linux-arm-kernel.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: linu.cherian@cavium.com (Linu Cherian)
To: linux-arm-kernel@lists.infradead.org
Subject: [v4 3/4] iommu/arm-smmu-v3: Add workaround for Cavium ThunderX2 erratum #74
Date: Tue, 9 May 2017 19:18:56 +0530	[thread overview]
Message-ID: <20170509134856.GA1090@virtx40> (raw)
In-Reply-To: <bd0b9567-ccc5-8bf2-b113-d0f7a1ab2ed2@arm.com>

On Tue May 09, 2017 at 02:02:58PM +0100, Robin Murphy wrote:
> On 09/05/17 12:45, Geetha sowjanya wrote:
> > From: Linu Cherian <linu.cherian@cavium.com>
> > 
> > Cavium ThunderX2 SMMU implementation doesn't support page 1 register space
> > and PAGE0_REGS_ONLY option is enabled as an errata workaround.
> > This option when turned on, replaces all page 1 offsets used for
> > EVTQ_PROD/CONS, PRIQ_PROD/CONS register access with page 0 offsets.
> > 
> > SMMU resource size checks are now based on SMMU option PAGE0_REGS_ONLY,
> > since resource size can be either 64k/128k.
> > For this, arm_smmu_device_dt_probe/acpi_probe has been moved before
> > platform_get_resource call, so that SMMU options are set beforehand.
> > 
> > Signed-off-by: Linu Cherian <linu.cherian@cavium.com>
> > Signed-off-by: Geetha Sowjanya <geethasowjanya.akula@cavium.com>
> > ---
> >  Documentation/arm64/silicon-errata.txt             |  1 +
> >  .../devicetree/bindings/iommu/arm,smmu-v3.txt      |  6 ++
> >  drivers/iommu/arm-smmu-v3.c                        | 80 ++++++++++++++++------
> >  3 files changed, 66 insertions(+), 21 deletions(-)
> > 
> > diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt
> > index 10f2ddd..4693a32 100644
> > --- a/Documentation/arm64/silicon-errata.txt
> > +++ b/Documentation/arm64/silicon-errata.txt
> > @@ -62,6 +62,7 @@ stable kernels.
> >  | Cavium         | ThunderX GICv3  | #23154          | CAVIUM_ERRATUM_23154        |
> >  | Cavium         | ThunderX Core   | #27456          | CAVIUM_ERRATUM_27456        |
> >  | Cavium         | ThunderX SMMUv2 | #27704          | N/A                         |
> > +| Cavium         | ThunderX2 SMMUv3| #74             | N/A                         |
> >  |                |                 |                 |                             |
> >  | Freescale/NXP  | LS2080A/LS1043A | A-008585        | FSL_ERRATUM_A008585         |
> >  |                |                 |                 |                             |
> > diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu-v3.txt b/Documentation/devicetree/bindings/iommu/arm,smmu-v3.txt
> > index be57550..e6da62b 100644
> > --- a/Documentation/devicetree/bindings/iommu/arm,smmu-v3.txt
> > +++ b/Documentation/devicetree/bindings/iommu/arm,smmu-v3.txt
> > @@ -49,6 +49,12 @@ the PCIe specification.
> >  - hisilicon,broken-prefetch-cmd
> >                      : Avoid sending CMD_PREFETCH_* commands to the SMMU.
> >  
> > +- cavium-cn99xx,broken-page1-regspace
> > +                    : Replaces all page 1 offsets used for EVTQ_PROD/CONS,
> > +						PRIQ_PROD/CONS register access with page 0 offsets.
> > +						Set for Caviun ThunderX2 silicon that doesn't support
> > +						SMMU page1 register space.
> > +
> >  ** Example
> >  
> >          smmu at 2b400000 {
> > diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
> > index 380969a..1e986a0 100644
> > --- a/drivers/iommu/arm-smmu-v3.c
> > +++ b/drivers/iommu/arm-smmu-v3.c
> > @@ -176,15 +176,15 @@
> >  #define ARM_SMMU_CMDQ_CONS		0x9c
> >  
> >  #define ARM_SMMU_EVTQ_BASE		0xa0
> > -#define ARM_SMMU_EVTQ_PROD		0x100a8
> > -#define ARM_SMMU_EVTQ_CONS		0x100ac
> > +#define ARM_SMMU_EVTQ_PROD(smmu)	(page1_offset_adjust(0x100a8, smmu))
> > +#define ARM_SMMU_EVTQ_CONS(smmu)	(page1_offset_adjust(0x100ac, smmu))
> 
> Sorry, perhaps I should have communicated the rest of the idea more
> explicitly - you now don't need to change these definitions...
> 

Fine. 


> >  #define ARM_SMMU_EVTQ_IRQ_CFG0		0xb0
> >  #define ARM_SMMU_EVTQ_IRQ_CFG1		0xb8
> >  #define ARM_SMMU_EVTQ_IRQ_CFG2		0xbc
> >  
> >  #define ARM_SMMU_PRIQ_BASE		0xc0
> > -#define ARM_SMMU_PRIQ_PROD		0x100c8
> > -#define ARM_SMMU_PRIQ_CONS		0x100cc
> > +#define ARM_SMMU_PRIQ_PROD(smmu)	(page1_offset_adjust(0x100c8, smmu))
> > +#define ARM_SMMU_PRIQ_CONS(smmu)	(page1_offset_adjust(0x100cc, smmu))
> >  #define ARM_SMMU_PRIQ_IRQ_CFG0		0xd0
> >  #define ARM_SMMU_PRIQ_IRQ_CFG1		0xd8
> >  #define ARM_SMMU_PRIQ_IRQ_CFG2		0xdc
> > @@ -412,6 +412,9 @@
> >  #define MSI_IOVA_BASE			0x8000000
> >  #define MSI_IOVA_LENGTH			0x100000
> >  
> > +#define ARM_SMMU_PAGE0_REGS_ONLY(smmu)		\
> > +	((smmu)->options & ARM_SMMU_OPT_PAGE0_REGS_ONLY)
> > +
> >  static bool disable_bypass;
> >  module_param_named(disable_bypass, disable_bypass, bool, S_IRUGO);
> >  MODULE_PARM_DESC(disable_bypass,
> > @@ -597,6 +600,7 @@ struct arm_smmu_device {
> >  	u32				features;
> >  
> >  #define ARM_SMMU_OPT_SKIP_PREFETCH	(1 << 0)
> > +#define ARM_SMMU_OPT_PAGE0_REGS_ONLY    (1 << 1)
> >  	u32				options;
> >  
> >  	struct arm_smmu_cmdq		cmdq;
> > @@ -663,9 +667,19 @@ struct arm_smmu_option_prop {
> >  
> >  static struct arm_smmu_option_prop arm_smmu_options[] = {
> >  	{ ARM_SMMU_OPT_SKIP_PREFETCH, "hisilicon,broken-prefetch-cmd" },
> > +	{ ARM_SMMU_OPT_PAGE0_REGS_ONLY, "cavium-cn99xx,broken-page1-regspace"},
> >  	{ 0, NULL},
> >  };
> >  
> > +static inline unsigned long page1_offset_adjust(
> > +	unsigned long off, struct arm_smmu_device *smmu)
> > +{
> > +	if (off > SZ_64K && ARM_SMMU_PAGE0_REGS_ONLY(smmu))
> > +		return (off - SZ_64K);
> > +
> > +	return off;
> > +}
> > +
> >  static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
> >  {
> >  	return container_of(dom, struct arm_smmu_domain, domain);
> > @@ -1986,8 +2000,10 @@ static int arm_smmu_init_queues(struct arm_smmu_device *smmu)
> >  		return ret;
> >  
> >  	/* evtq */
> > -	ret = arm_smmu_init_one_queue(smmu, &smmu->evtq.q, ARM_SMMU_EVTQ_PROD,
> > -				      ARM_SMMU_EVTQ_CONS, EVTQ_ENT_DWORDS);
> > +	ret = arm_smmu_init_one_queue(smmu, &smmu->evtq.q,
> > +				      ARM_SMMU_EVTQ_PROD(smmu),
> > +				      ARM_SMMU_EVTQ_CONS(smmu),
> > +				      EVTQ_ENT_DWORDS);
> 
> ...or these callsites; you can just use page1_offset_adjust() directly
> within arm_smmu_init_one_queue(), i.e.

> 
> 
>        q->prod_reg = smmu->base + page1_offset_adjust(prod_off, smmu);
>        q->cons_reg = smmu->base + page1_offset_adjust(cons_off, smmu);
> 
> because it won't affect page 0 offsets either way.
> 
> >  	if (ret)
> >  		return ret;
> >  
> > @@ -1995,8 +2011,10 @@ static int arm_smmu_init_queues(struct arm_smmu_device *smmu)
> >  	if (!(smmu->features & ARM_SMMU_FEAT_PRI))
> >  		return 0;
> >  
> > -	return arm_smmu_init_one_queue(smmu, &smmu->priq.q, ARM_SMMU_PRIQ_PROD,
> > -				       ARM_SMMU_PRIQ_CONS, PRIQ_ENT_DWORDS);
> > +	return arm_smmu_init_one_queue(smmu, &smmu->priq.q,
> > +				       ARM_SMMU_PRIQ_PROD(smmu),
> > +				       ARM_SMMU_PRIQ_CONS(smmu),
> > +				       PRIQ_ENT_DWORDS);
> >  }
> >  
> >  static int arm_smmu_init_l1_strtab(struct arm_smmu_device *smmu)
> > @@ -2363,8 +2381,10 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass)
> >  
> >  	/* Event queue */
> >  	writeq_relaxed(smmu->evtq.q.q_base, smmu->base + ARM_SMMU_EVTQ_BASE);
> > -	writel_relaxed(smmu->evtq.q.prod, smmu->base + ARM_SMMU_EVTQ_PROD);
> > -	writel_relaxed(smmu->evtq.q.cons, smmu->base + ARM_SMMU_EVTQ_CONS);
> > +	writel_relaxed(smmu->evtq.q.prod, smmu->base +
> > +		       ARM_SMMU_EVTQ_PROD(smmu));
> 
> And correspondingly just use page1_offset_adjust(ARM_SMMU_EVTQ_*, smmu)
> explicitly for these writes.
> 
> In fact, if all the potential callsites are immediately converting the
> offset into an address, then it may be worth just factoring that into
> the helper as well, something like:
> 
> static inline void __iomem *arm_smmu_page1_fixup(unsigned long offset,
> 					struct arm_smmu_device *smmu)
> {
> 	if (offset > SZ_64K && ARM_SMMU_PAGE0_REGS_ONLY(smmu))
> 		offset -= SZ_64K;
> 
> 	return smmu->base + offset;
> }
> 
> What do you reckon?
> 

Just had a opinion that, replacing all page1 offset macros(ARM_SMMU_EVTQ/PRIQ_PROD/CONS) with
page1_offset_adjust(ARM_SMMU_EVTQ/PRIQ_PROD/CONS, smmu) will make the changes 
more uniform. In that case, we wont need, offset > SZ_64K  check as
well.

Hope the intention is not to change the offset definitions.


-- 
Linu cherian

  reply	other threads:[~2017-05-09 13:48 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-05-09 11:45 [v4 0/4] Cavium ThunderX2 SMMUv3 errata workarounds Geetha sowjanya
2017-05-09 11:45 ` [v4 1/4] ACPICA: IORT: Add Cavium ThunderX2 SMMUv3 model definition Geetha sowjanya
2017-05-09 11:45 ` [v4 2/4] ACPI/IORT: Fixup SMMUv3 resource size for Cavium ThunderX2 SMMUv3 model Geetha sowjanya
2017-05-09 11:45 ` [v4 3/4] iommu/arm-smmu-v3: Add workaround for Cavium ThunderX2 erratum #74 Geetha sowjanya
2017-05-09 13:02   ` Robin Murphy
2017-05-09 13:48     ` Linu Cherian [this message]
2017-05-10  5:31       ` Linu Cherian
2017-05-09 11:45 ` [v4 4/4] iommu/arm-smmu-v3: Add workaround for Cavium ThunderX2 erratum #126 Geetha sowjanya

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=20170509134856.GA1090@virtx40 \
    --to=linu.cherian@cavium.com \
    --cc=linux-arm-kernel@lists.infradead.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).