From: Robin Murphy <robin.murphy@arm.com>
To: Nicolin Chen <nicolinc@nvidia.com>, will@kernel.org, jgg@nvidia.com
Cc: joro@8bytes.org, jean-philippe@linaro.org, apopple@nvidia.com,
linux-kernel@vger.kernel.org,
linux-arm-kernel@lists.infradead.org, iommu@lists.linux.dev
Subject: Re: [PATCH 1/3] iommu/io-pgtable-arm: Add nents_per_pgtable in struct io_pgtable_cfg
Date: Tue, 22 Aug 2023 10:19:21 +0100 [thread overview]
Message-ID: <f468b461-b203-5179-eb6d-9432b9911329@arm.com> (raw)
In-Reply-To: <0fe68babdb3a07adf024ed471fead4e3eb7e703f.1692693557.git.nicolinc@nvidia.com>
On 2023-08-22 09:45, Nicolin Chen wrote:
> Add a new nents_per_pgtable in struct io_pgtable_cfg to store the number
> of entries per IO pagetable, so it can be passed back to an IOMMU driver.
> It will be used by one of the following changes to set the maximum number
> of TLBI operations in the arm-smmu-v3 driver.
>
> Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
> ---
> drivers/iommu/io-pgtable-arm.c | 3 +++
> include/linux/io-pgtable.h | 2 ++
> 2 files changed, 5 insertions(+)
>
> diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
> index 72dcdd468cf3..7583d9ecca2b 100644
> --- a/drivers/iommu/io-pgtable-arm.c
> +++ b/drivers/iommu/io-pgtable-arm.c
> @@ -891,6 +891,7 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
>
> /* TTBR */
> cfg->arm_lpae_s1_cfg.ttbr = virt_to_phys(data->pgd);
> + cfg->nents_per_pgtable = 1 << data->bits_per_level;
> return &data->iop;
>
> out_free_data:
> @@ -993,6 +994,7 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
>
> /* VTTBR */
> cfg->arm_lpae_s2_cfg.vttbr = virt_to_phys(data->pgd);
> + cfg->nents_per_pgtable = 1 << data->bits_per_level;
> return &data->iop;
>
> out_free_data:
> @@ -1071,6 +1073,7 @@ arm_mali_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
> ARM_MALI_LPAE_TTBR_ADRMODE_TABLE;
> if (cfg->coherent_walk)
> cfg->arm_mali_lpae_cfg.transtab |= ARM_MALI_LPAE_TTBR_SHARE_OUTER;
> + cfg->nents_per_pgtable = 1 << data->bits_per_level;
The result of this highly complex and expensive calculation is clearly
redundant with the existing bits_per_level field, so why do we need to
waste space storing when the driver could simply use bits_per_level?
Thanks,
Robin.
> return &data->iop;
>
> diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
> index 1b7a44b35616..4b55a327abc1 100644
> --- a/include/linux/io-pgtable.h
> +++ b/include/linux/io-pgtable.h
> @@ -55,6 +55,7 @@ struct iommu_flush_ops {
> * tables.
> * @ias: Input address (iova) size, in bits.
> * @oas: Output address (paddr) size, in bits.
> + * @nents_per_pgtable: Number of entries per page table.
> * @coherent_walk A flag to indicate whether or not page table walks made
> * by the IOMMU are coherent with the CPU caches.
> * @tlb: TLB management callbacks for this set of tables.
> @@ -96,6 +97,7 @@ struct io_pgtable_cfg {
> unsigned long pgsize_bitmap;
> unsigned int ias;
> unsigned int oas;
> + unsigned int nents_per_pgtable;
> bool coherent_walk;
> const struct iommu_flush_ops *tlb;
> struct device *iommu_dev;
next prev parent reply other threads:[~2023-08-22 9:19 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-08-22 8:45 [PATCH 0/3] iommu/arm-smmu-v3: Reduce latency in __arm_smmu_tlb_inv_range() Nicolin Chen
2023-08-22 8:45 ` [PATCH 1/3] iommu/io-pgtable-arm: Add nents_per_pgtable in struct io_pgtable_cfg Nicolin Chen
2023-08-22 9:19 ` Robin Murphy [this message]
2023-08-22 16:42 ` Nicolin Chen
2023-08-29 15:37 ` Robin Murphy
2023-08-29 20:15 ` Nicolin Chen
2023-08-29 21:25 ` Robin Murphy
2023-08-29 22:15 ` Nicolin Chen
2023-08-30 21:49 ` Will Deacon
2023-08-31 17:39 ` Nicolin Chen
2023-09-01 0:08 ` Nicolin Chen
2023-09-01 18:02 ` Robin Murphy
2023-09-01 18:23 ` Nicolin Chen
2024-01-20 19:59 ` Nicolin Chen
2024-01-22 13:01 ` Jason Gunthorpe
2024-01-22 17:24 ` Nicolin Chen
2024-01-22 17:57 ` Jason Gunthorpe
2024-01-24 0:11 ` Nicolin Chen
2024-01-25 13:55 ` Jason Gunthorpe
2024-01-25 17:23 ` Nicolin Chen
2024-01-25 17:47 ` Jason Gunthorpe
2024-01-25 19:55 ` Nicolin Chen
[not found] ` <098d64da-ecf5-4a23-bff9-a04840726ef0@huawei.com>
2024-01-25 5:09 ` Nicolin Chen
2023-08-22 8:45 ` [PATCH 2/3] iommu/arm-smmu-v3: Add an arm_smmu_tlb_inv_domain helper Nicolin Chen
2023-08-22 9:40 ` Robin Murphy
2023-08-22 17:03 ` Nicolin Chen
2023-08-29 21:54 ` Robin Murphy
2023-08-29 23:03 ` Nicolin Chen
2023-08-22 8:45 ` [PATCH 3/3] iommu/arm-smmu-v3: Add a max_tlbi_ops for __arm_smmu_tlb_inv_range() Nicolin Chen
2023-08-22 9:30 ` Robin Murphy
2023-08-22 16:32 ` Nicolin Chen
2023-08-22 23:04 ` Nicolin Chen
2023-08-29 22:40 ` Robin Murphy
2023-08-29 23:14 ` Nicolin Chen
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=f468b461-b203-5179-eb6d-9432b9911329@arm.com \
--to=robin.murphy@arm.com \
--cc=apopple@nvidia.com \
--cc=iommu@lists.linux.dev \
--cc=jean-philippe@linaro.org \
--cc=jgg@nvidia.com \
--cc=joro@8bytes.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=nicolinc@nvidia.com \
--cc=will@kernel.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
all inboxes | Powered by JetHome®