LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Alexandre Chartre <alexandre.chartre@oracle.com>
To: pbonzini@redhat.com, rkrcmar@redhat.com, tglx@linutronix.de,
	mingo@redhat.com, bp@alien8.de, hpa@zytor.com,
	dave.hansen@linux.intel.com, luto@kernel.org,
	peterz@infradead.org, kvm@vger.kernel.org, x86@kernel.org,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc: konrad.wilk@oracle.com, jan.setjeeilers@oracle.com,
	liran.alon@oracle.com, jwadams@google.com,
	alexandre.chartre@oracle.com
Subject: [RFC KVM 16/27] kvm/isolation: functions to clear page table entries for a VA range
Date: Mon, 13 May 2019 16:38:24 +0200	[thread overview]
Message-ID: <1557758315-12667-17-git-send-email-alexandre.chartre@oracle.com> (raw)
In-Reply-To: <1557758315-12667-1-git-send-email-alexandre.chartre@oracle.com>

These functions will be used to unmapped memory from the KVM
address space.

When clearing mapping in the KVM page table, check that the clearing
effectively happens in the KVM page table and there is no crossing of
the KVM page table boundary (with references to the kernel page table),
so that the kernel page table isn't mistakenly modified.

Information (address, size, page table level) about address ranges
mapped to the KVM page table is tracked, so mapping clearing is done
with just specified the start address of the range.

Signed-off-by: Alexandre Chartre <alexandre.chartre@oracle.com>
---
 arch/x86/kvm/isolation.c |  172 ++++++++++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/isolation.h |    1 +
 2 files changed, 173 insertions(+), 0 deletions(-)

diff --git a/arch/x86/kvm/isolation.c b/arch/x86/kvm/isolation.c
index c8358a9..e494a15 100644
--- a/arch/x86/kvm/isolation.c
+++ b/arch/x86/kvm/isolation.c
@@ -758,6 +758,178 @@ int kvm_copy_ptes(void *ptr, unsigned long size)
 }
 EXPORT_SYMBOL(kvm_copy_ptes);
 
+static void kvm_clear_pte_range(pmd_t *pmd, unsigned long addr,
+				unsigned long end)
+{
+	pte_t *pte;
+
+	pte = kvm_pte_offset(pmd, addr);
+	if (IS_ERR(pte)) {
+		pr_debug("PTE not found, skip clearing\n");
+		return;
+	}
+	do {
+		pr_debug("PTE: %lx/%lx clear[%lx]\n", addr, end, (long)pte);
+		pte_clear(NULL, addr, pte);
+	} while (pte++, addr += PAGE_SIZE, addr < end);
+}
+
+static void kvm_clear_pmd_range(pud_t *pud, unsigned long addr,
+				unsigned long end, enum page_table_level level)
+{
+	pmd_t *pmd;
+	unsigned long next;
+
+	pmd = kvm_pmd_offset(pud, addr);
+	if (IS_ERR(pmd)) {
+		pr_debug("PMD not found, skip clearing\n");
+		return;
+	}
+	do {
+		next = pmd_addr_end(addr, end);
+		if (pmd_none(*pmd))
+			continue;
+		BUG_ON(!pmd_present(*pmd));
+		if (level == PGT_LEVEL_PMD || pmd_trans_huge(*pmd) ||
+		    pmd_devmap(*pmd)) {
+			pr_debug("PMD: %lx/%lx clear[%lx]\n",
+			    addr, end, (long)pmd);
+			pmd_clear(pmd);
+			continue;
+		}
+		kvm_clear_pte_range(pmd, addr, next);
+	} while (pmd++, addr = next, addr < end);
+}
+
+static void kvm_clear_pud_range(p4d_t *p4d, unsigned long addr,
+				unsigned long end, enum page_table_level level)
+{
+	pud_t *pud;
+	unsigned long next;
+
+	pud = kvm_pud_offset(p4d, addr);
+	if (IS_ERR(pud)) {
+		pr_debug("PUD not found, skip clearing\n");
+		return;
+	}
+	do {
+		next = pud_addr_end(addr, end);
+		if (pud_none(*pud))
+			continue;
+		if (level == PGT_LEVEL_PUD || pud_trans_huge(*pud) ||
+		    pud_devmap(*pud)) {
+			pr_debug("PUD: %lx/%lx clear[%lx]\n",
+			    addr, end, (long)pud);
+			pud_clear(pud);
+			continue;
+		}
+		kvm_clear_pmd_range(pud, addr, next, level);
+	} while (pud++, addr = next, addr < end);
+}
+
+static void kvm_clear_p4d_range(pgd_t *pgd, unsigned long addr,
+				unsigned long end, enum page_table_level level)
+{
+	p4d_t *p4d;
+	unsigned long next;
+
+	p4d = kvm_p4d_offset(pgd, addr);
+	if (IS_ERR(p4d)) {
+		pr_debug("P4D not found, skip clearing\n");
+		return;
+	}
+
+	do {
+		next = p4d_addr_end(addr, end);
+		if (p4d_none(*p4d))
+			continue;
+		if (level == PGT_LEVEL_P4D) {
+			pr_debug("P4D: %lx/%lx clear[%lx]\n",
+			    addr, end, (long)p4d);
+			p4d_clear(p4d);
+			continue;
+		}
+		kvm_clear_pud_range(p4d, addr, next, level);
+	} while (p4d++, addr = next, addr < end);
+}
+
+static void kvm_clear_pgd_range(struct mm_struct *mm, unsigned long addr,
+				unsigned long end, enum page_table_level level)
+{
+	pgd_t *pgd;
+	unsigned long next;
+
+	pgd = pgd_offset(mm, addr);
+	do {
+		next = pgd_addr_end(addr, end);
+		if (pgd_none(*pgd))
+			continue;
+		if (level == PGT_LEVEL_PGD) {
+			pr_debug("PGD: %lx/%lx clear[%lx]\n",
+			    addr, end, (long)pgd);
+			pgd_clear(pgd);
+			continue;
+		}
+		kvm_clear_p4d_range(pgd, addr, next, level);
+	} while (pgd++, addr = next, addr < end);
+}
+
+/*
+ * Clear page table entries in the KVM page table. The level parameter
+ * specifies the page table level (PGD, P4D, PUD PMD, PTE) at which the
+ * clear should be done.
+ *
+ * WARNING: The KVM page table can have direct references to the kernel
+ * page table, at different levels (PGD, P4D, PUD, PMD). When clearing
+ * such references, if the level is incorrect (for example, clear at the
+ * PTE level while the mapping was done at PMD level), then the clearing
+ * will occur in the kernel page table and the system will likely crash
+ * on an unhandled page fault.
+ */
+static void kvm_clear_mapping(void *ptr, size_t size,
+			      enum page_table_level level)
+{
+	unsigned long start = (unsigned long)ptr;
+	unsigned long end = start + ((unsigned long)size);
+
+	pr_debug("CLEAR %px, %lx [%lx,%lx], level=%d\n",
+	    ptr, size, start, end, level);
+	kvm_clear_pgd_range(&kvm_mm, start, end, level);
+}
+
+/*
+ * Clear a range mapping in the KVM page table.
+ */
+void kvm_clear_range_mapping(void *ptr)
+{
+	struct kvm_range_mapping *range_mapping;
+	bool subset;
+
+	mutex_lock(&kvm_range_mapping_lock);
+
+	range_mapping = kvm_get_range_mapping_locked(ptr, &subset);
+	if (!range_mapping) {
+		mutex_unlock(&kvm_range_mapping_lock);
+		pr_debug("CLEAR %px - range not found\n", ptr);
+		return;
+	}
+	if (subset) {
+		mutex_unlock(&kvm_range_mapping_lock);
+		pr_debug("CLEAR %px - ignored, subset of %px/%lx/%d\n",
+			 ptr, range_mapping->ptr, range_mapping->size,
+			 range_mapping->level);
+		return;
+	}
+
+	kvm_clear_mapping(range_mapping->ptr, range_mapping->size,
+	    range_mapping->level);
+	list_del(&range_mapping->list);
+	mutex_unlock(&kvm_range_mapping_lock);
+
+	kfree(range_mapping);
+}
+EXPORT_SYMBOL(kvm_clear_range_mapping);
+
 
 static int kvm_isolation_init_mm(void)
 {
diff --git a/arch/x86/kvm/isolation.h b/arch/x86/kvm/isolation.h
index e8c018a..7d3c985 100644
--- a/arch/x86/kvm/isolation.h
+++ b/arch/x86/kvm/isolation.h
@@ -17,5 +17,6 @@ static inline bool kvm_isolation(void)
 extern void kvm_isolation_exit(void);
 extern void kvm_may_access_sensitive_data(struct kvm_vcpu *vcpu);
 extern int kvm_copy_ptes(void *ptr, unsigned long size);
+extern void kvm_clear_range_mapping(void *ptr);
 
 #endif
-- 
1.7.1


  parent reply	other threads:[~2019-05-13 14:40 UTC|newest]

Thread overview: 86+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-05-13 14:38 [RFC KVM 00/27] KVM Address Space Isolation Alexandre Chartre
2019-05-13 14:38 ` [RFC KVM 01/27] kernel: Export memory-management symbols required for KVM address space isolation Alexandre Chartre
2019-05-13 15:15   ` Peter Zijlstra
2019-05-13 15:17     ` Liran Alon
2019-05-13 14:38 ` [RFC KVM 02/27] KVM: x86: Introduce address_space_isolation module parameter Alexandre Chartre
2019-05-13 15:46   ` Andy Lutomirski
2019-05-13 15:55     ` Alexandre Chartre
2019-05-13 14:38 ` [RFC KVM 03/27] KVM: x86: Introduce KVM separate virtual address space Alexandre Chartre
2019-05-13 15:45   ` Andy Lutomirski
2019-05-13 16:04     ` Alexandre Chartre
2019-05-13 14:38 ` [RFC KVM 04/27] KVM: x86: Switch to KVM address space on entry to guest Alexandre Chartre
2019-05-13 14:38 ` [RFC KVM 05/27] KVM: x86: Add handler to exit kvm isolation Alexandre Chartre
2019-05-13 15:49   ` Andy Lutomirski
2019-05-13 16:10     ` Alexandre Chartre
2019-05-13 14:38 ` [RFC KVM 06/27] KVM: x86: Exit KVM isolation on IRQ entry Alexandre Chartre
2019-05-13 15:51   ` Andy Lutomirski
2019-05-13 16:28     ` Alexandre Chartre
2019-05-13 18:13       ` Andy Lutomirski
2019-05-14  7:07         ` Peter Zijlstra
2019-05-14  7:58           ` Alexandre Chartre
2019-05-13 14:38 ` [RFC KVM 07/27] KVM: x86: Switch to host address space when may access sensitive data Alexandre Chartre
2019-05-13 14:38 ` [RFC KVM 08/27] KVM: x86: Optimize branches which checks if address space isolation enabled Alexandre Chartre
2019-05-13 14:38 ` [RFC KVM 09/27] kvm/isolation: function to track buffers allocated for the KVM page table Alexandre Chartre
2019-05-13 14:38 ` [RFC KVM 10/27] kvm/isolation: add KVM page table entry free functions Alexandre Chartre
2019-05-13 14:38 ` [RFC KVM 11/27] kvm/isolation: add KVM page table entry offset functions Alexandre Chartre
2019-05-13 14:38 ` [RFC KVM 12/27] kvm/isolation: add KVM page table entry allocation functions Alexandre Chartre
2019-05-13 14:38 ` [RFC KVM 13/27] kvm/isolation: add KVM page table entry set functions Alexandre Chartre
2019-05-13 14:38 ` [RFC KVM 14/27] kvm/isolation: functions to copy page table entries for a VA range Alexandre Chartre
2019-05-13 14:38 ` [RFC KVM 15/27] kvm/isolation: keep track of VA range mapped in KVM address space Alexandre Chartre
2019-05-13 14:38 ` Alexandre Chartre [this message]
2019-05-13 14:38 ` [RFC KVM 17/27] kvm/isolation: improve mapping copy when mapping is already present Alexandre Chartre
2019-05-13 14:38 ` [RFC KVM 18/27] kvm/isolation: function to copy page table entries for percpu buffer Alexandre Chartre
2019-05-13 18:18   ` Andy Lutomirski
2019-05-14  7:09     ` Peter Zijlstra
2019-05-14  8:25       ` Alexandre Chartre
2019-05-14  8:34         ` Andy Lutomirski
2019-05-14  9:41           ` Alexandre Chartre
2019-05-14 15:23             ` Andy Lutomirski
2019-05-14 16:24               ` Alexandre Chartre
2019-05-14 17:05                 ` Peter Zijlstra
2019-05-14 18:09                   ` Sean Christopherson
2019-05-14 20:33                     ` Andy Lutomirski
2019-05-14 21:06                       ` Sean Christopherson
2019-05-14 21:55                         ` Andy Lutomirski
2019-05-14 22:38                           ` Sean Christopherson
2019-05-18  0:05                             ` Jonathan Adams
2019-05-14 20:27                   ` Andy Lutomirski
2019-05-13 14:38 ` [RFC KVM 19/27] kvm/isolation: initialize the KVM page table with core mappings Alexandre Chartre
2019-05-13 15:50   ` Dave Hansen
2019-05-13 16:00     ` Andy Lutomirski
2019-05-13 17:00       ` Alexandre Chartre
2019-05-13 16:46     ` Sean Christopherson
2019-05-13 16:47     ` Alexandre Chartre
2019-05-14 10:26       ` Alexandre Chartre
2019-05-13 14:38 ` [RFC KVM 20/27] kvm/isolation: initialize the KVM page table with vmx specific data Alexandre Chartre
2019-05-13 14:38 ` [RFC KVM 21/27] kvm/isolation: initialize the KVM page table with vmx VM data Alexandre Chartre
2019-05-13 14:38 ` [RFC KVM 22/27] kvm/isolation: initialize the KVM page table with vmx cpu data Alexandre Chartre
2019-05-13 14:38 ` [RFC KVM 23/27] kvm/isolation: initialize the KVM page table with the vcpu tasks Alexandre Chartre
2019-05-13 14:38 ` [RFC KVM 24/27] kvm/isolation: KVM page fault handler Alexandre Chartre
2019-05-13 15:15   ` Peter Zijlstra
2019-05-13 21:25     ` Liran Alon
2019-05-14  2:02       ` Andy Lutomirski
2019-05-14  7:21         ` Peter Zijlstra
2019-05-14 15:36           ` Alexandre Chartre
2019-05-14 15:43             ` Andy Lutomirski
2019-05-13 16:02   ` Andy Lutomirski
2019-05-13 16:21     ` Alexandre Chartre
2019-05-13 14:38 ` [RFC KVM 25/27] kvm/isolation: implement actual KVM isolation enter/exit Alexandre Chartre
2019-05-13 15:16   ` Peter Zijlstra
2019-05-13 16:01   ` Andy Lutomirski
2019-05-13 14:38 ` [RFC KVM 26/27] kvm/isolation: initialize the KVM page table with KVM memslots Alexandre Chartre
2019-05-13 14:38 ` [RFC KVM 27/27] kvm/isolation: initialize the KVM page table with KVM buses Alexandre Chartre
2019-05-13 16:42 ` [RFC KVM 00/27] KVM Address Space Isolation Liran Alon
2019-05-13 18:17 ` Andy Lutomirski
2019-05-13 21:08   ` Liran Alon
2019-05-14  2:07     ` Andy Lutomirski
2019-05-14  7:37       ` Peter Zijlstra
2019-05-14 21:32         ` Jan Setje-Eilers
2019-05-14  8:05       ` Liran Alon
2019-05-14  7:29     ` Peter Zijlstra
2019-05-14  7:57       ` Liran Alon
2019-05-14  8:33     ` Alexandre Chartre
2019-05-13 19:31 ` Nakajima, Jun
2019-05-13 21:16   ` Liran Alon
     [not found]     ` <D07C8F51-F2DF-4C8B-AB3B-0DFABD5F4C33@intel.com>
2019-05-13 21:53       ` Liran Alon
2019-05-15 12:52 ` Alexandre Chartre

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=1557758315-12667-17-git-send-email-alexandre.chartre@oracle.com \
    --to=alexandre.chartre@oracle.com \
    --cc=bp@alien8.de \
    --cc=dave.hansen@linux.intel.com \
    --cc=hpa@zytor.com \
    --cc=jan.setjeeilers@oracle.com \
    --cc=jwadams@google.com \
    --cc=konrad.wilk@oracle.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=liran.alon@oracle.com \
    --cc=luto@kernel.org \
    --cc=mingo@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rkrcmar@redhat.com \
    --cc=tglx@linutronix.de \
    --cc=x86@kernel.org \
    --subject='Re: [RFC KVM 16/27] kvm/isolation: functions to clear page table entries for a VA range' \
    /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

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).