From: Ben Gardon <bgardon@google.com>
To: linux-kernel@vger.kernel.org, kvm@vger.kernel.org
Cc: Cannon Matthews <cannonmatthews@google.com>,
Paolo Bonzini <pbonzini@redhat.com>, Peter Xu <peterx@redhat.com>,
Sean Christopherson <sean.j.christopherson@intel.com>,
Peter Shier <pshier@google.com>,
Peter Feiner <pfeiner@google.com>,
Junaid Shahid <junaids@google.com>,
Jim Mattson <jmattson@google.com>,
Yulei Zhang <yulei.kernel@gmail.com>,
Wanpeng Li <kernellwp@gmail.com>,
Vitaly Kuznetsov <vkuznets@redhat.com>,
Xiao Guangrong <xiaoguangrong.eric@gmail.com>,
Ben Gardon <bgardon@google.com>
Subject: [PATCH 15/22] kvm: mmu: Support changed pte notifier in tdp MMU
Date: Fri, 25 Sep 2020 14:22:55 -0700 [thread overview]
Message-ID: <20200925212302.3979661-16-bgardon@google.com> (raw)
In-Reply-To: <20200925212302.3979661-1-bgardon@google.com>
In order to interoperate correctly with the rest of KVM and other Linux
subsystems, the TDP MMU must correctly handle various MMU notifiers. Add
a hook and handle the change_pte MMU notifier.
Tested by running kvm-unit-tests and KVM selftests on an Intel Haswell
machine. This series introduced no new failures.
This series can be viewed in Gerrit at:
https://linux-review.googlesource.com/c/virt/kvm/kvm/+/2538
Signed-off-by: Ben Gardon <bgardon@google.com>
---
arch/x86/kvm/mmu/mmu.c | 46 +++++++++++++------------
arch/x86/kvm/mmu/mmu_internal.h | 13 +++++++
arch/x86/kvm/mmu/tdp_mmu.c | 61 +++++++++++++++++++++++++++++++++
arch/x86/kvm/mmu/tdp_mmu.h | 3 ++
4 files changed, 102 insertions(+), 21 deletions(-)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 8c1e806b3d53f..0d80abe82ca93 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -122,9 +122,6 @@ module_param(dbg, bool, 0644);
#define PTE_PREFETCH_NUM 8
-#define PT_FIRST_AVAIL_BITS_SHIFT 10
-#define PT64_SECOND_AVAIL_BITS_SHIFT 54
-
/*
* The mask used to denote special SPTEs, which can be either MMIO SPTEs or
* Access Tracking SPTEs.
@@ -147,13 +144,6 @@ module_param(dbg, bool, 0644);
#define PT32_INDEX(address, level)\
(((address) >> PT32_LEVEL_SHIFT(level)) & ((1 << PT32_LEVEL_BITS) - 1))
-
-#ifdef CONFIG_DYNAMIC_PHYSICAL_MASK
-#define PT64_BASE_ADDR_MASK (physical_mask & ~(u64)(PAGE_SIZE-1))
-#else
-#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
-#endif
-
#define PT32_BASE_ADDR_MASK PAGE_MASK
#define PT32_DIR_BASE_ADDR_MASK \
(PAGE_MASK & ~((1ULL << (PAGE_SHIFT + PT32_LEVEL_BITS)) - 1))
@@ -170,9 +160,6 @@ module_param(dbg, bool, 0644);
#include <trace/events/kvm.h>
-#define SPTE_HOST_WRITEABLE (1ULL << PT_FIRST_AVAIL_BITS_SHIFT)
-#define SPTE_MMU_WRITEABLE (1ULL << (PT_FIRST_AVAIL_BITS_SHIFT + 1))
-
/* make pte_list_desc fit well in cache line */
#define PTE_LIST_EXT 3
@@ -1708,6 +1695,21 @@ static int kvm_unmap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
return kvm_zap_rmapp(kvm, rmap_head);
}
+u64 kvm_mmu_changed_pte_notifier_make_spte(u64 old_spte, kvm_pfn_t new_pfn)
+{
+ u64 new_spte;
+
+ new_spte = old_spte & ~PT64_BASE_ADDR_MASK;
+ new_spte |= (u64)new_pfn << PAGE_SHIFT;
+
+ new_spte &= ~PT_WRITABLE_MASK;
+ new_spte &= ~SPTE_HOST_WRITEABLE;
+
+ new_spte = mark_spte_for_access_track(new_spte);
+
+ return new_spte;
+}
+
static int kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
struct kvm_memory_slot *slot, gfn_t gfn, int level,
unsigned long data)
@@ -1733,13 +1735,8 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
pte_list_remove(rmap_head, sptep);
goto restart;
} else {
- new_spte = *sptep & ~PT64_BASE_ADDR_MASK;
- new_spte |= (u64)new_pfn << PAGE_SHIFT;
-
- new_spte &= ~PT_WRITABLE_MASK;
- new_spte &= ~SPTE_HOST_WRITEABLE;
-
- new_spte = mark_spte_for_access_track(new_spte);
+ new_spte = kvm_mmu_changed_pte_notifier_make_spte(
+ *sptep, new_pfn);
mmu_spte_clear_track_bits(sptep);
mmu_spte_set(sptep, new_spte);
@@ -1895,7 +1892,14 @@ int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end,
int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
{
- return kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp);
+ int r;
+
+ r = kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp);
+
+ if (kvm->arch.tdp_mmu_enabled)
+ r |= kvm_tdp_mmu_set_spte_hva(kvm, hva, &pte);
+
+ return r;
}
static int kvm_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 228bda0885552..8eaa6e4764bce 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -80,6 +80,12 @@ bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
(PT64_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \
* PT64_LEVEL_BITS))) - 1))
+#ifdef CONFIG_DYNAMIC_PHYSICAL_MASK
+#define PT64_BASE_ADDR_MASK (physical_mask & ~(u64)(PAGE_SIZE-1))
+#else
+#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
+#endif
+
extern u64 shadow_user_mask;
extern u64 shadow_accessed_mask;
extern u64 shadow_present_mask;
@@ -89,6 +95,12 @@ extern u64 shadow_present_mask;
#define ACC_USER_MASK PT_USER_MASK
#define ACC_ALL (ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK)
+#define PT_FIRST_AVAIL_BITS_SHIFT 10
+#define PT64_SECOND_AVAIL_BITS_SHIFT 54
+
+#define SPTE_HOST_WRITEABLE (1ULL << PT_FIRST_AVAIL_BITS_SHIFT)
+#define SPTE_MMU_WRITEABLE (1ULL << (PT_FIRST_AVAIL_BITS_SHIFT + 1))
+
/* Functions for interpreting SPTEs */
kvm_pfn_t spte_to_pfn(u64 pte);
bool is_mmio_spte(u64 spte);
@@ -138,5 +150,6 @@ bool is_nx_huge_page_enabled(void);
void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
u64 mark_spte_for_access_track(u64 spte);
+u64 kvm_mmu_changed_pte_notifier_make_spte(u64 old_spte, kvm_pfn_t new_pfn);
#endif /* __KVM_X86_MMU_INTERNAL_H */
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 0a4b98669b3ef..3119583409131 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -722,3 +722,64 @@ int kvm_tdp_mmu_test_age_hva(struct kvm *kvm, unsigned long hva)
return kvm_tdp_mmu_handle_hva_range(kvm, hva, hva + 1, 0,
test_age_gfn);
}
+
+/*
+ * Handle the changed_pte MMU notifier for the TDP MMU.
+ * data is a pointer to the new pte_t mapping the HVA specified by the MMU
+ * notifier.
+ * Returns non-zero if a flush is needed before releasing the MMU lock.
+ */
+static int set_tdp_spte(struct kvm *kvm, struct kvm_memory_slot *slot,
+ struct kvm_mmu_page *root, gfn_t gfn, gfn_t unused,
+ unsigned long data)
+{
+ struct tdp_iter iter;
+ pte_t *ptep = (pte_t *)data;
+ kvm_pfn_t new_pfn;
+ u64 new_spte;
+ int need_flush = 0;
+ int as_id = kvm_mmu_page_as_id(root);
+
+ WARN_ON(pte_huge(*ptep));
+
+ new_pfn = pte_pfn(*ptep);
+
+ for_each_tdp_pte_root(iter, root, gfn, gfn + 1) {
+ if (iter.level != PG_LEVEL_4K)
+ continue;
+
+ if (!is_shadow_present_pte(iter.old_spte))
+ break;
+
+ *iter.sptep = 0;
+ handle_changed_spte(kvm, as_id, iter.gfn, iter.old_spte,
+ new_spte, iter.level);
+
+ kvm_flush_remote_tlbs_with_address(kvm, iter.gfn, 1);
+
+ if (!pte_write(*ptep)) {
+ new_spte = kvm_mmu_changed_pte_notifier_make_spte(
+ iter.old_spte, new_pfn);
+
+ *iter.sptep = new_spte;
+ handle_changed_spte(kvm, as_id, iter.gfn, iter.old_spte,
+ new_spte, iter.level);
+ }
+
+ need_flush = 1;
+ }
+
+ if (need_flush)
+ kvm_flush_remote_tlbs_with_address(kvm, gfn, 1);
+
+ return 0;
+}
+
+int kvm_tdp_mmu_set_spte_hva(struct kvm *kvm, unsigned long address,
+ pte_t *host_ptep)
+{
+ return kvm_tdp_mmu_handle_hva_range(kvm, address, address + 1,
+ (unsigned long)host_ptep,
+ set_tdp_spte);
+}
+
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index f316773b7b5a8..5a399aa60b8d8 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -25,4 +25,7 @@ int kvm_tdp_mmu_zap_hva_range(struct kvm *kvm, unsigned long start,
int kvm_tdp_mmu_age_hva_range(struct kvm *kvm, unsigned long start,
unsigned long end);
int kvm_tdp_mmu_test_age_hva(struct kvm *kvm, unsigned long hva);
+
+int kvm_tdp_mmu_set_spte_hva(struct kvm *kvm, unsigned long address,
+ pte_t *host_ptep);
#endif /* __KVM_X86_MMU_TDP_MMU_H */
--
2.28.0.709.gb0816b6eb0-goog
next prev parent reply other threads:[~2020-09-25 21:23 UTC|newest]
Thread overview: 105+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-09-25 21:22 [PATCH 00/22] Introduce the TDP MMU Ben Gardon
2020-09-25 21:22 ` [PATCH 01/22] kvm: mmu: Separate making SPTEs from set_spte Ben Gardon
2020-09-30 4:55 ` Sean Christopherson
2020-09-30 23:03 ` Ben Gardon
2020-09-25 21:22 ` [PATCH 02/22] kvm: mmu: Introduce tdp_iter Ben Gardon
2020-09-26 0:04 ` Paolo Bonzini
2020-09-30 5:06 ` Sean Christopherson
2020-09-26 0:54 ` Paolo Bonzini
2020-09-30 5:08 ` Sean Christopherson
2020-09-30 5:24 ` Sean Christopherson
2020-09-30 6:24 ` Paolo Bonzini
2020-09-30 23:20 ` Eric van Tassell
2020-09-30 23:34 ` Paolo Bonzini
2020-10-01 0:07 ` Sean Christopherson
2020-09-25 21:22 ` [PATCH 03/22] kvm: mmu: Init / Uninit the TDP MMU Ben Gardon
2020-09-26 0:06 ` Paolo Bonzini
2020-09-30 5:34 ` Sean Christopherson
2020-09-30 18:36 ` Ben Gardon
2020-09-30 16:57 ` Sean Christopherson
2020-09-30 17:39 ` Paolo Bonzini
2020-09-30 18:42 ` Ben Gardon
2020-09-25 21:22 ` [PATCH 04/22] kvm: mmu: Allocate and free TDP MMU roots Ben Gardon
2020-09-30 6:06 ` Sean Christopherson
2020-09-30 6:26 ` Paolo Bonzini
2020-09-30 15:38 ` Sean Christopherson
2020-10-12 22:59 ` Ben Gardon
2020-10-12 23:59 ` Sean Christopherson
2020-09-25 21:22 ` [PATCH 05/22] kvm: mmu: Add functions to handle changed TDP SPTEs Ben Gardon
2020-09-26 0:39 ` Paolo Bonzini
2020-09-28 17:23 ` Paolo Bonzini
2020-09-25 21:22 ` [PATCH 06/22] kvm: mmu: Make address space ID a property of memslots Ben Gardon
2020-09-30 6:10 ` Sean Christopherson
2020-09-30 23:11 ` Ben Gardon
2020-09-25 21:22 ` [PATCH 07/22] kvm: mmu: Support zapping SPTEs in the TDP MMU Ben Gardon
2020-09-26 0:14 ` Paolo Bonzini
2020-09-30 6:15 ` Sean Christopherson
2020-09-30 6:28 ` Paolo Bonzini
2020-09-25 21:22 ` [PATCH 08/22] kvm: mmu: Separate making non-leaf sptes from link_shadow_page Ben Gardon
2020-09-25 21:22 ` [PATCH 09/22] kvm: mmu: Remove disallowed_hugepage_adjust shadow_walk_iterator arg Ben Gardon
2020-09-30 16:19 ` Sean Christopherson
2020-09-25 21:22 ` [PATCH 10/22] kvm: mmu: Add TDP MMU PF handler Ben Gardon
2020-09-26 0:24 ` Paolo Bonzini
2020-09-30 16:37 ` Sean Christopherson
2020-09-30 16:55 ` Paolo Bonzini
2020-09-30 17:37 ` Paolo Bonzini
2020-10-06 22:35 ` Ben Gardon
2020-10-06 22:33 ` Ben Gardon
2020-10-07 20:55 ` Sean Christopherson
2020-09-25 21:22 ` [PATCH 11/22] kvm: mmu: Factor out allocating a new tdp_mmu_page Ben Gardon
2020-09-26 0:22 ` Paolo Bonzini
2020-09-30 18:53 ` Ben Gardon
2020-09-25 21:22 ` [PATCH 12/22] kvm: mmu: Allocate struct kvm_mmu_pages for all pages in TDP MMU Ben Gardon
2020-09-25 21:22 ` [PATCH 13/22] kvm: mmu: Support invalidate range MMU notifier for " Ben Gardon
2020-09-30 17:03 ` Sean Christopherson
2020-09-30 23:15 ` Ben Gardon
2020-09-30 23:24 ` Sean Christopherson
2020-09-30 23:27 ` Ben Gardon
2020-09-25 21:22 ` [PATCH 14/22] kvm: mmu: Add access tracking for tdp_mmu Ben Gardon
2020-09-26 0:32 ` Paolo Bonzini
2020-09-30 17:48 ` Sean Christopherson
2020-10-06 23:38 ` Ben Gardon
2020-09-25 21:22 ` Ben Gardon [this message]
2020-09-26 0:33 ` [PATCH 15/22] kvm: mmu: Support changed pte notifier in tdp MMU Paolo Bonzini
2020-09-28 15:11 ` Paolo Bonzini
2020-10-07 16:53 ` Ben Gardon
2020-10-07 17:18 ` Paolo Bonzini
2020-10-07 17:30 ` Ben Gardon
2020-10-07 17:54 ` Paolo Bonzini
2020-09-25 21:22 ` [PATCH 16/22] kvm: mmu: Add dirty logging handler for changed sptes Ben Gardon
2020-09-26 0:45 ` Paolo Bonzini
2020-09-25 21:22 ` [PATCH 17/22] kvm: mmu: Support dirty logging for the TDP MMU Ben Gardon
2020-09-26 1:04 ` Paolo Bonzini
2020-10-08 18:27 ` Ben Gardon
2020-09-29 15:07 ` Paolo Bonzini
2020-09-30 18:04 ` Sean Christopherson
2020-09-30 18:08 ` Paolo Bonzini
2020-09-25 21:22 ` [PATCH 18/22] kvm: mmu: Support disabling dirty logging for the tdp MMU Ben Gardon
2020-09-26 1:09 ` Paolo Bonzini
2020-10-07 16:30 ` Ben Gardon
2020-10-07 17:21 ` Paolo Bonzini
2020-10-07 17:28 ` Ben Gardon
2020-10-07 17:53 ` Paolo Bonzini
2020-09-25 21:22 ` [PATCH 19/22] kvm: mmu: Support write protection for nesting in " Ben Gardon
2020-09-30 18:06 ` Sean Christopherson
2020-09-25 21:23 ` [PATCH 20/22] kvm: mmu: NX largepage recovery for TDP MMU Ben Gardon
2020-09-26 1:14 ` Paolo Bonzini
2020-09-30 22:23 ` Ben Gardon
2020-09-29 18:24 ` Paolo Bonzini
2020-09-30 18:15 ` Sean Christopherson
2020-09-30 19:56 ` Paolo Bonzini
2020-09-30 22:33 ` Ben Gardon
2020-09-30 22:27 ` Ben Gardon
2020-09-25 21:23 ` [PATCH 21/22] kvm: mmu: Support MMIO in the " Ben Gardon
2020-09-30 18:19 ` Sean Christopherson
2020-09-25 21:23 ` [PATCH 22/22] kvm: mmu: Don't clear write flooding count for direct roots Ben Gardon
2020-09-26 1:25 ` Paolo Bonzini
2020-10-05 22:48 ` Ben Gardon
2020-10-05 23:44 ` Sean Christopherson
2020-10-06 16:19 ` Ben Gardon
2020-09-26 1:14 ` [PATCH 00/22] Introduce the TDP MMU Paolo Bonzini
2020-09-28 17:31 ` Paolo Bonzini
2020-09-29 17:40 ` Ben Gardon
2020-09-29 18:10 ` Paolo Bonzini
2020-09-30 6:19 ` Sean Christopherson
2020-09-30 6:30 ` Paolo Bonzini
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=20200925212302.3979661-16-bgardon@google.com \
--to=bgardon@google.com \
--cc=cannonmatthews@google.com \
--cc=jmattson@google.com \
--cc=junaids@google.com \
--cc=kernellwp@gmail.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=pbonzini@redhat.com \
--cc=peterx@redhat.com \
--cc=pfeiner@google.com \
--cc=pshier@google.com \
--cc=sean.j.christopherson@intel.com \
--cc=vkuznets@redhat.com \
--cc=xiaoguangrong.eric@gmail.com \
--cc=yulei.kernel@gmail.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).