mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Dev Jain <dev.jain@arm.com>
To: Bradley Morgan <include@grrlz.net>, Marc Zyngier <maz@kernel.org>,
	Oliver Upton <oupton@kernel.org>
Cc: Fuad Tabba <tabba@google.com>, Joey Gouly <joey.gouly@arm.com>,
	Steffen Eiden <seiden@linux.ibm.com>,
	Suzuki K Poulose <suzuki.poulose@arm.com>,
	Zenghui Yu <yuzenghui@huawei.com>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will@kernel.org>,
	Quentin Perret <qperret@google.com>,
	linux-arm-kernel@lists.infradead.org, kvmarm@lists.linux.dev,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH v4] KVM: arm64: Record whether pKVM stage 2 mapping is cacheable
Date: Sun, 5 Jul 2026 19:38:58 +0530	[thread overview]
Message-ID: <a3b2423e-d8bc-4713-90ef-5bfac7079834@arm.com> (raw)
In-Reply-To: <20260701192428.17430-1-include@grrlz.net>



On 02/07/26 12:54 am, Bradley Morgan wrote:
> pKVM keeps its own mapping list for stage 2 operations. Its flush path
> uses that list directly, so it lost the PTE attribute check done by the
> generic stage 2 walker.
> 
> Record whether a mapping is cacheable and skip cache maintenance for
> mappings that are not cacheable.
> 
> Fixes: e912efed485a ("KVM: arm64: Introduce the EL1 pKVM MMU")

Is Fixes tag required? If I am reading correctly, Arm ARM says this:

"For VA-based cache maintenance instructions, the instruction operates on the
caches regardless of the memory type and cacheability attributes marked for
the memory address in the VMSA translation table entries. This means that
the effects of the cache maintenance instructions can apply regardless of:
  Whether the address accessed:
    Is Normal memory or Device memory.
    Has the Cacheable attribute or the Non-cacheable attribute."

So nothing goes wrong if we do dcache clean for non-cacheable memory.

> Signed-off-by: Bradley Morgan <include@grrlz.net>
> ---
> Changes since V3:
> - addressed some review :)
> 
>  arch/arm64/kvm/pkvm.c | 51 ++++++++++++++++++++++++++++++++++---------
>  1 file changed, 41 insertions(+), 10 deletions(-)
> 
> diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
> index 053e4f733e4b..6d1cad890c7e 100644
> --- a/arch/arm64/kvm/pkvm.c
> +++ b/arch/arm64/kvm/pkvm.c
> @@ -302,9 +302,32 @@ static u64 __pkvm_mapping_start(struct pkvm_mapping *m)
>  	return m->gfn * PAGE_SIZE;
>  }
>  
> +#define PKVM_MAPPING_NR_PAGES_MASK     GENMASK_ULL(47, 0)
> +#define PKVM_MAPPING_NC                        BIT_ULL(48)
> +
> +static u64 pkvm_mapping_nr_pages(struct pkvm_mapping *m)
> +{
> +	return m->nr_pages & PKVM_MAPPING_NR_PAGES_MASK;
> +}
> +
> +static bool pkvm_mapping_is_nc(struct pkvm_mapping *m)
> +{
> +	return m->nr_pages & PKVM_MAPPING_NC;
> +}
> +
> +static void pkvm_mapping_set_nr_pages(struct pkvm_mapping *m, u64 nr_pages,
> +				      bool nc)
> +{
> +	WARN_ON_ONCE(nr_pages & ~PKVM_MAPPING_NR_PAGES_MASK);
> +
> +	m->nr_pages = nr_pages & PKVM_MAPPING_NR_PAGES_MASK;
> +	if (nc)
> +		m->nr_pages |= PKVM_MAPPING_NC;
> +}
> +
>  static u64 __pkvm_mapping_end(struct pkvm_mapping *m)
>  {
> -	return (m->gfn + m->nr_pages) * PAGE_SIZE - 1;
> +	return (m->gfn + pkvm_mapping_nr_pages(m)) * PAGE_SIZE - 1;
>  }
>  
>  INTERVAL_TREE_DEFINE(struct pkvm_mapping, node, u64, __subtree_last,
> @@ -350,7 +373,7 @@ static int __pkvm_pgtable_stage2_reclaim(struct kvm_pgtable *pgt, u64 start, u64
>  			continue;
>  
>  		page = pfn_to_page(mapping->pfn);
> -		WARN_ON_ONCE(mapping->nr_pages != 1);
> +	       WARN_ON_ONCE(pkvm_mapping_nr_pages(mapping) != 1);
>  		unpin_user_pages_dirty_lock(&page, 1, true);
>  		account_locked_vm(current->mm, 1, false);
>  		pkvm_mapping_remove(mapping, &pgt->pkvm_mappings);
> @@ -369,7 +392,7 @@ static int __pkvm_pgtable_stage2_unshare(struct kvm_pgtable *pgt, u64 start, u64
>  
>  	for_each_mapping_in_range_safe(pgt, start, end, mapping) {
>  		ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn,
> -					mapping->nr_pages);
> +				       pkvm_mapping_nr_pages(mapping));
>  		if (WARN_ON(ret))
>  			return ret;
>  		pkvm_mapping_remove(mapping, &pgt->pkvm_mappings);
> @@ -448,7 +471,7 @@ int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
>  		 * permission faults are handled in the relax_perms() path.
>  		 */
>  		if (mapping) {
> -			if (size == (mapping->nr_pages * PAGE_SIZE))
> +			if (size == (pkvm_mapping_nr_pages(mapping) * PAGE_SIZE))
>  				return -EAGAIN;
>  
>  			/*
> @@ -472,7 +495,9 @@ int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
>  	swap(mapping, cache->mapping);
>  	mapping->gfn = gfn;
>  	mapping->pfn = pfn;
> -	mapping->nr_pages = size / PAGE_SIZE;
> +	pkvm_mapping_set_nr_pages(mapping, size / PAGE_SIZE,
> +				  (prot & (KVM_PGTABLE_PROT_DEVICE |
> +					   KVM_PGTABLE_PROT_NORMAL_NC)));
>  	pkvm_mapping_insert(mapping, &pgt->pkvm_mappings);
>  
>  	return ret;
> @@ -503,7 +528,7 @@ int pkvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
>  	lockdep_assert_held(&kvm->mmu_lock);
>  	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) {
>  		ret = kvm_call_hyp_nvhe(__pkvm_host_wrprotect_guest, handle, mapping->gfn,
> -					mapping->nr_pages);
> +				       pkvm_mapping_nr_pages(mapping));
>  		if (WARN_ON(ret))
>  			break;
>  	}
> @@ -517,9 +542,13 @@ int pkvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size)
>  	struct pkvm_mapping *mapping;
>  
>  	lockdep_assert_held(&kvm->mmu_lock);
> -	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping)
> +	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) {
> +		if (pkvm_mapping_is_nc(mapping))
> +			continue;
> +
>  		__clean_dcache_guest_page(pfn_to_kaddr(mapping->pfn),
> -					  PAGE_SIZE * mapping->nr_pages);
> +					  PAGE_SIZE * pkvm_mapping_nr_pages(mapping));
> +	}
>  
>  	return 0;
>  }
> @@ -536,8 +565,10 @@ bool pkvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64
>  
>  	lockdep_assert_held(&kvm->mmu_lock);
>  	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping)
> -		young |= kvm_call_hyp_nvhe(__pkvm_host_test_clear_young_guest, handle, mapping->gfn,
> -					   mapping->nr_pages, mkold);
> +		young |= kvm_call_hyp_nvhe(__pkvm_host_test_clear_young_guest,
> +					   handle, mapping->gfn,
> +					   pkvm_mapping_nr_pages(mapping),
> +					   mkold);
>  
>  	return young;
>  }


  parent reply	other threads:[~2026-07-05 14:09 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-07-01 19:24 Bradley Morgan
2026-07-02  8:59 ` Marc Zyngier
2026-07-02 11:18   ` Leonardo Bras
2026-07-02 14:52     ` Bradley Morgan
2026-07-02 15:13       ` Leonardo Bras
2026-07-02 15:34       ` Marc Zyngier
2026-07-03 16:59         ` Bradley Morgan
2026-07-05 14:08 ` Dev Jain [this message]
2026-07-05 14:12   ` Bradley Morgan
2026-07-05 19:27   ` Marc Zyngier
2026-07-05 19:29     ` Bradley Morgan
2026-07-05 20:13       ` Marc Zyngier
2026-07-05 20:17         ` Bradley Morgan
2026-07-09 14:06     ` Dev Jain

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=a3b2423e-d8bc-4713-90ef-5bfac7079834@arm.com \
    --to=dev.jain@arm.com \
    --cc=catalin.marinas@arm.com \
    --cc=include@grrlz.net \
    --cc=joey.gouly@arm.com \
    --cc=kvmarm@lists.linux.dev \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=maz@kernel.org \
    --cc=oupton@kernel.org \
    --cc=qperret@google.com \
    --cc=seiden@linux.ibm.com \
    --cc=suzuki.poulose@arm.com \
    --cc=tabba@google.com \
    --cc=will@kernel.org \
    --cc=yuzenghui@huawei.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 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®