From: Sean Christopherson <seanjc@google.com>
To: Sean Christopherson <seanjc@google.com>,
Paolo Bonzini <pbonzini@redhat.com>
Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
Oliver Upton <oliver.upton@linux.dev>,
Marc Zyngier <maz@kernel.org>, Peter Xu <peterx@redhat.com>,
James Houghton <jthoughton@google.com>
Subject: [PATCH 17/22] KVM: x86/mmu: Refactor low level rmap helpers to prep for walking w/o mmu_lock
Date: Fri, 9 Aug 2024 12:43:29 -0700 [thread overview]
Message-ID: <20240809194335.1726916-18-seanjc@google.com> (raw)
In-Reply-To: <20240809194335.1726916-1-seanjc@google.com>
Refactor the pte_list and rmap code to always read and write rmap_head->val
exactly once, e.g. by collecting changes in a local variable and then
propagating those changes back to rmap_head->val as appropriate. This will
allow implementing a per-rmap rwlock (of sorts) by adding a LOCKED bit into
the rmap value alongside the MANY bit.
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
arch/x86/kvm/mmu/mmu.c | 83 +++++++++++++++++++++++++-----------------
1 file changed, 50 insertions(+), 33 deletions(-)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 73569979130d..49c1f6cc1526 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -920,21 +920,24 @@ static struct kvm_memory_slot *gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu
static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte,
struct kvm_rmap_head *rmap_head)
{
+ unsigned long old_val, new_val;
struct pte_list_desc *desc;
int count = 0;
- if (!rmap_head->val) {
- rmap_head->val = (unsigned long)spte;
- } else if (!(rmap_head->val & KVM_RMAP_MANY)) {
+ old_val = rmap_head->val;
+
+ if (!old_val) {
+ new_val = (unsigned long)spte;
+ } else if (!(old_val & KVM_RMAP_MANY)) {
desc = kvm_mmu_memory_cache_alloc(cache);
- desc->sptes[0] = (u64 *)rmap_head->val;
+ desc->sptes[0] = (u64 *)old_val;
desc->sptes[1] = spte;
desc->spte_count = 2;
desc->tail_count = 0;
- rmap_head->val = (unsigned long)desc | KVM_RMAP_MANY;
+ new_val = (unsigned long)desc | KVM_RMAP_MANY;
++count;
} else {
- desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY);
+ desc = (struct pte_list_desc *)(old_val & ~KVM_RMAP_MANY);
count = desc->tail_count + desc->spte_count;
/*
@@ -943,21 +946,25 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte,
*/
if (desc->spte_count == PTE_LIST_EXT) {
desc = kvm_mmu_memory_cache_alloc(cache);
- desc->more = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY);
+ desc->more = (struct pte_list_desc *)(old_val & ~KVM_RMAP_MANY);
desc->spte_count = 0;
desc->tail_count = count;
- rmap_head->val = (unsigned long)desc | KVM_RMAP_MANY;
+ new_val = (unsigned long)desc | KVM_RMAP_MANY;
+ } else {
+ new_val = old_val;
}
desc->sptes[desc->spte_count++] = spte;
}
+
+ rmap_head->val = new_val;
+
return count;
}
-static void pte_list_desc_remove_entry(struct kvm *kvm,
- struct kvm_rmap_head *rmap_head,
+static void pte_list_desc_remove_entry(struct kvm *kvm, unsigned long *rmap_val,
struct pte_list_desc *desc, int i)
{
- struct pte_list_desc *head_desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY);
+ struct pte_list_desc *head_desc = (struct pte_list_desc *)(*rmap_val & ~KVM_RMAP_MANY);
int j = head_desc->spte_count - 1;
/*
@@ -984,9 +991,9 @@ static void pte_list_desc_remove_entry(struct kvm *kvm,
* head at the next descriptor, i.e. the new head.
*/
if (!head_desc->more)
- rmap_head->val = 0;
+ *rmap_val = 0;
else
- rmap_head->val = (unsigned long)head_desc->more | KVM_RMAP_MANY;
+ *rmap_val = (unsigned long)head_desc->more | KVM_RMAP_MANY;
mmu_free_pte_list_desc(head_desc);
}
@@ -994,24 +1001,26 @@ static void pte_list_remove(struct kvm *kvm, u64 *spte,
struct kvm_rmap_head *rmap_head)
{
struct pte_list_desc *desc;
+ unsigned long rmap_val;
int i;
- if (KVM_BUG_ON_DATA_CORRUPTION(!rmap_head->val, kvm))
- return;
+ rmap_val = rmap_head->val;
+ if (KVM_BUG_ON_DATA_CORRUPTION(!rmap_val, kvm))
+ goto out;
- if (!(rmap_head->val & KVM_RMAP_MANY)) {
- if (KVM_BUG_ON_DATA_CORRUPTION((u64 *)rmap_head->val != spte, kvm))
- return;
+ if (!(rmap_val & KVM_RMAP_MANY)) {
+ if (KVM_BUG_ON_DATA_CORRUPTION((u64 *)rmap_val != spte, kvm))
+ goto out;
- rmap_head->val = 0;
+ rmap_val = 0;
} else {
- desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY);
+ desc = (struct pte_list_desc *)(rmap_val & ~KVM_RMAP_MANY);
while (desc) {
for (i = 0; i < desc->spte_count; ++i) {
if (desc->sptes[i] == spte) {
- pte_list_desc_remove_entry(kvm, rmap_head,
+ pte_list_desc_remove_entry(kvm, &rmap_val,
desc, i);
- return;
+ goto out;
}
}
desc = desc->more;
@@ -1019,6 +1028,9 @@ static void pte_list_remove(struct kvm *kvm, u64 *spte,
KVM_BUG_ON_DATA_CORRUPTION(true, kvm);
}
+
+out:
+ rmap_head->val = rmap_val;
}
static void kvm_zap_one_rmap_spte(struct kvm *kvm,
@@ -1033,17 +1045,19 @@ static bool kvm_zap_all_rmap_sptes(struct kvm *kvm,
struct kvm_rmap_head *rmap_head)
{
struct pte_list_desc *desc, *next;
+ unsigned long rmap_val;
int i;
- if (!rmap_head->val)
+ rmap_val = rmap_head->val;
+ if (!rmap_val)
return false;
- if (!(rmap_head->val & KVM_RMAP_MANY)) {
- mmu_spte_clear_track_bits(kvm, (u64 *)rmap_head->val);
+ if (!(rmap_val & KVM_RMAP_MANY)) {
+ mmu_spte_clear_track_bits(kvm, (u64 *)rmap_val);
goto out;
}
- desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY);
+ desc = (struct pte_list_desc *)(rmap_val & ~KVM_RMAP_MANY);
for (; desc; desc = next) {
for (i = 0; i < desc->spte_count; i++)
@@ -1059,14 +1073,15 @@ static bool kvm_zap_all_rmap_sptes(struct kvm *kvm,
unsigned int pte_list_count(struct kvm_rmap_head *rmap_head)
{
+ unsigned long rmap_val = rmap_head->val;
struct pte_list_desc *desc;
- if (!rmap_head->val)
+ if (!rmap_val)
return 0;
- else if (!(rmap_head->val & KVM_RMAP_MANY))
+ else if (!(rmap_val & KVM_RMAP_MANY))
return 1;
- desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY);
+ desc = (struct pte_list_desc *)(rmap_val & ~KVM_RMAP_MANY);
return desc->tail_count + desc->spte_count;
}
@@ -1109,6 +1124,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte)
*/
struct rmap_iterator {
/* private fields */
+ struct rmap_head *head;
struct pte_list_desc *desc; /* holds the sptep if not NULL */
int pos; /* index of the sptep */
};
@@ -1123,18 +1139,19 @@ struct rmap_iterator {
static u64 *rmap_get_first(struct kvm_rmap_head *rmap_head,
struct rmap_iterator *iter)
{
+ unsigned long rmap_val = rmap_head->val;
u64 *sptep;
- if (!rmap_head->val)
+ if (!rmap_val)
return NULL;
- if (!(rmap_head->val & KVM_RMAP_MANY)) {
+ if (!(rmap_val & KVM_RMAP_MANY)) {
iter->desc = NULL;
- sptep = (u64 *)rmap_head->val;
+ sptep = (u64 *)rmap_val;
goto out;
}
- iter->desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY);
+ iter->desc = (struct pte_list_desc *)(rmap_val & ~KVM_RMAP_MANY);
iter->pos = 0;
sptep = iter->desc->sptes[iter->pos];
out:
--
2.46.0.76.ge559c4bf1a-goog
next prev parent reply other threads:[~2024-08-09 19:44 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-08-09 19:43 [PATCH 00/22] KVM: x86/mmu: Allow yielding on mmu_notifier zap Sean Christopherson
2024-08-09 19:43 ` [PATCH 01/22] KVM: selftests: Check for a potential unhandled exception iff KVM_RUN succeeded Sean Christopherson
2024-08-09 19:43 ` [PATCH 02/22] KVM: selftests: Rename max_guest_memory_test to mmu_stress_test Sean Christopherson
2024-08-09 19:43 ` [PATCH 03/22] KVM: selftests: Only muck with SREGS on x86 in mmu_stress_test Sean Christopherson
2024-08-09 19:43 ` [PATCH 04/22] KVM: selftests: Compute number of extra pages needed " Sean Christopherson
2024-09-06 0:03 ` James Houghton
2024-09-06 4:42 ` Sean Christopherson
2024-09-06 18:25 ` James Houghton
2024-08-09 19:43 ` [PATCH 05/22] KVM: selftests: Enable mmu_stress_test on arm64 Sean Christopherson
2024-08-09 19:43 ` [PATCH 06/22] KVM: selftests: Use vcpu_arch_put_guest() in mmu_stress_test Sean Christopherson
2024-08-09 19:43 ` [PATCH 07/22] KVM: selftests: Precisely limit the number of guest loops " Sean Christopherson
2024-08-09 19:43 ` [PATCH 08/22] KVM: selftests: Add a read-only mprotect() phase to mmu_stress_test Sean Christopherson
2024-08-09 19:43 ` [PATCH 09/22] KVM: selftests: Verify KVM correctly handles mprotect(PROT_READ) Sean Christopherson
[not found] ` <CADrL8HXcD--jn1iLeCJycCd3Btv4_rBPxz6NMnTREXfeh0vRZA@mail.gmail.com>
2024-09-07 0:53 ` Sean Christopherson
2024-09-07 2:26 ` James Houghton
2024-09-09 15:49 ` Sean Christopherson
2024-08-09 19:43 ` [PATCH 10/22] KVM: x86/mmu: Move walk_slot_rmaps() up near for_each_slot_rmap_range() Sean Christopherson
2024-08-28 18:20 ` Sean Christopherson
2024-08-09 19:43 ` [PATCH 11/22] KVM: x86/mmu: Plumb a @can_yield parameter into __walk_slot_rmaps() Sean Christopherson
2024-08-09 19:43 ` [PATCH 12/22] KVM: x86/mmu: Add a helper to walk and zap rmaps for a memslot Sean Christopherson
2024-08-09 19:43 ` [PATCH 13/22] KVM: x86/mmu: Honor NEED_RESCHED when zapping rmaps and blocking is allowed Sean Christopherson
2024-08-09 19:43 ` [PATCH 14/22] KVM: x86/mmu: Morph kvm_handle_gfn_range() into an aging specific helper Sean Christopherson
2024-08-12 21:53 ` David Matlack
2024-08-12 21:58 ` David Matlack
2024-08-09 19:43 ` [PATCH 15/22] KVM: x86/mmu: Fold mmu_spte_age() into kvm_rmap_age_gfn_range() Sean Christopherson
2024-08-09 19:43 ` [PATCH 16/22] KVM: x86/mmu: Add KVM_RMAP_MANY to replace open coded '1' and '1ul' literals Sean Christopherson
2024-08-09 19:43 ` Sean Christopherson [this message]
2024-08-09 19:43 ` [PATCH 18/22] KVM: x86/mmu: Use KVM_PAGES_PER_HPAGE() instead of an open coded equivalent Sean Christopherson
2024-08-09 19:43 ` [PATCH 19/22] KVM: x86/mmu: Add infrastructure to allow walking rmaps outside of mmu_lock Sean Christopherson
2024-08-12 8:39 ` Lai Jiangshan
2024-08-12 15:22 ` Sean Christopherson
2024-08-13 6:35 ` Lai Jiangshan
2024-08-13 15:19 ` Sean Christopherson
2024-09-03 20:17 ` James Houghton
2024-09-03 21:27 ` Sean Christopherson
2024-09-03 21:40 ` James Houghton
2024-09-09 19:00 ` James Houghton
2024-09-09 20:02 ` Sean Christopherson
2024-09-09 20:46 ` James Houghton
2024-09-09 22:02 ` Sean Christopherson
2024-09-10 0:28 ` James Houghton
2024-09-10 1:42 ` Sean Christopherson
2024-09-10 21:11 ` James Houghton
2024-09-11 15:33 ` Sean Christopherson
2024-08-09 19:43 ` [PATCH 20/22] KVM: x86/mmu: Add support for lockless walks of rmap SPTEs Sean Christopherson
2024-08-09 19:43 ` [PATCH 21/22] KVM: x86/mmu: Support rmap walks without holding mmu_lock when aging gfns Sean Christopherson
2024-09-03 20:36 ` James Houghton
2024-09-04 15:48 ` Sean Christopherson
2024-08-09 19:43 ` [PATCH 22/22] ***HACK*** KVM: x86: Don't take " Sean Christopherson
2024-09-10 4:56 ` [PATCH 00/22] KVM: x86/mmu: Allow yielding on mmu_notifier zap Sean Christopherson
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=20240809194335.1726916-18-seanjc@google.com \
--to=seanjc@google.com \
--cc=jthoughton@google.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=maz@kernel.org \
--cc=oliver.upton@linux.dev \
--cc=pbonzini@redhat.com \
--cc=peterx@redhat.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®