May 2024 - Linux-stable-mirror

[PATCH v6] can: mcp251xfd: fix infinite loop when xmit fails

by Vitor Soares

From: Vitor Soares <vitor.soares(a)toradex.com> When the mcp251xfd_start_xmit() function fails, the driver stops processing messages, and the interrupt routine does not return, running indefinitely even after killing the running application. Error messages: [ 441.298819] mcp251xfd spi2.0 can0: ERROR in mcp251xfd_start_xmit: -16 [ 441.306498] mcp251xfd spi2.0 can0: Transmit Event FIFO buffer not empty. (seq=0x000017c7, tef_tail=0x000017cf, tef_head=0x000017d0, tx_head=0x000017d3). ... and repeat forever. The issue can be triggered when multiple devices share the same SPI interface. And there is concurrent access to the bus. The problem occurs because tx_ring->head increments even if mcp251xfd_start_xmit() fails. Consequently, the driver skips one TX package while still expecting a response in mcp251xfd_handle_tefif_one(). This patch resolves the issue by starting a workqueue to write the tx obj synchronously if err = -EBUSY. In case of another error, it decrements tx_ring->head, removes skb from the echo stack, and drops the message. Fixes: 55e5b97f003e ("can: mcp25xxfd: add driver for Microchip MCP25xxFD SPI CAN") Cc: stable(a)vger.kernel.org Signed-off-by: Vitor Soares <vitor.soares(a)toradex.com> --- v5->v6 - Move alloc/destroy workqueue to open()/stop() callbacks. - Change workqueue to workqueue ordered. - Return NETDEV_TX_BUSY if the worker is busy, replacing the previouse priv->tx_work_obj = NULL. With this change, setting priv->tx_work_obj = NULL is not necessary anymore. V4->V5: - Start a workqueue to write tx obj with spi_sync() when spi_async() == -EBUSY. V3->V4: - Leave can_put_echo_skb() and stop the queue if needed, before mcp251xfd_tx_obj_write(). - Re-sync head and remove echo skb if mcp251xfd_tx_obj_write() fails. - Revert -> return NETDEV_TX_BUSY if mcp251xfd_tx_obj_write() == -EBUSY. V2->V3: - Add tx_dropped stats. - netdev_sent_queue() only if can_put_echo_skb() succeed. V1->V2: - Return NETDEV_TX_BUSY if mcp251xfd_tx_obj_write() == -EBUSY. - Rework the commit message to address the change above. - Change can_put_echo_skb() to be called after mcp251xfd_tx_obj_write() succeed. Otherwise, we get Kernel NULL pointer dereference error. .../net/can/spi/mcp251xfd/mcp251xfd-core.c | 14 ++++- drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c | 55 ++++++++++++++++--- drivers/net/can/spi/mcp251xfd/mcp251xfd.h | 5 ++ 3 files changed, 65 insertions(+), 9 deletions(-) diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c index 1d9057dc44f2..bf1589aef1fc 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c @@ -1618,11 +1618,20 @@ static int mcp251xfd_open(struct net_device *ndev) clear_bit(MCP251XFD_FLAGS_DOWN, priv->flags); can_rx_offload_enable(&priv->offload); + priv->wq = alloc_ordered_workqueue("%s-mcp251xfd_wq", + WQ_FREEZABLE | WQ_MEM_RECLAIM, + dev_name(&spi->dev)); + if (!priv->wq) { + err = -ENOMEM; + goto out_can_rx_offload_disable; + } + INIT_WORK(&priv->tx_work, mcp251xfd_tx_obj_write_sync); + err = request_threaded_irq(spi->irq, NULL, mcp251xfd_irq, IRQF_SHARED | IRQF_ONESHOT, dev_name(&spi->dev), priv); if (err) - goto out_can_rx_offload_disable; + goto out_destroy_workqueue; err = mcp251xfd_chip_interrupts_enable(priv); if (err) @@ -1634,6 +1643,8 @@ static int mcp251xfd_open(struct net_device *ndev) out_free_irq: free_irq(spi->irq, priv); + out_destroy_workqueue: + destroy_workqueue(priv->wq); out_can_rx_offload_disable: can_rx_offload_disable(&priv->offload); set_bit(MCP251XFD_FLAGS_DOWN, priv->flags); @@ -1661,6 +1672,7 @@ static int mcp251xfd_stop(struct net_device *ndev) hrtimer_cancel(&priv->tx_irq_timer); mcp251xfd_chip_interrupts_disable(priv); free_irq(ndev->irq, priv); + destroy_workqueue(priv->wq); can_rx_offload_disable(&priv->offload); mcp251xfd_timestamp_stop(priv); mcp251xfd_chip_stop(priv, CAN_STATE_STOPPED); diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c index 160528d3cc26..b1de8052a45c 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c @@ -131,6 +131,39 @@ mcp251xfd_tx_obj_from_skb(const struct mcp251xfd_priv *priv, tx_obj->xfer[0].len = len; } +static void mcp251xfd_tx_failure_drop(const struct mcp251xfd_priv *priv, + struct mcp251xfd_tx_ring *tx_ring, + int err) +{ + struct net_device *ndev = priv->ndev; + struct net_device_stats *stats = &ndev->stats; + unsigned int frame_len = 0; + u8 tx_head; + + tx_ring->head--; + stats->tx_dropped++; + tx_head = mcp251xfd_get_tx_head(tx_ring); + can_free_echo_skb(ndev, tx_head, &frame_len); + netdev_completed_queue(ndev, 1, frame_len); + netif_wake_queue(ndev); + + if (net_ratelimit()) + netdev_err(priv->ndev, "ERROR in %s: %d\n", __func__, err); +} + +void mcp251xfd_tx_obj_write_sync(struct work_struct *work) +{ + struct mcp251xfd_priv *priv = container_of(work, struct mcp251xfd_priv, + tx_work); + struct mcp251xfd_tx_obj *tx_obj = priv->tx_work_obj; + struct mcp251xfd_tx_ring *tx_ring = priv->tx; + int err; + + err = spi_sync(priv->spi, &tx_obj->msg); + if (err) + mcp251xfd_tx_failure_drop(priv, tx_ring, err); +} + static int mcp251xfd_tx_obj_write(const struct mcp251xfd_priv *priv, struct mcp251xfd_tx_obj *tx_obj) { @@ -162,6 +195,11 @@ static bool mcp251xfd_tx_busy(const struct mcp251xfd_priv *priv, return false; } +static bool mcp251xfd_work_busy(struct work_struct *work) +{ + return work_busy(work); +} + netdev_tx_t mcp251xfd_start_xmit(struct sk_buff *skb, struct net_device *ndev) { @@ -175,7 +213,8 @@ netdev_tx_t mcp251xfd_start_xmit(struct sk_buff *skb, if (can_dev_dropped_skb(ndev, skb)) return NETDEV_TX_OK; - if (mcp251xfd_tx_busy(priv, tx_ring)) + if (mcp251xfd_tx_busy(priv, tx_ring) || + mcp251xfd_work_busy(&priv->tx_work)) return NETDEV_TX_BUSY; tx_obj = mcp251xfd_get_tx_obj_next(tx_ring); @@ -193,13 +232,13 @@ netdev_tx_t mcp251xfd_start_xmit(struct sk_buff *skb, netdev_sent_queue(priv->ndev, frame_len); err = mcp251xfd_tx_obj_write(priv, tx_obj); - if (err) - goto out_err; - - return NETDEV_TX_OK; - - out_err: - netdev_err(priv->ndev, "ERROR in %s: %d\n", __func__, err); + if (err == -EBUSY) { + netif_stop_queue(ndev); + priv->tx_work_obj = tx_obj; + queue_work(priv->wq, &priv->tx_work); + } else if (err) { + mcp251xfd_tx_failure_drop(priv, tx_ring, err); + } return NETDEV_TX_OK; } diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h index 24510b3b8020..b35bfebd23f2 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h @@ -633,6 +633,10 @@ struct mcp251xfd_priv { struct mcp251xfd_rx_ring *rx[MCP251XFD_FIFO_RX_NUM]; struct mcp251xfd_tx_ring tx[MCP251XFD_FIFO_TX_NUM]; + struct workqueue_struct *wq; + struct work_struct tx_work; + struct mcp251xfd_tx_obj *tx_work_obj; + DECLARE_BITMAP(flags, __MCP251XFD_FLAGS_SIZE__); u8 rx_ring_num; @@ -952,6 +956,7 @@ void mcp251xfd_skb_set_timestamp(const struct mcp251xfd_priv *priv, void mcp251xfd_timestamp_init(struct mcp251xfd_priv *priv); void mcp251xfd_timestamp_stop(struct mcp251xfd_priv *priv); +void mcp251xfd_tx_obj_write_sync(struct work_struct *work); netdev_tx_t mcp251xfd_start_xmit(struct sk_buff *skb, struct net_device *ndev); -- 2.34.1

11 months

4
3
0 0

[PATCH v2] i2c: ocores: set IACK bit after core is enabled

by Grygorii Tertychnyi

Setting IACK bit when core is disabled does not clear the "Interrupt Flag" bit in the status register, and the interrupt remains pending. Sometimes it causes failure for the very first message transfer, that is usually a device probe. Hence, set IACK bit after core is enabled to clear pending interrupt. Fixes: 18f98b1e3147 ("[PATCH] i2c: New bus driver for the OpenCores I2C controller") Signed-off-by: Grygorii Tertychnyi <grygorii.tertychnyi(a)leica-geosystems.com> Acked-by: Peter Korsgaard <peter(a)korsgaard.com> Cc: stable(a)vger.kernel.org --- V1 -> V2: Added "Acked-by:", "Fixes:" and "Cc:" tags drivers/i2c/busses/i2c-ocores.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-ocores.c b/drivers/i2c/busses/i2c-ocores.c index e106af83cef4..350ccfbe8634 100644 --- a/drivers/i2c/busses/i2c-ocores.c +++ b/drivers/i2c/busses/i2c-ocores.c @@ -442,8 +442,8 @@ static int ocores_init(struct device *dev, struct ocores_i2c *i2c) oc_setreg(i2c, OCI2C_PREHIGH, prescale >> 8); /* Init the device */ - oc_setreg(i2c, OCI2C_CMD, OCI2C_CMD_IACK); oc_setreg(i2c, OCI2C_CONTROL, ctrl | OCI2C_CTRL_EN); + oc_setreg(i2c, OCI2C_CMD, OCI2C_CMD_IACK); return 0; } -- 2.43.0

11 months

5
5
0 0

[PATCH AUTOSEL 6.9 01/23] drm/amd/display: Exit idle optimizations before HDCP execution

by Sasha Levin

From: Nicholas Kazlauskas <nicholas.kazlauskas(a)amd.com> [ Upstream commit f30a3bea92bdab398531129d187629fb1d28f598 ] [WHY] PSP can access DCN registers during command submission and we need to ensure that DCN is not in PG before doing so. [HOW] Add a callback to DM to lock and notify DC for idle optimization exit. It can't be DC directly because of a potential race condition with the link protection thread and the rest of DM operation. Cc: Mario Limonciello <mario.limonciello(a)amd.com> Cc: Alex Deucher <alexander.deucher(a)amd.com> Reviewed-by: Charlene Liu <charlene.liu(a)amd.com> Acked-by: Alex Hung <alex.hung(a)amd.com> Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas(a)amd.com> Tested-by: Daniel Wheeler <daniel.wheeler(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c | 10 ++++++++++ drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h | 8 ++++++++ 2 files changed, 18 insertions(+) diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c index 5e01c6e24cbc8..9a5a1726acaf8 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c @@ -88,6 +88,14 @@ static uint8_t is_cp_desired_hdcp2(struct mod_hdcp *hdcp) !hdcp->connection.is_hdcp2_revoked; } +static void exit_idle_optimizations(struct mod_hdcp *hdcp) +{ + struct mod_hdcp_dm *dm = &hdcp->config.dm; + + if (dm->funcs.exit_idle_optimizations) + dm->funcs.exit_idle_optimizations(dm->handle); +} + static enum mod_hdcp_status execution(struct mod_hdcp *hdcp, struct mod_hdcp_event_context *event_ctx, union mod_hdcp_transition_input *input) @@ -543,6 +551,8 @@ enum mod_hdcp_status mod_hdcp_process_event(struct mod_hdcp *hdcp, memset(&event_ctx, 0, sizeof(struct mod_hdcp_event_context)); event_ctx.event = event; + exit_idle_optimizations(hdcp); + /* execute and transition */ exec_status = execution(hdcp, &event_ctx, &hdcp->auth.trans_input); trans_status = transition( diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h index a4d344a4db9e1..cdb17b093f2b8 100644 --- a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h +++ b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h @@ -156,6 +156,13 @@ struct mod_hdcp_ddc { } funcs; }; +struct mod_hdcp_dm { + void *handle; + struct { + void (*exit_idle_optimizations)(void *handle); + } funcs; +}; + struct mod_hdcp_psp { void *handle; void *funcs; @@ -272,6 +279,7 @@ struct mod_hdcp_display_query { struct mod_hdcp_config { struct mod_hdcp_psp psp; struct mod_hdcp_ddc ddc; + struct mod_hdcp_dm dm; uint8_t index; }; -- 2.43.0

11 months

4
27
0 0

[PATCH AUTOSEL 6.9 01/35] ssb: Fix potential NULL pointer dereference in ssb_device_uevent()

by Sasha Levin

From: Rand Deeb <rand.sec96(a)gmail.com> [ Upstream commit 789c17185fb0f39560496c2beab9b57ce1d0cbe7 ] The ssb_device_uevent() function first attempts to convert the 'dev' pointer to 'struct ssb_device *'. However, it mistakenly dereferences 'dev' before performing the NULL check, potentially leading to a NULL pointer dereference if 'dev' is NULL. To fix this issue, move the NULL check before dereferencing the 'dev' pointer, ensuring that the pointer is valid before attempting to use it. Found by Linux Verification Center (linuxtesting.org) with SVACE. Signed-off-by: Rand Deeb <rand.sec96(a)gmail.com> Signed-off-by: Kalle Valo <kvalo(a)kernel.org> Link: https://msgid.link/20240306123028.164155-1-rand.sec96@gmail.com Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/ssb/main.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c index 9f30e0edadfe2..bdb6595ffd2d5 100644 --- a/drivers/ssb/main.c +++ b/drivers/ssb/main.c @@ -341,11 +341,13 @@ static int ssb_bus_match(struct device *dev, struct device_driver *drv) static int ssb_device_uevent(const struct device *dev, struct kobj_uevent_env *env) { - const struct ssb_device *ssb_dev = dev_to_ssb_dev(dev); + const struct ssb_device *ssb_dev; if (!dev) return -ENODEV; + ssb_dev = dev_to_ssb_dev(dev); + return add_uevent_var(env, "MODALIAS=ssb:v%04Xid%04Xrev%02X", ssb_dev->id.vendor, ssb_dev->id.coreid, -- 2.43.0

11 months

3
38
0 0

[PATCH AUTOSEL 6.9 01/15] fs/writeback: bail out if there is no more inodes for IO and queued once

by Sasha Levin

From: Kemeng Shi <shikemeng(a)huaweicloud.com> [ Upstream commit d92109891f21cf367caa2cc6dff11a4411d917f4 ] For case there is no more inodes for IO in io list from last wb_writeback, We may bail out early even there is inode in dirty list should be written back. Only bail out when we queued once to avoid missing dirtied inode. This is from code reading... Signed-off-by: Kemeng Shi <shikemeng(a)huaweicloud.com> Link: https://lore.kernel.org/r/20240228091958.288260-3-shikemeng@huaweicloud.com Reviewed-by: Jan Kara <jack(a)suse.cz> [brauner(a)kernel.org: fold in memory corruption fix from Jan in [1]] Link: https://lore.kernel.org/r/20240405132346.bid7gibby3lxxhez@quack3 [1] Signed-off-by: Christian Brauner <brauner(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- fs/fs-writeback.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index e4f17c53ddfcf..d31853032a931 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -2069,6 +2069,7 @@ static long wb_writeback(struct bdi_writeback *wb, struct inode *inode; long progress; struct blk_plug plug; + bool queued = false; blk_start_plug(&plug); for (;;) { @@ -2111,8 +2112,10 @@ static long wb_writeback(struct bdi_writeback *wb, dirtied_before = jiffies; trace_writeback_start(wb, work); - if (list_empty(&wb->b_io)) + if (list_empty(&wb->b_io)) { queue_io(wb, work, dirtied_before); + queued = true; + } if (work->sb) progress = writeback_sb_inodes(work->sb, wb, work); else @@ -2127,7 +2130,7 @@ static long wb_writeback(struct bdi_writeback *wb, * mean the overall work is done. So we keep looping as long * as made some progress on cleaning pages or inodes. */ - if (progress) { + if (progress || !queued) { spin_unlock(&wb->list_lock); continue; } -- 2.43.0

11 months

3
18
0 0

Candidates for stable v6.9..v6.10-rc1 Use After Free

by Ronnie Sahlberg

These commits reference use.after.free between v6.9 and v6.10-rc1 These commits are not, yet, in stable/linux-rolling-stable. Let me know if you would rather me compare to a different repo/branch. The list has been manually pruned to only contain commits that look like actual issues. If they contain a Fixes line it has been verified that at least one of the commits that the Fixes tag(s) reference is in stable/linux-rolling-stable 90e823498881fb8a91d8 5c9c5d7f26acc2c669c1 573601521277119f2e2b f88da7fbf665ffdcbf5b 47a92dfbe01f41bcbf35 5bc9de065b8bb9b8dd87 5f204051d998ec3d7306 be84f32bb2c981ca6709 88ce0106a1f603bf360c -- Ronnie Sahlberg [Principal Software Engineer, Linux] P 775 384 8203 | E [email] | W ciq.com

11 months

2
1
0 0

Bug in Kernel 6.8.x, 6.9.x Causing Trace/Panic During Shutdown/Reboot

by Ilkka Naulapää

Greetings fellas, I have encountered a critical bug in the Linux vanilla kernel that leads to a kernel panic during the shutdown or reboot process. The issue arises after all services, including `journald`, have been stopped. As a result, the machine fails to complete the shutdown or reboot procedure, effectively causing the system to hang and not shut down or reboot. Here are the details of the issue: - Affected Versions: Before kernel version 6.8.10, the bug caused a quick display of a kernel trace dump before the shutdown/reboot completed. Starting from version 6.8.10 and continuing into version 6.9.0 and 6.9.1, this issue has escalated to a kernel panic, preventing the shutdown or reboot from completing and leaving the machine stuck. - Symptoms: - In normal shutdown/reboot scenarios, the kernel trace dump briefly appears as the last message on the screen. - In rescue mode, the kernel panic message is displayed. Normally it is not shown. Since `journald` is stopped before this issue occurs, no textual logs are available. However, I have captured two pictures illustrating these related issues, which I am attaching to this email for your reference. Also added my custom kernel config. Thank you for your attention to this matter. Please let me know if any additional information is required to assist in diagnosing and resolving this bug. Best regards, Ilkka Naulapää

11 months

4
23
0 0

[PATCH v4] media: venus: fix use after free in vdec_close

by Dikshita Agarwal

There appears to be a possible use after free with vdec_close(). The firmware will add buffer release work to the work queue through HFI callbacks as a normal part of decoding. Randomly closing the decoder device from userspace during normal decoding can incur a read after free for inst. Fix it by cancelling the work in vdec_close. Cc: stable(a)vger.kernel.org Fixes: af2c3834c8ca ("[media] media: venus: adding core part and helper functions") Signed-off-by: Dikshita Agarwal <quic_dikshita(a)quicinc.com> --- Changes since v3: - Fixed style issue with fixes tag Changes since v2: - Fixed email id Changes since v1: - Added fixes and stable tags drivers/media/platform/qcom/venus/vdec.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c index 29130a9..56f8a25 100644 --- a/drivers/media/platform/qcom/venus/vdec.c +++ b/drivers/media/platform/qcom/venus/vdec.c @@ -1747,6 +1747,7 @@ static int vdec_close(struct file *file) vdec_pm_get(inst); + cancel_work_sync(&inst->delayed_process_work); v4l2_m2m_ctx_release(inst->m2m_ctx); v4l2_m2m_release(inst->m2m_dev); vdec_ctrl_deinit(inst); -- 2.7.4

11 months, 1 week

2
1
0 0

[PATCH AUTOSEL 5.10 1/7] drm/amd/display: Exit idle optimizations before HDCP execution

by Sasha Levin

From: Nicholas Kazlauskas <nicholas.kazlauskas(a)amd.com> [ Upstream commit f30a3bea92bdab398531129d187629fb1d28f598 ] [WHY] PSP can access DCN registers during command submission and we need to ensure that DCN is not in PG before doing so. [HOW] Add a callback to DM to lock and notify DC for idle optimization exit. It can't be DC directly because of a potential race condition with the link protection thread and the rest of DM operation. Cc: Mario Limonciello <mario.limonciello(a)amd.com> Cc: Alex Deucher <alexander.deucher(a)amd.com> Reviewed-by: Charlene Liu <charlene.liu(a)amd.com> Acked-by: Alex Hung <alex.hung(a)amd.com> Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas(a)amd.com> Tested-by: Daniel Wheeler <daniel.wheeler(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c | 10 ++++++++++ drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h | 8 ++++++++ 2 files changed, 18 insertions(+) diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c index fa8aeec304ef4..c39cb4b6767cf 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c @@ -86,6 +86,14 @@ static uint8_t is_cp_desired_hdcp2(struct mod_hdcp *hdcp) !hdcp->connection.is_hdcp2_revoked; } +static void exit_idle_optimizations(struct mod_hdcp *hdcp) +{ + struct mod_hdcp_dm *dm = &hdcp->config.dm; + + if (dm->funcs.exit_idle_optimizations) + dm->funcs.exit_idle_optimizations(dm->handle); +} + static enum mod_hdcp_status execution(struct mod_hdcp *hdcp, struct mod_hdcp_event_context *event_ctx, union mod_hdcp_transition_input *input) @@ -448,6 +456,8 @@ enum mod_hdcp_status mod_hdcp_process_event(struct mod_hdcp *hdcp, memset(&event_ctx, 0, sizeof(struct mod_hdcp_event_context)); event_ctx.event = event; + exit_idle_optimizations(hdcp); + /* execute and transition */ exec_status = execution(hdcp, &event_ctx, &hdcp->auth.trans_input); trans_status = transition( diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h index eed560eecbab4..fb195276fb704 100644 --- a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h +++ b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h @@ -143,6 +143,13 @@ struct mod_hdcp_ddc { } funcs; }; +struct mod_hdcp_dm { + void *handle; + struct { + void (*exit_idle_optimizations)(void *handle); + } funcs; +}; + struct mod_hdcp_psp { void *handle; void *funcs; @@ -252,6 +259,7 @@ struct mod_hdcp_display_query { struct mod_hdcp_config { struct mod_hdcp_psp psp; struct mod_hdcp_ddc ddc; + struct mod_hdcp_dm dm; uint8_t index; }; -- 2.43.0

11 months, 1 week

2
7
0 0

Re: Kernel 5.15.150 black screen with AMD Raven/Picasso GPU

by Armin Wolf

Am 23.05.24 um 15:13 schrieb Barry Kauler: > On Wed, May 22, 2024 at 12:58 AM Armin Wolf <W_Armin(a)gmx.de> wrote: >> Am 20.05.24 um 18:22 schrieb Alex Deucher: >> >>> On Sat, May 18, 2024 at 8:17 PM Armin Wolf <W_Armin(a)gmx.de> wrote: >>>> Am 17.05.24 um 03:30 schrieb Barry Kauler: >>>> >>>>> Armin, Yifan, Prike, >>>>> I will top-post, so you don't have to scroll down. >>>>> After identifying the commit that causes black screen with my gpu, I >>>>> posted the result to you guys, on May 9. >>>>> It is now May 17 and no reply. >>>>> OK, I have now created a patch that reverts Yifan's commit, compiled >>>>> 5.15.158, and my gpu now works. >>>>> Note, the radeon module is not loaded, so it is not a factor. >>>>> I'm not a kernel developer. I have identified the culprit and it is up >>>>> to you guys to fix it, Yifan especially, as you are the person who has >>>>> created the regression. >>>>> I will attach my patch. >>>>> Regards, >>>>> Barry Kauler >>>> Hi, >>>> >>>> sorry for not responding to your findings. I normally do not work with GPU drivers, >>>> so i hoped one of the amdgpu developers would handle this. >>>> >>>> I CCeddri-devel(a)lists.freedesktop.org and amd-gfx(a)lists.freedesktop.org so that other >>>> amdgpu developers hear from this issue. >>>> >>>> Thanks you for you persistence in finding the offending commit. >>> Likely this patch should not have been ported to 5.15 in the first >>> place. The IOMMU requirements have been dropped from the driver for >>> the last few kernel versions so it is no longer relevant on newer >>> kernels. >>> >>> Alex >> Barry, can you verify that the latest upstream kernel works on you device? >> If yes, then the commit itself is ok and just the backporting itself was wrong. >> >> Thanks, >> Armin Wolf > Armin, > The unmodified 6.8.1 kernel works ok. > I presume that patch was applied long before 6.8.1 got released and > only got backported to 5.15.x recently. > > Regards, > Barry > Great to hear, that means we only have to revert commit 56b522f46681 ("drm/amdgpu: init iommu after amdkfd device init") from the 5.15.y series. I CCed the stable mailing list so that they can revert the offending commit. Thanks, Armin Wolf >>>> Armin Wolf >>>> >>>>> On Thu, May 9, 2024 at 4:08 PM Barry Kauler <bkauler(a)gmail.com> wrote: >>>>>> On Fri, May 3, 2024 at 9:03 PM Armin Wolf <W_Armin(a)gmx.de> wrote: >>>>>>>> ... >>>>>>>> # lspci | grep VGA >>>>>>>> 05:00.0 VGA compatible controller: Advanced Micro Devices, Inc. >>>>>>>> [AMD/ATI] Picasso/Raven 2 [Radeon Vega Series / Radeon Vega Mobile >>>>>>>> Series] (rev c2) >>>>>>>> 05:00.7 Non-VGA unclassified device: Advanced Micro Devices, Inc. >>>>>>>> [AMD] Raven/Raven2/Renoir Non-Sensor Fusion Hub KMDF driver >>>>>>>> >>>>>>>> # lspci -n -k >>>>>>>> ... >>>>>>>> 05:00.0 0300: 1002:15d8 (rev c2) >>>>>>>> Subsystem: 1025:1456 >>>>>>>> Kernel driver in use: amdgpu >>>>>>>> Kernel modules: amdgpu >>>>>>>> ... >>>>>>> thanks for informing us of this regression. Since there are four commits affecting >>>>>>> amdgpu in 5.15.150, i suggest that you use "git bisect" to find the faulty commits, >>>>>>> see https://docs.kernel.org/admin-guide/bug-bisect.html for details. >>>>>>> >>>>>>> I think you can speed up the bisecting process by limiting yourself to the AMD DRM >>>>>>> driver directory with "git bisect start -- drivers/gpu/drm/amd", take a look at the >>>>>>> man page of "git bisect" for details. >>>>>>> >>>>>>> Thanks, >>>>>>> Armin Wolf >>>>>> Armin, >>>>>> Thanks for the advice. I am unfamiliar with git on the commandline. >>>>>> Previously only used SmartGit gui. >>>>>> EasyOS requires aufs patch, and for a few days tried to figure out how >>>>>> to use that with git bisect, then gave up. Changed to testing with my >>>>>> "QV" distro, which is more conventional, doesn't need any kernel >>>>>> patches. Managed to get it down to one commit. Here are the steps I >>>>>> followed: >>>>>> >>>>>> # git clone git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable.git >>>>>> # cd linux-stable >>>>>> # git tag -l | grep '5\.15\.150' >>>>>> v5.15.150 >>>>>> # git checkout -b my5.15.150 v5.15.150 >>>>>> Updating files: 100% (65776/65776), done. >>>>>> Switched to a new branch 'my5.15.150' >>>>>> >>>>>> Copied in my .config then... >>>>>> >>>>>> # make menuconfig >>>>>> # git bisect start -- drivers/gpu/drm/amd >>>>>> # git bisect bad >>>>>> # git bisect good v5.15.149 >>>>>> Bisecting: 1 revision left to test after this (roughly 1 step) >>>>>> [b9a61ee2bb2704e42516e3da962f99dfa98f3b20] drm/amdgpu: reset gpu for >>>>>> s3 suspend abort case >>>>>> # make >>>>>> # rm -rf /boot2 >>>>>> # mkdir -p /boot2/lib/modules >>>>>> # make INSTALL_MOD_STRIP=1 INSTALL_MOD_PATH=/boot2 modules_install >>>>>> # cp arch/x86/boot/bzImage /boot2/vmlinuz >>>>>> # sync >>>>>> ...QV on Acer laptop, with amdgpu, works! >>>>>> # git bisect good >>>>>> Bisecting: 0 revisions left to test after this (roughly 0 steps) >>>>>> [56b522f4668167096a50c39446d6263c96219f5f] drm/amdgpu: init iommu >>>>>> after amdkfd device init >>>>>> # make >>>>>> # mkdir -p /boot2/lib/modules >>>>>> # make INSTALL_MOD_STRIP=1 INSTALL_MOD_PATH=/boot2 modules_install >>>>>> # cp arch/x86/boot/bzImage /boot2/vmlinuz >>>>>> # sync >>>>>> ...QV on Acer laptop, black screen! >>>>>> >>>>>> # git bisect bad >>>>>> 56b522f4668167096a50c39446d6263c96219f5f is the first bad commit >>>>>> commit 56b522f4668167096a50c39446d6263c96219f5f >>>>>> Author: Yifan Zhang <yifan1.zhang(a)amd.com> >>>>>> Date: Tue Sep 28 15:42:35 2021 +0800 >>>>>> >>>>>> drm/amdgpu: init iommu after amdkfd device init >>>>>> >>>>>> [ Upstream commit 286826d7d976e7646b09149d9bc2899d74ff962b ] >>>>>> >>>>>> This patch is to fix clinfo failure in Raven/Picasso: >>>>>> >>>>>> Number of platforms: 1 >>>>>> Platform Profile: FULL_PROFILE >>>>>> Platform Version: OpenCL 2.2 AMD-APP (3364.0) >>>>>> Platform Name: AMD Accelerated Parallel Processing >>>>>> Platform Vendor: Advanced Micro Devices, Inc. >>>>>> Platform Extensions: cl_khr_icd cl_amd_event_callback >>>>>> >>>>>> Platform Name: AMD Accelerated Parallel Processing Number of devices: 0 >>>>>> >>>>>> Signed-off-by: Yifan Zhang <yifan1.zhang(a)amd.com> >>>>>> Reviewed-by: James Zhu <James.Zhu(a)amd.com> >>>>>> Tested-by: James Zhu <James.Zhu(a)amd.com> >>>>>> Acked-by: Felix Kuehling <Felix.Kuehling(a)amd.com> >>>>>> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> >>>>>> Signed-off-by: Sasha Levin <sashal(a)kernel.org> >>>>>> >>>>>> drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 8 ++++---- >>>>>> 1 file changed, 4 insertions(+), 4 deletions(-) >>>>>> >>>>>> Anything else I should do, to identify what in this commit is the >>>>>> likely culprit? >>>>>> Regards, >>>>>> Barry Kauler

11 months, 1 week

2
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror May 2024