- Kernel - mailweb.openeuler.org

[PATCH OLK-6.6] platform/x86: panasonic-laptop: Fix SINF array out of bounds accesses
by Wupeng Ma 15 Oct '24

15 Oct '24

From: Hans de Goede <hdegoede(a)redhat.com> stable inclusion from stable-v6.6.52 commit 6821a82616f60aa72c5909b3e252ad97fb9f7e2a category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAUA6B CVE: CVE-2024-46859 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit f52e98d16e9bd7dd2b3aef8e38db5cbc9899d6a4 upstream. The panasonic laptop code in various places uses the SINF array with index values of 0 - SINF_CUR_BRIGHT(0x0d) without checking that the SINF array is big enough. Not all panasonic laptops have this many SINF array entries, for example the Toughbook CF-18 model only has 10 SINF array entries. So it only supports the AC+DC brightness entries and mute. Check that the SINF array has a minimum size which covers all AC+DC brightness entries and refuse to load if the SINF array is smaller. For higher SINF indexes hide the sysfs attributes when the SINF array does not contain an entry for that attribute, avoiding show()/store() accessing the array out of bounds and add bounds checking to the probe() and resume() code accessing these. Fixes: e424fb8cc4e6 ("panasonic-laptop: avoid overflow in acpi_pcc_hotkey_add()") Cc: stable(a)vger.kernel.org Signed-off-by: Hans de Goede <hdegoede(a)redhat.com> Link: https://lore.kernel.org/r/20240909113227.254470-1-hdegoede@redhat.com Reviewed-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com> Signed-off-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Ma Wupeng <mawupeng1(a)huawei.com> --- drivers/platform/x86/panasonic-laptop.c | 49 ++++++++++++++++++++----- 1 file changed, 39 insertions(+), 10 deletions(-) diff --git a/drivers/platform/x86/panasonic-laptop.c b/drivers/platform/x86/panasonic-laptop.c index cf845ee1c7b1f..39044119d2a6e 100644 --- a/drivers/platform/x86/panasonic-laptop.c +++ b/drivers/platform/x86/panasonic-laptop.c @@ -773,6 +773,24 @@ static DEVICE_ATTR_RW(dc_brightness); static DEVICE_ATTR_RW(current_brightness); static DEVICE_ATTR_RW(cdpower); +static umode_t pcc_sysfs_is_visible(struct kobject *kobj, struct attribute *attr, int idx) +{ + struct device *dev = kobj_to_dev(kobj); + struct acpi_device *acpi = to_acpi_device(dev); + struct pcc_acpi *pcc = acpi_driver_data(acpi); + + if (attr == &dev_attr_mute.attr) + return (pcc->num_sifr > SINF_MUTE) ? attr->mode : 0; + + if (attr == &dev_attr_eco_mode.attr) + return (pcc->num_sifr > SINF_ECO_MODE) ? attr->mode : 0; + + if (attr == &dev_attr_current_brightness.attr) + return (pcc->num_sifr > SINF_CUR_BRIGHT) ? attr->mode : 0; + + return attr->mode; +} + static struct attribute *pcc_sysfs_entries[] = { &dev_attr_numbatt.attr, &dev_attr_lcdtype.attr, @@ -787,8 +805,9 @@ static struct attribute *pcc_sysfs_entries[] = { }; static const struct attribute_group pcc_attr_group = { - .name = NULL, /* put in device directory */ - .attrs = pcc_sysfs_entries, + .name = NULL, /* put in device directory */ + .attrs = pcc_sysfs_entries, + .is_visible = pcc_sysfs_is_visible, }; @@ -941,12 +960,15 @@ static int acpi_pcc_hotkey_resume(struct device *dev) if (!pcc) return -EINVAL; - acpi_pcc_write_sset(pcc, SINF_MUTE, pcc->mute); - acpi_pcc_write_sset(pcc, SINF_ECO_MODE, pcc->eco_mode); + if (pcc->num_sifr > SINF_MUTE) + acpi_pcc_write_sset(pcc, SINF_MUTE, pcc->mute); + if (pcc->num_sifr > SINF_ECO_MODE) + acpi_pcc_write_sset(pcc, SINF_ECO_MODE, pcc->eco_mode); acpi_pcc_write_sset(pcc, SINF_STICKY_KEY, pcc->sticky_key); acpi_pcc_write_sset(pcc, SINF_AC_CUR_BRIGHT, pcc->ac_brightness); acpi_pcc_write_sset(pcc, SINF_DC_CUR_BRIGHT, pcc->dc_brightness); - acpi_pcc_write_sset(pcc, SINF_CUR_BRIGHT, pcc->current_brightness); + if (pcc->num_sifr > SINF_CUR_BRIGHT) + acpi_pcc_write_sset(pcc, SINF_CUR_BRIGHT, pcc->current_brightness); return 0; } @@ -963,8 +985,12 @@ static int acpi_pcc_hotkey_add(struct acpi_device *device) num_sifr = acpi_pcc_get_sqty(device); - if (num_sifr < 0 || num_sifr > 255) { - pr_err("num_sifr out of range"); + /* + * pcc->sinf is expected to at least have the AC+DC brightness entries. + * Accesses to higher SINF entries are checked against num_sifr. + */ + if (num_sifr <= SINF_DC_CUR_BRIGHT || num_sifr > 255) { + pr_err("num_sifr %d out of range %d - 255\n", num_sifr, SINF_DC_CUR_BRIGHT + 1); return -ENODEV; } @@ -1020,11 +1046,14 @@ static int acpi_pcc_hotkey_add(struct acpi_device *device) acpi_pcc_write_sset(pcc, SINF_STICKY_KEY, 0); pcc->sticky_key = 0; - pcc->eco_mode = pcc->sinf[SINF_ECO_MODE]; - pcc->mute = pcc->sinf[SINF_MUTE]; pcc->ac_brightness = pcc->sinf[SINF_AC_CUR_BRIGHT]; pcc->dc_brightness = pcc->sinf[SINF_DC_CUR_BRIGHT]; - pcc->current_brightness = pcc->sinf[SINF_CUR_BRIGHT]; + if (pcc->num_sifr > SINF_MUTE) + pcc->mute = pcc->sinf[SINF_MUTE]; + if (pcc->num_sifr > SINF_ECO_MODE) + pcc->eco_mode = pcc->sinf[SINF_ECO_MODE]; + if (pcc->num_sifr > SINF_CUR_BRIGHT) + pcc->current_brightness = pcc->sinf[SINF_CUR_BRIGHT]; /* add sysfs attributes */ result = sysfs_create_group(&device->dev.kobj, &pcc_attr_group); -- 2.25.1

2 1

[PATCH OLK-5.10] scsi: qla2xxx: During vport delete send async logout explicitly
by Wupeng Ma 15 Oct '24

15 Oct '24

From: Manish Rangankar <mrangankar(a)marvell.com> stable inclusion from stable-v5.10.224 commit e5ed6a26ffdec0c91cf0b6138afbd675c00ad5fc category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAKQ92 CVE: CVE-2024-42289 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 76f480d7c717368f29a3870f7d64471ce0ff8fb2 upstream. During vport delete, it is observed that during unload we hit a crash because of stale entries in outstanding command array. For all these stale I/O entries, eh_abort was issued and aborted (fast_fail_io = 2009h) but I/Os could not complete while vport delete is in process of deleting. BUG: kernel NULL pointer dereference, address: 000000000000001c #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP NOPTI Workqueue: qla2xxx_wq qla_do_work [qla2xxx] RIP: 0010:dma_direct_unmap_sg+0x51/0x1e0 RSP: 0018:ffffa1e1e150fc68 EFLAGS: 00010046 RAX: 0000000000000000 RBX: 0000000000000021 RCX: 0000000000000001 RDX: 0000000000000021 RSI: 0000000000000000 RDI: ffff8ce208a7a0d0 RBP: ffff8ce208a7a0d0 R08: 0000000000000000 R09: ffff8ce378aac9c8 R10: ffff8ce378aac8a0 R11: ffffa1e1e150f9d8 R12: 0000000000000000 R13: 0000000000000000 R14: ffff8ce378aac9c8 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff8d217f000000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000000001c CR3: 0000002089acc000 CR4: 0000000000350ee0 Call Trace: <TASK> qla2xxx_qpair_sp_free_dma+0x417/0x4e0 ? qla2xxx_qpair_sp_compl+0x10d/0x1a0 ? qla2x00_status_entry+0x768/0x2830 ? newidle_balance+0x2f0/0x430 ? dequeue_entity+0x100/0x3c0 ? qla24xx_process_response_queue+0x6a1/0x19e0 ? __schedule+0x2d5/0x1140 ? qla_do_work+0x47/0x60 ? process_one_work+0x267/0x440 ? process_one_work+0x440/0x440 ? worker_thread+0x2d/0x3d0 ? process_one_work+0x440/0x440 ? kthread+0x156/0x180 ? set_kthread_struct+0x50/0x50 ? ret_from_fork+0x22/0x30 </TASK> Send out async logout explicitly for all the ports during vport delete. Cc: stable(a)vger.kernel.org Signed-off-by: Manish Rangankar <mrangankar(a)marvell.com> Signed-off-by: Nilesh Javali <njavali(a)marvell.com> Link: https://lore.kernel.org/r/20240710171057.35066-8-njavali@marvell.com Reviewed-by: Himanshu Madhani <himanshu.madhani(a)oracle.com> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Ma Wupeng <mawupeng1(a)huawei.com> --- drivers/scsi/qla2xxx/qla_mid.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c index c7caf322f445..b98c390b4b27 100644 --- a/drivers/scsi/qla2xxx/qla_mid.c +++ b/drivers/scsi/qla2xxx/qla_mid.c @@ -164,7 +164,7 @@ qla24xx_disable_vp(scsi_qla_host_t *vha) atomic_set(&vha->loop_state, LOOP_DOWN); atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME); list_for_each_entry(fcport, &vha->vp_fcports, list) - fcport->logout_on_delete = 0; + fcport->logout_on_delete = 1; qla2x00_mark_all_devices_lost(vha); -- 2.25.1

2 1

[PATCH OLK-5.10] platform/x86: panasonic-laptop: Fix SINF array out of bounds accesses
by Wupeng Ma 15 Oct '24

15 Oct '24

From: Hans de Goede <hdegoede(a)redhat.com> stable inclusion from stable-v6.6.52 commit 6821a82616f60aa72c5909b3e252ad97fb9f7e2a category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAUA6B CVE: CVE-2024-46859 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit f52e98d16e9bd7dd2b3aef8e38db5cbc9899d6a4 upstream. The panasonic laptop code in various places uses the SINF array with index values of 0 - SINF_CUR_BRIGHT(0x0d) without checking that the SINF array is big enough. Not all panasonic laptops have this many SINF array entries, for example the Toughbook CF-18 model only has 10 SINF array entries. So it only supports the AC+DC brightness entries and mute. Check that the SINF array has a minimum size which covers all AC+DC brightness entries and refuse to load if the SINF array is smaller. For higher SINF indexes hide the sysfs attributes when the SINF array does not contain an entry for that attribute, avoiding show()/store() accessing the array out of bounds and add bounds checking to the probe() and resume() code accessing these. Fixes: e424fb8cc4e6 ("panasonic-laptop: avoid overflow in acpi_pcc_hotkey_add()") Cc: stable(a)vger.kernel.org Signed-off-by: Hans de Goede <hdegoede(a)redhat.com> Link: https://lore.kernel.org/r/20240909113227.254470-1-hdegoede@redhat.com Reviewed-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com> Signed-off-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: drivers/platform/x86/panasonic-laptop.c [Ma Wupeng: mode SINF_ECO_MODE, SINF_CUR_BRIGHT do not exist until 5.11] Signed-off-by: Ma Wupeng <mawupeng1(a)huawei.com> --- drivers/platform/x86/panasonic-laptop.c | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) diff --git a/drivers/platform/x86/panasonic-laptop.c b/drivers/platform/x86/panasonic-laptop.c index 59e38a1d2830..5f18f15df6af 100644 --- a/drivers/platform/x86/panasonic-laptop.c +++ b/drivers/platform/x86/panasonic-laptop.c @@ -416,6 +416,18 @@ static DEVICE_ATTR(lcdtype, S_IRUGO, show_lcdtype, NULL); static DEVICE_ATTR(mute, S_IRUGO, show_mute, NULL); static DEVICE_ATTR(sticky_key, S_IRUGO | S_IWUSR, show_sticky, set_sticky); +static umode_t pcc_sysfs_is_visible(struct kobject *kobj, struct attribute *attr, int idx) +{ + struct device *dev = kobj_to_dev(kobj); + struct acpi_device *acpi = to_acpi_device(dev); + struct pcc_acpi *pcc = acpi_driver_data(acpi); + + if (attr == &dev_attr_mute.attr) + return (pcc->num_sifr > SINF_MUTE) ? attr->mode : 0; + + return attr->mode; +} + static struct attribute *pcc_sysfs_entries[] = { &dev_attr_numbatt.attr, &dev_attr_lcdtype.attr, @@ -425,8 +437,9 @@ static struct attribute *pcc_sysfs_entries[] = { }; static const struct attribute_group pcc_attr_group = { - .name = NULL, /* put in device directory */ - .attrs = pcc_sysfs_entries, + .name = NULL, /* put in device directory */ + .attrs = pcc_sysfs_entries, + .is_visible = pcc_sysfs_is_visible, }; @@ -546,8 +559,12 @@ static int acpi_pcc_hotkey_add(struct acpi_device *device) num_sifr = acpi_pcc_get_sqty(device); - if (num_sifr < 0 || num_sifr > 255) { - ACPI_DEBUG_PRINT((ACPI_DB_ERROR, "num_sifr out of range")); + /* + * pcc->sinf is expected to at least have the AC+DC brightness entries. + * Accesses to higher SINF entries are checked against num_sifr. + */ + if (num_sifr <= SINF_DC_CUR_BRIGHT || num_sifr > 255) { + ACPI_DEBUG_PRINT((ACPI_DB_ERROR, "num_sifr %d out of range %d - 255\n", num_sifr, SINF_DC_CUR_BRIGHT + 1)); return -ENODEV; } -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1] scsi: qla2xxx: During vport delete send async logout explicitly
by Wupeng Ma 15 Oct '24

15 Oct '24

From: Manish Rangankar <mrangankar(a)marvell.com> stable inclusion from stable-v5.10.224 commit e5ed6a26ffdec0c91cf0b6138afbd675c00ad5fc category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAKQ92 CVE: CVE-2024-42289 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 76f480d7c717368f29a3870f7d64471ce0ff8fb2 upstream. During vport delete, it is observed that during unload we hit a crash because of stale entries in outstanding command array. For all these stale I/O entries, eh_abort was issued and aborted (fast_fail_io = 2009h) but I/Os could not complete while vport delete is in process of deleting. BUG: kernel NULL pointer dereference, address: 000000000000001c #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP NOPTI Workqueue: qla2xxx_wq qla_do_work [qla2xxx] RIP: 0010:dma_direct_unmap_sg+0x51/0x1e0 RSP: 0018:ffffa1e1e150fc68 EFLAGS: 00010046 RAX: 0000000000000000 RBX: 0000000000000021 RCX: 0000000000000001 RDX: 0000000000000021 RSI: 0000000000000000 RDI: ffff8ce208a7a0d0 RBP: ffff8ce208a7a0d0 R08: 0000000000000000 R09: ffff8ce378aac9c8 R10: ffff8ce378aac8a0 R11: ffffa1e1e150f9d8 R12: 0000000000000000 R13: 0000000000000000 R14: ffff8ce378aac9c8 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff8d217f000000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000000001c CR3: 0000002089acc000 CR4: 0000000000350ee0 Call Trace: <TASK> qla2xxx_qpair_sp_free_dma+0x417/0x4e0 ? qla2xxx_qpair_sp_compl+0x10d/0x1a0 ? qla2x00_status_entry+0x768/0x2830 ? newidle_balance+0x2f0/0x430 ? dequeue_entity+0x100/0x3c0 ? qla24xx_process_response_queue+0x6a1/0x19e0 ? __schedule+0x2d5/0x1140 ? qla_do_work+0x47/0x60 ? process_one_work+0x267/0x440 ? process_one_work+0x440/0x440 ? worker_thread+0x2d/0x3d0 ? process_one_work+0x440/0x440 ? kthread+0x156/0x180 ? set_kthread_struct+0x50/0x50 ? ret_from_fork+0x22/0x30 </TASK> Send out async logout explicitly for all the ports during vport delete. Cc: stable(a)vger.kernel.org Signed-off-by: Manish Rangankar <mrangankar(a)marvell.com> Signed-off-by: Nilesh Javali <njavali(a)marvell.com> Link: https://lore.kernel.org/r/20240710171057.35066-8-njavali@marvell.com Reviewed-by: Himanshu Madhani <himanshu.madhani(a)oracle.com> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Ma Wupeng <mawupeng1(a)huawei.com> --- drivers/scsi/qla2xxx/qla_mid.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c index c7caf322f445..b98c390b4b27 100644 --- a/drivers/scsi/qla2xxx/qla_mid.c +++ b/drivers/scsi/qla2xxx/qla_mid.c @@ -164,7 +164,7 @@ qla24xx_disable_vp(scsi_qla_host_t *vha) atomic_set(&vha->loop_state, LOOP_DOWN); atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME); list_for_each_entry(fcport, &vha->vp_fcports, list) - fcport->logout_on_delete = 0; + fcport->logout_on_delete = 1; qla2x00_mark_all_devices_lost(vha); -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1] platform/x86: panasonic-laptop: Fix SINF array out of bounds accesses
by Wupeng Ma 15 Oct '24

15 Oct '24

From: Hans de Goede <hdegoede(a)redhat.com> stable inclusion from stable-v6.6.52 commit 6821a82616f60aa72c5909b3e252ad97fb9f7e2a category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAUA6B CVE: CVE-2024-46859 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit f52e98d16e9bd7dd2b3aef8e38db5cbc9899d6a4 upstream. The panasonic laptop code in various places uses the SINF array with index values of 0 - SINF_CUR_BRIGHT(0x0d) without checking that the SINF array is big enough. Not all panasonic laptops have this many SINF array entries, for example the Toughbook CF-18 model only has 10 SINF array entries. So it only supports the AC+DC brightness entries and mute. Check that the SINF array has a minimum size which covers all AC+DC brightness entries and refuse to load if the SINF array is smaller. For higher SINF indexes hide the sysfs attributes when the SINF array does not contain an entry for that attribute, avoiding show()/store() accessing the array out of bounds and add bounds checking to the probe() and resume() code accessing these. Fixes: e424fb8cc4e6 ("panasonic-laptop: avoid overflow in acpi_pcc_hotkey_add()") Cc: stable(a)vger.kernel.org Signed-off-by: Hans de Goede <hdegoede(a)redhat.com> Link: https://lore.kernel.org/r/20240909113227.254470-1-hdegoede@redhat.com Reviewed-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com> Signed-off-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: drivers/platform/x86/panasonic-laptop.c [Ma Wupeng: mode SINF_ECO_MODE, SINF_CUR_BRIGHT do not exist until 5.11] Signed-off-by: Ma Wupeng <mawupeng1(a)huawei.com> --- drivers/platform/x86/panasonic-laptop.c | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) diff --git a/drivers/platform/x86/panasonic-laptop.c b/drivers/platform/x86/panasonic-laptop.c index 59e38a1d2830..5f18f15df6af 100644 --- a/drivers/platform/x86/panasonic-laptop.c +++ b/drivers/platform/x86/panasonic-laptop.c @@ -416,6 +416,18 @@ static DEVICE_ATTR(lcdtype, S_IRUGO, show_lcdtype, NULL); static DEVICE_ATTR(mute, S_IRUGO, show_mute, NULL); static DEVICE_ATTR(sticky_key, S_IRUGO | S_IWUSR, show_sticky, set_sticky); +static umode_t pcc_sysfs_is_visible(struct kobject *kobj, struct attribute *attr, int idx) +{ + struct device *dev = kobj_to_dev(kobj); + struct acpi_device *acpi = to_acpi_device(dev); + struct pcc_acpi *pcc = acpi_driver_data(acpi); + + if (attr == &dev_attr_mute.attr) + return (pcc->num_sifr > SINF_MUTE) ? attr->mode : 0; + + return attr->mode; +} + static struct attribute *pcc_sysfs_entries[] = { &dev_attr_numbatt.attr, &dev_attr_lcdtype.attr, @@ -425,8 +437,9 @@ static struct attribute *pcc_sysfs_entries[] = { }; static const struct attribute_group pcc_attr_group = { - .name = NULL, /* put in device directory */ - .attrs = pcc_sysfs_entries, + .name = NULL, /* put in device directory */ + .attrs = pcc_sysfs_entries, + .is_visible = pcc_sysfs_is_visible, }; @@ -546,8 +559,12 @@ static int acpi_pcc_hotkey_add(struct acpi_device *device) num_sifr = acpi_pcc_get_sqty(device); - if (num_sifr < 0 || num_sifr > 255) { - ACPI_DEBUG_PRINT((ACPI_DB_ERROR, "num_sifr out of range")); + /* + * pcc->sinf is expected to at least have the AC+DC brightness entries. + * Accesses to higher SINF entries are checked against num_sifr. + */ + if (num_sifr <= SINF_DC_CUR_BRIGHT || num_sifr > 255) { + ACPI_DEBUG_PRINT((ACPI_DB_ERROR, "num_sifr %d out of range %d - 255\n", num_sifr, SINF_DC_CUR_BRIGHT + 1)); return -ENODEV; } -- 2.25.1

2 1

[openeuler:openEuler-1.0-LTS] BUILD REGRESSION 260ccfea902b0a60d1b7c40c1de0cfad0d119f5b
by kernel test robot 15 Oct '24

15 Oct '24

tree/branch: https://gitee.com/openeuler/kernel.git openEuler-1.0-LTS branch HEAD: 260ccfea902b0a60d1b7c40c1de0cfad0d119f5b !8720 net: USB: Fix wrong-direction WARNING in plusb.c Error/Warning ids grouped by kconfigs: recent_errors `-- x86_64-kexec `-- mm-memory.c:error:implicit-declaration-of-function-hugetlb_insert_hugepage_pte_by_pa-Werror-Wimplicit-function-declaration elapsed time: 1475m configs tested: 2 configs skipped: 6 tested configs: x86_64 kexec clang-18 x86_64 rhel-8.3 gcc-12 -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH OLK-6.6] net/hinic3: fix version showed in ethtool
by s00851154 15 Oct '24

15 Oct '24

From: Shi Jing <shijing34(a)huawei.com> driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAWIA2 CVE: NA -------------------------------- Fix the version in the output of ethtool commands from empty to the right version. Fixes: 3b469ecc9cb3 ("Add Huawei Intelligent Network Card Driver: hinic3") Signed-off-by: Shi Jing <shijing34(a)huawei.com> --- drivers/net/ethernet/huawei/hinic3/hinic3_crm.h | 2 +- drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_crm.h b/drivers/net/ethernet/huawei/hinic3/hinic3_crm.h index 195a5cf08f66e..f269691d757bc 100644 --- a/drivers/net/ethernet/huawei/hinic3/hinic3_crm.h +++ b/drivers/net/ethernet/huawei/hinic3/hinic3_crm.h @@ -8,7 +8,7 @@ #include "mpu_cmd_base_defs.h" -#define HINIC3_DRV_VERSION "" +#define HINIC3_DRV_VERSION "15.17.1.1" #define HINIC3_DRV_DESC "Intelligent Network Interface Card Driver" #define HIUDK_DRV_DESC "Intelligent Network Unified Driver" diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h index 2967311aab76c..800fa73613c86 100644 --- a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h +++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h @@ -17,7 +17,7 @@ #include "hinic3_dcb.h" #define HINIC3_NIC_DRV_NAME "hinic3" -#define HINIC3_NIC_DRV_VERSION "" +#define HINIC3_NIC_DRV_VERSION "15.17.1.1" #define HINIC3_FUNC_IS_VF(hwdev) (hinic3_func_type(hwdev) == TYPE_VF) -- 2.28.0.windows.1

2 1

[PATCH OLK-5.10 0/3] Some bugfixs for ubi/fs
by Zhihao Cheng 15 Oct '24

15 Oct '24

From: Zhihao Cheng <chengzhihao1(a)huawei.com> Amir Goldstein (1): locks: fix TOCTOU race when granting write lease Li Nan (1): ubi: block: fix null-pointer-dereference in ubiblock_create() Li zeming (1): ubi: block: Remove in vain semicolon drivers/mtd/ubi/block.c | 9 +++++---- fs/file_table.c | 7 +------ fs/internal.h | 10 ++++++++++ fs/open.c | 11 ++++------- 4 files changed, 20 insertions(+), 17 deletions(-) -- 2.39.2

2 4

[PATCH v2 OLK-5.10] atm: idt77252: prevent use after free in dequeue_rx()
by Peng Zhang 15 Oct '24

15 Oct '24

From: Dan Carpenter <dan.carpenter(a)linaro.org> stable inclusion from stable-v5.10.225 commit 1cece837e387c039225f19028df255df87a97c0d category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAOXZG CVE: CVE-2024-44998 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit a9a18e8f770c9b0703dab93580d0b02e199a4c79 ] We can't dereference "skb" after calling vcc->push() because the skb is released. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Dan Carpenter <dan.carpenter(a)linaro.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: ZhangPeng <zhangpeng362(a)huawei.com> --- drivers/atm/idt77252.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index e616e33c8a20..25fd73fafb37 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -1118,8 +1118,8 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe) rpp->len += skb->len; if (stat & SAR_RSQE_EPDU) { + unsigned int len, truesize; unsigned char *l1l2; - unsigned int len; l1l2 = (unsigned char *) ((unsigned long) skb->data + skb->len - 6); @@ -1189,14 +1189,15 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe) ATM_SKB(skb)->vcc = vcc; __net_timestamp(skb); + truesize = skb->truesize; vcc->push(vcc, skb); atomic_inc(&vcc->stats->rx); - if (skb->truesize > SAR_FB_SIZE_3) + if (truesize > SAR_FB_SIZE_3) add_rx_skb(card, 3, SAR_FB_SIZE_3, 1); - else if (skb->truesize > SAR_FB_SIZE_2) + else if (truesize > SAR_FB_SIZE_2) add_rx_skb(card, 2, SAR_FB_SIZE_2, 1); - else if (skb->truesize > SAR_FB_SIZE_1) + else if (truesize > SAR_FB_SIZE_1) add_rx_skb(card, 1, SAR_FB_SIZE_1, 1); else add_rx_skb(card, 0, SAR_FB_SIZE_0, 1); -- 2.25.1

2 1

[PATCH v2 openEuler-22.03-LTS-SP1] atm: idt77252: prevent use after free in dequeue_rx()
by Peng Zhang 15 Oct '24

15 Oct '24

From: Dan Carpenter <dan.carpenter(a)linaro.org> stable inclusion from stable-v5.10.225 commit 1cece837e387c039225f19028df255df87a97c0d category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAOXZG CVE: CVE-2024-44998 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit a9a18e8f770c9b0703dab93580d0b02e199a4c79 ] We can't dereference "skb" after calling vcc->push() because the skb is released. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Dan Carpenter <dan.carpenter(a)linaro.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: ZhangPeng <zhangpeng362(a)huawei.com> --- drivers/atm/idt77252.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index e616e33c8a20..25fd73fafb37 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -1118,8 +1118,8 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe) rpp->len += skb->len; if (stat & SAR_RSQE_EPDU) { + unsigned int len, truesize; unsigned char *l1l2; - unsigned int len; l1l2 = (unsigned char *) ((unsigned long) skb->data + skb->len - 6); @@ -1189,14 +1189,15 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe) ATM_SKB(skb)->vcc = vcc; __net_timestamp(skb); + truesize = skb->truesize; vcc->push(vcc, skb); atomic_inc(&vcc->stats->rx); - if (skb->truesize > SAR_FB_SIZE_3) + if (truesize > SAR_FB_SIZE_3) add_rx_skb(card, 3, SAR_FB_SIZE_3, 1); - else if (skb->truesize > SAR_FB_SIZE_2) + else if (truesize > SAR_FB_SIZE_2) add_rx_skb(card, 2, SAR_FB_SIZE_2, 1); - else if (skb->truesize > SAR_FB_SIZE_1) + else if (truesize > SAR_FB_SIZE_1) add_rx_skb(card, 1, SAR_FB_SIZE_1, 1); else add_rx_skb(card, 0, SAR_FB_SIZE_0, 1); -- 2.25.1

2 1

[PATCH OLK-5.10 v6 00/12] xfs: some fix for forcealign
by Long Li 15 Oct '24

15 Oct '24

This patch set fix some bug for forcealign: patch 1 ~ 6 : fix tail alignment issue while approach to no space. patch 7 : fix forcealign not compatible with reflink and realtime. patch 8 : only datafork need bunmap algin for focealign patch 9 ~ 12 : fix truncate for forcealign Dave Chinner (3): xfs: only allow minlen allocations when near ENOSPC xfs: always tail align maxlen allocations xfs: align args->minlen for forced allocation alignment John Garry (1): xfs: Don't revert allocated offset for forcealign Long Li (5): xfs: don't attempting non-aligned fallbacks alloc for forcealign xfs: simplify extent allocation alignment xfs: forcealign not compatible with reflink and realtime device xfs: only bunmap align in datafork for forcealign xfs: correct the truncate blocksize of forcealign Zhang Yi (3): math64: add rem_u64() to just return the remainder iomap: pass blocksize to iomap_truncate_page() xfs: refactor the truncating order fs/iomap/buffered-io.c | 8 +-- fs/xfs/libxfs/xfs_alloc.c | 31 +++++---- fs/xfs/libxfs/xfs_bmap.c | 140 ++++++++++++++++++++------------------ fs/xfs/xfs_iops.c | 124 +++++++++++++++++---------------- fs/xfs/xfs_super.c | 19 +++++- include/linux/iomap.h | 4 +- include/linux/math64.h | 24 +++++++ 7 files changed, 208 insertions(+), 142 deletions(-) -- 2.39.2

2 13

[openeuler:OLK-5.10 22909/30000] kernel/sched/topology.c:1749:9: error: implicit declaration of function 'register_sysctl_init'; did you mean 'register_sysctl'?
by kernel test robot 15 Oct '24

15 Oct '24

tree: https://gitee.com/openeuler/kernel.git OLK-5.10 head: 5f264976b651040f3fac9a10fca21c542662709b commit: f4128ae8e6ff03b4c805707fe75d0345797f7f53 [22909/30000] sched: Add cluster scheduler level for x86 config: x86_64-buildonly-randconfig-002-20241013 (https://download.01.org/0day-ci/archive/20241015/202410150906.0KpoaIkq-lkp@…) compiler: gcc-12 (Debian 12.2.0-14) 12.2.0 reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20241015/202410150906.0KpoaIkq-lkp@…) If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <lkp(a)intel.com> | Closes: https://lore.kernel.org/oe-kbuild-all/202410150906.0KpoaIkq-lkp@intel.com/ All errors (new ones prefixed by >>): kernel/sched/topology.c: In function 'sched_cluster_sysctl_init': >> kernel/sched/topology.c:1749:9: error: implicit declaration of function 'register_sysctl_init'; did you mean 'register_sysctl'? [-Werror=implicit-function-declaration] 1749 | register_sysctl_init("kernel", sched_cluster_sysctls); | ^~~~~~~~~~~~~~~~~~~~ | register_sysctl cc1: some warnings being treated as errors vim +1749 kernel/sched/topology.c 8ce3e706b31409 Tim Chen 2021-12-03 1746 8ce3e706b31409 Tim Chen 2021-12-03 1747 static int __init sched_cluster_sysctl_init(void) 8ce3e706b31409 Tim Chen 2021-12-03 1748 { 8ce3e706b31409 Tim Chen 2021-12-03 @1749 register_sysctl_init("kernel", sched_cluster_sysctls); 8ce3e706b31409 Tim Chen 2021-12-03 1750 return 0; 8ce3e706b31409 Tim Chen 2021-12-03 1751 } 8ce3e706b31409 Tim Chen 2021-12-03 1752 late_initcall(sched_cluster_sysctl_init); 9e68cc2bf535a2 Tim Chen 2021-12-03 1753 :::::: The code at line 1749 was first introduced by commit :::::: 8ce3e706b31409147f035c037055caa68e450ce5 scheduler: Add runtime knob sysctl_sched_cluster :::::: TO: Tim Chen <tim.c.chen(a)linux.intel.com> :::::: CC: Jie Liu <liujie375(a)h-partners.com> -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH OLK-5.10 0/2] Backport "ima: Avoid blocking in RCU read-side critical section"
by Gu Bowen 15 Oct '24

15 Oct '24

Revert self-developed solution and backport mainline one. GUO Zihua (1): ima: Avoid blocking in RCU read-side critical section Gu Bowen (1): Revert "ima: Avoid blocking in RCU read-side critical section" include/linux/lsm_hook_defs.h | 2 +- include/linux/security.h | 5 +++-- kernel/auditfilter.c | 5 +++-- security/apparmor/audit.c | 6 +++--- security/apparmor/include/audit.h | 2 +- security/integrity/ima/ima.h | 2 +- security/integrity/ima/ima_policy.c | 15 +++++++++------ security/security.c | 6 ++++-- security/selinux/include/audit.h | 4 +++- security/selinux/ss/services.c | 5 +++-- security/smack/smack_lsm.c | 4 +++- 11 files changed, 34 insertions(+), 22 deletions(-) -- 2.25.1

2 3

[PATCH openEuler-22.03-LTS-SP1] spi: hisi-kunpeng: Add verification for the max_frequency provided by the firmware
by Yongjian Sun 14 Oct '24

14 Oct '24

From: Devyn Liu <liudingyuan(a)huawei.com> mainline inclusion from mainline-v6.11-rc3 commit 5127c42c77de18651aa9e8e0a3ced190103b449c category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAVU80 CVE: CVE-2024-47664 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- If the value of max_speed_hz is 0, it may cause a division by zero error in hisi_calc_effective_speed(). The value of max_speed_hz is provided by firmware. Firmware is generally considered as a trusted domain. However, as division by zero errors can cause system failure, for defense measure, the value of max_speed is validated here. So 0 is regarded as invalid and an error code is returned. Signed-off-by: Devyn Liu <liudingyuan(a)huawei.com> Reviewed-by: Jay Fang <f.fangjian(a)huawei.com> Link: https://patch.msgid.link/20240730032040.3156393-3-liudingyuan@huawei.com Signed-off-by: Mark Brown <broonie(a)kernel.org> Conflicts: drivers/spi/spi-hisi-kunpeng.c [The author changed the variable naming, replacing all instances of "master" with "host", which aligns with modern naming conventions.] Signed-off-by: Yongjian Sun <sunyongjian1(a)huawei.com> --- drivers/spi/spi-hisi-kunpeng.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/spi/spi-hisi-kunpeng.c b/drivers/spi/spi-hisi-kunpeng.c index 525cc0143a30..54e05fb0387e 100644 --- a/drivers/spi/spi-hisi-kunpeng.c +++ b/drivers/spi/spi-hisi-kunpeng.c @@ -483,6 +483,9 @@ static int hisi_spi_probe(struct platform_device *pdev) return -EINVAL; } + if (master->max_speed_hz == 0) + return dev_err_probe(dev, -EINVAL, "spi-max-frequency can't be 0\n"); + ret = device_property_read_u16(dev, "num-cs", &master->num_chipselect); if (ret) -- 2.39.2

2 1

[openeuler:OLK-5.10 15571/30000] mm/memcontrol.c:5402:40: error: implicit declaration of function 'ksm_process_profit'
by kernel test robot 14 Oct '24

14 Oct '24

Hi Nanyong, FYI, the error/warning still remains. tree: https://gitee.com/openeuler/kernel.git OLK-5.10 head: 748eeb7da1ecddfb1ace5ec61a512befe217702e commit: 0f6fb3570be40b783d8c756d64297be1a8e3d2b3 [15571/30000] memcg: support ksm merge any mode per cgroup config: x86_64-buildonly-randconfig-002-20241013 (https://download.01.org/0day-ci/archive/20241014/202410142209.nmkFxV8P-lkp@…) compiler: gcc-12 (Debian 12.2.0-14) 12.2.0 reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20241014/202410142209.nmkFxV8P-lkp@…) If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <lkp(a)intel.com> | Closes: https://lore.kernel.org/oe-kbuild-all/202410142209.nmkFxV8P-lkp@intel.com/ All errors (new ones prefixed by >>): mm/memcontrol.c: In function 'memory_ksm_show': >> mm/memcontrol.c:5402:40: error: implicit declaration of function 'ksm_process_profit' [-Werror=implicit-function-declaration] 5402 | ksm_process_profits += ksm_process_profit(mm); | ^~~~~~~~~~~~~~~~~~ cc1: some warnings being treated as errors vim +/ksm_process_profit +5402 mm/memcontrol.c 5379 5380 static int memory_ksm_show(struct seq_file *m, void *v) 5381 { 5382 unsigned long ksm_merging_pages = 0; 5383 unsigned long ksm_rmap_items = 0; 5384 long ksm_process_profits = 0; 5385 unsigned int tasks = 0; 5386 struct task_struct *task; 5387 struct mm_struct *mm; 5388 struct css_task_iter it; 5389 struct mem_cgroup *memcg = mem_cgroup_from_seq(m); 5390 5391 css_task_iter_start(&memcg->css, CSS_TASK_ITER_PROCS, &it); 5392 while ((task = css_task_iter_next(&it))) { 5393 mm = get_task_mm(task); 5394 if (!mm) 5395 continue; 5396 5397 if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) 5398 tasks++; 5399 5400 ksm_rmap_items += mm->ksm_rmap_items; 5401 ksm_merging_pages += mm->ksm_merging_pages; > 5402 ksm_process_profits += ksm_process_profit(mm); 5403 mmput(mm); 5404 } 5405 css_task_iter_end(&it); 5406 5407 seq_printf(m, "merge any state: %d\n", READ_ONCE(memcg->ksm_merge_any)); 5408 seq_printf(m, "merge any tasks: %u\n", tasks); 5409 seq_printf(m, "ksm_rmap_items %lu\n", ksm_rmap_items); 5410 seq_printf(m, "ksm_merging_pages %lu\n", ksm_merging_pages); 5411 seq_printf(m, "ksm_process_profits %ld\n", ksm_process_profits); 5412 return 0; 5413 } 5414 -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH OLK-5.10] netfilter: nf_tables: use timestamp to check for set element timeout
by Liu Jian 14 Oct '24

14 Oct '24

From: Pablo Neira Ayuso <pablo(a)netfilter.org> mainline inclusion from mainline-v6.8-rc4 commit 7395dfacfff65e9938ac0889dafa1ab01e987d15 category: bugfix bugzilla: 189924 CVE: CVE-2024-27397 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- Add a timestamp field at the beginning of the transaction, store it in the nftables per-netns area. Update set backend .insert, .deactivate and sync gc path to use the timestamp, this avoids that an element expires while control plane transaction is still unfinished. .lookup and .update, which are used from packet path, still use the current time to check if the element has expired. And .get path and dump also since this runs lockless under rcu read size lock. Then, there is async gc which also needs to check the current time since it runs asynchronously from a workqueue. Fixes: c3e1b005ed1c ("netfilter: nf_tables: add set element timeout support") Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Conflicts: include/net/netfilter/nf_tables.h net/netfilter/nf_tables_api.c net/netfilter/nft_set_pipapo.c net/netfilter/nft_set_rbtree.c [Do not backport nft_rbtree_gc() part, it is a async gc in our repository. Others caused by we did not backport commit ab482c6b66a4, b2d306542ff9, 8837ba3e58ea, 5f68718b34a5, d59d2f82f984.] Signed-off-by: Liu Jian <liujian56(a)huawei.com> --- include/net/netfilter/nf_tables.h | 24 ++++++++++++++++++++++-- net/netfilter/nf_tables_api.c | 1 + net/netfilter/nft_set_hash.c | 8 +++++++- net/netfilter/nft_set_pipapo.c | 18 +++++++++++------- net/netfilter/nft_set_rbtree.c | 6 ++++-- 5 files changed, 45 insertions(+), 12 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 17659138e15a..a6e221de31ef 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -13,6 +13,7 @@ #include <net/netfilter/nf_flow_table.h> #include <net/netlink.h> #include <net/flow_offload.h> +#include <net/netns/generic.h> #define NFT_MAX_HOOKS (NF_INET_INGRESS + 1) @@ -700,10 +701,16 @@ static inline struct nft_expr *nft_set_ext_expr(const struct nft_set_ext *ext) return nft_set_ext(ext, NFT_SET_EXT_EXPR); } -static inline bool nft_set_elem_expired(const struct nft_set_ext *ext) +static inline bool __nft_set_elem_expired(const struct nft_set_ext *ext, + u64 tstamp) { return nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION) && - time_is_before_eq_jiffies64(*nft_set_ext_expiration(ext)); + time_after_eq64(tstamp, *nft_set_ext_expiration(ext)); +} + +static inline bool nft_set_elem_expired(const struct nft_set_ext *ext) +{ + return __nft_set_elem_expired(ext, get_jiffies_64()); } static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set, @@ -1592,9 +1599,22 @@ struct nftables_pernet { struct list_head module_list; struct list_head notify_list; struct mutex commit_mutex; + u64 tstamp; unsigned int base_seq; u8 validate_state; unsigned int gc_seq; }; +extern unsigned int nf_tables_net_id; + +static inline struct nftables_pernet *nft_pernet(const struct net *net) +{ + return net_generic(net, nf_tables_net_id); +} + +static inline u64 nft_net_tstamp(const struct net *net) +{ + return nft_pernet(net)->tstamp; +} + #endif /* _NET_NF_TABLES_H */ diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 82526a768e15..81caffd53912 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -9074,6 +9074,7 @@ static bool nf_tables_valid_genid(struct net *net, u32 genid) bool genid_ok; mutex_lock(&nft_net->commit_mutex); + nft_net->tstamp = get_jiffies_64(); genid_ok = genid == 0 || nft_net->base_seq == genid; if (!genid_ok) diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index f4a76ae8a11c..1c52e0559011 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -38,6 +38,7 @@ struct nft_rhash_cmp_arg { const struct nft_set *set; const u32 *key; u8 genmask; + u64 tstamp; }; static inline u32 nft_rhash_key(const void *data, u32 len, u32 seed) @@ -64,7 +65,7 @@ static inline int nft_rhash_cmp(struct rhashtable_compare_arg *arg, return 1; if (nft_set_elem_is_dead(&he->ext)) return 1; - if (nft_set_elem_expired(&he->ext)) + if (__nft_set_elem_expired(&he->ext, x->tstamp)) return 1; if (!nft_set_elem_active(&he->ext, x->genmask)) return 1; @@ -88,6 +89,7 @@ static bool nft_rhash_lookup(const struct net *net, const struct nft_set *set, .genmask = nft_genmask_cur(net), .set = set, .key = key, + .tstamp = get_jiffies_64(), }; he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); @@ -106,6 +108,7 @@ static void *nft_rhash_get(const struct net *net, const struct nft_set *set, .genmask = nft_genmask_cur(net), .set = set, .key = elem->key.val.data, + .tstamp = get_jiffies_64(), }; he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); @@ -129,6 +132,7 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key, .genmask = NFT_GENMASK_ANY, .set = set, .key = key, + .tstamp = get_jiffies_64(), }; he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); @@ -172,6 +176,7 @@ static int nft_rhash_insert(const struct net *net, const struct nft_set *set, .genmask = nft_genmask_next(net), .set = set, .key = elem->key.val.data, + .tstamp = nft_net_tstamp(net), }; struct nft_rhash_elem *prev; @@ -214,6 +219,7 @@ static void *nft_rhash_deactivate(const struct net *net, .genmask = nft_genmask_next(net), .set = set, .key = elem->key.val.data, + .tstamp = nft_net_tstamp(net), }; rcu_read_lock(); diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 2a147e969c66..65ecf486f8d1 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -504,6 +504,7 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, * @set: nftables API set representation * @data: Key data to be matched against existing elements * @genmask: If set, check that element is active in given genmask + * @tstamp: timestamp to check for expired elements * * This is essentially the same as the lookup function, except that it matches * key data against the uncommitted copy and doesn't use preallocated maps for @@ -513,7 +514,8 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, */ static struct nft_pipapo_elem *pipapo_get(const struct net *net, const struct nft_set *set, - const u8 *data, u8 genmask) + const u8 *data, u8 genmask, + u64 tstamp) { struct nft_pipapo_elem *ret = ERR_PTR(-ENOENT); struct nft_pipapo *priv = nft_set_priv(set); @@ -566,7 +568,7 @@ static struct nft_pipapo_elem *pipapo_get(const struct net *net, goto out; if (last) { - if (nft_set_elem_expired(&f->mt[b].e->ext)) + if (__nft_set_elem_expired(&f->mt[b].e->ext, tstamp)) goto next_match; if ((genmask && !nft_set_elem_active(&f->mt[b].e->ext, genmask))) @@ -603,7 +605,7 @@ static void *nft_pipapo_get(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags) { return pipapo_get(net, set, (const u8 *)elem->key.val.data, - nft_genmask_cur(net)); + nft_genmask_cur(net), get_jiffies_64()); } /** @@ -1197,6 +1199,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m = priv->clone; u8 genmask = nft_genmask_next(net); + u64 tstamp = nft_net_tstamp(net); struct nft_pipapo_field *f; const u8 *start_p, *end_p; int i, bsize_max, err = 0; @@ -1206,7 +1209,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, else end = start; - dup = pipapo_get(net, set, start, genmask); + dup = pipapo_get(net, set, start, genmask, tstamp); if (!IS_ERR(dup)) { /* Check if we already have the same exact entry */ const struct nft_data *dup_key, *dup_end; @@ -1228,7 +1231,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, if (PTR_ERR(dup) == -ENOENT) { /* Look for partially overlapping entries */ - dup = pipapo_get(net, set, end, nft_genmask_next(net)); + dup = pipapo_get(net, set, end, nft_genmask_next(net), tstamp); } if (PTR_ERR(dup) != -ENOENT) { @@ -1580,6 +1583,7 @@ static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) struct nft_set *set = (struct nft_set *) _set; struct nft_pipapo *priv = nft_set_priv(set); struct net *net = read_pnet(&set->net); + u64 tstamp = nft_net_tstamp(net); int rules_f0, first_rule = 0; struct nft_trans_gc *gc; @@ -1613,7 +1617,7 @@ static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) /* synchronous gc never fails, there is no need to set on * NFT_SET_ELEM_DEAD_BIT. */ - if (nft_set_elem_expired(&e->ext)) { + if (__nft_set_elem_expired(&e->ext, tstamp)) { priv->dirty = true; gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); @@ -1772,7 +1776,7 @@ static void *pipapo_deactivate(const struct net *net, const struct nft_set *set, { struct nft_pipapo_elem *e; - e = pipapo_get(net, set, data, nft_genmask_next(net)); + e = pipapo_get(net, set, data, nft_genmask_next(net), nft_net_tstamp(net)); if (IS_ERR(e)) return NULL; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 323cbb446d19..2d29cf8d51e0 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -314,6 +314,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct rb_node *node, *next, *parent, **p, *first = NULL; struct nft_rbtree *priv = nft_set_priv(set); u8 genmask = nft_genmask_next(net); + u64 tstamp = nft_net_tstamp(net); int d, err; /* Descend the tree to search for an existing element greater than the @@ -359,7 +360,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, continue; /* perform garbage collection to avoid bogus overlap reports. */ - if (nft_set_elem_expired(&rbe->ext)) { + if (__nft_set_elem_expired(&rbe->ext, tstamp)) { err = nft_rbtree_gc_elem(set, priv, rbe); if (err < 0) return err; @@ -533,6 +534,7 @@ static void *nft_rbtree_deactivate(const struct net *net, const struct rb_node *parent = priv->root.rb_node; struct nft_rbtree_elem *rbe, *this = elem->priv; u8 genmask = nft_genmask_next(net); + u64 tstamp = nft_net_tstamp(net); int d; while (parent != NULL) { @@ -553,7 +555,7 @@ static void *nft_rbtree_deactivate(const struct net *net, nft_rbtree_interval_end(this)) { parent = parent->rb_right; continue; - } else if (nft_set_elem_expired(&rbe->ext)) { + } else if (__nft_set_elem_expired(&rbe->ext, tstamp)) { break; } else if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = parent->rb_left; -- 2.34.1

2 1

[PATCH OLK-6.6] netfilter: nf_tables: use timestamp to check for set element timeout
by Liu Jian 14 Oct '24

14 Oct '24

From: Pablo Neira Ayuso <pablo(a)netfilter.org> mainline inclusion from mainline-v6.8-rc4 commit 7395dfacfff65e9938ac0889dafa1ab01e987d15 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9O0MR CVE: CVE-2024-27397 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- Add a timestamp field at the beginning of the transaction, store it in the nftables per-netns area. Update set backend .insert, .deactivate and sync gc path to use the timestamp, this avoids that an element expires while control plane transaction is still unfinished. .lookup and .update, which are used from packet path, still use the current time to check if the element has expired. And .get path and dump also since this runs lockless under rcu read size lock. Then, there is async gc which also needs to check the current time since it runs asynchronously from a workqueue. Fixes: c3e1b005ed1c ("netfilter: nf_tables: add set element timeout support") Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Conflicts: net/netfilter/nft_set_pipapo.c net/netfilter/nft_set_rbtree.c net/netfilter/nf_tables_api.c [Do not backport nft_rbtree_gc() part, it is a async gc in our repository. The sync gc need backport 7d259f021aaa. Another caused by we did not backport commit 9dad402b89e8.] Signed-off-by: Liu Jian <liujian56(a)huawei.com> --- include/net/netfilter/nf_tables.h | 16 ++++++++++++++-- net/netfilter/nf_tables_api.c | 4 +++- net/netfilter/nft_set_hash.c | 8 +++++++- net/netfilter/nft_set_pipapo.c | 18 +++++++++++------- net/netfilter/nft_set_rbtree.c | 6 ++++-- 5 files changed, 39 insertions(+), 13 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 8af2543520b9..45dc6922dec0 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -794,10 +794,16 @@ static inline struct nft_set_elem_expr *nft_set_ext_expr(const struct nft_set_ex return nft_set_ext(ext, NFT_SET_EXT_EXPRESSIONS); } -static inline bool nft_set_elem_expired(const struct nft_set_ext *ext) +static inline bool __nft_set_elem_expired(const struct nft_set_ext *ext, + u64 tstamp) { return nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION) && - time_is_before_eq_jiffies64(*nft_set_ext_expiration(ext)); + time_after_eq64(tstamp, *nft_set_ext_expiration(ext)); +} + +static inline bool nft_set_elem_expired(const struct nft_set_ext *ext) +{ + return __nft_set_elem_expired(ext, get_jiffies_64()); } static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set, @@ -1740,6 +1746,7 @@ struct nftables_pernet { struct list_head notify_list; struct mutex commit_mutex; u64 table_handle; + u64 tstamp; unsigned int base_seq; unsigned int gc_seq; u8 validate_state; @@ -1752,6 +1759,11 @@ static inline struct nftables_pernet *nft_pernet(const struct net *net) return net_generic(net, nf_tables_net_id); } +static inline u64 nft_net_tstamp(const struct net *net) +{ + return nft_pernet(net)->tstamp; +} + #define __NFT_REDUCE_READONLY 1UL #define NFT_REDUCE_READONLY (void *)__NFT_REDUCE_READONLY diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index ea139fca74cb..1899ec55b872 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -9773,6 +9773,7 @@ struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc, struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc) { struct nft_set_elem_catchall *catchall, *next; + u64 tstamp = nft_net_tstamp(gc->net); const struct nft_set *set = gc->set; struct nft_set_elem elem; struct nft_set_ext *ext; @@ -9782,7 +9783,7 @@ struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc) list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_set_elem_expired(ext)) + if (!__nft_set_elem_expired(ext, tstamp)) continue; gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); @@ -10581,6 +10582,7 @@ static bool nf_tables_valid_genid(struct net *net, u32 genid) bool genid_ok; mutex_lock(&nft_net->commit_mutex); + nft_net->tstamp = get_jiffies_64(); genid_ok = genid == 0 || nft_net->base_seq == genid; if (!genid_ok) diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 2013de934cef..1fd3b413350d 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -35,6 +35,7 @@ struct nft_rhash_cmp_arg { const struct nft_set *set; const u32 *key; u8 genmask; + u64 tstamp; }; static inline u32 nft_rhash_key(const void *data, u32 len, u32 seed) @@ -61,7 +62,7 @@ static inline int nft_rhash_cmp(struct rhashtable_compare_arg *arg, return 1; if (nft_set_elem_is_dead(&he->ext)) return 1; - if (nft_set_elem_expired(&he->ext)) + if (__nft_set_elem_expired(&he->ext, x->tstamp)) return 1; if (!nft_set_elem_active(&he->ext, x->genmask)) return 1; @@ -86,6 +87,7 @@ bool nft_rhash_lookup(const struct net *net, const struct nft_set *set, .genmask = nft_genmask_cur(net), .set = set, .key = key, + .tstamp = get_jiffies_64(), }; he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); @@ -104,6 +106,7 @@ static void *nft_rhash_get(const struct net *net, const struct nft_set *set, .genmask = nft_genmask_cur(net), .set = set, .key = elem->key.val.data, + .tstamp = get_jiffies_64(), }; he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); @@ -127,6 +130,7 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key, .genmask = NFT_GENMASK_ANY, .set = set, .key = key, + .tstamp = get_jiffies_64(), }; he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); @@ -170,6 +174,7 @@ static int nft_rhash_insert(const struct net *net, const struct nft_set *set, .genmask = nft_genmask_next(net), .set = set, .key = elem->key.val.data, + .tstamp = nft_net_tstamp(net), }; struct nft_rhash_elem *prev; @@ -212,6 +217,7 @@ static void *nft_rhash_deactivate(const struct net *net, .genmask = nft_genmask_next(net), .set = set, .key = elem->key.val.data, + .tstamp = nft_net_tstamp(net), }; rcu_read_lock(); diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index e4dd73093048..b72d9f7ff78f 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -504,6 +504,7 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, * @set: nftables API set representation * @data: Key data to be matched against existing elements * @genmask: If set, check that element is active in given genmask + * @tstamp: timestamp to check for expired elements * * This is essentially the same as the lookup function, except that it matches * key data against the uncommitted copy and doesn't use preallocated maps for @@ -513,7 +514,8 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, */ static struct nft_pipapo_elem *pipapo_get(const struct net *net, const struct nft_set *set, - const u8 *data, u8 genmask) + const u8 *data, u8 genmask, + u64 tstamp) { struct nft_pipapo_elem *ret = ERR_PTR(-ENOENT); struct nft_pipapo *priv = nft_set_priv(set); @@ -568,7 +570,7 @@ static struct nft_pipapo_elem *pipapo_get(const struct net *net, goto out; if (last) { - if (nft_set_elem_expired(&f->mt[b].e->ext)) + if (__nft_set_elem_expired(&f->mt[b].e->ext, tstamp)) goto next_match; if ((genmask && !nft_set_elem_active(&f->mt[b].e->ext, genmask))) @@ -605,7 +607,7 @@ static void *nft_pipapo_get(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags) { return pipapo_get(net, set, (const u8 *)elem->key.val.data, - nft_genmask_cur(net)); + nft_genmask_cur(net), get_jiffies_64()); } /** @@ -1199,6 +1201,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m = priv->clone; u8 genmask = nft_genmask_next(net); + u64 tstamp = nft_net_tstamp(net); struct nft_pipapo_field *f; const u8 *start_p, *end_p; int i, bsize_max, err = 0; @@ -1208,7 +1211,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, else end = start; - dup = pipapo_get(net, set, start, genmask); + dup = pipapo_get(net, set, start, genmask, tstamp); if (!IS_ERR(dup)) { /* Check if we already have the same exact entry */ const struct nft_data *dup_key, *dup_end; @@ -1230,7 +1233,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, if (PTR_ERR(dup) == -ENOENT) { /* Look for partially overlapping entries */ - dup = pipapo_get(net, set, end, nft_genmask_next(net)); + dup = pipapo_get(net, set, end, nft_genmask_next(net), tstamp); } if (PTR_ERR(dup) != -ENOENT) { @@ -1582,6 +1585,7 @@ static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) struct nft_set *set = (struct nft_set *) _set; struct nft_pipapo *priv = nft_set_priv(set); struct net *net = read_pnet(&set->net); + u64 tstamp = nft_net_tstamp(net); int rules_f0, first_rule = 0; struct nft_pipapo_elem *e; struct nft_trans_gc *gc; @@ -1616,7 +1620,7 @@ static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) /* synchronous gc never fails, there is no need to set on * NFT_SET_ELEM_DEAD_BIT. */ - if (nft_set_elem_expired(&e->ext)) { + if (__nft_set_elem_expired(&e->ext, tstamp)) { priv->dirty = true; gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); @@ -1787,7 +1791,7 @@ static void *pipapo_deactivate(const struct net *net, const struct nft_set *set, { struct nft_pipapo_elem *e; - e = pipapo_get(net, set, data, nft_genmask_next(net)); + e = pipapo_get(net, set, data, nft_genmask_next(net), nft_net_tstamp(net)); if (IS_ERR(e)) return NULL; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 5bf5572e945c..021d9e76129a 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -314,6 +314,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree *priv = nft_set_priv(set); u8 cur_genmask = nft_genmask_cur(net); u8 genmask = nft_genmask_next(net); + u64 tstamp = nft_net_tstamp(net); int d; /* Descend the tree to search for an existing element greater than the @@ -361,7 +362,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, /* perform garbage collection to avoid bogus overlap reports * but skip new elements in this transaction. */ - if (nft_set_elem_expired(&rbe->ext) && + if (__nft_set_elem_expired(&rbe->ext, tstamp) && nft_set_elem_active(&rbe->ext, cur_genmask)) { const struct nft_rbtree_elem *removed_end; @@ -548,6 +549,7 @@ static void *nft_rbtree_deactivate(const struct net *net, const struct rb_node *parent = priv->root.rb_node; struct nft_rbtree_elem *rbe, *this = elem->priv; u8 genmask = nft_genmask_next(net); + u64 tstamp = nft_net_tstamp(net); int d; while (parent != NULL) { @@ -568,7 +570,7 @@ static void *nft_rbtree_deactivate(const struct net *net, nft_rbtree_interval_end(this)) { parent = parent->rb_right; continue; - } else if (nft_set_elem_expired(&rbe->ext)) { + } else if (__nft_set_elem_expired(&rbe->ext, tstamp)) { break; } else if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = parent->rb_left; -- 2.34.1

2 1

[PATCH OLK-6.6 0/2] CVE-2024-38608
by Liu Jian 14 Oct '24

14 Oct '24

CVE-2024-38608 Shay Drory (1): net/mlx5e: Fix netif state handling Tariq Toukan (1): net/mlx5e: Add wrapping for auxiliary_driver ops and remove unused args .../net/ethernet/mellanox/mlx5/core/en_main.c | 24 ++++++++++++------- 1 file changed, 16 insertions(+), 8 deletions(-) -- 2.34.1

2 3

[PATCH OLK-5.10] net/mlx5e: Fix netif state handling
by Liu Jian 14 Oct '24

14 Oct '24

From: Shay Drory <shayd(a)nvidia.com> mainline inclusion from mainline-v6.10-rc1 commit 3d5918477f94e4c2f064567875c475468e264644 category: bugfix bugzilla: 190126 CVE: CVE-2024-38608 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- mlx5e_suspend cleans resources only if netif_device_present() returns true. However, mlx5e_resume changes the state of netif, via mlx5e_nic_enable, only if reg_state == NETREG_REGISTERED. In the below case, the above leads to NULL-ptr Oops[1] and memory leaks: mlx5e_probe _mlx5e_resume mlx5e_attach_netdev mlx5e_nic_enable <-- netdev not reg, not calling netif_device_attach() register_netdev <-- failed for some reason. ERROR_FLOW: _mlx5e_suspend <-- netif_device_present return false, resources aren't freed :( Hence, clean resources in this case as well. [1] BUG: kernel NULL pointer dereference, address: 0000000000000000 PGD 0 P4D 0 Oops: 0010 [#1] SMP CPU: 2 PID: 9345 Comm: test-ovs-ct-gen Not tainted 6.5.0_for_upstream_min_debug_2023_09_05_16_01 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:0x0 Code: Unable to access opcode bytes at0xffffffffffffffd6. RSP: 0018:ffff888178aaf758 EFLAGS: 00010246 Call Trace: <TASK> ? __die+0x20/0x60 ? page_fault_oops+0x14c/0x3c0 ? exc_page_fault+0x75/0x140 ? asm_exc_page_fault+0x22/0x30 notifier_call_chain+0x35/0xb0 blocking_notifier_call_chain+0x3d/0x60 mlx5_blocking_notifier_call_chain+0x22/0x30 [mlx5_core] mlx5_core_uplink_netdev_event_replay+0x3e/0x60 [mlx5_core] mlx5_mdev_netdev_track+0x53/0x60 [mlx5_ib] mlx5_ib_roce_init+0xc3/0x340 [mlx5_ib] __mlx5_ib_add+0x34/0xd0 [mlx5_ib] mlx5r_probe+0xe1/0x210 [mlx5_ib] ? auxiliary_match_id+0x6a/0x90 auxiliary_bus_probe+0x38/0x80 ? driver_sysfs_add+0x51/0x80 really_probe+0xc9/0x3e0 ? driver_probe_device+0x90/0x90 __driver_probe_device+0x80/0x160 driver_probe_device+0x1e/0x90 __device_attach_driver+0x7d/0x100 bus_for_each_drv+0x80/0xd0 __device_attach+0xbc/0x1f0 bus_probe_device+0x86/0xa0 device_add+0x637/0x840 __auxiliary_device_add+0x3b/0xa0 add_adev+0xc9/0x140 [mlx5_core] mlx5_rescan_drivers_locked+0x22a/0x310 [mlx5_core] mlx5_register_device+0x53/0xa0 [mlx5_core] mlx5_init_one_devl_locked+0x5c4/0x9c0 [mlx5_core] mlx5_init_one+0x3b/0x60 [mlx5_core] probe_one+0x44c/0x730 [mlx5_core] local_pci_probe+0x3e/0x90 pci_device_probe+0xbf/0x210 ? kernfs_create_link+0x5d/0xa0 ? sysfs_do_create_link_sd+0x60/0xc0 really_probe+0xc9/0x3e0 ? driver_probe_device+0x90/0x90 __driver_probe_device+0x80/0x160 driver_probe_device+0x1e/0x90 __device_attach_driver+0x7d/0x100 bus_for_each_drv+0x80/0xd0 __device_attach+0xbc/0x1f0 pci_bus_add_device+0x54/0x80 pci_iov_add_virtfn+0x2e6/0x320 sriov_enable+0x208/0x420 mlx5_core_sriov_configure+0x9e/0x200 [mlx5_core] sriov_numvfs_store+0xae/0x1a0 kernfs_fop_write_iter+0x10c/0x1a0 vfs_write+0x291/0x3c0 ksys_write+0x5f/0xe0 do_syscall_64+0x3d/0x90 entry_SYSCALL_64_after_hwframe+0x46/0xb0 CR2: 0000000000000000 ---[ end trace 0000000000000000 ]--- Fixes: 2c3b5beec46a ("net/mlx5e: More generic netdev management API") Signed-off-by: Shay Drory <shayd(a)nvidia.com> Signed-off-by: Tariq Toukan <tariqt(a)nvidia.com> Reviewed-by: Simon Horman <horms(a)kernel.org> Link: https://lore.kernel.org/r/20240509112951.590184-2-tariqt@nvidia.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: drivers/net/ethernet/mellanox/mlx5/core/en_main.c [Did not backport 912cebf420c2.] Signed-off-by: Liu Jian <liujian56(a)huawei.com> --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 5673a4113253..160ab564d641 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -5578,7 +5578,7 @@ static int mlx5e_attach(struct mlx5_core_dev *mdev, void *vpriv) return 0; } -static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv) +static void __mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv, bool pre_netdev_reg) { struct mlx5e_priv *priv = vpriv; struct net_device *netdev = priv->netdev; @@ -5588,13 +5588,18 @@ static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv) return; #endif - if (!netif_device_present(netdev)) + if (!pre_netdev_reg && !netif_device_present(netdev)) return; mlx5e_detach_netdev(priv); mlx5e_destroy_mdev_resources(mdev); } +static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv) +{ + __mlx5e_detach(mdev, vpriv, false); +} + static void *mlx5e_add(struct mlx5_core_dev *mdev) { struct net_device *netdev; @@ -5642,7 +5647,7 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev) return priv; err_detach: - mlx5e_detach(mdev, priv); + __mlx5e_detach(mdev, priv, true); err_destroy_netdev: mlx5e_destroy_netdev(priv); return NULL; -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1] net/mlx5e: Fix netif state handling
by Liu Jian 14 Oct '24

14 Oct '24

From: Shay Drory <shayd(a)nvidia.com> mainline inclusion from mainline-v6.10-rc1 commit 3d5918477f94e4c2f064567875c475468e264644 category: bugfix bugzilla: 190126 CVE: CVE-2024-38608 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- mlx5e_suspend cleans resources only if netif_device_present() returns true. However, mlx5e_resume changes the state of netif, via mlx5e_nic_enable, only if reg_state == NETREG_REGISTERED. In the below case, the above leads to NULL-ptr Oops[1] and memory leaks: mlx5e_probe _mlx5e_resume mlx5e_attach_netdev mlx5e_nic_enable <-- netdev not reg, not calling netif_device_attach() register_netdev <-- failed for some reason. ERROR_FLOW: _mlx5e_suspend <-- netif_device_present return false, resources aren't freed :( Hence, clean resources in this case as well. [1] BUG: kernel NULL pointer dereference, address: 0000000000000000 PGD 0 P4D 0 Oops: 0010 [#1] SMP CPU: 2 PID: 9345 Comm: test-ovs-ct-gen Not tainted 6.5.0_for_upstream_min_debug_2023_09_05_16_01 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:0x0 Code: Unable to access opcode bytes at0xffffffffffffffd6. RSP: 0018:ffff888178aaf758 EFLAGS: 00010246 Call Trace: <TASK> ? __die+0x20/0x60 ? page_fault_oops+0x14c/0x3c0 ? exc_page_fault+0x75/0x140 ? asm_exc_page_fault+0x22/0x30 notifier_call_chain+0x35/0xb0 blocking_notifier_call_chain+0x3d/0x60 mlx5_blocking_notifier_call_chain+0x22/0x30 [mlx5_core] mlx5_core_uplink_netdev_event_replay+0x3e/0x60 [mlx5_core] mlx5_mdev_netdev_track+0x53/0x60 [mlx5_ib] mlx5_ib_roce_init+0xc3/0x340 [mlx5_ib] __mlx5_ib_add+0x34/0xd0 [mlx5_ib] mlx5r_probe+0xe1/0x210 [mlx5_ib] ? auxiliary_match_id+0x6a/0x90 auxiliary_bus_probe+0x38/0x80 ? driver_sysfs_add+0x51/0x80 really_probe+0xc9/0x3e0 ? driver_probe_device+0x90/0x90 __driver_probe_device+0x80/0x160 driver_probe_device+0x1e/0x90 __device_attach_driver+0x7d/0x100 bus_for_each_drv+0x80/0xd0 __device_attach+0xbc/0x1f0 bus_probe_device+0x86/0xa0 device_add+0x637/0x840 __auxiliary_device_add+0x3b/0xa0 add_adev+0xc9/0x140 [mlx5_core] mlx5_rescan_drivers_locked+0x22a/0x310 [mlx5_core] mlx5_register_device+0x53/0xa0 [mlx5_core] mlx5_init_one_devl_locked+0x5c4/0x9c0 [mlx5_core] mlx5_init_one+0x3b/0x60 [mlx5_core] probe_one+0x44c/0x730 [mlx5_core] local_pci_probe+0x3e/0x90 pci_device_probe+0xbf/0x210 ? kernfs_create_link+0x5d/0xa0 ? sysfs_do_create_link_sd+0x60/0xc0 really_probe+0xc9/0x3e0 ? driver_probe_device+0x90/0x90 __driver_probe_device+0x80/0x160 driver_probe_device+0x1e/0x90 __device_attach_driver+0x7d/0x100 bus_for_each_drv+0x80/0xd0 __device_attach+0xbc/0x1f0 pci_bus_add_device+0x54/0x80 pci_iov_add_virtfn+0x2e6/0x320 sriov_enable+0x208/0x420 mlx5_core_sriov_configure+0x9e/0x200 [mlx5_core] sriov_numvfs_store+0xae/0x1a0 kernfs_fop_write_iter+0x10c/0x1a0 vfs_write+0x291/0x3c0 ksys_write+0x5f/0xe0 do_syscall_64+0x3d/0x90 entry_SYSCALL_64_after_hwframe+0x46/0xb0 CR2: 0000000000000000 ---[ end trace 0000000000000000 ]--- Fixes: 2c3b5beec46a ("net/mlx5e: More generic netdev management API") Signed-off-by: Shay Drory <shayd(a)nvidia.com> Signed-off-by: Tariq Toukan <tariqt(a)nvidia.com> Reviewed-by: Simon Horman <horms(a)kernel.org> Link: https://lore.kernel.org/r/20240509112951.590184-2-tariqt@nvidia.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: drivers/net/ethernet/mellanox/mlx5/core/en_main.c [Did not backport 912cebf420c2.] Signed-off-by: Liu Jian <liujian56(a)huawei.com> --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index cfc3bfcb04a2..b8717cbf23dd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -5578,7 +5578,7 @@ static int mlx5e_attach(struct mlx5_core_dev *mdev, void *vpriv) return 0; } -static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv) +static void __mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv, bool pre_netdev_reg) { struct mlx5e_priv *priv = vpriv; struct net_device *netdev = priv->netdev; @@ -5588,13 +5588,18 @@ static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv) return; #endif - if (!netif_device_present(netdev)) + if (!pre_netdev_reg && !netif_device_present(netdev)) return; mlx5e_detach_netdev(priv); mlx5e_destroy_mdev_resources(mdev); } +static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv) +{ + __mlx5e_detach(mdev, vpriv, false); +} + static void *mlx5e_add(struct mlx5_core_dev *mdev) { struct net_device *netdev; @@ -5642,7 +5647,7 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev) return priv; err_detach: - mlx5e_detach(mdev, priv); + __mlx5e_detach(mdev, priv, true); err_destroy_netdev: mlx5e_destroy_netdev(priv); return NULL; -- 2.34.1

2 1

[PATCH OLK-5.10] net: flow_dissector: use DEBUG_NET_WARN_ON_ONCE
by Liu Jian 14 Oct '24

14 Oct '24

From: Pablo Neira Ayuso <pablo(a)netfilter.org> mainline inclusion from mainline-v6.11-rc1 commit 120f1c857a73e52132e473dee89b340440cb692b category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAKPY5 CVE: CVE-2024-42321 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ------------------------------------------------- The following splat is easy to reproduce upstream as well as in -stable kernels. Florian Westphal provided the following commit: d1dab4f71d37 ("net: add and use __skb_get_hash_symmetric_net") but this complementary fix has been also suggested by Willem de Bruijn and it can be easily backported to -stable kernel which consists in using DEBUG_NET_WARN_ON_ONCE instead to silence the following splat given __skb_get_hash() is used by the nftables tracing infrastructure to to identify packets in traces. [69133.561393] ------------[ cut here ]------------ [69133.561404] WARNING: CPU: 0 PID: 43576 at net/core/flow_dissector.c:1104 __skb_flow_dissect+0x134f/ [...] [69133.561944] CPU: 0 PID: 43576 Comm: socat Not tainted 6.10.0-rc7+ #379 [69133.561959] RIP: 0010:__skb_flow_dissect+0x134f/0x2ad0 [69133.561970] Code: 83 f9 04 0f 84 b3 00 00 00 45 85 c9 0f 84 aa 00 00 00 41 83 f9 02 0f 84 81 fc ff ff 44 0f b7 b4 24 80 00 00 00 e9 8b f9 ff ff <0f> 0b e9 20 f3 ff ff 41 f6 c6 20 0f 84 e4 ef ff ff 48 8d 7b 12 e8 [69133.561979] RSP: 0018:ffffc90000006fc0 EFLAGS: 00010246 [69133.561988] RAX: 0000000000000000 RBX: ffffffff82f33e20 RCX: ffffffff81ab7e19 [69133.561994] RDX: dffffc0000000000 RSI: ffffc90000007388 RDI: ffff888103a1b418 [69133.562001] RBP: ffffc90000007310 R08: 0000000000000000 R09: 0000000000000000 [69133.562007] R10: ffffc90000007388 R11: ffffffff810cface R12: ffff888103a1b400 [69133.562013] R13: 0000000000000000 R14: ffffffff82f33e2a R15: ffffffff82f33e28 [69133.562020] FS: 00007f40f7131740(0000) GS:ffff888390800000(0000) knlGS:0000000000000000 [69133.562027] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [69133.562033] CR2: 00007f40f7346ee0 CR3: 000000015d200001 CR4: 00000000001706f0 [69133.562040] Call Trace: [69133.562044] <IRQ> [69133.562049] ? __warn+0x9f/0x1a0 [ 1211.841384] ? __skb_flow_dissect+0x107e/0x2860 [...] [ 1211.841496] ? bpf_flow_dissect+0x160/0x160 [ 1211.841753] __skb_get_hash+0x97/0x280 [ 1211.841765] ? __skb_get_hash_symmetric+0x230/0x230 [ 1211.841776] ? mod_find+0xbf/0xe0 [ 1211.841786] ? get_stack_info_noinstr+0x12/0xe0 [ 1211.841798] ? bpf_ksym_find+0x56/0xe0 [ 1211.841807] ? __rcu_read_unlock+0x2a/0x70 [ 1211.841819] nft_trace_init+0x1b9/0x1c0 [nf_tables] [ 1211.841895] ? nft_trace_notify+0x830/0x830 [nf_tables] [ 1211.841964] ? get_stack_info+0x2b/0x80 [ 1211.841975] ? nft_do_chain_arp+0x80/0x80 [nf_tables] [ 1211.842044] nft_do_chain+0x79c/0x850 [nf_tables] Fixes: 9b52e3f267a6 ("flow_dissector: handle no-skb use case") Suggested-by: Willem de Bruijn <willemb(a)google.com> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Reviewed-by: Willem de Bruijn <willemb(a)google.com> Link: https://patch.msgid.link/20240715141442.43775-1-pablo@netfilter.org Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Conflicts: include/linux/netdevice.h [Did not backport 4d92b95ff2f9, 5b87be9e4978, d268c1f5cfc9] Signed-off-by: Liu Jian <liujian56(a)huawei.com> --- include/linux/netdevice.h | 6 ++++++ net/core/flow_dissector.c | 2 +- 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 87fc83328987..dc52d8b57b2f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -5346,6 +5346,12 @@ do { \ }) #endif +#if defined(CONFIG_DEBUG_NET) +#define DEBUG_NET_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond) +#else +#define DEBUG_NET_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond) +#endif + /* * The list of packet types we will receive (as opposed to discard) * and the routines to invoke. diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 18f29cedb2b9..4280164a40ec 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -972,7 +972,7 @@ bool __skb_flow_dissect(const struct net *net, } } - WARN_ON_ONCE(!net); + DEBUG_NET_WARN_ON_ONCE(!net); if (net) { enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; struct bpf_prog_array *run_array; -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1] net: flow_dissector: use DEBUG_NET_WARN_ON_ONCE
by Liu Jian 14 Oct '24

14 Oct '24

From: Pablo Neira Ayuso <pablo(a)netfilter.org> mainline inclusion from mainline-v6.11-rc1 commit 120f1c857a73e52132e473dee89b340440cb692b category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAKPY5 CVE: CVE-2024-42321 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ------------------------------------------------- The following splat is easy to reproduce upstream as well as in -stable kernels. Florian Westphal provided the following commit: d1dab4f71d37 ("net: add and use __skb_get_hash_symmetric_net") but this complementary fix has been also suggested by Willem de Bruijn and it can be easily backported to -stable kernel which consists in using DEBUG_NET_WARN_ON_ONCE instead to silence the following splat given __skb_get_hash() is used by the nftables tracing infrastructure to to identify packets in traces. [69133.561393] ------------[ cut here ]------------ [69133.561404] WARNING: CPU: 0 PID: 43576 at net/core/flow_dissector.c:1104 __skb_flow_dissect+0x134f/ [...] [69133.561944] CPU: 0 PID: 43576 Comm: socat Not tainted 6.10.0-rc7+ #379 [69133.561959] RIP: 0010:__skb_flow_dissect+0x134f/0x2ad0 [69133.561970] Code: 83 f9 04 0f 84 b3 00 00 00 45 85 c9 0f 84 aa 00 00 00 41 83 f9 02 0f 84 81 fc ff ff 44 0f b7 b4 24 80 00 00 00 e9 8b f9 ff ff <0f> 0b e9 20 f3 ff ff 41 f6 c6 20 0f 84 e4 ef ff ff 48 8d 7b 12 e8 [69133.561979] RSP: 0018:ffffc90000006fc0 EFLAGS: 00010246 [69133.561988] RAX: 0000000000000000 RBX: ffffffff82f33e20 RCX: ffffffff81ab7e19 [69133.561994] RDX: dffffc0000000000 RSI: ffffc90000007388 RDI: ffff888103a1b418 [69133.562001] RBP: ffffc90000007310 R08: 0000000000000000 R09: 0000000000000000 [69133.562007] R10: ffffc90000007388 R11: ffffffff810cface R12: ffff888103a1b400 [69133.562013] R13: 0000000000000000 R14: ffffffff82f33e2a R15: ffffffff82f33e28 [69133.562020] FS: 00007f40f7131740(0000) GS:ffff888390800000(0000) knlGS:0000000000000000 [69133.562027] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [69133.562033] CR2: 00007f40f7346ee0 CR3: 000000015d200001 CR4: 00000000001706f0 [69133.562040] Call Trace: [69133.562044] <IRQ> [69133.562049] ? __warn+0x9f/0x1a0 [ 1211.841384] ? __skb_flow_dissect+0x107e/0x2860 [...] [ 1211.841496] ? bpf_flow_dissect+0x160/0x160 [ 1211.841753] __skb_get_hash+0x97/0x280 [ 1211.841765] ? __skb_get_hash_symmetric+0x230/0x230 [ 1211.841776] ? mod_find+0xbf/0xe0 [ 1211.841786] ? get_stack_info_noinstr+0x12/0xe0 [ 1211.841798] ? bpf_ksym_find+0x56/0xe0 [ 1211.841807] ? __rcu_read_unlock+0x2a/0x70 [ 1211.841819] nft_trace_init+0x1b9/0x1c0 [nf_tables] [ 1211.841895] ? nft_trace_notify+0x830/0x830 [nf_tables] [ 1211.841964] ? get_stack_info+0x2b/0x80 [ 1211.841975] ? nft_do_chain_arp+0x80/0x80 [nf_tables] [ 1211.842044] nft_do_chain+0x79c/0x850 [nf_tables] Fixes: 9b52e3f267a6 ("flow_dissector: handle no-skb use case") Suggested-by: Willem de Bruijn <willemb(a)google.com> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Reviewed-by: Willem de Bruijn <willemb(a)google.com> Link: https://patch.msgid.link/20240715141442.43775-1-pablo@netfilter.org Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Conflicts: include/linux/netdevice.h [Did not backport 4d92b95ff2f9, 5b87be9e4978, d268c1f5cfc9] Signed-off-by: Liu Jian <liujian56(a)huawei.com> --- include/linux/netdevice.h | 6 ++++++ net/core/flow_dissector.c | 2 +- 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 316cc8240fc5..76c38d8f1fe4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -5311,6 +5311,12 @@ do { \ }) #endif +#if defined(CONFIG_DEBUG_NET) +#define DEBUG_NET_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond) +#else +#define DEBUG_NET_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond) +#endif + /* * The list of packet types we will receive (as opposed to discard) * and the routines to invoke. diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 7044a98d144d..d770f82ede78 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -972,7 +972,7 @@ bool __skb_flow_dissect(const struct net *net, } } - WARN_ON_ONCE(!net); + DEBUG_NET_WARN_ON_ONCE(!net); if (net) { enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; struct bpf_prog_array *run_array; -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1] netfilter: nft_flow_offload: reset dst in route object after setting up flow
by Liu Jian 14 Oct '24

14 Oct '24

From: Pablo Neira Ayuso <pablo(a)netfilter.org> mainline inclusion from mainline-v6.8-rc6 commit 9e0f0430389be7696396c62f037be4bf72cf93e3 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9Q8LQ CVE: CVE-2024-27403 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- dst is transferred to the flow object, route object does not own it anymore. Reset dst in route object, otherwise if flow_offload_add() fails, error path releases dst twice, leading to a refcount underflow. Fixes: a3c90f7a2323 ("netfilter: nf_tables: flow offload expression") Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Conflicts: include/net/netfilter/nf_flow_table.h net/netfilter/nf_flow_table_core.c [This is because we did not backport fa502c865666, 8b9229d15877, 7a27f6ab4135] Signed-off-by: Liu Jian <liujian56(a)huawei.com> --- include/net/netfilter/nf_flow_table.h | 2 +- net/netfilter/nf_flow_table_core.c | 16 +++++++++++++--- 2 files changed, 14 insertions(+), 4 deletions(-) diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index b338638f2279..b49dfb415bad 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -207,7 +207,7 @@ nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table, } int flow_offload_route_init(struct flow_offload *flow, - const struct nf_flow_route *route); + struct nf_flow_route *route); int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow); void flow_offload_refresh(struct nf_flowtable *flow_table, diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index d091d51b5e19..5a5faefb181d 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -74,13 +74,23 @@ struct flow_offload *flow_offload_alloc(struct nf_conn *ct) } EXPORT_SYMBOL_GPL(flow_offload_alloc); +static struct dst_entry *nft_route_dst_fetch(struct nf_flow_route *route, + enum flow_offload_tuple_dir dir) +{ + struct dst_entry *dst = route->tuple[dir].dst; + + route->tuple[dir].dst = NULL; + + return dst; +} + static int flow_offload_fill_route(struct flow_offload *flow, - const struct nf_flow_route *route, + struct nf_flow_route *route, enum flow_offload_tuple_dir dir) { struct flow_offload_tuple *flow_tuple = &flow->tuplehash[dir].tuple; struct dst_entry *other_dst = route->tuple[!dir].dst; - struct dst_entry *dst = route->tuple[dir].dst; + struct dst_entry *dst = nft_route_dst_fetch(route, dir); if (!dst_hold_safe(route->tuple[dir].dst)) return -1; @@ -101,7 +111,7 @@ static int flow_offload_fill_route(struct flow_offload *flow, } int flow_offload_route_init(struct flow_offload *flow, - const struct nf_flow_route *route) + struct nf_flow_route *route) { int err; -- 2.34.1

2 9

[PATCH OLK-6.6] net/hinic3: fix version showed in ethtool
by s00851154 14 Oct '24

14 Oct '24

From: Shi Jing <shijing34(a)huawei.com> driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAWGUW CVE: NA -------------------------------- Fix the version in the output of ethtool commands from empty to the right version. Fixes: 3b469ecc9cb3 ("Add Huawei Intelligent Network Card Driver: hinic3") Signed-off-by: Shi Jing <shijing34(a)huawei.com> --- drivers/net/ethernet/huawei/hinic3/hinic3_crm.h | 2 +- drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_crm.h b/drivers/net/ethernet/huawei/hinic3/hinic3_crm.h index 195a5cf08f66e..6b84d7d960efc 100644 --- a/drivers/net/ethernet/huawei/hinic3/hinic3_crm.h +++ b/drivers/net/ethernet/huawei/hinic3/hinic3_crm.h @@ -8,7 +8,7 @@ #include "mpu_cmd_base_defs.h" -#define HINIC3_DRV_VERSION "" +#define HINIC3_DRV_VERSION "16.13.8.1" #define HINIC3_DRV_DESC "Intelligent Network Interface Card Driver" #define HIUDK_DRV_DESC "Intelligent Network Unified Driver" diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h index 2967311aab76c..476645637e831 100644 --- a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h +++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h @@ -17,7 +17,7 @@ #include "hinic3_dcb.h" #define HINIC3_NIC_DRV_NAME "hinic3" -#define HINIC3_NIC_DRV_VERSION "" +#define HINIC3_NIC_DRV_VERSION "16.13.8.1" #define HINIC3_FUNC_IS_VF(hwdev) (hinic3_func_type(hwdev) == TYPE_VF) -- 2.28.0.windows.1

2 1

[PATCH OLK-5.10] net/hinic3: fix version showed in ethtool
by s00851154 14 Oct '24

14 Oct '24

From: Shi Jing <shijing34(a)huawei.com> driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAWGUW CVE: NA -------------------------------- Fix the version in the output of ethtool commands from empty to the right version. Fixes: 3b469ecc9cb3 ("Add Huawei Intelligent Network Card Driver: hinic3") Signed-off-by: Shi Jing <shijing34(a)huawei.com> --- drivers/net/ethernet/huawei/hinic3/hinic3_crm.h | 2 +- drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_crm.h b/drivers/net/ethernet/huawei/hinic3/hinic3_crm.h index 195a5cf..f269691 100644 --- a/drivers/net/ethernet/huawei/hinic3/hinic3_crm.h +++ b/drivers/net/ethernet/huawei/hinic3/hinic3_crm.h @@ -8,7 +8,7 @@ #include "mpu_cmd_base_defs.h" -#define HINIC3_DRV_VERSION "" +#define HINIC3_DRV_VERSION "15.17.1.1" #define HINIC3_DRV_DESC "Intelligent Network Interface Card Driver" #define HIUDK_DRV_DESC "Intelligent Network Unified Driver" diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h index 2967311..800fa73 100644 --- a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h +++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h @@ -17,7 +17,7 @@ #include "hinic3_dcb.h" #define HINIC3_NIC_DRV_NAME "hinic3" -#define HINIC3_NIC_DRV_VERSION "" +#define HINIC3_NIC_DRV_VERSION "15.17.1.1" #define HINIC3_FUNC_IS_VF(hwdev) (hinic3_func_type(hwdev) == TYPE_VF) -- 2.28.0.windows.1

2 1

[PATCH OLK-5.10] net/hinic3: fix version showed in ethtool
by s00851154 14 Oct '24

14 Oct '24

From: Shi Jing <shijing34(a)huawei.com> driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAWGUW CVE: NA -------------------------------- Fix the version in the output of ethtool commands from empty to the kernel version. Use the macro HINIC3_NIC_DRV_VERSION to record driver changes for developers. The last number 1.0.X grow as minor changes, like this revision which does not affect the main functions. The middle number 1.X.1 iterates with changes to drivers functionality and fixing of serious bugs, and the first one X.0.1 means the number of releases of the driver. Fixes: 3b469ecc9cb3 ("Add Huawei Intelligent Network Card Driver: hinic3") Signed-off-by: Shi Jing <shijing34(a)huawei.com> --- drivers/net/ethernet/huawei/hinic3/hinic3_crm.h | 2 +- drivers/net/ethernet/huawei/hinic3/hinic3_ethtool.c | 1 - drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h | 2 +- 3 files changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_crm.h b/drivers/net/ethernet/huawei/hinic3/hinic3_crm.h index 195a5cf..f269691 100644 --- a/drivers/net/ethernet/huawei/hinic3/hinic3_crm.h +++ b/drivers/net/ethernet/huawei/hinic3/hinic3_crm.h @@ -8,7 +8,7 @@ #include "mpu_cmd_base_defs.h" -#define HINIC3_DRV_VERSION "" +#define HINIC3_DRV_VERSION "15.17.1.1" #define HINIC3_DRV_DESC "Intelligent Network Interface Card Driver" #define HIUDK_DRV_DESC "Intelligent Network Unified Driver" diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_ethtool.c b/drivers/net/ethernet/huawei/hinic3/hinic3_ethtool.c index 2b3561e..696d441 100644 --- a/drivers/net/ethernet/huawei/hinic3/hinic3_ethtool.c +++ b/drivers/net/ethernet/huawei/hinic3/hinic3_ethtool.c @@ -45,7 +45,6 @@ static void hinic3_get_drvinfo(struct net_device *netdev, int err; strlcpy(info->driver, HINIC3_NIC_DRV_NAME, sizeof(info->driver)); - strlcpy(info->version, HINIC3_NIC_DRV_VERSION, sizeof(info->version)); strlcpy(info->bus_info, pci_name(pdev), sizeof(info->bus_info)); err = hinic3_get_mgmt_version(nic_dev->hwdev, mgmt_ver, diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h index 2967311..800fa73 100644 --- a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h +++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h @@ -17,7 +17,7 @@ #include "hinic3_dcb.h" #define HINIC3_NIC_DRV_NAME "hinic3" -#define HINIC3_NIC_DRV_VERSION "" +#define HINIC3_NIC_DRV_VERSION "15.17.1.1" #define HINIC3_FUNC_IS_VF(hwdev) (hinic3_func_type(hwdev) == TYPE_VF) -- 2.28.0.windows.1

2 1

[PATCH OLK-5.10 v5 00/12] xfs: some fix for forcealign
by Long Li 14 Oct '24

14 Oct '24

This patch set fix some bug for forcealign: patch 1 ~ 5 : fix tail alignment issue while approach to no space. patch 6 : fix forcealign not compatible with reflink and realtime. patch 7 : only datafork need bunmap algin for focealign patch 8 ~ 11 : fix truncate for forcealign Dave Chinner (3): xfs: only allow minlen allocations when near ENOSPC xfs: always tail align maxlen allocations xfs: align args->minlen for forced allocation alignment John Garry (1): xfs: Don't revert allocated offset for forcealign Long Li (5): xfs: don't attempting non-aligned fallbacks alloc for forcealign xfs: simplify extent allocation alignment xfs: forcealign not compatible with reflink and realtime device xfs: only bunmap align in datafork for forcealign xfs: correct the truncate blocksize of forcealign Zhang Yi (3): math64: add rem_u64() to just return the remainder iomap: pass blocksize to iomap_truncate_page() xfs: refactor the truncating order fs/iomap/buffered-io.c | 8 +-- fs/xfs/libxfs/xfs_alloc.c | 31 +++++---- fs/xfs/libxfs/xfs_bmap.c | 140 ++++++++++++++++++++------------------ fs/xfs/xfs_iops.c | 124 +++++++++++++++++---------------- fs/xfs/xfs_super.c | 19 +++++- include/linux/iomap.h | 4 +- include/linux/math64.h | 24 +++++++ 7 files changed, 208 insertions(+), 142 deletions(-) -- 2.39.2

2 13

[PATCH OLK-5.10 v2] ipv4: Fix uninit-value access in __ip_make_skb()
by Dong Chenchen 14 Oct '24

14 Oct '24

From: Shigeru Yoshida <syoshida(a)redhat.com> mainline inclusion from mainline-v6.9-rc7 commit fc1092f51567277509563800a3c56732070b6aa4 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9TXIE CVE: CVE-2024-36927 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- KMSAN reported uninit-value access in __ip_make_skb() [1]. __ip_make_skb() tests HDRINCL to know if the skb has icmphdr. However, HDRINCL can cause a race condition. If calling setsockopt(2) with IP_HDRINCL changes HDRINCL while __ip_make_skb() is running, the function will access icmphdr in the skb even if it is not included. This causes the issue reported by KMSAN. Check FLOWI_FLAG_KNOWN_NH on fl4->flowi4_flags instead of testing HDRINCL on the socket. Also, fl4->fl4_icmp_type and fl4->fl4_icmp_code are not initialized. These are union in struct flowi4 and are implicitly initialized by flowi4_init_output(), but we should not rely on specific union layout. Initialize these explicitly in raw_sendmsg(). [1] BUG: KMSAN: uninit-value in __ip_make_skb+0x2b74/0x2d20 net/ipv4/ip_output.c:1481 __ip_make_skb+0x2b74/0x2d20 net/ipv4/ip_output.c:1481 ip_finish_skb include/net/ip.h:243 [inline] ip_push_pending_frames+0x4c/0x5c0 net/ipv4/ip_output.c:1508 raw_sendmsg+0x2381/0x2690 net/ipv4/raw.c:654 inet_sendmsg+0x27b/0x2a0 net/ipv4/af_inet.c:851 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x274/0x3c0 net/socket.c:745 __sys_sendto+0x62c/0x7b0 net/socket.c:2191 __do_sys_sendto net/socket.c:2203 [inline] __se_sys_sendto net/socket.c:2199 [inline] __x64_sys_sendto+0x130/0x200 net/socket.c:2199 do_syscall_64+0xd8/0x1f0 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x6d/0x75 Uninit was created at: slab_post_alloc_hook mm/slub.c:3804 [inline] slab_alloc_node mm/slub.c:3845 [inline] kmem_cache_alloc_node+0x5f6/0xc50 mm/slub.c:3888 kmalloc_reserve+0x13c/0x4a0 net/core/skbuff.c:577 __alloc_skb+0x35a/0x7c0 net/core/skbuff.c:668 alloc_skb include/linux/skbuff.h:1318 [inline] __ip_append_data+0x49ab/0x68c0 net/ipv4/ip_output.c:1128 ip_append_data+0x1e7/0x260 net/ipv4/ip_output.c:1365 raw_sendmsg+0x22b1/0x2690 net/ipv4/raw.c:648 inet_sendmsg+0x27b/0x2a0 net/ipv4/af_inet.c:851 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x274/0x3c0 net/socket.c:745 __sys_sendto+0x62c/0x7b0 net/socket.c:2191 __do_sys_sendto net/socket.c:2203 [inline] __se_sys_sendto net/socket.c:2199 [inline] __x64_sys_sendto+0x130/0x200 net/socket.c:2199 do_syscall_64+0xd8/0x1f0 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x6d/0x75 CPU: 1 PID: 15709 Comm: syz-executor.7 Not tainted 6.8.0-11567-gb3603fcb79b1 #25 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-1.fc39 04/01/2014 Fixes: 99e5acae193e ("ipv4: Fix potential uninit variable access bug in __ip_make_skb()") Reported-by: syzkaller <syzkaller(a)googlegroups.com> Signed-off-by: Shigeru Yoshida <syoshida(a)redhat.com> Link: https://lore.kernel.org/r/20240430123945.2057348-1-syoshida@redhat.com Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Conflicts: net/ipv4/ip_output.c [commit cafbe182a467 wasnt merged in 5.10, which leads to context conflicts for inet_test_bit() not implemented] Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/ipv4/ip_output.c | 3 ++- net/ipv4/raw.c | 3 +++ 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 5d20dac19e0b..79ff136ae6f5 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1571,7 +1571,8 @@ struct sk_buff *__ip_make_skb(struct sock *sk, * so icmphdr does not in skb linear region and can not get icmp_type * by icmp_hdr(skb)->type. */ - if (sk->sk_type == SOCK_RAW && !inet_sk(sk)->hdrincl) + if (sk->sk_type == SOCK_RAW && + !(fl4->flowi4_flags & FLOWI_FLAG_KNOWN_NH)) icmp_type = fl4->fl4_icmp_type; else icmp_type = icmp_hdr(skb)->type; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 5336731b2401..3909dcccdd3e 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -606,6 +606,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0, sk->sk_uid); + fl4.fl4_icmp_type = 0; + fl4.fl4_icmp_code = 0; + if (!hdrincl) { rfv.msg = msg; rfv.hlen = 0; -- 2.25.1

2 1

[PATCH OLK-5.10] mlxsw: spectrum_acl_erp: Fix object nesting warning
by Dong Chenchen 14 Oct '24

14 Oct '24

From: Ido Schimmel <idosch(a)nvidia.com> stable inclusion from stable-v5.10.223 commit 36a9996e020dd5aa325e0ecc55eb2328288ea6bb category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IALEAO CVE: CVE-2024-43880 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 97d833ceb27dc19f8777d63f90be4a27b5daeedf ] ACLs in Spectrum-2 and newer ASICs can reside in the algorithmic TCAM (A-TCAM) or in the ordinary circuit TCAM (C-TCAM). The former can contain more ACLs (i.e., tc filters), but the number of masks in each region (i.e., tc chain) is limited. In order to mitigate the effects of the above limitation, the device allows filters to share a single mask if their masks only differ in up to 8 consecutive bits. For example, dst_ip/25 can be represented using dst_ip/24 with a delta of 1 bit. The C-TCAM does not have a limit on the number of masks being used (and therefore does not support mask aggregation), but can contain a limited number of filters. The driver uses the "objagg" library to perform the mask aggregation by passing it objects that consist of the filter's mask and whether the filter is to be inserted into the A-TCAM or the C-TCAM since filters in different TCAMs cannot share a mask. The set of created objects is dependent on the insertion order of the filters and is not necessarily optimal. Therefore, the driver will periodically ask the library to compute a more optimal set ("hints") by looking at all the existing objects. When the library asks the driver whether two objects can be aggregated the driver only compares the provided masks and ignores the A-TCAM / C-TCAM indication. This is the right thing to do since the goal is to move as many filters as possible to the A-TCAM. The driver also forbids two identical masks from being aggregated since this can only happen if one was intentionally put in the C-TCAM to avoid a conflict in the A-TCAM. The above can result in the following set of hints: H1: {mask X, A-TCAM} -> H2: {mask Y, A-TCAM} // X is Y + delta H3: {mask Y, C-TCAM} -> H4: {mask Z, A-TCAM} // Y is Z + delta After getting the hints from the library the driver will start migrating filters from one region to another while consulting the computed hints and instructing the device to perform a lookup in both regions during the transition. Assuming a filter with mask X is being migrated into the A-TCAM in the new region, the hints lookup will return H1. Since H2 is the parent of H1, the library will try to find the object associated with it and create it if necessary in which case another hints lookup (recursive) will be performed. This hints lookup for {mask Y, A-TCAM} will either return H2 or H3 since the driver passes the library an object comparison function that ignores the A-TCAM / C-TCAM indication. This can eventually lead to nested objects which are not supported by the library [1]. Fix by removing the object comparison function from both the driver and the library as the driver was the only user. That way the lookup will only return exact matches. I do not have a reliable reproducer that can reproduce the issue in a timely manner, but before the fix the issue would reproduce in several minutes and with the fix it does not reproduce in over an hour. Note that the current usefulness of the hints is limited because they include the C-TCAM indication and represent aggregation that cannot actually happen. This will be addressed in net-next. [1] WARNING: CPU: 0 PID: 153 at lib/objagg.c:170 objagg_obj_parent_assign+0xb5/0xd0 Modules linked in: CPU: 0 PID: 153 Comm: kworker/0:18 Not tainted 6.9.0-rc6-custom-g70fbc2c1c38b #42 Hardware name: Mellanox Technologies Ltd. MSN3700C/VMOD0008, BIOS 5.11 10/10/2018 Workqueue: mlxsw_core mlxsw_sp_acl_tcam_vregion_rehash_work RIP: 0010:objagg_obj_parent_assign+0xb5/0xd0 [...] Call Trace: <TASK> __objagg_obj_get+0x2bb/0x580 objagg_obj_get+0xe/0x80 mlxsw_sp_acl_erp_mask_get+0xb5/0xf0 mlxsw_sp_acl_atcam_entry_add+0xe8/0x3c0 mlxsw_sp_acl_tcam_entry_create+0x5e/0xa0 mlxsw_sp_acl_tcam_vchunk_migrate_one+0x16b/0x270 mlxsw_sp_acl_tcam_vregion_rehash_work+0xbe/0x510 process_one_work+0x151/0x370 Fixes: 9069a3817d82 ("lib: objagg: implement optimization hints assembly and use hints for object creation") Signed-off-by: Ido Schimmel <idosch(a)nvidia.com> Reviewed-by: Amit Cohen <amcohen(a)nvidia.com> Tested-by: Alexander Zubkov <green(a)qrator.net> Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Simon Horman <horms(a)kernel.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- .../ethernet/mellanox/mlxsw/spectrum_acl_erp.c | 13 ------------- include/linux/objagg.h | 1 - lib/objagg.c | 15 --------------- 3 files changed, 29 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c index d231f4d2888b..9eee229303cc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c @@ -1217,18 +1217,6 @@ static bool mlxsw_sp_acl_erp_delta_check(void *priv, const void *parent_obj, return err ? false : true; } -static int mlxsw_sp_acl_erp_hints_obj_cmp(const void *obj1, const void *obj2) -{ - const struct mlxsw_sp_acl_erp_key *key1 = obj1; - const struct mlxsw_sp_acl_erp_key *key2 = obj2; - - /* For hints purposes, two objects are considered equal - * in case the masks are the same. Does not matter what - * the "ctcam" value is. - */ - return memcmp(key1->mask, key2->mask, sizeof(key1->mask)); -} - static void *mlxsw_sp_acl_erp_delta_create(void *priv, void *parent_obj, void *obj) { @@ -1308,7 +1296,6 @@ static void mlxsw_sp_acl_erp_root_destroy(void *priv, void *root_priv) static const struct objagg_ops mlxsw_sp_acl_erp_objagg_ops = { .obj_size = sizeof(struct mlxsw_sp_acl_erp_key), .delta_check = mlxsw_sp_acl_erp_delta_check, - .hints_obj_cmp = mlxsw_sp_acl_erp_hints_obj_cmp, .delta_create = mlxsw_sp_acl_erp_delta_create, .delta_destroy = mlxsw_sp_acl_erp_delta_destroy, .root_create = mlxsw_sp_acl_erp_root_create, diff --git a/include/linux/objagg.h b/include/linux/objagg.h index 78021777df46..6df5b887dc54 100644 --- a/include/linux/objagg.h +++ b/include/linux/objagg.h @@ -8,7 +8,6 @@ struct objagg_ops { size_t obj_size; bool (*delta_check)(void *priv, const void *parent_obj, const void *obj); - int (*hints_obj_cmp)(const void *obj1, const void *obj2); void * (*delta_create)(void *priv, void *parent_obj, void *obj); void (*delta_destroy)(void *priv, void *delta_priv); void * (*root_create)(void *priv, void *obj, unsigned int root_id); diff --git a/lib/objagg.c b/lib/objagg.c index 73d711602573..57bde522f249 100644 --- a/lib/objagg.c +++ b/lib/objagg.c @@ -909,20 +909,6 @@ static const struct objagg_opt_algo *objagg_opt_algos[] = { [OBJAGG_OPT_ALGO_SIMPLE_GREEDY] = &objagg_opt_simple_greedy, }; -static int objagg_hints_obj_cmp(struct rhashtable_compare_arg *arg, - const void *obj) -{ - struct rhashtable *ht = arg->ht; - struct objagg_hints *objagg_hints = - container_of(ht, struct objagg_hints, node_ht); - const struct objagg_ops *ops = objagg_hints->ops; - const char *ptr = obj; - - ptr += ht->p.key_offset; - return ops->hints_obj_cmp ? ops->hints_obj_cmp(ptr, arg->key) : - memcmp(ptr, arg->key, ht->p.key_len); -} - /** * objagg_hints_get - obtains hints instance * @objagg: objagg instance @@ -961,7 +947,6 @@ struct objagg_hints *objagg_hints_get(struct objagg *objagg, offsetof(struct objagg_hints_node, obj); objagg_hints->ht_params.head_offset = offsetof(struct objagg_hints_node, ht_node); - objagg_hints->ht_params.obj_cmpfn = objagg_hints_obj_cmp; err = rhashtable_init(&objagg_hints->node_ht, &objagg_hints->ht_params); if (err) -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1] mlxsw: spectrum_acl_erp: Fix object nesting warning
by Dong Chenchen 14 Oct '24

14 Oct '24

From: Ido Schimmel <idosch(a)nvidia.com> stable inclusion from stable-v5.10.223 commit 36a9996e020dd5aa325e0ecc55eb2328288ea6bb category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IALEAO CVE: CVE-2024-43880 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 97d833ceb27dc19f8777d63f90be4a27b5daeedf ] ACLs in Spectrum-2 and newer ASICs can reside in the algorithmic TCAM (A-TCAM) or in the ordinary circuit TCAM (C-TCAM). The former can contain more ACLs (i.e., tc filters), but the number of masks in each region (i.e., tc chain) is limited. In order to mitigate the effects of the above limitation, the device allows filters to share a single mask if their masks only differ in up to 8 consecutive bits. For example, dst_ip/25 can be represented using dst_ip/24 with a delta of 1 bit. The C-TCAM does not have a limit on the number of masks being used (and therefore does not support mask aggregation), but can contain a limited number of filters. The driver uses the "objagg" library to perform the mask aggregation by passing it objects that consist of the filter's mask and whether the filter is to be inserted into the A-TCAM or the C-TCAM since filters in different TCAMs cannot share a mask. The set of created objects is dependent on the insertion order of the filters and is not necessarily optimal. Therefore, the driver will periodically ask the library to compute a more optimal set ("hints") by looking at all the existing objects. When the library asks the driver whether two objects can be aggregated the driver only compares the provided masks and ignores the A-TCAM / C-TCAM indication. This is the right thing to do since the goal is to move as many filters as possible to the A-TCAM. The driver also forbids two identical masks from being aggregated since this can only happen if one was intentionally put in the C-TCAM to avoid a conflict in the A-TCAM. The above can result in the following set of hints: H1: {mask X, A-TCAM} -> H2: {mask Y, A-TCAM} // X is Y + delta H3: {mask Y, C-TCAM} -> H4: {mask Z, A-TCAM} // Y is Z + delta After getting the hints from the library the driver will start migrating filters from one region to another while consulting the computed hints and instructing the device to perform a lookup in both regions during the transition. Assuming a filter with mask X is being migrated into the A-TCAM in the new region, the hints lookup will return H1. Since H2 is the parent of H1, the library will try to find the object associated with it and create it if necessary in which case another hints lookup (recursive) will be performed. This hints lookup for {mask Y, A-TCAM} will either return H2 or H3 since the driver passes the library an object comparison function that ignores the A-TCAM / C-TCAM indication. This can eventually lead to nested objects which are not supported by the library [1]. Fix by removing the object comparison function from both the driver and the library as the driver was the only user. That way the lookup will only return exact matches. I do not have a reliable reproducer that can reproduce the issue in a timely manner, but before the fix the issue would reproduce in several minutes and with the fix it does not reproduce in over an hour. Note that the current usefulness of the hints is limited because they include the C-TCAM indication and represent aggregation that cannot actually happen. This will be addressed in net-next. [1] WARNING: CPU: 0 PID: 153 at lib/objagg.c:170 objagg_obj_parent_assign+0xb5/0xd0 Modules linked in: CPU: 0 PID: 153 Comm: kworker/0:18 Not tainted 6.9.0-rc6-custom-g70fbc2c1c38b #42 Hardware name: Mellanox Technologies Ltd. MSN3700C/VMOD0008, BIOS 5.11 10/10/2018 Workqueue: mlxsw_core mlxsw_sp_acl_tcam_vregion_rehash_work RIP: 0010:objagg_obj_parent_assign+0xb5/0xd0 [...] Call Trace: <TASK> __objagg_obj_get+0x2bb/0x580 objagg_obj_get+0xe/0x80 mlxsw_sp_acl_erp_mask_get+0xb5/0xf0 mlxsw_sp_acl_atcam_entry_add+0xe8/0x3c0 mlxsw_sp_acl_tcam_entry_create+0x5e/0xa0 mlxsw_sp_acl_tcam_vchunk_migrate_one+0x16b/0x270 mlxsw_sp_acl_tcam_vregion_rehash_work+0xbe/0x510 process_one_work+0x151/0x370 Fixes: 9069a3817d82 ("lib: objagg: implement optimization hints assembly and use hints for object creation") Signed-off-by: Ido Schimmel <idosch(a)nvidia.com> Reviewed-by: Amit Cohen <amcohen(a)nvidia.com> Tested-by: Alexander Zubkov <green(a)qrator.net> Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Simon Horman <horms(a)kernel.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- .../ethernet/mellanox/mlxsw/spectrum_acl_erp.c | 13 ------------- include/linux/objagg.h | 1 - lib/objagg.c | 15 --------------- 3 files changed, 29 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c index d231f4d2888b..9eee229303cc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c @@ -1217,18 +1217,6 @@ static bool mlxsw_sp_acl_erp_delta_check(void *priv, const void *parent_obj, return err ? false : true; } -static int mlxsw_sp_acl_erp_hints_obj_cmp(const void *obj1, const void *obj2) -{ - const struct mlxsw_sp_acl_erp_key *key1 = obj1; - const struct mlxsw_sp_acl_erp_key *key2 = obj2; - - /* For hints purposes, two objects are considered equal - * in case the masks are the same. Does not matter what - * the "ctcam" value is. - */ - return memcmp(key1->mask, key2->mask, sizeof(key1->mask)); -} - static void *mlxsw_sp_acl_erp_delta_create(void *priv, void *parent_obj, void *obj) { @@ -1308,7 +1296,6 @@ static void mlxsw_sp_acl_erp_root_destroy(void *priv, void *root_priv) static const struct objagg_ops mlxsw_sp_acl_erp_objagg_ops = { .obj_size = sizeof(struct mlxsw_sp_acl_erp_key), .delta_check = mlxsw_sp_acl_erp_delta_check, - .hints_obj_cmp = mlxsw_sp_acl_erp_hints_obj_cmp, .delta_create = mlxsw_sp_acl_erp_delta_create, .delta_destroy = mlxsw_sp_acl_erp_delta_destroy, .root_create = mlxsw_sp_acl_erp_root_create, diff --git a/include/linux/objagg.h b/include/linux/objagg.h index 78021777df46..6df5b887dc54 100644 --- a/include/linux/objagg.h +++ b/include/linux/objagg.h @@ -8,7 +8,6 @@ struct objagg_ops { size_t obj_size; bool (*delta_check)(void *priv, const void *parent_obj, const void *obj); - int (*hints_obj_cmp)(const void *obj1, const void *obj2); void * (*delta_create)(void *priv, void *parent_obj, void *obj); void (*delta_destroy)(void *priv, void *delta_priv); void * (*root_create)(void *priv, void *obj, unsigned int root_id); diff --git a/lib/objagg.c b/lib/objagg.c index 73d711602573..57bde522f249 100644 --- a/lib/objagg.c +++ b/lib/objagg.c @@ -909,20 +909,6 @@ static const struct objagg_opt_algo *objagg_opt_algos[] = { [OBJAGG_OPT_ALGO_SIMPLE_GREEDY] = &objagg_opt_simple_greedy, }; -static int objagg_hints_obj_cmp(struct rhashtable_compare_arg *arg, - const void *obj) -{ - struct rhashtable *ht = arg->ht; - struct objagg_hints *objagg_hints = - container_of(ht, struct objagg_hints, node_ht); - const struct objagg_ops *ops = objagg_hints->ops; - const char *ptr = obj; - - ptr += ht->p.key_offset; - return ops->hints_obj_cmp ? ops->hints_obj_cmp(ptr, arg->key) : - memcmp(ptr, arg->key, ht->p.key_len); -} - /** * objagg_hints_get - obtains hints instance * @objagg: objagg instance @@ -961,7 +947,6 @@ struct objagg_hints *objagg_hints_get(struct objagg *objagg, offsetof(struct objagg_hints_node, obj); objagg_hints->ht_params.head_offset = offsetof(struct objagg_hints_node, ht_node); - objagg_hints->ht_params.obj_cmpfn = objagg_hints_obj_cmp; err = rhashtable_init(&objagg_hints->node_ht, &objagg_hints->ht_params); if (err) -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1] netns: Make get_net_ns() handle zero refcount net
by Dong Chenchen 14 Oct '24

14 Oct '24

From: Yue Haibing <yuehaibing(a)huawei.com> stable inclusion from stable-v5.10.221 commit 2b82028a1f5ee3a8e04090776b10c534144ae77b category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IACR2S CVE: CVE-2024-40958 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit ff960f9d3edbe08a736b5a224d91a305ccc946b0 ] Syzkaller hit a warning: refcount_t: addition on 0; use-after-free. WARNING: CPU: 3 PID: 7890 at lib/refcount.c:25 refcount_warn_saturate+0xdf/0x1d0 Modules linked in: CPU: 3 PID: 7890 Comm: tun Not tainted 6.10.0-rc3-00100-gcaa4f9578aba-dirty #310 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 RIP: 0010:refcount_warn_saturate+0xdf/0x1d0 Code: 41 49 04 31 ff 89 de e8 9f 1e cd fe 84 db 75 9c e8 76 26 cd fe c6 05 b6 41 49 04 01 90 48 c7 c7 b8 8e 25 86 e8 d2 05 b5 fe 90 <0f> 0b 90 90 e9 79 ff ff ff e8 53 26 cd fe 0f b6 1 RSP: 0018:ffff8881067b7da0 EFLAGS: 00010286 RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffffffff811c72ac RDX: ffff8881026a2140 RSI: ffffffff811c72b5 RDI: 0000000000000001 RBP: ffff8881067b7db0 R08: 0000000000000000 R09: 205b5d3730353139 R10: 0000000000000000 R11: 205d303938375420 R12: ffff8881086500c4 R13: ffff8881086500c4 R14: ffff8881086500b0 R15: ffff888108650040 FS: 00007f5b2961a4c0(0000) GS:ffff88823bd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055d7ed36fd18 CR3: 00000001482f6000 CR4: 00000000000006f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> ? show_regs+0xa3/0xc0 ? __warn+0xa5/0x1c0 ? refcount_warn_saturate+0xdf/0x1d0 ? report_bug+0x1fc/0x2d0 ? refcount_warn_saturate+0xdf/0x1d0 ? handle_bug+0xa1/0x110 ? exc_invalid_op+0x3c/0xb0 ? asm_exc_invalid_op+0x1f/0x30 ? __warn_printk+0xcc/0x140 ? __warn_printk+0xd5/0x140 ? refcount_warn_saturate+0xdf/0x1d0 get_net_ns+0xa4/0xc0 ? __pfx_get_net_ns+0x10/0x10 open_related_ns+0x5a/0x130 __tun_chr_ioctl+0x1616/0x2370 ? __sanitizer_cov_trace_switch+0x58/0xa0 ? __sanitizer_cov_trace_const_cmp2+0x1c/0x30 ? __pfx_tun_chr_ioctl+0x10/0x10 tun_chr_ioctl+0x2f/0x40 __x64_sys_ioctl+0x11b/0x160 x64_sys_call+0x1211/0x20d0 do_syscall_64+0x9e/0x1d0 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f5b28f165d7 Code: b3 66 90 48 8b 05 b1 48 2d 00 64 c7 00 26 00 00 00 48 c7 c0 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 81 48 2d 00 8 RSP: 002b:00007ffc2b59c5e8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f5b28f165d7 RDX: 0000000000000000 RSI: 00000000000054e3 RDI: 0000000000000003 RBP: 00007ffc2b59c650 R08: 00007f5b291ed8c0 R09: 00007f5b2961a4c0 R10: 0000000029690010 R11: 0000000000000246 R12: 0000000000400730 R13: 00007ffc2b59cf40 R14: 0000000000000000 R15: 0000000000000000 </TASK> Kernel panic - not syncing: kernel: panic_on_warn set ... This is trigger as below: ns0 ns1 tun_set_iff() //dev is tun0 tun->dev = dev //ip link set tun0 netns ns1 put_net() //ref is 0 __tun_chr_ioctl() //TUNGETDEVNETNS net = dev_net(tun->dev); open_related_ns(&net->ns, get_net_ns); //ns1 get_net_ns() get_net() //addition on 0 Use maybe_get_net() in get_net_ns in case net's ref is zero to fix this Fixes: 0c3e0e3bb623 ("tun: Add ioctl() TUNGETDEVNETNS cmd to allow obtaining real net ns of tun device") Signed-off-by: Yue Haibing <yuehaibing(a)huawei.com> Link: https://lore.kernel.org/r/20240614131302.2698509-1-yuehaibing@huawei.com Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/core/net_namespace.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index cd867cb408c9..640891b6d1c2 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -661,11 +661,16 @@ EXPORT_SYMBOL_GPL(__put_net); * get_net_ns - increment the refcount of the network namespace * @ns: common namespace (net) * - * Returns the net's common namespace. + * Returns the net's common namespace or ERR_PTR() if ref is zero. */ struct ns_common *get_net_ns(struct ns_common *ns) { - return &get_net(container_of(ns, struct net, ns))->ns; + struct net *net; + + net = maybe_get_net(container_of(ns, struct net, ns)); + if (net) + return &net->ns; + return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(get_net_ns); -- 2.25.1

2 1

[PATCH OLK-5.10] netns: Make get_net_ns() handle zero refcount net
by Dong Chenchen 14 Oct '24

14 Oct '24

From: Yue Haibing <yuehaibing(a)huawei.com> stable inclusion from stable-v5.10.221 commit 2b82028a1f5ee3a8e04090776b10c534144ae77b category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IACR2S CVE: CVE-2024-40958 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit ff960f9d3edbe08a736b5a224d91a305ccc946b0 ] Syzkaller hit a warning: refcount_t: addition on 0; use-after-free. WARNING: CPU: 3 PID: 7890 at lib/refcount.c:25 refcount_warn_saturate+0xdf/0x1d0 Modules linked in: CPU: 3 PID: 7890 Comm: tun Not tainted 6.10.0-rc3-00100-gcaa4f9578aba-dirty #310 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 RIP: 0010:refcount_warn_saturate+0xdf/0x1d0 Code: 41 49 04 31 ff 89 de e8 9f 1e cd fe 84 db 75 9c e8 76 26 cd fe c6 05 b6 41 49 04 01 90 48 c7 c7 b8 8e 25 86 e8 d2 05 b5 fe 90 <0f> 0b 90 90 e9 79 ff ff ff e8 53 26 cd fe 0f b6 1 RSP: 0018:ffff8881067b7da0 EFLAGS: 00010286 RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffffffff811c72ac RDX: ffff8881026a2140 RSI: ffffffff811c72b5 RDI: 0000000000000001 RBP: ffff8881067b7db0 R08: 0000000000000000 R09: 205b5d3730353139 R10: 0000000000000000 R11: 205d303938375420 R12: ffff8881086500c4 R13: ffff8881086500c4 R14: ffff8881086500b0 R15: ffff888108650040 FS: 00007f5b2961a4c0(0000) GS:ffff88823bd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055d7ed36fd18 CR3: 00000001482f6000 CR4: 00000000000006f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> ? show_regs+0xa3/0xc0 ? __warn+0xa5/0x1c0 ? refcount_warn_saturate+0xdf/0x1d0 ? report_bug+0x1fc/0x2d0 ? refcount_warn_saturate+0xdf/0x1d0 ? handle_bug+0xa1/0x110 ? exc_invalid_op+0x3c/0xb0 ? asm_exc_invalid_op+0x1f/0x30 ? __warn_printk+0xcc/0x140 ? __warn_printk+0xd5/0x140 ? refcount_warn_saturate+0xdf/0x1d0 get_net_ns+0xa4/0xc0 ? __pfx_get_net_ns+0x10/0x10 open_related_ns+0x5a/0x130 __tun_chr_ioctl+0x1616/0x2370 ? __sanitizer_cov_trace_switch+0x58/0xa0 ? __sanitizer_cov_trace_const_cmp2+0x1c/0x30 ? __pfx_tun_chr_ioctl+0x10/0x10 tun_chr_ioctl+0x2f/0x40 __x64_sys_ioctl+0x11b/0x160 x64_sys_call+0x1211/0x20d0 do_syscall_64+0x9e/0x1d0 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f5b28f165d7 Code: b3 66 90 48 8b 05 b1 48 2d 00 64 c7 00 26 00 00 00 48 c7 c0 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 81 48 2d 00 8 RSP: 002b:00007ffc2b59c5e8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f5b28f165d7 RDX: 0000000000000000 RSI: 00000000000054e3 RDI: 0000000000000003 RBP: 00007ffc2b59c650 R08: 00007f5b291ed8c0 R09: 00007f5b2961a4c0 R10: 0000000029690010 R11: 0000000000000246 R12: 0000000000400730 R13: 00007ffc2b59cf40 R14: 0000000000000000 R15: 0000000000000000 </TASK> Kernel panic - not syncing: kernel: panic_on_warn set ... This is trigger as below: ns0 ns1 tun_set_iff() //dev is tun0 tun->dev = dev //ip link set tun0 netns ns1 put_net() //ref is 0 __tun_chr_ioctl() //TUNGETDEVNETNS net = dev_net(tun->dev); open_related_ns(&net->ns, get_net_ns); //ns1 get_net_ns() get_net() //addition on 0 Use maybe_get_net() in get_net_ns in case net's ref is zero to fix this Fixes: 0c3e0e3bb623 ("tun: Add ioctl() TUNGETDEVNETNS cmd to allow obtaining real net ns of tun device") Signed-off-by: Yue Haibing <yuehaibing(a)huawei.com> Link: https://lore.kernel.org/r/20240614131302.2698509-1-yuehaibing@huawei.com Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/core/net_namespace.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index cd867cb408c9..640891b6d1c2 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -661,11 +661,16 @@ EXPORT_SYMBOL_GPL(__put_net); * get_net_ns - increment the refcount of the network namespace * @ns: common namespace (net) * - * Returns the net's common namespace. + * Returns the net's common namespace or ERR_PTR() if ref is zero. */ struct ns_common *get_net_ns(struct ns_common *ns) { - return &get_net(container_of(ns, struct net, ns))->ns; + struct net *net; + + net = maybe_get_net(container_of(ns, struct net, ns)); + if (net) + return &net->ns; + return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(get_net_ns); -- 2.25.1

2 1

[PATCH OLK-6.6] net: ena: Add validation for completion descriptors consistency
by Dong Chenchen 14 Oct '24

14 Oct '24

From: David Arinzon <darinzon(a)amazon.com> mainline inclusion from mainline-v6.10-rc1 commit b37b98a3a0c1198bafe8c2d9ce0bc845b4e7a9a7 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IACS9I CVE: CVE-2024-40999 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Validate that `first` flag is set only for the first descriptor in multi-buffer packets. In case of an invalid descriptor, a reset will occur. A new reset reason for RX data corruption has been added. Signed-off-by: Shahar Itzko <itzko(a)amazon.com> Signed-off-by: David Arinzon <darinzon(a)amazon.com> Reviewed-by: Simon Horman <horms(a)kernel.org> Link: https://lore.kernel.org/r/20240512134637.25299-4-darinzon@amazon.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: drivers/net/ethernet/amazon/ena/ena_regs_defs.h [commit 071271f39ce8 add ENA_REGS_RESET_SUSPECTED_POLL_STARVATION, which lead to conflicts for not merged] Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- drivers/net/ethernet/amazon/ena/ena_eth_com.c | 37 ++++++++++++++----- drivers/net/ethernet/amazon/ena/ena_netdev.c | 2 + .../net/ethernet/amazon/ena/ena_regs_defs.h | 1 + 3 files changed, 30 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.c b/drivers/net/ethernet/amazon/ena/ena_eth_com.c index 933e619b3a31..4c6e07aa4bbb 100644 --- a/drivers/net/ethernet/amazon/ena/ena_eth_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.c @@ -229,30 +229,43 @@ static struct ena_eth_io_rx_cdesc_base * idx * io_cq->cdesc_entry_size_in_bytes); } -static u16 ena_com_cdesc_rx_pkt_get(struct ena_com_io_cq *io_cq, - u16 *first_cdesc_idx) +static int ena_com_cdesc_rx_pkt_get(struct ena_com_io_cq *io_cq, + u16 *first_cdesc_idx, + u16 *num_descs) { + u16 count = io_cq->cur_rx_pkt_cdesc_count, head_masked; struct ena_eth_io_rx_cdesc_base *cdesc; - u16 count = 0, head_masked; u32 last = 0; do { + u32 status; + cdesc = ena_com_get_next_rx_cdesc(io_cq); if (!cdesc) break; + status = READ_ONCE(cdesc->status); ena_com_cq_inc_head(io_cq); + if (unlikely((status & ENA_ETH_IO_RX_CDESC_BASE_FIRST_MASK) >> + ENA_ETH_IO_RX_CDESC_BASE_FIRST_SHIFT && count != 0)) { + struct ena_com_dev *dev = ena_com_io_cq_to_ena_dev(io_cq); + + netdev_err(dev->net_device, + "First bit is on in descriptor #%d on q_id: %d, req_id: %u\n", + count, io_cq->qid, cdesc->req_id); + return -EFAULT; + } count++; - last = (READ_ONCE(cdesc->status) & ENA_ETH_IO_RX_CDESC_BASE_LAST_MASK) >> - ENA_ETH_IO_RX_CDESC_BASE_LAST_SHIFT; + last = (status & ENA_ETH_IO_RX_CDESC_BASE_LAST_MASK) >> + ENA_ETH_IO_RX_CDESC_BASE_LAST_SHIFT; } while (!last); if (last) { *first_cdesc_idx = io_cq->cur_rx_pkt_cdesc_start_idx; - count += io_cq->cur_rx_pkt_cdesc_count; head_masked = io_cq->head & (io_cq->q_depth - 1); + *num_descs = count; io_cq->cur_rx_pkt_cdesc_count = 0; io_cq->cur_rx_pkt_cdesc_start_idx = head_masked; @@ -260,11 +273,11 @@ static u16 ena_com_cdesc_rx_pkt_get(struct ena_com_io_cq *io_cq, "ENA q_id: %d packets were completed. first desc idx %u descs# %d\n", io_cq->qid, *first_cdesc_idx, count); } else { - io_cq->cur_rx_pkt_cdesc_count += count; - count = 0; + io_cq->cur_rx_pkt_cdesc_count = count; + *num_descs = 0; } - return count; + return 0; } static int ena_com_create_meta(struct ena_com_io_sq *io_sq, @@ -539,10 +552,14 @@ int ena_com_rx_pkt(struct ena_com_io_cq *io_cq, u16 cdesc_idx = 0; u16 nb_hw_desc; u16 i = 0; + int rc; WARN(io_cq->direction != ENA_COM_IO_QUEUE_DIRECTION_RX, "wrong Q type"); - nb_hw_desc = ena_com_cdesc_rx_pkt_get(io_cq, &cdesc_idx); + rc = ena_com_cdesc_rx_pkt_get(io_cq, &cdesc_idx, &nb_hw_desc); + if (unlikely(rc != 0)) + return -EFAULT; + if (nb_hw_desc == 0) { ena_rx_ctx->descs = nb_hw_desc; return 0; diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 0d201a57d7e2..6907e99b2ea7 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -1323,6 +1323,8 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, if (rc == -ENOSPC) { ena_increase_stat(&rx_ring->rx_stats.bad_desc_num, 1, &rx_ring->syncp); ena_reset_device(adapter, ENA_REGS_RESET_TOO_MANY_RX_DESCS); + } else if (rc == -EFAULT) { + ena_reset_device(adapter, ENA_REGS_RESET_RX_DESCRIPTOR_MALFORMED); } else { ena_increase_stat(&rx_ring->rx_stats.bad_req_id, 1, &rx_ring->syncp); diff --git a/drivers/net/ethernet/amazon/ena/ena_regs_defs.h b/drivers/net/ethernet/amazon/ena/ena_regs_defs.h index 1e007a41a525..2e7109968205 100644 --- a/drivers/net/ethernet/amazon/ena/ena_regs_defs.h +++ b/drivers/net/ethernet/amazon/ena/ena_regs_defs.h @@ -21,6 +21,7 @@ enum ena_regs_reset_reason_types { ENA_REGS_RESET_USER_TRIGGER = 12, ENA_REGS_RESET_GENERIC = 13, ENA_REGS_RESET_MISS_INTERRUPT = 14, + ENA_REGS_RESET_RX_DESCRIPTOR_MALFORMED = 15, }; /* ena_registers offsets */ -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1 0/2] net/sched: Fix CVE-2024-36244
by Dong Chenchen 14 Oct '24

14 Oct '24

Fix CVE-2024-36244. Kuniyuki Iwashima (1): net/sched: taprio: Limit TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME to INT_MAX. Vladimir Oltean (1): net/sched: taprio: extend minimum interval restriction to entire cycle too net/sched/sch_taprio.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) -- 2.25.1

2 3

[PATCH OLK-5.10 0/2] net/sched: Fix CVE-2024-36244
by Dong Chenchen 14 Oct '24

14 Oct '24

Fix CVE-2024-36244 Kuniyuki Iwashima (1): net/sched: taprio: Limit TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME to INT_MAX. Vladimir Oltean (1): net/sched: taprio: extend minimum interval restriction to entire cycle too net/sched/sch_taprio.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) -- 2.25.1

2 3

[PATCH OLK-6.6] net: stmmac: move the EST lock to struct stmmac_priv
by Dong Chenchen 14 Oct '24

14 Oct '24

From: Xiaolei Wang <xiaolei.wang(a)windriver.com> mainline inclusion from mainline-v6.10-rc1 commit 36ac9e7f2e5786bd37c5cd91132e1f39c29b8197 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IA6S5U CVE: CVE-2024-38594 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Reinitialize the whole EST structure would also reset the mutex lock which is embedded in the EST structure, and then trigger the following warning. To address this, move the lock to struct stmmac_priv. We also need to reacquire the mutex lock when doing this initialization. DEBUG_LOCKS_WARN_ON(lock->magic != lock) WARNING: CPU: 3 PID: 505 at kernel/locking/mutex.c:587 __mutex_lock+0xd84/0x1068 Modules linked in: CPU: 3 PID: 505 Comm: tc Not tainted 6.9.0-rc6-00053-g0106679839f7-dirty #29 Hardware name: NXP i.MX8MPlus EVK board (DT) pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : __mutex_lock+0xd84/0x1068 lr : __mutex_lock+0xd84/0x1068 sp : ffffffc0864e3570 x29: ffffffc0864e3570 x28: ffffffc0817bdc78 x27: 0000000000000003 x26: ffffff80c54f1808 x25: ffffff80c9164080 x24: ffffffc080d723ac x23: 0000000000000000 x22: 0000000000000002 x21: 0000000000000000 x20: 0000000000000000 x19: ffffffc083bc3000 x18: ffffffffffffffff x17: ffffffc08117b080 x16: 0000000000000002 x15: ffffff80d2d40000 x14: 00000000000002da x13: ffffff80d2d404b8 x12: ffffffc082b5a5c8 x11: ffffffc082bca680 x10: ffffffc082bb2640 x9 : ffffffc082bb2698 x8 : 0000000000017fe8 x7 : c0000000ffffefff x6 : 0000000000000001 x5 : ffffff8178fe0d48 x4 : 0000000000000000 x3 : 0000000000000027 x2 : ffffff8178fe0d50 x1 : 0000000000000000 x0 : 0000000000000000 Call trace: __mutex_lock+0xd84/0x1068 mutex_lock_nested+0x28/0x34 tc_setup_taprio+0x118/0x68c stmmac_setup_tc+0x50/0xf0 taprio_change+0x868/0xc9c Fixes: b2aae654a479 ("net: stmmac: add mutex lock to protect est parameters") Signed-off-by: Xiaolei Wang <xiaolei.wang(a)windriver.com> Reviewed-by: Simon Horman <horms(a)kernel.org> Reviewed-by: Serge Semin <fancer.lancer(a)gmail.com> Reviewed-by: Andrew Halaney <ahalaney(a)redhat.com> Link: https://lore.kernel.org/r/20240513014346.1718740-2-xiaolei.wang@windriver.c… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c [commit c5c3e1bfc9e0("net: stmmac: Offload queueMaxSDU from tc-taprio") wasnt merged, which add tc_taprio_map_maxsdu_txq lead to conflicts.] Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- drivers/net/ethernet/stmicro/stmmac/stmmac.h | 2 ++ .../net/ethernet/stmicro/stmmac/stmmac_ptp.c | 8 ++++---- .../net/ethernet/stmicro/stmmac/stmmac_tc.c | 18 ++++++++++-------- include/linux/stmmac.h | 1 - 4 files changed, 16 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index b8c93b881a65..85a55f459af0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -248,6 +248,8 @@ struct stmmac_priv { struct stmmac_extra_stats xstats ____cacheline_aligned_in_smp; struct stmmac_safety_stats sstats; struct plat_stmmacenet_data *plat; + /* Protect est parameters */ + struct mutex est_lock; struct dma_features dma_cap; struct stmmac_counters mmc; int hw_cap_support; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index 3d7825cb30bb..a04bb2e42c4e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -70,11 +70,11 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta) /* If EST is enabled, disabled it before adjust ptp time. */ if (priv->plat->est && priv->plat->est->enable) { est_rst = true; - mutex_lock(&priv->plat->est->lock); + mutex_lock(&priv->est_lock); priv->plat->est->enable = false; stmmac_est_configure(priv, priv->ioaddr, priv->plat->est, priv->plat->clk_ptp_rate); - mutex_unlock(&priv->plat->est->lock); + mutex_unlock(&priv->est_lock); } write_lock_irqsave(&priv->ptp_lock, flags); @@ -87,7 +87,7 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta) ktime_t current_time_ns, basetime; u64 cycle_time; - mutex_lock(&priv->plat->est->lock); + mutex_lock(&priv->est_lock); priv->ptp_clock_ops.gettime64(&priv->ptp_clock_ops, &current_time); current_time_ns = timespec64_to_ktime(current_time); time.tv_nsec = priv->plat->est->btr_reserve[0]; @@ -104,7 +104,7 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta) priv->plat->est->enable = true; ret = stmmac_est_configure(priv, priv->ioaddr, priv->plat->est, priv->plat->clk_ptp_rate); - mutex_unlock(&priv->plat->est->lock); + mutex_unlock(&priv->est_lock); if (ret) netdev_err(priv->dev, "failed to configure EST\n"); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 77245f856dd0..a11bb042db27 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -983,17 +983,19 @@ static int tc_setup_taprio(struct stmmac_priv *priv, if (!plat->est) return -ENOMEM; - mutex_init(&priv->plat->est->lock); + mutex_init(&priv->est_lock); } else { + mutex_lock(&priv->est_lock); memset(plat->est, 0, sizeof(*plat->est)); + mutex_unlock(&priv->est_lock); } size = qopt->num_entries; - mutex_lock(&priv->plat->est->lock); + mutex_lock(&priv->est_lock); priv->plat->est->gcl_size = size; priv->plat->est->enable = qopt->cmd == TAPRIO_CMD_REPLACE; - mutex_unlock(&priv->plat->est->lock); + mutex_unlock(&priv->est_lock); for (i = 0; i < size; i++) { s64 delta_ns = qopt->entries[i].interval; @@ -1024,7 +1026,7 @@ static int tc_setup_taprio(struct stmmac_priv *priv, priv->plat->est->gcl[i] = delta_ns | (gates << wid); } - mutex_lock(&priv->plat->est->lock); + mutex_lock(&priv->est_lock); /* Adjust for real system time */ priv->ptp_clock_ops.gettime64(&priv->ptp_clock_ops, &current_time); current_time_ns = timespec64_to_ktime(current_time); @@ -1043,7 +1045,7 @@ static int tc_setup_taprio(struct stmmac_priv *priv, priv->plat->est->ctr[1] = (u32)ctr; if (fpe && !priv->dma_cap.fpesel) { - mutex_unlock(&priv->plat->est->lock); + mutex_unlock(&priv->est_lock); return -EOPNOTSUPP; } @@ -1054,7 +1056,7 @@ static int tc_setup_taprio(struct stmmac_priv *priv, ret = stmmac_est_configure(priv, priv->ioaddr, priv->plat->est, priv->plat->clk_ptp_rate); - mutex_unlock(&priv->plat->est->lock); + mutex_unlock(&priv->est_lock); if (ret) { netdev_err(priv->dev, "failed to configure EST\n"); goto disable; @@ -1071,11 +1073,11 @@ static int tc_setup_taprio(struct stmmac_priv *priv, disable: if (priv->plat->est) { - mutex_lock(&priv->plat->est->lock); + mutex_lock(&priv->est_lock); priv->plat->est->enable = false; stmmac_est_configure(priv, priv->ioaddr, priv->plat->est, priv->plat->clk_ptp_rate); - mutex_unlock(&priv->plat->est->lock); + mutex_unlock(&priv->est_lock); } priv->plat->fpe_cfg->enable = false; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 482f56e27988..e286ebd32fe6 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -118,7 +118,6 @@ struct stmmac_axi { #define EST_GCL 1024 struct stmmac_est { - struct mutex lock; int enable; u32 btr_reserve[2]; u32 btr_offset[2]; -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1] ipv6: sr: fix invalid unregister error path
by Dong Chenchen 14 Oct '24

14 Oct '24

From: Hangbin Liu <liuhangbin(a)gmail.com> stable inclusion from stable-v5.10.219 commit 00e6335329f23ac6cf3105931691674e28bc598c category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IA6SHW CVE: CVE-2024-38612 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 160e9d2752181fcf18c662e74022d77d3164cd45 ] The error path of seg6_init() is wrong in case CONFIG_IPV6_SEG6_LWTUNNEL is not defined. In that case if seg6_hmac_init() fails, the genl_unregister_family() isn't called. This issue exist since commit 46738b1317e1 ("ipv6: sr: add option to control lwtunnel support"), and commit 5559cea2d5aa ("ipv6: sr: fix possible use-after-free and null-ptr-deref") replaced unregister_pernet_subsys() with genl_unregister_family() in this error path. Fixes: 46738b1317e1 ("ipv6: sr: add option to control lwtunnel support") Reported-by: Guillaume Nault <gnault(a)redhat.com> Signed-off-by: Hangbin Liu <liuhangbin(a)gmail.com> Reviewed-by: Sabrina Dubroca <sd(a)queasysnail.net> Reviewed-by: David Ahern <dsahern(a)kernel.org> Link: https://lore.kernel.org/r/20240509131812.1662197-4-liuhangbin@gmail.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/ipv6/seg6.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index d59eef2f41c6..327e231021e3 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -494,6 +494,8 @@ int __init seg6_init(void) #endif #ifdef CONFIG_IPV6_SEG6_LWTUNNEL out_unregister_genl: +#endif +#if IS_ENABLED(CONFIG_IPV6_SEG6_LWTUNNEL) || IS_ENABLED(CONFIG_IPV6_SEG6_HMAC) genl_unregister_family(&seg6_genl_family); #endif out_unregister_pernet: -- 2.25.1

2 1

[PATCH OLK-5.10] ipv6: sr: fix invalid unregister error path
by Dong Chenchen 14 Oct '24

14 Oct '24

From: Hangbin Liu <liuhangbin(a)gmail.com> stable inclusion from stable-v5.10.219 commit 00e6335329f23ac6cf3105931691674e28bc598c category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IA6SHW CVE: CVE-2024-38612 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 160e9d2752181fcf18c662e74022d77d3164cd45 ] The error path of seg6_init() is wrong in case CONFIG_IPV6_SEG6_LWTUNNEL is not defined. In that case if seg6_hmac_init() fails, the genl_unregister_family() isn't called. This issue exist since commit 46738b1317e1 ("ipv6: sr: add option to control lwtunnel support"), and commit 5559cea2d5aa ("ipv6: sr: fix possible use-after-free and null-ptr-deref") replaced unregister_pernet_subsys() with genl_unregister_family() in this error path. Fixes: 46738b1317e1 ("ipv6: sr: add option to control lwtunnel support") Reported-by: Guillaume Nault <gnault(a)redhat.com> Signed-off-by: Hangbin Liu <liuhangbin(a)gmail.com> Reviewed-by: Sabrina Dubroca <sd(a)queasysnail.net> Reviewed-by: David Ahern <dsahern(a)kernel.org> Link: https://lore.kernel.org/r/20240509131812.1662197-4-liuhangbin@gmail.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/ipv6/seg6.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index d59eef2f41c6..327e231021e3 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -494,6 +494,8 @@ int __init seg6_init(void) #endif #ifdef CONFIG_IPV6_SEG6_LWTUNNEL out_unregister_genl: +#endif +#if IS_ENABLED(CONFIG_IPV6_SEG6_LWTUNNEL) || IS_ENABLED(CONFIG_IPV6_SEG6_HMAC) genl_unregister_family(&seg6_genl_family); #endif out_unregister_pernet: -- 2.25.1

2 1

[PATCH OLK-5.10] ipv4: Fix uninit-value access in __ip_make_skb()
by Dong Chenchen 14 Oct '24

14 Oct '24

From: Shigeru Yoshida <syoshida(a)redhat.com> mainline inclusion from mainline-v6.9-rc7 commit fc1092f51567277509563800a3c56732070b6aa4 category: bugfix bugzilla: 190087 CVE: CVE-2024-36927 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- KMSAN reported uninit-value access in __ip_make_skb() [1]. __ip_make_skb() tests HDRINCL to know if the skb has icmphdr. However, HDRINCL can cause a race condition. If calling setsockopt(2) with IP_HDRINCL changes HDRINCL while __ip_make_skb() is running, the function will access icmphdr in the skb even if it is not included. This causes the issue reported by KMSAN. Check FLOWI_FLAG_KNOWN_NH on fl4->flowi4_flags instead of testing HDRINCL on the socket. Also, fl4->fl4_icmp_type and fl4->fl4_icmp_code are not initialized. These are union in struct flowi4 and are implicitly initialized by flowi4_init_output(), but we should not rely on specific union layout. Initialize these explicitly in raw_sendmsg(). [1] BUG: KMSAN: uninit-value in __ip_make_skb+0x2b74/0x2d20 net/ipv4/ip_output.c:1481 __ip_make_skb+0x2b74/0x2d20 net/ipv4/ip_output.c:1481 ip_finish_skb include/net/ip.h:243 [inline] ip_push_pending_frames+0x4c/0x5c0 net/ipv4/ip_output.c:1508 raw_sendmsg+0x2381/0x2690 net/ipv4/raw.c:654 inet_sendmsg+0x27b/0x2a0 net/ipv4/af_inet.c:851 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x274/0x3c0 net/socket.c:745 __sys_sendto+0x62c/0x7b0 net/socket.c:2191 __do_sys_sendto net/socket.c:2203 [inline] __se_sys_sendto net/socket.c:2199 [inline] __x64_sys_sendto+0x130/0x200 net/socket.c:2199 do_syscall_64+0xd8/0x1f0 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x6d/0x75 Uninit was created at: slab_post_alloc_hook mm/slub.c:3804 [inline] slab_alloc_node mm/slub.c:3845 [inline] kmem_cache_alloc_node+0x5f6/0xc50 mm/slub.c:3888 kmalloc_reserve+0x13c/0x4a0 net/core/skbuff.c:577 __alloc_skb+0x35a/0x7c0 net/core/skbuff.c:668 alloc_skb include/linux/skbuff.h:1318 [inline] __ip_append_data+0x49ab/0x68c0 net/ipv4/ip_output.c:1128 ip_append_data+0x1e7/0x260 net/ipv4/ip_output.c:1365 raw_sendmsg+0x22b1/0x2690 net/ipv4/raw.c:648 inet_sendmsg+0x27b/0x2a0 net/ipv4/af_inet.c:851 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x274/0x3c0 net/socket.c:745 __sys_sendto+0x62c/0x7b0 net/socket.c:2191 __do_sys_sendto net/socket.c:2203 [inline] __se_sys_sendto net/socket.c:2199 [inline] __x64_sys_sendto+0x130/0x200 net/socket.c:2199 do_syscall_64+0xd8/0x1f0 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x6d/0x75 CPU: 1 PID: 15709 Comm: syz-executor.7 Not tainted 6.8.0-11567-gb3603fcb79b1 #25 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-1.fc39 04/01/2014 Fixes: 99e5acae193e ("ipv4: Fix potential uninit variable access bug in __ip_make_skb()") Reported-by: syzkaller <syzkaller(a)googlegroups.com> Signed-off-by: Shigeru Yoshida <syoshida(a)redhat.com> Link: https://lore.kernel.org/r/20240430123945.2057348-1-syoshida@redhat.com Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Conflicts: net/ipv4/ip_output.c [commit cafbe182a467 wasnt merged in 5.10, which leads to context conflicts for inet_test_bit() not implemented] Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/ipv4/ip_output.c | 3 ++- net/ipv4/raw.c | 3 +++ 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 5d20dac19e0b..79ff136ae6f5 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1571,7 +1571,8 @@ struct sk_buff *__ip_make_skb(struct sock *sk, * so icmphdr does not in skb linear region and can not get icmp_type * by icmp_hdr(skb)->type. */ - if (sk->sk_type == SOCK_RAW && !inet_sk(sk)->hdrincl) + if (sk->sk_type == SOCK_RAW && + !(fl4->flowi4_flags & FLOWI_FLAG_KNOWN_NH)) icmp_type = fl4->fl4_icmp_type; else icmp_type = icmp_hdr(skb)->type; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 5336731b2401..3909dcccdd3e 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -606,6 +606,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0, sk->sk_uid); + fl4.fl4_icmp_type = 0; + fl4.fl4_icmp_code = 0; + if (!hdrincl) { rfv.msg = msg; rfv.hlen = 0; -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1] atm: idt77252: prevent use after free in dequeue_rx()
by Peng Zhang 14 Oct '24

14 Oct '24

From: Dan Carpenter <dan.carpenter(a)linaro.org> stable inclusion from stable-v5.10.225 commit 1cece837e387c039225f19028df255df87a97c0d category: bugfix bugzilla: 189268 CVE: CVE-2024-44998 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit a9a18e8f770c9b0703dab93580d0b02e199a4c79 ] We can't dereference "skb" after calling vcc->push() because the skb is released. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Dan Carpenter <dan.carpenter(a)linaro.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: ZhangPeng <zhangpeng362(a)huawei.com> --- drivers/atm/idt77252.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index e616e33c8a20..25fd73fafb37 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -1118,8 +1118,8 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe) rpp->len += skb->len; if (stat & SAR_RSQE_EPDU) { + unsigned int len, truesize; unsigned char *l1l2; - unsigned int len; l1l2 = (unsigned char *) ((unsigned long) skb->data + skb->len - 6); @@ -1189,14 +1189,15 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe) ATM_SKB(skb)->vcc = vcc; __net_timestamp(skb); + truesize = skb->truesize; vcc->push(vcc, skb); atomic_inc(&vcc->stats->rx); - if (skb->truesize > SAR_FB_SIZE_3) + if (truesize > SAR_FB_SIZE_3) add_rx_skb(card, 3, SAR_FB_SIZE_3, 1); - else if (skb->truesize > SAR_FB_SIZE_2) + else if (truesize > SAR_FB_SIZE_2) add_rx_skb(card, 2, SAR_FB_SIZE_2, 1); - else if (skb->truesize > SAR_FB_SIZE_1) + else if (truesize > SAR_FB_SIZE_1) add_rx_skb(card, 1, SAR_FB_SIZE_1, 1); else add_rx_skb(card, 0, SAR_FB_SIZE_0, 1); -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1] fou: remove warn in gue_gro_receive on unsupported protocol
by Peng Zhang 14 Oct '24

14 Oct '24

From: Willem de Bruijn <willemb(a)google.com> mainline inclusion from mainline-v6.11-rc1 commit dd89a81d850fa9a65f67b4527c0e420d15bf836c category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAMMLZ CVE: CVE-2024-44940 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Drop the WARN_ON_ONCE inn gue_gro_receive if the encapsulated type is not known or does not have a GRO handler. Such a packet is easily constructed. Syzbot generates them and sets off this warning. Remove the warning as it is expected and not actionable. The warning was previously reduced from WARN_ON to WARN_ON_ONCE in commit 270136613bf7 ("fou: Do WARN_ON_ONCE in gue_gro_receive for bad proto callbacks"). Signed-off-by: Willem de Bruijn <willemb(a)google.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Link: https://lore.kernel.org/r/20240614122552.1649044-1-willemdebruijn.kernel@gm… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: net/ipv4/fou.c net/ipv4/fou_core.c [The file where the code is located is changed due to refactoring] Signed-off-by: ZhangPeng <zhangpeng362(a)huawei.com> --- net/ipv4/fou.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index e5f69b0bf3df..3b777457ad5b 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -441,7 +441,7 @@ static struct sk_buff *gue_gro_receive(struct sock *sk, rcu_read_lock(); offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[proto]); - if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive)) + if (!ops || !ops->callbacks.gro_receive) goto out_unlock; pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); -- 2.25.1

2 1

[PATCH OLK-5.10] fou: remove warn in gue_gro_receive on unsupported protocol
by Peng Zhang 14 Oct '24

14 Oct '24

From: Willem de Bruijn <willemb(a)google.com> mainline inclusion from mainline-v6.11-rc1 commit dd89a81d850fa9a65f67b4527c0e420d15bf836c category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAMMLZ CVE: CVE-2024-44940 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Drop the WARN_ON_ONCE inn gue_gro_receive if the encapsulated type is not known or does not have a GRO handler. Such a packet is easily constructed. Syzbot generates them and sets off this warning. Remove the warning as it is expected and not actionable. The warning was previously reduced from WARN_ON to WARN_ON_ONCE in commit 270136613bf7 ("fou: Do WARN_ON_ONCE in gue_gro_receive for bad proto callbacks"). Signed-off-by: Willem de Bruijn <willemb(a)google.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Link: https://lore.kernel.org/r/20240614122552.1649044-1-willemdebruijn.kernel@gm… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: net/ipv4/fou.c net/ipv4/fou_core.c [The file where the code is located is changed due to refactoring] Signed-off-by: ZhangPeng <zhangpeng362(a)huawei.com> --- net/ipv4/fou.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index e5f69b0bf3df..3b777457ad5b 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -441,7 +441,7 @@ static struct sk_buff *gue_gro_receive(struct sock *sk, rcu_read_lock(); offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[proto]); - if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive)) + if (!ops || !ops->callbacks.gro_receive) goto out_unlock; pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); -- 2.25.1

2 1

[PATCH OLK-5.10] atm: idt77252: prevent use after free in dequeue_rx()
by Peng Zhang 14 Oct '24

14 Oct '24

From: Dan Carpenter <dan.carpenter(a)linaro.org> stable inclusion from stable-v5.10.225 commit 1cece837e387c039225f19028df255df87a97c0d category: bugfix bugzilla: 189268 CVE: CVE-2024-44998 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit a9a18e8f770c9b0703dab93580d0b02e199a4c79 ] We can't dereference "skb" after calling vcc->push() because the skb is released. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Dan Carpenter <dan.carpenter(a)linaro.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: ZhangPeng <zhangpeng362(a)huawei.com> --- drivers/atm/idt77252.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index e616e33c8a20..25fd73fafb37 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -1118,8 +1118,8 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe) rpp->len += skb->len; if (stat & SAR_RSQE_EPDU) { + unsigned int len, truesize; unsigned char *l1l2; - unsigned int len; l1l2 = (unsigned char *) ((unsigned long) skb->data + skb->len - 6); @@ -1189,14 +1189,15 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe) ATM_SKB(skb)->vcc = vcc; __net_timestamp(skb); + truesize = skb->truesize; vcc->push(vcc, skb); atomic_inc(&vcc->stats->rx); - if (skb->truesize > SAR_FB_SIZE_3) + if (truesize > SAR_FB_SIZE_3) add_rx_skb(card, 3, SAR_FB_SIZE_3, 1); - else if (skb->truesize > SAR_FB_SIZE_2) + else if (truesize > SAR_FB_SIZE_2) add_rx_skb(card, 2, SAR_FB_SIZE_2, 1); - else if (skb->truesize > SAR_FB_SIZE_1) + else if (truesize > SAR_FB_SIZE_1) add_rx_skb(card, 1, SAR_FB_SIZE_1, 1); else add_rx_skb(card, 0, SAR_FB_SIZE_0, 1); -- 2.25.1

2 1

[PATCH OLK-5.10] xhci: Fix Panther point NULL pointer deref at full-speed re-enumeration
by Peng Zhang 14 Oct '24

14 Oct '24

From: Mathias Nyman <mathias.nyman(a)linux.intel.com> stable inclusion from stable-v5.10.225 commit 0f0654318e25b2c185e245ba4a591e42fabb5e59 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAOXZE CVE: CVE-2024-45006 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit af8e119f52e9c13e556be9e03f27957554a84656 upstream. re-enumerating full-speed devices after a failed address device command can trigger a NULL pointer dereference. Full-speed devices may need to reconfigure the endpoint 0 Max Packet Size value during enumeration. Usb core calls usb_ep0_reinit() in this case, which ends up calling xhci_configure_endpoint(). On Panther point xHC the xhci_configure_endpoint() function will additionally check and reserve bandwidth in software. Other hosts do this in hardware If xHC address device command fails then a new xhci_virt_device structure is allocated as part of re-enabling the slot, but the bandwidth table pointers are not set up properly here. This triggers the NULL pointer dereference the next time usb_ep0_reinit() is called and xhci_configure_endpoint() tries to check and reserve bandwidth [46710.713538] usb 3-1: new full-speed USB device number 5 using xhci_hcd [46710.713699] usb 3-1: Device not responding to setup address. [46710.917684] usb 3-1: Device not responding to setup address. [46711.125536] usb 3-1: device not accepting address 5, error -71 [46711.125594] BUG: kernel NULL pointer dereference, address: 0000000000000008 [46711.125600] #PF: supervisor read access in kernel mode [46711.125603] #PF: error_code(0x0000) - not-present page [46711.125606] PGD 0 P4D 0 [46711.125610] Oops: Oops: 0000 [#1] PREEMPT SMP PTI [46711.125615] CPU: 1 PID: 25760 Comm: kworker/1:2 Not tainted 6.10.3_2 #1 [46711.125620] Hardware name: Gigabyte Technology Co., Ltd. [46711.125623] Workqueue: usb_hub_wq hub_event [usbcore] [46711.125668] RIP: 0010:xhci_reserve_bandwidth (drivers/usb/host/xhci.c Fix this by making sure bandwidth table pointers are set up correctly after a failed address device command, and additionally by avoiding checking for bandwidth in cases like this where no actual endpoints are added or removed, i.e. only context for default control endpoint 0 is evaluated. Reported-by: Karel Balej <balejk(a)matfyz.cz> Closes: https://lore.kernel.org/linux-usb/D3CKQQAETH47.1MUO22RTCH2O3@matfyz.cz/ Cc: stable(a)vger.kernel.org Fixes: 651aaf36a7d7 ("usb: xhci: Handle USB transaction error on address command") Signed-off-by: Mathias Nyman <mathias.nyman(a)linux.intel.com> Link: https://lore.kernel.org/r/20240815141117.2702314-2-mathias.nyman@linux.inte… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: ZhangPeng <zhangpeng362(a)huawei.com> --- drivers/usb/host/xhci.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index b37ddbb88b74..b4e5b15fbed9 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -2826,7 +2826,7 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci, xhci->num_active_eps); return -ENOMEM; } - if ((xhci->quirks & XHCI_SW_BW_CHECKING) && + if ((xhci->quirks & XHCI_SW_BW_CHECKING) && !ctx_change && xhci_reserve_bandwidth(xhci, virt_dev, command->in_ctx)) { if ((xhci->quirks & XHCI_EP_LIMIT_QUIRK)) xhci_free_host_resources(xhci, ctrl_ctx); @@ -4242,8 +4242,10 @@ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev, mutex_unlock(&xhci->mutex); ret = xhci_disable_slot(xhci, udev->slot_id); xhci_free_virt_device(xhci, udev->slot_id); - if (!ret) - xhci_alloc_dev(hcd, udev); + if (!ret) { + if (xhci_alloc_dev(hcd, udev) == 1) + xhci_setup_addressable_virt_dev(xhci, udev); + } kfree(command->completion); kfree(command); return -EPROTO; -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1] xhci: Fix Panther point NULL pointer deref at full-speed re-enumeration
by Peng Zhang 14 Oct '24

14 Oct '24

From: Mathias Nyman <mathias.nyman(a)linux.intel.com> stable inclusion from stable-v5.10.225 commit 0f0654318e25b2c185e245ba4a591e42fabb5e59 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAOXZE CVE: CVE-2024-45006 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit af8e119f52e9c13e556be9e03f27957554a84656 upstream. re-enumerating full-speed devices after a failed address device command can trigger a NULL pointer dereference. Full-speed devices may need to reconfigure the endpoint 0 Max Packet Size value during enumeration. Usb core calls usb_ep0_reinit() in this case, which ends up calling xhci_configure_endpoint(). On Panther point xHC the xhci_configure_endpoint() function will additionally check and reserve bandwidth in software. Other hosts do this in hardware If xHC address device command fails then a new xhci_virt_device structure is allocated as part of re-enabling the slot, but the bandwidth table pointers are not set up properly here. This triggers the NULL pointer dereference the next time usb_ep0_reinit() is called and xhci_configure_endpoint() tries to check and reserve bandwidth [46710.713538] usb 3-1: new full-speed USB device number 5 using xhci_hcd [46710.713699] usb 3-1: Device not responding to setup address. [46710.917684] usb 3-1: Device not responding to setup address. [46711.125536] usb 3-1: device not accepting address 5, error -71 [46711.125594] BUG: kernel NULL pointer dereference, address: 0000000000000008 [46711.125600] #PF: supervisor read access in kernel mode [46711.125603] #PF: error_code(0x0000) - not-present page [46711.125606] PGD 0 P4D 0 [46711.125610] Oops: Oops: 0000 [#1] PREEMPT SMP PTI [46711.125615] CPU: 1 PID: 25760 Comm: kworker/1:2 Not tainted 6.10.3_2 #1 [46711.125620] Hardware name: Gigabyte Technology Co., Ltd. [46711.125623] Workqueue: usb_hub_wq hub_event [usbcore] [46711.125668] RIP: 0010:xhci_reserve_bandwidth (drivers/usb/host/xhci.c Fix this by making sure bandwidth table pointers are set up correctly after a failed address device command, and additionally by avoiding checking for bandwidth in cases like this where no actual endpoints are added or removed, i.e. only context for default control endpoint 0 is evaluated. Reported-by: Karel Balej <balejk(a)matfyz.cz> Closes: https://lore.kernel.org/linux-usb/D3CKQQAETH47.1MUO22RTCH2O3@matfyz.cz/ Cc: stable(a)vger.kernel.org Fixes: 651aaf36a7d7 ("usb: xhci: Handle USB transaction error on address command") Signed-off-by: Mathias Nyman <mathias.nyman(a)linux.intel.com> Link: https://lore.kernel.org/r/20240815141117.2702314-2-mathias.nyman@linux.inte… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: ZhangPeng <zhangpeng362(a)huawei.com> --- drivers/usb/host/xhci.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index b37ddbb88b74..b4e5b15fbed9 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -2826,7 +2826,7 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci, xhci->num_active_eps); return -ENOMEM; } - if ((xhci->quirks & XHCI_SW_BW_CHECKING) && + if ((xhci->quirks & XHCI_SW_BW_CHECKING) && !ctx_change && xhci_reserve_bandwidth(xhci, virt_dev, command->in_ctx)) { if ((xhci->quirks & XHCI_EP_LIMIT_QUIRK)) xhci_free_host_resources(xhci, ctrl_ctx); @@ -4242,8 +4242,10 @@ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev, mutex_unlock(&xhci->mutex); ret = xhci_disable_slot(xhci, udev->slot_id); xhci_free_virt_device(xhci, udev->slot_id); - if (!ret) - xhci_alloc_dev(hcd, udev); + if (!ret) { + if (xhci_alloc_dev(hcd, udev) == 1) + xhci_setup_addressable_virt_dev(xhci, udev); + } kfree(command->completion); kfree(command); return -EPROTO; -- 2.25.1

2 1

[PATCH OLK-6.6] crypto: stm32/cryp - call finalize with bh disabled
by Huang Xiaojia 14 Oct '24

14 Oct '24

From: Maxime Méré <maxime.mere(a)foss.st.com> stable inclusion from stable-v6.6.50 commit d93a2f86b0a998aa1f0870c85a2a60a0771ef89a category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAVU3C CVE: CVE-2024-47658 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 56ddb9aa3b324c2d9645b5a7343e46010cf3f6ce ] The finalize operation in interrupt mode produce a produces a spinlock recursion warning. The reason is the fact that BH must be disabled during this process. Signed-off-by: Maxime Méré <maxime.mere(a)foss.st.com> Signed-off-by: Herbert Xu <herbert(a)gondor.apana.org.au> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Huang Xiaojia <huangxiaojia2(a)huawei.com> --- drivers/crypto/stm32/stm32-cryp.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/crypto/stm32/stm32-cryp.c b/drivers/crypto/stm32/stm32-cryp.c index f095f0065428..2f1b82cf10b1 100644 --- a/drivers/crypto/stm32/stm32-cryp.c +++ b/drivers/crypto/stm32/stm32-cryp.c @@ -11,6 +11,7 @@ #include <crypto/internal/des.h> #include <crypto/internal/skcipher.h> #include <crypto/scatterwalk.h> +#include <linux/bottom_half.h> #include <linux/clk.h> #include <linux/delay.h> #include <linux/err.h> @@ -1665,8 +1666,11 @@ static irqreturn_t stm32_cryp_irq_thread(int irq, void *arg) it_mask &= ~IMSCR_OUT; stm32_cryp_write(cryp, cryp->caps->imsc, it_mask); - if (!cryp->payload_in && !cryp->header_in && !cryp->payload_out) + if (!cryp->payload_in && !cryp->header_in && !cryp->payload_out) { + local_bh_disable(); stm32_cryp_finish_req(cryp, 0); + local_bh_enable(); + } return IRQ_HANDLED; } -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1] crypto: stm32/cryp - call finalize with bh disabled
by Huang Xiaojia 14 Oct '24

14 Oct '24

From: Maxime Méré <maxime.mere(a)foss.st.com> stable inclusion from stable-v6.6.50 commit d93a2f86b0a998aa1f0870c85a2a60a0771ef89a category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAVU3C CVE: CVE-2024-47658 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 56ddb9aa3b324c2d9645b5a7343e46010cf3f6ce ] The finalize operation in interrupt mode produce a produces a spinlock recursion warning. The reason is the fact that BH must be disabled during this process. Signed-off-by: Maxime Méré <maxime.mere(a)foss.st.com> Signed-off-by: Herbert Xu <herbert(a)gondor.apana.org.au> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: drivers/crypto/stm32/stm32-cryp.c [Adapt context conflict] Signed-off-by: Huang Xiaojia <huangxiaojia2(a)huawei.com> --- drivers/crypto/stm32/stm32-cryp.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/crypto/stm32/stm32-cryp.c b/drivers/crypto/stm32/stm32-cryp.c index 81eb136b6c11..3467d0c98129 100644 --- a/drivers/crypto/stm32/stm32-cryp.c +++ b/drivers/crypto/stm32/stm32-cryp.c @@ -1525,8 +1525,11 @@ static irqreturn_t stm32_cryp_irq_thread(int irq, void *arg) it_mask &= ~IMSCR_OUT; stm32_cryp_write(cryp, CRYP_IMSCR, it_mask); - if (!cryp->payload_in && !cryp->header_in && !cryp->payload_out) + if (!cryp->payload_in && !cryp->header_in && !cryp->payload_out) { + local_bh_disable(); stm32_cryp_finish_req(cryp, 0); + local_bh_enable(); + } return IRQ_HANDLED; } -- 2.34.1

2 1

[PATCH OLK-5.10] crypto: stm32/cryp - call finalize with bh disabled
by Huang Xiaojia 14 Oct '24

14 Oct '24

From: Maxime Méré <maxime.mere(a)foss.st.com> stable inclusion from stable-v6.6.50 commit d93a2f86b0a998aa1f0870c85a2a60a0771ef89a category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAVU3C CVE: CVE-2024-47658 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 56ddb9aa3b324c2d9645b5a7343e46010cf3f6ce ] The finalize operation in interrupt mode produce a produces a spinlock recursion warning. The reason is the fact that BH must be disabled during this process. Signed-off-by: Maxime Méré <maxime.mere(a)foss.st.com> Signed-off-by: Herbert Xu <herbert(a)gondor.apana.org.au> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: drivers/crypto/stm32/stm32-cryp.c [Adapt context conflict] Signed-off-by: Huang Xiaojia <huangxiaojia2(a)huawei.com> --- drivers/crypto/stm32/stm32-cryp.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/crypto/stm32/stm32-cryp.c b/drivers/crypto/stm32/stm32-cryp.c index 81eb136b6c11..3467d0c98129 100644 --- a/drivers/crypto/stm32/stm32-cryp.c +++ b/drivers/crypto/stm32/stm32-cryp.c @@ -1525,8 +1525,11 @@ static irqreturn_t stm32_cryp_irq_thread(int irq, void *arg) it_mask &= ~IMSCR_OUT; stm32_cryp_write(cryp, CRYP_IMSCR, it_mask); - if (!cryp->payload_in && !cryp->header_in && !cryp->payload_out) + if (!cryp->payload_in && !cryp->header_in && !cryp->payload_out) { + local_bh_disable(); stm32_cryp_finish_req(cryp, 0); + local_bh_enable(); + } return IRQ_HANDLED; } -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1] bpf: Take return from set_memory_rox() into account with bpf_jit_binary_lock_ro()
by Yuan Can 14 Oct '24

14 Oct '24

From: Christophe Leroy <christophe.leroy(a)csgroup.eu> mainline inclusion from mainline-v6.10-rc1 commit e60adf513275c3a38e5cb67f7fd12387e43a3ff5 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAGEOD CVE: CVE-2024-42067 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- set_memory_rox() can fail, leaving memory unprotected. Check return and bail out when bpf_jit_binary_lock_ro() returns an error. Link: https://github.com/KSPP/linux/issues/7 Signed-off-by: Christophe Leroy <christophe.leroy(a)csgroup.eu> Cc: linux-hardening(a)vger.kernel.org <linux-hardening(a)vger.kernel.org> Reviewed-by: Kees Cook <keescook(a)chromium.org> Reviewed-by: Puranjay Mohan <puranjay12(a)gmail.com> Reviewed-by: Ilya Leoshkevich <iii(a)linux.ibm.com> # s390x Acked-by: Tiezhu Yang <yangtiezhu(a)loongson.cn> # LoongArch Reviewed-by: Johan Almbladh <johan.almbladh(a)anyfinetworks.com> # MIPS Part Message-ID: <036b6393f23a2032ce75a1c92220b2afcb798d5d.1709850515.git.christophe.leroy(a)csgroup.eu> Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: include/linux/filter.h arch/sparc/net/bpf_jit_comp_64.c arch/loongarch/net/bpf_jit.c arch/parisc/net/bpf_jit_core.c arch/arm/net/bpf_jit_32.c arch/mips/net/bpf_jit_comp.c arch/arm64/net/bpf_jit_comp.c arch/x86/net/bpf_jit_comp.c [some context conflict and unintroduced files on 5.10] Signed-off-by: Yuan Can <yuancan(a)huawei.com> --- arch/arm/net/bpf_jit_32.c | 25 ++++++++++++------------- arch/arm64/net/bpf_jit_comp.c | 9 ++++++++- arch/mips/net/ebpf_jit.c | 3 ++- arch/s390/net/bpf_jit_comp.c | 6 +++++- arch/sparc/net/bpf_jit_comp_64.c | 6 +++++- arch/sw_64/net/bpf_jit_comp.c | 6 +++++- arch/x86/net/bpf_jit_comp.c | 9 ++++++++- arch/x86/net/bpf_jit_comp32.c | 3 +-- include/linux/filter.h | 10 +++++++--- 9 files changed, 53 insertions(+), 24 deletions(-) diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 1214e39aad5e..9f9a2481b95f 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -2003,28 +2003,21 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) /* If building the body of the JITed code fails somehow, * we fall back to the interpretation. */ - if (build_body(&ctx) < 0) { - image_ptr = NULL; - bpf_jit_binary_free(header); - prog = orig_prog; - goto out_imms; - } + if (build_body(&ctx) < 0) + goto out_free; build_epilogue(&ctx); /* 3.) Extra pass to validate JITed Code */ - if (validate_code(&ctx)) { - image_ptr = NULL; - bpf_jit_binary_free(header); - prog = orig_prog; - goto out_imms; - } + if (validate_code(&ctx)) + goto out_free; flush_icache_range((u32)header, (u32)(ctx.target + ctx.idx)); if (bpf_jit_enable > 1) /* there are 2 passes here */ bpf_jit_dump(prog->len, image_size, 2, ctx.target); - bpf_jit_binary_lock_ro(header); + if (bpf_jit_binary_lock_ro(header)) + goto out_free; prog->bpf_func = (void *)ctx.target; prog->jited = 1; prog->jited_len = image_size; @@ -2041,5 +2034,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) bpf_jit_prog_release_other(prog, prog == orig_prog ? tmp : orig_prog); return prog; + +out_free: + image_ptr = NULL; + bpf_jit_binary_free(header); + prog = orig_prog; + goto out_imms; } diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 18627cbd6da4..aee69d78dbfa 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1114,7 +1114,14 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) prog->jited_len = 0; goto out_off; } - bpf_jit_binary_lock_ro(header); + if (bpf_jit_binary_lock_ro(header)) { + bpf_jit_binary_free(header); + prog = orig_prog; + prog->bpf_func = NULL; + prog->jited = 0; + prog->jited_len = 0; + goto out_off; + } } else { jit_data->ctx = ctx; jit_data->image = image_ptr; diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c index b31b91e57c34..a012366155c6 100644 --- a/arch/mips/net/ebpf_jit.c +++ b/arch/mips/net/ebpf_jit.c @@ -1912,7 +1912,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) /* Dump JIT code */ bpf_jit_dump(prog->len, image_size, 2, ctx.target); - bpf_jit_binary_lock_ro(header); + if (bpf_jit_binary_lock_ro(header)) + goto out_err; prog->bpf_func = (void *)ctx.target; prog->jited = 1; prog->jited_len = image_size; diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index cd0cbdafedbd..4915868bec1e 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -1807,7 +1807,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) print_fn_code(jit.prg_buf, jit.size_prg); } if (!fp->is_func || extra_pass) { - bpf_jit_binary_lock_ro(header); + if (bpf_jit_binary_lock_ro(header)) { + bpf_jit_binary_free(header); + fp = orig_fp; + goto free_addrs; + } } else { jit_data->header = header; jit_data->ctx = jit; diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c index fef734473c0f..32a53eb91797 100644 --- a/arch/sparc/net/bpf_jit_comp_64.c +++ b/arch/sparc/net/bpf_jit_comp_64.c @@ -1591,7 +1591,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) bpf_flush_icache(header, (u8 *)header + (header->pages * PAGE_SIZE)); if (!prog->is_func || extra_pass) { - bpf_jit_binary_lock_ro(header); + if (bpf_jit_binary_lock_ro(header)) { + bpf_jit_binary_free(header); + prog = orig_prog; + goto out_off; + } } else { jit_data->ctx = ctx; jit_data->image = image_ptr; diff --git a/arch/sw_64/net/bpf_jit_comp.c b/arch/sw_64/net/bpf_jit_comp.c index 47e805569154..7931c5536170 100644 --- a/arch/sw_64/net/bpf_jit_comp.c +++ b/arch/sw_64/net/bpf_jit_comp.c @@ -1466,7 +1466,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) bpf_flush_icache(header, ctx.image + ctx.idx); if (!prog->is_func || extra_pass) { - bpf_jit_binary_lock_ro(header); + if (bpf_jit_binary_lock_ro(header)) { + bpf_jit_binary_free(header); + prog = orig_prog; + goto out_off; + } } else { jit_data->ctx = ctx; jit_data->image = image_ptr; diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 6c8b9151eda8..7202dd20240a 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -2127,7 +2127,14 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) if (image) { if (!prog->is_func || extra_pass) { bpf_tail_call_direct_fixup(prog); - bpf_jit_binary_lock_ro(header); + if (bpf_jit_binary_lock_ro(header)) { + bpf_jit_binary_free(header); + prog = orig_prog; + prog->bpf_func = NULL; + prog->jited = 0; + prog->jited_len = 0; + goto out_addrs; + } } else { jit_data->addrs = addrs; jit_data->ctx = ctx; diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 622af951220c..5a208eba5f35 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -2409,8 +2409,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) if (bpf_jit_enable > 1) bpf_jit_dump(prog->len, proglen, pass + 1, image); - if (image) { - bpf_jit_binary_lock_ro(header); + if (image && !bpf_jit_binary_lock_ro(header)) { prog->bpf_func = (void *)image; prog->jited = 1; prog->jited_len = proglen; diff --git a/include/linux/filter.h b/include/linux/filter.h index 8ee00f20614f..0f85a05a1971 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -835,11 +835,15 @@ static inline int __must_check bpf_prog_lock_ro(struct bpf_prog *fp) return 0; } -static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) +static inline int __must_check +bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { + int ret = 0; set_vm_flush_reset_perms(hdr); - set_memory_ro((unsigned long)hdr, hdr->pages); - set_memory_x((unsigned long)hdr, hdr->pages); + ret = set_memory_ro((unsigned long)hdr, hdr->pages); + if (ret) + return ret; + return set_memory_x((unsigned long)hdr, hdr->pages); } static inline struct bpf_binary_header * -- 2.17.1

2 1

[PATCH openEuler-22.03-LTS-SP1] bpf: Take return from set_memory_rox() into account with bpf_jit_binary_lock_ro()
by Yuan Can 14 Oct '24

14 Oct '24

From: Christophe Leroy <christophe.leroy(a)csgroup.eu> mainline inclusion from mainline-v6.10-rc1 commit e60adf513275c3a38e5cb67f7fd12387e43a3ff5 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAGEOD CVE: CVE-2024-42067 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- set_memory_rox() can fail, leaving memory unprotected. Check return and bail out when bpf_jit_binary_lock_ro() returns an error. Link: https://github.com/KSPP/linux/issues/7 Signed-off-by: Christophe Leroy <christophe.leroy(a)csgroup.eu> Cc: linux-hardening(a)vger.kernel.org <linux-hardening(a)vger.kernel.org> Reviewed-by: Kees Cook <keescook(a)chromium.org> Reviewed-by: Puranjay Mohan <puranjay12(a)gmail.com> Reviewed-by: Ilya Leoshkevich <iii(a)linux.ibm.com> # s390x Acked-by: Tiezhu Yang <yangtiezhu(a)loongson.cn> # LoongArch Reviewed-by: Johan Almbladh <johan.almbladh(a)anyfinetworks.com> # MIPS Part Message-ID: <036b6393f23a2032ce75a1c92220b2afcb798d5d.1709850515.git.christophe.leroy(a)csgroup.eu> Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: include/linux/filter.h arch/sparc/net/bpf_jit_comp_64.c arch/loongarch/net/bpf_jit.c arch/parisc/net/bpf_jit_core.c arch/arm/net/bpf_jit_32.c arch/mips/net/bpf_jit_comp.c arch/arm64/net/bpf_jit_comp.c arch/riscv/net/bpf_jit_core.c arch/x86/net/bpf_jit_comp.c [some context conflict and unintroduced files on 5.10] Signed-off-by: Yuan Can <yuancan(a)huawei.com> --- arch/arm/net/bpf_jit_32.c | 25 ++++++++++++------------- arch/arm64/net/bpf_jit_comp.c | 9 ++++++++- arch/mips/net/ebpf_jit.c | 3 ++- arch/riscv/net/bpf_jit_core.c | 9 ++++++++- arch/s390/net/bpf_jit_comp.c | 6 +++++- arch/sparc/net/bpf_jit_comp_64.c | 6 +++++- arch/sw_64/net/bpf_jit_comp.c | 6 +++++- arch/x86/net/bpf_jit_comp.c | 9 ++++++++- arch/x86/net/bpf_jit_comp32.c | 3 +-- include/linux/filter.h | 10 +++++++--- 10 files changed, 61 insertions(+), 25 deletions(-) diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 1214e39aad5e..9f9a2481b95f 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -2003,28 +2003,21 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) /* If building the body of the JITed code fails somehow, * we fall back to the interpretation. */ - if (build_body(&ctx) < 0) { - image_ptr = NULL; - bpf_jit_binary_free(header); - prog = orig_prog; - goto out_imms; - } + if (build_body(&ctx) < 0) + goto out_free; build_epilogue(&ctx); /* 3.) Extra pass to validate JITed Code */ - if (validate_code(&ctx)) { - image_ptr = NULL; - bpf_jit_binary_free(header); - prog = orig_prog; - goto out_imms; - } + if (validate_code(&ctx)) + goto out_free; flush_icache_range((u32)header, (u32)(ctx.target + ctx.idx)); if (bpf_jit_enable > 1) /* there are 2 passes here */ bpf_jit_dump(prog->len, image_size, 2, ctx.target); - bpf_jit_binary_lock_ro(header); + if (bpf_jit_binary_lock_ro(header)) + goto out_free; prog->bpf_func = (void *)ctx.target; prog->jited = 1; prog->jited_len = image_size; @@ -2041,5 +2034,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) bpf_jit_prog_release_other(prog, prog == orig_prog ? tmp : orig_prog); return prog; + +out_free: + image_ptr = NULL; + bpf_jit_binary_free(header); + prog = orig_prog; + goto out_imms; } diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index f6e790058b0a..adab5f03a306 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1425,7 +1425,14 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) prog->jited_len = 0; goto out_off; } - bpf_jit_binary_lock_ro(header); + if (bpf_jit_binary_lock_ro(header)) { + bpf_jit_binary_free(header); + prog = orig_prog; + prog->bpf_func = NULL; + prog->jited = 0; + prog->jited_len = 0; + goto out_off; + } } else { jit_data->ctx = ctx; jit_data->image = image_ptr; diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c index b31b91e57c34..a012366155c6 100644 --- a/arch/mips/net/ebpf_jit.c +++ b/arch/mips/net/ebpf_jit.c @@ -1912,7 +1912,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) /* Dump JIT code */ bpf_jit_dump(prog->len, image_size, 2, ctx.target); - bpf_jit_binary_lock_ro(header); + if (bpf_jit_binary_lock_ro(header)) + goto out_err; prog->bpf_func = (void *)ctx.target; prog->jited = 1; prog->jited_len = image_size; diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c index ef17bc8055d4..30a144b7650a 100644 --- a/arch/riscv/net/bpf_jit_core.c +++ b/arch/riscv/net/bpf_jit_core.c @@ -163,7 +163,14 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) bpf_flush_icache(jit_data->header, ctx->insns + ctx->ninsns); if (!prog->is_func || extra_pass) { - bpf_jit_binary_lock_ro(jit_data->header); + if (bpf_jit_binary_lock_ro(jit_data->header)) { + bpf_jit_binary_free(jit_data->header); + prog = orig_prog; + prog->bpf_func = NULL; + prog->jited = 0; + prog->jited_len = 0; + goto out_offset; + } for (i = 0; i < prog->len; i++) ctx->offset[i] = ninsns_rvoff(ctx->offset[i]); bpf_prog_fill_jited_linfo(prog, ctx->offset); diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index cd0cbdafedbd..4915868bec1e 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -1807,7 +1807,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) print_fn_code(jit.prg_buf, jit.size_prg); } if (!fp->is_func || extra_pass) { - bpf_jit_binary_lock_ro(header); + if (bpf_jit_binary_lock_ro(header)) { + bpf_jit_binary_free(header); + fp = orig_fp; + goto free_addrs; + } } else { jit_data->header = header; jit_data->ctx = jit; diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c index fef734473c0f..32a53eb91797 100644 --- a/arch/sparc/net/bpf_jit_comp_64.c +++ b/arch/sparc/net/bpf_jit_comp_64.c @@ -1591,7 +1591,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) bpf_flush_icache(header, (u8 *)header + (header->pages * PAGE_SIZE)); if (!prog->is_func || extra_pass) { - bpf_jit_binary_lock_ro(header); + if (bpf_jit_binary_lock_ro(header)) { + bpf_jit_binary_free(header); + prog = orig_prog; + goto out_off; + } } else { jit_data->ctx = ctx; jit_data->image = image_ptr; diff --git a/arch/sw_64/net/bpf_jit_comp.c b/arch/sw_64/net/bpf_jit_comp.c index a8393598a4bc..43d548f7f755 100644 --- a/arch/sw_64/net/bpf_jit_comp.c +++ b/arch/sw_64/net/bpf_jit_comp.c @@ -1424,7 +1424,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) bpf_flush_icache(header, ctx.image + ctx.idx); if (!prog->is_func || extra_pass) { - bpf_jit_binary_lock_ro(header); + if (bpf_jit_binary_lock_ro(header)) { + bpf_jit_binary_free(header); + prog = orig_prog; + goto out_off; + } } else { jit_data->ctx = ctx; jit_data->image = image_ptr; diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 3a82c9508817..987b02b857bc 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -2127,7 +2127,14 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) if (image) { if (!prog->is_func || extra_pass) { bpf_tail_call_direct_fixup(prog); - bpf_jit_binary_lock_ro(header); + if (bpf_jit_binary_lock_ro(header)) { + bpf_jit_binary_free(header); + prog = orig_prog; + prog->bpf_func = NULL; + prog->jited = 0; + prog->jited_len = 0; + goto out_addrs; + } } else { jit_data->addrs = addrs; jit_data->ctx = ctx; diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 622af951220c..5a208eba5f35 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -2409,8 +2409,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) if (bpf_jit_enable > 1) bpf_jit_dump(prog->len, proglen, pass + 1, image); - if (image) { - bpf_jit_binary_lock_ro(header); + if (image && !bpf_jit_binary_lock_ro(header)) { prog->bpf_func = (void *)image; prog->jited = 1; prog->jited_len = proglen; diff --git a/include/linux/filter.h b/include/linux/filter.h index 41627cfaf7f9..758adb32d352 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -846,11 +846,15 @@ static inline int __must_check bpf_prog_lock_ro(struct bpf_prog *fp) return 0; } -static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) +static inline int __must_check +bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { + int ret = 0; set_vm_flush_reset_perms(hdr); - set_memory_ro((unsigned long)hdr, hdr->pages); - set_memory_x((unsigned long)hdr, hdr->pages); + ret = set_memory_ro((unsigned long)hdr, hdr->pages); + if (ret) + return ret; + return set_memory_x((unsigned long)hdr, hdr->pages); } static inline struct bpf_binary_header * -- 2.17.1

2 1