK: ffff95c1090c5c40 CPU: 41 COMMAND: "mrdiagd" !# 0 [ffffb80edbf37b58] __read_once_size at ffffffff9b871a40 include/linux/compiler.h:185:0 !# 1 [ffffb80edbf37b58] atomic_read at ffffffff9b871a40 arch/x86/include/asm/atomic.h:27:0 !# 2 [ffffb80edbf37b58] dump_stack at ffffffff9b871a40 lib/dump_stack.c:54:0 # 3 [ffffb80edbf37b78] csd_lock_wait_toolong at ffffffff9b131ad5 kernel/smp.c:364:0 # 4 [ffffb80edbf37b78] __csd_lock_wait at ffffffff9b131ad5 kernel/smp.c:384:0 # 5 [ffffb80edbf37bf8] csd_lock_wait at ffffffff9b13267a kernel/smp.c:394:0 # 6 [ffffb80edbf37bf8] smp_call_function_many at ffffffff9b13267a kernel/smp.c:843:0 # 7 [ffffb80edbf37c50] smp_call_function at ffffffff9b13279d kernel/smp.c:867:0 # 8 [ffffb80edbf37c50] on_each_cpu at ffffffff9b13279d kernel/smp.c:976:0 # 9 [ffffb80edbf37c78] flush_tlb_kernel_range at ffffffff9b085c4b arch/x86/mm/tlb.c:742:0 #10 [ffffb80edbf37cb8] __purge_vmap_area_lazy at ffffffff9b23a1e0 mm/vmalloc.c:701:0 #11 [ffffb80edbf37ce0] try_purge_vmap_area_lazy at ffffffff9b23a2cc mm/vmalloc.c:722:0 #12 [ffffb80edbf37ce0] free_vmap_area_noflush at ffffffff9b23a2cc mm/vmalloc.c:754:0 #13 [ffffb80edbf37cf8] free_unmap_vmap_area at ffffffff9b23bb3b mm/vmalloc.c:764:0 #14 [ffffb80edbf37cf8] remove_vm_area at ffffffff9b23bb3b mm/vmalloc.c:1509:0 #15 [ffffb80edbf37d18] __vunmap at ffffffff9b23bb8a mm/vmalloc.c:1537:0 #16 [ffffb80edbf37d40] vfree at ffffffff9b23bc85 mm/vmalloc.c:1612:0 #17 [ffffb80edbf37d58] megasas_free_host_crash_buffer [megaraid_sas] at ffffffffc020b7f2 drivers/scsi/megaraid/megaraid_sas_fusion.c:3932:0 #18 [ffffb80edbf37d80] fw_crash_state_store [megaraid_sas] at ffffffffc01f804d drivers/scsi/megaraid/megaraid_sas_base.c:3291:0 #19 [ffffb80edbf37dc0] dev_attr_store at ffffffff9b56dd7b drivers/base/core.c:758:0 #20 [ffffb80edbf37dd0] sysfs_kf_write at ffffffff9b326acf fs/sysfs/file.c:144:0 #21 [ffffb80edbf37de0] kernfs_fop_write at ffffffff9b325fd4 fs/kernfs/file.c:316:0 #22 [ffffb80edbf37e20] __vfs_write at ffffffff9b29418a fs/read_write.c:480:0 #23 [ffffb80edbf37ea8] vfs_write at ffffffff9b294462 fs/read_write.c:544:0 #24 [ffffb80edbf37ee8] SYSC_write at ffffffff9b2946ec fs/read_write.c:590:0 #25 [ffffb80edbf37ee8] SyS_write at ffffffff9b2946ec fs/read_write.c:582:0 #26 [ffffb80edbf37f30] do_syscall_64 at ffffffff9b003ca9 arch/x86/entry/common.c:298:0 #27 [ffffb80edbf37f58] entry_SYSCALL_64 at ffffffff9ba001b1 arch/x86/entry/entry_64.S:238:0

PID: 17355 TASK: ffff95c1090c3d80 CPU: 29 COMMAND: "mrdiagd" !# 0 [ffffb80f2d3c7d30] __read_once_size at ffffffff9b0f2ab0 include/linux/compiler.h:185:0 !# 1 [ffffb80f2d3c7d30] native_queued_spin_lock_slowpath at ffffffff9b0f2ab0 kernel/locking/qspinlock.c:368:0 # 2 [ffffb80f2d3c7d58] pv_queued_spin_lock_slowpath at ffffffff9b0f244b arch/x86/include/asm/paravirt.h:674:0 # 3 [ffffb80f2d3c7d58] queued_spin_lock_slowpath at ffffffff9b0f244b arch/x86/include/asm/qspinlock.h:53:0 # 4 [ffffb80f2d3c7d68] queued_spin_lock at ffffffff9b8961a6 include/asm-generic/qspinlock.h:90:0 # 5 [ffffb80f2d3c7d68] do_raw_spin_lock_flags at ffffffff9b8961a6 include/linux/spinlock.h:173:0 # 6 [ffffb80f2d3c7d68] __raw_spin_lock_irqsave at ffffffff9b8961a6 include/linux/spinlock_api_smp.h:122:0 # 7 [ffffb80f2d3c7d68] _raw_spin_lock_irqsave at ffffffff9b8961a6 kernel/locking/spinlock.c:160:0 # 8 [ffffb80f2d3c7d88] fw_crash_buffer_store [megaraid_sas] at ffffffffc01f8129 drivers/scsi/megaraid/megaraid_sas_base.c:3205:0 # 9 [ffffb80f2d3c7dc0] dev_attr_store at ffffffff9b56dd7b drivers/base/core.c:758:0 #10 [ffffb80f2d3c7dd0] sysfs_kf_write at ffffffff9b326acf fs/sysfs/file.c:144:0 #11 [ffffb80f2d3c7de0] kernfs_fop_write at ffffffff9b325fd4 fs/kernfs/file.c:316:0 #12 [ffffb80f2d3c7e20] __vfs_write at ffffffff9b29418a fs/read_write.c:480:0 #13 [ffffb80f2d3c7ea8] vfs_write at ffffffff9b294462 fs/read_write.c:544:0 #14 [ffffb80f2d3c7ee8] SYSC_write at ffffffff9b2946ec fs/read_write.c:590:0 #15 [ffffb80f2d3c7ee8] SyS_write at ffffffff9b2946ec fs/read_write.c:582:0 #16 [ffffb80f2d3c7f30] do_syscall_64 at ffffffff9b003ca9 arch/x86/entry/common.c:298:0 #17 [ffffb80f2d3c7f58] entry_SYSCALL_64 at ffffffff9ba001b1 arch/x86/entry/entry_64.S:238:0

The lock is used to synchronize different sysfs operations, it doesn't protect any resource that will be touched by an interrupt. Consequently it's not required to disable IRQs. Replace the spinlock with a mutex to fix the deadlock.

Signed-off-by: Junxiao Bi junxiao.bi@oracle.com Link: https://lore.kernel.org/r/20230828221018.19471-1-junxiao.bi@oracle.com Reviewed-by: Mike Christie michael.christie@oracle.com Cc: stable@vger.kernel.org Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/scsi/megaraid/megaraid_sas.h | 2 +- drivers/scsi/megaraid/megaraid_sas_base.c | 21 +++++++++------------ 2 files changed, 10 insertions(+), 13 deletions(-)

--- a/drivers/scsi/megaraid/megaraid_sas.h +++ b/drivers/scsi/megaraid/megaraid_sas.h @@ -2327,7 +2327,7 @@ struct megasas_instance { u32 support_morethan256jbod; /* FW support for more than 256 PD/JBOD */ bool use_seqnum_jbod_fp; /* Added for PD sequence */ bool smp_affinity_enable; - spinlock_t crashdump_lock; + struct mutex crashdump_lock;

struct megasas_register_set __iomem *reg_set; u32 __iomem *reply_post_host_index_addr[MR_MAX_MSIX_REG_ARRAY]; --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -3221,14 +3221,13 @@ fw_crash_buffer_store(struct device *cde struct megasas_instance *instance = (struct megasas_instance *) shost->hostdata; int val = 0; - unsigned long flags;

if (kstrtoint(buf, 0, &val) != 0) return -EINVAL;

- spin_lock_irqsave(&instance->crashdump_lock, flags); + mutex_lock(&instance->crashdump_lock); instance->fw_crash_buffer_offset = val; - spin_unlock_irqrestore(&instance->crashdump_lock, flags); + mutex_unlock(&instance->crashdump_lock); return strlen(buf); }

@@ -3243,24 +3242,23 @@ fw_crash_buffer_show(struct device *cdev unsigned long dmachunk = CRASH_DMA_BUF_SIZE; unsigned long chunk_left_bytes; unsigned long src_addr; - unsigned long flags; u32 buff_offset;

- spin_lock_irqsave(&instance->crashdump_lock, flags); + mutex_lock(&instance->crashdump_lock); buff_offset = instance->fw_crash_buffer_offset; if (!instance->crash_dump_buf || !((instance->fw_crash_state == AVAILABLE) || (instance->fw_crash_state == COPYING))) { dev_err(&instance->pdev->dev, "Firmware crash dump is not available\n"); - spin_unlock_irqrestore(&instance->crashdump_lock, flags); + mutex_unlock(&instance->crashdump_lock); return -EINVAL; }

if (buff_offset > (instance->fw_crash_buffer_size * dmachunk)) { dev_err(&instance->pdev->dev, "Firmware crash dump offset is out of range\n"); - spin_unlock_irqrestore(&instance->crashdump_lock, flags); + mutex_unlock(&instance->crashdump_lock); return 0; }

@@ -3272,7 +3270,7 @@ fw_crash_buffer_show(struct device *cdev src_addr = (unsigned long)instance->crash_buf[buff_offset / dmachunk] + (buff_offset % dmachunk); memcpy(buf, (void *)src_addr, size); - spin_unlock_irqrestore(&instance->crashdump_lock, flags); + mutex_unlock(&instance->crashdump_lock);

return size; } @@ -3297,7 +3295,6 @@ fw_crash_state_store(struct device *cdev struct megasas_instance *instance = (struct megasas_instance *) shost->hostdata; int val = 0; - unsigned long flags;

if (kstrtoint(buf, 0, &val) != 0) return -EINVAL; @@ -3311,9 +3308,9 @@ fw_crash_state_store(struct device *cdev instance->fw_crash_state = val;

if ((val == COPIED) || (val == COPY_ERROR)) { - spin_lock_irqsave(&instance->crashdump_lock, flags); + mutex_lock(&instance->crashdump_lock); megasas_free_host_crash_buffer(instance); - spin_unlock_irqrestore(&instance->crashdump_lock, flags); + mutex_unlock(&instance->crashdump_lock); if (val == COPY_ERROR) dev_info(&instance->pdev->dev, "application failed to " "copy Firmware crash dump\n"); @@ -7325,7 +7322,7 @@ static inline void megasas_init_ctrl_par init_waitqueue_head(&instance->int_cmd_wait_q); init_waitqueue_head(&instance->abort_cmd_wait_q);

- spin_lock_init(&instance->crashdump_lock); + mutex_init(&instance->crashdump_lock); spin_lock_init(&instance->mfi_pool_lock); spin_lock_init(&instance->hba_lock); spin_lock_init(&instance->stream_lock);

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Shida Zhang zhangshida@kylinos.cn

commit 7fda67e8c3ab6069f75888f67958a6d30454a9f6 upstream.

With the configuration PAGE_SIZE 64k and filesystem blocksize 64k, a problem occurred when more than 13 million files were directly created under a directory:

EXT4-fs error (device xx): ext4_dx_csum_set:492: inode #xxxx: comm xxxxx: dir seems corrupt? Run e2fsck -D. EXT4-fs error (device xx): ext4_dx_csum_verify:463: inode #xxxx: comm xxxxx: dir seems corrupt? Run e2fsck -D. EXT4-fs error (device xx): dx_probe:856: inode #xxxx: block 8188: comm xxxxx: Directory index failed checksum

When enough files are created, the fake_dirent->reclen will be 0xffff. it doesn't equal to the blocksize 65536, i.e. 0x10000.

But it is not the same condition when blocksize equals to 4k. when enough files are created, the fake_dirent->reclen will be 0x1000. it equals to the blocksize 4k, i.e. 0x1000.

The problem seems to be related to the limitation of the 16-bit field when the blocksize is set to 64k. To address this, helpers like ext4_rec_len_{from,to}_disk has already been introduced to complete the conversion between the encoded and the plain form of rec_len.

So fix this one by using the helper, and all the other in this file too.

Cc: stable@kernel.org Fixes: dbe89444042a ("ext4: Calculate and verify checksums for htree nodes") Suggested-by: Andreas Dilger adilger@dilger.ca Suggested-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Shida Zhang zhangshida@kylinos.cn Reviewed-by: Andreas Dilger adilger@dilger.ca Reviewed-by: Darrick J. Wong djwong@kernel.org Link: https://lore.kernel.org/r/20230803060938.1929759-1-zhangshida@kylinos.cn Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ext4/namei.c | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-)

--- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -339,17 +339,17 @@ static struct ext4_dir_entry_tail *get_d struct buffer_head *bh) { struct ext4_dir_entry_tail *t; + int blocksize = EXT4_BLOCK_SIZE(inode->i_sb);

#ifdef PARANOID struct ext4_dir_entry *d, *top;

d = (struct ext4_dir_entry *)bh->b_data; top = (struct ext4_dir_entry *)(bh->b_data + - (EXT4_BLOCK_SIZE(inode->i_sb) - - sizeof(struct ext4_dir_entry_tail))); - while (d < top && d->rec_len) + (blocksize - sizeof(struct ext4_dir_entry_tail))); + while (d < top && ext4_rec_len_from_disk(d->rec_len, blocksize)) d = (struct ext4_dir_entry *)(((void *)d) + - le16_to_cpu(d->rec_len)); + ext4_rec_len_from_disk(d->rec_len, blocksize));

if (d != top) return NULL; @@ -360,7 +360,8 @@ static struct ext4_dir_entry_tail *get_d #endif

if (t->det_reserved_zero1 || - le16_to_cpu(t->det_rec_len) != sizeof(struct ext4_dir_entry_tail) || + (ext4_rec_len_from_disk(t->det_rec_len, blocksize) != + sizeof(struct ext4_dir_entry_tail)) || t->det_reserved_zero2 || t->det_reserved_ft != EXT4_FT_DIR_CSUM) return NULL; @@ -441,13 +442,14 @@ static struct dx_countlimit *get_dx_coun struct ext4_dir_entry *dp; struct dx_root_info *root; int count_offset; + int blocksize = EXT4_BLOCK_SIZE(inode->i_sb); + unsigned int rlen = ext4_rec_len_from_disk(dirent->rec_len, blocksize);

- if (le16_to_cpu(dirent->rec_len) == EXT4_BLOCK_SIZE(inode->i_sb)) + if (rlen == blocksize) count_offset = 8; - else if (le16_to_cpu(dirent->rec_len) == 12) { + else if (rlen == 12) { dp = (struct ext4_dir_entry *)(((void *)dirent) + 12); - if (le16_to_cpu(dp->rec_len) != - EXT4_BLOCK_SIZE(inode->i_sb) - 12) + if (ext4_rec_len_from_disk(dp->rec_len, blocksize) != blocksize - 12) return NULL; root = (struct dx_root_info *)(((void *)dp + 12)); if (root->reserved_zero || @@ -1256,6 +1258,7 @@ static int dx_make_map(struct inode *dir unsigned int buflen = bh->b_size; char *base = bh->b_data; struct dx_hash_info h = *hinfo; + int blocksize = EXT4_BLOCK_SIZE(dir->i_sb);

if (ext4_has_metadata_csum(dir->i_sb)) buflen -= sizeof(struct ext4_dir_entry_tail); @@ -1269,11 +1272,12 @@ static int dx_make_map(struct inode *dir map_tail--; map_tail->hash = h.hash; map_tail->offs = ((char *) de - base)>>2; - map_tail->size = le16_to_cpu(de->rec_len); + map_tail->size = ext4_rec_len_from_disk(de->rec_len, + blocksize); count++; cond_resched(); } - de = ext4_next_entry(de, dir->i_sb->s_blocksize); + de = ext4_next_entry(de, blocksize); } return count; }