intel-xe.lists.freedesktop.org archive mirror
 help / color / mirror / Atom feed
From: "Upadhyay, Tejas" <tejas.upadhyay@intel.com>
To: "Tauro, Riana" <riana.tauro@intel.com>,
	"intel-xe@lists.freedesktop.org" <intel-xe@lists.freedesktop.org>
Cc: "Gupta, Anshuman" <anshuman.gupta@intel.com>,
	"Vivi, Rodrigo" <rodrigo.vivi@intel.com>,
	"aravind.iddamsetty@linux.intel.com"
	<aravind.iddamsetty@linux.intel.com>,
	"Nilawar, Badal" <badal.nilawar@intel.com>,
	"Jadav, Raag" <raag.jadav@intel.com>,
	"Koppuravuri, Ravi Kishore" <ravi.kishore.koppuravuri@intel.com>,
	"Koujalagi,  Mallesh" <mallesh.koujalagi@intel.com>,
	"Purkait, Soham" <soham.purkait@intel.com>,
	"Ghimiray, Himal Prasad" <himal.prasad.ghimiray@intel.com>
Subject: RE: [PATCH v4 11/13] drm/xe/xe_ras: Add support for page offline list and queue commands
Date: Tue, 21 Apr 2026 09:10:49 +0000	[thread overview]
Message-ID: <DM6PR11MB32277AE94FAD89591953174B812C2@DM6PR11MB3227.namprd11.prod.outlook.com> (raw)
In-Reply-To: <20260417085812.4013309-26-riana.tauro@intel.com>



> -----Original Message-----
> From: Tauro, Riana <riana.tauro@intel.com>
> Sent: 17 April 2026 14:28
> To: intel-xe@lists.freedesktop.org
> Cc: Tauro, Riana <riana.tauro@intel.com>; Gupta, Anshuman
> <anshuman.gupta@intel.com>; Vivi, Rodrigo <rodrigo.vivi@intel.com>;
> aravind.iddamsetty@linux.intel.com; Nilawar, Badal
> <badal.nilawar@intel.com>; Jadav, Raag <raag.jadav@intel.com>;
> Koppuravuri, Ravi Kishore <ravi.kishore.koppuravuri@intel.com>; Koujalagi,
> Mallesh <mallesh.koujalagi@intel.com>; Purkait, Soham
> <soham.purkait@intel.com>; Upadhyay, Tejas <tejas.upadhyay@intel.com>;
> Ghimiray, Himal Prasad <himal.prasad.ghimiray@intel.com>
> Subject: [PATCH v4 11/13] drm/xe/xe_ras: Add support for page offline list
> and queue commands
> 
> Add handling for page offline list and queue sysctrl commands. The page
> offline list command retrieves pages that are already offlined by the firmware.
> The page offline queue command retrieves the pages pending to be offlined by
> the firmware.
> 
> Cc: Tejas Upadhyay <tejas.upadhyay@intel.com>
> Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
> Signed-off-by: Riana Tauro <riana.tauro@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_ras.c                   | 85 +++++++++++++++++++
>  drivers/gpu/drm/xe/xe_ras_types.h             | 39 +++++++++
>  drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h |  6 +-
>  3 files changed, 129 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c index
> cd1ac6441b92..42ec27c05e9a 100644
> --- a/drivers/gpu/drm/xe/xe_ras.c
> +++ b/drivers/gpu/drm/xe/xe_ras.c
> @@ -319,6 +319,87 @@ int xe_ras_page_offline(struct xe_device *xe, enum
> xe_ras_page_action action, u6
>  	return 0;
>  }
> 
> +static void get_queued_pages(struct xe_device *xe) {
> +	struct xe_sysctrl_mailbox_command command = {0};
> +	struct xe_ras_page_offline_queue response = {0};
> +	u32 count = 0;
> +	size_t rlen;
> +	int ret;
> +
> +	/* Supported only on platforms with system controller */
> +	if (!xe->info.has_sysctrl)
> +		return;
> +
> +	prepare_sysctrl_command(&command,
> XE_SYSCTRL_CMD_GET_OFFLINE_QUEUE, NULL, 0,
> +				&response, sizeof(response));
> +
> +	do {
> +		memset(&response, 0, sizeof(response));
> +
> +		ret = xe_sysctrl_send_command(&xe->sc, &command, &rlen);
> +		if (ret) {
> +			xe_err(xe, "[RAS]: sysctrl: error ret %d\n", ret);
> +			return;
> +		}
> +
> +		if (rlen != sizeof(response)) {
> +			xe_err(xe, "[RAS]: sysctrl: response size mismatch.
> Expected %zu, got %zu\n",
> +			       sizeof(response), rlen);
> +			return;
> +		}
> +
> +		/* TODO: Process pages and offline them */
> +
> +		count += response.pages_returned;
> +		if (count > response.total_pages) {
> +			xe_err(xe, "[RAS]: sysctrl: Pages returned exceed total
> pages %u, returned %u\n",
> +			       response.total_pages, count);
> +			return;
> +		}
> +	} while (response.additional_data);
> +}
> +
> +static void get_offlined_list(struct xe_device *xe) {
> +	struct xe_sysctrl_mailbox_command command = {0};
> +	struct xe_ras_page_offline_list response = {0};
> +	int ret, count = 0;
> +	size_t rlen;
> +
> +	/* Supported only on platforms with system controller */
> +	if (!xe->info.has_sysctrl)
> +		return;
> +
> +	prepare_sysctrl_command(&command,
> XE_SYSCTRL_CMD_GET_OFFLINE_LIST, NULL, 0,
> +				&response, sizeof(response));
> +
> +	do {
> +		memset(&response, 0, sizeof(response));
> +
> +		ret = xe_sysctrl_send_command(&xe->sc, &command, &rlen);
> +		if (ret) {
> +			xe_err(xe, "[RAS]: sysctrl: error ret %d\n", ret);
> +			return;
> +		}
> +
> +		if (rlen != sizeof(response)) {
> +			xe_err(xe, "[RAS]: sysctrl: response size mismatch.
> Expected %zu, got %zu\n",
> +			       sizeof(response), rlen);
> +			return;
> +		}
> +
> +		/* TODO: Process pages and offline them */
> +
> +		count += response.pages_returned;
> +		if (count > response.total_pages) {
> +			xe_err(xe, "[RAS]: sysctrl: Pages returned exceed total
> pages %u, returned %u\n",
> +			       response.total_pages, count);
> +			return;
> +		}
> +	} while (response.additional_data);
> +}
> +
>  #ifdef CONFIG_PCIEAER
>  static void aer_unmask_and_downgrade_internal_error(struct xe_device *xe)
> { @@ -394,4 +475,8 @@ void xe_ras_init(struct xe_device *xe)  #ifdef
> CONFIG_PCIEAER
>  	aer_unmask_and_downgrade_internal_error(xe);
>  #endif
> +
> +	/* Get any pages that need to be offlined from firmware and reserve
> them */
> +	get_offlined_list(xe);
> +	get_queued_pages(xe);
>  }
> diff --git a/drivers/gpu/drm/xe/xe_ras_types.h
> b/drivers/gpu/drm/xe/xe_ras_types.h
> index d76310866da5..1a5de6cd16a1 100644
> --- a/drivers/gpu/drm/xe/xe_ras_types.h
> +++ b/drivers/gpu/drm/xe/xe_ras_types.h
> @@ -10,6 +10,7 @@
> 
>  #define XE_RAS_NUM_ERROR_ARR		3
>  #define XE_RAS_MAX_ERROR_DETAILS	16
> +#define XE_RAS_NUM_PAGES		25
>  #define XE_RAS_IEH_PUNIT_ERROR		BIT(1)
> 
>  /**
> @@ -297,4 +298,42 @@ struct xe_ras_page_offline_response {
>  	/** @reserved: Reserved for future use */
>  	u32 reserved;
>  } __packed;
> +
> +/**
> + * struct xe_ras_page_offline_list - Response from get offline list
> +command
> + *
> + * This structure provides the details of offlined pages from flash.
> + */
> +struct xe_ras_page_offline_list {
> +	/** @max_entries: Total no of pages that can be stored in flash */
> +	u32 max_entries;
> +	/** @total_pages: Total number of permanently offlined pages */
> +	u32 total_pages;
> +	/** @pages_returned: Number of pages returned in this response */
> +	u32 pages_returned;
> +	/** @page_addresses: Array of permanently offlined page addresses
> (4KB aligned) */
> +	u64 page_addresses[XE_RAS_NUM_PAGES];
> +	/** @additional_data: Indicates if more data is available */
> +	u8 additional_data;
> +	/** @reserved: Reserved for future use */
> +	u8 reserved[3];
> +} __packed;
> +
> +/**
> + * struct xe_ras_page_offline_queue - Response from get offline queue
> +command
> + *
> + * This structure provides the details of queued offlined pages from firmware.
> + */
> +struct xe_ras_page_offline_queue {
> +	/** @total_pages: Total number of queued pages */
> +	u32 total_pages;
> +	/** @pages_returned: Number of pages returned in this response */
> +	u32 pages_returned;
> +	/** @page_addresses: Array of offlined page addresses (4KB aligned)

I understand that we will have 4K aligned addresses reported to core offline API right? If yes can you also add double check before passing if its really 4K aligned?

Tejas
> */
> +	u64 page_addresses[XE_RAS_NUM_PAGES];
> +	/** @additional_data: Indicates if more data is available */
> +	u8 additional_data;
> +	/** @reserved: Reserved for future use */
> +	u8 reserved[3];
> +} __packed;
>  #endif
> diff --git a/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
> b/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
> index 2cafa8a14cc3..b6139ac0eaca 100644
> --- a/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
> +++ b/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
> @@ -15,10 +15,14 @@
>   *
>   * @XE_SYSCTRL_CMD_GET_SOC_ERROR: Get basic error information
>   * @XE_SYSCTRL_CMD_PAGE_OFFLINE: Instruct firmware to offline/decline a
> page
> + * @XE_SYSCTRL_CMD_GET_OFFLINE_LIST: Get list of all offlined pages
> + from flash
> + * @XE_SYSCTRL_CMD_GET_OFFLINE_QUEUE: Get list of offlined queued
> pages
> + from firmware
>   */
>  enum xe_sysctrl_mailbox_command_id {
>  	XE_SYSCTRL_CMD_GET_SOC_ERROR		= 0x01,
> -	XE_SYSCTRL_CMD_PAGE_OFFLINE		= 0x08
> +	XE_SYSCTRL_CMD_PAGE_OFFLINE		= 0x08,
> +	XE_SYSCTRL_CMD_GET_OFFLINE_LIST		= 0x09,
> +	XE_SYSCTRL_CMD_GET_OFFLINE_QUEUE	= 0x0A
>  };
> 
>  enum xe_sysctrl_group {
> --
> 2.47.1


  parent reply	other threads:[~2026-04-21  9:10 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-04-17  8:58 [PATCH v4 00/13] Introduce Xe Uncorrectable Error Handling Riana Tauro
2026-04-17  8:58 ` [PATCH v4 01/13] drm/xe/xe_survivability: Decouple survivability info from boot survivability Riana Tauro
2026-04-17  8:58 ` [PATCH v4 02/13] drm/xe/xe_pci_error: Implement PCI error recovery callbacks Riana Tauro
2026-04-27  6:35   ` Raag Jadav
2026-05-06 13:59     ` Tauro, Riana
2026-04-17  8:58 ` [PATCH v4 03/13] drm/xe/xe_pci_error: Group all devres to release them on PCIe slot reset Riana Tauro
2026-04-17  8:58 ` [PATCH v4 04/13] drm/xe: Skip device access during PCI error recovery Riana Tauro
2026-04-30 12:58   ` Anshuman Gupta
2026-05-06 15:41     ` Tauro, Riana
2026-04-17  8:58 ` [PATCH v4 05/13] drm/xe/xe_ras: Initialize Uncorrectable AER Registers Riana Tauro
2026-04-27  7:56   ` Raag Jadav
2026-05-05  5:22     ` Tauro, Riana
2026-04-17  8:58 ` [PATCH v4 06/13] drm/xe/xe_ras: Add basic structures and commands for uncorrectable errors Riana Tauro
2026-04-17 17:38   ` Matt Roper
2026-04-17 21:25     ` Jadav, Raag
2026-04-17 21:32       ` Matt Roper
2026-04-20  5:34         ` Tauro, Riana
2026-04-20  7:49           ` Raag Jadav
2026-04-17  8:58 ` [PATCH v4 07/13] drm/xe/xe_ras: Add support for uncorrectable core-compute errors Riana Tauro
2026-04-27  8:24   ` Raag Jadav
2026-05-05  5:28     ` Tauro, Riana
2026-04-17  8:58 ` [PATCH v4 08/13] drm/xe/xe_ras: Handle uncorrectable SoC Internal errors Riana Tauro
2026-04-17  8:58 ` [PATCH v4 09/13] drm/xe/xe_ras: Handle uncorrectable device memory errors Riana Tauro
2026-04-21  6:08   ` Upadhyay, Tejas
2026-05-05  5:03     ` Tauro, Riana
2026-04-17  8:58 ` [PATCH v4 10/13] drm/xe/xe_ras: Add support to offline/decline a page Riana Tauro
2026-04-21  6:21   ` Upadhyay, Tejas
2026-05-05  5:16     ` Tauro, Riana
2026-04-17  8:58 ` [PATCH v4 11/13] drm/xe/xe_ras: Add support for page offline list and queue commands Riana Tauro
2026-04-21  6:19   ` Upadhyay, Tejas
2026-05-05  5:08     ` Tauro, Riana
2026-04-21  9:10   ` Upadhyay, Tejas [this message]
2026-05-05  5:17     ` Tauro, Riana
2026-04-17  8:58 ` [PATCH v4 12/13] drm/xe/xe_ras: Query errors from system controller on probe Riana Tauro
2026-04-28 11:46   ` Raag Jadav
2026-05-05 13:50     ` Tauro, Riana
2026-04-17  8:58 ` [PATCH v4 13/13] drm/xe/xe_pci_error: Process errors in mmio_enabled Riana Tauro
2026-04-28 11:39   ` Raag Jadav
2026-05-05  5:31     ` Tauro, Riana
2026-04-30 11:15   ` Gupta, Anshuman
2026-05-02 17:55     ` Raag Jadav
2026-04-20 13:33 ` ✗ CI.checkpatch: warning for Introduce Xe Uncorrectable Error Handling (rev4) Patchwork
2026-04-20 13:35 ` ✓ CI.KUnit: success " Patchwork
2026-04-20 14:42 ` ✓ Xe.CI.BAT: " Patchwork
2026-04-20 17:14 ` ✗ Xe.CI.FULL: failure " Patchwork

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=DM6PR11MB32277AE94FAD89591953174B812C2@DM6PR11MB3227.namprd11.prod.outlook.com \
    --to=tejas.upadhyay@intel.com \
    --cc=anshuman.gupta@intel.com \
    --cc=aravind.iddamsetty@linux.intel.com \
    --cc=badal.nilawar@intel.com \
    --cc=himal.prasad.ghimiray@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=mallesh.koujalagi@intel.com \
    --cc=raag.jadav@intel.com \
    --cc=ravi.kishore.koppuravuri@intel.com \
    --cc=riana.tauro@intel.com \
    --cc=rodrigo.vivi@intel.com \
    --cc=soham.purkait@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).