From: Rodrigo Siqueira Rodrigo.Siqueira@amd.com

[ Upstream commit 81f743a08f3b214638aa389e252ae5e6c3592e7c ]

[Why & How] This commit is part of a sequence of changes that replaces the commit sequence used in the DC with a new one. As a result of this transition, we moved some specific parts from the commit sequence and brought them to amdgpu_dm. This commit adds a wrapper inside DM that enable our drivers to do any necessary preparation or change before we offload the plane/stream update to DC.

Reviewed-by: Harry Wentland Harry.Wentland@amd.com Acked-by: Qingqing Zhuo qingqing.zhuo@amd.com Signed-off-by: Rodrigo Siqueira Rodrigo.Siqueira@amd.com Tested-by: Daniel Wheeler daniel.wheeler@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Stable-dep-of: ea2062dd1f03 ("drm/amd/display: fix the system hang while disable PSR") Signed-off-by: Sasha Levin sashal@kernel.org --- .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 51 +++++++++++++++---- 1 file changed, 41 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index a7bc57529e6c9..91f074f4f262c 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -348,6 +348,35 @@ static inline bool is_dc_timing_adjust_needed(struct dm_crtc_state *old_state, return false; }

+/** + * update_planes_and_stream_adapter() - Send planes to be updated in DC + * + * DC has a generic way to update planes and stream via + * dc_update_planes_and_stream function; however, DM might need some + * adjustments and preparation before calling it. This function is a wrapper + * for the dc_update_planes_and_stream that does any required configuration + * before passing control to DC. + */ +static inline bool update_planes_and_stream_adapter(struct dc *dc, + int update_type, + int planes_count, + struct dc_stream_state *stream, + struct dc_stream_update *stream_update, + struct dc_surface_update *array_of_surface_update) +{ + /* + * Previous frame finished and HW is ready for optimization. + */ + if (update_type == UPDATE_TYPE_FAST) + dc_post_update_surfaces_to_stream(dc); + + return dc_update_planes_and_stream(dc, + array_of_surface_update, + planes_count, + stream, + stream_update); +} + /** * dm_pflip_high_irq() - Handle pageflip interrupt * @interrupt_params: ignored @@ -2633,11 +2662,12 @@ static void dm_gpureset_commit_state(struct dc_state *dc_state, true; }

- dc_update_planes_and_stream(dm->dc, - bundle->surface_updates, - dc_state->stream_status->plane_count, - dc_state->streams[k], - &bundle->stream_update); + update_planes_and_stream_adapter(dm->dc, + UPDATE_TYPE_FULL, + dc_state->stream_status->plane_count, + dc_state->streams[k], + &bundle->stream_update, + bundle->surface_updates); }

cleanup: @@ -7889,11 +7919,12 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, acrtc_state->stream->link->psr_settings.psr_allow_active) amdgpu_dm_psr_disable(acrtc_state->stream);

- dc_update_planes_and_stream(dm->dc, - bundle->surface_updates, - planes_count, - acrtc_state->stream, - &bundle->stream_update); + update_planes_and_stream_adapter(dm->dc, + acrtc_state->update_type, + planes_count, + acrtc_state->stream, + &bundle->stream_update, + bundle->surface_updates);

/** * Enable or disable the interrupts on the backend.

From: Sherry Sun sherry.sun@nxp.com

[ Upstream commit 34ebb26f12a84b744f43c5c4869516f122a2dfaa ]

Add rx_watermark parameter for struct lpuart_port to make the receive watermark configurable for different platforms. No function changed.

Signed-off-by: Sherry Sun sherry.sun@nxp.com Link: https://lore.kernel.org/r/20230130064449.9564-2-sherry.sun@nxp.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Stable-dep-of: a82c3df955f8 ("tty: serial: fsl_lpuart: reduce RX watermark to 0 on LS1028A") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/tty/serial/fsl_lpuart.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index dc7ac1ddbca5e..82066f17bdfb1 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -257,6 +257,7 @@ struct lpuart_port { unsigned int txfifo_size; unsigned int rxfifo_size;

+ u8 rx_watermark; bool lpuart_dma_tx_use; bool lpuart_dma_rx_use; struct dma_chan *dma_tx_chan; @@ -283,38 +284,45 @@ struct lpuart_soc_data { enum lpuart_type devtype; char iotype; u8 reg_off; + u8 rx_watermark; };

static const struct lpuart_soc_data vf_data = { .devtype = VF610_LPUART, .iotype = UPIO_MEM, + .rx_watermark = 1, };

static const struct lpuart_soc_data ls1021a_data = { .devtype = LS1021A_LPUART, .iotype = UPIO_MEM32BE, + .rx_watermark = 1, };

static const struct lpuart_soc_data ls1028a_data = { .devtype = LS1028A_LPUART, .iotype = UPIO_MEM32, + .rx_watermark = 1, };

static struct lpuart_soc_data imx7ulp_data = { .devtype = IMX7ULP_LPUART, .iotype = UPIO_MEM32, .reg_off = IMX_REG_OFF, + .rx_watermark = 1, };

static struct lpuart_soc_data imx8qxp_data = { .devtype = IMX8QXP_LPUART, .iotype = UPIO_MEM32, .reg_off = IMX_REG_OFF, + .rx_watermark = 1, }; static struct lpuart_soc_data imxrt1050_data = { .devtype = IMXRT1050_LPUART, .iotype = UPIO_MEM32, .reg_off = IMX_REG_OFF, + .rx_watermark = 1, };

static const struct of_device_id lpuart_dt_ids[] = { @@ -1533,7 +1541,7 @@ static void lpuart_setup_watermark(struct lpuart_port *sport) }

writeb(0, sport->port.membase + UARTTWFIFO); - writeb(1, sport->port.membase + UARTRWFIFO); + writeb(sport->rx_watermark, sport->port.membase + UARTRWFIFO);

/* Restore cr2 */ writeb(cr2_saved, sport->port.membase + UARTCR2); @@ -1568,7 +1576,8 @@ static void lpuart32_setup_watermark(struct lpuart_port *sport) lpuart32_write(&sport->port, val, UARTFIFO);

/* set the watermark */ - val = (0x1 << UARTWATER_RXWATER_OFF) | (0x0 << UARTWATER_TXWATER_OFF); + val = (sport->rx_watermark << UARTWATER_RXWATER_OFF) | + (0x0 << UARTWATER_TXWATER_OFF); lpuart32_write(&sport->port, val, UARTWATER);

/* Restore cr2 */ @@ -2714,6 +2723,7 @@ static int lpuart_probe(struct platform_device *pdev) sport->port.dev = &pdev->dev; sport->port.type = PORT_LPUART; sport->devtype = sdata->devtype; + sport->rx_watermark = sdata->rx_watermark; ret = platform_get_irq(pdev, 0); if (ret < 0) return ret;

From: Damien Le Moal dlemoal@kernel.org

[ Upstream commit 6aa0365a3c8512587fffd42fe438768709ddef8e ]

When an ATA port is resumed from sleep, the port is reset and a power management request issued to libata EH to reset the port and rescanning the device(s) attached to the port. Device rescanning is done by scheduling an ata_scsi_dev_rescan() work, which will execute scsi_rescan_device().

However, scsi_rescan_device() takes the generic device lock, which is also taken by dpm_resume() when the SCSI device is resumed as well. If a device rescan execution starts before the completion of the SCSI device resume, the rcu locking used to refresh the cached VPD pages of the device, combined with the generic device locking from scsi_rescan_device() and from dpm_resume() can cause a deadlock.

Avoid this situation by changing struct ata_port scsi_rescan_task to be a delayed work instead of a simple work_struct. ata_scsi_dev_rescan() is modified to check if the SCSI device associated with the ATA device that must be rescanned is not suspended. If the SCSI device is still suspended, ata_scsi_dev_rescan() returns early and reschedule itself for execution after an arbitrary delay of 5ms.

Reported-by: Kai-Heng Feng kai.heng.feng@canonical.com Reported-by: Joe Breuer linux-kernel@jmbreuer.net Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217530 Fixes: a19a93e4c6a9 ("scsi: core: pm: Rely on the device driver core for async power management") Signed-off-by: Damien Le Moal dlemoal@kernel.org Reviewed-by: Hannes Reinecke hare@suse.de Tested-by: Kai-Heng Feng kai.heng.feng@canonical.com Tested-by: Joe Breuer linux-kernel@jmbreuer.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/ata/libata-core.c | 3 ++- drivers/ata/libata-eh.c | 2 +- drivers/ata/libata-scsi.c | 22 +++++++++++++++++++++- include/linux/libata.h | 2 +- 4 files changed, 25 insertions(+), 4 deletions(-)

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index a5ea144722fa3..0ba0c3d1613f1 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -5313,7 +5313,7 @@ struct ata_port *ata_port_alloc(struct ata_host *host)

mutex_init(&ap->scsi_scan_mutex); INIT_DELAYED_WORK(&ap->hotplug_task, ata_scsi_hotplug); - INIT_WORK(&ap->scsi_rescan_task, ata_scsi_dev_rescan); + INIT_DELAYED_WORK(&ap->scsi_rescan_task, ata_scsi_dev_rescan); INIT_LIST_HEAD(&ap->eh_done_q); init_waitqueue_head(&ap->eh_wait_q); init_completion(&ap->park_req_pending); @@ -5919,6 +5919,7 @@ static void ata_port_detach(struct ata_port *ap) WARN_ON(!(ap->pflags & ATA_PFLAG_UNLOADED));

cancel_delayed_work_sync(&ap->hotplug_task); + cancel_delayed_work_sync(&ap->scsi_rescan_task);

skip_eh: /* clean up zpodd on port removal */ diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 08e11bc312c28..a3ae5fc2a42fc 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -2973,7 +2973,7 @@ static int ata_eh_revalidate_and_attach(struct ata_link *link, ehc->i.flags |= ATA_EHI_SETMODE;

/* schedule the scsi_rescan_device() here */ - schedule_work(&(ap->scsi_rescan_task)); + schedule_delayed_work(&ap->scsi_rescan_task, 0); } else if (dev->class == ATA_DEV_UNKNOWN && ehc->tries[dev->devno] && ata_class_enabled(ehc->classes[dev->devno])) { diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 39e1ff9b686b9..9c0052d28078a 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -4601,10 +4601,11 @@ int ata_scsi_user_scan(struct Scsi_Host *shost, unsigned int channel, void ata_scsi_dev_rescan(struct work_struct *work) { struct ata_port *ap = - container_of(work, struct ata_port, scsi_rescan_task); + container_of(work, struct ata_port, scsi_rescan_task.work); struct ata_link *link; struct ata_device *dev; unsigned long flags; + bool delay_rescan = false;

mutex_lock(&ap->scsi_scan_mutex); spin_lock_irqsave(ap->lock, flags); @@ -4618,6 +4619,21 @@ void ata_scsi_dev_rescan(struct work_struct *work) if (scsi_device_get(sdev)) continue;

+ /* + * If the rescan work was scheduled because of a resume + * event, the port is already fully resumed, but the + * SCSI device may not yet be fully resumed. In such + * case, executing scsi_rescan_device() may cause a + * deadlock with the PM code on device_lock(). Prevent + * this by giving up and retrying rescan after a short + * delay. + */ + delay_rescan = sdev->sdev_gendev.power.is_suspended; + if (delay_rescan) { + scsi_device_put(sdev); + break; + } + spin_unlock_irqrestore(ap->lock, flags); scsi_rescan_device(&(sdev->sdev_gendev)); scsi_device_put(sdev); @@ -4627,4 +4643,8 @@ void ata_scsi_dev_rescan(struct work_struct *work)

spin_unlock_irqrestore(ap->lock, flags); mutex_unlock(&ap->scsi_scan_mutex); + + if (delay_rescan) + schedule_delayed_work(&ap->scsi_rescan_task, + msecs_to_jiffies(5)); } diff --git a/include/linux/libata.h b/include/linux/libata.h index fe990176e6ee9..9713f4d8f15f4 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -834,7 +834,7 @@ struct ata_port {

struct mutex scsi_scan_mutex; struct delayed_work hotplug_task; - struct work_struct scsi_rescan_task; + struct delayed_work scsi_rescan_task;

unsigned int hsm_task_state;

From: Lino Sanfilippo l.sanfilippo@kunbus.com

commit 0e069265bce5a40c4eee52e2364bbbd4dabee94a upstream.

Writing the TPM_INT_STATUS register in the interrupt handler to clear the interrupts only has effect if a locality is held. Since this is not guaranteed at the time the interrupt is fired, claim the locality explicitly in the handler.

Signed-off-by: Lino Sanfilippo l.sanfilippo@kunbus.com Tested-by: Michael Niewöhner linux@mniewoehner.de Tested-by: Jarkko Sakkinen jarkko@kernel.org Reviewed-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/char/tpm/tpm_tis_core.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -772,7 +772,9 @@ static irqreturn_t tis_int_handler(int d wake_up_interruptible(&priv->int_queue);

/* Clear interrupts handled with TPM_EOI */ + tpm_tis_request_locality(chip, 0); rc = tpm_tis_write32(priv, TPM_INT_STATUS(priv->locality), interrupt); + tpm_tis_relinquish_locality(chip, 0); if (rc < 0) return IRQ_NONE;

From: Namjae Jeon linkinjeon@kernel.org

commit 2b9b8f3b68edb3d67d79962f02e26dbb5ae3808d upstream.

->StructureSize2 indicates command payload size. ksmbd should validate this size with rfc1002 length before accessing it. This patch remove unneeded check and add the validation for this.

[ 8.912583] BUG: KASAN: slab-out-of-bounds in ksmbd_smb2_check_message+0x12a/0xc50 [ 8.913051] Read of size 2 at addr ffff88800ac7d92c by task kworker/0:0/7 ... [ 8.914967] Call Trace: [ 8.915126] <TASK> [ 8.915267] dump_stack_lvl+0x33/0x50 [ 8.915506] print_report+0xcc/0x620 [ 8.916558] kasan_report+0xae/0xe0 [ 8.917080] kasan_check_range+0x35/0x1b0 [ 8.917334] ksmbd_smb2_check_message+0x12a/0xc50 [ 8.917935] ksmbd_verify_smb_message+0xae/0xd0 [ 8.918223] handle_ksmbd_work+0x192/0x820 [ 8.918478] process_one_work+0x419/0x760 [ 8.918727] worker_thread+0x2a2/0x6f0 [ 8.919222] kthread+0x187/0x1d0 [ 8.919723] ret_from_fork+0x1f/0x30 [ 8.919954] </TASK>

Cc: stable@vger.kernel.org Reported-by: Chih-Yen Chang cc85nod@gmail.com Signed-off-by: Namjae Jeon linkinjeon@kernel.org Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ksmbd/smb2misc.c | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-)

--- a/fs/ksmbd/smb2misc.c +++ b/fs/ksmbd/smb2misc.c @@ -351,6 +351,7 @@ int ksmbd_smb2_check_message(struct ksmb int command; __u32 clc_len; /* calculated length */ __u32 len = get_rfc1002_len(work->request_buf); + __u32 req_struct_size;

if (le32_to_cpu(hdr->NextCommand) > 0) len = le32_to_cpu(hdr->NextCommand); @@ -373,17 +374,9 @@ int ksmbd_smb2_check_message(struct ksmb }

if (smb2_req_struct_sizes[command] != pdu->StructureSize2) { - if (command != SMB2_OPLOCK_BREAK_HE && - (hdr->Status == 0 || pdu->StructureSize2 != SMB2_ERROR_STRUCTURE_SIZE2_LE)) { - /* error packets have 9 byte structure size */ - ksmbd_debug(SMB, - "Illegal request size %u for command %d\n", - le16_to_cpu(pdu->StructureSize2), command); - return 1; - } else if (command == SMB2_OPLOCK_BREAK_HE && - hdr->Status == 0 && - le16_to_cpu(pdu->StructureSize2) != OP_BREAK_STRUCT_SIZE_20 && - le16_to_cpu(pdu->StructureSize2) != OP_BREAK_STRUCT_SIZE_21) { + if (command == SMB2_OPLOCK_BREAK_HE && + le16_to_cpu(pdu->StructureSize2) != OP_BREAK_STRUCT_SIZE_20 && + le16_to_cpu(pdu->StructureSize2) != OP_BREAK_STRUCT_SIZE_21) { /* special case for SMB2.1 lease break message */ ksmbd_debug(SMB, "Illegal request size %d for oplock break\n", @@ -392,6 +385,14 @@ int ksmbd_smb2_check_message(struct ksmb } }

+ req_struct_size = le16_to_cpu(pdu->StructureSize2) + + __SMB2_HEADER_STRUCTURE_SIZE; + if (command == SMB2_LOCK_HE) + req_struct_size -= sizeof(struct smb2_lock_element); + + if (req_struct_size > len + 1) + return 1; + if (smb2_calc_size(hdr, &clc_len)) return 1;

From: Namjae Jeon linkinjeon@kernel.org

commit 5005bcb4219156f1bf7587b185080ec1da08518e upstream.

This patch validate session id and tree id in compound request. If first operation in the compound is SMB2 ECHO request, ksmbd bypass session and tree validation. So work->sess and work->tcon could be NULL. If secound request in the compound access work->sess or tcon, It cause NULL pointer dereferecing error.

Cc: stable@vger.kernel.org Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-21165 Signed-off-by: Namjae Jeon linkinjeon@kernel.org Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ksmbd/server.c | 33 ++++++++++++++++++++------------- fs/ksmbd/smb2pdu.c | 44 +++++++++++++++++++++++++++++++++++++++----- 2 files changed, 59 insertions(+), 18 deletions(-)

--- a/fs/ksmbd/server.c +++ b/fs/ksmbd/server.c @@ -185,24 +185,31 @@ static void __handle_ksmbd_work(struct k goto send; }

- if (conn->ops->check_user_session) { - rc = conn->ops->check_user_session(work); - if (rc < 0) { - command = conn->ops->get_cmd_val(work); - conn->ops->set_rsp_status(work, - STATUS_USER_SESSION_DELETED); - goto send; - } else if (rc > 0) { - rc = conn->ops->get_ksmbd_tcon(work); + do { + if (conn->ops->check_user_session) { + rc = conn->ops->check_user_session(work); if (rc < 0) { - conn->ops->set_rsp_status(work, - STATUS_NETWORK_NAME_DELETED); + if (rc == -EINVAL) + conn->ops->set_rsp_status(work, + STATUS_INVALID_PARAMETER); + else + conn->ops->set_rsp_status(work, + STATUS_USER_SESSION_DELETED); goto send; + } else if (rc > 0) { + rc = conn->ops->get_ksmbd_tcon(work); + if (rc < 0) { + if (rc == -EINVAL) + conn->ops->set_rsp_status(work, + STATUS_INVALID_PARAMETER); + else + conn->ops->set_rsp_status(work, + STATUS_NETWORK_NAME_DELETED); + goto send; + } } } - }

- do { rc = __process_request(work, conn, &command); if (rc == SERVER_HANDLER_ABORT) break; --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -90,7 +90,6 @@ int smb2_get_ksmbd_tcon(struct ksmbd_wor unsigned int cmd = le16_to_cpu(req_hdr->Command); int tree_id;

- work->tcon = NULL; if (cmd == SMB2_TREE_CONNECT_HE || cmd == SMB2_CANCEL_HE || cmd == SMB2_LOGOFF_HE) { @@ -104,10 +103,28 @@ int smb2_get_ksmbd_tcon(struct ksmbd_wor }

tree_id = le32_to_cpu(req_hdr->Id.SyncId.TreeId); + + /* + * If request is not the first in Compound request, + * Just validate tree id in header with work->tcon->id. + */ + if (work->next_smb2_rcv_hdr_off) { + if (!work->tcon) { + pr_err("The first operation in the compound does not have tcon\n"); + return -EINVAL; + } + if (work->tcon->id != tree_id) { + pr_err("tree id(%u) is different with id(%u) in first operation\n", + tree_id, work->tcon->id); + return -EINVAL; + } + return 1; + } + work->tcon = ksmbd_tree_conn_lookup(work->sess, tree_id); if (!work->tcon) { pr_err("Invalid tid %d\n", tree_id); - return -EINVAL; + return -ENOENT; }

return 1; @@ -553,7 +570,6 @@ int smb2_check_user_session(struct ksmbd unsigned int cmd = conn->ops->get_cmd_val(work); unsigned long long sess_id;

- work->sess = NULL; /* * SMB2_ECHO, SMB2_NEGOTIATE, SMB2_SESSION_SETUP command do not * require a session id, so no need to validate user session's for @@ -564,15 +580,33 @@ int smb2_check_user_session(struct ksmbd return 0;

if (!ksmbd_conn_good(conn)) - return -EINVAL; + return -EIO;

sess_id = le64_to_cpu(req_hdr->SessionId); + + /* + * If request is not the first in Compound request, + * Just validate session id in header with work->sess->id. + */ + if (work->next_smb2_rcv_hdr_off) { + if (!work->sess) { + pr_err("The first operation in the compound does not have sess\n"); + return -EINVAL; + } + if (work->sess->id != sess_id) { + pr_err("session id(%llu) is different with the first operation(%lld)\n", + sess_id, work->sess->id); + return -EINVAL; + } + return 1; + } + /* Check for validity of user session */ work->sess = ksmbd_session_lookup_all(conn, sess_id); if (work->sess) return 1; ksmbd_debug(SMB, "Invalid user session, Uid %llu\n", sess_id); - return -EINVAL; + return -ENOENT; }

static void destroy_previous_session(struct ksmbd_conn *conn,

From: Matthieu Baerts matthieu.baerts@tessares.net

commit 0a85264e48b642d360720589fdb837a3643fb9b0 upstream.

mptcp_connect tool was printing some duplicated entries when showing how to use it: -j -l -r

While at it, I also:

- moved the very few entries that were not sorted,

- added -R that was missing since commit 8a4b910d005d ("mptcp: selftests: add rcvbuf set option"),

- removed the -u parameter that has been removed in commit f730b65c9d85 ("selftests: mptcp: try to set mptcp ulp mode in different sk states").

No need to backport this, it is just an internal tool used by our selftests. The help menu is mainly useful for MPTCP kernel devs.

Acked-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/net/mptcp/mptcp_connect.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -98,8 +98,8 @@ static struct cfg_sockopt_types cfg_sock static void die_usage(void) { fprintf(stderr, "Usage: mptcp_connect [-6] [-c cmsg] [-f offset] [-i file] [-I num] [-j] [-l] " - "[-m mode] [-M mark] [-o option] [-p port] [-P mode] [-j] [-l] [-r num] " - "[-s MPTCP|TCP] [-S num] [-r num] [-t num] [-T num] [-u] [-w sec] connect_address\n"); + "[-m mode] [-M mark] [-o option] [-p port] [-P mode] [-r num] [-R num] " + "[-s MPTCP|TCP] [-S num] [-t num] [-T num] [-w sec] connect_address\n"); fprintf(stderr, "\t-6 use ipv6\n"); fprintf(stderr, "\t-c cmsg -- test cmsg type <cmsg>\n"); fprintf(stderr, "\t-f offset -- stop the I/O after receiving and sending the specified amount " @@ -118,13 +118,13 @@ static void die_usage(void) fprintf(stderr, "\t-p num -- use port num\n"); fprintf(stderr, "\t-P [saveWithPeek|saveAfterPeek] -- save data with/after MSG_PEEK form tcp socket\n"); - fprintf(stderr, "\t-t num -- set poll timeout to num\n"); - fprintf(stderr, "\t-T num -- set expected runtime to num ms\n"); fprintf(stderr, "\t-r num -- enable slow mode, limiting each write to num bytes " "-- for remove addr tests\n"); fprintf(stderr, "\t-R num -- set SO_RCVBUF to num\n"); fprintf(stderr, "\t-s [MPTCP|TCP] -- use mptcp(default) or tcp sockets\n"); fprintf(stderr, "\t-S num -- set SO_SNDBUF to num\n"); + fprintf(stderr, "\t-t num -- set poll timeout to num\n"); + fprintf(stderr, "\t-T num -- set expected runtime to num ms\n"); fprintf(stderr, "\t-w num -- wait num sec before closing the socket\n"); exit(1); }

From: Matthieu Baerts matthieu.baerts@tessares.net

commit 673004821ab98c6645bd21af56a290854e88f533 upstream.

Selftests are supposed to run on any kernels, including the old ones not supporting all MPTCP features.

New functions are now available to easily detect if a certain feature is missing by looking at kallsyms.

These new helpers are going to be used in the following commits. In order to ease the backport of such future patches, it would be good if this patch is backported up to the introduction of MPTCP selftests, hence the Fixes tag below: this type of check was supposed to be done from the beginning.

Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368 Fixes: 048d19d444be ("mptcp: add basic kselftest for mptcp") Cc: stable@vger.kernel.org Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/net/mptcp/config | 1 tools/testing/selftests/net/mptcp/mptcp_lib.sh | 38 +++++++++++++++++++++++++ 2 files changed, 39 insertions(+)

--- a/tools/testing/selftests/net/mptcp/config +++ b/tools/testing/selftests/net/mptcp/config @@ -1,3 +1,4 @@ +CONFIG_KALLSYMS=y CONFIG_MPTCP=y CONFIG_IPV6=y CONFIG_MPTCP_IPV6=y --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -38,3 +38,41 @@ mptcp_lib_check_mptcp() { exit ${KSFT_SKIP} fi } + +mptcp_lib_check_kallsyms() { + if ! mptcp_lib_has_file "/proc/kallsyms"; then + echo "SKIP: CONFIG_KALLSYMS is missing" + exit ${KSFT_SKIP} + fi +} + +# Internal: use mptcp_lib_kallsyms_has() instead +__mptcp_lib_kallsyms_has() { + local sym="${1}" + + mptcp_lib_check_kallsyms + + grep -q " ${sym}" /proc/kallsyms +} + +# $1: part of a symbol to look at, add '$' at the end for full name +mptcp_lib_kallsyms_has() { + local sym="${1}" + + if __mptcp_lib_kallsyms_has "${sym}"; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "${sym} symbol not found" +} + +# $1: part of a symbol to look at, add '$' at the end for full name +mptcp_lib_kallsyms_doesnt_have() { + local sym="${1}" + + if ! __mptcp_lib_kallsyms_has "${sym}"; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "${sym} symbol has been found" +}

From: Matthieu Baerts matthieu.baerts@tessares.net

commit 4ad39a42da2e9770c8e4c37fe632ed8898419129 upstream.

Selftests are supposed to run on any kernels, including the old ones not supporting all MPTCP features.

One of them is the full support of disconnections from the userspace introduced by commit b29fcfb54cd7 ("mptcp: full disconnect implementation").

It is possible to look for "mptcp_pm_data_reset" in kallsyms because a preparation patch added it to ease the introduction of the mentioned feature.

Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368 Fixes: 05be5e273c84 ("selftests: mptcp: add disconnect tests") Cc: stable@vger.kernel.org Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/net/mptcp/mptcp_connect.sh | 5 +++++ 1 file changed, 5 insertions(+)

--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -782,6 +782,11 @@ run_tests_disconnect() local old_cin=$cin local old_sin=$sin

+ if ! mptcp_lib_kallsyms_has "mptcp_pm_data_reset$"; then + echo "INFO: Full disconnect not supported: SKIP" + return + fi + cat $cin $cin $cin > "$cin".disconnect

# force do_transfer to cope with the multiple tranmissions

From: Matthieu Baerts matthieu.baerts@tessares.net

commit f3761b50b8e4cb4807b5d41e02144c8c8a0f2512 upstream.

Selftests are supposed to run on any kernels, including the old ones not supporting all MPTCP features.

One of them is the fullmesh flag that can be given to the MPTCP in-kernel path-manager and introduced in commit 2843ff6f36db ("mptcp: remote addresses fullmesh").

If the flag is not visible in the dump after having set it, we don't check the content. Note that if we expect to have this feature and SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES env var is set to 1, we always check the content to avoid regressions.

Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368 Fixes: 6da1dfdd037e ("selftests: mptcp: add set_flags tests in pm_netlink.sh") Cc: stable@vger.kernel.org Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/net/mptcp/pm_netlink.sh | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 664cafc60705..d02e0d63a8f9 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -178,14 +178,19 @@ subflow,backup 10.0.1.1" "set flags (backup)" ip netns exec $ns1 ./pm_nl_ctl set 10.0.1.1 flags nobackup check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow 10.0.1.1" " (nobackup)" + +# fullmesh support has been added later ip netns exec $ns1 ./pm_nl_ctl set id 1 flags fullmesh -check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +if ip netns exec $ns1 ./pm_nl_ctl dump | grep -q "fullmesh" || + mptcp_lib_expect_all_features; then + check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow,fullmesh 10.0.1.1" " (fullmesh)" -ip netns exec $ns1 ./pm_nl_ctl set id 1 flags nofullmesh -check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ + ip netns exec $ns1 ./pm_nl_ctl set id 1 flags nofullmesh + check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow 10.0.1.1" " (nofullmesh)" -ip netns exec $ns1 ./pm_nl_ctl set id 1 flags backup,fullmesh -check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ + ip netns exec $ns1 ./pm_nl_ctl set id 1 flags backup,fullmesh + check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow,backup,fullmesh 10.0.1.1" " (backup,fullmesh)" +fi

exit $ret

From: Matthieu Baerts matthieu.baerts@tessares.net

commit c6f7eccc519837ebde1d099d9610c4f1d5bd975e upstream.

Selftests are supposed to run on any kernels, including the old ones not supporting all MPTCP features.

One of them is the getsockopt(SOL_MPTCP) to get info about the MPTCP connections introduced by commit 55c42fa7fa33 ("mptcp: add MPTCP_INFO getsockopt") and the following ones.

It is possible to look for "mptcp_diag_fill_info" in kallsyms because it is introduced by the mentioned feature. So we can know in advance if the feature is supported and skip the sub-test if not.

Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368 Fixes: ce9979129a0b ("selftests: mptcp: add mptcp getsockopt test cases") Cc: stable@vger.kernel.org Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/net/mptcp/mptcp_sockopt.sh | 6 ++++++ 1 file changed, 6 insertions(+)

--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -84,6 +84,7 @@ cleanup() }

mptcp_lib_check_mptcp +mptcp_lib_check_kallsyms

ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then @@ -248,6 +249,11 @@ do_mptcp_sockopt_tests() { local lret=0

+ if ! mptcp_lib_kallsyms_has "mptcp_diag_fill_info$"; then + echo "INFO: MPTCP sockopt not supported: SKIP" + return + fi + ip netns exec "$ns_sbox" ./mptcp_sockopt lret=$?

From: Matthieu Baerts matthieu.baerts@tessares.net

commit f90adb033891d418c5dafef34a9aa49f3c860991 upstream.

Selftests are supposed to run on any kernels, including the old ones not supporting all MPTCP features.

One of them is the MPTCP Userspace PM introduced by commit 4638de5aefe5 ("mptcp: handle local addrs announced by userspace PMs").

We can skip all these tests if the feature is not supported simply by looking for the MPTCP pm_type's sysctl knob.

Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368 Fixes: 259a834fadda ("selftests: mptcp: functional tests for the userspace PM type") Cc: stable@vger.kernel.org Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/net/mptcp/userspace_pm.sh | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 192ab818f292..38a1d34f7b4d 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -5,6 +5,11 @@

mptcp_lib_check_mptcp

+if ! mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then + echo "userspace pm tests are not supported by the kernel: SKIP" + exit ${KSFT_SKIP} +fi + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Cannot not run test without ip tool"

From: Matthieu Baerts matthieu.baerts@tessares.net

commit 0c4cd3f86a40028845ad6f8af5b37165666404cd upstream.

IPTables commands using 'iptables-nft' fail on old kernels, at least 5.15 because it doesn't see the default IPTables chains:

$ iptables -L iptables/1.8.2 Failed to initialize nft: Protocol not supported

As a first step before switching to NFTables, we can use iptables-legacy if available.

Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368 Fixes: 8d014eaa9254 ("selftests: mptcp: add ADD_ADDR timeout test case") Cc: stable@vger.kernel.org Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-)

--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -25,6 +25,8 @@ capout="" ns1="" ns2="" ksft_skip=4 +iptables="iptables" +ip6tables="ip6tables" timeout_poll=30 timeout_test=$((timeout_poll * 2 + 1)) capture=0 @@ -141,7 +143,11 @@ check_tools() exit $ksft_skip fi

- if ! iptables -V &> /dev/null; then + # Use the legacy version if available to support old kernel versions + if iptables-legacy -V &> /dev/null; then + iptables="iptables-legacy" + ip6tables="ip6tables-legacy" + elif ! iptables -V &> /dev/null; then echo "SKIP: Could not run all tests without iptables tool" exit $ksft_skip fi @@ -239,9 +245,9 @@ reset_with_add_addr_timeout()

reset "${1}" || return 1

- tables="iptables" + tables="${iptables}" if [ $ip -eq 6 ]; then - tables="ip6tables" + tables="${ip6tables}" fi

ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 @@ -306,9 +312,9 @@ reset_with_fail() local ip="${3:-4}" local tables

- tables="iptables" + tables="${iptables}" if [ $ip -eq 6 ]; then - tables="ip6tables" + tables="${ip6tables}" fi

ip netns exec $ns2 $tables \ @@ -678,7 +684,7 @@ filter_tcp_from() local src="${2}" local target="${3}"

- ip netns exec "${ns}" iptables -A INPUT -s "${src}" -p tcp -j "${target}" + ip netns exec "${ns}" ${iptables} -A INPUT -s "${src}" -p tcp -j "${target}" }

do_transfer()

From: Matthieu Baerts matthieu.baerts@tessares.net

commit 47867f0a7e831e24e5eab3330667ce9682d50fb1 upstream.

Selftests are supposed to run on any kernels, including the old ones not supporting all MPTCP features.

One of them is the MPTCP MIB counters introduced in commit fc518953bc9c ("mptcp: add and use MIB counter infrastructure") and more later. The MPTCP Join selftest heavily relies on these counters.

If a counter is not supported by the kernel, it is not displayed when using 'nstat -z'. We can then detect that and skip the verification. A new helper (get_counter()) has been added to do the required checks and return an error if the counter is not available.

Note that if we expect to have these features available and if SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES env var is set to 1, the tests will be marked as failed instead of skipped.

This new helper also makes sure we get the exact counter we want to avoid issues we had in the past, e.g. with MPTcpExtRmAddr and MPTcpExtRmAddrDrop sharing the same prefix. While at it, we uniform the way we fetch a MIB counter.

Note for the backports: we rarely change these modified blocks so if there is are conflicts, it is very likely because a counter is not used in the older kernels and we don't need that chunk.

Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368 Fixes: b08fbf241064 ("selftests: add test-cases for MPTCP MP_JOIN") Cc: stable@vger.kernel.org Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 230 +++++++++++++----------- 1 file changed, 130 insertions(+), 100 deletions(-)

--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -480,11 +480,25 @@ wait_local_port_listen() done }

-rm_addr_count() +# $1: ns ; $2: counter +get_counter() { - local ns=${1} + local ns="${1}" + local counter="${2}" + local count + + count=$(ip netns exec ${ns} nstat -asz "${counter}" | awk 'NR==1 {next} {print $2}') + if [ -z "${count}" ]; then + mptcp_lib_fail_if_expected_feature "${counter} counter" + return 1 + fi

- ip netns exec ${ns} nstat -as | grep MPTcpExtRmAddr | awk '{print $2}' + echo "${count}" +} + +rm_addr_count() +{ + get_counter "${1}" "MPTcpExtRmAddr" }

# $1: ns, $2: old rm_addr counter in $ns @@ -507,11 +521,11 @@ wait_mpj() local ns="${1}" local cnt old_cnt

- old_cnt=$(ip netns exec ${ns} nstat -as | grep MPJoinAckRx | awk '{print $2}') + old_cnt=$(get_counter ${ns} "MPTcpExtMPJoinAckRx")

local i for i in $(seq 10); do - cnt=$(ip netns exec ${ns} nstat -as | grep MPJoinAckRx | awk '{print $2}') + cnt=$(get_counter ${ns} "MPTcpExtMPJoinAckRx") [ "$cnt" = "${old_cnt}" ] || break sleep 0.1 done @@ -1191,12 +1205,13 @@ chk_csum_nr() fi

printf "%-${nr_blank}s %s" " " "sum" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}') - [ -z "$count" ] && count=0 + count=$(get_counter ${ns1} "MPTcpExtDataCsumErr") if [ "$count" != "$csum_ns1" ]; then extra_msg="$extra_msg ns1=$count" fi - if { [ "$count" != $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 0 ]; } || + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 0 ]; } || { [ "$count" -lt $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 1 ]; }; then echo "[fail] got $count data checksum error[s] expected $csum_ns1" fail_test @@ -1205,12 +1220,13 @@ chk_csum_nr() echo -n "[ ok ]" fi echo -n " - csum " - count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}') - [ -z "$count" ] && count=0 + count=$(get_counter ${ns2} "MPTcpExtDataCsumErr") if [ "$count" != "$csum_ns2" ]; then extra_msg="$extra_msg ns2=$count" fi - if { [ "$count" != $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 0 ]; } || + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 0 ]; } || { [ "$count" -lt $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 1 ]; }; then echo "[fail] got $count data checksum error[s] expected $csum_ns2" fail_test @@ -1252,12 +1268,13 @@ chk_fail_nr() fi

printf "%-${nr_blank}s %s" " " "ftx" - count=$(ip netns exec $ns_tx nstat -as | grep MPTcpExtMPFailTx | awk '{print $2}') - [ -z "$count" ] && count=0 + count=$(get_counter ${ns_tx} "MPTcpExtMPFailTx") if [ "$count" != "$fail_tx" ]; then extra_msg="$extra_msg,tx=$count" fi - if { [ "$count" != "$fail_tx" ] && [ $allow_tx_lost -eq 0 ]; } || + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != "$fail_tx" ] && [ $allow_tx_lost -eq 0 ]; } || { [ "$count" -gt "$fail_tx" ] && [ $allow_tx_lost -eq 1 ]; }; then echo "[fail] got $count MP_FAIL[s] TX expected $fail_tx" fail_test @@ -1267,12 +1284,13 @@ chk_fail_nr() fi

echo -n " - failrx" - count=$(ip netns exec $ns_rx nstat -as | grep MPTcpExtMPFailRx | awk '{print $2}') - [ -z "$count" ] && count=0 + count=$(get_counter ${ns_rx} "MPTcpExtMPFailRx") if [ "$count" != "$fail_rx" ]; then extra_msg="$extra_msg,rx=$count" fi - if { [ "$count" != "$fail_rx" ] && [ $allow_rx_lost -eq 0 ]; } || + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != "$fail_rx" ] && [ $allow_rx_lost -eq 0 ]; } || { [ "$count" -gt "$fail_rx" ] && [ $allow_rx_lost -eq 1 ]; }; then echo "[fail] got $count MP_FAIL[s] RX expected $fail_rx" fail_test @@ -1304,10 +1322,11 @@ chk_fclose_nr() fi

printf "%-${nr_blank}s %s" " " "ctx" - count=$(ip netns exec $ns_tx nstat -as | grep MPTcpExtMPFastcloseTx | awk '{print $2}') - [ -z "$count" ] && count=0 - [ "$count" != "$fclose_tx" ] && extra_msg="$extra_msg,tx=$count" - if [ "$count" != "$fclose_tx" ]; then + count=$(get_counter ${ns_tx} "MPTcpExtMPFastcloseTx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$fclose_tx" ]; then + extra_msg="$extra_msg,tx=$count" echo "[fail] got $count MP_FASTCLOSE[s] TX expected $fclose_tx" fail_test dump_stats=1 @@ -1316,10 +1335,11 @@ chk_fclose_nr() fi

echo -n " - fclzrx" - count=$(ip netns exec $ns_rx nstat -as | grep MPTcpExtMPFastcloseRx | awk '{print $2}') - [ -z "$count" ] && count=0 - [ "$count" != "$fclose_rx" ] && extra_msg="$extra_msg,rx=$count" - if [ "$count" != "$fclose_rx" ]; then + count=$(get_counter ${ns_rx} "MPTcpExtMPFastcloseRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$fclose_rx" ]; then + extra_msg="$extra_msg,rx=$count" echo "[fail] got $count MP_FASTCLOSE[s] RX expected $fclose_rx" fail_test dump_stats=1 @@ -1350,9 +1370,10 @@ chk_rst_nr() fi

printf "%-${nr_blank}s %s" " " "rtx" - count=$(ip netns exec $ns_tx nstat -as | grep MPTcpExtMPRstTx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ $count -lt $rst_tx ]; then + count=$(get_counter ${ns_tx} "MPTcpExtMPRstTx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ $count -lt $rst_tx ]; then echo "[fail] got $count MP_RST[s] TX expected $rst_tx" fail_test dump_stats=1 @@ -1361,9 +1382,10 @@ chk_rst_nr() fi

echo -n " - rstrx " - count=$(ip netns exec $ns_rx nstat -as | grep MPTcpExtMPRstRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" -lt "$rst_rx" ]; then + count=$(get_counter ${ns_rx} "MPTcpExtMPRstRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" -lt "$rst_rx" ]; then echo "[fail] got $count MP_RST[s] RX expected $rst_rx" fail_test dump_stats=1 @@ -1384,9 +1406,10 @@ chk_infi_nr() local dump_stats

printf "%-${nr_blank}s %s" " " "itx" - count=$(ip netns exec $ns2 nstat -as | grep InfiniteMapTx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$infi_tx" ]; then + count=$(get_counter ${ns2} "MPTcpExtInfiniteMapTx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$infi_tx" ]; then echo "[fail] got $count infinite map[s] TX expected $infi_tx" fail_test dump_stats=1 @@ -1395,9 +1418,10 @@ chk_infi_nr() fi

echo -n " - infirx" - count=$(ip netns exec $ns1 nstat -as | grep InfiniteMapRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$infi_rx" ]; then + count=$(get_counter ${ns1} "MPTcpExtInfiniteMapRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$infi_rx" ]; then echo "[fail] got $count infinite map[s] RX expected $infi_rx" fail_test dump_stats=1 @@ -1429,9 +1453,10 @@ chk_join_nr() fi

printf "%03u %-36s %s" "${TEST_COUNT}" "${title}" "syn" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinSynRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$syn_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPJoinSynRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_nr" ]; then echo "[fail] got $count JOIN[s] syn expected $syn_nr" fail_test dump_stats=1 @@ -1441,9 +1466,10 @@ chk_join_nr()

echo -n " - synack" with_cookie=$(ip netns exec $ns2 sysctl -n net.ipv4.tcp_syncookies) - count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinSynAckRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$syn_ack_nr" ]; then + count=$(get_counter ${ns2} "MPTcpExtMPJoinSynAckRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_ack_nr" ]; then # simult connections exceeding the limit with cookie enabled could go up to # synack validation as the conn limit can be enforced reliably only after # the subflow creation @@ -1459,9 +1485,10 @@ chk_join_nr() fi

echo -n " - ack" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinAckRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$ack_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPJoinAckRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$ack_nr" ]; then echo "[fail] got $count JOIN[s] ack expected $ack_nr" fail_test dump_stats=1 @@ -1493,12 +1520,12 @@ chk_stale_nr() local recover_nr

printf "%-${nr_blank}s %-18s" " " "stale" - stale_nr=$(ip netns exec $ns nstat -as | grep MPTcpExtSubflowStale | awk '{print $2}') - [ -z "$stale_nr" ] && stale_nr=0 - recover_nr=$(ip netns exec $ns nstat -as | grep MPTcpExtSubflowRecover | awk '{print $2}') - [ -z "$recover_nr" ] && recover_nr=0

- if [ $stale_nr -lt $stale_min ] || + stale_nr=$(get_counter ${ns} "MPTcpExtSubflowStale") + recover_nr=$(get_counter ${ns} "MPTcpExtSubflowRecover") + if [ -z "$stale_nr" ] || [ -z "$recover_nr" ]; then + echo "[skip]" + elif [ $stale_nr -lt $stale_min ] || { [ $stale_max -gt 0 ] && [ $stale_nr -gt $stale_max ]; } || [ $((stale_nr - recover_nr)) -ne $stale_delta ]; then echo "[fail] got $stale_nr stale[s] $recover_nr recover[s], " \ @@ -1534,12 +1561,12 @@ chk_add_nr() timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout)

printf "%-${nr_blank}s %s" " " "add" - count=$(ip netns exec $ns2 nstat -as MPTcpExtAddAddr | grep MPTcpExtAddAddr | awk '{print $2}') - [ -z "$count" ] && count=0 - + count=$(get_counter ${ns2} "MPTcpExtAddAddr") + if [ -z "$count" ]; then + echo -n "[skip]" # if the test configured a short timeout tolerate greater then expected # add addrs options, due to retransmissions - if [ "$count" != "$add_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_nr" ]; }; then + elif [ "$count" != "$add_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_nr" ]; }; then echo "[fail] got $count ADD_ADDR[s] expected $add_nr" fail_test dump_stats=1 @@ -1548,9 +1575,10 @@ chk_add_nr() fi

echo -n " - echo " - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtEchoAdd | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$echo_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtEchoAdd") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$echo_nr" ]; then echo "[fail] got $count ADD_ADDR echo[s] expected $echo_nr" fail_test dump_stats=1 @@ -1560,9 +1588,10 @@ chk_add_nr()

if [ $port_nr -gt 0 ]; then echo -n " - pt " - count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtPortAdd | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$port_nr" ]; then + count=$(get_counter ${ns2} "MPTcpExtPortAdd") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$port_nr" ]; then echo "[fail] got $count ADD_ADDR[s] with a port-number expected $port_nr" fail_test dump_stats=1 @@ -1571,10 +1600,10 @@ chk_add_nr() fi

printf "%-${nr_blank}s %s" " " "syn" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortSynRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$syn_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPJoinPortSynRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_nr" ]; then echo "[fail] got $count JOIN[s] syn with a different \ port-number expected $syn_nr" fail_test @@ -1584,10 +1613,10 @@ chk_add_nr() fi

echo -n " - synack" - count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinPortSynAckRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$syn_ack_nr" ]; then + count=$(get_counter ${ns2} "MPTcpExtMPJoinPortSynAckRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_ack_nr" ]; then echo "[fail] got $count JOIN[s] synack with a different \ port-number expected $syn_ack_nr" fail_test @@ -1597,10 +1626,10 @@ chk_add_nr() fi

echo -n " - ack" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortAckRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$ack_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPJoinPortAckRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$ack_nr" ]; then echo "[fail] got $count JOIN[s] ack with a different \ port-number expected $ack_nr" fail_test @@ -1610,10 +1639,10 @@ chk_add_nr() fi

printf "%-${nr_blank}s %s" " " "syn" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortSynRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$mis_syn_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMismatchPortSynRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$mis_syn_nr" ]; then echo "[fail] got $count JOIN[s] syn with a mismatched \ port-number expected $mis_syn_nr" fail_test @@ -1623,10 +1652,10 @@ chk_add_nr() fi

echo -n " - ack " - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortAckRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$mis_ack_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMismatchPortAckRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$mis_ack_nr" ]; then echo "[fail] got $count JOIN[s] ack with a mismatched \ port-number expected $mis_ack_nr" fail_test @@ -1670,9 +1699,10 @@ chk_rm_nr() fi

printf "%-${nr_blank}s %s" " " "rm " - count=$(ip netns exec $addr_ns nstat -as | grep MPTcpExtRmAddr | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$rm_addr_nr" ]; then + count=$(get_counter ${addr_ns} "MPTcpExtRmAddr") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$rm_addr_nr" ]; then echo "[fail] got $count RM_ADDR[s] expected $rm_addr_nr" fail_test dump_stats=1 @@ -1681,29 +1711,27 @@ chk_rm_nr() fi

echo -n " - rmsf " - count=$(ip netns exec $subflow_ns nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ -n "$simult" ]; then + count=$(get_counter ${subflow_ns} "MPTcpExtRmSubflow") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ -n "$simult" ]; then local cnt suffix

- cnt=$(ip netns exec $addr_ns nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}') + cnt=$(get_counter ${addr_ns} "MPTcpExtRmSubflow")

# in case of simult flush, the subflow removal count on each side is # unreliable - [ -z "$cnt" ] && cnt=0 count=$((count + cnt)) [ "$count" != "$rm_subflow_nr" ] && suffix="$count in [$rm_subflow_nr:$((rm_subflow_nr*2))]" if [ $count -ge "$rm_subflow_nr" ] && \ [ "$count" -le "$((rm_subflow_nr *2 ))" ]; then - echo "[ ok ] $suffix" + echo -n "[ ok ] $suffix" else echo "[fail] got $count RM_SUBFLOW[s] expected in range [$rm_subflow_nr:$((rm_subflow_nr*2))]" fail_test dump_stats=1 fi - return - fi - if [ "$count" != "$rm_subflow_nr" ]; then + elif [ "$count" != "$rm_subflow_nr" ]; then echo "[fail] got $count RM_SUBFLOW[s] expected $rm_subflow_nr" fail_test dump_stats=1 @@ -1724,9 +1752,10 @@ chk_prio_nr() local dump_stats

printf "%-${nr_blank}s %s" " " "ptx" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioTx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$mp_prio_nr_tx" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPPrioTx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$mp_prio_nr_tx" ]; then echo "[fail] got $count MP_PRIO[s] TX expected $mp_prio_nr_tx" fail_test dump_stats=1 @@ -1735,9 +1764,10 @@ chk_prio_nr() fi

echo -n " - prx " - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$mp_prio_nr_rx" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPPrioRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$mp_prio_nr_rx" ]; then echo "[fail] got $count MP_PRIO[s] RX expected $mp_prio_nr_rx" fail_test dump_stats=1 @@ -1813,7 +1843,7 @@ wait_attempt_fail() while [ $time -lt $timeout_ms ]; do local cnt

- cnt=$(ip netns exec $ns nstat -as TcpAttemptFails | grep TcpAttemptFails | awk '{print $2}') + cnt=$(get_counter ${ns} "TcpAttemptFails")

[ "$cnt" = 1 ] && return 1 time=$((time + 100))

From: Matthieu Baerts matthieu.baerts@tessares.net

commit ae947bb2c253ff5f395bb70cb9db8700543bf398 upstream.

Selftests are supposed to run on any kernels, including the old ones not supporting all MPTCP features.

One of them is the support of MP_FASTCLOSE introduced in commit f284c0c77321 ("mptcp: implement fastclose xmit path").

If the MIB counter is not available, the test cannot be verified and the behaviour will not be the expected one. So we can skip the test if the counter is missing.

Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368 Fixes: 01542c9bf9ab ("selftests: mptcp: add fastclose testcase") Cc: stable@vger.kernel.org Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-)

--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -253,6 +253,19 @@ reset() return 0 }

+# $1: test name ; $2: counter to check +reset_check_counter() +{ + reset "${1}" || return 1 + + local counter="${2}" + + if ! nstat -asz "${counter}" | grep -wq "${counter}"; then + mark_as_skipped "counter '${counter}' is not available" + return 1 + fi +} + # $1: test name reset_with_cookies() { @@ -2959,14 +2972,14 @@ fullmesh_tests()

fastclose_tests() { - if reset "fastclose test"; then + if reset_check_counter "fastclose test" "MPTcpExtMPFastcloseTx"; then run_tests $ns1 $ns2 10.0.1.1 1024 0 fastclose_client chk_join_nr 0 0 0 chk_fclose_nr 1 1 chk_rst_nr 1 1 invert fi

- if reset "fastclose server test"; then + if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then run_tests $ns1 $ns2 10.0.1.1 1024 0 fastclose_server chk_join_nr 0 0 0 chk_fclose_nr 1 1 invert

From: Matthieu Baerts matthieu.baerts@tessares.net

commit 36c4127ae8dd0ebac6d56d8a1b272dd483471c40 upstream.

Selftests are supposed to run on any kernels, including the old ones not supporting all MPTCP features.

One of them is the support of the implicit endpoints introduced by commit d045b9eb95a9 ("mptcp: introduce implicit endpoints").

It is possible to look for "mptcp_subflow_send_ack" in kallsyms because it was needed to introduce the mentioned feature. So we can know in advance if the feature is supported instead of trying and accepting any results.

Note that here and in the following commits, we re-do the same check for each sub-test of the same function for a few reasons. The main one is not to break the ID assign to each test in order to be able to easily compare results between different kernel versions. Also, we can still run a specific test even if it is skipped. Another reason is that it makes it clear during the review that a specific subtest will be skipped or not under certain conditions. At the end, it looks OK to call the exact same helper multiple times: it is not a critical path and it is the same code that is executed, not really more cases to maintain.

Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368 Fixes: 69c6ce7b6eca ("selftests: mptcp: add implicit endpoint test case") Cc: stable@vger.kernel.org Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -3108,8 +3108,10 @@ userspace_tests()

endpoint_tests() { + # subflow_rebuild_header is needed to support the implicit flag # userspace pm type prevents add_addr - if reset "implicit EP"; then + if reset "implicit EP" && + mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 2 2 pm_nl_set_limits $ns2 2 2 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal @@ -3129,7 +3131,8 @@ endpoint_tests() kill_tests_wait fi

- if reset "delete and re-add"; then + if reset "delete and re-add" && + mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow

From: Matthieu Baerts matthieu.baerts@tessares.net

commit 9db34c4294af9999edc773d96744e2d2d4eb5060 upstream.

Selftests are supposed to run on any kernels, including the old ones not supporting all MPTCP features.

One of them is the support of the fullmesh flag for the in-kernel PM introduced by commit 2843ff6f36db ("mptcp: remote addresses fullmesh") and commit 1a0d6136c5f0 ("mptcp: local addresses fullmesh").

It looks like there is no easy external sign we can use to predict the expected behaviour. We could add the flag and then check if it has been added but for that, and for each fullmesh test, we would need to setup a new environment, do the checks, clean it and then only start the test from yet another clean environment. To keep it simple and avoid introducing new issues, we look for a specific kernel version. That's not ideal but an acceptable solution for this case.

Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368 Fixes: 6a0653b96f5d ("selftests: mptcp: add fullmesh setting tests") Cc: stable@vger.kernel.org Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-)

--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -2936,7 +2936,8 @@ fullmesh_tests() fi

# set fullmesh flag - if reset "set fullmesh flag test"; then + if reset "set fullmesh flag test" && + continue_if mptcp_lib_kversion_ge 5.18; then pm_nl_set_limits $ns1 4 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow pm_nl_set_limits $ns2 4 4 @@ -2946,7 +2947,8 @@ fullmesh_tests() fi

# set nofullmesh flag - if reset "set nofullmesh flag test"; then + if reset "set nofullmesh flag test" && + continue_if mptcp_lib_kversion_ge 5.18; then pm_nl_set_limits $ns1 4 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow,fullmesh pm_nl_set_limits $ns2 4 4 @@ -2956,7 +2958,8 @@ fullmesh_tests() fi

# set backup,fullmesh flags - if reset "set backup,fullmesh flags test"; then + if reset "set backup,fullmesh flags test" && + continue_if mptcp_lib_kversion_ge 5.18; then pm_nl_set_limits $ns1 4 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow pm_nl_set_limits $ns2 4 4 @@ -2967,7 +2970,8 @@ fullmesh_tests() fi

# set nobackup,nofullmesh flags - if reset "set nobackup,nofullmesh flags test"; then + if reset "set nobackup,nofullmesh flags test" && + continue_if mptcp_lib_kversion_ge 5.18; then pm_nl_set_limits $ns1 4 4 pm_nl_set_limits $ns2 4 4 pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,backup,fullmesh

From: Shuah Khan skhan@linuxfoundation.org

commit d8e45bf1aed2e5fddd8985b5bb1aaf774a97aba8 upstream.

Fix the following build error due to redefining struct mount_attr by removing duplicate define from mount_setattr_test.c

gcc -g -isystem .../tools/testing/selftests/../../../usr/include -Wall -O2 -pthread mount_setattr_test.c -o .../tools/testing/selftests/mount_setattr/mount_setattr_test mount_setattr_test.c:107:8: error: redefinition of ‘struct mount_attr’ 107 | struct mount_attr { | ^~~~~~~~~~ In file included from /usr/include/x86_64-linux-gnu/sys/mount.h:32, from mount_setattr_test.c:10: .../usr/include/linux/mount.h:129:8: note: originally defined here 129 | struct mount_attr { | ^~~~~~~~~~ make: *** [../lib.mk:145: .../tools/testing/selftests/mount_setattr/mount_setattr_test] Error 1

Signed-off-by: Shuah Khan skhan@linuxfoundation.org Cc: Hardik Garg hargar@linux.microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/mount_setattr/mount_setattr_test.c | 7 ------- 1 file changed, 7 deletions(-)

--- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c +++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c @@ -104,13 +104,6 @@ #else #define __NR_mount_setattr 442 #endif - -struct mount_attr { - __u64 attr_set; - __u64 attr_clr; - __u64 propagation; - __u64 userns_fd; -}; #endif

#ifndef __NR_open_tree

From: Matthieu Baerts matthieu.baerts@tessares.net

commit b631e3a4e94c77c9007d60b577a069c203ce9594 upstream.

Selftests are supposed to run on any kernels, including the old ones not supporting all MPTCP features.

One of them is TCP_INQ cmsg support introduced in commit 2c9e77659a0c ("mptcp: add TCP_INQ cmsg support").

It is possible to look for "mptcp_ioctl" in kallsyms because it was needed to introduce the mentioned feature. We can skip these tests and not set TCPINQ option if the feature is not supported.

Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368 Fixes: 5cbd886ce2a9 ("selftests: mptcp: add TCP_INQ support") Cc: stable@vger.kernel.org Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/net/mptcp/mptcp_sockopt.sh | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-)

--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -182,9 +182,14 @@ do_transfer() local_addr="0.0.0.0" fi

+ cmsg="TIMESTAMPNS" + if mptcp_lib_kallsyms_has "mptcp_ioctl$"; then + cmsg+=",TCPINQ" + fi + timeout ${timeout_test} \ ip netns exec ${listener_ns} \ - $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c TIMESTAMPNS,TCPINQ \ + $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c "${cmsg}" \ ${local_addr} < "$sin" > "$sout" & spid=$!

@@ -192,7 +197,7 @@ do_transfer()

timeout ${timeout_test} \ ip netns exec ${connector_ns} \ - $mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c TIMESTAMPNS,TCPINQ \ + $mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c "${cmsg}" \ $connect_addr < "$cin" > "$cout" &

cpid=$! @@ -311,6 +316,11 @@ do_tcpinq_tests() ip netns exec "$ns1" iptables -F ip netns exec "$ns1" ip6tables -F

+ if ! mptcp_lib_kallsyms_has "mptcp_ioctl$"; then + echo "INFO: TCP_INQ not supported: SKIP" + return + fi + for args in "-t tcp" "-r tcp"; do do_tcpinq_test $args lret=$?

From: Matthieu Baerts matthieu.baerts@tessares.net

commit f2b492b04a167261e1c38eb76f78fb4294473a49 upstream.

Selftests are supposed to run on any kernels, including the old ones not supporting all MPTCP features.

One of them is the support of the userspace PM introduced by commit 4638de5aefe5 ("mptcp: handle local addrs announced by userspace PMs") and the following ones.

It is possible to look for the MPTCP pm_type's sysctl knob to know in advance if the userspace PM is available.

Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368 Fixes: 5ac1d2d63451 ("selftests: mptcp: Add tests for userspace PM type") Cc: stable@vger.kernel.org Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 26 +++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-)

--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -79,7 +79,7 @@ init_partial() ip netns add $netns || exit $ksft_skip ip -net $netns link set lo up ip netns exec $netns sysctl -q net.mptcp.enabled=1 - ip netns exec $netns sysctl -q net.mptcp.pm_type=0 + ip netns exec $netns sysctl -q net.mptcp.pm_type=0 2>/dev/null || true ip netns exec $netns sysctl -q net.ipv4.conf.all.rp_filter=0 ip netns exec $netns sysctl -q net.ipv4.conf.default.rp_filter=0 if [ $checksum -eq 1 ]; then @@ -3059,7 +3059,8 @@ fail_tests() userspace_tests() { # userspace pm type prevents add_addr - if reset "userspace pm type prevents add_addr"; then + if reset "userspace pm type prevents add_addr" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 0 2 @@ -3070,7 +3071,8 @@ userspace_tests() fi

# userspace pm type does not echo add_addr without daemon - if reset "userspace pm no echo w/o daemon"; then + if reset "userspace pm no echo w/o daemon" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 0 2 @@ -3081,7 +3083,8 @@ userspace_tests() fi

# userspace pm type rejects join - if reset "userspace pm type rejects join"; then + if reset "userspace pm type rejects join" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 @@ -3091,7 +3094,8 @@ userspace_tests() fi

# userspace pm type does not send join - if reset "userspace pm type does not send join"; then + if reset "userspace pm type does not send join" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 @@ -3101,7 +3105,8 @@ userspace_tests() fi

# userspace pm type prevents mp_prio - if reset "userspace pm type prevents mp_prio"; then + if reset "userspace pm type prevents mp_prio" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 @@ -3112,7 +3117,8 @@ userspace_tests() fi

# userspace pm type prevents rm_addr - if reset "userspace pm type prevents rm_addr"; then + if reset "userspace pm type prevents rm_addr" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 1 @@ -3124,7 +3130,8 @@ userspace_tests() fi

# userspace pm add & remove address - if reset "userspace pm add & remove address"; then + if reset "userspace pm add & remove address" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns2 1 1 run_tests $ns1 $ns2 10.0.1.1 0 userspace_1 0 slow @@ -3134,7 +3141,8 @@ userspace_tests() fi

# userspace pm create destroy subflow - if reset "userspace pm create destroy subflow"; then + if reset "userspace pm create destroy subflow" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 1 run_tests $ns1 $ns2 10.0.1.1 0 0 userspace_1 slow

From: Matthieu Baerts matthieu.baerts@tessares.net

It looks like this test was broken in v6.1 after the backport of commit 48d73f609dcc ("selftests: mptcp: update userspace pm addr tests").

It was not working because the commit ad3493746ebe ("selftests: mptcp: add test-cases for mixed v4/v6 subflows") is not in v6.1. This commit changes how the connections are being created in mptcp_join.sh selftest: with IPv6 support always enabled. But then in v6.1, the server still create IPv4 only connections, so without the v4-mapped-v6 format with the "::ffff:" prefix like we have in v6.3.

The modification here adds a support for connections created in v4 as well so it fixes the issue in v6.1. This patch is not needed for the selftests in v6.3 because only IPv6 listening sockets are being created.

Fixes: 8f0ba8ec18f5 ("selftests: mptcp: update userspace pm addr tests") Cc: stable@vger.kernel.org Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -946,11 +946,12 @@ do_transfer() sp=$(grep "type:10" "$evts_ns1" | sed -n 's/.*(sport:)([[:digit:]]*).*$/\2/p;q') da=$(grep "type:10" "$evts_ns1" | - sed -n 's/.*(daddr6:)([0-9a-f:.]*).*$/\2/p;q') + sed -n 's/.*(daddr[46]:)([0-9a-f:.]*).*$/\2/p;q') + echo "$da" | grep -q ":" && addr="::ffff:$addr" dp=$(grep "type:10" "$evts_ns1" | sed -n 's/.*(dport:)([[:digit:]]*).*$/\2/p;q') ip netns exec ${listener_ns} ./pm_nl_ctl rem token $tk id $id - ip netns exec ${listener_ns} ./pm_nl_ctl dsf lip "::ffff:$addr" \ + ip netns exec ${listener_ns} ./pm_nl_ctl dsf lip "$addr" \ lport $sp rip $da rport $dp token $tk fi

From: Prathu Baronia prathubaronia2011@gmail.com

commit 2049a7d0cbc6ac8e370e836ed68597be04a7dc49 upstream.

Since gfp flags have been shifted to gfp_types.h so update the path in the gfp-translate script.

Link: https://lkml.kernel.org/r/20230608154450.21758-1-prathubaronia2011@gmail.com Fixes: cb5a065b4ea9c ("headers/deps: mm: Split <linux/gfp_types.h> out of <linux/gfp.h>") Signed-off-by: Prathu Baronia prathubaronia2011@gmail.com Reviewed-by: David Hildenbrand david@redhat.com Cc: Masahiro Yamada masahiroy@kernel.org Cc: Nathan Chancellor nathan@kernel.org Cc: Nick Desaulniers ndesaulniers@google.com Cc: Nicolas Schier nicolas@fjasle.eu Cc: Ingo Molnar mingo@kernel.org Cc: Yury Norov yury.norov@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- scripts/gfp-translate | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/scripts/gfp-translate b/scripts/gfp-translate index b2ce416d944b..6c9aed17cf56 100755 --- a/scripts/gfp-translate +++ b/scripts/gfp-translate @@ -63,11 +63,11 @@ fi

# Extract GFP flags from the kernel source TMPFILE=`mktemp -t gfptranslate-XXXXXX` || exit 1 -grep -q ___GFP $SOURCE/include/linux/gfp.h +grep -q ___GFP $SOURCE/include/linux/gfp_types.h if [ $? -eq 0 ]; then - grep "^#define ___GFP" $SOURCE/include/linux/gfp.h | sed -e 's/u$//' | grep -v GFP_BITS > $TMPFILE + grep "^#define ___GFP" $SOURCE/include/linux/gfp_types.h | sed -e 's/u$//' | grep -v GFP_BITS > $TMPFILE else - grep "^#define __GFP" $SOURCE/include/linux/gfp.h | sed -e 's/(__force gfp_t)//' | sed -e 's/u)/)/' | grep -v GFP_BITS | sed -e 's/)//) //' > $TMPFILE + grep "^#define __GFP" $SOURCE/include/linux/gfp_types.h | sed -e 's/(__force gfp_t)//' | sed -e 's/u)/)/' | grep -v GFP_BITS | sed -e 's/)//) //' > $TMPFILE fi

# Parse the flags

From: Rafael J. Wysocki rafael.j.wysocki@intel.com

commit 22db06337f590d01d79f60f181d8dfe5a9ef9085 upstream.

The addition of might_sleep() to down_timeout() caused the latter to enable interrupts unconditionally in some cases, which in turn broke the ACPI S3 wakeup path in acpi_suspend_enter(), where down_timeout() is called by acpi_disable_all_gpes() via acpi_ut_acquire_mutex().

Namely, if CONFIG_DEBUG_ATOMIC_SLEEP is set, might_sleep() causes might_resched() to be used and if CONFIG_PREEMPT_VOLUNTARY is set, this triggers __cond_resched() which may call preempt_schedule_common(), so __schedule() gets invoked and it ends up with enabled interrupts (in the prev == next case).

Now, enabling interrupts early in the S3 wakeup path causes the kernel to crash.

Address this by modifying acpi_suspend_enter() to disable GPEs without attempting to acquire the sleeping lock which is not needed in that code path anyway.

Fixes: 99409b935c9a ("locking/semaphore: Add might_sleep() to down_*() family") Reported-by: Srinivas Pandruvada srinivas.pandruvada@linux.intel.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: 5.15+ stable@vger.kernel.org # 5.15+ Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/acpi/acpica/achware.h | 2 -- drivers/acpi/sleep.c | 16 ++++++++++++---- include/acpi/acpixf.h | 1 + 3 files changed, 13 insertions(+), 6 deletions(-)

--- a/drivers/acpi/acpica/achware.h +++ b/drivers/acpi/acpica/achware.h @@ -101,8 +101,6 @@ acpi_status acpi_hw_get_gpe_status(struct acpi_gpe_event_info *gpe_event_info, acpi_event_status *event_status);

-acpi_status acpi_hw_disable_all_gpes(void); - acpi_status acpi_hw_enable_all_runtime_gpes(void);

acpi_status acpi_hw_enable_all_wakeup_gpes(void); --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -636,11 +636,19 @@ static int acpi_suspend_enter(suspend_st }

/* - * Disable and clear GPE status before interrupt is enabled. Some GPEs - * (like wakeup GPE) haven't handler, this can avoid such GPE misfire. - * acpi_leave_sleep_state will reenable specific GPEs later + * Disable all GPE and clear their status bits before interrupts are + * enabled. Some GPEs (like wakeup GPEs) have no handlers and this can + * prevent them from producing spurious interrups. + * + * acpi_leave_sleep_state() will reenable specific GPEs later. + * + * Because this code runs on one CPU with disabled interrupts (all of + * the other CPUs are offline at this time), it need not acquire any + * sleeping locks which may trigger an implicit preemption point even + * if there is no contention, so avoid doing that by using a low-level + * library routine here. */ - acpi_disable_all_gpes(); + acpi_hw_disable_all_gpes(); /* Allow EC transactions to happen. */ acpi_ec_unblock_transactions();

--- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -751,6 +751,7 @@ ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_sta acpi_event_status *event_status)) ACPI_HW_DEPENDENT_RETURN_UINT32(u32 acpi_dispatch_gpe(acpi_handle gpe_device, u32 gpe_number)) +ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_hw_disable_all_gpes(void)) ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_disable_all_gpes(void)) ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_runtime_gpes(void)) ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_wakeup_gpes(void))

From: Dexuan Cui decui@microsoft.com

commit ec97e112985c2581ee61854a4b74f080f6cdfc2c upstream.

Commit 572086325ce9 ("Drivers: hv: vmbus: Cleanup synic memory free path") says "Any memory allocations that succeeded will be freed when the caller cleans up by calling hv_synic_free()", but if the get_zeroed_page() in hv_synic_alloc() fails, currently hv_synic_free() is not really called in vmbus_bus_init(), consequently there will be a memory leak, e.g. hv_context.hv_numa_map is not freed in the error path. Fix this by updating the goto labels.

Cc: stable@kernel.org Signed-off-by: Dexuan Cui decui@microsoft.com Fixes: 4df4cb9e99f8 ("x86/hyperv: Initialize clockevents earlier in CPU onlining") Reviewed-by: Michael Kelley mikelley@microsoft.com Link: https://lore.kernel.org/r/20230504224155.10484-1-decui@microsoft.com Signed-off-by: Wei Liu wei.liu@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/hv/vmbus_drv.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)

--- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -1504,7 +1504,7 @@ static int vmbus_bus_init(void) ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "hyperv/vmbus:online", hv_synic_init, hv_synic_cleanup); if (ret < 0) - goto err_cpuhp; + goto err_alloc; hyperv_cpuhp_online = ret;

ret = vmbus_connect(); @@ -1555,9 +1555,8 @@ static int vmbus_bus_init(void)

err_connect: cpuhp_remove_state(hyperv_cpuhp_online); -err_cpuhp: - hv_synic_free(); err_alloc: + hv_synic_free(); if (vmbus_irq == -1) { hv_remove_vmbus_handler(); } else {

From: Dexuan Cui decui@microsoft.com

commit 440b5e3663271b0ffbd4908115044a6a51fb938b upstream.

Since day 1 of the driver, there has been a race between hv_pci_query_relations() and survey_child_resources(): during fast device hotplug, hv_pci_query_relations() may error out due to device-remove and the stack variable 'comp' is no longer valid; however, pci_devices_present_work() -> survey_child_resources() -> complete() may be running on another CPU and accessing the no-longer-valid 'comp'. Fix the race by flushing the workqueue before we exit from hv_pci_query_relations().

Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Signed-off-by: Dexuan Cui decui@microsoft.com Reviewed-by: Michael Kelley mikelley@microsoft.com Acked-by: Lorenzo Pieralisi lpieralisi@kernel.org Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-2-decui@microsoft.com Signed-off-by: Wei Liu wei.liu@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/pci/controller/pci-hyperv.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+)

--- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -3321,6 +3321,24 @@ static int hv_pci_query_relations(struct if (!ret) ret = wait_for_response(hdev, &comp);

+ /* + * In the case of fast device addition/removal, it's possible that + * vmbus_sendpacket() or wait_for_response() returns -ENODEV but we + * already got a PCI_BUS_RELATIONS* message from the host and the + * channel callback already scheduled a work to hbus->wq, which can be + * running pci_devices_present_work() -> survey_child_resources() -> + * complete(&hbus->survey_event), even after hv_pci_query_relations() + * exits and the stack variable 'comp' is no longer valid; as a result, + * a hang or a page fault may happen when the complete() calls + * raw_spin_lock_irqsave(). Flush hbus->wq before we exit from + * hv_pci_query_relations() to avoid the issues. Note: if 'ret' is + * -ENODEV, there can't be any more work item scheduled to hbus->wq + * after the flush_workqueue(): see vmbus_onoffer_rescind() -> + * vmbus_reset_channel_cb(), vmbus_rescind_cleanup() -> + * channel->rescind = true. + */ + flush_workqueue(hbus->wq); + return ret; }

From: Dexuan Cui decui@microsoft.com

commit add9195e69c94b32e96f78c2f9cea68f0e850b3f upstream.

The hpdev->state is never really useful. The only use in hv_pci_eject_device() and hv_eject_device_work() is not really necessary.

Signed-off-by: Dexuan Cui decui@microsoft.com Reviewed-by: Michael Kelley mikelley@microsoft.com Acked-by: Lorenzo Pieralisi lpieralisi@kernel.org Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-4-decui@microsoft.com Signed-off-by: Wei Liu wei.liu@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/pci/controller/pci-hyperv.c | 12 ------------ 1 file changed, 12 deletions(-)

--- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -553,19 +553,10 @@ struct hv_dr_state { struct hv_pcidev_description func[]; };

-enum hv_pcichild_state { - hv_pcichild_init = 0, - hv_pcichild_requirements, - hv_pcichild_resourced, - hv_pcichild_ejecting, - hv_pcichild_maximum -}; - struct hv_pci_dev { /* List protected by pci_rescan_remove_lock */ struct list_head list_entry; refcount_t refs; - enum hv_pcichild_state state; struct pci_slot *pci_slot; struct hv_pcidev_description desc; bool reported_missing; @@ -2764,8 +2755,6 @@ static void hv_eject_device_work(struct hpdev = container_of(work, struct hv_pci_dev, wrk); hbus = hpdev->hbus;

- WARN_ON(hpdev->state != hv_pcichild_ejecting); - /* * Ejection can come before or after the PCI bus has been set up, so * attempt to find it and tear down the bus state, if it exists. This @@ -2822,7 +2811,6 @@ static void hv_pci_eject_device(struct h return; }

- hpdev->state = hv_pcichild_ejecting; get_pcichild(hpdev); INIT_WORK(&hpdev->wrk, hv_eject_device_work); queue_work(hbus->wq, &hpdev->wrk);

From: Dexuan Cui decui@microsoft.com

commit 067d6ec7ed5b49380688e06c1e5f883a71bef4fe upstream.

In the case of fast device addition/removal, it's possible that hv_eject_device_work() can start to run before create_root_hv_pci_bus() starts to run; as a result, the pci_get_domain_bus_and_slot() in hv_eject_device_work() can return a 'pdev' of NULL, and hv_eject_device_work() can remove the 'hpdev', and immediately send a message PCI_EJECTION_COMPLETE to the host, and the host immediately unassigns the PCI device from the guest; meanwhile, create_root_hv_pci_bus() and the PCI device driver can be probing the dead PCI device and reporting timeout errors.

Fix the issue by adding a per-bus mutex 'state_lock' and grabbing the mutex before powering on the PCI bus in hv_pci_enter_d0(): when hv_eject_device_work() starts to run, it's able to find the 'pdev' and call pci_stop_and_remove_bus_device(pdev): if the PCI device driver has loaded, the PCI device driver's probe() function is already called in create_root_hv_pci_bus() -> pci_bus_add_devices(), and now hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to call the PCI device driver's remove() function and remove the device reliably; if the PCI device driver hasn't loaded yet, the function call hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to remove the PCI device reliably and the PCI device driver's probe() function won't be called; if the PCI device driver's probe() is already running (e.g., systemd-udev is loading the PCI device driver), it must be holding the per-device lock, and after the probe() finishes and releases the lock, hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to proceed to remove the device reliably.

Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Signed-off-by: Dexuan Cui decui@microsoft.com Reviewed-by: Michael Kelley mikelley@microsoft.com Acked-by: Lorenzo Pieralisi lpieralisi@kernel.org Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com Signed-off-by: Wei Liu wei.liu@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/pci/controller/pci-hyperv.c | 29 ++++++++++++++++++++++++++--- 1 file changed, 26 insertions(+), 3 deletions(-)

--- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -489,7 +489,10 @@ struct hv_pcibus_device { struct fwnode_handle *fwnode; /* Protocol version negotiated with the host */ enum pci_protocol_version_t protocol_version; + + struct mutex state_lock; enum hv_pcibus_state state; + struct hv_device *hdev; resource_size_t low_mmio_space; resource_size_t high_mmio_space; @@ -2525,6 +2528,8 @@ static void pci_devices_present_work(str if (!dr) return;

+ mutex_lock(&hbus->state_lock); + /* First, mark all existing children as reported missing. */ spin_lock_irqsave(&hbus->device_list_lock, flags); list_for_each_entry(hpdev, &hbus->children, list_entry) { @@ -2606,6 +2611,8 @@ static void pci_devices_present_work(str break; }

+ mutex_unlock(&hbus->state_lock); + kfree(dr); }

@@ -2754,6 +2761,8 @@ static void hv_eject_device_work(struct hpdev = container_of(work, struct hv_pci_dev, wrk); hbus = hpdev->hbus;

+ mutex_lock(&hbus->state_lock); + /* * Ejection can come before or after the PCI bus has been set up, so * attempt to find it and tear down the bus state, if it exists. This @@ -2790,6 +2799,8 @@ static void hv_eject_device_work(struct put_pcichild(hpdev); put_pcichild(hpdev); /* hpdev has been freed. Do not use it any more. */ + + mutex_unlock(&hbus->state_lock); }

/** @@ -3580,6 +3591,7 @@ static int hv_pci_probe(struct hv_device return -ENOMEM;

hbus->bridge = bridge; + mutex_init(&hbus->state_lock); hbus->state = hv_pcibus_init; hbus->wslot_res_allocated = -1;

@@ -3688,9 +3700,11 @@ static int hv_pci_probe(struct hv_device if (ret) goto free_irq_domain;

+ mutex_lock(&hbus->state_lock); + ret = hv_pci_enter_d0(hdev); if (ret) - goto free_irq_domain; + goto release_state_lock;

ret = hv_pci_allocate_bridge_windows(hbus); if (ret) @@ -3708,12 +3722,15 @@ static int hv_pci_probe(struct hv_device if (ret) goto free_windows;

+ mutex_unlock(&hbus->state_lock); return 0;

free_windows: hv_pci_free_bridge_windows(hbus); exit_d0: (void) hv_pci_bus_exit(hdev, true); +release_state_lock: + mutex_unlock(&hbus->state_lock); free_irq_domain: irq_domain_remove(hbus->irq_domain); free_fwnode: @@ -3967,20 +3984,26 @@ static int hv_pci_resume(struct hv_devic if (ret) goto out;

+ mutex_lock(&hbus->state_lock); + ret = hv_pci_enter_d0(hdev); if (ret) - goto out; + goto release_state_lock;

ret = hv_send_resources_allocated(hdev); if (ret) - goto out; + goto release_state_lock;

prepopulate_bars(hbus);

hv_pci_restore_msi_state(hbus);

hbus->state = hv_pcibus_installed; + mutex_unlock(&hbus->state_lock); return 0; + +release_state_lock: + mutex_unlock(&hbus->state_lock); out: vmbus_close(hdev->channel); return ret;

From: Jens Axboe axboe@kernel.dk

commit 78d0d2063bab954d19a1696feae4c7706a626d48 upstream.

We cannot sanely handle partial retries for recvmsg if we have cmsg attached. If we don't, then we'd just be overwriting the initial cmsg header on retries. Alternatively we could increment and handle this appropriately, but it doesn't seem worth the complication.

Move the MSG_WAITALL check into the non-multishot case while at it, since MSG_WAITALL is explicitly disabled for multishot anyway.

Link: https://lore.kernel.org/io-uring/0b0d4411-c8fd-4272-770b-e030af6919a0@kernel... Cc: stable@vger.kernel.org # 5.10+ Reported-by: Stefan Metzmacher metze@samba.org Reviewed-by: Stefan Metzmacher metze@samba.org Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- io_uring/net.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-)

--- a/io_uring/net.c +++ b/io_uring/net.c @@ -781,16 +781,19 @@ retry_multishot: flags = sr->msg_flags; if (force_nonblock) flags |= MSG_DONTWAIT; - if (flags & MSG_WAITALL) - min_ret = iov_iter_count(&kmsg->msg.msg_iter);

kmsg->msg.msg_get_inq = 1; - if (req->flags & REQ_F_APOLL_MULTISHOT) + if (req->flags & REQ_F_APOLL_MULTISHOT) { ret = io_recvmsg_multishot(sock, sr, kmsg, flags, &mshot_finished); - else + } else { + /* disable partial retry for recvmsg with cmsg attached */ + if (flags & MSG_WAITALL && !kmsg->msg.msg_controllen) + min_ret = iov_iter_count(&kmsg->msg.msg_iter); + ret = __sys_recvmsg_sock(sock, &kmsg->msg, sr->umsg, kmsg->uaddr, flags); + }

if (ret < min_ret) { if (ret == -EAGAIN && force_nonblock) {

From: Paolo Abeni pabeni@redhat.com

commit 0ad529d9fd2bfa3fc619552a8d2fb2f2ef0bce2e upstream.

Christoph reported a divide by zero bug in mptcp_recvmsg():

divide error: 0000 [#1] PREEMPT SMP CPU: 1 PID: 19978 Comm: syz-executor.6 Not tainted 6.4.0-rc2-gffcc7899081b #20 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.el7 04/01/2014 RIP: 0010:__tcp_select_window+0x30e/0x420 net/ipv4/tcp_output.c:3018 Code: 11 ff 0f b7 cd c1 e9 0c b8 ff ff ff ff d3 e0 89 c1 f7 d1 01 cb 21 c3 eb 17 e8 2e 83 11 ff 31 db eb 0e e8 25 83 11 ff 89 d8 99 <f7> 7c 24 04 29 d3 65 48 8b 04 25 28 00 00 00 48 3b 44 24 10 75 60 RSP: 0018:ffffc90000a07a18 EFLAGS: 00010246 RAX: 000000000000ffd7 RBX: 000000000000ffd7 RCX: 0000000000040000 RDX: 0000000000000000 RSI: 000000000003ffff RDI: 0000000000040000 RBP: 000000000000ffd7 R08: ffffffff820cf297 R09: 0000000000000001 R10: 0000000000000000 R11: ffffffff8103d1a0 R12: 0000000000003f00 R13: 0000000000300000 R14: ffff888101cf3540 R15: 0000000000180000 FS: 00007f9af4c09640(0000) GS:ffff88813bd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000001b33824000 CR3: 000000012f241001 CR4: 0000000000170ee0 Call Trace: <TASK> __tcp_cleanup_rbuf+0x138/0x1d0 net/ipv4/tcp.c:1611 mptcp_recvmsg+0xcb8/0xdd0 net/mptcp/protocol.c:2034 inet_recvmsg+0x127/0x1f0 net/ipv4/af_inet.c:861 ____sys_recvmsg+0x269/0x2b0 net/socket.c:1019 ___sys_recvmsg+0xe6/0x260 net/socket.c:2764 do_recvmmsg+0x1a5/0x470 net/socket.c:2858 __do_sys_recvmmsg net/socket.c:2937 [inline] __se_sys_recvmmsg net/socket.c:2953 [inline] __x64_sys_recvmmsg+0xa6/0x130 net/socket.c:2953 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x47/0xa0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc RIP: 0033:0x7f9af58fc6a9 Code: 5c c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 4f 37 0d 00 f7 d8 64 89 01 48 RSP: 002b:00007f9af4c08cd8 EFLAGS: 00000246 ORIG_RAX: 000000000000012b RAX: ffffffffffffffda RBX: 00000000006bc050 RCX: 00007f9af58fc6a9 RDX: 0000000000000001 RSI: 0000000020000140 RDI: 0000000000000004 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000f00 R11: 0000000000000246 R12: 00000000006bc05c R13: fffffffffffffea8 R14: 00000000006bc050 R15: 000000000001fe40 </TASK>

mptcp_recvmsg is allowed to release the msk socket lock when blocking, and before re-acquiring it another thread could have switched the sock to TCP_LISTEN status - with a prior connect(AF_UNSPEC) - also clearing icsk_ack.rcv_mss.

Address the issue preventing the disconnect if some other process is concurrently performing a blocking syscall on the same socket, alike commit 4faeee0cf8a5 ("tcp: deny tcp_disconnect() when threads are waiting").

Fixes: a6b118febbab ("mptcp: add receive buffer auto-tuning") Cc: stable@vger.kernel.org Reported-by: Christoph Paasch cpaasch@apple.com Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/404 Signed-off-by: Paolo Abeni pabeni@redhat.com Tested-by: Christoph Paasch cpaasch@apple.com Reviewed-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/mptcp/protocol.c | 7 +++++++ 1 file changed, 7 insertions(+)

--- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3060,6 +3060,12 @@ static int mptcp_disconnect(struct sock { struct mptcp_sock *msk = mptcp_sk(sk);

+ /* Deny disconnect if other threads are blocked in sk_wait_event() + * or inet_wait_for_connect(). + */ + if (sk->sk_wait_pending) + return -EBUSY; + /* We are on the fastopen error path. We can't call straight into the * subflows cleanup code due to lock nesting (we are already under * msk->firstsocket lock). @@ -3126,6 +3132,7 @@ struct sock *mptcp_sk_clone_init(const s inet_sk(nsk)->pinet6 = mptcp_inet6_sk(nsk); #endif

+ nsk->sk_wait_pending = 0; __mptcp_init_sock(nsk);

msk = mptcp_sk(nsk);

From: Paolo Abeni pabeni@redhat.com

commit 81c1d029016001f994ce1c46849c5e9900d8eab8 upstream.

An orphaned msk releases the used resources via the worker, when the latter first see the msk in CLOSED status.

If the msk status transitions to TCP_CLOSE in the release callback invoked by the worker's final release_sock(), such instance of the workqueue will not take any action.

Additionally the MPTCP code prevents scheduling the worker once the socket reaches the CLOSE status: such msk resources will be leaked.

The only code path that can trigger the above scenario is the __mptcp_check_send_data_fin() in fallback mode.

Address the issue removing the special handling of fallback socket in __mptcp_check_send_data_fin(), consolidating the state machine for fallback and non fallback socket.

Since non-fallback sockets do not send and do not receive data_fin, the mptcp code can update the msk internal status to match the next step in the SM every time data fin (ack) should be generated or received.

As a consequence we can remove a bunch of checks for fallback from the fastpath.

Fixes: 6e628cd3a8f7 ("mptcp: use mptcp release_cb for delayed tasks") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni pabeni@redhat.com Reviewed-by: Mat Martineau martineau@kernel.org Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/mptcp/protocol.c | 41 +++++++++++++++-------------------------- net/mptcp/subflow.c | 17 ++++++++++------- 2 files changed, 25 insertions(+), 33 deletions(-)

--- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -53,7 +53,7 @@ enum { static struct percpu_counter mptcp_sockets_allocated ____cacheline_aligned_in_smp;

static void __mptcp_destroy_sock(struct sock *sk); -static void __mptcp_check_send_data_fin(struct sock *sk); +static void mptcp_check_send_data_fin(struct sock *sk);

DEFINE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions); static struct net_device mptcp_napi_dev; @@ -420,8 +420,7 @@ static bool mptcp_pending_data_fin_ack(s { struct mptcp_sock *msk = mptcp_sk(sk);

- return !__mptcp_check_fallback(msk) && - ((1 << sk->sk_state) & + return ((1 << sk->sk_state) & (TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK)) && msk->write_seq == READ_ONCE(msk->snd_una); } @@ -579,9 +578,6 @@ static bool mptcp_check_data_fin(struct u64 rcv_data_fin_seq; bool ret = false;

- if (__mptcp_check_fallback(msk)) - return ret; - /* Need to ack a DATA_FIN received from a peer while this side * of the connection is in ESTABLISHED, FIN_WAIT1, or FIN_WAIT2. * msk->rcv_data_fin was set when parsing the incoming options @@ -619,7 +615,8 @@ static bool mptcp_check_data_fin(struct }

ret = true; - mptcp_send_ack(msk); + if (!__mptcp_check_fallback(msk)) + mptcp_send_ack(msk); mptcp_close_wake_up(sk); } return ret; @@ -1606,7 +1603,7 @@ out: if (!mptcp_timer_pending(sk)) mptcp_reset_timer(sk); if (do_check_data_fin) - __mptcp_check_send_data_fin(sk); + mptcp_check_send_data_fin(sk); }

static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk) @@ -2665,8 +2662,6 @@ static void mptcp_worker(struct work_str if (unlikely((1 << state) & (TCPF_CLOSE | TCPF_LISTEN))) goto unlock;

- mptcp_check_data_fin_ack(sk); - mptcp_check_fastclose(msk);

mptcp_pm_nl_work(msk); @@ -2674,7 +2669,8 @@ static void mptcp_worker(struct work_str if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags)) mptcp_check_for_eof(msk);

- __mptcp_check_send_data_fin(sk); + mptcp_check_send_data_fin(sk); + mptcp_check_data_fin_ack(sk); mptcp_check_data_fin(sk);

if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) @@ -2815,6 +2811,12 @@ void mptcp_subflow_shutdown(struct sock pr_debug("Fallback"); ssk->sk_shutdown |= how; tcp_shutdown(ssk, how); + + /* simulate the data_fin ack reception to let the state + * machine move forward + */ + WRITE_ONCE(mptcp_sk(sk)->snd_una, mptcp_sk(sk)->snd_nxt); + mptcp_schedule_work(sk); } else { pr_debug("Sending DATA_FIN on subflow %p", ssk); tcp_send_ack(ssk); @@ -2854,7 +2856,7 @@ static int mptcp_close_state(struct sock return next & TCP_ACTION_FIN; }

-static void __mptcp_check_send_data_fin(struct sock *sk) +static void mptcp_check_send_data_fin(struct sock *sk) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); @@ -2872,19 +2874,6 @@ static void __mptcp_check_send_data_fin(

WRITE_ONCE(msk->snd_nxt, msk->write_seq);

- /* fallback socket will not get data_fin/ack, can move to the next - * state now - */ - if (__mptcp_check_fallback(msk)) { - WRITE_ONCE(msk->snd_una, msk->write_seq); - if ((1 << sk->sk_state) & (TCPF_CLOSING | TCPF_LAST_ACK)) { - inet_sk_state_store(sk, TCP_CLOSE); - mptcp_close_wake_up(sk); - } else if (sk->sk_state == TCP_FIN_WAIT1) { - inet_sk_state_store(sk, TCP_FIN_WAIT2); - } - } - mptcp_for_each_subflow(msk, subflow) { struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);

@@ -2904,7 +2893,7 @@ static void __mptcp_wr_shutdown(struct s WRITE_ONCE(msk->write_seq, msk->write_seq + 1); WRITE_ONCE(msk->snd_data_fin_enable, 1);

- __mptcp_check_send_data_fin(sk); + mptcp_check_send_data_fin(sk); }

static void __mptcp_destroy_sock(struct sock *sk) --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1688,14 +1688,16 @@ static void subflow_state_change(struct { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct sock *parent = subflow->conn; + struct mptcp_sock *msk;

__subflow_state_change(sk);

+ msk = mptcp_sk(parent); if (subflow_simultaneous_connect(sk)) { mptcp_propagate_sndbuf(parent, sk); mptcp_do_fallback(sk); - mptcp_rcv_space_init(mptcp_sk(parent), sk); - pr_fallback(mptcp_sk(parent)); + mptcp_rcv_space_init(msk, sk); + pr_fallback(msk); subflow->conn_finished = 1; mptcp_set_connected(parent); } @@ -1711,11 +1713,12 @@ static void subflow_state_change(struct

subflow_sched_work_if_closed(mptcp_sk(parent), sk);

- if (__mptcp_check_fallback(mptcp_sk(parent)) && - !subflow->rx_eof && subflow_is_done(sk)) { - subflow->rx_eof = 1; - mptcp_subflow_eof(parent); - } + /* when the fallback subflow closes the rx side, trigger a 'dummy' + * ingress data fin, so that the msk state will follow along + */ + if (__mptcp_check_fallback(msk) && subflow_is_done(sk) && msk->first == sk && + mptcp_update_rcv_data_fin(msk, READ_ONCE(msk->ack_seq), true)) + mptcp_schedule_work(parent); }

void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk)

From: Tetsuo Handa penguin-kernel@I-love.SAKURA.ne.jp

commit f0cc749254d12c78e93dae3b27b21dc9546843d0 upstream.

syzbot is again reporting circular locking dependency between cpu_hotplug_lock and freezer_mutex. Do like what we did with commit 57dcd64c7e036299 ("cgroup,freezer: hold cpu_hotplug_lock before freezer_mutex").

Reported-by: syzbot syzbot+2ab700fe1829880a2ec6@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=2ab700fe1829880a2ec6 Signed-off-by: Tetsuo Handa penguin-kernel@I-love.SAKURA.ne.jp Tested-by: syzbot syzbot+2ab700fe1829880a2ec6@syzkaller.appspotmail.com Fixes: f5d39b020809 ("freezer,sched: Rewrite core freezer logic") Cc: stable@vger.kernel.org # v6.1+ Signed-off-by: Tejun Heo tj@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/cgroup/legacy_freezer.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

--- a/kernel/cgroup/legacy_freezer.c +++ b/kernel/cgroup/legacy_freezer.c @@ -108,16 +108,18 @@ static int freezer_css_online(struct cgr struct freezer *freezer = css_freezer(css); struct freezer *parent = parent_freezer(freezer);

+ cpus_read_lock(); mutex_lock(&freezer_mutex);

freezer->state |= CGROUP_FREEZER_ONLINE;

if (parent && (parent->state & CGROUP_FREEZING)) { freezer->state |= CGROUP_FREEZING_PARENT | CGROUP_FROZEN; - static_branch_inc(&freezer_active); + static_branch_inc_cpuslocked(&freezer_active); }

mutex_unlock(&freezer_mutex); + cpus_read_unlock(); return 0; }

@@ -132,14 +134,16 @@ static void freezer_css_offline(struct c { struct freezer *freezer = css_freezer(css);

+ cpus_read_lock(); mutex_lock(&freezer_mutex);

if (freezer->state & CGROUP_FREEZING) - static_branch_dec(&freezer_active); + static_branch_dec_cpuslocked(&freezer_active);

freezer->state = 0;

mutex_unlock(&freezer_mutex); + cpus_read_unlock(); }

static void freezer_css_free(struct cgroup_subsys_state *css)

From: Stephan Gerhold stephan@gerhold.net

commit e6f9e590b72e12bbb86b1b8be7e1981f357392ad upstream.

While SDHCI claims to support 64-bit DMA on MSM8916 it does not seem to be properly functional. It is not immediately obvious because SDHCI is usually used with IOMMU bypassed on this SoC, and all physical memory has 32-bit addresses. But when trying to enable the IOMMU it quickly fails with an error such as the following:

arm-smmu 1e00000.iommu: Unhandled context fault: fsr=0x402, iova=0xfffff200, fsynr=0xe0000, cbfrsynra=0x140, cb=3 mmc1: ADMA error: 0x02000000 mmc1: sdhci: ============ SDHCI REGISTER DUMP =========== mmc1: sdhci: Sys addr: 0x00000000 | Version: 0x00002e02 mmc1: sdhci: Blk size: 0x00000008 | Blk cnt: 0x00000000 mmc1: sdhci: Argument: 0x00000000 | Trn mode: 0x00000013 mmc1: sdhci: Present: 0x03f80206 | Host ctl: 0x00000019 mmc1: sdhci: Power: 0x0000000f | Blk gap: 0x00000000 mmc1: sdhci: Wake-up: 0x00000000 | Clock: 0x00000007 mmc1: sdhci: Timeout: 0x0000000a | Int stat: 0x00000001 mmc1: sdhci: Int enab: 0x03ff900b | Sig enab: 0x03ff100b mmc1: sdhci: ACmd stat: 0x00000000 | Slot int: 0x00000000 mmc1: sdhci: Caps: 0x322dc8b2 | Caps_1: 0x00008007 mmc1: sdhci: Cmd: 0x0000333a | Max curr: 0x00000000 mmc1: sdhci: Resp[0]: 0x00000920 | Resp[1]: 0x5b590000 mmc1: sdhci: Resp[2]: 0xe6487f80 | Resp[3]: 0x0a404094 mmc1: sdhci: Host ctl2: 0x00000008 mmc1: sdhci: ADMA Err: 0x00000001 | ADMA Ptr: 0x0000000ffffff224 mmc1: sdhci_msm: ----------- VENDOR REGISTER DUMP ----------- mmc1: sdhci_msm: DLL sts: 0x00000000 | DLL cfg: 0x60006400 | DLL cfg2: 0x00000000 mmc1: sdhci_msm: DLL cfg3: 0x00000000 | DLL usr ctl: 0x00000000 | DDR cfg: 0x00000000 mmc1: sdhci_msm: Vndr func: 0x00018a9c | Vndr func2 : 0xf88018a8 Vndr func3: 0x00000000 mmc1: sdhci: ============================================ mmc1: sdhci: fffffffff200: DMA 0x0000ffffffffe100, LEN 0x0008, Attr=0x21 mmc1: sdhci: fffffffff20c: DMA 0x0000000000000000, LEN 0x0000, Attr=0x03

Looking closely it's obvious that only the 32-bit part of the address (0xfffff200) arrives at the SMMU, the higher 16-bit (0xffff...) get lost somewhere. This might not be a limitation of the SDHCI itself but perhaps the bus/interconnect it is connected to, or even the connection to the SMMU.

Work around this by setting SDHCI_QUIRK2_BROKEN_64_BIT_DMA to avoid using 64-bit addresses.

Signed-off-by: Stephan Gerhold stephan@gerhold.net Acked-by: Adrian Hunter adrian.hunter@intel.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230518-msm8916-64bit-v1-1-5694b0f35211@gerhold.n... Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/mmc/host/sdhci-msm.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -2486,6 +2486,9 @@ static inline void sdhci_msm_get_of_prop msm_host->ddr_config = DDR_CONFIG_POR_VAL;

of_property_read_u32(node, "qcom,dll-config", &msm_host->dll_config); + + if (of_device_is_compatible(node, "qcom,msm8916-sdhci")) + host->quirks2 |= SDHCI_QUIRK2_BROKEN_64_BIT_DMA; }

static int sdhci_msm_gcc_reset(struct device *dev, struct sdhci_host *host)

From: Christophe Kerello christophe.kerello@foss.st.com

commit 47b3ad6b7842f49d374a01b054a4b1461a621bdc upstream.

The way that the timeout is currently calculated could lead to a u64 timeout value in mmci_start_command(). This value is then cast in a u32 register that leads to mmc erase failed issue with some SD cards.

Fixes: 8266c585f489 ("mmc: mmci: add hardware busy timeout feature") Signed-off-by: Yann Gautier yann.gautier@foss.st.com Signed-off-by: Christophe Kerello christophe.kerello@foss.st.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230613134146.418016-1-yann.gautier@foss.st.com Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/mmc/host/mmci.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/mmc/host/mmci.c +++ b/drivers/mmc/host/mmci.c @@ -1735,7 +1735,8 @@ static void mmci_set_max_busy_timeout(st return;

if (host->variant->busy_timeout && mmc->actual_clock) - max_busy_timeout = ~0UL / (mmc->actual_clock / MSEC_PER_SEC); + max_busy_timeout = U32_MAX / DIV_ROUND_UP(mmc->actual_clock, + MSEC_PER_SEC);

mmc->max_busy_timeout = max_busy_timeout; }

From: Sergey Shtylyov s.shtylyov@omp.ru

commit 71150ac12558bcd9d75e6e24cf7c872c2efd80f3 upstream.

The driver overrides the error codes and IRQ0 returned by platform_get_irq() to -EINVAL, so if it returns -EPROBE_DEFER, the driver will fail the probe permanently instead of the deferred probing. Switch to propagating the error codes upstream. Since commit ce753ad1549c ("platform: finally disallow IRQ0 in platform_get_irq() and its ilk") IRQ0 is no longer returned by those APIs, so we now can safely ignore it...

Fixes: 660fc733bd74 ("mmc: bcm2835: Add new driver for the sdhost controller.") Cc: stable@vger.kernel.org # v5.19+ Signed-off-by: Sergey Shtylyov s.shtylyov@omp.ru Link: https://lore.kernel.org/r/20230617203622.6812-2-s.shtylyov@omp.ru Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/mmc/host/bcm2835.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/mmc/host/bcm2835.c +++ b/drivers/mmc/host/bcm2835.c @@ -1411,8 +1411,8 @@ static int bcm2835_probe(struct platform host->max_clk = clk_get_rate(clk);

host->irq = platform_get_irq(pdev, 0); - if (host->irq <= 0) { - ret = -EINVAL; + if (host->irq < 0) { + ret = host->irq; goto err; }

From: Krister Johansen kjlx@templeofstupid.com

commit 0108a4e9f3584a7a2c026d1601b0682ff7335d95 upstream.

When subprograms are in use, the main program is not jit'd after the subprograms because jit_subprogs sets a value for prog->bpf_func upon success. Subsequent calls to the JIT are bypassed when this value is non-NULL. This leads to a situation where the main program and its func[0] counterpart are both in the bpf kallsyms tree, but only func[0] has an extable. Extables are only created during JIT. Now there are two nearly identical program ksym entries in the tree, but only one has an extable. Depending upon how the entries are placed, there's a chance that a fault will call search_extable on the aux with the NULL entry.

Since jit_subprogs already copies state from func[0] to the main program, include the extable pointer in this state duplication. Additionally, ensure that the copy of the main program in func[0] is not added to the bpf_prog_kallsyms table. Instead, let the main program get added later in bpf_prog_load(). This ensures there is only a single copy of the main program in the kallsyms table, and that its tag matches the tag observed by tooling like bpftool.

Cc: stable@vger.kernel.org Fixes: 1c2a088a6626 ("bpf: x64: add JIT support for multi-function programs") Signed-off-by: Krister Johansen kjlx@templeofstupid.com Acked-by: Yonghong Song yhs@fb.com Acked-by: Ilya Leoshkevich iii@linux.ibm.com Tested-by: Ilya Leoshkevich iii@linux.ibm.com Link: https://lore.kernel.org/r/6de9b2f4b4724ef56efbb0339daaa66c8b68b1e7.168661666... Signed-off-by: Alexei Starovoitov ast@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/bpf/verifier.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

--- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -13819,9 +13819,10 @@ static int jit_subprogs(struct bpf_verif }

/* finally lock prog and jit images for all functions and - * populate kallsysm + * populate kallsysm. Begin at the first subprogram, since + * bpf_prog_load will add the kallsyms for the main program. */ - for (i = 0; i < env->subprog_cnt; i++) { + for (i = 1; i < env->subprog_cnt; i++) { bpf_prog_lock_ro(func[i]); bpf_prog_kallsyms_add(func[i]); } @@ -13847,6 +13848,8 @@ static int jit_subprogs(struct bpf_verif prog->jited = 1; prog->bpf_func = func[0]->bpf_func; prog->jited_len = func[0]->jited_len; + prog->aux->extable = func[0]->aux->extable; + prog->aux->num_exentries = func[0]->aux->num_exentries; prog->aux->func = func; prog->aux->func_cnt = env->subprog_cnt; bpf_prog_jit_attempt_done(prog);

From: Neil Armstrong neil.armstrong@linaro.org

[ Upstream commit 9d7054fb3ac2e8d252aae1268f20623f244e644f ]

Now spi_geni_grab_gpi_chan() errors are correctly reported, the -EPROBE_DEFER error should be returned from probe in case the GPI dma driver is built as module and/or not probed yet.

Fixes: b59c122484ec ("spi: spi-geni-qcom: Add support for GPI dma") Fixes: 6532582c353f ("spi: spi-geni-qcom: fix error handling in spi_geni_grab_gpi_chan()") Signed-off-by: Neil Armstrong neil.armstrong@linaro.org Link: https://lore.kernel.org/r/20230615-topic-sm8550-upstream-fix-spi-geni-qcom-p... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/spi/spi-geni-qcom.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/spi/spi-geni-qcom.c b/drivers/spi/spi-geni-qcom.c index 4e83cc5b445d8..dd1581893fe72 100644 --- a/drivers/spi/spi-geni-qcom.c +++ b/drivers/spi/spi-geni-qcom.c @@ -595,6 +595,8 @@ static int spi_geni_init(struct spi_geni_master *mas) geni_se_select_mode(se, GENI_GPI_DMA); dev_dbg(mas->dev, "Using GPI DMA mode for SPI\n"); break; + } else if (ret == -EPROBE_DEFER) { + goto out_pm; } /* * in case of failure to get dma channel, we can still do the

From: Russ Weight russell.h.weight@intel.com

[ Upstream commit c8e796895e2310b6130e7577248da1d771431a77 ]

The max_raw_write member of the regmap_spi_avmm_bus structure is defined as: .max_raw_write = SPI_AVMM_VAL_SIZE * MAX_WRITE_CNT

SPI_AVMM_VAL_SIZE == 4 and MAX_WRITE_CNT == 1 so this results in a maximum write transfer size of 4 bytes which provides only enough space to transfer the address of the target register. It provides no space for the value to be transferred. This bug became an issue (divide-by-zero in _regmap_raw_write()) after the following was accepted into mainline:

commit 3981514180c9 ("regmap: Account for register length when chunking")

Change max_raw_write to include space (4 additional bytes) for both the register address and value:

.max_raw_write = SPI_AVMM_REG_SIZE + SPI_AVMM_VAL_SIZE * MAX_WRITE_CNT

Fixes: 7f9fb67358a2 ("regmap: add Intel SPI Slave to AVMM Bus Bridge support") Reviewed-by: Matthew Gerlach matthew.gerlach@linux.intel.com Signed-off-by: Russ Weight russell.h.weight@intel.com Link: https://lore.kernel.org/r/20230620202824.380313-1-russell.h.weight@intel.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/base/regmap/regmap-spi-avmm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/base/regmap/regmap-spi-avmm.c b/drivers/base/regmap/regmap-spi-avmm.c index 4c2b94b3e30be..6af692844c196 100644 --- a/drivers/base/regmap/regmap-spi-avmm.c +++ b/drivers/base/regmap/regmap-spi-avmm.c @@ -660,7 +660,7 @@ static const struct regmap_bus regmap_spi_avmm_bus = { .reg_format_endian_default = REGMAP_ENDIAN_NATIVE, .val_format_endian_default = REGMAP_ENDIAN_NATIVE, .max_raw_read = SPI_AVMM_VAL_SIZE * MAX_READ_CNT, - .max_raw_write = SPI_AVMM_VAL_SIZE * MAX_WRITE_CNT, + .max_raw_write = SPI_AVMM_REG_SIZE + SPI_AVMM_VAL_SIZE * MAX_WRITE_CNT, .free_context = spi_avmm_bridge_ctx_free, };

From: Jens Axboe axboe@kernel.dk

Commit ef7dfac51d8ed961b742218f526bd589f3900a59 upstream.

We selectively grab the ctx->uring_lock for poll update/removal, but we really should grab it from the start to fully synchronize with linked timeouts. Normally this is indeed the case, but if requests are forced async by the application, we don't fully cover removal and timer disarm within the uring_lock.

Make this simpler by having consistent locking state for poll removal.

Cc: stable@vger.kernel.org # 6.1+ Reported-by: Querijn Voet querijnqyn@gmail.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- io_uring/poll.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-)

--- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -993,8 +993,9 @@ int io_poll_remove(struct io_kiocb *req, struct io_hash_bucket *bucket; struct io_kiocb *preq; int ret2, ret = 0; - bool locked; + bool locked = true;

+ io_ring_submit_lock(ctx, issue_flags); preq = io_poll_find(ctx, true, &cd, &ctx->cancel_table, &bucket); ret2 = io_poll_disarm(preq); if (bucket) @@ -1006,12 +1007,10 @@ int io_poll_remove(struct io_kiocb *req, goto out; }

- io_ring_submit_lock(ctx, issue_flags); preq = io_poll_find(ctx, true, &cd, &ctx->cancel_table_locked, &bucket); ret2 = io_poll_disarm(preq); if (bucket) spin_unlock(&bucket->lock); - io_ring_submit_unlock(ctx, issue_flags); if (ret2) { ret = ret2; goto out; @@ -1035,7 +1034,7 @@ found: if (poll_update->update_user_data) preq->cqe.user_data = poll_update->new_user_data;

- ret2 = io_poll_add(preq, issue_flags); + ret2 = io_poll_add(preq, issue_flags & ~IO_URING_F_UNLOCKED); /* successfully updated, don't complete poll request */ if (!ret2 || ret2 == -EIOCBQUEUED) goto out; @@ -1043,9 +1042,9 @@ found:

req_set_fail(preq); io_req_set_res(preq, -ECANCELED, 0); - locked = !(issue_flags & IO_URING_F_UNLOCKED); io_req_task_complete(preq, &locked); out: + io_ring_submit_unlock(ctx, issue_flags); if (ret < 0) { req_set_fail(req); return ret;

From: Lee Jones lee@kernel.org

commit d082d48737c75d2b3cc1f972b8c8674c25131534 upstream.

KPTI keeps around two PGDs: one for userspace and another for the kernel. Among other things, set_pgd() contains infrastructure to ensure that updates to the kernel PGD are reflected in the user PGD as well.

One side-effect of this is that set_pgd() expects to be passed whole pages. Unfortunately, init_trampoline_kaslr() passes in a single entry: 'trampoline_pgd_entry'.

When KPTI is on, set_pgd() will update 'trampoline_pgd_entry' (an 8-Byte globally stored [.bss] variable) and will then proceed to replicate that value into the non-existent neighboring user page (located +4k away), leading to the corruption of other global [.bss] stored variables.

Fix it by directly assigning 'trampoline_pgd_entry' and avoiding set_pgd().

[ dhansen: tweak subject and changelog ]

Fixes: 0925dda5962e ("x86/mm/KASLR: Use only one PUD entry for real mode trampoline") Suggested-by: Dave Hansen dave.hansen@linux.intel.com Signed-off-by: Lee Jones lee@kernel.org Signed-off-by: Dave Hansen dave.hansen@linux.intel.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/20230614163859.924309-1-lee@kernel.org/g Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/mm/kaslr.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -172,10 +172,10 @@ void __meminit init_trampoline_kaslr(voi set_p4d(p4d_tramp, __p4d(_KERNPG_TABLE | __pa(pud_page_tramp)));

- set_pgd(&trampoline_pgd_entry, - __pgd(_KERNPG_TABLE | __pa(p4d_page_tramp))); + trampoline_pgd_entry = + __pgd(_KERNPG_TABLE | __pa(p4d_page_tramp)); } else { - set_pgd(&trampoline_pgd_entry, - __pgd(_KERNPG_TABLE | __pa(pud_page_tramp))); + trampoline_pgd_entry = + __pgd(_KERNPG_TABLE | __pa(pud_page_tramp)); } }

From: Sergey Shtylyov s.shtylyov@omp.ru

[ Upstream commit b8ada54fa1b83f3b6480d4cced71354301750153 ]

The driver overrides the error codes and IRQ0 returned by platform_get_irq() to -EINVAL, so if it returns -EPROBE_DEFER, the driver will fail the probe permanently instead of the deferred probing. Switch to propagating the error codes upstream. Since commit ce753ad1549c ("platform: finally disallow IRQ0 in platform_get_irq() and its ilk") IRQ0 is no longer returned by those APIs, so we now can safely ignore it...

Fixes: cbcaac6d7dd2 ("mmc: meson-gx-mmc: Fix platform_get_irq's error checking") Cc: stable@vger.kernel.org # v5.19+ Signed-off-by: Sergey Shtylyov s.shtylyov@omp.ru Reviewed-by: Neil Armstrong neil.armstrong@linaro.org Link: https://lore.kernel.org/r/20230617203622.6812-3-s.shtylyov@omp.ru Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/mmc/host/meson-gx-mmc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c index 5fb18be6f8660..0f39f86bd0c26 100644 --- a/drivers/mmc/host/meson-gx-mmc.c +++ b/drivers/mmc/host/meson-gx-mmc.c @@ -1227,8 +1227,8 @@ static int meson_mmc_probe(struct platform_device *pdev) }

host->irq = platform_get_irq(pdev, 0); - if (host->irq <= 0) { - ret = -EINVAL; + if (host->irq < 0) { + ret = host->irq; goto free_host; }

From: Benedict Wong benedictwong@google.com

[ Upstream commit 1f8b6df6a997a430b0c48b504638154b520781ad ]

This change allows inbound traffic through nested IPsec tunnels to successfully match policies and templates, while retaining the secpath stack trace as necessary for netfilter policies.

Specifically, this patch marks secpath entries that have already matched against a relevant policy as having been verified, allowing it to be treated as optional and skipped after a tunnel decapsulation (during which the src/dst/proto/etc may have changed, and the correct policy chain no long be resolvable).

This approach is taken as opposed to the iteration in b0355dbbf13c, where the secpath was cleared, since that breaks subsequent validations that rely on the existence of the secpath entries (netfilter policies, or transport-in-tunnel mode, where policies remain resolvable).

Fixes: b0355dbbf13c ("Fix XFRM-I support for nested ESP tunnels") Test: Tested against Android Kernel Unit Tests Test: Tested against Android CTS Signed-off-by: Benedict Wong benedictwong@google.com Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/xfrm.h | 1 + net/xfrm/xfrm_input.c | 1 + net/xfrm/xfrm_policy.c | 12 ++++++++++++ 3 files changed, 14 insertions(+)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h index dbc81f5eb5538..9ec6f2e92ad3a 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1039,6 +1039,7 @@ struct xfrm_offload { struct sec_path { int len; int olen; + int verified_cnt;

struct xfrm_state *xvec[XFRM_MAX_DEPTH]; struct xfrm_offload ovec[XFRM_MAX_OFFLOAD_DEPTH]; diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 2defd89da700d..ac1a645afa8df 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -131,6 +131,7 @@ struct sec_path *secpath_set(struct sk_buff *skb) memset(sp->ovec, 0, sizeof(sp->ovec)); sp->olen = 0; sp->len = 0; + sp->verified_cnt = 0;

return sp; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index e894c269affb1..7b1b93584bdbe 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3274,6 +3274,13 @@ xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int star if (xfrm_state_ok(tmpl, sp->xvec[idx], family, if_id)) return ++idx; if (sp->xvec[idx]->props.mode != XFRM_MODE_TRANSPORT) { + if (idx < sp->verified_cnt) { + /* Secpath entry previously verified, consider optional and + * continue searching + */ + continue; + } + if (start == -1) start = -2-idx; break; @@ -3648,6 +3655,9 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, * Order is _important_. Later we will implement * some barriers, but at the moment barriers * are implied between each two transformations. + * Upon success, marks secpath entries as having been + * verified to allow them to be skipped in future policy + * checks (e.g. nested tunnels). */ for (i = xfrm_nr-1, k = 0; i >= 0; i--) { k = xfrm_policy_ok(tpp[i], sp, k, family, if_id); @@ -3666,6 +3676,8 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, }

xfrm_pols_put(pols, npols); + sp->verified_cnt = k; + return 1; } XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLBLOCK);

From: Benedict Wong benedictwong@google.com

[ Upstream commit a287f5b0cfc6804c5b12a4be13c7c9fe27869e90 ]

This change adds methods in the XFRM-I input path that ensures that policies are checked prior to processing of the subsequent decapsulated packet, after which the relevant policies may no longer be resolvable (due to changing src/dst/proto/etc).

Notably, raw ESP/AH packets did not perform policy checks inherently, whereas all other encapsulated packets (UDP, TCP encapsulated) do policy checks after calling xfrm_input handling in the respective encapsulation layer.

Fixes: b0355dbbf13c ("Fix XFRM-I support for nested ESP tunnels") Test: Verified with additional Android Kernel Unit tests Test: Verified against Android CTS Signed-off-by: Benedict Wong benedictwong@google.com Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/xfrm/xfrm_interface_core.c | 54 +++++++++++++++++++++++++++++++--- 1 file changed, 50 insertions(+), 4 deletions(-)

diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 5a67b120c4dbd..94a3609548b11 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -310,6 +310,52 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) skb->mark = 0; }

+static int xfrmi_input(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type, unsigned short family) +{ + struct sec_path *sp; + + sp = skb_sec_path(skb); + if (sp && (sp->len || sp->olen) && + !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) + goto discard; + + XFRM_SPI_SKB_CB(skb)->family = family; + if (family == AF_INET) { + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + } else { + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; + } + + return xfrm_input(skb, nexthdr, spi, encap_type); +discard: + kfree_skb(skb); + return 0; +} + +static int xfrmi4_rcv(struct sk_buff *skb) +{ + return xfrmi_input(skb, ip_hdr(skb)->protocol, 0, 0, AF_INET); +} + +static int xfrmi6_rcv(struct sk_buff *skb) +{ + return xfrmi_input(skb, skb_network_header(skb)[IP6CB(skb)->nhoff], + 0, 0, AF_INET6); +} + +static int xfrmi4_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) +{ + return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET); +} + +static int xfrmi6_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) +{ + return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET6); +} + static int xfrmi_rcv_cb(struct sk_buff *skb, int err) { const struct xfrm_mode *inner_mode; @@ -937,8 +983,8 @@ static struct pernet_operations xfrmi_net_ops = { };

static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = { - .handler = xfrm6_rcv, - .input_handler = xfrm_input, + .handler = xfrmi6_rcv, + .input_handler = xfrmi6_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, @@ -988,8 +1034,8 @@ static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = { #endif

static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = { - .handler = xfrm4_rcv, - .input_handler = xfrm_input, + .handler = xfrmi4_rcv, + .input_handler = xfrmi4_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10,

From: Eduard Zingerman eddyz87@gmail.com

[ Upstream commit ecdf985d7615356b78241fdb159c091830ed0380 ]

For aligned stack writes using BPF_ST instruction track stored values in a same way BPF_STX is handled, e.g. make sure that the following commands produce similar verifier knowledge:

fp[-8] = 42; r1 = 42; fp[-8] = r1;

This covers two cases: - non-null values written to stack are stored as spill of fake registers; - null values written to stack are stored as STACK_ZERO marks.

Previously both cases above used STACK_MISC marks instead.

Some verifier test cases relied on the old logic to obtain STACK_MISC marks for some stack values. These test cases are updated in the same commit to avoid failures during bisect.

Signed-off-by: Eduard Zingerman eddyz87@gmail.com Link: https://lore.kernel.org/r/20230214232030.1502829-2-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov ast@kernel.org Stable-dep-of: 713274f1f2c8 ("bpf: Fix verifier id tracking of scalars on spill") Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/bpf/verifier.c | 18 ++- .../bpf/verifier/bounds_mix_sign_unsign.c | 110 ++++++++++-------- 2 files changed, 80 insertions(+), 48 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a0e573c08f79f..c4ceb4166528b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3061,6 +3061,11 @@ static void save_register_state(struct bpf_func_state *state, scrub_spilled_slot(&state->stack[spi].slot_type[i - 1]); }

+static bool is_bpf_st_mem(struct bpf_insn *insn) +{ + return BPF_CLASS(insn->code) == BPF_ST && BPF_MODE(insn->code) == BPF_MEM; +} + /* check_stack_{read,write}_fixed_off functions track spill/fill of registers, * stack boundary and alignment are checked in check_mem_access() */ @@ -3072,8 +3077,9 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, { struct bpf_func_state *cur; /* state of the current function */ int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err; - u32 dst_reg = env->prog->insnsi[insn_idx].dst_reg; + struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; struct bpf_reg_state *reg = NULL; + u32 dst_reg = insn->dst_reg;

err = grow_stack_state(state, round_up(slot + 1, BPF_REG_SIZE)); if (err) @@ -3122,6 +3128,13 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, return err; } save_register_state(state, spi, reg, size); + } else if (!reg && !(off % BPF_REG_SIZE) && is_bpf_st_mem(insn) && + insn->imm != 0 && env->bpf_capable) { + struct bpf_reg_state fake_reg = {}; + + __mark_reg_known(&fake_reg, (u32)insn->imm); + fake_reg.type = SCALAR_VALUE; + save_register_state(state, spi, &fake_reg, size); } else if (reg && is_spillable_regtype(reg->type)) { /* register containing pointer is being spilled into stack */ if (size != BPF_REG_SIZE) { @@ -3156,7 +3169,8 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;

/* when we zero initialize stack slots mark them as such */ - if (reg && register_is_null(reg)) { + if ((reg && register_is_null(reg)) || + (!reg && is_bpf_st_mem(insn) && insn->imm == 0)) { /* backtracking doesn't work for STACK_ZERO yet. */ err = mark_chain_precision(env, value_regno); if (err) diff --git a/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c b/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c index c2aa6f26738b4..bf82b923c5fe5 100644 --- a/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c +++ b/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c @@ -1,13 +1,14 @@ { "bounds checks mixing signed and unsigned, positive bounds", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, 2), BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 3), @@ -17,20 +18,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -1), BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 3), @@ -40,20 +42,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 2", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -1), BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 5), @@ -65,20 +68,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 3", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -1), BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 4), @@ -89,20 +93,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 4", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, 1), BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), @@ -112,19 +117,20 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .result = ACCEPT, }, { "bounds checks mixing signed and unsigned, variant 5", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -1), BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 5), @@ -135,17 +141,20 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 6", .insns = { + BPF_MOV64_REG(BPF_REG_9, BPF_REG_1), + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_9), BPF_MOV64_IMM(BPF_REG_2, 0), BPF_MOV64_REG(BPF_REG_3, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -512), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_6, -1), BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_6, 5), @@ -163,13 +172,14 @@ { "bounds checks mixing signed and unsigned, variant 7", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, 1024 * 1024 * 1024), BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 3), @@ -179,19 +189,20 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .result = ACCEPT, }, { "bounds checks mixing signed and unsigned, variant 8", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -1), BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 2), @@ -203,20 +214,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 9", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_LD_IMM64(BPF_REG_2, -9223372036854775808ULL), BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 2), @@ -228,19 +240,20 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .result = ACCEPT, }, { "bounds checks mixing signed and unsigned, variant 10", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, 0), BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 2), @@ -252,20 +265,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 11", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -1), BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), @@ -278,20 +292,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 12", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -6), BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), @@ -303,20 +318,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 13", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, 2), BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), @@ -331,7 +347,7 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, @@ -340,13 +356,14 @@ .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1, offsetof(struct __sk_buff, mark)), + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -1), BPF_MOV64_IMM(BPF_REG_8, 2), @@ -360,20 +377,21 @@ BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, -3), BPF_JMP_IMM(BPF_JA, 0, 0, -7), }, - .fixup_map_hash_8b = { 4 }, + .fixup_map_hash_8b = { 6 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 15", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -6), BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), @@ -387,7 +405,7 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, },

From: Maciej Żenczykowski maze@google.com

[ Upstream commit 1166a530a84758bb9e6b448fc8c195ed413f5ded ]

Before Linux v5.8 an AF_INET6 SOCK_DGRAM (udp/udplite) socket with SOL_UDP, UDP_ENCAP, UDP_ENCAP_ESPINUDP{,_NON_IKE} enabled would just unconditionally use xfrm4_udp_encap_rcv(), afterwards such a socket would use the newly added xfrm6_udp_encap_rcv() which only handles IPv6 packets.

Cc: Sabrina Dubroca sd@queasysnail.net Cc: Steffen Klassert steffen.klassert@secunet.com Cc: Jakub Kicinski kuba@kernel.org Cc: Benedict Wong benedictwong@google.com Cc: Yan Yan evitayan@google.com Fixes: 0146dca70b87 ("xfrm: add support for UDPv6 encapsulation of ESP") Signed-off-by: Maciej Żenczykowski maze@google.com Reviewed-by: Simon Horman simon.horman@corigine.com Reviewed-by: Sabrina Dubroca sd@queasysnail.net Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/xfrm4_input.c | 1 + net/ipv6/xfrm6_input.c | 3 +++ 2 files changed, 4 insertions(+)

diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index ad2afeef4f106..eac206a290d05 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -164,6 +164,7 @@ int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); return 0; } +EXPORT_SYMBOL(xfrm4_udp_encap_rcv);

int xfrm4_rcv(struct sk_buff *skb) { diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 04cbeefd89828..4907ab241d6be 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -86,6 +86,9 @@ int xfrm6_udp_encap_rcv(struct sock *sk, struct sk_buff *skb) __be32 *udpdata32; __u16 encap_type = up->encap_type;

+ if (skb->protocol == htons(ETH_P_IP)) + return xfrm4_udp_encap_rcv(sk, skb); + /* if this is not encapsulated socket, then just return now */ if (!encap_type) return 1;

From: Magali Lemes magali.lemes@canonical.com

[ Upstream commit d113c395c67b62fc0d3f2004c0afc406aca0a2b7 ]

TLS selftests use the ChaCha20-Poly1305 and SM4 algorithms, which are not FIPS compliant. When fips=1, this set of tests fails. Add a check and only run these tests if not in FIPS mode.

Fixes: 4f336e88a870 ("selftests/tls: add CHACHA20-POLY1305 to tls selftests") Fixes: e506342a03c7 ("selftests/tls: add SM4 GCM/CCM to tls selftests") Reviewed-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Magali Lemes magali.lemes@canonical.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/net/tls.c | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 2cbb12736596d..c0ad8385441f2 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -25,6 +25,8 @@ #define TLS_PAYLOAD_MAX_LEN 16384 #define SOL_TLS 282

+static int fips_enabled; + struct tls_crypto_info_keys { union { struct tls12_crypto_info_aes_gcm_128 aes128; @@ -235,7 +237,7 @@ FIXTURE_VARIANT(tls) { uint16_t tls_version; uint16_t cipher_type; - bool nopad; + bool nopad, fips_non_compliant; };

FIXTURE_VARIANT_ADD(tls, 12_aes_gcm) @@ -254,24 +256,28 @@ FIXTURE_VARIANT_ADD(tls, 12_chacha) { .tls_version = TLS_1_2_VERSION, .cipher_type = TLS_CIPHER_CHACHA20_POLY1305, + .fips_non_compliant = true, };

FIXTURE_VARIANT_ADD(tls, 13_chacha) { .tls_version = TLS_1_3_VERSION, .cipher_type = TLS_CIPHER_CHACHA20_POLY1305, + .fips_non_compliant = true, };

FIXTURE_VARIANT_ADD(tls, 13_sm4_gcm) { .tls_version = TLS_1_3_VERSION, .cipher_type = TLS_CIPHER_SM4_GCM, + .fips_non_compliant = true, };

FIXTURE_VARIANT_ADD(tls, 13_sm4_ccm) { .tls_version = TLS_1_3_VERSION, .cipher_type = TLS_CIPHER_SM4_CCM, + .fips_non_compliant = true, };

FIXTURE_VARIANT_ADD(tls, 12_aes_ccm) @@ -311,6 +317,9 @@ FIXTURE_SETUP(tls) int one = 1; int ret;

+ if (fips_enabled && variant->fips_non_compliant) + SKIP(return, "Unsupported cipher in FIPS mode"); + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12);

@@ -1820,4 +1829,17 @@ TEST(tls_v6ops) { close(sfd); }

+static void __attribute__((constructor)) fips_check(void) { + int res; + FILE *f; + + f = fopen("/proc/sys/crypto/fips_enabled", "r"); + if (f) { + res = fscanf(f, "%d", &fips_enabled); + if (res != 1) + ksft_print_msg("ERROR: Couldn't read /proc/sys/crypto/fips_enabled\n"); + fclose(f); + } +} + TEST_HARNESS_MAIN

From: Magali Lemes magali.lemes@canonical.com

[ Upstream commit d7a2fc1437f71cb058c7b11bc33dfc19e4bf277a ]

There are some MD5 tests which fail when the kernel is in FIPS mode, since MD5 is not FIPS compliant. Add a check and only run those tests if FIPS mode is not enabled.

Fixes: f0bee1ebb5594 ("fcnal-test: Add TCP MD5 tests") Fixes: 5cad8bce26e01 ("fcnal-test: Add TCP MD5 tests for VRF") Reviewed-by: David Ahern dsahern@kernel.org Signed-off-by: Magali Lemes magali.lemes@canonical.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/net/fcnal-test.sh | 27 ++++++++++++++++------- 1 file changed, 19 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 21ca91473c095..ee6880ac3e5ed 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -92,6 +92,13 @@ NSC_CMD="ip netns exec ${NSC}"

which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)

+# Check if FIPS mode is enabled +if [ -f /proc/sys/crypto/fips_enabled ]; then + fips_enabled=`cat /proc/sys/crypto/fips_enabled` +else + fips_enabled=0 +fi + ################################################################################ # utilities

@@ -1216,7 +1223,7 @@ ipv4_tcp_novrf() run_cmd nettest -d ${NSA_DEV} -r ${a} log_test_addr ${a} $? 1 "No server, device client, local conn"

- ipv4_tcp_md5_novrf + [ "$fips_enabled" = "1" ] || ipv4_tcp_md5_novrf }

ipv4_tcp_vrf() @@ -1270,9 +1277,11 @@ ipv4_tcp_vrf() log_test_addr ${a} $? 1 "Global server, local connection"

# run MD5 tests - setup_vrf_dup - ipv4_tcp_md5 - cleanup_vrf_dup + if [ "$fips_enabled" = "0" ]; then + setup_vrf_dup + ipv4_tcp_md5 + cleanup_vrf_dup + fi

# # enable VRF global server @@ -2772,7 +2781,7 @@ ipv6_tcp_novrf() log_test_addr ${a} $? 1 "No server, device client, local conn" done

- ipv6_tcp_md5_novrf + [ "$fips_enabled" = "1" ] || ipv6_tcp_md5_novrf }

ipv6_tcp_vrf() @@ -2842,9 +2851,11 @@ ipv6_tcp_vrf() log_test_addr ${a} $? 1 "Global server, local connection"

# run MD5 tests - setup_vrf_dup - ipv6_tcp_md5 - cleanup_vrf_dup + if [ "$fips_enabled" = "0" ]; then + setup_vrf_dup + ipv6_tcp_md5 + cleanup_vrf_dup + fi

# # enable VRF global server

From: Yevgeny Kliteynik kliteyn@nvidia.com

[ Upstream commit ef4c5afc783dc3d47640270a9b94713229c697e8 ]

When TUNNEL_L3_TO_L2 decap action was created, a pointer to a local variable was passed as its HW action data, resulting in attempt to free invalid address:

BUG: KASAN: invalid-free in mlx5dr_action_destroy+0x318/0x410 [mlx5_core]

Fixes: 4781df92f4da ("net/mlx5: DR, Move STEv0 modify header logic") Signed-off-by: Yevgeny Kliteynik kliteyn@nvidia.com Reviewed-by: Alex Vesker valex@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/ethernet/mellanox/mlx5/core/steering/dr_action.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index b1dfad274a39e..a3e7602b044e5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -1200,9 +1200,13 @@ dr_action_create_reformat_action(struct mlx5dr_domain *dmn, } case DR_ACTION_TYP_TNL_L3_TO_L2: { - u8 hw_actions[ACTION_CACHE_LINE_SIZE] = {}; + u8 *hw_actions; int ret;

+ hw_actions = kzalloc(ACTION_CACHE_LINE_SIZE, GFP_KERNEL); + if (!hw_actions) + return -ENOMEM; + ret = mlx5dr_ste_set_action_decap_l3_list(dmn->ste_ctx, data, data_sz, hw_actions, @@ -1210,6 +1214,7 @@ dr_action_create_reformat_action(struct mlx5dr_domain *dmn, &action->rewrite->num_of_actions); if (ret) { mlx5dr_dbg(dmn, "Failed creating decap l3 action list\n"); + kfree(hw_actions); return ret; }

@@ -1217,6 +1222,7 @@ dr_action_create_reformat_action(struct mlx5dr_domain *dmn, DR_CHUNK_SIZE_8); if (!action->rewrite->chunk) { mlx5dr_dbg(dmn, "Failed allocating modify header chunk\n"); + kfree(hw_actions); return -ENOMEM; }

@@ -1230,6 +1236,7 @@ dr_action_create_reformat_action(struct mlx5dr_domain *dmn, if (ret) { mlx5dr_dbg(dmn, "Writing decap l3 actions to ICM failed\n"); mlx5dr_icm_free_chunk(action->rewrite->chunk); + kfree(hw_actions); return ret; } return 0;

From: Stefan Wahren stefan.wahren@i2se.com

[ Upstream commit 92717c2356cb62c89e8a3dc37cbbab2502562524 ]

In case the QCA7000 is not available via SPI (e.g. in reset), the driver will cause a high load. The reason for this is that the synchronization is never finished and schedule() is never called. Since the synchronization is not timing critical, it's safe to drop this from the scheduling condition.

Signed-off-by: Stefan Wahren stefan.wahren@i2se.com Fixes: 291ab06ecf67 ("net: qualcomm: new Ethernet over SPI driver for QCA7000") Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/qualcomm/qca_spi.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index c865a4be05eec..4a1b94e5a8ea9 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -582,8 +582,7 @@ qcaspi_spi_thread(void *data) while (!kthread_should_stop()) { set_current_state(TASK_INTERRUPTIBLE); if ((qca->intr_req == qca->intr_svc) && - (qca->txr.skb[qca->txr.head] == NULL) && - (qca->sync == QCASPI_SYNC_READY)) + !qca->txr.skb[qca->txr.head]) schedule();

set_current_state(TASK_RUNNING);

From: Sergey Shtylyov s.shtylyov@omp.ru

[ Upstream commit 8d84064da0d4672e74f984e8710f27881137472c ]

The driver overrides the error codes returned by platform_get_irq() to -ENXIO, so if it returns -EPROBE_DEFER, the driver will fail the probe permanently instead of the deferred probing. Switch to propagating the error codes upstream.

Fixes: 9ec36cafe43b ("of/irq: do irq resolution in platform_get_irq") Signed-off-by: Sergey Shtylyov s.shtylyov@omp.ru Link: https://lore.kernel.org/r/20230617203622.6812-5-s.shtylyov@omp.ru Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/mmc/host/mvsdio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mmc/host/mvsdio.c b/drivers/mmc/host/mvsdio.c index 629efbe639c4f..b4f6a0a2fcb51 100644 --- a/drivers/mmc/host/mvsdio.c +++ b/drivers/mmc/host/mvsdio.c @@ -704,7 +704,7 @@ static int mvsd_probe(struct platform_device *pdev) } irq = platform_get_irq(pdev, 0); if (irq < 0) - return -ENXIO; + return irq;

mmc = mmc_alloc_host(sizeof(struct mvsd_host), &pdev->dev); if (!mmc) {

From: Sergey Shtylyov s.shtylyov@omp.ru

[ Upstream commit fb51b74a57859b707c3e8055ed0c25a7ca4f6a29 ]

The driver overrides the error codes returned by platform_get_irq() to -ENXIO, so if it returns -EPROBE_DEFER, the driver will fail the probe permanently instead of the deferred probing. Switch to propagating the error codes upstream.

Fixes: 9ec36cafe43b ("of/irq: do irq resolution in platform_get_irq") Signed-off-by: Sergey Shtylyov s.shtylyov@omp.ru Link: https://lore.kernel.org/r/20230617203622.6812-7-s.shtylyov@omp.ru Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/mmc/host/omap_hsmmc.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index 4bd7447552055..2db3a16e63c48 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -1791,9 +1791,11 @@ static int omap_hsmmc_probe(struct platform_device *pdev) }

res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - irq = platform_get_irq(pdev, 0); - if (res == NULL || irq < 0) + if (!res) return -ENXIO; + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq;

base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(base))

From: Sergey Shtylyov s.shtylyov@omp.ru

[ Upstream commit b465dea5e1540c7d7b5211adaf94926980d3014b ]

The driver overrides the error codes returned by platform_get_irq() to -EINVAL, so if it returns -EPROBE_DEFER, the driver will fail the probe permanently instead of the deferred probing. Switch to propagating the error codes upstream.

Fixes: 1b7ba57ecc86 ("mmc: sdhci-acpi: Handle return value of platform_get_irq") Signed-off-by: Sergey Shtylyov s.shtylyov@omp.ru Acked-by: Adrian Hunter adrian.hunter@intel.com Link: https://lore.kernel.org/r/20230617203622.6812-9-s.shtylyov@omp.ru Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/mmc/host/sdhci-acpi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c index 4cca4c90769bc..b917060a258a4 100644 --- a/drivers/mmc/host/sdhci-acpi.c +++ b/drivers/mmc/host/sdhci-acpi.c @@ -829,7 +829,7 @@ static int sdhci_acpi_probe(struct platform_device *pdev) host->ops = &sdhci_acpi_ops_dflt; host->irq = platform_get_irq(pdev, 0); if (host->irq < 0) { - err = -EINVAL; + err = host->irq; goto err_free; }

From: Sergey Shtylyov s.shtylyov@omp.ru

[ Upstream commit 413db499730248431c1005b392e8ed82c4fa19bf ]

The driver overrides the error codes returned by platform_get_irq_byname() to -ENODEV, so if it returns -EPROBE_DEFER, the driver will fail the probe permanently instead of the deferred probing. Switch to propagating error codes upstream.

Fixes: 9ec36cafe43b ("of/irq: do irq resolution in platform_get_irq") Signed-off-by: Sergey Shtylyov s.shtylyov@omp.ru Link: https://lore.kernel.org/r/20230617203622.6812-13-s.shtylyov@omp.ru Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/mmc/host/usdhi6rol0.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/mmc/host/usdhi6rol0.c b/drivers/mmc/host/usdhi6rol0.c index 99515be6e5e57..2032e4e1ee68b 100644 --- a/drivers/mmc/host/usdhi6rol0.c +++ b/drivers/mmc/host/usdhi6rol0.c @@ -1757,8 +1757,10 @@ static int usdhi6_probe(struct platform_device *pdev) irq_cd = platform_get_irq_byname(pdev, "card detect"); irq_sd = platform_get_irq_byname(pdev, "data"); irq_sdio = platform_get_irq_byname(pdev, "SDIO"); - if (irq_sd < 0 || irq_sdio < 0) - return -ENODEV; + if (irq_sd < 0) + return irq_sd; + if (irq_sdio < 0) + return irq_sdio;

mmc = mmc_alloc_host(sizeof(struct usdhi6_host), dev); if (!mmc)

From: Arınç ÜNAL arinc.unal@arinc9.com

[ Upstream commit 4ae90f90e4909e3014e2dc6a0627964617a7b824 ]

All MT7530 switch IP variants share the MT7530_MFC register, but the current driver only writes it for the switch variant that is integrated in the MT7621 SoC. Modify the code to include all MT7530 derivatives.

Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch") Suggested-by: Vladimir Oltean olteanv@gmail.com Signed-off-by: Arınç ÜNAL arinc.unal@arinc9.com Reviewed-by: Vladimir Oltean olteanv@gmail.com Reviewed-by: Russell King (Oracle) rmk+kernel@armlinux.org.uk Reviewed-by: Florian Fainelli florian.fainelli@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/dsa/mt7530.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 855220c5ce339..886dc7d3d85d3 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1020,7 +1020,7 @@ mt753x_cpu_port_enable(struct dsa_switch *ds, int port) UNU_FFP(BIT(port)));

/* Set CPU port number */ - if (priv->id == ID_MT7621) + if (priv->id == ID_MT7530 || priv->id == ID_MT7621) mt7530_rmw(priv, MT7530_MFC, CPU_MASK, CPU_EN | CPU_PORT(port));

/* CPU port gets connected to all user ports of

From: Arınç ÜNAL arinc.unal@arinc9.com

[ Upstream commit 8332cf6fd7c7087dbc2067115b33979c9851bbc4 ]

LLDP frames are link-local frames, therefore they must be trapped to the CPU port. Currently, the MT753X switches treat LLDP frames as regular multicast frames, therefore flooding them to user ports. To fix this, set LLDP frames to be trapped to the CPU port(s).

Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch") Signed-off-by: Arınç ÜNAL arinc.unal@arinc9.com Reviewed-by: Vladimir Oltean olteanv@gmail.com Reviewed-by: Russell King (Oracle) rmk+kernel@armlinux.org.uk Reviewed-by: Florian Fainelli florian.fainelli@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/dsa/mt7530.c | 4 ++++ drivers/net/dsa/mt7530.h | 5 +++++ 2 files changed, 9 insertions(+)

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index ec43edcaa7d9f..51d2ef0dc835c 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1004,6 +1004,10 @@ mt753x_trap_frames(struct mt7530_priv *priv) /* Trap BPDUs to the CPU port(s) */ mt7530_rmw(priv, MT753X_BPC, MT753X_BPDU_PORT_FW_MASK, MT753X_BPDU_CPU_ONLY); + + /* Trap LLDP frames with :0E MAC DA to the CPU port(s) */ + mt7530_rmw(priv, MT753X_RGAC2, MT753X_R0E_PORT_FW_MASK, + MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY)); }

static int diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index e8d9664353504..9a45663d8b4ef 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -65,6 +65,11 @@ enum mt753x_id { #define MT753X_BPC 0x24 #define MT753X_BPDU_PORT_FW_MASK GENMASK(2, 0)

+/* Register for :03 and :0E MAC DA frame control */ +#define MT753X_RGAC2 0x2c +#define MT753X_R0E_PORT_FW_MASK GENMASK(18, 16) +#define MT753X_R0E_PORT_FW(x) FIELD_PREP(MT753X_R0E_PORT_FW_MASK, x) + enum mt753x_bpdu_port_fw { MT753X_BPDU_FOLLOW_MFC, MT753X_BPDU_CPU_EXCLUDE = 4,

From: Pablo Neira Ayuso pablo@netfilter.org

[ Upstream commit 4bedf9eee016286c835e3d8fa981ddece5338795 ]

Add bound flag to rule and chain transactions as in 6a0a8d10a366 ("netfilter: nf_tables: use-after-free in failing rule with bound set") to skip them in case that the chain is already bound from the abort path.

This patch fixes an imbalance in the chain use refcnt that triggers a WARN_ON on the table and chain destroy path.

This patch also disallows nested chain bindings, which is not supported from userspace.

The logic to deal with chain binding in nft_data_hold() and nft_data_release() is not correct. The NFT_TRANS_PREPARE state needs a special handling in case a chain is bound but next expressions in the same rule fail to initialize as described by 1240eb93f061 ("netfilter: nf_tables: incorrect error path handling with NFT_MSG_NEWRULE").

The chain is left bound if rule construction fails, so the objects stored in this chain (and the chain itself) are released by the transaction records from the abort path, follow up patch ("netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain") completes this error handling.

When deleting an existing rule, chain bound flag is set off so the rule expression .destroy path releases the objects.

Fixes: d0e2c7de92c7 ("netfilter: nf_tables: add NFT_CHAIN_BINDING") Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/netfilter/nf_tables.h | 21 +++++++- net/netfilter/nf_tables_api.c | 86 +++++++++++++++++++----------- net/netfilter/nft_immediate.c | 87 +++++++++++++++++++++++++++---- 3 files changed, 153 insertions(+), 41 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 22e96b7e1b44a..c13a84c0b4965 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1002,7 +1002,10 @@ static inline struct nft_userdata *nft_userdata(const struct nft_rule *rule) return (void *)&rule->data[rule->dlen]; }

-void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule); +void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_rule *rule); +void nft_rule_expr_deactivate(const struct nft_ctx *ctx, struct nft_rule *rule, + enum nft_trans_phase phase); +void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule);

static inline void nft_set_elem_update_expr(const struct nft_set_ext *ext, struct nft_regs *regs, @@ -1085,6 +1088,7 @@ int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_set_elem *elem); int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set); +int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain);

enum nft_chain_types { NFT_CHAIN_T_DEFAULT = 0, @@ -1121,11 +1125,17 @@ int nft_chain_validate_dependency(const struct nft_chain *chain, int nft_chain_validate_hooks(const struct nft_chain *chain, unsigned int hook_flags);

+static inline bool nft_chain_binding(const struct nft_chain *chain) +{ + return chain->flags & NFT_CHAIN_BINDING; +} + static inline bool nft_chain_is_bound(struct nft_chain *chain) { return (chain->flags & NFT_CHAIN_BINDING) && chain->bound; }

+int nft_chain_add(struct nft_table *table, struct nft_chain *chain); void nft_chain_del(struct nft_chain *chain); void nf_tables_chain_destroy(struct nft_ctx *ctx);

@@ -1560,6 +1570,7 @@ struct nft_trans_rule { struct nft_rule *rule; struct nft_flow_rule *flow; u32 rule_id; + bool bound; };

#define nft_trans_rule(trans) \ @@ -1568,6 +1579,8 @@ struct nft_trans_rule { (((struct nft_trans_rule *)trans->data)->flow) #define nft_trans_rule_id(trans) \ (((struct nft_trans_rule *)trans->data)->rule_id) +#define nft_trans_rule_bound(trans) \ + (((struct nft_trans_rule *)trans->data)->bound)

struct nft_trans_set { struct nft_set *set; @@ -1592,13 +1605,17 @@ struct nft_trans_set { (((struct nft_trans_set *)trans->data)->gc_int)

struct nft_trans_chain { + struct nft_chain *chain; bool update; char *name; struct nft_stats __percpu *stats; u8 policy; + bool bound; u32 chain_id; };

+#define nft_trans_chain(trans) \ + (((struct nft_trans_chain *)trans->data)->chain) #define nft_trans_chain_update(trans) \ (((struct nft_trans_chain *)trans->data)->update) #define nft_trans_chain_name(trans) \ @@ -1607,6 +1624,8 @@ struct nft_trans_chain { (((struct nft_trans_chain *)trans->data)->stats) #define nft_trans_chain_policy(trans) \ (((struct nft_trans_chain *)trans->data)->policy) +#define nft_trans_chain_bound(trans) \ + (((struct nft_trans_chain *)trans->data)->bound) #define nft_trans_chain_id(trans) \ (((struct nft_trans_chain *)trans->data)->chain_id)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 13d4913266b4d..8f8e315691dde 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -195,6 +195,48 @@ static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) } }

+static void nft_chain_trans_bind(const struct nft_ctx *ctx, struct nft_chain *chain) +{ + struct nftables_pernet *nft_net; + struct net *net = ctx->net; + struct nft_trans *trans; + + if (!nft_chain_binding(chain)) + return; + + nft_net = nft_pernet(net); + list_for_each_entry_reverse(trans, &nft_net->commit_list, list) { + switch (trans->msg_type) { + case NFT_MSG_NEWCHAIN: + if (nft_trans_chain(trans) == chain) + nft_trans_chain_bound(trans) = true; + break; + case NFT_MSG_NEWRULE: + if (trans->ctx.chain == chain) + nft_trans_rule_bound(trans) = true; + break; + } + } +} + +int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain) +{ + if (!nft_chain_binding(chain)) + return 0; + + if (nft_chain_binding(ctx->chain)) + return -EOPNOTSUPP; + + if (chain->bound) + return -EBUSY; + + chain->bound = true; + chain->use++; + nft_chain_trans_bind(ctx, chain); + + return 0; +} + static int nft_netdev_register_hooks(struct net *net, struct list_head *hook_list) { @@ -340,8 +382,9 @@ static struct nft_trans *nft_trans_chain_add(struct nft_ctx *ctx, int msg_type) ntohl(nla_get_be32(ctx->nla[NFTA_CHAIN_ID])); } } - + nft_trans_chain(trans) = ctx->chain; nft_trans_commit_list_add_tail(ctx->net, trans); + return trans; }

@@ -359,8 +402,7 @@ static int nft_delchain(struct nft_ctx *ctx) return 0; }

-static void nft_rule_expr_activate(const struct nft_ctx *ctx, - struct nft_rule *rule) +void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_rule *rule) { struct nft_expr *expr;

@@ -373,9 +415,8 @@ static void nft_rule_expr_activate(const struct nft_ctx *ctx, } }

-static void nft_rule_expr_deactivate(const struct nft_ctx *ctx, - struct nft_rule *rule, - enum nft_trans_phase phase) +void nft_rule_expr_deactivate(const struct nft_ctx *ctx, struct nft_rule *rule, + enum nft_trans_phase phase) { struct nft_expr *expr;

@@ -2188,7 +2229,7 @@ static int nft_basechain_init(struct nft_base_chain *basechain, u8 family, return 0; }

-static int nft_chain_add(struct nft_table *table, struct nft_chain *chain) +int nft_chain_add(struct nft_table *table, struct nft_chain *chain) { int err;

@@ -3315,8 +3356,7 @@ static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info, return err; }

-static void nf_tables_rule_destroy(const struct nft_ctx *ctx, - struct nft_rule *rule) +void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule) { struct nft_expr *expr, *next;

@@ -3333,7 +3373,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, kfree(rule); }

-void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule) +static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule) { nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE); nf_tables_rule_destroy(ctx, rule); @@ -6446,7 +6486,6 @@ static int nf_tables_newsetelem(struct sk_buff *skb, void nft_data_hold(const struct nft_data *data, enum nft_data_types type) { struct nft_chain *chain; - struct nft_rule *rule;

if (type == NFT_DATA_VERDICT) { switch (data->verdict.code) { @@ -6454,15 +6493,6 @@ void nft_data_hold(const struct nft_data *data, enum nft_data_types type) case NFT_GOTO: chain = data->verdict.chain; chain->use++; - - if (!nft_chain_is_bound(chain)) - break; - - chain->table->use++; - list_for_each_entry(rule, &chain->rules, list) - chain->use++; - - nft_chain_add(chain->table, chain); break; } } @@ -9368,7 +9398,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) kfree(nft_trans_chain_name(trans)); nft_trans_destroy(trans); } else { - if (nft_chain_is_bound(trans->ctx.chain)) { + if (nft_trans_chain_bound(trans)) { nft_trans_destroy(trans); break; } @@ -9385,6 +9415,10 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; case NFT_MSG_NEWRULE: + if (nft_trans_rule_bound(trans)) { + nft_trans_destroy(trans); + break; + } trans->ctx.chain->use--; list_del_rcu(&nft_trans_rule(trans)->list); nft_rule_expr_deactivate(&trans->ctx, @@ -9943,22 +9977,12 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, static void nft_verdict_uninit(const struct nft_data *data) { struct nft_chain *chain; - struct nft_rule *rule;

switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: chain = data->verdict.chain; chain->use--; - - if (!nft_chain_is_bound(chain)) - break; - - chain->table->use--; - list_for_each_entry(rule, &chain->rules, list) - chain->use--; - - nft_chain_del(chain); break; } } diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 5f28b21abc7df..457fc1e218410 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -76,11 +76,9 @@ static int nft_immediate_init(const struct nft_ctx *ctx, switch (priv->data.verdict.code) { case NFT_JUMP: case NFT_GOTO: - if (nft_chain_is_bound(chain)) { - err = -EBUSY; - goto err1; - } - chain->bound = true; + err = nf_tables_bind_chain(ctx, chain); + if (err < 0) + return err; break; default: break; @@ -98,6 +96,31 @@ static void nft_immediate_activate(const struct nft_ctx *ctx, const struct nft_expr *expr) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); + const struct nft_data *data = &priv->data; + struct nft_ctx chain_ctx; + struct nft_chain *chain; + struct nft_rule *rule; + + if (priv->dreg == NFT_REG_VERDICT) { + switch (data->verdict.code) { + case NFT_JUMP: + case NFT_GOTO: + chain = data->verdict.chain; + if (!nft_chain_binding(chain)) + break; + + chain_ctx = *ctx; + chain_ctx.chain = chain; + + list_for_each_entry(rule, &chain->rules, list) + nft_rule_expr_activate(&chain_ctx, rule); + + nft_clear(ctx->net, chain); + break; + default: + break; + } + }

return nft_data_hold(&priv->data, nft_dreg_to_type(priv->dreg)); } @@ -107,6 +130,40 @@ static void nft_immediate_deactivate(const struct nft_ctx *ctx, enum nft_trans_phase phase) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); + const struct nft_data *data = &priv->data; + struct nft_ctx chain_ctx; + struct nft_chain *chain; + struct nft_rule *rule; + + if (priv->dreg == NFT_REG_VERDICT) { + switch (data->verdict.code) { + case NFT_JUMP: + case NFT_GOTO: + chain = data->verdict.chain; + if (!nft_chain_binding(chain)) + break; + + chain_ctx = *ctx; + chain_ctx.chain = chain; + + list_for_each_entry(rule, &chain->rules, list) + nft_rule_expr_deactivate(&chain_ctx, rule, phase); + + switch (phase) { + case NFT_TRANS_PREPARE: + nft_deactivate_next(ctx->net, chain); + break; + default: + nft_chain_del(chain); + chain->bound = false; + chain->table->use--; + break; + } + break; + default: + break; + } + }

if (phase == NFT_TRANS_COMMIT) return; @@ -131,15 +188,27 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx, case NFT_GOTO: chain = data->verdict.chain;

- if (!nft_chain_is_bound(chain)) + if (!nft_chain_binding(chain)) + break; + + /* Rule construction failed, but chain is already bound: + * let the transaction records release this chain and its rules. + */ + if (chain->bound) { + chain->use--; break; + }

+ /* Rule has been deleted, release chain and its rules. */ chain_ctx = *ctx; chain_ctx.chain = chain;

- list_for_each_entry_safe(rule, n, &chain->rules, list) - nf_tables_rule_release(&chain_ctx, rule); - + chain->use--; + list_for_each_entry_safe(rule, n, &chain->rules, list) { + chain->use--; + list_del(&rule->list); + nf_tables_rule_destroy(&chain_ctx, rule); + } nf_tables_chain_destroy(&chain_ctx); break; default:

From: Pablo Neira Ayuso pablo@netfilter.org

[ Upstream commit 628bd3e49cba1c066228e23d71a852c23e26da73 ]

set .destroy callback releases the references to other objects in maps. This is very late and it results in spurious EBUSY errors. Drop refcount from the preparation phase instead, update set backend not to drop reference counter from set .destroy path.

Exceptions: NFT_TRANS_PREPARE_ERROR does not require to drop the reference counter because the transaction abort path releases the map references for each element since the set is unbound. The abort path also deals with releasing reference counter for new elements added to unbound sets.

Fixes: 591054469b3e ("netfilter: nf_tables: revisit chain/object refcounting from elements") Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/netfilter/nf_tables.h | 5 +- net/netfilter/nf_tables_api.c | 147 ++++++++++++++++++++++++++---- net/netfilter/nft_set_bitmap.c | 5 +- net/netfilter/nft_set_hash.c | 23 ++++- net/netfilter/nft_set_pipapo.c | 14 ++- net/netfilter/nft_set_rbtree.c | 5 +- 6 files changed, 167 insertions(+), 32 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 984f7d3087735..bbcd558f19344 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -467,7 +467,8 @@ struct nft_set_ops { int (*init)(const struct nft_set *set, const struct nft_set_desc *desc, const struct nlattr * const nla[]); - void (*destroy)(const struct nft_set *set); + void (*destroy)(const struct nft_ctx *ctx, + const struct nft_set *set); void (*gc_init)(const struct nft_set *set);

unsigned int elemsize; @@ -804,6 +805,8 @@ int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set, struct nft_expr *expr_array[]); void nft_set_elem_destroy(const struct nft_set *set, void *elem, bool destroy_expr); +void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, + const struct nft_set *set, void *elem);

/** * struct nft_set_gc_batch_head - nf_tables set garbage collection batch diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 72bb2b3977480..337bab663540a 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -561,6 +561,58 @@ static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, return __nft_trans_set_add(ctx, msg_type, set, NULL); }

+static void nft_setelem_data_deactivate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem); + +static int nft_mapelem_deactivate(const struct nft_ctx *ctx, + struct nft_set *set, + const struct nft_set_iter *iter, + struct nft_set_elem *elem) +{ + nft_setelem_data_deactivate(ctx->net, set, elem); + + return 0; +} + +struct nft_set_elem_catchall { + struct list_head list; + struct rcu_head rcu; + void *elem; +}; + +static void nft_map_catchall_deactivate(const struct nft_ctx *ctx, + struct nft_set *set) +{ + u8 genmask = nft_genmask_next(ctx->net); + struct nft_set_elem_catchall *catchall; + struct nft_set_elem elem; + struct nft_set_ext *ext; + + list_for_each_entry(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (!nft_set_elem_active(ext, genmask)) + continue; + + elem.priv = catchall->elem; + nft_setelem_data_deactivate(ctx->net, set, &elem); + break; + } +} + +static void nft_map_deactivate(const struct nft_ctx *ctx, struct nft_set *set) +{ + struct nft_set_iter iter = { + .genmask = nft_genmask_next(ctx->net), + .fn = nft_mapelem_deactivate, + }; + + set->ops->walk(ctx, set, &iter); + WARN_ON_ONCE(iter.err); + + nft_map_catchall_deactivate(ctx, set); +} + static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set) { int err; @@ -569,6 +621,9 @@ static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set) if (err < 0) return err;

+ if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_deactivate(ctx, set); + nft_deactivate_next(ctx->net, set); ctx->table->use--;

@@ -3484,12 +3539,6 @@ int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, return 0; }

-struct nft_set_elem_catchall { - struct list_head list; - struct rcu_head rcu; - void *elem; -}; - int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set) { u8 genmask = nft_genmask_next(ctx->net); @@ -4808,7 +4857,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, for (i = 0; i < set->num_exprs; i++) nft_expr_destroy(&ctx, set->exprs[i]); err_set_destroy: - ops->destroy(set); + ops->destroy(&ctx, set); err_set_init: kfree(set->name); err_set_name: @@ -4823,7 +4872,7 @@ static void nft_set_catchall_destroy(const struct nft_ctx *ctx,

list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { list_del_rcu(&catchall->list); - nft_set_elem_destroy(set, catchall->elem, true); + nf_tables_set_elem_destroy(ctx, set, catchall->elem); kfree_rcu(catchall, rcu); } } @@ -4838,7 +4887,7 @@ static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) for (i = 0; i < set->num_exprs; i++) nft_expr_destroy(ctx, set->exprs[i]);

- set->ops->destroy(set); + set->ops->destroy(ctx, set); nft_set_catchall_destroy(ctx, set); kfree(set->name); kvfree(set); @@ -4999,10 +5048,60 @@ static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, } }

+static void nft_setelem_data_activate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem); + +static int nft_mapelem_activate(const struct nft_ctx *ctx, + struct nft_set *set, + const struct nft_set_iter *iter, + struct nft_set_elem *elem) +{ + nft_setelem_data_activate(ctx->net, set, elem); + + return 0; +} + +static void nft_map_catchall_activate(const struct nft_ctx *ctx, + struct nft_set *set) +{ + u8 genmask = nft_genmask_next(ctx->net); + struct nft_set_elem_catchall *catchall; + struct nft_set_elem elem; + struct nft_set_ext *ext; + + list_for_each_entry(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (!nft_set_elem_active(ext, genmask)) + continue; + + elem.priv = catchall->elem; + nft_setelem_data_activate(ctx->net, set, &elem); + break; + } +} + +static void nft_map_activate(const struct nft_ctx *ctx, struct nft_set *set) +{ + struct nft_set_iter iter = { + .genmask = nft_genmask_next(ctx->net), + .fn = nft_mapelem_activate, + }; + + set->ops->walk(ctx, set, &iter); + WARN_ON_ONCE(iter.err); + + nft_map_catchall_activate(ctx, set); +} + void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set) { - if (nft_set_is_anonymous(set)) + if (nft_set_is_anonymous(set)) { + if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_activate(ctx, set); + nft_clear(ctx->net, set); + }

set->use++; } @@ -5021,13 +5120,20 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, set->use--; break; case NFT_TRANS_PREPARE: - if (nft_set_is_anonymous(set)) - nft_deactivate_next(ctx->net, set); + if (nft_set_is_anonymous(set)) { + if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_deactivate(ctx, set);

+ nft_deactivate_next(ctx->net, set); + } set->use--; return; case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: + if (nft_set_is_anonymous(set) && + set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_deactivate(ctx, set); + set->use--; fallthrough; default: @@ -5780,6 +5886,7 @@ static void nft_set_elem_expr_destroy(const struct nft_ctx *ctx, __nft_set_elem_expr_destroy(ctx, expr); }

+/* Drop references and destroy. Called from gc, dynset and abort path. */ void nft_set_elem_destroy(const struct nft_set *set, void *elem, bool destroy_expr) { @@ -5801,11 +5908,11 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem, } EXPORT_SYMBOL_GPL(nft_set_elem_destroy);

-/* Only called from commit path, nft_setelem_data_deactivate() already deals - * with the refcounting from the preparation phase. +/* Destroy element. References have been already dropped in the preparation + * path via nft_setelem_data_deactivate(). */ -static void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, - const struct nft_set *set, void *elem) +void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, + const struct nft_set *set, void *elem) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem);

@@ -6438,7 +6545,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (obj) obj->use--; err_elem_userdata: - nf_tables_set_elem_destroy(ctx, set, elem.priv); + nft_set_elem_destroy(set, elem.priv, true); err_parse_data: if (nla[NFTA_SET_ELEM_DATA] != NULL) nft_data_release(&elem.data.val, desc.type); @@ -9482,6 +9589,9 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) case NFT_MSG_DELSET: trans->ctx.table->use++; nft_clear(trans->ctx.net, nft_trans_set(trans)); + if (nft_trans_set(trans)->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_activate(&trans->ctx, nft_trans_set(trans)); + nft_trans_destroy(trans); break; case NFT_MSG_NEWSETELEM: @@ -10248,6 +10358,9 @@ static void __nft_release_table(struct net *net, struct nft_table *table) list_for_each_entry_safe(set, ns, &table->sets, list) { list_del(&set->list); table->use--; + if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_deactivate(&ctx, set); + nft_set_destroy(&ctx, set); } list_for_each_entry_safe(obj, ne, &table->objects, list) { diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 96081ac8d2b4c..1e5e7a181e0bc 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -271,13 +271,14 @@ static int nft_bitmap_init(const struct nft_set *set, return 0; }

-static void nft_bitmap_destroy(const struct nft_set *set) +static void nft_bitmap_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_bitmap *priv = nft_set_priv(set); struct nft_bitmap_elem *be, *n;

list_for_each_entry_safe(be, n, &priv->list, head) - nft_set_elem_destroy(set, be, true); + nf_tables_set_elem_destroy(ctx, set, be); }

static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features, diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 76de6c8d98655..0b73cb0e752f7 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -400,19 +400,31 @@ static int nft_rhash_init(const struct nft_set *set, return 0; }

+struct nft_rhash_ctx { + const struct nft_ctx ctx; + const struct nft_set *set; +}; + static void nft_rhash_elem_destroy(void *ptr, void *arg) { - nft_set_elem_destroy(arg, ptr, true); + struct nft_rhash_ctx *rhash_ctx = arg; + + nf_tables_set_elem_destroy(&rhash_ctx->ctx, rhash_ctx->set, ptr); }

-static void nft_rhash_destroy(const struct nft_set *set) +static void nft_rhash_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_rhash *priv = nft_set_priv(set); + struct nft_rhash_ctx rhash_ctx = { + .ctx = *ctx, + .set = set, + };

cancel_delayed_work_sync(&priv->gc_work); rcu_barrier(); rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy, - (void *)set); + (void *)&rhash_ctx); }

/* Number of buckets is stored in u32, so cap our result to 1U<<31 */ @@ -643,7 +655,8 @@ static int nft_hash_init(const struct nft_set *set, return 0; }

-static void nft_hash_destroy(const struct nft_set *set) +static void nft_hash_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_hash *priv = nft_set_priv(set); struct nft_hash_elem *he; @@ -653,7 +666,7 @@ static void nft_hash_destroy(const struct nft_set *set) for (i = 0; i < priv->buckets; i++) { hlist_for_each_entry_safe(he, next, &priv->table[i], node) { hlist_del_rcu(&he->node); - nft_set_elem_destroy(set, he, true); + nf_tables_set_elem_destroy(ctx, set, he); } } } diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 15e451dc3fc46..c867b5b772e86 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -2148,10 +2148,12 @@ static int nft_pipapo_init(const struct nft_set *set,

/** * nft_set_pipapo_match_destroy() - Destroy elements from key mapping array + * @ctx: context * @set: nftables API set representation * @m: matching data pointing to key mapping array */ -static void nft_set_pipapo_match_destroy(const struct nft_set *set, +static void nft_set_pipapo_match_destroy(const struct nft_ctx *ctx, + const struct nft_set *set, struct nft_pipapo_match *m) { struct nft_pipapo_field *f; @@ -2168,15 +2170,17 @@ static void nft_set_pipapo_match_destroy(const struct nft_set *set,

e = f->mt[r].e;

- nft_set_elem_destroy(set, e, true); + nf_tables_set_elem_destroy(ctx, set, e); } }

/** * nft_pipapo_destroy() - Free private data for set and all committed elements + * @ctx: context * @set: nftables API set representation */ -static void nft_pipapo_destroy(const struct nft_set *set) +static void nft_pipapo_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m; @@ -2186,7 +2190,7 @@ static void nft_pipapo_destroy(const struct nft_set *set) if (m) { rcu_barrier();

- nft_set_pipapo_match_destroy(set, m); + nft_set_pipapo_match_destroy(ctx, set, m);

#ifdef NFT_PIPAPO_ALIGN free_percpu(m->scratch_aligned); @@ -2203,7 +2207,7 @@ static void nft_pipapo_destroy(const struct nft_set *set) m = priv->clone;

if (priv->dirty) - nft_set_pipapo_match_destroy(set, m); + nft_set_pipapo_match_destroy(ctx, set, m);

#ifdef NFT_PIPAPO_ALIGN free_percpu(priv->clone->scratch_aligned); diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 2f114aa10f1a7..5c05c9b990fba 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -664,7 +664,8 @@ static int nft_rbtree_init(const struct nft_set *set, return 0; }

-static void nft_rbtree_destroy(const struct nft_set *set) +static void nft_rbtree_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe; @@ -675,7 +676,7 @@ static void nft_rbtree_destroy(const struct nft_set *set) while ((node = priv->root.rb_node) != NULL) { rb_erase(node, &priv->root); rbe = rb_entry(node, struct nft_rbtree_elem, node); - nft_set_elem_destroy(set, rbe, true); + nf_tables_set_elem_destroy(ctx, set, rbe); } }

From: Pablo Neira Ayuso pablo@netfilter.org

[ Upstream commit c88c535b592d3baeee74009f3eceeeaf0fdd5e1b ]

Anonymous sets come with NFT_SET_CONSTANT from userspace. Although API allows to create anonymous sets without NFT_SET_CONSTANT, it makes no sense to allow to add and to delete elements for bound anonymous sets.

Fixes: 96518518cc41 ("netfilter: add nftables") Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nf_tables_api.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 337bab663540a..2cd83d09f4192 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -6590,7 +6590,8 @@ static int nf_tables_newsetelem(struct sk_buff *skb, if (IS_ERR(set)) return PTR_ERR(set);

- if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT) + if (!list_empty(&set->bindings) && + (set->flags & (NFT_SET_CONSTANT | NFT_SET_ANONYMOUS))) return -EBUSY;

nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); @@ -6864,7 +6865,9 @@ static int nf_tables_delsetelem(struct sk_buff *skb, set = nft_set_lookup(table, nla[NFTA_SET_ELEM_LIST_SET], genmask); if (IS_ERR(set)) return PTR_ERR(set); - if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT) + + if (!list_empty(&set->bindings) && + (set->flags & (NFT_SET_CONSTANT | NFT_SET_ANONYMOUS))) return -EBUSY;

nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla);

From: Pablo Neira Ayuso pablo@netfilter.org

[ Upstream commit 62e1e94b246e685d89c3163aaef4b160e42ceb02 ]

Use binding list to track set transaction and to check for unbound chains before entering the commit phase.

Bail out if chain binding remain unused before entering the commit step.

Fixes: d0e2c7de92c7 ("netfilter: nf_tables: add NFT_CHAIN_BINDING") Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nf_tables_api.c | 13 +++++++++++++ 1 file changed, 13 insertions(+)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c0126aac035f8..984720964a498 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -372,6 +372,11 @@ static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *tr nft_set_is_anonymous(nft_trans_set(trans))) list_add_tail(&trans->binding_list, &nft_net->binding_list); break; + case NFT_MSG_NEWCHAIN: + if (!nft_trans_chain_update(trans) && + nft_chain_binding(nft_trans_chain(trans))) + list_add_tail(&trans->binding_list, &nft_net->binding_list); + break; }

list_add_tail(&trans->list, &nft_net->commit_list); @@ -9221,6 +9226,14 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) return -EINVAL; } break; + case NFT_MSG_NEWCHAIN: + if (!nft_trans_chain_update(trans) && + nft_chain_binding(nft_trans_chain(trans)) && + !nft_trans_chain_bound(trans)) { + pr_warn_once("nftables ruleset with unbound chain\n"); + return -EINVAL; + } + break; } }

From: Pablo Neira Ayuso pablo@netfilter.org

[ Upstream commit 62f9a68a36d4441a6c412b81faed102594bc6670 ]

Move the alias from xt_osf to nfnetlink_osf.

Fixes: f9324952088f ("netfilter: nfnetlink_osf: extract nfnetlink_subsystem code from xt_osf.c") Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nfnetlink_osf.c | 1 + net/netfilter/xt_osf.c | 1 - 2 files changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index ee6840bd59337..8f1bfa6ccc2d9 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -439,3 +439,4 @@ module_init(nfnl_osf_init); module_exit(nfnl_osf_fini);

MODULE_LICENSE("GPL"); +MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_OSF); diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index e1990baf3a3b7..dc9485854002a 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -71,4 +71,3 @@ MODULE_AUTHOR("Evgeniy Polyakov zbr@ioremap.net"); MODULE_DESCRIPTION("Passive OS fingerprint matching."); MODULE_ALIAS("ipt_osf"); MODULE_ALIAS("ip6t_osf"); -MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_OSF);

From: Florent Revest revest@chromium.org

[ Upstream commit 9724160b3942b0a967b91a59f81da5593f28b8ba ]

When building a kernel with LLVM=1, LLVM_IAS=0 and CONFIG_KASAN=y, LLVM leaves DWARF tags for the "asan.module_ctor" & co symbols. In turn, pahole creates BTF_KIND_FUNC entries for these and this makes the BTF metadata validation fail because they contain a dot.

In a dramatic turn of event, this BTF verification failure can cause the netfilter_bpf initialization to fail, causing netfilter_core to free the netfilter_helper hashmap and netfilter_ftp to trigger a use-after-free. The risk of u-a-f in netfilter will be addressed separately but the existence of "asan.module_ctor" debug info under some build conditions sounds like a good enough reason to accept functions that contain dots in BTF.

Although using only LLVM=1 is the recommended way to compile clang-based kernels, users can certainly do LLVM=1, LLVM_IAS=0 as well and we still try to support that combination according to Nick. To clarify:

- > v5.10 kernel, LLVM=1 (LLVM_IAS=0 is not the default) is recommended, but user can still have LLVM=1, LLVM_IAS=0 to trigger the issue

- <= 5.10 kernel, LLVM=1 (LLVM_IAS=0 is the default) is recommended in which case GNU as will be used

Fixes: 1dc92851849c ("bpf: kernel side support for BTF Var and DataSec") Signed-off-by: Florent Revest revest@chromium.org Signed-off-by: Daniel Borkmann daniel@iogearbox.net Acked-by: Andrii Nakryiko andrii@kernel.org Cc: Yonghong Song yhs@meta.com Cc: Nick Desaulniers ndesaulniers@google.com Link: https://lore.kernel.org/bpf/20230615145607.3469985-1-revest@chromium.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/bpf/btf.c | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-)

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index a8838a32f750e..8220caa488c54 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -735,13 +735,12 @@ static bool btf_name_offset_valid(const struct btf *btf, u32 offset) return offset < btf->hdr.str_len; }

-static bool __btf_name_char_ok(char c, bool first, bool dot_ok) +static bool __btf_name_char_ok(char c, bool first) { if ((first ? !isalpha(c) : !isalnum(c)) && c != '_' && - ((c == '.' && !dot_ok) || - c != '.')) + c != '.') return false; return true; } @@ -758,20 +757,20 @@ static const char *btf_str_by_offset(const struct btf *btf, u32 offset) return NULL; }

-static bool __btf_name_valid(const struct btf *btf, u32 offset, bool dot_ok) +static bool __btf_name_valid(const struct btf *btf, u32 offset) { /* offset must be valid */ const char *src = btf_str_by_offset(btf, offset); const char *src_limit;

- if (!__btf_name_char_ok(*src, true, dot_ok)) + if (!__btf_name_char_ok(*src, true)) return false;

/* set a limit on identifier length */ src_limit = src + KSYM_NAME_LEN; src++; while (*src && src < src_limit) { - if (!__btf_name_char_ok(*src, false, dot_ok)) + if (!__btf_name_char_ok(*src, false)) return false; src++; } @@ -779,17 +778,14 @@ static bool __btf_name_valid(const struct btf *btf, u32 offset, bool dot_ok) return !*src; }

-/* Only C-style identifier is permitted. This can be relaxed if - * necessary. - */ static bool btf_name_valid_identifier(const struct btf *btf, u32 offset) { - return __btf_name_valid(btf, offset, false); + return __btf_name_valid(btf, offset); }

static bool btf_name_valid_section(const struct btf *btf, u32 offset) { - return __btf_name_valid(btf, offset, true); + return __btf_name_valid(btf, offset); }

static const char *__btf_name_by_offset(const struct btf *btf, u32 offset) @@ -4044,7 +4040,7 @@ static s32 btf_var_check_meta(struct btf_verifier_env *env, }

if (!t->name_off || - !__btf_name_valid(env->btf, t->name_off, true)) { + !__btf_name_valid(env->btf, t->name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; }

From: Jens Axboe axboe@kernel.dk

[ Upstream commit 26fed83653d0154704cadb7afc418f315c7ac1f0 ]

Rather than assign the user pointer to msghdr->msg_control, assign it to msghdr->msg_control_user to make sparse happy. They are in a union so the end result is the same, but let's avoid new sparse warnings and squash this one.

Reported-by: kernel test robot lkp@intel.com Closes: https://lore.kernel.org/oe-kbuild-all/202306210654.mDMcyMuB-lkp@intel.com/ Fixes: cac9e4418f4c ("io_uring/net: save msghdr->msg_control for retries") Reviewed-by: Christoph Hellwig hch@lst.de Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- io_uring/net.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/io_uring/net.c b/io_uring/net.c index 41f828d93c899..2b44126a876ef 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -190,7 +190,7 @@ static int io_sendmsg_copy_hdr(struct io_kiocb *req, ret = sendmsg_copy_msghdr(&iomsg->msg, sr->umsg, sr->msg_flags, &iomsg->free_iov); /* save msg_control as sys_sendmsg() overwrites it */ - sr->msg_control = iomsg->msg.msg_control; + sr->msg_control = iomsg->msg.msg_control_user; return ret; }

@@ -289,7 +289,7 @@ int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)

if (req_has_async_data(req)) { kmsg = req->async_data; - kmsg->msg.msg_control = sr->msg_control; + kmsg->msg.msg_control_user = sr->msg_control; } else { ret = io_sendmsg_copy_hdr(req, &iomsg); if (ret)

From: Shyam Sundar S K Shyam-sundar.S-k@amd.com

[ Upstream commit 146b6f6855e7656e8329910606595220c761daac ]

Power source notify handler is getting registered even when none of the PMF feature in enabled leading to a crash.

... [ 22.592162] Call Trace: [ 22.592164] <TASK> [ 22.592164] ? rcu_note_context_switch+0x5e0/0x660 [ 22.592166] ? __warn+0x81/0x130 [ 22.592171] ? rcu_note_context_switch+0x5e0/0x660 [ 22.592172] ? report_bug+0x171/0x1a0 [ 22.592175] ? prb_read_valid+0x1b/0x30 [ 22.592177] ? handle_bug+0x3c/0x80 [ 22.592178] ? exc_invalid_op+0x17/0x70 [ 22.592179] ? asm_exc_invalid_op+0x1a/0x20 [ 22.592182] ? rcu_note_context_switch+0x5e0/0x660 [ 22.592183] ? acpi_ut_delete_object_desc+0x86/0xb0 [ 22.592186] ? acpi_ut_update_ref_count.part.0+0x22d/0x930 [ 22.592187] __schedule+0xc0/0x1410 [ 22.592189] ? ktime_get+0x3c/0xa0 [ 22.592191] ? lapic_next_event+0x1d/0x30 [ 22.592193] ? hrtimer_start_range_ns+0x25b/0x350 [ 22.592196] schedule+0x5e/0xd0 [ 22.592197] schedule_hrtimeout_range_clock+0xbe/0x140 [ 22.592199] ? __pfx_hrtimer_wakeup+0x10/0x10 [ 22.592200] usleep_range_state+0x64/0x90 [ 22.592203] amd_pmf_send_cmd+0x106/0x2a0 [amd_pmf bddfe0fe3712aaa99acce3d5487405c5213c6616] [ 22.592207] amd_pmf_update_slider+0x56/0x1b0 [amd_pmf bddfe0fe3712aaa99acce3d5487405c5213c6616] [ 22.592210] amd_pmf_set_sps_power_limits+0x72/0x80 [amd_pmf bddfe0fe3712aaa99acce3d5487405c5213c6616] [ 22.592213] amd_pmf_pwr_src_notify_call+0x49/0x90 [amd_pmf bddfe0fe3712aaa99acce3d5487405c5213c6616] [ 22.592216] notifier_call_chain+0x5a/0xd0 [ 22.592218] atomic_notifier_call_chain+0x32/0x50 ...

Fix this by moving the registration of source change notify handler only when SPS(Static Slider) is advertised as supported.

Reported-by: Allen Zhong allen@atr.me Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217571 Fixes: 4c71ae414474 ("platform/x86/amd/pmf: Add support SPS PMF feature") Tested-by: Patil Rajesh Reddy Patil.Reddy@amd.com Reviewed-by: Mario Limonciello mario.limonciello@amd.com Signed-off-by: Shyam Sundar S K Shyam-sundar.S-k@amd.com Link: https://lore.kernel.org/r/20230622060309.310001-1-Shyam-sundar.S-k@amd.com Reviewed-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/platform/x86/amd/pmf/core.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c index dc9803e1a4b9b..73d2357e32f8e 100644 --- a/drivers/platform/x86/amd/pmf/core.c +++ b/drivers/platform/x86/amd/pmf/core.c @@ -297,6 +297,8 @@ static void amd_pmf_init_features(struct amd_pmf_dev *dev) /* Enable Static Slider */ if (is_apmf_func_supported(dev, APMF_FUNC_STATIC_SLIDER_GRANULAR)) { amd_pmf_init_sps(dev); + dev->pwr_src_notifier.notifier_call = amd_pmf_pwr_src_notify_call; + power_supply_reg_notifier(&dev->pwr_src_notifier); dev_dbg(dev->dev, "SPS enabled and Platform Profiles registered\n"); }

@@ -315,8 +317,10 @@ static void amd_pmf_init_features(struct amd_pmf_dev *dev)

static void amd_pmf_deinit_features(struct amd_pmf_dev *dev) { - if (is_apmf_func_supported(dev, APMF_FUNC_STATIC_SLIDER_GRANULAR)) + if (is_apmf_func_supported(dev, APMF_FUNC_STATIC_SLIDER_GRANULAR)) { + power_supply_unreg_notifier(&dev->pwr_src_notifier); amd_pmf_deinit_sps(dev); + }

if (is_apmf_func_supported(dev, APMF_FUNC_AUTO_MODE)) { amd_pmf_deinit_auto_mode(dev); @@ -399,9 +403,6 @@ static int amd_pmf_probe(struct platform_device *pdev) apmf_install_handler(dev); amd_pmf_dbgfs_register(dev);

- dev->pwr_src_notifier.notifier_call = amd_pmf_pwr_src_notify_call; - power_supply_reg_notifier(&dev->pwr_src_notifier); - dev_info(dev->dev, "registered PMF device successfully\n");

return 0; @@ -411,7 +412,6 @@ static int amd_pmf_remove(struct platform_device *pdev) { struct amd_pmf_dev *dev = platform_get_drvdata(pdev);

- power_supply_unreg_notifier(&dev->pwr_src_notifier); amd_pmf_deinit_features(dev); apmf_acpi_deinit(dev); amd_pmf_dbgfs_unregister(dev);

From: Maciej Żenczykowski maze@google.com

[ Upstream commit a9628e88776eb7d045cf46467f1afdd0f7fe72ea ]

This reverts commit 1f86123b9749 ("net: align SO_RCVMARK required privileges with SO_MARK") because the reasoning in the commit message is not really correct: SO_RCVMARK is used for 'reading' incoming skb mark (via cmsg), as such it is more equivalent to 'getsockopt(SO_MARK)' which has no priv check and retrieves the socket mark, rather than 'setsockopt(SO_MARK) which sets the socket mark and does require privs.

Additionally incoming skb->mark may already be visible if sysctl_fwmark_reflect and/or sysctl_tcp_fwmark_accept are enabled.

Furthermore, it is easier to block the getsockopt via bpf (either cgroup setsockopt hook, or via syscall filters) then to unblock it if it requires CAP_NET_RAW/ADMIN.

On Android the socket mark is (among other things) used to store the network identifier a socket is bound to. Setting it is privileged, but retrieving it is not. We'd like unprivileged userspace to be able to read the network id of incoming packets (where mark is set via iptables [to be moved to bpf])...

An alternative would be to add another sysctl to control whether setting SO_RCVMARK is privilged or not. (or even a MASK of which bits in the mark can be exposed) But this seems like over-engineering...

Note: This is a non-trivial revert, due to later merged commit e42c7beee71d ("bpf: net: Consider has_current_bpf_ctx() when testing capable() in sk_setsockopt()") which changed both 'ns_capable' into 'sockopt_ns_capable' calls.

Fixes: 1f86123b9749 ("net: align SO_RCVMARK required privileges with SO_MARK") Cc: Larysa Zaremba larysa.zaremba@intel.com Cc: Simon Horman simon.horman@corigine.com Cc: Paolo Abeni pabeni@redhat.com Cc: Eyal Birger eyal.birger@gmail.com Cc: Jakub Kicinski kuba@kernel.org Cc: Eric Dumazet edumazet@google.com Cc: Patrick Rohr prohr@google.com Signed-off-by: Maciej Żenczykowski maze@google.com Reviewed-by: Simon Horman simon.horman@corigine.com Reviewed-by: Kuniyuki Iwashima kuniyu@amazon.com Link: https://lore.kernel.org/r/20230618103130.51628-1-maze@google.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/core/sock.c | 6 ------ 1 file changed, 6 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c index 83f590d8d0850..b021cb9c95ef3 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1355,12 +1355,6 @@ int sk_setsockopt(struct sock *sk, int level, int optname, __sock_set_mark(sk, val); break; case SO_RCVMARK: - if (!sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) && - !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { - ret = -EPERM; - break; - } - sock_valbool_flag(sk, SOCK_RCVMARK, valbool); break;

From: Nicolas Frattaroli frattaroli.nicolas@gmail.com

[ Upstream commit cf9ae4a0077496e8224d68fc88e3df13dd7e5f37 ]

In pre-production prototypes (of which I only know one person having one, Peter Geis), GPIO0 pin A5 was tied to the SDMMC power enable pin on the CM4 connector. On all production models, this is not the case; instead, this pin is used for the nEXTRST signal, and the SDMMC power enable pin is always pulled high.

Since everyone currently using the SOQuartz device trees will want this change, it is made to the tree without splitting the trees into two separate ones of which users will then inevitably choose the wrong one.

This fixes USB and PCIe on a wide variety of CM4IO-compatible boards which use the nEXTRST signal.

Fixes: 5859b5a9c3ac ("arm64: dts: rockchip: add SoQuartz CM4IO dts") Signed-off-by: Nicolas Frattaroli frattaroli.nicolas@gmail.com Link: https://lore.kernel.org/r/20230421152610.21688-1-frattaroli.nicolas@gmail.co... Signed-off-by: Heiko Stuebner heiko@sntech.de Signed-off-by: Sasha Levin sashal@kernel.org --- .../boot/dts/rockchip/rk3566-soquartz-cm4.dts | 18 +++++++----- .../boot/dts/rockchip/rk3566-soquartz.dtsi | 29 +++++++++---------- 2 files changed, 24 insertions(+), 23 deletions(-)

diff --git a/arch/arm64/boot/dts/rockchip/rk3566-soquartz-cm4.dts b/arch/arm64/boot/dts/rockchip/rk3566-soquartz-cm4.dts index e00568a6be5cc..6ba562b922e6c 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-soquartz-cm4.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-soquartz-cm4.dts @@ -28,6 +28,16 @@ regulator-max-microvolt = <5000000>; vin-supply = <&vcc12v_dcin>; }; + + vcc_sd_pwr: vcc-sd-pwr-regulator { + compatible = "regulator-fixed"; + regulator-name = "vcc_sd_pwr"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <&vcc3v3_sys>; + }; };

&gmac1 { @@ -119,13 +129,7 @@ };

&sdmmc0 { - vmmc-supply = <&sdmmc_pwr>; - status = "okay"; -}; - -&sdmmc_pwr { - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; + vmmc-supply = <&vcc_sd_pwr>; status = "okay"; };

diff --git a/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi index 4ceb9a979f6ad..ba56ca2e66c8d 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi @@ -92,16 +92,6 @@ regulator-max-microvolt = <3300000>; vin-supply = <&vcc5v0_sys>; }; - - sdmmc_pwr: sdmmc-pwr-regulator { - compatible = "regulator-fixed"; - enable-active-high; - gpio = <&gpio0 RK_PA5 GPIO_ACTIVE_HIGH>; - pinctrl-names = "default"; - pinctrl-0 = <&sdmmc_pwr_h>; - regulator-name = "sdmmc_pwr"; - status = "disabled"; - }; };

&cpu0 { @@ -143,6 +133,19 @@ status = "disabled"; };

+&gpio0 { + nextrst-hog { + gpio-hog; + /* + * GPIO_ACTIVE_LOW + output-low here means that the pin is set + * to high, because output-low decides the value pre-inversion. + */ + gpios = <RK_PA5 GPIO_ACTIVE_LOW>; + line-name = "nEXTRST"; + output-low; + }; +}; + &gpu { mali-supply = <&vdd_gpu>; status = "okay"; @@ -485,12 +488,6 @@ rockchip,pins = <2 RK_PC2 RK_FUNC_GPIO &pcfg_pull_none>; }; }; - - sdmmc-pwr { - sdmmc_pwr_h: sdmmc-pwr-h { - rockchip,pins = <0 RK_PA5 RK_FUNC_GPIO &pcfg_pull_none>; - }; - }; };

&pmu_io_domains {

From: Jiasheng Jiang jiasheng@iscas.ac.cn

[ Upstream commit c1bcb976d8feb107ff2c12caaf12ac5e70f44d5f ]

Add the missing check for platform_get_irq() and return error code if it fails.

The returned error code will be dealed with in builtin_platform_driver(sifive_gpio_driver) and the driver will not be registered.

Fixes: f52d6d8b43e5 ("gpio: sifive: To get gpio irq offset from device tree data") Signed-off-by: Jiasheng Jiang jiasheng@iscas.ac.cn Signed-off-by: Bartosz Golaszewski bartosz.golaszewski@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpio/gpio-sifive.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpio/gpio-sifive.c b/drivers/gpio/gpio-sifive.c index bc5660f61c570..0f1e1226ebbe8 100644 --- a/drivers/gpio/gpio-sifive.c +++ b/drivers/gpio/gpio-sifive.c @@ -221,8 +221,12 @@ static int sifive_gpio_probe(struct platform_device *pdev) return -ENODEV; }

- for (i = 0; i < ngpio; i++) - chip->irq_number[i] = platform_get_irq(pdev, i); + for (i = 0; i < ngpio; i++) { + ret = platform_get_irq(pdev, i); + if (ret < 0) + return ret; + chip->irq_number[i] = ret; + }

ret = bgpio_init(&chip->gc, dev, 4, chip->base + SIFIVE_GPIO_INPUT_VAL,

From: Maurizio Lombardi mlombard@redhat.com

[ Upstream commit 2a737d3b8c792400118d6cf94958f559de9c5e59 ]

The tpg->np_login_sem is a semaphore that is used to serialize the login process when multiple login threads run concurrently against the same target portal group.

The iscsi_target_locate_portal() function finds the tpg, calls iscsit_access_np() against the np_login_sem semaphore and saves the tpg pointer in conn->tpg;

If iscsi_target_locate_portal() fails, the caller will check for the conn->tpg pointer and, if it's not NULL, then it will assume that iscsi_target_locate_portal() called iscsit_access_np() on the semaphore.

Make sure that conn->tpg gets initialized only if iscsit_access_np() was successful, otherwise iscsit_deaccess_np() may end up being called against a semaphore we never took, allowing more than one thread to access the same tpg.

Signed-off-by: Maurizio Lombardi mlombard@redhat.com Link: https://lore.kernel.org/r/20230508162219.1731964-4-mlombard@redhat.com Reviewed-by: Mike Christie michael.christie@oracle.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/target/iscsi/iscsi_target_nego.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c index ff49c8f3fe241..62b2d0dcfda86 100644 --- a/drivers/target/iscsi/iscsi_target_nego.c +++ b/drivers/target/iscsi/iscsi_target_nego.c @@ -1128,6 +1128,7 @@ int iscsi_target_locate_portal( iscsi_target_set_sock_callbacks(conn);

login->np = np; + conn->tpg = NULL;

login_req = (struct iscsi_login_req *) login->req; payload_length = ntoh24(login_req->dlength); @@ -1195,7 +1196,6 @@ int iscsi_target_locate_portal( */ sessiontype = strncmp(s_buf, DISCOVERY, 9); if (!sessiontype) { - conn->tpg = iscsit_global->discovery_tpg; if (!login->leading_connection) goto get_target;

@@ -1212,9 +1212,11 @@ int iscsi_target_locate_portal( * Serialize access across the discovery struct iscsi_portal_group to * process login attempt. */ + conn->tpg = iscsit_global->discovery_tpg; if (iscsit_access_np(np, conn->tpg) < 0) { iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR, ISCSI_LOGIN_STATUS_SVC_UNAVAILABLE); + conn->tpg = NULL; ret = -1; goto out; }

From: Marc Zyngier maz@kernel.org

[ Upstream commit 8d0f019e4c4f2ee2de81efd9bf1c27e9fb3c0460 ]

Add the missing Set/Way CMOs that apply to tagged memory.

Signed-off-by: Marc Zyngier maz@kernel.org Reviewed-by: Cornelia Huck cohuck@redhat.com Reviewed-by: Steven Price steven.price@arm.com Reviewed-by: Oliver Upton oliver.upton@linux.dev Link: https://lore.kernel.org/r/20230515204601.1270428-2-maz@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/include/asm/sysreg.h | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 7d301700d1a93..3a448ab0924b3 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -111,8 +111,14 @@ #define SB_BARRIER_INSN __SYS_BARRIER_INSN(0, 7, 31)

#define SYS_DC_ISW sys_insn(1, 0, 7, 6, 2) +#define SYS_DC_IGSW sys_insn(1, 0, 7, 6, 4) +#define SYS_DC_IGDSW sys_insn(1, 0, 7, 6, 6) #define SYS_DC_CSW sys_insn(1, 0, 7, 10, 2) +#define SYS_DC_CGSW sys_insn(1, 0, 7, 10, 4) +#define SYS_DC_CGDSW sys_insn(1, 0, 7, 10, 6) #define SYS_DC_CISW sys_insn(1, 0, 7, 14, 2) +#define SYS_DC_CIGSW sys_insn(1, 0, 7, 14, 4) +#define SYS_DC_CIGDSW sys_insn(1, 0, 7, 14, 6)

/* * Automatically generated definitions for system registers, the

From: Hans Verkuil hverkuil-cisco@xs4all.nl

[ Upstream commit fe4526d99e2e06b08bb80316c3a596ea6a807b75 ]

Explicitly disable the CEC adapter in cec_devnode_unregister()

Usually this does not really do anything important, but for drivers that use the CEC pin framework this is needed to properly stop the hrtimer. Without this a crash would happen when such a driver is unloaded with rmmod.

Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Mauro Carvalho Chehab mchehab@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/cec/core/cec-adap.c | 5 ++++- drivers/media/cec/core/cec-core.c | 2 ++ drivers/media/cec/core/cec-priv.h | 1 + 3 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/media/cec/core/cec-adap.c b/drivers/media/cec/core/cec-adap.c index 4f5ab3cae8a71..ac18707fddcd2 100644 --- a/drivers/media/cec/core/cec-adap.c +++ b/drivers/media/cec/core/cec-adap.c @@ -1582,7 +1582,7 @@ static void cec_claim_log_addrs(struct cec_adapter *adap, bool block) * * This function is called with adap->lock held. */ -static int cec_adap_enable(struct cec_adapter *adap) +int cec_adap_enable(struct cec_adapter *adap) { bool enable; int ret = 0; @@ -1592,6 +1592,9 @@ static int cec_adap_enable(struct cec_adapter *adap) if (adap->needs_hpd) enable = enable && adap->phys_addr != CEC_PHYS_ADDR_INVALID;

+ if (adap->devnode.unregistered) + enable = false; + if (enable == adap->is_enabled) return 0;

diff --git a/drivers/media/cec/core/cec-core.c b/drivers/media/cec/core/cec-core.c index af358e901b5f3..7e153c5cad04f 100644 --- a/drivers/media/cec/core/cec-core.c +++ b/drivers/media/cec/core/cec-core.c @@ -191,6 +191,8 @@ static void cec_devnode_unregister(struct cec_adapter *adap) mutex_lock(&adap->lock); __cec_s_phys_addr(adap, CEC_PHYS_ADDR_INVALID, false); __cec_s_log_addrs(adap, NULL, false); + // Disable the adapter (since adap->devnode.unregistered is true) + cec_adap_enable(adap); mutex_unlock(&adap->lock);

cdev_device_del(&devnode->cdev, &devnode->dev); diff --git a/drivers/media/cec/core/cec-priv.h b/drivers/media/cec/core/cec-priv.h index b78df931aa74b..ed1f8c67626bf 100644 --- a/drivers/media/cec/core/cec-priv.h +++ b/drivers/media/cec/core/cec-priv.h @@ -47,6 +47,7 @@ int cec_monitor_pin_cnt_inc(struct cec_adapter *adap); void cec_monitor_pin_cnt_dec(struct cec_adapter *adap); int cec_adap_status(struct seq_file *file, void *priv); int cec_thread_func(void *_adap); +int cec_adap_enable(struct cec_adapter *adap); void __cec_s_phys_addr(struct cec_adapter *adap, u16 phys_addr, bool block); int __cec_s_log_addrs(struct cec_adapter *adap, struct cec_log_addrs *log_addrs, bool block);

From: Osama Muhammad osmtendev@gmail.com

[ Upstream commit 9b9e46aa07273ceb96866b2e812b46f1ee0b8d2f ]

This patch fixes the error checking in nfcsim.c. The DebugFS kernel API is developed in a way that the caller can safely ignore the errors that occur during the creation of DebugFS nodes.

Signed-off-by: Osama Muhammad osmtendev@gmail.com Reviewed-by: Simon Horman simon.horman@corigine.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nfc/nfcsim.c | 4 ---- 1 file changed, 4 deletions(-)

diff --git a/drivers/nfc/nfcsim.c b/drivers/nfc/nfcsim.c index 85bf8d586c707..0f6befe8be1e2 100644 --- a/drivers/nfc/nfcsim.c +++ b/drivers/nfc/nfcsim.c @@ -336,10 +336,6 @@ static struct dentry *nfcsim_debugfs_root; static void nfcsim_debugfs_init(void) { nfcsim_debugfs_root = debugfs_create_dir("nfcsim", NULL); - - if (!nfcsim_debugfs_root) - pr_err("Could not create debugfs entry\n"); - }

static void nfcsim_debugfs_remove(void)

From: Dan Carpenter dan.carpenter@linaro.org

[ Upstream commit 016da9c65fec9f0e78c4909ed9a0f2d567af6775 ]

The "udc" pointer was never set in the probe() function so it will lead to a NULL dereference in udc_pci_remove() when we do:

usb_del_gadget_udc(&udc->gadget);

Signed-off-by: Dan Carpenter dan.carpenter@linaro.org Link: https://lore.kernel.org/r/ZG+A/dNpFWAlCChk@kili Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/usb/gadget/udc/amd5536udc_pci.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/usb/gadget/udc/amd5536udc_pci.c b/drivers/usb/gadget/udc/amd5536udc_pci.c index c80f9bd51b750..a36913ae31f9e 100644 --- a/drivers/usb/gadget/udc/amd5536udc_pci.c +++ b/drivers/usb/gadget/udc/amd5536udc_pci.c @@ -170,6 +170,9 @@ static int udc_pci_probe( retval = -ENODEV; goto err_probe; } + + udc = dev; + return 0;

err_probe:

From: Uday Shankar ushankar@purestorage.com

[ Upstream commit 774a9636514764ddc0d072ae0d1d1c01a47e6ddd ]

When a command completes, we set a flag which will skip sending a keep alive at the next run of nvme_keep_alive_work when TBKAS is on. However, if the command was submitted long ago, it's possible that the controller may have also restarted its keep alive timer (as a result of receiving the command) long ago. The following trace demonstrates the issue, assuming TBKAS is on and KATO = 8 for simplicity:

1. t = 0: submit I/O commands A, B, C, D, E 2. t = 0.5: commands A, B, C, D, E reach controller, restart its keep alive timer 3. t = 1: A completes 4. t = 2: run nvme_keep_alive_work, see recent completion, do nothing 5. t = 3: B completes 6. t = 4: run nvme_keep_alive_work, see recent completion, do nothing 7. t = 5: C completes 8. t = 6: run nvme_keep_alive_work, see recent completion, do nothing 9. t = 7: D completes 10. t = 8: run nvme_keep_alive_work, see recent completion, do nothing 11. t = 9: E completes

At this point, 8.5 seconds have passed without restarting the controller's keep alive timer, so the controller will detect a keep alive timeout.

Fix this by checking the IO start time when deciding to defer sending a keep alive command. Only set comp_seen if the command started after the most recent run of nvme_keep_alive_work. With this change, the completions of B, C, and D will not set comp_seen and the run of nvme_keep_alive_work at t = 4 will send a keep alive.

Reported-by: Costa Sapuntzakis costa@purestorage.com Reported-by: Randy Jennings randyj@purestorage.com Signed-off-by: Uday Shankar ushankar@purestorage.com Reviewed-by: Hannes Reinecke hare@suse.de Reviewed-by: Sagi Grimberg sagi@grimberg.me Reviewed-by: Christoph Hellwig hch@lst.de Signed-off-by: Keith Busch kbusch@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/core.c | 14 +++++++++++++- drivers/nvme/host/nvme.h | 1 + 2 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index a97f2f21c5321..15eb2ee1be66e 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -395,7 +395,16 @@ void nvme_complete_rq(struct request *req) trace_nvme_complete_rq(req); nvme_cleanup_cmd(req);

- if (ctrl->kas) + /* + * Completions of long-running commands should not be able to + * defer sending of periodic keep alives, since the controller + * may have completed processing such commands a long time ago + * (arbitrarily close to command submission time). + * req->deadline - req->timeout is the command submission time + * in jiffies. + */ + if (ctrl->kas && + req->deadline - req->timeout >= ctrl->ka_last_check_time) ctrl->comp_seen = true;

switch (nvme_decide_disposition(req)) { @@ -1235,6 +1244,7 @@ static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq, return RQ_END_IO_NONE; }

+ ctrl->ka_last_check_time = jiffies; ctrl->comp_seen = false; spin_lock_irqsave(&ctrl->lock, flags); if (ctrl->state == NVME_CTRL_LIVE || @@ -1253,6 +1263,8 @@ static void nvme_keep_alive_work(struct work_struct *work) bool comp_seen = ctrl->comp_seen; struct request *rq;

+ ctrl->ka_last_check_time = jiffies; + if ((ctrl->ctratt & NVME_CTRL_ATTR_TBKAS) && comp_seen) { dev_dbg(ctrl->device, "reschedule traffic based keep-alive timer\n"); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 3f82de6060ef7..2aa514c3dfa17 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -323,6 +323,7 @@ struct nvme_ctrl { struct delayed_work ka_work; struct delayed_work failfast_work; struct nvme_command ka_cmd; + unsigned long ka_last_check_time; struct work_struct fw_act_work; unsigned long events;

From: Hans de Goede hdegoede@redhat.com

[ Upstream commit 20a99a291d564a559cc2fd013b4824a3bb3f1db7 ]

Some devices have a wrong entry in their button array which points to a GPIO which is required in another driver, so soc_button_array must not claim it.

A specific example of this is the Lenovo Yoga Book X90F / X90L, where the PNP0C40 home button entry points to a GPIO which is not a home button and which is required by the lenovo-yogabook driver.

Add a DMI quirk table which can specify an ACPI GPIO resource index which should be skipped; and add an entry for the Lenovo Yoga Book X90F / X90L to this new DMI quirk table.

Signed-off-by: Hans de Goede hdegoede@redhat.com Link: https://lore.kernel.org/r/20230414072116.4497-1-hdegoede@redhat.com Signed-off-by: Dmitry Torokhov dmitry.torokhov@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/input/misc/soc_button_array.c | 30 +++++++++++++++++++++++++++ 1 file changed, 30 insertions(+)

diff --git a/drivers/input/misc/soc_button_array.c b/drivers/input/misc/soc_button_array.c index 09489380afda7..e79f5497948b8 100644 --- a/drivers/input/misc/soc_button_array.c +++ b/drivers/input/misc/soc_button_array.c @@ -108,6 +108,27 @@ static const struct dmi_system_id dmi_use_low_level_irq[] = { {} /* Terminating entry */ };

+/* + * Some devices have a wrong entry which points to a GPIO which is + * required in another driver, so this driver must not claim it. + */ +static const struct dmi_system_id dmi_invalid_acpi_index[] = { + { + /* + * Lenovo Yoga Book X90F / X90L, the PNP0C40 home button entry + * points to a GPIO which is not a home button and which is + * required by the lenovo-yogabook driver. + */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Intel Corporation"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "CHERRYVIEW D1 PLATFORM"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "YETI-11"), + }, + .driver_data = (void *)1l, + }, + {} /* Terminating entry */ +}; + /* * Get the Nth GPIO number from the ACPI object. */ @@ -137,6 +158,8 @@ soc_button_device_create(struct platform_device *pdev, struct platform_device *pd; struct gpio_keys_button *gpio_keys; struct gpio_keys_platform_data *gpio_keys_pdata; + const struct dmi_system_id *dmi_id; + int invalid_acpi_index = -1; int error, gpio, irq; int n_buttons = 0;

@@ -154,10 +177,17 @@ soc_button_device_create(struct platform_device *pdev, gpio_keys = (void *)(gpio_keys_pdata + 1); n_buttons = 0;

+ dmi_id = dmi_first_match(dmi_invalid_acpi_index); + if (dmi_id) + invalid_acpi_index = (long)dmi_id->driver_data; + for (info = button_info; info->name; info++) { if (info->autorepeat != autorepeat) continue;

+ if (info->acpi_index == invalid_acpi_index) + continue; + error = soc_button_lookup_gpio(&pdev->dev, info->acpi_index, &gpio, &irq); if (error || irq < 0) { /*

From: Krzysztof Kozlowski krzysztof.kozlowski@linaro.org

[ Upstream commit 16bd455d0897d1b8b7a9aee2ed51d75b14a34563 ]

The WCD938x audio codec Soundwire interface part is not a DAI and does not allow sound-dai-cells:

sc7280-herobrine-crd.dtb: codec@0,4: '#sound-dai-cells' does not match any of the regexes: 'pinctrl-[0-9]+'

Signed-off-by: Krzysztof Kozlowski krzysztof.kozlowski@linaro.org Reviewed-by: Douglas Anderson dianders@chromium.org Reviewed-by: Konrad Dybcio konrad.dybcio@linaro.org Signed-off-by: Bjorn Andersson andersson@kernel.org Link: https://lore.kernel.org/r/20230220095401.64196-2-krzysztof.kozlowski@linaro.... Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/boot/dts/qcom/sc7280-qcard.dtsi | 2 -- 1 file changed, 2 deletions(-)

diff --git a/arch/arm64/boot/dts/qcom/sc7280-qcard.dtsi b/arch/arm64/boot/dts/qcom/sc7280-qcard.dtsi index f7665b3799233..c358abc052eb8 100644 --- a/arch/arm64/boot/dts/qcom/sc7280-qcard.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7280-qcard.dtsi @@ -418,7 +418,6 @@ wcd_rx: codec@0,4 { compatible = "sdw20217010d00"; reg = <0 4>; - #sound-dai-cells = <1>; qcom,rx-port-mapping = <1 2 3 4 5>; }; }; @@ -427,7 +426,6 @@ wcd_tx: codec@0,3 { compatible = "sdw20217010d00"; reg = <0 3>; - #sound-dai-cells = <1>; qcom,tx-port-mapping = <1 2 3 4>; }; };

From: Clark Wang xiaoning.wang@nxp.com

[ Upstream commit 9728fb3ce11729aa8c276825ddf504edeb00611d ]

When all bits of IER are set to 0, we still can observe the lpspi irq events when using DMA mode to transfer data.

So disable irq to avoid the too much irq events.

Signed-off-by: Clark Wang xiaoning.wang@nxp.com Link: https://lore.kernel.org/r/20230505063557.3962220-1-xiaoning.wang@nxp.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/spi/spi-fsl-lpspi.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c index e8c1c8a4c6c82..9e324d72596af 100644 --- a/drivers/spi/spi-fsl-lpspi.c +++ b/drivers/spi/spi-fsl-lpspi.c @@ -905,9 +905,14 @@ static int fsl_lpspi_probe(struct platform_device *pdev) ret = fsl_lpspi_dma_init(&pdev->dev, fsl_lpspi, controller); if (ret == -EPROBE_DEFER) goto out_pm_get; - if (ret < 0) dev_err(&pdev->dev, "dma setup error %d, use pio\n", ret); + else + /* + * disable LPSPI module IRQ when enable DMA mode successfully, + * to prevent the unexpected LPSPI module IRQ events. + */ + disable_irq(irq);

ret = devm_spi_register_controller(&pdev->dev, controller); if (ret < 0) {

From: Herve Codina herve.codina@bootlin.com

[ Upstream commit 8938f75a5e35c597a647c28984a0304da7a33d63 ]

In the error path, a of_node_put() for platform is missing. Just add it.

Signed-off-by: Herve Codina herve.codina@bootlin.com Acked-by: Kuninori Morimoto kuninori.morimoto.gx@renesas.com Link: https://lore.kernel.org/r/20230523151223.109551-9-herve.codina@bootlin.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/generic/simple-card.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c index feb55b66239b8..fbb682747f598 100644 --- a/sound/soc/generic/simple-card.c +++ b/sound/soc/generic/simple-card.c @@ -416,6 +416,7 @@ static int __simple_for_each_link(struct asoc_simple_priv *priv,

if (ret < 0) { of_node_put(codec); + of_node_put(plat); of_node_put(np); goto error; }

From: Krzysztof Kozlowski krzysztof.kozlowski@linaro.org

[ Upstream commit 99e09b9c0ab43346c52f2787ca4e5c4b1798362e ]

Reverse actions in qcom_swrm_startup() error paths to avoid leaking stream memory and keeping runtime PM unbalanced.

Signed-off-by: Krzysztof Kozlowski krzysztof.kozlowski@linaro.org Reviewed-by: Pierre-Louis Bossart pierre-louis.bossart@linux.intel.com Link: https://lore.kernel.org/r/20230517163736.997553-1-krzysztof.kozlowski@linaro... Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/soundwire/qcom.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c index 21c50972047f5..b2eb3090f4b46 100644 --- a/drivers/soundwire/qcom.c +++ b/drivers/soundwire/qcom.c @@ -1090,8 +1090,10 @@ static int qcom_swrm_startup(struct snd_pcm_substream *substream, }

sruntime = sdw_alloc_stream(dai->name); - if (!sruntime) - return -ENOMEM; + if (!sruntime) { + ret = -ENOMEM; + goto err_alloc; + }

ctrl->sruntime[dai->id] = sruntime;

@@ -1101,12 +1103,19 @@ static int qcom_swrm_startup(struct snd_pcm_substream *substream, if (ret < 0 && ret != -ENOTSUPP) { dev_err(dai->dev, "Failed to set sdw stream on %s\n", codec_dai->name); - sdw_release_stream(sruntime); - return ret; + goto err_set_stream; } }

return 0; + +err_set_stream: + sdw_release_stream(sruntime); +err_alloc: + pm_runtime_mark_last_busy(ctrl->dev); + pm_runtime_put_autosuspend(ctrl->dev); + + return ret; }

static void qcom_swrm_shutdown(struct snd_pcm_substream *substream,

From: Sicong Jiang kevin.jiangsc@gmail.com

[ Upstream commit 57d1e8900495cf1751cec74db16fe1a0fe47efbb ]

Thinkpad Neo14 Ryzen Edition uses Ryzen 6800H processor, and adding to quirks list for acp6x will enable internal mic.

Signed-off-by: Sicong Jiang kevin.jiangsc@gmail.com Link: https://lore.kernel.org/r/20230531090635.89565-1-kevin.jiangsc@gmail.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/amd/yc/acp6x-mach.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 84b401b685f7f..c1ca3ceac5f2f 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -171,6 +171,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "21CL"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "21EF"), + } + }, { .driver_data = &acp6x_card, .matches = {

From: Alexander Gordeev agordeev@linux.ibm.com

[ Upstream commit 03c5c83b70dca3729a3eb488e668e5044bd9a5ea ]

Avoid linker error for randomly generated config file that has CONFIG_BRANCH_PROFILE_NONE enabled and make it similar to riscv, x86 and also to commit 4bf3ec384edf ("s390: disable branch profiling for vdso").

Reviewed-by: Vasily Gorbik gor@linux.ibm.com Signed-off-by: Alexander Gordeev agordeev@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/s390/purgatory/Makefile | 1 + 1 file changed, 1 insertion(+)

diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile index d237bc6841cb8..4cbf306b8181f 100644 --- a/arch/s390/purgatory/Makefile +++ b/arch/s390/purgatory/Makefile @@ -26,6 +26,7 @@ KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding KBUILD_CFLAGS += -c -MD -Os -m64 -msoft-float -fno-common KBUILD_CFLAGS += -fno-stack-protector +KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING KBUILD_CFLAGS += $(CLANG_FLAGS) KBUILD_CFLAGS += $(call cc-option,-fno-PIE) KBUILD_AFLAGS := $(filter-out -DCC_USING_EXPOLINE,$(KBUILD_AFLAGS))

From: Sayed, Karimuddin karimuddin.sayed@intel.com

[ Upstream commit 1a93f10c5b12bd766a537b24a50fca5373467303 ]

Add "Intel Reference boad" and "Intel NUC 13" SSID in the alc256. Enable jack headset volume buttons

Reviewed-by: Kai Vehmanen kai.vehmanen@linux.intel.com Signed-off-by: Sayed, Karimuddin karimuddin.sayed@intel.com Signed-off-by: Pierre-Louis Bossart pierre-louis.bossart@linux.intel.com Link: https://lore.kernel.org/r/20230602193812.66768-1-pierre-louis.bossart@linux.... Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/pci/hda/patch_realtek.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 920e44ba998a5..eb049014f87ac 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9594,6 +9594,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10ec, 0x124c, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10ec, 0x1252, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10ec, 0x1254, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), + SND_PCI_QUIRK(0x10ec, 0x12cc, "Intel Reference board", ALC225_FIXUP_HEADSET_JACK), SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE), SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_AMP), @@ -9814,6 +9815,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x8086, 0x2074, "Intel NUC 8", ALC233_FIXUP_INTEL_NUC8_DMIC), SND_PCI_QUIRK(0x8086, 0x2080, "Intel NUC 8 Rugged", ALC256_FIXUP_INTEL_NUC8_RUGGED), SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", ALC256_FIXUP_INTEL_NUC10), + SND_PCI_QUIRK(0x8086, 0x3038, "Intel NUC 13", ALC225_FIXUP_HEADSET_JACK), SND_PCI_QUIRK(0xf111, 0x0001, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE),

#if 0

From: Linus Walleij linus.walleij@linaro.org

[ Upstream commit 4a672d500bfd6bb87092c33d5a2572c3d0a1cf83 ]

Several device tree files get the polarity of the pendown-gpios wrong: this signal is active low. Fix up all incorrect flags, so that operating systems can rely on the flag being correctly set.

Signed-off-by: Linus Walleij linus.walleij@linaro.org Link: https://lore.kernel.org/r/20230510105156.1134320-1-linus.walleij@linaro.org Signed-off-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/am57xx-cl-som-am57x.dts | 2 +- arch/arm/boot/dts/at91sam9261ek.dts | 2 +- arch/arm/boot/dts/imx7d-pico-hobbit.dts | 2 +- arch/arm/boot/dts/imx7d-sdb.dts | 2 +- arch/arm/boot/dts/omap3-cm-t3x.dtsi | 2 +- arch/arm/boot/dts/omap3-devkit8000-lcd-common.dtsi | 2 +- arch/arm/boot/dts/omap3-lilly-a83x.dtsi | 2 +- arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi | 2 +- arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi | 2 +- arch/arm/boot/dts/omap3-pandora-common.dtsi | 2 +- arch/arm/boot/dts/omap5-cm-t54.dts | 2 +- 11 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/arch/arm/boot/dts/am57xx-cl-som-am57x.dts b/arch/arm/boot/dts/am57xx-cl-som-am57x.dts index 2fc9a5d5e0c0d..625b9b311b49d 100644 --- a/arch/arm/boot/dts/am57xx-cl-som-am57x.dts +++ b/arch/arm/boot/dts/am57xx-cl-som-am57x.dts @@ -527,7 +527,7 @@

interrupt-parent = <&gpio1>; interrupts = <31 0>; - pendown-gpio = <&gpio1 31 0>; + pendown-gpio = <&gpio1 31 GPIO_ACTIVE_LOW>;

ti,x-min = /bits/ 16 <0x0>; diff --git a/arch/arm/boot/dts/at91sam9261ek.dts b/arch/arm/boot/dts/at91sam9261ek.dts index 88869ca874d1a..045cb253f23a6 100644 --- a/arch/arm/boot/dts/at91sam9261ek.dts +++ b/arch/arm/boot/dts/at91sam9261ek.dts @@ -156,7 +156,7 @@ compatible = "ti,ads7843"; interrupts-extended = <&pioC 2 IRQ_TYPE_EDGE_BOTH>; spi-max-frequency = <3000000>; - pendown-gpio = <&pioC 2 GPIO_ACTIVE_HIGH>; + pendown-gpio = <&pioC 2 GPIO_ACTIVE_LOW>;

ti,x-min = /bits/ 16 <150>; ti,x-max = /bits/ 16 <3830>; diff --git a/arch/arm/boot/dts/imx7d-pico-hobbit.dts b/arch/arm/boot/dts/imx7d-pico-hobbit.dts index d917dc4f2f227..6ad39dca70096 100644 --- a/arch/arm/boot/dts/imx7d-pico-hobbit.dts +++ b/arch/arm/boot/dts/imx7d-pico-hobbit.dts @@ -64,7 +64,7 @@ interrupt-parent = <&gpio2>; interrupts = <7 0>; spi-max-frequency = <1000000>; - pendown-gpio = <&gpio2 7 0>; + pendown-gpio = <&gpio2 7 GPIO_ACTIVE_LOW>; vcc-supply = <&reg_3p3v>; ti,x-min = /bits/ 16 <0>; ti,x-max = /bits/ 16 <4095>; diff --git a/arch/arm/boot/dts/imx7d-sdb.dts b/arch/arm/boot/dts/imx7d-sdb.dts index f483bc0afe5ea..234e5fc647b22 100644 --- a/arch/arm/boot/dts/imx7d-sdb.dts +++ b/arch/arm/boot/dts/imx7d-sdb.dts @@ -205,7 +205,7 @@ pinctrl-0 = <&pinctrl_tsc2046_pendown>; interrupt-parent = <&gpio2>; interrupts = <29 0>; - pendown-gpio = <&gpio2 29 GPIO_ACTIVE_HIGH>; + pendown-gpio = <&gpio2 29 GPIO_ACTIVE_LOW>; touchscreen-max-pressure = <255>; wakeup-source; }; diff --git a/arch/arm/boot/dts/omap3-cm-t3x.dtsi b/arch/arm/boot/dts/omap3-cm-t3x.dtsi index e61b8a2bfb7de..51baedf1603bd 100644 --- a/arch/arm/boot/dts/omap3-cm-t3x.dtsi +++ b/arch/arm/boot/dts/omap3-cm-t3x.dtsi @@ -227,7 +227,7 @@

interrupt-parent = <&gpio2>; interrupts = <25 0>; /* gpio_57 */ - pendown-gpio = <&gpio2 25 GPIO_ACTIVE_HIGH>; + pendown-gpio = <&gpio2 25 GPIO_ACTIVE_LOW>;

ti,x-min = /bits/ 16 <0x0>; ti,x-max = /bits/ 16 <0x0fff>; diff --git a/arch/arm/boot/dts/omap3-devkit8000-lcd-common.dtsi b/arch/arm/boot/dts/omap3-devkit8000-lcd-common.dtsi index 3decc2d78a6ca..a7f99ae0c1fe9 100644 --- a/arch/arm/boot/dts/omap3-devkit8000-lcd-common.dtsi +++ b/arch/arm/boot/dts/omap3-devkit8000-lcd-common.dtsi @@ -54,7 +54,7 @@

interrupt-parent = <&gpio1>; interrupts = <27 0>; /* gpio_27 */ - pendown-gpio = <&gpio1 27 GPIO_ACTIVE_HIGH>; + pendown-gpio = <&gpio1 27 GPIO_ACTIVE_LOW>;

ti,x-min = /bits/ 16 <0x0>; ti,x-max = /bits/ 16 <0x0fff>; diff --git a/arch/arm/boot/dts/omap3-lilly-a83x.dtsi b/arch/arm/boot/dts/omap3-lilly-a83x.dtsi index c595afe4181d7..d310b5c7bac36 100644 --- a/arch/arm/boot/dts/omap3-lilly-a83x.dtsi +++ b/arch/arm/boot/dts/omap3-lilly-a83x.dtsi @@ -311,7 +311,7 @@ interrupt-parent = <&gpio1>; interrupts = <8 0>; /* boot6 / gpio_8 */ spi-max-frequency = <1000000>; - pendown-gpio = <&gpio1 8 GPIO_ACTIVE_HIGH>; + pendown-gpio = <&gpio1 8 GPIO_ACTIVE_LOW>; vcc-supply = <&reg_vcc3>; pinctrl-names = "default"; pinctrl-0 = <&tsc2048_pins>; diff --git a/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi b/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi index 1d6e88f99eb31..c3570acc35fad 100644 --- a/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi +++ b/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi @@ -149,7 +149,7 @@

interrupt-parent = <&gpio4>; interrupts = <18 0>; /* gpio_114 */ - pendown-gpio = <&gpio4 18 GPIO_ACTIVE_HIGH>; + pendown-gpio = <&gpio4 18 GPIO_ACTIVE_LOW>;

ti,x-min = /bits/ 16 <0x0>; ti,x-max = /bits/ 16 <0x0fff>; diff --git a/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi b/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi index 7e30f9d45790e..d95a0e130058c 100644 --- a/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi +++ b/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi @@ -160,7 +160,7 @@

interrupt-parent = <&gpio4>; interrupts = <18 0>; /* gpio_114 */ - pendown-gpio = <&gpio4 18 GPIO_ACTIVE_HIGH>; + pendown-gpio = <&gpio4 18 GPIO_ACTIVE_LOW>;

ti,x-min = /bits/ 16 <0x0>; ti,x-max = /bits/ 16 <0x0fff>; diff --git a/arch/arm/boot/dts/omap3-pandora-common.dtsi b/arch/arm/boot/dts/omap3-pandora-common.dtsi index 559853764487f..4c3b6bab179cc 100644 --- a/arch/arm/boot/dts/omap3-pandora-common.dtsi +++ b/arch/arm/boot/dts/omap3-pandora-common.dtsi @@ -651,7 +651,7 @@ pinctrl-0 = <&penirq_pins>; interrupt-parent = <&gpio3>; interrupts = <30 IRQ_TYPE_NONE>; /* GPIO_94 */ - pendown-gpio = <&gpio3 30 GPIO_ACTIVE_HIGH>; + pendown-gpio = <&gpio3 30 GPIO_ACTIVE_LOW>; vcc-supply = <&vaux4>;

ti,x-min = /bits/ 16 <0>; diff --git a/arch/arm/boot/dts/omap5-cm-t54.dts b/arch/arm/boot/dts/omap5-cm-t54.dts index ca759b7b8a580..e62ea8b6d53fd 100644 --- a/arch/arm/boot/dts/omap5-cm-t54.dts +++ b/arch/arm/boot/dts/omap5-cm-t54.dts @@ -354,7 +354,7 @@

interrupt-parent = <&gpio1>; interrupts = <15 0>; /* gpio1_wk15 */ - pendown-gpio = <&gpio1 15 GPIO_ACTIVE_HIGH>; + pendown-gpio = <&gpio1 15 GPIO_ACTIVE_LOW>;

ti,x-min = /bits/ 16 <0x0>;

From: Inki Dae inki.dae@samsung.com

[ Upstream commit 4a059559809fd1ddbf16f847c4d2237309c08edf ]

Fix a wrong error return by dropping an error return.

When vidi driver is remvoed, if ctx->raw_edid isn't same as fake_edid_info then only what we have to is to free ctx->raw_edid so that driver removing can work correctly - it's not an error case.

Signed-off-by: Inki Dae inki.dae@samsung.com Reviewed-by: Andi Shyti andi.shyti@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/exynos/exynos_drm_vidi.c | 2 -- 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c index 4d56c8c799c5a..f5e1adfcaa514 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c @@ -469,8 +469,6 @@ static int vidi_remove(struct platform_device *pdev) if (ctx->raw_edid != (struct edid *)fake_edid_info) { kfree(ctx->raw_edid); ctx->raw_edid = NULL; - - return -EINVAL; }

component_del(&pdev->dev, &vidi_component_ops);

From: Min Li lm0963hack@gmail.com

[ Upstream commit 982b173a6c6d9472730c3116051977e05d17c8c5 ]

Userspace can race to free the gobj(robj converted from), robj should not be accessed again after drm_gem_object_put, otherwith it will result in use-after-free.

Reviewed-by: Christian König christian.koenig@amd.com Signed-off-by: Min Li lm0963hack@gmail.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/radeon/radeon_gem.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index 261fcbae88d78..75d79c3110389 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -459,7 +459,6 @@ int radeon_gem_set_domain_ioctl(struct drm_device *dev, void *data, struct radeon_device *rdev = dev->dev_private; struct drm_radeon_gem_set_domain *args = data; struct drm_gem_object *gobj; - struct radeon_bo *robj; int r;

/* for now if someone requests domain CPU - @@ -472,13 +471,12 @@ int radeon_gem_set_domain_ioctl(struct drm_device *dev, void *data, up_read(&rdev->exclusive_lock); return -ENOENT; } - robj = gem_to_radeon_bo(gobj);

r = radeon_gem_set_domain(gobj, args->read_domains, args->write_domain);

drm_gem_object_put(gobj); up_read(&rdev->exclusive_lock); - r = radeon_gem_handle_lockup(robj->rdev, r); + r = radeon_gem_handle_lockup(rdev, r); return r; }