From: Fuad Tabba <tabba@google.com>
To: kvm@vger.kernel.org, linux-arm-msm@vger.kernel.org,
linux-mm@kvack.org, kvmarm@lists.linux.dev
Cc: pbonzini@redhat.com, chenhuacai@kernel.org, mpe@ellerman.id.au,
anup@brainfault.org, paul.walmsley@sifive.com,
palmer@dabbelt.com, aou@eecs.berkeley.edu, seanjc@google.com,
viro@zeniv.linux.org.uk, brauner@kernel.org,
willy@infradead.org, akpm@linux-foundation.org,
xiaoyao.li@intel.com, yilun.xu@intel.com,
chao.p.peng@linux.intel.com, jarkko@kernel.org,
amoorthy@google.com, dmatlack@google.com,
isaku.yamahata@intel.com, mic@digikod.net, vbabka@suse.cz,
vannapurve@google.com, ackerleytng@google.com,
mail@maciej.szmigiero.name, david@redhat.com,
michael.roth@amd.com, wei.w.wang@intel.com,
liam.merwick@oracle.com, isaku.yamahata@gmail.com,
kirill.shutemov@linux.intel.com, suzuki.poulose@arm.com,
steven.price@arm.com, quic_eberman@quicinc.com,
quic_mnalajal@quicinc.com, quic_tsoni@quicinc.com,
quic_svaddagi@quicinc.com, quic_cvanscha@quicinc.com,
quic_pderrin@quicinc.com, quic_pheragu@quicinc.com,
catalin.marinas@arm.com, james.morse@arm.com,
yuzenghui@huawei.com, oliver.upton@linux.dev, maz@kernel.org,
will@kernel.org, qperret@google.com, keirf@google.com,
roypat@amazon.co.uk, shuah@kernel.org, hch@infradead.org,
jgg@nvidia.com, rientjes@google.com, jhubbard@nvidia.com,
fvdl@google.com, hughd@google.com, jthoughton@google.com,
peterx@redhat.com, pankaj.gupta@amd.com, ira.weiny@intel.com,
tabba@google.com
Subject: [PATCH v11 13/18] KVM: arm64: Refactor user_mem_abort()
Date: Thu, 5 Jun 2025 16:37:55 +0100 [thread overview]
Message-ID: <20250605153800.557144-14-tabba@google.com> (raw)
In-Reply-To: <20250605153800.557144-1-tabba@google.com>
To simplify the code and to make the assumptions clearer,
refactor user_mem_abort() by immediately setting force_pte to
true if the conditions are met.
Remove the comment about logging_active being guaranteed to never be
true for VM_PFNMAP memslots, since it's not actually correct.
Move code that will be reused in the following patch into separate
functions.
Other small instances of tidying up.
No functional change intended.
Signed-off-by: Fuad Tabba <tabba@google.com>
---
arch/arm64/kvm/mmu.c | 100 ++++++++++++++++++++++++-------------------
1 file changed, 55 insertions(+), 45 deletions(-)
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index eeda92330ade..ce80be116a30 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1466,13 +1466,56 @@ static bool kvm_vma_mte_allowed(struct vm_area_struct *vma)
return vma->vm_flags & VM_MTE_ALLOWED;
}
+static int prepare_mmu_memcache(struct kvm_vcpu *vcpu, bool topup_memcache,
+ void **memcache)
+{
+ int min_pages;
+
+ if (!is_protected_kvm_enabled())
+ *memcache = &vcpu->arch.mmu_page_cache;
+ else
+ *memcache = &vcpu->arch.pkvm_memcache;
+
+ if (!topup_memcache)
+ return 0;
+
+ min_pages = kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu);
+
+ if (!is_protected_kvm_enabled())
+ return kvm_mmu_topup_memory_cache(*memcache, min_pages);
+
+ return topup_hyp_memcache(*memcache, min_pages);
+}
+
+/*
+ * Potentially reduce shadow S2 permissions to match the guest's own S2. For
+ * exec faults, we'd only reach this point if the guest actually allowed it (see
+ * kvm_s2_handle_perm_fault).
+ *
+ * Also encode the level of the original translation in the SW bits of the leaf
+ * entry as a proxy for the span of that translation. This will be retrieved on
+ * TLB invalidation from the guest and used to limit the invalidation scope if a
+ * TTL hint or a range isn't provided.
+ */
+static void adjust_nested_fault_perms(struct kvm_s2_trans *nested,
+ enum kvm_pgtable_prot *prot,
+ bool *writable)
+{
+ *writable &= kvm_s2_trans_writable(nested);
+ if (!kvm_s2_trans_readable(nested))
+ *prot &= ~KVM_PGTABLE_PROT_R;
+
+ *prot |= kvm_encode_nested_level(nested);
+}
+
static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
struct kvm_s2_trans *nested,
struct kvm_memory_slot *memslot, unsigned long hva,
bool fault_is_perm)
{
int ret = 0;
- bool write_fault, writable, force_pte = false;
+ bool topup_memcache;
+ bool write_fault, writable;
bool exec_fault, mte_allowed;
bool device = false, vfio_allow_any_uc = false;
unsigned long mmu_seq;
@@ -1484,6 +1527,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
gfn_t gfn;
kvm_pfn_t pfn;
bool logging_active = memslot_is_logging(memslot);
+ bool force_pte = logging_active || is_protected_kvm_enabled();
long vma_pagesize, fault_granule;
enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
struct kvm_pgtable *pgt;
@@ -1501,28 +1545,16 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
return -EFAULT;
}
- if (!is_protected_kvm_enabled())
- memcache = &vcpu->arch.mmu_page_cache;
- else
- memcache = &vcpu->arch.pkvm_memcache;
-
/*
* Permission faults just need to update the existing leaf entry,
* and so normally don't require allocations from the memcache. The
* only exception to this is when dirty logging is enabled at runtime
* and a write fault needs to collapse a block entry into a table.
*/
- if (!fault_is_perm || (logging_active && write_fault)) {
- int min_pages = kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu);
-
- if (!is_protected_kvm_enabled())
- ret = kvm_mmu_topup_memory_cache(memcache, min_pages);
- else
- ret = topup_hyp_memcache(memcache, min_pages);
-
- if (ret)
- return ret;
- }
+ topup_memcache = !fault_is_perm || (logging_active && write_fault);
+ ret = prepare_mmu_memcache(vcpu, topup_memcache, &memcache);
+ if (ret)
+ return ret;
/*
* Let's check if we will get back a huge page backed by hugetlbfs, or
@@ -1536,16 +1568,10 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
return -EFAULT;
}
- /*
- * logging_active is guaranteed to never be true for VM_PFNMAP
- * memslots.
- */
- if (logging_active || is_protected_kvm_enabled()) {
- force_pte = true;
+ if (force_pte)
vma_shift = PAGE_SHIFT;
- } else {
+ else
vma_shift = get_vma_page_shift(vma, hva);
- }
switch (vma_shift) {
#ifndef __PAGETABLE_PMD_FOLDED
@@ -1597,7 +1623,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
max_map_size = PAGE_SIZE;
force_pte = (max_map_size == PAGE_SIZE);
- vma_pagesize = min(vma_pagesize, (long)max_map_size);
+ vma_pagesize = min_t(long, vma_pagesize, max_map_size);
}
/*
@@ -1626,7 +1652,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
* Rely on mmap_read_unlock() for an implicit smp_rmb(), which pairs
* with the smp_wmb() in kvm_mmu_invalidate_end().
*/
- mmu_seq = vcpu->kvm->mmu_invalidate_seq;
+ mmu_seq = kvm->mmu_invalidate_seq;
mmap_read_unlock(current->mm);
pfn = __kvm_faultin_pfn(memslot, gfn, write_fault ? FOLL_WRITE : 0,
@@ -1661,24 +1687,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
if (exec_fault && device)
return -ENOEXEC;
- /*
- * Potentially reduce shadow S2 permissions to match the guest's own
- * S2. For exec faults, we'd only reach this point if the guest
- * actually allowed it (see kvm_s2_handle_perm_fault).
- *
- * Also encode the level of the original translation in the SW bits
- * of the leaf entry as a proxy for the span of that translation.
- * This will be retrieved on TLB invalidation from the guest and
- * used to limit the invalidation scope if a TTL hint or a range
- * isn't provided.
- */
- if (nested) {
- writable &= kvm_s2_trans_writable(nested);
- if (!kvm_s2_trans_readable(nested))
- prot &= ~KVM_PGTABLE_PROT_R;
-
- prot |= kvm_encode_nested_level(nested);
- }
+ if (nested)
+ adjust_nested_fault_perms(nested, &prot, &writable);
kvm_fault_lock(kvm);
pgt = vcpu->arch.hw_mmu->pgt;
--
2.49.0.1266.g31b7d2e469-goog
next prev parent reply other threads:[~2025-06-05 15:38 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-06-05 15:37 [PATCH v11 00/18] KVM: Mapping guest_memfd backed memory at the host for software protected VMs Fuad Tabba
2025-06-05 15:37 ` [PATCH v11 01/18] KVM: Rename CONFIG_KVM_PRIVATE_MEM to CONFIG_KVM_GMEM Fuad Tabba
2025-06-05 15:37 ` [PATCH v11 02/18] KVM: Rename CONFIG_KVM_GENERIC_PRIVATE_MEM to CONFIG_KVM_GENERIC_GMEM_POPULATE Fuad Tabba
2025-06-05 15:37 ` [PATCH v11 03/18] KVM: Rename kvm_arch_has_private_mem() to kvm_arch_supports_gmem() Fuad Tabba
2025-06-05 15:37 ` [PATCH v11 04/18] KVM: x86: Rename kvm->arch.has_private_mem to kvm->arch.supports_gmem Fuad Tabba
2025-06-05 15:37 ` [PATCH v11 05/18] KVM: Rename kvm_slot_can_be_private() to kvm_slot_has_gmem() Fuad Tabba
2025-06-05 15:37 ` [PATCH v11 06/18] KVM: Fix comments that refer to slots_lock Fuad Tabba
2025-06-05 15:37 ` [PATCH v11 07/18] KVM: Fix comment that refers to kvm uapi header path Fuad Tabba
2025-06-05 15:37 ` [PATCH v11 08/18] KVM: guest_memfd: Allow host to map guest_memfd pages Fuad Tabba
2025-06-06 9:12 ` David Hildenbrand
2025-06-06 9:30 ` Fuad Tabba
2025-06-06 9:55 ` David Hildenbrand
2025-06-06 10:33 ` Fuad Tabba
2025-06-11 6:29 ` Shivank Garg
2025-06-11 18:20 ` Ackerley Tng
2025-06-08 23:42 ` Gavin Shan
2025-06-05 15:37 ` [PATCH v11 09/18] KVM: guest_memfd: Track shared memory support in memslot Fuad Tabba
2025-06-06 9:13 ` David Hildenbrand
2025-06-08 23:42 ` Gavin Shan
2025-06-05 15:37 ` [PATCH v11 10/18] KVM: x86/mmu: Handle guest page faults for guest_memfd with shared memory Fuad Tabba
2025-06-05 15:37 ` [PATCH v11 11/18] KVM: x86: Consult guest_memfd when computing max_mapping_level Fuad Tabba
2025-06-06 9:14 ` David Hildenbrand
2025-06-06 9:48 ` Fuad Tabba
2025-06-05 15:37 ` [PATCH v11 12/18] KVM: x86: Enable guest_memfd shared memory for SW-protected VMs Fuad Tabba
2025-06-05 15:49 ` David Hildenbrand
2025-06-05 16:11 ` Fuad Tabba
2025-06-05 17:35 ` David Hildenbrand
2025-06-05 17:43 ` Fuad Tabba
2025-06-05 17:45 ` David Hildenbrand
2025-06-05 18:29 ` Fuad Tabba
2025-06-05 15:37 ` Fuad Tabba [this message]
2025-06-09 0:27 ` [PATCH v11 13/18] KVM: arm64: Refactor user_mem_abort() Gavin Shan
2025-06-09 7:01 ` Fuad Tabba
2025-06-09 9:02 ` Gavin Shan
2025-06-05 15:37 ` [PATCH v11 14/18] KVM: arm64: Handle guest_memfd-backed guest page faults Fuad Tabba
2025-06-05 17:21 ` James Houghton
2025-06-06 7:31 ` Fuad Tabba
2025-06-06 7:39 ` David Hildenbrand
2025-06-09 4:08 ` Gavin Shan
2025-06-09 7:04 ` Fuad Tabba
2025-06-09 9:06 ` Gavin Shan
2025-06-05 15:37 ` [PATCH v11 15/18] KVM: arm64: Enable host mapping of shared guest_memfd memory Fuad Tabba
2025-06-05 17:26 ` James Houghton
2025-06-09 0:29 ` Gavin Shan
2025-06-05 15:37 ` [PATCH v11 16/18] KVM: Introduce the KVM capability KVM_CAP_GMEM_SHARED_MEM Fuad Tabba
2025-06-05 15:37 ` [PATCH v11 17/18] KVM: selftests: Don't use hardcoded page sizes in guest_memfd test Fuad Tabba
2025-06-06 8:15 ` David Hildenbrand
2025-06-08 23:43 ` Gavin Shan
2025-06-05 15:38 ` [PATCH v11 18/18] KVM: selftests: guest_memfd mmap() test when mapping is allowed Fuad Tabba
2025-06-05 22:07 ` James Houghton
2025-06-05 22:12 ` Sean Christopherson
2025-06-05 22:17 ` James Houghton
2025-06-06 8:14 ` Fuad Tabba
2025-06-08 23:43 ` Gavin Shan
2025-06-09 7:06 ` Fuad Tabba
2025-06-06 9:18 ` [PATCH v11 00/18] KVM: Mapping guest_memfd backed memory at the host for software protected VMs David Hildenbrand
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=20250605153800.557144-14-tabba@google.com \
--to=tabba@google.com \
--cc=ackerleytng@google.com \
--cc=akpm@linux-foundation.org \
--cc=amoorthy@google.com \
--cc=anup@brainfault.org \
--cc=aou@eecs.berkeley.edu \
--cc=brauner@kernel.org \
--cc=catalin.marinas@arm.com \
--cc=chao.p.peng@linux.intel.com \
--cc=chenhuacai@kernel.org \
--cc=david@redhat.com \
--cc=dmatlack@google.com \
--cc=fvdl@google.com \
--cc=hch@infradead.org \
--cc=hughd@google.com \
--cc=ira.weiny@intel.com \
--cc=isaku.yamahata@gmail.com \
--cc=isaku.yamahata@intel.com \
--cc=james.morse@arm.com \
--cc=jarkko@kernel.org \
--cc=jgg@nvidia.com \
--cc=jhubbard@nvidia.com \
--cc=jthoughton@google.com \
--cc=keirf@google.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=kvm@vger.kernel.org \
--cc=kvmarm@lists.linux.dev \
--cc=liam.merwick@oracle.com \
--cc=linux-arm-msm@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mail@maciej.szmigiero.name \
--cc=maz@kernel.org \
--cc=mic@digikod.net \
--cc=michael.roth@amd.com \
--cc=mpe@ellerman.id.au \
--cc=oliver.upton@linux.dev \
--cc=palmer@dabbelt.com \
--cc=pankaj.gupta@amd.com \
--cc=paul.walmsley@sifive.com \
--cc=pbonzini@redhat.com \
--cc=peterx@redhat.com \
--cc=qperret@google.com \
--cc=quic_cvanscha@quicinc.com \
--cc=quic_eberman@quicinc.com \
--cc=quic_mnalajal@quicinc.com \
--cc=quic_pderrin@quicinc.com \
--cc=quic_pheragu@quicinc.com \
--cc=quic_svaddagi@quicinc.com \
--cc=quic_tsoni@quicinc.com \
--cc=rientjes@google.com \
--cc=roypat@amazon.co.uk \
--cc=seanjc@google.com \
--cc=shuah@kernel.org \
--cc=steven.price@arm.com \
--cc=suzuki.poulose@arm.com \
--cc=vannapurve@google.com \
--cc=vbabka@suse.cz \
--cc=viro@zeniv.linux.org.uk \
--cc=wei.w.wang@intel.com \
--cc=will@kernel.org \
--cc=willy@infradead.org \
--cc=xiaoyao.li@intel.com \
--cc=yilun.xu@intel.com \
--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