iommu.lists.linux-foundation.org archive mirror
 help / color / mirror / Atom feed
From: Joerg Roedel <joerg.roedel-5C7GfCeVMHo@public.gmane.org>
To: iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org
Cc: linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Subject: Re: [PATCH 17/28] iommu/amd: Split device table initialization into irq and dma part
Date: Fri, 6 Jul 2012 15:08:38 +0200	[thread overview]
Message-ID: <20120706130838.GD2639@amd.com> (raw)
In-Reply-To: <1341491808-23083-18-git-send-email-joerg.roedel-5C7GfCeVMHo@public.gmane.org>

On Thu, Jul 05, 2012 at 02:36:37PM +0200, Joerg Roedel wrote:
> When the IOMMU is enabled very early (as with irq-remapping)
> some devices are still in BIOS hand. When dma is blocked
> early this can cause lots of IO_PAGE_FAULTs. So delay the
> DMA initialization and do it right before the dma_ops are
> initialized.
> 
> Signed-off-by: Joerg Roedel <joerg.roedel-5C7GfCeVMHo@public.gmane.org>

Okay, I merged this patch with the previous one after another review.
This patch basically undoes and refactors what the previous patch did.
So it makes sense to do it all in one patch.

> ---
>  drivers/iommu/amd_iommu_init.c |   22 ++++++++++++++++++----
>  1 file changed, 18 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
> index e663f1d..453f80a 100644
> --- a/drivers/iommu/amd_iommu_init.c
> +++ b/drivers/iommu/amd_iommu_init.c
> @@ -1383,19 +1383,27 @@ static int __init init_memory_definitions(struct acpi_table_header *table)
>   * Init the device table to not allow DMA access for devices and
>   * suppress all page faults
>   */
> -static void init_device_table(void)
> +static void init_device_table_dma(void)
>  {
>  	u32 devid;
>  
>  	for (devid = 0; devid <= amd_iommu_last_bdf; ++devid) {
>  		set_dev_entry_bit(devid, DEV_ENTRY_VALID);
>  		set_dev_entry_bit(devid, DEV_ENTRY_TRANSLATION);
> -
> -		if (amd_iommu_irq_remap)
> -			set_dev_entry_bit(devid, DEV_ENTRY_IRQ_TBL_EN);
>  	}
>  }
>  
> +static void init_device_table(void)
> +{
> +	u32 devid;
> +
> +	if (!amd_iommu_irq_remap)
> +		return;
> +
> +	for (devid = 0; devid <= amd_iommu_last_bdf; ++devid)
> +		set_dev_entry_bit(devid, DEV_ENTRY_IRQ_TBL_EN);
> +}
> +
>  static void iommu_init_flags(struct amd_iommu *iommu)
>  {
>  	iommu->acpi_flags & IVHD_FLAG_HT_TUN_EN_MASK ?
> @@ -1783,8 +1791,14 @@ static bool detect_ivrs(void)
>  
>  static int amd_iommu_init_dma(void)
>  {
> +	struct amd_iommu *iommu;
>  	int ret;
>  
> +	init_device_table_dma();
> +
> +	for_each_iommu(iommu)
> +		iommu_flush_all_caches(iommu);
> +
>  	if (iommu_pass_through)
>  		ret = amd_iommu_init_passthrough();
>  	else
> -- 
> 1.7.9.5

-- 
AMD Operating System Research Center

Advanced Micro Devices GmbH Einsteinring 24 85609 Dornach
General Managers: Alberto Bozzo
Registration: Dornach, Landkr. Muenchen; Registerger. Muenchen, HRB Nr. 43632

  parent reply	other threads:[~2012-07-06 13:08 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-07-05 12:36 [PATCH 0/28] AMD IOMMU interrupt remapping support Joerg Roedel
     [not found] ` <1341491808-23083-1-git-send-email-joerg.roedel-5C7GfCeVMHo@public.gmane.org>
2012-07-05 12:36   ` [PATCH 01/28] x86/irq: Add data structure to keep AMD specific irq remapping information Joerg Roedel
2012-07-05 12:36   ` [PATCH 02/28] x86/irq: Introduce irq_cfg->remapped Joerg Roedel
2012-07-05 12:36   ` [PATCH 03/28] x86/irq: Use irq_remap specific print_IO_APIC paths only on Intel Joerg Roedel
     [not found]     ` <1341491808-23083-4-git-send-email-joerg.roedel-5C7GfCeVMHo@public.gmane.org>
2012-07-06  8:50       ` Ingo Molnar
2012-07-06 13:05         ` Joerg Roedel
2012-07-06 14:00           ` Ingo Molnar
     [not found]             ` <20120706140037.GA22845-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2012-07-09 12:32               ` Joerg Roedel
2012-07-05 12:36   ` [PATCH 04/28] iommu/amd: Use acpi_get_table instead of acpi_table_parse Joerg Roedel
2012-07-05 12:36   ` [PATCH 05/28] iommu/amd: Split out PCI related parts of IOMMU initialization Joerg Roedel
2012-07-05 12:36   ` [PATCH 06/28] iommu/amd: Move informational prinks out of iommu_enable Joerg Roedel
2012-07-06  4:08     ` Joe Perches
2012-07-06 12:08       ` Joerg Roedel
2012-07-05 12:36   ` [PATCH 07/28] iommu/amd: Introduce early_amd_iommu_init routine Joerg Roedel
2012-07-05 12:36   ` [PATCH 08/28] iommu/amd: Split enable_iommus() routine Joerg Roedel
2012-07-05 12:36   ` [PATCH 09/28] iommu/amd: Move unmap_flush message to amd_iommu_init_dma_ops() Joerg Roedel
2012-07-05 12:36   ` [PATCH 10/28] iommu/amd: Introduce amd_iommu_init_dma routine Joerg Roedel
2012-07-05 12:36   ` [PATCH 11/28] iommu/amd: Convert iommu initialization to state machine Joerg Roedel
2012-07-05 12:36   ` [PATCH 12/28] iommu/amd: Keep track of HPET and IOAPIC device ids Joerg Roedel
2012-07-05 12:36   ` [PATCH 13/28] iommu/amd: Add slab-cache for irq remapping tables Joerg Roedel
2012-07-05 12:36   ` [PATCH 14/28] iommu/amd: Allocate data structures to keep track of " Joerg Roedel
2012-07-05 12:36   ` [PATCH 15/28] iommu/amd: Check if IOAPIC information is correct Joerg Roedel
2012-07-05 12:36   ` [PATCH 16/28] iommu/amd: Block all interrupts by default with irq-remapping enabled Joerg Roedel
2012-07-05 12:36   ` [PATCH 17/28] iommu/amd: Split device table initialization into irq and dma part Joerg Roedel
     [not found]     ` <1341491808-23083-18-git-send-email-joerg.roedel-5C7GfCeVMHo@public.gmane.org>
2012-07-06 13:08       ` Joerg Roedel [this message]
2012-07-05 12:36   ` [PATCH 18/28] iommu/amd: Make sure IOMMU is not considered to translate itself Joerg Roedel
2012-07-05 12:36   ` [PATCH 19/28] iommu/amd: Add IRTE invalidation routine Joerg Roedel
2012-07-05 12:36   ` [PATCH 20/28] iommu/amd: Add routines to manage irq remapping tables Joerg Roedel
2012-07-05 12:36   ` [PATCH 21/28] iommu/amd: Add IOAPIC remapping routines Joerg Roedel
2012-07-05 12:36   ` [PATCH 22/28] iommu/amd: Implement MSI routines for interrupt remapping Joerg Roedel
2012-07-05 12:36   ` [PATCH 23/28] iommu/amd: Add call-back routine for HPET MSI Joerg Roedel
2012-07-05 12:36   ` [PATCH 24/28] iommu/amd: Add initialization routines for AMD interrupt remapping Joerg Roedel
2012-07-05 12:36   ` [PATCH 25/28] iommu/amd: Make sure irq remapping still works on dma init failure Joerg Roedel
2012-07-05 12:36   ` [PATCH 26/28] iommu/irq: Use amd_iommu_irq_ops if supported Joerg Roedel
2012-07-05 12:36   ` [PATCH 27/28] iommu/amd: Print message to system log when irq remapping is enabled Joerg Roedel
2012-07-05 12:36   ` [PATCH 28/28] iommu/amd: Report irq remapping through IOMMU-API Joerg Roedel
2012-07-06 14:08   ` [PATCH 0/28] AMD IOMMU interrupt remapping support Joerg Roedel

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=20120706130838.GD2639@amd.com \
    --to=joerg.roedel-5c7gfcevmho@public.gmane.org \
    --cc=iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org \
    --cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    /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 NNTP newsgroup(s).