From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
To: pbonzini@redhat.com, seanjc@google.com, dave.hansen@linux.intel.com
Cc: rick.p.edgecombe@intel.com, isaku.yamahata@intel.com,
kai.huang@intel.com, yan.y.zhao@intel.com, chao.gao@intel.com,
tglx@linutronix.de, mingo@redhat.com, bp@alien8.de,
kvm@vger.kernel.org, x86@kernel.org, linux-coco@lists.linux.dev,
linux-kernel@vger.kernel.org,
"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Subject: [PATCHv2 07/12] KVM: TDX: Preallocate PAMT pages to be used in page fault path
Date: Mon, 9 Jun 2025 22:13:35 +0300 [thread overview]
Message-ID: <20250609191340.2051741-8-kirill.shutemov@linux.intel.com> (raw)
In-Reply-To: <20250609191340.2051741-1-kirill.shutemov@linux.intel.com>
Preallocate a page to be used in the link_external_spt() and
set_external_spte() paths.
In the worst-case scenario, handling a page fault might require a
tdx_nr_pamt_pages() pages for each page table level.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
arch/x86/include/asm/kvm_host.h | 2 ++
arch/x86/include/asm/tdx.h | 2 ++
arch/x86/kvm/mmu/mmu.c | 7 +++++++
arch/x86/virt/vmx/tdx/tdx.c | 3 ++-
4 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 330cdcbed1a6..02dbbf848182 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -849,6 +849,8 @@ struct kvm_vcpu_arch {
*/
struct kvm_mmu_memory_cache mmu_external_spt_cache;
+ struct kvm_mmu_memory_cache pamt_page_cache;
+
/*
* QEMU userspace and the guest each have their own FPU state.
* In vcpu_run, we switch between the user and guest FPU contexts.
diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index d9a77147412f..47092eb13eb3 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -115,6 +115,7 @@ int tdx_guest_keyid_alloc(void);
u32 tdx_get_nr_guest_keyids(void);
void tdx_guest_keyid_free(unsigned int keyid);
+int tdx_nr_pamt_pages(void);
struct page *tdx_alloc_page(void);
void tdx_free_page(struct page *page);
@@ -188,6 +189,7 @@ static inline int tdx_enable(void) { return -ENODEV; }
static inline u32 tdx_get_nr_guest_keyids(void) { return 0; }
static inline const char *tdx_dump_mce_info(struct mce *m) { return NULL; }
static inline const struct tdx_sys_info *tdx_get_sysinfo(void) { return NULL; }
+static inline int tdx_nr_pamt_pages(void) { return 0; }
#endif /* CONFIG_INTEL_TDX_HOST */
#endif /* !__ASSEMBLER__ */
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index cbc84c6abc2e..d99bb27b5b01 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -616,6 +616,12 @@ static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu, bool maybe_indirect)
if (r)
return r;
}
+
+ r = kvm_mmu_topup_memory_cache(&vcpu->arch.pamt_page_cache,
+ tdx_nr_pamt_pages() * PT64_ROOT_MAX_LEVEL);
+ if (r)
+ return r;
+
return kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_page_header_cache,
PT64_ROOT_MAX_LEVEL);
}
@@ -626,6 +632,7 @@ static void mmu_free_memory_caches(struct kvm_vcpu *vcpu)
kvm_mmu_free_memory_cache(&vcpu->arch.mmu_shadow_page_cache);
kvm_mmu_free_memory_cache(&vcpu->arch.mmu_shadowed_info_cache);
kvm_mmu_free_memory_cache(&vcpu->arch.mmu_external_spt_cache);
+ kvm_mmu_free_memory_cache(&vcpu->arch.pamt_page_cache);
kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_header_cache);
}
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index c514c60e8c8d..4f9eaba4af4a 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -2001,13 +2001,14 @@ u64 tdh_phymem_page_wbinvd_hkid(u64 hkid, struct page *page)
}
EXPORT_SYMBOL_GPL(tdh_phymem_page_wbinvd_hkid);
-static int tdx_nr_pamt_pages(void)
+int tdx_nr_pamt_pages(void)
{
if (!tdx_supports_dynamic_pamt(&tdx_sysinfo))
return 0;
return tdx_sysinfo.tdmr.pamt_4k_entry_size * PTRS_PER_PTE / PAGE_SIZE;
}
+EXPORT_SYMBOL_GPL(tdx_nr_pamt_pages);
static u64 tdh_phymem_pamt_add(unsigned long hpa,
struct list_head *pamt_pages)
--
2.47.2
next prev parent reply other threads:[~2025-06-09 19:14 UTC|newest]
Thread overview: 90+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-06-09 19:13 [PATCHv2 00/12] TDX: Enable Dynamic PAMT Kirill A. Shutemov
2025-06-09 19:13 ` [PATCHv2 01/12] x86/tdx: Consolidate TDX error handling Kirill A. Shutemov
2025-06-25 17:58 ` Dave Hansen
2025-06-25 20:58 ` Edgecombe, Rick P
2025-06-25 21:27 ` Sean Christopherson
2025-06-25 21:46 ` Edgecombe, Rick P
2025-06-26 9:25 ` kirill.shutemov
2025-06-26 14:46 ` Dave Hansen
2025-06-26 15:51 ` Sean Christopherson
2025-06-26 16:59 ` Dave Hansen
2025-06-27 10:42 ` kirill.shutemov
2025-07-30 18:32 ` Edgecombe, Rick P
2025-07-31 23:31 ` Sean Christopherson
2025-07-31 23:46 ` Edgecombe, Rick P
2025-07-31 23:53 ` Sean Christopherson
2025-08-01 15:03 ` Edgecombe, Rick P
2025-08-06 15:19 ` Sean Christopherson
2025-06-26 0:05 ` Huang, Kai
2025-07-30 18:33 ` Edgecombe, Rick P
2025-06-09 19:13 ` [PATCHv2 02/12] x86/virt/tdx: Allocate page bitmap for Dynamic PAMT Kirill A. Shutemov
2025-06-25 18:06 ` Dave Hansen
2025-06-26 9:25 ` Kirill A. Shutemov
2025-07-31 1:06 ` Edgecombe, Rick P
2025-07-31 4:10 ` Huang, Kai
2025-06-26 11:08 ` Huang, Kai
2025-06-27 10:42 ` kirill.shutemov
2025-06-09 19:13 ` [PATCHv2 03/12] x86/virt/tdx: Allocate reference counters for PAMT memory Kirill A. Shutemov
2025-06-25 19:26 ` Dave Hansen
2025-06-27 11:27 ` Kirill A. Shutemov
2025-06-27 14:03 ` Dave Hansen
2025-06-26 0:53 ` Huang, Kai
2025-06-26 4:48 ` Huang, Kai
2025-06-27 11:35 ` kirill.shutemov
2025-06-09 19:13 ` [PATCHv2 04/12] x86/virt/tdx: Add tdx_alloc/free_page() helpers Kirill A. Shutemov
2025-06-10 2:36 ` Chao Gao
2025-06-10 14:51 ` [PATCHv2.1 " Kirill A. Shutemov
2025-06-25 18:01 ` Dave Hansen
2025-06-25 20:09 ` [PATCHv2 " Dave Hansen
2025-06-26 0:46 ` Chao Gao
2025-06-25 20:02 ` Dave Hansen
2025-06-27 13:00 ` Kirill A. Shutemov
2025-06-27 7:49 ` Adrian Hunter
2025-06-27 13:03 ` Kirill A. Shutemov
2025-06-09 19:13 ` [PATCHv2 05/12] KVM: TDX: Allocate PAMT memory in __tdx_td_init() Kirill A. Shutemov
2025-06-09 19:13 ` [PATCHv2 06/12] KVM: TDX: Allocate PAMT memory in tdx_td_vcpu_init() Kirill A. Shutemov
2025-06-09 19:13 ` Kirill A. Shutemov [this message]
2025-06-26 11:21 ` [PATCHv2 07/12] KVM: TDX: Preallocate PAMT pages to be used in page fault path Huang, Kai
2025-07-10 1:34 ` Edgecombe, Rick P
2025-07-10 7:49 ` kirill.shutemov
2025-06-09 19:13 ` [PATCHv2 08/12] KVM: TDX: Handle PAMT allocation in " Kirill A. Shutemov
2025-06-12 12:19 ` Chao Gao
2025-06-12 13:05 ` [PATCHv2.1 " Kirill A. Shutemov
2025-06-25 22:38 ` [PATCHv2 " Edgecombe, Rick P
2025-07-09 14:29 ` kirill.shutemov
2025-07-10 1:33 ` Edgecombe, Rick P
2025-07-10 8:45 ` kirill.shutemov
2025-08-21 19:21 ` Sagi Shahar
2025-08-21 19:35 ` Edgecombe, Rick P
2025-08-21 19:53 ` Sagi Shahar
2025-06-09 19:13 ` [PATCHv2 09/12] KVM: TDX: Reclaim PAMT memory Kirill A. Shutemov
2025-06-09 19:13 ` [PATCHv2 10/12] [NOT-FOR-UPSTREAM] x86/virt/tdx: Account PAMT memory and print it in /proc/meminfo Kirill A. Shutemov
2025-06-09 19:13 ` [PATCHv2 11/12] x86/virt/tdx: Enable Dynamic PAMT Kirill A. Shutemov
2025-06-09 19:13 ` [PATCHv2 12/12] Documentation/x86: Add documentation for TDX's " Kirill A. Shutemov
2025-06-25 13:25 ` [PATCHv2 00/12] TDX: Enable " Kirill A. Shutemov
2025-06-25 22:49 ` Edgecombe, Rick P
2025-06-27 13:05 ` kirill.shutemov
2025-08-08 23:18 ` Edgecombe, Rick P
2025-08-11 6:31 ` kas
2025-08-11 22:30 ` Edgecombe, Rick P
2025-08-12 2:02 ` Sean Christopherson
2025-08-12 2:31 ` Vishal Annapurve
2025-08-12 8:04 ` kas
2025-08-12 15:12 ` Edgecombe, Rick P
2025-08-12 16:15 ` Sean Christopherson
2025-08-12 18:39 ` Edgecombe, Rick P
2025-08-12 22:00 ` Vishal Annapurve
2025-08-12 23:34 ` Edgecombe, Rick P
2025-08-13 0:18 ` Vishal Annapurve
2025-08-13 0:51 ` Edgecombe, Rick P
2025-08-12 18:44 ` Vishal Annapurve
2025-08-13 8:09 ` Kiryl Shutsemau
2025-08-13 7:49 ` Kiryl Shutsemau
2025-08-12 8:03 ` kas
2025-08-13 22:43 ` Edgecombe, Rick P
2025-08-13 23:31 ` Dave Hansen
2025-08-14 0:14 ` Edgecombe, Rick P
2025-08-14 10:55 ` Kiryl Shutsemau
2025-08-15 1:03 ` Edgecombe, Rick P
2025-08-20 15:31 ` Sean Christopherson
2025-08-20 16:35 ` Edgecombe, Rick P
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=20250609191340.2051741-8-kirill.shutemov@linux.intel.com \
--to=kirill.shutemov@linux.intel.com \
--cc=bp@alien8.de \
--cc=chao.gao@intel.com \
--cc=dave.hansen@linux.intel.com \
--cc=isaku.yamahata@intel.com \
--cc=kai.huang@intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-coco@lists.linux.dev \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=pbonzini@redhat.com \
--cc=rick.p.edgecombe@intel.com \
--cc=seanjc@google.com \
--cc=tglx@linutronix.de \
--cc=x86@kernel.org \
--cc=yan.y.zhao@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).