Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 286CB10FCAC0 for ; Wed, 1 Apr 2026 18:21:14 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id ACA5F10EED1; Wed, 1 Apr 2026 18:21:13 +0000 (UTC) Authentication-Results: gabe.freedesktop.org; dkim=pass (2048-bit key; unprotected) header.d=intel.com header.i=@intel.com header.b="YjQhh0BG"; dkim-atps=neutral Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.21]) by gabe.freedesktop.org (Postfix) with ESMTPS id 3347A10EED1 for ; Wed, 1 Apr 2026 18:21:12 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1775067673; x=1806603673; h=date:from:to:cc:subject:message-id:references: mime-version:in-reply-to; bh=PZQ8k8QQC/RhZBZoXkr1LvEjGePoWVJDvRlg+ETQ5C0=; b=YjQhh0BG6WpClLQqOyZpEW+IsKOZoXmYrOAscX0EnLaGMKhsGVse1kpx izWTCw52pfNrNY9UqcWhfeAzR1ttgpQWJ1rk27TGsZQ+jLhj8+lTkbfwg PD+pbbbEaUqCF34jB/TAcK2KXWYLjJQBVOFvUQWkkYxp9LBzHIjC0eE2j edoiZPdb0Z6038szqrxVWCpxeTZhs0+vJCZTQLiPe/72NaD90ZeSuRiM4 Mzr/hX2tzX1F5dKAkwD3bmHDwf2QryyQZ68tVJwTbW4G8/j3bJWCWh5AY 5ZxTu9tvqmguIHy+4heciF6t2DQOBIR06Y3Fj2GTj2+ak1U+VG0vzdNvs g==; X-CSE-ConnectionGUID: fiwDOAqQQM66hGs7lUiMXg== X-CSE-MsgGUID: 7LyMlU++TDe5cIzAbn3uIA== X-IronPort-AV: E=McAfee;i="6800,10657,11745"; a="76002502" X-IronPort-AV: E=Sophos;i="6.23,153,1770624000"; d="scan'208";a="76002502" Received: from orviesa001.jf.intel.com ([10.64.159.141]) by orvoesa113.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 01 Apr 2026 11:21:12 -0700 X-CSE-ConnectionGUID: +LxDMWLJSmiNOGGiE1Fw6A== X-CSE-MsgGUID: 9RtQ0N4OQ6SRxH/JW6E0sQ== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.23,153,1770624000"; d="scan'208";a="264685155" Received: from black.igk.intel.com ([10.91.253.5]) by orviesa001.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 01 Apr 2026 11:21:10 -0700 Date: Wed, 1 Apr 2026 20:21:06 +0200 From: Raag Jadav To: "Mallesh, Koujalagi" Cc: matthew.brost@intel.com, rodrigo.vivi@intel.com, riana.tauro@intel.com, michal.wajdeczko@intel.com, matthew.d.roper@intel.com, umesh.nerlige.ramappa@intel.com, intel-xe@lists.freedesktop.org Subject: Re: [PATCH v1 1/3] drm/xe/cri: Setup hardware error routing Message-ID: References: <20260217114656.2546878-1-raag.jadav@intel.com> <20260217114656.2546878-2-raag.jadav@intel.com> <6c7b27a8-d5bc-4854-8252-8b38e269f80b@intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <6c7b27a8-d5bc-4854-8252-8b38e269f80b@intel.com> X-BeenThere: intel-xe@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Intel Xe graphics driver List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: intel-xe-bounces@lists.freedesktop.org Sender: "Intel-xe" On Thu, Mar 26, 2026 at 06:19:00PM +0530, Mallesh, Koujalagi wrote: > On 17-02-2026 05:16 pm, Raag Jadav wrote: > > Setup hardware error routing based on XE_WEDGED_MODE_UPON_ANY_HANG_NO_RESET > > which will be used for debug cases on Crescent Island. > > > > Signed-off-by: Raag Jadav > > --- > > drivers/gpu/drm/xe/regs/xe_hw_error_regs.h | 5 +++++ > > drivers/gpu/drm/xe/xe_hw_error.c | 22 +++++++++++++++++++++- > > drivers/gpu/drm/xe/xe_hw_error.h | 1 + > > 3 files changed, 27 insertions(+), 1 deletion(-) > > > > diff --git a/drivers/gpu/drm/xe/regs/xe_hw_error_regs.h b/drivers/gpu/drm/xe/regs/xe_hw_error_regs.h > > index c146b9ef44eb..88593f0a48fd 100644 > > --- a/drivers/gpu/drm/xe/regs/xe_hw_error_regs.h > > +++ b/drivers/gpu/drm/xe/regs/xe_hw_error_regs.h > > @@ -11,6 +11,11 @@ > > #define HEC_UNCORR_FW_ERR_DW0(base) XE_REG((base) + 0x124) > > +#define DEV_ERR_ROUTING_CTRL XE_REG(0x100170) > > +#define FATAL_ERR_ROUTING BIT(2) > > +#define NONFATAL_ERR_ROUTING BIT(1) > > +#define CORR_ERR_ROUTING BIT(0) > > + > > #define DEV_ERR_STAT_NONFATAL 0x100178 > > #define DEV_ERR_STAT_CORRECTABLE 0x10017c > > #define DEV_ERR_STAT_REG(x) XE_REG(_PICK_EVEN((x), \ > > diff --git a/drivers/gpu/drm/xe/xe_hw_error.c b/drivers/gpu/drm/xe/xe_hw_error.c > > index 8c65291f36fc..eb557266d083 100644 > > --- a/drivers/gpu/drm/xe/xe_hw_error.c > > +++ b/drivers/gpu/drm/xe/xe_hw_error.c > > @@ -146,6 +146,23 @@ void xe_hw_error_irq_handler(struct xe_tile *tile, const u32 master_ctl) > > hw_error_source_handler(tile, hw_err); > > } > > +/** > > + * xe_hw_error_irq_route - irq routing of hw errors > > + * @xe: xe device instance > > + * > > + * Set irq routing of hw errors. > > + */ > > +void xe_hw_error_irq_route(struct xe_device *xe) > > +{ > > + u32 mask = CORR_ERR_ROUTING | NONFATAL_ERR_ROUTING | FATAL_ERR_ROUTING; > > + bool irq = xe->wedged.mode == XE_WEDGED_MODE_UPON_ANY_HANG_NO_RESET; > > What happen when wedge mode change during execution? This needs to be called when it happens. The only place I could find as of now is through debugfs, will add in this in v2. Raag > > + struct xe_tile *tile; > > + u8 id; > > + > > + for_each_tile(tile, xe, id) > > + xe_mmio_rmw32(&tile->mmio, DEV_ERR_ROUTING_CTRL, mask, irq ? mask : 0); > > +} > > + > > /* > > * Process hardware errors during boot > > */ > > @@ -178,5 +195,8 @@ void xe_hw_error_init(struct xe_device *xe) > > INIT_WORK(&tile->csc_hw_error_work, csc_hw_error_work); > > - process_hw_errors(xe); > > + if (xe->info.platform == XE_CRESCENTISLAND) > > + xe_hw_error_irq_route(xe); > > + else > > + process_hw_errors(xe); > > } > > diff --git a/drivers/gpu/drm/xe/xe_hw_error.h b/drivers/gpu/drm/xe/xe_hw_error.h > > index d86e28c5180c..8f155b66b5f1 100644 > > --- a/drivers/gpu/drm/xe/xe_hw_error.h > > +++ b/drivers/gpu/drm/xe/xe_hw_error.h > > @@ -11,5 +11,6 @@ struct xe_tile; > > struct xe_device; > > void xe_hw_error_irq_handler(struct xe_tile *tile, const u32 master_ctl); > > +void xe_hw_error_irq_route(struct xe_device *xe); > > void xe_hw_error_init(struct xe_device *xe); > > #endif