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 24/27] kvm/isolation: KVM page fault handler
Date: Mon, 13 May 2019 16:38:32 +0200	[thread overview]
Message-ID: <1557758315-12667-25-git-send-email-alexandre.chartre@oracle.com> (raw)
In-Reply-To: <1557758315-12667-1-git-send-email-alexandre.chartre@oracle.com>

The KVM page fault handler handles page fault occurring while using
the KVM address space by switching to the kernel address space and
retrying the access (except if the fault occurs while switching
to the kernel address space). Processing of page faults occurring
while using the kernel address space is unchanged.

Page fault log is cleared when creating a vm so that page fault
information doesn't persist when qemu is stopped and restarted.

The KVM module parameter page_fault_stack can be used to disable
dumping stack trace when a page fault occurs while using the KVM
address space. The fault will still be reported but without the
stack trace.

Signed-off-by: Alexandre Chartre <alexandre.chartre@oracle.com>
---
 arch/x86/kernel/dumpstack.c |    1 +
 arch/x86/kvm/isolation.c    |  202 +++++++++++++++++++++++++++++++++++++++++++
 arch/x86/mm/fault.c         |   12 +++
 3 files changed, 215 insertions(+), 0 deletions(-)

diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 2b58864..aa28763 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -292,6 +292,7 @@ void show_stack(struct task_struct *task, unsigned long *sp)
 
 	show_trace_log_lvl(task, NULL, sp, KERN_DEFAULT);
 }
+EXPORT_SYMBOL(show_stack);
 
 void show_stack_regs(struct pt_regs *regs)
 {
diff --git a/arch/x86/kvm/isolation.c b/arch/x86/kvm/isolation.c
index e7979b3..db0a7ce 100644
--- a/arch/x86/kvm/isolation.c
+++ b/arch/x86/kvm/isolation.c
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/printk.h>
+#include <linux/sched/debug.h>
 #include <linux/slab.h>
 
 #include <asm/cpu_entry_area.h>
@@ -17,6 +18,9 @@
 
 #include "isolation.h"
 
+extern bool (*kvm_page_fault_handler)(struct pt_regs *regs,
+				      unsigned long error_code,
+				      unsigned long address);
 
 enum page_table_level {
 	PGT_LEVEL_PTE,
@@ -91,6 +95,25 @@ struct kvm_range_mapping {
 static LIST_HEAD(kvm_range_mapping_list);
 static DEFINE_MUTEX(kvm_range_mapping_lock);
 
+/*
+ * When a page fault occurs, while running with the KVM address space,
+ * the KVM page fault handler prints information about the fault (in
+ * particular the stack trace), and it switches back to the kernel
+ * address space.
+ *
+ * Information printed by the KVM page fault handler can be used to find
+ * out data not mapped in the KVM address space. Then the KVM address
+ * space can be augmented to include the missing mapping so that we don't
+ * fault at that same place anymore.
+ *
+ * The following variables keep track of page faults occurring while running
+ * with the KVM address space to prevent displaying the same information.
+ */
+
+#define KVM_LAST_FAULT_COUNT	128
+
+static unsigned long kvm_last_fault[KVM_LAST_FAULT_COUNT];
+
 
 struct mm_struct kvm_mm = {
 	.mm_rb			= RB_ROOT,
@@ -126,6 +149,14 @@ static void kvm_clear_mapping(void *ptr, size_t size,
 static bool __read_mostly address_space_isolation;
 module_param(address_space_isolation, bool, 0444);
 
+/*
+ * When set to true, KVM dumps the stack when a page fault occurs while
+ * running with the KVM address space. Otherwise the page fault is still
+ * reported but without the stack trace.
+ */
+static bool __read_mostly page_fault_stack = true;
+module_param(page_fault_stack, bool, 0444);
+
 static struct kvm_range_mapping *kvm_get_range_mapping_locked(void *ptr,
 							      bool *subset)
 {
@@ -1195,6 +1226,173 @@ static void kvm_reset_all_task_mapping(void)
 	mutex_unlock(&kvm_task_mapping_lock);
 }
 
+static int bad_address(void *p)
+{
+	unsigned long dummy;
+
+	return probe_kernel_address((unsigned long *)p, dummy);
+}
+
+static void kvm_dump_pagetable(pgd_t *base, unsigned long address)
+{
+	pgd_t *pgd = base + pgd_index(address);
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	pr_info("BASE %px ", base);
+
+	if (bad_address(pgd))
+		goto bad;
+
+	pr_cont("PGD %lx ", pgd_val(*pgd));
+
+	if (!pgd_present(*pgd))
+		goto out;
+
+	p4d = p4d_offset(pgd, address);
+	if (bad_address(p4d))
+		goto bad;
+
+	pr_cont("P4D %lx ", p4d_val(*p4d));
+	if (!p4d_present(*p4d) || p4d_large(*p4d))
+		goto out;
+
+	pud = pud_offset(p4d, address);
+	if (bad_address(pud))
+		goto bad;
+
+	pr_cont("PUD %lx ", pud_val(*pud));
+	if (!pud_present(*pud) || pud_large(*pud))
+		goto out;
+
+	pmd = pmd_offset(pud, address);
+	if (bad_address(pmd))
+		goto bad;
+
+	pr_cont("PMD %lx ", pmd_val(*pmd));
+	if (!pmd_present(*pmd) || pmd_large(*pmd))
+		goto out;
+
+	pte = pte_offset_kernel(pmd, address);
+	if (bad_address(pte))
+		goto bad;
+
+	pr_cont("PTE %lx", pte_val(*pte));
+out:
+	pr_cont("\n");
+	return;
+bad:
+	pr_info("BAD\n");
+}
+
+static void kvm_clear_page_fault(void)
+{
+	int i;
+
+	for (i = 0; i < KVM_LAST_FAULT_COUNT; i++)
+		kvm_last_fault[i] = 0;
+}
+
+static void kvm_log_page_fault(struct pt_regs *regs, unsigned long error_code,
+			       unsigned long address)
+{
+	int i;
+
+	/*
+	 * Log information about the fault only if this is a fault
+	 * we don't know about yet (or if the fault tracking buffer
+	 * is full).
+	 */
+	for (i = 0; i < KVM_LAST_FAULT_COUNT; i++) {
+		if (!kvm_last_fault[i]) {
+			kvm_last_fault[i] = regs->ip;
+			break;
+		}
+		if (kvm_last_fault[i] == regs->ip)
+			return;
+	}
+
+	if (i >= KVM_LAST_FAULT_COUNT)
+		pr_warn("KVM isolation: fault tracking buffer is full [%d]\n",
+			i);
+
+	pr_info("KVM isolation: page fault #%d (%ld) at %pS on %px (%pS)\n",
+		i, error_code, (void *)regs->ip,
+		(void *)address, (void *)address);
+	if (page_fault_stack)
+		show_stack(NULL, (unsigned long *)regs->sp);
+}
+
+/*
+ * KVM Page Fault Handler. The handler handles two simple cases:
+ *
+ * - If the fault occurs while using the kernel address space, then let
+ *   the kernel handles the fault normally.
+ *
+ * - If the fault occurs while using the KVM address space, then switch
+ *   to the kernel address space, and retry.
+ *
+ * It also handles a tricky case: if the fault occurs when using the KVM
+ * address space but while switching to the kernel address space then the
+ * switch is failing and we can't recover. In that case, we force switching
+ * to the kernel address space, print information and let the kernel
+ * handles the fault.
+ */
+static bool kvm_page_fault(struct pt_regs *regs, unsigned long error_code,
+			   unsigned long address)
+{
+	struct mm_struct *active_mm = current->active_mm;
+	unsigned long cr3;
+
+	/*
+	 * First, do a quick and simple test to see if we are using
+	 * the KVM address space. If we do then exit KVM isolation,
+	 * log the fault and report that we have handled the fault.
+	 */
+	if (likely(active_mm == &kvm_mm)) {
+		kvm_isolation_exit();
+		kvm_log_page_fault(regs, error_code, address);
+		return true;
+	}
+
+	/*
+	 * Verify that we are effectively using the kernel address space.
+	 * When switching address space, active_mm is not necessarily up
+	 * to date as it can already be set with the next mm while %cr3
+	 * has not been updated yet. So check loaded_mm which is updated
+	 * after %cr3.
+	 *
+	 * If we are effectively using the kernel address space then report
+	 * that we haven't handled the fault.
+	 */
+	if (this_cpu_read(cpu_tlbstate.loaded_mm) != &kvm_mm)
+		return false;
+
+	/*
+	 * We are actually using the KVM address space and faulting while
+	 * switching address space. Force swiching to the kernel address
+	 * space, log information and reported that we haven't handled
+	 * the fault.
+	 */
+	cr3 = __read_cr3();
+	write_cr3(build_cr3(active_mm->pgd, 0));
+	kvm_dump_pagetable(kvm_mm.pgd, address);
+	kvm_dump_pagetable(active_mm->pgd, address);
+	printk(KERN_DEFAULT "KVM isolation: page fault %ld at %pS on %lx (%pS) while switching mm\n"
+	       "  cr3=%lx\n"
+	       "  kvm_mm=%px pgd=%px\n"
+	       "  active_mm=%px pgd=%px\n",
+	       error_code, (void *)regs->ip, address, (void *)address,
+	       cr3,
+	       &kvm_mm, kvm_mm.pgd,
+	       active_mm, active_mm->pgd);
+	dump_stack();
+
+	return false;
+}
+
 
 static int kvm_isolation_init_page_table(void)
 {
@@ -1384,11 +1582,13 @@ static void kvm_isolation_uninit_mm(void)
 static void kvm_isolation_set_handlers(void)
 {
 	kvm_set_isolation_exit_handler(kvm_isolation_exit);
+	kvm_page_fault_handler = kvm_page_fault;
 }
 
 static void kvm_isolation_clear_handlers(void)
 {
 	kvm_set_isolation_exit_handler(NULL);
+	kvm_page_fault_handler = NULL;
 }
 
 int kvm_isolation_init_vm(struct kvm *kvm)
@@ -1396,6 +1596,8 @@ int kvm_isolation_init_vm(struct kvm *kvm)
 	if (!kvm_isolation())
 		return 0;
 
+	kvm_clear_page_fault();
+
 	pr_debug("mapping kvm srcu sda\n");
 
 	return (kvm_copy_percpu_mapping(kvm->srcu.sda,
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 46df4c6..317e105 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -33,6 +33,10 @@
 #define CREATE_TRACE_POINTS
 #include <asm/trace/exceptions.h>
 
+bool (*kvm_page_fault_handler)(struct pt_regs *regs, unsigned long error_code,
+			       unsigned long address);
+EXPORT_SYMBOL(kvm_page_fault_handler);
+
 /*
  * Returns 0 if mmiotrace is disabled, or if the fault is not
  * handled by mmiotrace:
@@ -1253,6 +1257,14 @@ static int fault_in_kernel_space(unsigned long address)
 	WARN_ON_ONCE(hw_error_code & X86_PF_PK);
 
 	/*
+	 * KVM might be able to handle the fault when running with the
+	 * KVM address space.
+	 */
+	if (kvm_page_fault_handler &&
+	    kvm_page_fault_handler(regs, hw_error_code, address))
+		return;
+
+	/*
 	 * We can fault-in kernel-space virtual memory on-demand. The
 	 * 'reference' page table is init_mm.pgd.
 	 *
-- 
1.7.1


  parent reply	other threads:[~2019-05-13 14:41 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 ` [RFC KVM 16/27] kvm/isolation: functions to clear page table entries for a VA range Alexandre Chartre
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 ` Alexandre Chartre [this message]
2019-05-13 15:15   ` [RFC KVM 24/27] kvm/isolation: KVM page fault handler 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=1557758315-12667-25-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 24/27] kvm/isolation: KVM page fault handler' \
    /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).