From: Chao Peng <chao.p.peng@linux.intel.com>
To: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
qemu-devel@nongnu.org
Cc: Paolo Bonzini <pbonzini@redhat.com>,
Jonathan Corbet <corbet@lwn.net>,
Sean Christopherson <seanjc@google.com>,
Vitaly Kuznetsov <vkuznets@redhat.com>,
Wanpeng Li <wanpengli@tencent.com>,
Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
x86@kernel.org, "H . Peter Anvin" <hpa@zytor.com>,
Hugh Dickins <hughd@google.com>, Jeff Layton <jlayton@kernel.org>,
"J . Bruce Fields" <bfields@fieldses.org>,
Andrew Morton <akpm@linux-foundation.org>,
Yu Zhang <yu.c.zhang@linux.intel.com>,
Chao Peng <chao.p.peng@linux.intel.com>,
"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
luto@kernel.org, john.ji@intel.com, susie.li@intel.com,
jun.nakajima@intel.com, dave.hansen@intel.com,
ak@linux.intel.com, david@redhat.com
Subject: [PATCH v3 kvm/queue 07/16] KVM: Refactor hva based memory invalidation code
Date: Thu, 23 Dec 2021 20:30:02 +0800 [thread overview]
Message-ID: <20211223123011.41044-8-chao.p.peng@linux.intel.com> (raw)
In-Reply-To: <20211223123011.41044-1-chao.p.peng@linux.intel.com>
The purpose of this patch is for fd-based memslot to reuse the same
mmu_notifier based guest memory invalidation code for private pages.
No functional changes except renaming 'hva' to more neutral 'useraddr'
so that it can also cover 'offset' in a fd that private pages live in.
Signed-off-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
---
include/linux/kvm_host.h | 8 ++++--
virt/kvm/kvm_main.c | 55 ++++++++++++++++++++++------------------
2 files changed, 36 insertions(+), 27 deletions(-)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 21f8b1880723..07863ff855cd 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1464,9 +1464,13 @@ static inline int memslot_id(struct kvm *kvm, gfn_t gfn)
}
static inline gfn_t
-hva_to_gfn_memslot(unsigned long hva, struct kvm_memory_slot *slot)
+useraddr_to_gfn_memslot(unsigned long useraddr, struct kvm_memory_slot *slot,
+ bool addr_is_hva)
{
- gfn_t gfn_offset = (hva - slot->userspace_addr) >> PAGE_SHIFT;
+ unsigned long useraddr_base = addr_is_hva ? slot->userspace_addr
+ : slot->ofs;
+
+ gfn_t gfn_offset = (useraddr - useraddr_base) >> PAGE_SHIFT;
return slot->base_gfn + gfn_offset;
}
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 47e96d1eb233..b7a1c4d7eaaa 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -486,16 +486,16 @@ static void kvm_mmu_notifier_invalidate_range(struct mmu_notifier *mn,
srcu_read_unlock(&kvm->srcu, idx);
}
-typedef bool (*hva_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range);
+typedef bool (*gfn_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range);
typedef void (*on_lock_fn_t)(struct kvm *kvm, unsigned long start,
unsigned long end);
-struct kvm_hva_range {
+struct kvm_useraddr_range {
unsigned long start;
unsigned long end;
pte_t pte;
- hva_handler_t handler;
+ gfn_handler_t handler;
on_lock_fn_t on_lock;
bool flush_on_ret;
bool may_block;
@@ -515,13 +515,13 @@ static void kvm_null_fn(void)
#define IS_KVM_NULL_FN(fn) ((fn) == (void *)kvm_null_fn)
/* Iterate over each memslot intersecting [start, last] (inclusive) range */
-#define kvm_for_each_memslot_in_hva_range(node, slots, start, last) \
- for (node = interval_tree_iter_first(&slots->hva_tree, start, last); \
+#define kvm_for_each_memslot_in_useraddr_range(node, tree, start, last) \
+ for (node = interval_tree_iter_first(tree, start, last); \
node; \
node = interval_tree_iter_next(node, start, last)) \
-static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
- const struct kvm_hva_range *range)
+static __always_inline int __kvm_handle_useraddr_range(struct kvm *kvm,
+ const struct kvm_useraddr_range *range)
{
bool ret = false, locked = false;
struct kvm_gfn_range gfn_range;
@@ -540,17 +540,19 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
idx = srcu_read_lock(&kvm->srcu);
for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+ struct rb_root_cached *useraddr_tree;
struct interval_tree_node *node;
slots = __kvm_memslots(kvm, i);
- kvm_for_each_memslot_in_hva_range(node, slots,
+ useraddr_tree = &slots->hva_tree;
+ kvm_for_each_memslot_in_useraddr_range(node, useraddr_tree,
range->start, range->end - 1) {
- unsigned long hva_start, hva_end;
+ unsigned long useraddr_start, useraddr_end;
slot = container_of(node, struct kvm_memory_slot, hva_node[slots->node_idx]);
- hva_start = max(range->start, slot->userspace_addr);
- hva_end = min(range->end, slot->userspace_addr +
- (slot->npages << PAGE_SHIFT));
+ useraddr_start = max(range->start, slot->userspace_addr);
+ useraddr_end = min(range->end, slot->userspace_addr +
+ (slot->npages << PAGE_SHIFT));
/*
* To optimize for the likely case where the address
@@ -562,11 +564,14 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
gfn_range.may_block = range->may_block;
/*
- * {gfn(page) | page intersects with [hva_start, hva_end)} =
+ * {gfn(page) | page intersects with [useraddr_start, useraddr_end)} =
* {gfn_start, gfn_start+1, ..., gfn_end-1}.
*/
- gfn_range.start = hva_to_gfn_memslot(hva_start, slot);
- gfn_range.end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, slot);
+ gfn_range.start = useraddr_to_gfn_memslot(useraddr_start,
+ slot, true);
+ gfn_range.end = useraddr_to_gfn_memslot(
+ useraddr_end + PAGE_SIZE - 1,
+ slot, true);
gfn_range.slot = slot;
if (!locked) {
@@ -597,10 +602,10 @@ static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
unsigned long start,
unsigned long end,
pte_t pte,
- hva_handler_t handler)
+ gfn_handler_t handler)
{
struct kvm *kvm = mmu_notifier_to_kvm(mn);
- const struct kvm_hva_range range = {
+ const struct kvm_useraddr_range range = {
.start = start,
.end = end,
.pte = pte,
@@ -610,16 +615,16 @@ static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
.may_block = false,
};
- return __kvm_handle_hva_range(kvm, &range);
+ return __kvm_handle_useraddr_range(kvm, &range);
}
static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn,
unsigned long start,
unsigned long end,
- hva_handler_t handler)
+ gfn_handler_t handler)
{
struct kvm *kvm = mmu_notifier_to_kvm(mn);
- const struct kvm_hva_range range = {
+ const struct kvm_useraddr_range range = {
.start = start,
.end = end,
.pte = __pte(0),
@@ -629,7 +634,7 @@ static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn
.may_block = false,
};
- return __kvm_handle_hva_range(kvm, &range);
+ return __kvm_handle_useraddr_range(kvm, &range);
}
static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
struct mm_struct *mm,
@@ -687,7 +692,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
const struct mmu_notifier_range *range)
{
struct kvm *kvm = mmu_notifier_to_kvm(mn);
- const struct kvm_hva_range hva_range = {
+ const struct kvm_useraddr_range useraddr_range = {
.start = range->start,
.end = range->end,
.pte = __pte(0),
@@ -711,7 +716,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
kvm->mn_active_invalidate_count++;
spin_unlock(&kvm->mn_invalidate_lock);
- __kvm_handle_hva_range(kvm, &hva_range);
+ __kvm_handle_useraddr_range(kvm, &useraddr_range);
return 0;
}
@@ -738,7 +743,7 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
const struct mmu_notifier_range *range)
{
struct kvm *kvm = mmu_notifier_to_kvm(mn);
- const struct kvm_hva_range hva_range = {
+ const struct kvm_useraddr_range useraddr_range = {
.start = range->start,
.end = range->end,
.pte = __pte(0),
@@ -749,7 +754,7 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
};
bool wake;
- __kvm_handle_hva_range(kvm, &hva_range);
+ __kvm_handle_useraddr_range(kvm, &useraddr_range);
/* Pairs with the increment in range_start(). */
spin_lock(&kvm->mn_invalidate_lock);
--
2.17.1
next prev parent reply other threads:[~2021-12-23 12:32 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-12-23 12:29 [PATCH v3 kvm/queue 00/16] KVM: mm: fd-based approach for supporting KVM guest private memory Chao Peng
2021-12-23 12:29 ` [PATCH v3 kvm/queue 01/16] mm/shmem: Introduce F_SEAL_INACCESSIBLE Chao Peng
2022-01-04 14:22 ` David Hildenbrand
2022-01-06 13:06 ` Chao Peng
2022-01-13 15:56 ` David Hildenbrand
2021-12-23 12:29 ` [PATCH v3 kvm/queue 02/16] mm/memfd: Introduce MFD_INACCESSIBLE flag Chao Peng
2021-12-23 12:29 ` [PATCH v3 kvm/queue 03/16] mm/memfd: Introduce MEMFD_OPS Chao Peng
2021-12-24 3:53 ` Robert Hoo
2021-12-31 2:38 ` Chao Peng
2022-01-04 17:38 ` Sean Christopherson
2022-01-05 6:07 ` Chao Peng
2021-12-23 12:29 ` [PATCH v3 kvm/queue 04/16] KVM: Extend the memslot to support fd-based private memory Chao Peng
2021-12-23 17:35 ` Sean Christopherson
2021-12-31 2:53 ` Chao Peng
2022-01-04 17:34 ` Sean Christopherson
2021-12-23 12:30 ` [PATCH v3 kvm/queue 05/16] KVM: Maintain ofs_tree for fast memslot lookup by file offset Chao Peng
2021-12-23 18:02 ` Sean Christopherson
2021-12-24 3:54 ` Chao Peng
2021-12-27 23:50 ` Yao Yuan
2021-12-28 21:48 ` Sean Christopherson
2021-12-31 2:26 ` Chao Peng
2022-01-04 17:43 ` Sean Christopherson
2022-01-05 6:09 ` Chao Peng
2021-12-23 12:30 ` [PATCH v3 kvm/queue 06/16] KVM: Implement fd-based memory using MEMFD_OPS interfaces Chao Peng
2021-12-23 18:34 ` Sean Christopherson
2021-12-23 23:09 ` Paolo Bonzini
2021-12-24 4:25 ` Chao Peng
2021-12-28 22:14 ` Sean Christopherson
2021-12-24 4:12 ` Chao Peng
2021-12-24 4:22 ` Chao Peng
2021-12-23 12:30 ` Chao Peng [this message]
2021-12-23 12:30 ` [PATCH v3 kvm/queue 08/16] KVM: Special handling for fd-based memory invalidation Chao Peng
2021-12-23 12:30 ` [PATCH v3 kvm/queue 09/16] KVM: Split out common memory invalidation code Chao Peng
2021-12-23 12:30 ` [PATCH v3 kvm/queue 10/16] KVM: Implement fd-based memory invalidation Chao Peng
2021-12-23 12:30 ` [PATCH v3 kvm/queue 11/16] KVM: Add kvm_map_gfn_range Chao Peng
2021-12-23 18:06 ` Sean Christopherson
2021-12-24 4:13 ` Chao Peng
2021-12-31 2:33 ` Chao Peng
2022-01-04 17:31 ` Sean Christopherson
2022-01-05 6:14 ` Chao Peng
2022-01-05 17:03 ` Sean Christopherson
2022-01-06 12:35 ` Chao Peng
2021-12-23 12:30 ` [PATCH v3 kvm/queue 12/16] KVM: Implement fd-based memory fallocation Chao Peng
2021-12-23 12:30 ` [PATCH v3 kvm/queue 13/16] KVM: Add KVM_EXIT_MEMORY_ERROR exit Chao Peng
2021-12-23 18:28 ` Sean Christopherson
2021-12-23 12:30 ` [PATCH v3 kvm/queue 14/16] KVM: Handle page fault for private memory Chao Peng
2022-01-04 1:46 ` Yan Zhao
2022-01-04 9:10 ` Chao Peng
2022-01-04 10:06 ` Yan Zhao
2022-01-05 6:28 ` Chao Peng
2022-01-05 7:53 ` Yan Zhao
2022-01-05 20:52 ` Sean Christopherson
2022-01-14 5:53 ` Yan Zhao
2021-12-23 12:30 ` [PATCH v3 kvm/queue 15/16] KVM: Use kvm_userspace_memory_region_ext Chao Peng
2021-12-23 12:30 ` [PATCH v3 kvm/queue 16/16] KVM: Register/unregister private memory slot to memfd Chao Peng
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=20211223123011.41044-8-chao.p.peng@linux.intel.com \
--to=chao.p.peng@linux.intel.com \
--cc=ak@linux.intel.com \
--cc=akpm@linux-foundation.org \
--cc=bfields@fieldses.org \
--cc=bp@alien8.de \
--cc=corbet@lwn.net \
--cc=dave.hansen@intel.com \
--cc=david@redhat.com \
--cc=hpa@zytor.com \
--cc=hughd@google.com \
--cc=jlayton@kernel.org \
--cc=jmattson@google.com \
--cc=john.ji@intel.com \
--cc=joro@8bytes.org \
--cc=jun.nakajima@intel.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=luto@kernel.org \
--cc=mingo@redhat.com \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=seanjc@google.com \
--cc=susie.li@intel.com \
--cc=tglx@linutronix.de \
--cc=vkuznets@redhat.com \
--cc=wanpengli@tencent.com \
--cc=x86@kernel.org \
--cc=yu.c.zhang@linux.intel.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;
as well as URLs for NNTP newsgroup(s).