All of lore.kernel.org
 help / color / mirror / Atom feed
From: Will Deacon <will@kernel.org>
To: "Isaac J. Manjarres" <isaacm@codeaurora.org>
Cc: pratikp@codeaurora.org, iommu@lists.linux-foundation.org,
	robin.murphy@arm.com, linux-arm-kernel@lists.infradead.org
Subject: Re: [RFC PATCH v4 10/15] iommu/io-pgtable-arm: Implement arm_lpae_unmap_pages()
Date: Thu, 8 Apr 2021 15:32:11 +0100	[thread overview]
Message-ID: <20210408143211.GE17998@willie-the-truck> (raw)
In-Reply-To: <20210408045241.27316-11-isaacm@codeaurora.org>

On Wed, Apr 07, 2021 at 09:52:36PM -0700, Isaac J. Manjarres wrote:
> Implement the unmap_pages() callback for the ARM LPAE io-pgtable
> format.
> 
> Signed-off-by: Isaac J. Manjarres <isaacm@codeaurora.org>
> Suggested-by: Will Deacon <will@kernel.org>
> ---
>  drivers/iommu/io-pgtable-arm.c | 70 ++++++++++++++++++++++------------
>  1 file changed, 45 insertions(+), 25 deletions(-)
> 
> diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
> index ea66b10c04c4..6700685f81d4 100644
> --- a/drivers/iommu/io-pgtable-arm.c
> +++ b/drivers/iommu/io-pgtable-arm.c
> @@ -253,8 +253,8 @@ static void __arm_lpae_set_pte(arm_lpae_iopte *ptep, arm_lpae_iopte pte,
>  
>  static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
>  			       struct iommu_iotlb_gather *gather,
> -			       unsigned long iova, size_t size, int lvl,
> -			       arm_lpae_iopte *ptep);
> +			       unsigned long iova, size_t size, size_t pgcount,
> +			       int lvl, arm_lpae_iopte *ptep);
>  
>  static void __arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
>  				phys_addr_t paddr, arm_lpae_iopte prot,
> @@ -298,7 +298,7 @@ static int arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
>  			size_t sz = ARM_LPAE_BLOCK_SIZE(lvl, data);
>  
>  			tblp = ptep - ARM_LPAE_LVL_IDX(iova, lvl, data);
> -			if (__arm_lpae_unmap(data, NULL, iova + i * sz, sz,
> +			if (__arm_lpae_unmap(data, NULL, iova + i * sz, sz, 1,
>  					     lvl, tblp) != sz) {
>  				WARN_ON(1);
>  				return -EINVAL;
> @@ -526,14 +526,14 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
>  				       struct iommu_iotlb_gather *gather,
>  				       unsigned long iova, size_t size,
>  				       arm_lpae_iopte blk_pte, int lvl,
> -				       arm_lpae_iopte *ptep)
> +				       arm_lpae_iopte *ptep, size_t pgcount)
>  {
>  	struct io_pgtable_cfg *cfg = &data->iop.cfg;
>  	arm_lpae_iopte pte, *tablep;
>  	phys_addr_t blk_paddr;
>  	size_t tablesz = ARM_LPAE_GRANULE(data);
>  	size_t split_sz = ARM_LPAE_BLOCK_SIZE(lvl, data);
> -	int i, unmap_idx = -1;
> +	int i, unmap_idx_start = -1, num_entries = 0, max_entries;
>  
>  	if (WARN_ON(lvl == ARM_LPAE_MAX_LEVELS))
>  		return 0;
> @@ -542,15 +542,18 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
>  	if (!tablep)
>  		return 0; /* Bytes unmapped */
>  
> -	if (size == split_sz)
> -		unmap_idx = ARM_LPAE_LVL_IDX(iova, lvl, data);
> +	if (size == split_sz) {
> +		unmap_idx_start = ARM_LPAE_LVL_IDX(iova, lvl, data);
> +		max_entries = (tablesz >> ilog2(sizeof(pte))) - unmap_idx_start;
> +		num_entries = min_t(int, pgcount, max_entries);
> +	}
>  
>  	blk_paddr = iopte_to_paddr(blk_pte, data);
>  	pte = iopte_prot(blk_pte);
>  
>  	for (i = 0; i < tablesz / sizeof(pte); i++, blk_paddr += split_sz) {

Given that we already have a 'tablesz / sizeof(pte)' expression here, I'd be
inclined to have either a local variable or a macro helper to get at the
ptes_per_table value that you also need to compute max_entries.

>  		/* Unmap! */
> -		if (i == unmap_idx)
> +		if (i >= unmap_idx_start && i < (unmap_idx_start + num_entries))
>  			continue;
>  
>  		__arm_lpae_init_pte(data, blk_paddr, pte, lvl, 1, &tablep[i]);
> @@ -568,38 +571,45 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
>  			return 0;
>  
>  		tablep = iopte_deref(pte, data);
> -	} else if (unmap_idx >= 0) {
> -		io_pgtable_tlb_add_page(&data->iop, gather, iova, size);
> -		return size;
> +	} else if (unmap_idx_start >= 0) {
> +		for (i = 0; i < num_entries; i++)
> +			io_pgtable_tlb_add_page(&data->iop, gather, iova + i * size, size);

I suppose we could add a count paramater to the iotlb gather stuff in
future too, but for now this is fine as this series is already pretty big.

Will
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

WARNING: multiple messages have this Message-ID (diff)
From: Will Deacon <will@kernel.org>
To: "Isaac J. Manjarres" <isaacm@codeaurora.org>
Cc: iommu@lists.linux-foundation.org,
	linux-arm-kernel@lists.infradead.org, baolu.lu@linux.intel.com,
	robin.murphy@arm.com, pratikp@codeaurora.org
Subject: Re: [RFC PATCH v4 10/15] iommu/io-pgtable-arm: Implement arm_lpae_unmap_pages()
Date: Thu, 8 Apr 2021 15:32:11 +0100	[thread overview]
Message-ID: <20210408143211.GE17998@willie-the-truck> (raw)
In-Reply-To: <20210408045241.27316-11-isaacm@codeaurora.org>

On Wed, Apr 07, 2021 at 09:52:36PM -0700, Isaac J. Manjarres wrote:
> Implement the unmap_pages() callback for the ARM LPAE io-pgtable
> format.
> 
> Signed-off-by: Isaac J. Manjarres <isaacm@codeaurora.org>
> Suggested-by: Will Deacon <will@kernel.org>
> ---
>  drivers/iommu/io-pgtable-arm.c | 70 ++++++++++++++++++++++------------
>  1 file changed, 45 insertions(+), 25 deletions(-)
> 
> diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
> index ea66b10c04c4..6700685f81d4 100644
> --- a/drivers/iommu/io-pgtable-arm.c
> +++ b/drivers/iommu/io-pgtable-arm.c
> @@ -253,8 +253,8 @@ static void __arm_lpae_set_pte(arm_lpae_iopte *ptep, arm_lpae_iopte pte,
>  
>  static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
>  			       struct iommu_iotlb_gather *gather,
> -			       unsigned long iova, size_t size, int lvl,
> -			       arm_lpae_iopte *ptep);
> +			       unsigned long iova, size_t size, size_t pgcount,
> +			       int lvl, arm_lpae_iopte *ptep);
>  
>  static void __arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
>  				phys_addr_t paddr, arm_lpae_iopte prot,
> @@ -298,7 +298,7 @@ static int arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
>  			size_t sz = ARM_LPAE_BLOCK_SIZE(lvl, data);
>  
>  			tblp = ptep - ARM_LPAE_LVL_IDX(iova, lvl, data);
> -			if (__arm_lpae_unmap(data, NULL, iova + i * sz, sz,
> +			if (__arm_lpae_unmap(data, NULL, iova + i * sz, sz, 1,
>  					     lvl, tblp) != sz) {
>  				WARN_ON(1);
>  				return -EINVAL;
> @@ -526,14 +526,14 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
>  				       struct iommu_iotlb_gather *gather,
>  				       unsigned long iova, size_t size,
>  				       arm_lpae_iopte blk_pte, int lvl,
> -				       arm_lpae_iopte *ptep)
> +				       arm_lpae_iopte *ptep, size_t pgcount)
>  {
>  	struct io_pgtable_cfg *cfg = &data->iop.cfg;
>  	arm_lpae_iopte pte, *tablep;
>  	phys_addr_t blk_paddr;
>  	size_t tablesz = ARM_LPAE_GRANULE(data);
>  	size_t split_sz = ARM_LPAE_BLOCK_SIZE(lvl, data);
> -	int i, unmap_idx = -1;
> +	int i, unmap_idx_start = -1, num_entries = 0, max_entries;
>  
>  	if (WARN_ON(lvl == ARM_LPAE_MAX_LEVELS))
>  		return 0;
> @@ -542,15 +542,18 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
>  	if (!tablep)
>  		return 0; /* Bytes unmapped */
>  
> -	if (size == split_sz)
> -		unmap_idx = ARM_LPAE_LVL_IDX(iova, lvl, data);
> +	if (size == split_sz) {
> +		unmap_idx_start = ARM_LPAE_LVL_IDX(iova, lvl, data);
> +		max_entries = (tablesz >> ilog2(sizeof(pte))) - unmap_idx_start;
> +		num_entries = min_t(int, pgcount, max_entries);
> +	}
>  
>  	blk_paddr = iopte_to_paddr(blk_pte, data);
>  	pte = iopte_prot(blk_pte);
>  
>  	for (i = 0; i < tablesz / sizeof(pte); i++, blk_paddr += split_sz) {

Given that we already have a 'tablesz / sizeof(pte)' expression here, I'd be
inclined to have either a local variable or a macro helper to get at the
ptes_per_table value that you also need to compute max_entries.

>  		/* Unmap! */
> -		if (i == unmap_idx)
> +		if (i >= unmap_idx_start && i < (unmap_idx_start + num_entries))
>  			continue;
>  
>  		__arm_lpae_init_pte(data, blk_paddr, pte, lvl, 1, &tablep[i]);
> @@ -568,38 +571,45 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
>  			return 0;
>  
>  		tablep = iopte_deref(pte, data);
> -	} else if (unmap_idx >= 0) {
> -		io_pgtable_tlb_add_page(&data->iop, gather, iova, size);
> -		return size;
> +	} else if (unmap_idx_start >= 0) {
> +		for (i = 0; i < num_entries; i++)
> +			io_pgtable_tlb_add_page(&data->iop, gather, iova + i * size, size);

I suppose we could add a count paramater to the iotlb gather stuff in
future too, but for now this is fine as this series is already pretty big.

Will

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

  reply	other threads:[~2021-04-08 14:32 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-08  4:52 [RFC PATCH v4 00/15] Optimizing iommu_[map/unmap] performance Isaac J. Manjarres
2021-04-08  4:52 ` [RFC PATCH v4 01/15] iommu/io-pgtable: Introduce unmap_pages() as a page table op Isaac J. Manjarres
2021-04-08  4:52 ` [RFC PATCH v4 02/15] iommu: Add an unmap_pages() op for IOMMU drivers Isaac J. Manjarres
2021-04-08  4:52 ` [RFC PATCH v4 03/15] iommu/io-pgtable: Introduce map_pages() as a page table op Isaac J. Manjarres
2021-04-08  4:52 ` [RFC PATCH v4 04/15] iommu: Add a map_pages() op for IOMMU drivers Isaac J. Manjarres
2021-04-08  4:52 ` [RFC PATCH v4 05/15] iommu: Use bitmap to calculate page size in iommu_pgsize() Isaac J. Manjarres
2021-04-08  4:52 ` [RFC PATCH v4 06/15] iommu: Split 'addr_merge' argument to iommu_pgsize() into separate parts Isaac J. Manjarres
2021-04-08 13:59   ` Will Deacon
2021-04-08 13:59     ` Will Deacon
2021-04-08 14:19     ` isaacm
2021-04-08  4:52 ` [RFC PATCH v4 07/15] iommu: Hook up '->unmap_pages' driver callback Isaac J. Manjarres
2021-04-08  4:52 ` [RFC PATCH v4 08/15] iommu: Add support for the map_pages() callback Isaac J. Manjarres
2021-04-08  4:52 ` [RFC PATCH v4 09/15] iommu/io-pgtable-arm: Prepare PTE methods for handling multiple entries Isaac J. Manjarres
2021-04-08 13:59   ` Will Deacon
2021-04-08 13:59     ` Will Deacon
2021-04-08 14:02     ` Christoph Hellwig
2021-04-08 14:02       ` Christoph Hellwig
2021-04-08 14:20       ` Will Deacon
2021-04-08 14:20         ` Will Deacon
2021-04-08  4:52 ` [RFC PATCH v4 10/15] iommu/io-pgtable-arm: Implement arm_lpae_unmap_pages() Isaac J. Manjarres
2021-04-08 14:32   ` Will Deacon [this message]
2021-04-08 14:32     ` Will Deacon
2021-04-08 14:40     ` isaacm
2021-04-08  4:52 ` [RFC PATCH v4 11/15] iommu/io-pgtable-arm: Implement arm_lpae_map_pages() Isaac J. Manjarres
2021-04-08  4:52 ` [RFC PATCH v4 12/15] iommu/io-pgtable-arm-v7s: Implement arm_v7s_unmap_pages() Isaac J. Manjarres
2021-04-08 13:58   ` Will Deacon
2021-04-08 13:58     ` Will Deacon
2021-04-08 14:19     ` isaacm
2021-04-08 14:32       ` Will Deacon
2021-04-08 14:32         ` Will Deacon
2021-04-08  4:52 ` [RFC PATCH v4 13/15] iommu/io-pgtable-arm-v7s: Implement arm_v7s_map_pages() Isaac J. Manjarres
2021-04-08  4:52 ` [RFC PATCH v4 14/15] iommu/arm-smmu: Implement the unmap_pages() IOMMU driver callback Isaac J. Manjarres
2021-04-08  4:52 ` [RFC PATCH v4 15/15] iommu/arm-smmu: Implement the map_pages() " Isaac J. Manjarres

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=20210408143211.GE17998@willie-the-truck \
    --to=will@kernel.org \
    --cc=iommu@lists.linux-foundation.org \
    --cc=isaacm@codeaurora.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=pratikp@codeaurora.org \
    --cc=robin.murphy@arm.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.