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, graf@amazon.de,
rppt@linux.vnet.ibm.com, alexandre.chartre@oracle.com
Subject: [RFC v2 01/26] mm/x86: Introduce kernel address space isolation
Date: Thu, 11 Jul 2019 16:25:13 +0200 [thread overview]
Message-ID: <1562855138-19507-2-git-send-email-alexandre.chartre@oracle.com> (raw)
In-Reply-To: <1562855138-19507-1-git-send-email-alexandre.chartre@oracle.com>
Introduce core functions and structures for implementing Address Space
Isolation (ASI). Kernel address space isolation provides the ability to
run some kernel code with a reduced kernel address space.
An address space isolation is defined with a struct asi structure which
has its own page-table. While, for now, this page-table is empty, it
will eventually be possible to populate it so that it is much smaller
than the full kernel page-table.
Isolation is entered by calling asi_enter() which switches the kernel
page-table to the address space isolation page-table. Isolation is then
exited by calling asi_exit() which switches the page-table back to the
kernel page-table.
Signed-off-by: Alexandre Chartre <alexandre.chartre@oracle.com>
---
arch/x86/include/asm/asi.h | 41 ++++++++++++
arch/x86/mm/Makefile | 2 +
arch/x86/mm/asi.c | 152 ++++++++++++++++++++++++++++++++++++++++++++
security/Kconfig | 10 +++
4 files changed, 205 insertions(+), 0 deletions(-)
create mode 100644 arch/x86/include/asm/asi.h
create mode 100644 arch/x86/mm/asi.c
diff --git a/arch/x86/include/asm/asi.h b/arch/x86/include/asm/asi.h
new file mode 100644
index 0000000..8a13f73
--- /dev/null
+++ b/arch/x86/include/asm/asi.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ARCH_X86_MM_ASI_H
+#define ARCH_X86_MM_ASI_H
+
+#ifdef CONFIG_ADDRESS_SPACE_ISOLATION
+
+#include <linux/spinlock.h>
+#include <asm/pgtable.h>
+
+struct asi {
+ spinlock_t lock; /* protect all attributes */
+ pgd_t *pgd; /* ASI page-table */
+};
+
+/*
+ * An ASI session maintains the state of address state isolation on a
+ * cpu. There is one ASI session per cpu. There is no lock to protect
+ * members of the asi_session structure as each cpu is managing its
+ * own ASI session.
+ */
+
+enum asi_session_state {
+ ASI_SESSION_STATE_INACTIVE, /* no address space isolation */
+ ASI_SESSION_STATE_ACTIVE, /* address space isolation is active */
+};
+
+struct asi_session {
+ struct asi *asi; /* ASI for this session */
+ enum asi_session_state state; /* state of ASI session */
+ unsigned long original_cr3; /* cr3 before entering ASI */
+ struct task_struct *task; /* task during isolation */
+} __aligned(PAGE_SIZE);
+
+extern struct asi *asi_create(void);
+extern void asi_destroy(struct asi *asi);
+extern int asi_enter(struct asi *asi);
+extern void asi_exit(struct asi *asi);
+
+#endif /* CONFIG_ADDRESS_SPACE_ISOLATION */
+
+#endif
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 84373dc..dae5c8a 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -49,7 +49,9 @@ obj-$(CONFIG_X86_INTEL_MPX) += mpx.o
obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o
obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o
obj-$(CONFIG_PAGE_TABLE_ISOLATION) += pti.o
+obj-$(CONFIG_ADDRESS_SPACE_ISOLATION) += asi.o
obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt.o
obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_identity.o
obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_boot.o
+
diff --git a/arch/x86/mm/asi.c b/arch/x86/mm/asi.c
new file mode 100644
index 0000000..c3993b7
--- /dev/null
+++ b/arch/x86/mm/asi.c
@@ -0,0 +1,152 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2019, Oracle and/or its affiliates. All rights reserved.
+ *
+ * Kernel Address Space Isolation (ASI)
+ */
+
+#include <linux/export.h>
+#include <linux/gfp.h>
+#include <linux/mm.h>
+#include <linux/printk.h>
+#include <linux/slab.h>
+
+#include <asm/asi.h>
+#include <asm/bug.h>
+#include <asm/mmu_context.h>
+
+/* ASI sessions, one per cpu */
+DEFINE_PER_CPU_PAGE_ALIGNED(struct asi_session, cpu_asi_session);
+
+static int asi_init_mapping(struct asi *asi)
+{
+ /*
+ * TODO: Populate the ASI page-table with minimal mappings so
+ * that we can at least enter isolation and abort.
+ */
+ return 0;
+}
+
+struct asi *asi_create(void)
+{
+ struct page *page;
+ struct asi *asi;
+ int err;
+
+ asi = kzalloc(sizeof(*asi), GFP_KERNEL);
+ if (!asi)
+ return NULL;
+
+ page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+ if (!page)
+ goto error;
+
+ asi->pgd = page_address(page);
+ spin_lock_init(&asi->lock);
+
+ err = asi_init_mapping(asi);
+ if (err)
+ goto error;
+
+ return asi;
+
+error:
+ asi_destroy(asi);
+ return NULL;
+}
+EXPORT_SYMBOL(asi_create);
+
+void asi_destroy(struct asi *asi)
+{
+ if (!asi)
+ return;
+
+ if (asi->pgd)
+ free_page((unsigned long)asi->pgd);
+
+ kfree(asi);
+}
+EXPORT_SYMBOL(asi_destroy);
+
+
+/*
+ * When isolation is active, the address space doesn't necessarily map
+ * the percpu offset value (this_cpu_off) which is used to get pointers
+ * to percpu variables. So functions which can be invoked while isolation
+ * is active shouldn't be getting pointers to percpu variables (i.e. with
+ * get_cpu_var() or this_cpu_ptr()). Instead percpu variable should be
+ * directly read or written to (i.e. with this_cpu_read() or
+ * this_cpu_write()).
+ */
+
+int asi_enter(struct asi *asi)
+{
+ enum asi_session_state state;
+ struct asi *current_asi;
+ struct asi_session *asi_session;
+
+ state = this_cpu_read(cpu_asi_session.state);
+ /*
+ * We can re-enter isolation, but only with the same ASI (we don't
+ * support nesting isolation). Also, if isolation is still active,
+ * then we should be re-entering with the same task.
+ */
+ if (state == ASI_SESSION_STATE_ACTIVE) {
+ current_asi = this_cpu_read(cpu_asi_session.asi);
+ if (current_asi != asi) {
+ WARN_ON(1);
+ return -EBUSY;
+ }
+ WARN_ON(this_cpu_read(cpu_asi_session.task) != current);
+ return 0;
+ }
+
+ /* isolation is not active so we can safely access the percpu pointer */
+ asi_session = &get_cpu_var(cpu_asi_session);
+ asi_session->asi = asi;
+ asi_session->task = current;
+ asi_session->original_cr3 = __get_current_cr3_fast();
+ if (!asi_session->original_cr3) {
+ WARN_ON(1);
+ err = -EINVAL;
+ goto err_clear_asi;
+ }
+ asi_session->state = ASI_SESSION_STATE_ACTIVE;
+
+ load_cr3(asi->pgd);
+
+ return 0;
+
+err_clear_asi:
+ asi_session->asi = NULL;
+ asi_session->task = NULL;
+
+ return err;
+
+}
+EXPORT_SYMBOL(asi_enter);
+
+void asi_exit(struct asi *asi)
+{
+ struct asi_session *asi_session;
+ enum asi_session_state asi_state;
+ unsigned long original_cr3;
+
+ asi_state = this_cpu_read(cpu_asi_session.state);
+ if (asi_state == ASI_SESSION_STATE_INACTIVE)
+ return;
+
+ /* TODO: Kick sibling hyperthread before switching to kernel cr3 */
+ original_cr3 = this_cpu_read(cpu_asi_session.original_cr3);
+ if (original_cr3)
+ write_cr3(original_cr3);
+
+ /* page-table was switched, we can now access the percpu pointer */
+ asi_session = &get_cpu_var(cpu_asi_session);
+ WARN_ON(asi_session->task != current);
+ asi_session->state = ASI_SESSION_STATE_INACTIVE;
+ asi_session->asi = NULL;
+ asi_session->task = NULL;
+ asi_session->original_cr3 = 0;
+}
+EXPORT_SYMBOL(asi_exit);
diff --git a/security/Kconfig b/security/Kconfig
index 466cc1f..241b9a7 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -65,6 +65,16 @@ config PAGE_TABLE_ISOLATION
See Documentation/x86/pti.txt for more details.
+config ADDRESS_SPACE_ISOLATION
+ bool "Allow code to run with a reduced kernel address space"
+ default y
+ depends on (X86_64 || X86_PAE) && !UML
+ help
+ This feature provides the ability to run some kernel code
+ with a reduced kernel address space. This can be used to
+ mitigate speculative execution attacks which are able to
+ leak data between sibling CPU hyper-threads.
+
config SECURITY_INFINIBAND
bool "Infiniband Security Hooks"
depends on SECURITY && INFINIBAND
--
1.7.1
next prev parent reply other threads:[~2019-07-11 14:30 UTC|newest]
Thread overview: 68+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-11 14:25 [RFC v2 00/27] Kernel Address Space Isolation Alexandre Chartre
2019-07-11 14:25 ` Alexandre Chartre [this message]
2019-07-11 21:33 ` [RFC v2 01/26] mm/x86: Introduce kernel address space isolation Thomas Gleixner
2019-07-12 7:43 ` Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 02/26] mm/asi: Abort isolation on interrupt, exception and context switch Alexandre Chartre
2019-07-11 20:11 ` Andi Kleen
2019-07-11 20:17 ` Mike Rapoport
2019-07-11 20:41 ` Alexandre Chartre
2019-07-12 0:05 ` Andy Lutomirski
2019-07-12 7:50 ` Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 03/26] mm/asi: Handle page fault due to address space isolation Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 04/26] mm/asi: Functions to track buffers allocated for an ASI page-table Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 05/26] mm/asi: Add ASI page-table entry offset functions Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 06/26] mm/asi: Add ASI page-table entry allocation functions Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 07/26] mm/asi: Add ASI page-table entry set functions Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 08/26] mm/asi: Functions to populate an ASI page-table from a VA range Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 09/26] mm/asi: Helper functions to map module into ASI Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 10/26] mm/asi: Keep track of VA ranges mapped in ASI page-table Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 11/26] mm/asi: Functions to clear ASI page-table entries for a VA range Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 12/26] mm/asi: Function to copy page-table entries for percpu buffer Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 13/26] mm/asi: Add asi_remap() function Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 14/26] mm/asi: Handle ASI mapped range leaks and overlaps Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 15/26] mm/asi: Initialize the ASI page-table with core mappings Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 16/26] mm/asi: Option to map current task into ASI Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 17/26] rcu: Move tree.h static forward declarations to tree.c Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 18/26] rcu: Make percpu rcu_data non-static Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 19/26] mm/asi: Add option to map RCU data Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 20/26] mm/asi: Add option to map cpu_hw_events Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 21/26] mm/asi: Make functions to read cr3/cr4 ASI aware Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 22/26] KVM: x86/asi: Introduce address_space_isolation module parameter Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 23/26] KVM: x86/asi: Introduce KVM address space isolation Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 24/26] KVM: x86/asi: Populate the KVM ASI page-table Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 25/26] KVM: x86/asi: Switch to KVM address space on entry to guest Alexandre Chartre
2019-07-11 14:25 ` [RFC v2 26/26] KVM: x86/asi: Map KVM memslots and IO buses into KVM ASI Alexandre Chartre
2019-07-11 14:40 ` [RFC v2 00/27] Kernel Address Space Isolation Alexandre Chartre
2019-07-11 22:38 ` Dave Hansen
2019-07-12 8:09 ` Alexandre Chartre
2019-07-12 13:51 ` Dave Hansen
2019-07-12 14:06 ` Alexandre Chartre
2019-07-12 15:23 ` Thomas Gleixner
2019-07-12 10:44 ` Thomas Gleixner
2019-07-12 11:56 ` Alexandre Chartre
2019-07-12 12:50 ` Peter Zijlstra
2019-07-12 13:43 ` Alexandre Chartre
2019-07-12 13:58 ` Dave Hansen
2019-07-12 14:36 ` Andy Lutomirski
2019-07-14 18:17 ` Alexander Graf
2019-07-12 13:54 ` Dave Hansen
2019-07-12 15:20 ` Peter Zijlstra
2019-07-12 15:16 ` Thomas Gleixner
2019-07-12 16:37 ` Alexandre Chartre
2019-07-12 16:45 ` Andy Lutomirski
2019-07-14 17:11 ` Mike Rapoport
2019-07-12 19:06 ` Peter Zijlstra
2019-07-14 15:06 ` Andy Lutomirski
2019-07-15 10:33 ` Peter Zijlstra
2019-07-12 19:48 ` Thomas Gleixner
2019-07-15 8:23 ` Alexandre Chartre
2019-07-15 8:28 ` Thomas Gleixner
2019-07-12 16:00 ` Thomas Gleixner
2019-07-12 11:44 ` Peter Zijlstra
2019-07-12 12:17 ` Alexandre Chartre
2019-07-12 12:36 ` Peter Zijlstra
2019-07-12 12:47 ` Alexandre Chartre
2019-07-12 13:07 ` Peter Zijlstra
2019-07-12 13:46 ` Alexandre Chartre
2019-07-31 16:31 ` Dario Faggioli
2019-08-22 12:31 ` 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=1562855138-19507-2-git-send-email-alexandre.chartre@oracle.com \
--to=alexandre.chartre@oracle.com \
--cc=bp@alien8.de \
--cc=dave.hansen@linux.intel.com \
--cc=graf@amazon.de \
--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=rppt@linux.vnet.ibm.com \
--cc=tglx@linutronix.de \
--cc=x86@kernel.org \
/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).