[PATCH 0/2] Add SOF panic dump support for AMD platform.

This patch series consists of >> Use poll function instead of simple read ACP_SHA_DSP_FW_QUALIFIER >> Add support for IPC and DSP dumps
Ajye Huang (1): ASoC: SOF: amd: Use poll function instead to read ACP_SHA_DSP_FW_QUALIFIER
V sujith kumar Reddy (1): ASoC : SOF: amd: Add support for IPC and DSP dumps
sound/soc/sof/amd/Kconfig | 1 + sound/soc/sof/amd/acp-common.c | 108 +++++++++++++++++++++++++++++++++ sound/soc/sof/amd/acp-ipc.c | 13 ++++ sound/soc/sof/amd/acp.c | 8 ++- sound/soc/sof/amd/acp.h | 6 ++ 5 files changed, 133 insertions(+), 3 deletions(-)

From: Ajye Huang ajye_huang@compal.corp-partner.google.com
The Skyrim project and Whiterun met error when DSP loading during device boot. Ex, error in kernel log, ERR kernel: [ 16.124537] snd_sof_amd_rembrandt 0000:04:00.5: PSP validation failed.
Use the snd_sof_dsp_read_poll_timeout function to successfully read the FW_QUALIFIER register
Signed-off-by: Ajye Huang ajye_huang@compal.corp-partner.google.com Signed-off-by: V sujith kumar Reddy Vsujithkumar.Reddy@amd.com --- sound/soc/sof/amd/acp.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/sound/soc/sof/amd/acp.c b/sound/soc/sof/amd/acp.c index 47115a77c92c..6bd2888fbb66 100644 --- a/sound/soc/sof/amd/acp.c +++ b/sound/soc/sof/amd/acp.c @@ -255,10 +255,12 @@ int configure_and_run_sha_dma(struct acp_dev_data *adata, void *image_addr, if (ret) return ret;
- fw_qualifier = snd_sof_dsp_read(sdev, ACP_DSP_BAR, ACP_SHA_DSP_FW_QUALIFIER); - if (!(fw_qualifier & DSP_FW_RUN_ENABLE)) { + ret = snd_sof_dsp_read_poll_timeout(sdev, ACP_DSP_BAR, ACP_SHA_DSP_FW_QUALIFIER, + fw_qualifier, fw_qualifier & DSP_FW_RUN_ENABLE, + ACP_REG_POLL_INTERVAL, ACP_DMA_COMPLETE_TIMEOUT_US); + if (ret < 0) { dev_err(sdev->dev, "PSP validation failed\n"); - return -EINVAL; + return ret; }
return 0;

Add support for IPC and DSP dumps for AMD platforms.
Signed-off-by: V sujith kumar Reddy Vsujithkumar.Reddy@amd.com --- sound/soc/sof/amd/Kconfig | 1 + sound/soc/sof/amd/acp-common.c | 108 +++++++++++++++++++++++++++++++++ sound/soc/sof/amd/acp-ipc.c | 13 ++++ sound/soc/sof/amd/acp.h | 6 ++ 4 files changed, 128 insertions(+)
diff --git a/sound/soc/sof/amd/Kconfig b/sound/soc/sof/amd/Kconfig index a305ea6efea9..1cb92d6030e3 100644 --- a/sound/soc/sof/amd/Kconfig +++ b/sound/soc/sof/amd/Kconfig @@ -20,6 +20,7 @@ config SND_SOC_SOF_AMD_COMMON select SND_SOC_SOF_IPC3 select SND_SOC_SOF_PCI_DEV select SND_AMD_ACP_CONFIG + select SND_SOC_SOF_XTENSA select SND_SOC_ACPI if ACPI help This option is not user-selectable but automatically handled by diff --git a/sound/soc/sof/amd/acp-common.c b/sound/soc/sof/amd/acp-common.c index 150e042e4039..bd6c1b198736 100644 --- a/sound/soc/sof/amd/acp-common.c +++ b/sound/soc/sof/amd/acp-common.c @@ -16,6 +16,7 @@ #include "../sof-audio.h" #include "acp.h" #include "acp-dsp-offset.h" +#include <sound/sof/xtensa.h>
int acp_dai_probe(struct snd_soc_dai *dai) { @@ -33,6 +34,107 @@ int acp_dai_probe(struct snd_soc_dai *dai) } EXPORT_SYMBOL_NS(acp_dai_probe, SND_SOC_SOF_AMD_COMMON);
+/** + * amd_sof_ipc_dump() - This function is called when IPC tx times out. + * @sdev: SOF device. + */ +void amd_sof_ipc_dump(struct snd_sof_dev *sdev) +{ + const struct sof_amd_acp_desc *desc = get_chip_info(sdev->pdata); + u32 base = desc->dsp_intr_base; + u32 dsp_msg_write = sdev->debug_box.offset + + offsetof(struct scratch_ipc_conf, sof_dsp_msg_write); + u32 dsp_ack_write = sdev->debug_box.offset + + offsetof(struct scratch_ipc_conf, sof_dsp_ack_write); + u32 host_msg_write = sdev->debug_box.offset + + offsetof(struct scratch_ipc_conf, sof_host_msg_write); + u32 host_ack_write = sdev->debug_box.offset + + offsetof(struct scratch_ipc_conf, sof_host_ack_write); + u32 dsp_msg, dsp_ack, host_msg, host_ack, irq_stat; + + dsp_msg = snd_sof_dsp_read(sdev, ACP_DSP_BAR, ACP_SCRATCH_REG_0 + dsp_msg_write); + dsp_ack = snd_sof_dsp_read(sdev, ACP_DSP_BAR, ACP_SCRATCH_REG_0 + dsp_ack_write); + host_msg = snd_sof_dsp_read(sdev, ACP_DSP_BAR, ACP_SCRATCH_REG_0 + host_msg_write); + host_ack = snd_sof_dsp_read(sdev, ACP_DSP_BAR, ACP_SCRATCH_REG_0 + host_ack_write); + irq_stat = snd_sof_dsp_read(sdev, ACP_DSP_BAR, base + DSP_SW_INTR_STAT_OFFSET); + + dev_err(sdev->dev, + "dsp_msg = %#x dsp_ack = %#x host_msg = %#x host_ack = %#x irq_stat = %#x\n", + dsp_msg, dsp_ack, host_msg, host_ack, irq_stat); +} + +/** + * amd_get_registers() - This function is called in case of DSP oops + * in order to gather information about the registers, filename and + * linenumber and stack. + * @sdev: SOF device. + * @xoops: Stores information about registers. + * @panic_info: Stores information about filename and line number. + * @stack: Stores the stack dump. + * @stack_words: Size of the stack dump. + */ +static void amd_get_registers(struct snd_sof_dev *sdev, + struct sof_ipc_dsp_oops_xtensa *xoops, + struct sof_ipc_panic_info *panic_info, + u32 *stack, size_t stack_words) +{ + u32 offset = sdev->dsp_oops_offset; + + /* first read registers */ + acp_mailbox_read(sdev, offset, xoops, sizeof(*xoops)); + + /* then get panic info */ + if (xoops->arch_hdr.totalsize > EXCEPT_MAX_HDR_SIZE) { + dev_err(sdev->dev, "invalid header size 0x%x. FW oops is bogus\n", + xoops->arch_hdr.totalsize); + return; + } + + offset += xoops->arch_hdr.totalsize; + acp_mailbox_read(sdev, offset, panic_info, sizeof(*panic_info)); + + /* then get the stack */ + offset += sizeof(*panic_info); + acp_mailbox_read(sdev, offset, stack, stack_words * sizeof(u32)); +} + +/** + * amd_sof_dump() - This function is called when a panic message is + * received from the firmware. + * @sdev: SOF device. + * @flags: parameter not used but required by ops prototype + */ +void amd_sof_dump(struct snd_sof_dev *sdev, u32 flags) +{ + struct sof_ipc_dsp_oops_xtensa xoops; + struct sof_ipc_panic_info panic_info; + u32 stack[AMD_STACK_DUMP_SIZE]; + u32 status; + + /* Get information about the panic status from the debug box area. + * Compute the trace point based on the status. + */ + if (sdev->dsp_oops_offset > sdev->debug_box.offset) { + acp_mailbox_read(sdev, sdev->debug_box.offset, &status, sizeof(u32)); + } else { + /* Read DSP Panic status from dsp_box. + * As window information for exception box offset and size is not available + * before FW_READY + */ + acp_mailbox_read(sdev, sdev->dsp_box.offset, &status, sizeof(u32)); + sdev->dsp_oops_offset = sdev->dsp_box.offset + sizeof(status); + } + + /* Get information about the registers, the filename and line + * number and the stack. + */ + amd_get_registers(sdev, &xoops, &panic_info, stack, AMD_STACK_DUMP_SIZE); + + /* Print the information to the console */ + sof_print_oops_and_stack(sdev, KERN_ERR, status, status, &xoops, + &panic_info, stack, AMD_STACK_DUMP_SIZE); +} + struct snd_soc_acpi_mach *amd_sof_machine_select(struct snd_sof_dev *sdev) { struct snd_sof_pdata *sof_pdata = sdev->pdata; @@ -104,9 +206,15 @@ struct snd_sof_dsp_ops sof_acp_common_ops = { /* PM */ .suspend = amd_sof_acp_suspend, .resume = amd_sof_acp_resume, + + .ipc_dump = amd_sof_ipc_dump, + .dbg_dump = amd_sof_dump, + .debugfs_add_region_item = snd_sof_debugfs_add_region_item_iomem, + .dsp_arch_ops = &sof_xtensa_arch_ops, }; EXPORT_SYMBOL_NS(sof_acp_common_ops, SND_SOC_SOF_AMD_COMMON);
MODULE_IMPORT_NS(SND_SOC_SOF_AMD_COMMON); +MODULE_IMPORT_NS(SND_SOC_SOF_XTENSA); MODULE_DESCRIPTION("ACP SOF COMMON Driver"); MODULE_LICENSE("Dual BSD/GPL"); diff --git a/sound/soc/sof/amd/acp-ipc.c b/sound/soc/sof/amd/acp-ipc.c index dd6e53c63407..5a02753c4610 100644 --- a/sound/soc/sof/amd/acp-ipc.c +++ b/sound/soc/sof/amd/acp-ipc.c @@ -154,8 +154,15 @@ irqreturn_t acp_sof_ipc_irq_thread(int irq, void *context) offsetof(struct scratch_ipc_conf, sof_dsp_ack_write); bool ipc_irq = false; int dsp_msg, dsp_ack; + unsigned int status;
if (sdev->first_boot && sdev->fw_state != SOF_FW_BOOT_COMPLETE) { + acp_mailbox_read(sdev, sdev->dsp_box.offset, &status, sizeof(status)); + if ((status & SOF_IPC_PANIC_MAGIC_MASK) == SOF_IPC_PANIC_MAGIC) { + snd_sof_dsp_panic(sdev, sdev->dsp_box.offset + sizeof(status), + true); + return IRQ_HANDLED; + } snd_sof_ipc_msgs_rx(sdev); acp_dsp_ipc_host_done(sdev); return IRQ_HANDLED; @@ -180,6 +187,12 @@ irqreturn_t acp_sof_ipc_irq_thread(int irq, void *context) ipc_irq = true; }
+ acp_mailbox_read(sdev, sdev->debug_box.offset, &status, sizeof(u32)); + if ((status & SOF_IPC_PANIC_MAGIC_MASK) == SOF_IPC_PANIC_MAGIC) { + snd_sof_dsp_panic(sdev, sdev->dsp_oops_offset, true); + return IRQ_HANDLED; + } + if (!ipc_irq) dev_dbg_ratelimited(sdev->dev, "nothing to do in IPC IRQ thread\n");
diff --git a/sound/soc/sof/amd/acp.h b/sound/soc/sof/amd/acp.h index 76ad963faec1..09e16ef8afa0 100644 --- a/sound/soc/sof/amd/acp.h +++ b/sound/soc/sof/amd/acp.h @@ -69,6 +69,9 @@ #define BOX_SIZE_512 0x200 #define BOX_SIZE_1024 0x400
+#define EXCEPT_MAX_HDR_SIZE 0x400 +#define AMD_STACK_DUMP_SIZE 32 + enum clock_source { ACP_CLOCK_96M = 0, ACP_CLOCK_48M, @@ -254,6 +257,9 @@ int acp_sof_trace_release(struct snd_sof_dev *sdev); int amd_sof_acp_suspend(struct snd_sof_dev *sdev, u32 target_state); int amd_sof_acp_resume(struct snd_sof_dev *sdev);
+void amd_sof_ipc_dump(struct snd_sof_dev *sdev); +void amd_sof_dump(struct snd_sof_dev *sdev, u32 flags); + static inline const struct sof_amd_acp_desc *get_chip_info(struct snd_sof_pdata *pdata) { const struct sof_dev_desc *desc = pdata->desc;

On Mon, 5 Dec 2022 17:36:47 +0530, V sujith kumar Reddy wrote:
This patch series consists of
Use poll function instead of simple read ACP_SHA_DSP_FW_QUALIFIER Add support for IPC and DSP dumps
Ajye Huang (1): ASoC: SOF: amd: Use poll function instead to read ACP_SHA_DSP_FW_QUALIFIER
[...]
Applied to
https://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound.git for-next
Thanks!
[1/2] ASoC: SOF: amd: Use poll function instead to read ACP_SHA_DSP_FW_QUALIFIER commit: 2a2f5f2384b9791a028901aac3f49c488839d073 [2/2] ASoC : SOF: amd: Add support for IPC and DSP dumps commit: 41cfad23b5ebef2dbddecff2ddeb27ca973f98a8
All being well this means that it will be integrated into the linux-next tree (usually sometime in the next 24 hours) and sent to Linus during the next merge window (or sooner if it is a bug fix), however if problems are discovered then the patch may be dropped or reverted.
You may get further e-mails resulting from automated or manual testing and review of the tree, please engage with people reporting problems and send followup patches addressing any issues that are reported if needed.
If any updates are required or you are submitting further changes they should be sent as incremental updates against current git, existing patches will not be replaced.
Please add any relevant lists and maintainers to the CCs when replying to this mail.
Thanks, Mark
participants (2)
-
Mark Brown
-
V sujith kumar Reddy