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 09/27] kvm/isolation: function to track buffers allocated for the KVM page table
Date: Mon, 13 May 2019 16:38:17 +0200	[thread overview]
Message-ID: <1557758315-12667-10-git-send-email-alexandre.chartre@oracle.com> (raw)
In-Reply-To: <1557758315-12667-1-git-send-email-alexandre.chartre@oracle.com>

The KVM page table will have direct references to the kernel page table,
at different levels (PGD, P4D, PUD, PMD). When freeing the KVM page table,
we should make sure that we free parts actually allocated for the KVM
page table, and not parts of the kernel page table referenced from the
KVM page table. To do so, we will keep track of buffers when building
the KVM page table.

Signed-off-by: Alexandre Chartre <alexandre.chartre@oracle.com>
---
 arch/x86/kvm/isolation.c |  119 ++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 119 insertions(+), 0 deletions(-)

diff --git a/arch/x86/kvm/isolation.c b/arch/x86/kvm/isolation.c
index 43fd924..1efdab1 100644
--- a/arch/x86/kvm/isolation.c
+++ b/arch/x86/kvm/isolation.c
@@ -8,12 +8,60 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/printk.h>
+#include <linux/slab.h>
 
 #include <asm/mmu_context.h>
 #include <asm/pgalloc.h>
 
 #include "isolation.h"
 
+
+enum page_table_level {
+	PGT_LEVEL_PTE,
+	PGT_LEVEL_PMD,
+	PGT_LEVEL_PUD,
+	PGT_LEVEL_P4D,
+	PGT_LEVEL_PGD
+};
+
+/*
+ * The KVM page table can have direct references to the kernel page table,
+ * at different levels (PGD, P4D, PUD, PMD). When freeing the KVM page
+ * table, we should make sure that we free parts actually allocated for
+ * the KVM page table, and not parts of the kernel page table referenced
+ * from the KVM page table.
+ *
+ * To do so, page table directories (struct pgt_directory) are used to keep
+ * track of buffers allocated when building the KVM page table. Also, as
+ * a page table can have many buffers, page table directory groups (struct
+ * (pgt_directory_group) are used to group page table directories and save
+ * some space (instead of allocating each directory individually).
+ */
+
+#define PGT_DIRECTORY_GROUP_SIZE	64
+
+struct pgt_directory {
+	enum page_table_level level;
+	void *ptr;
+};
+
+struct pgt_directory_group {
+	struct list_head list;
+	int count;
+	struct pgt_directory directory[PGT_DIRECTORY_GROUP_SIZE];
+};
+
+static LIST_HEAD(kvm_pgt_dgroup_list);
+static DEFINE_MUTEX(kvm_pgt_dgroup_lock);
+
+/*
+ * Get the pointer to the beginning of a page table directory from a page
+ * table directory entry.
+ */
+#define PGTD_ALIGN(entry)	\
+	((typeof(entry))(((unsigned long)(entry)) & PAGE_MASK))
+
+
 struct mm_struct kvm_mm = {
 	.mm_rb			= RB_ROOT,
 	.mm_users		= ATOMIC_INIT(2),
@@ -43,6 +91,77 @@ struct mm_struct kvm_mm = {
 static bool __read_mostly address_space_isolation;
 module_param(address_space_isolation, bool, 0444);
 
+
+static struct pgt_directory_group *pgt_directory_group_create(void)
+{
+	struct pgt_directory_group *dgroup;
+
+	dgroup = kzalloc(sizeof(struct pgt_directory_group), GFP_KERNEL);
+	if (!dgroup)
+		return NULL;
+
+	INIT_LIST_HEAD(&dgroup->list);
+	dgroup->count = 0;
+
+	return dgroup;
+}
+
+static bool kvm_add_pgt_directory(void *ptr, enum page_table_level level)
+{
+	struct pgt_directory_group *dgroup;
+	int index;
+
+	mutex_lock(&kvm_pgt_dgroup_lock);
+
+	if (list_empty(&kvm_pgt_dgroup_list))
+		dgroup = NULL;
+	else
+		dgroup = list_entry(kvm_pgt_dgroup_list.next,
+				    struct pgt_directory_group, list);
+
+	if (!dgroup || dgroup->count >= PGT_DIRECTORY_GROUP_SIZE) {
+		dgroup = pgt_directory_group_create();
+		if (!dgroup) {
+			mutex_unlock(&kvm_pgt_dgroup_lock);
+			return false;
+		}
+		list_add_tail(&dgroup->list, &kvm_pgt_dgroup_list);
+	}
+
+	index = dgroup->count;
+	dgroup->directory[index].level = level;
+	dgroup->directory[index].ptr = PGTD_ALIGN(ptr);
+	dgroup->count = index + 1;
+
+	mutex_unlock(&kvm_pgt_dgroup_lock);
+
+	return true;
+}
+
+static bool kvm_valid_pgt_entry(void *ptr)
+{
+	struct pgt_directory_group *dgroup;
+	int i;
+
+	mutex_lock(&kvm_pgt_dgroup_lock);
+
+	ptr = PGTD_ALIGN(ptr);
+	list_for_each_entry(dgroup, &kvm_pgt_dgroup_list, list) {
+		for (i = 0; i < dgroup->count; i++) {
+			if (dgroup->directory[i].ptr == ptr) {
+				mutex_unlock(&kvm_pgt_dgroup_lock);
+				return true;
+			}
+		}
+	}
+
+	mutex_unlock(&kvm_pgt_dgroup_lock);
+
+	return false;
+
+}
+
+
 static int kvm_isolation_init_mm(void)
 {
 	pgd_t *kvm_pgd;
-- 
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 ` Alexandre Chartre [this message]
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 ` [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=1557758315-12667-10-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 09/27] kvm/isolation: function to track buffers allocated for the KVM page table' \
    /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).