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 04/26] mm/asi: Functions to track buffers allocated for an ASI page-table
Date: Thu, 11 Jul 2019 16:25:16 +0200 [thread overview]
Message-ID: <1562855138-19507-5-git-send-email-alexandre.chartre@oracle.com> (raw)
In-Reply-To: <1562855138-19507-1-git-send-email-alexandre.chartre@oracle.com>
Add functions to track buffers allocated for an ASI page-table. An ASI
page-table can have direct references to the kernel page table, at
different levels (PGD, P4D, PUD, PMD). When freeing an ASI page-table,
we should make sure that we free parts actually allocated for the ASI
page-table, and not parts of the kernel page table referenced from the
ASI page-table. To do so, we will keep track of buffers when building
the ASI page-table.
Signed-off-by: Alexandre Chartre <alexandre.chartre@oracle.com>
---
arch/x86/include/asm/asi.h | 26 +++++++++++
arch/x86/mm/Makefile | 2 +-
arch/x86/mm/asi.c | 3 +
arch/x86/mm/asi_pagetable.c | 99 +++++++++++++++++++++++++++++++++++++++++++
4 files changed, 129 insertions(+), 1 deletions(-)
create mode 100644 arch/x86/mm/asi_pagetable.c
diff --git a/arch/x86/include/asm/asi.h b/arch/x86/include/asm/asi.h
index 013d77a..3d965e6 100644
--- a/arch/x86/include/asm/asi.h
+++ b/arch/x86/include/asm/asi.h
@@ -8,12 +8,35 @@
#include <linux/spinlock.h>
#include <asm/pgtable.h>
+#include <linux/xarray.h>
+
+enum page_table_level {
+ PGT_LEVEL_PTE,
+ PGT_LEVEL_PMD,
+ PGT_LEVEL_PUD,
+ PGT_LEVEL_P4D,
+ PGT_LEVEL_PGD
+};
#define ASI_FAULT_LOG_SIZE 128
struct asi {
spinlock_t lock; /* protect all attributes */
pgd_t *pgd; /* ASI page-table */
+
+ /*
+ * An ASI page-table can have direct references to the full kernel
+ * page-table, at different levels (PGD, P4D, PUD, PMD). When freeing
+ * an ASI page-table, we should make sure that we free parts actually
+ * allocated for the ASI page-table, and not part of the full kernel
+ * page-table referenced from the ASI page-table.
+ *
+ * To do so, the backend_pages XArray is used to keep track of pages
+ * used for the kernel isolation page-table.
+ */
+ struct xarray backend_pages; /* page-table pages */
+ unsigned long backend_pages_count; /* pages count */
+
spinlock_t fault_lock; /* protect fault_log */
unsigned long fault_log[ASI_FAULT_LOG_SIZE];
bool fault_stack; /* display stack of fault? */
@@ -43,6 +66,9 @@ struct asi_session {
DECLARE_PER_CPU_PAGE_ALIGNED(struct asi_session, cpu_asi_session);
+void asi_init_backend(struct asi *asi);
+void asi_fini_backend(struct asi *asi);
+
extern struct asi *asi_create(void);
extern void asi_destroy(struct asi *asi);
extern int asi_enter(struct asi *asi);
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index dae5c8a..b972f0f 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -49,7 +49,7 @@ 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_ADDRESS_SPACE_ISOLATION) += asi.o asi_pagetable.o
obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt.o
obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_identity.o
diff --git a/arch/x86/mm/asi.c b/arch/x86/mm/asi.c
index 717160d..dfde245 100644
--- a/arch/x86/mm/asi.c
+++ b/arch/x86/mm/asi.c
@@ -111,6 +111,7 @@ struct asi *asi_create(void)
asi->pgd = page_address(page);
spin_lock_init(&asi->lock);
spin_lock_init(&asi->fault_lock);
+ asi_init_backend(asi);
err = asi_init_mapping(asi);
if (err)
@@ -132,6 +133,8 @@ void asi_destroy(struct asi *asi)
if (asi->pgd)
free_page((unsigned long)asi->pgd);
+ asi_fini_backend(asi);
+
kfree(asi);
}
EXPORT_SYMBOL(asi_destroy);
diff --git a/arch/x86/mm/asi_pagetable.c b/arch/x86/mm/asi_pagetable.c
new file mode 100644
index 0000000..7a8f791
--- /dev/null
+++ b/arch/x86/mm/asi_pagetable.c
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2019, Oracle and/or its affiliates. All rights reserved.
+ *
+ */
+
+#include <asm/asi.h>
+
+/*
+ * Get the pointer to the beginning of a page table directory from a page
+ * table directory entry.
+ */
+#define ASI_BACKEND_PAGE_ALIGN(entry) \
+ ((typeof(entry))(((unsigned long)(entry)) & PAGE_MASK))
+
+/*
+ * Pages used to build the address space isolation page-table are stored
+ * in the backend_pages XArray. Each entry in the array is a logical OR
+ * of the page address and the page table level (PTE, PMD, PUD, P4D) this
+ * page is used for in the address space isolation page-table.
+ *
+ * As a page address is aligned with PAGE_SIZE, we have plenty of space
+ * for storing the page table level (which is a value between 0 and 4) in
+ * the low bits of the page address.
+ *
+ */
+
+#define ASI_BACKEND_PAGE_ENTRY(addr, level) \
+ ((typeof(addr))(((unsigned long)(addr)) | ((unsigned long)(level))))
+#define ASI_BACKEND_PAGE_ADDR(entry) \
+ ((void *)(((unsigned long)(entry)) & PAGE_MASK))
+#define ASI_BACKEND_PAGE_LEVEL(entry) \
+ ((enum page_table_level)(((unsigned long)(entry)) & ~PAGE_MASK))
+
+static int asi_add_backend_page(struct asi *asi, void *addr,
+ enum page_table_level level)
+{
+ unsigned long index;
+ void *old_entry;
+
+ if ((!addr) || ((unsigned long)addr) & ~PAGE_MASK)
+ return -EINVAL;
+
+ lockdep_assert_held(&asi->lock);
+ index = asi->backend_pages_count;
+
+ old_entry = xa_store(&asi->backend_pages, index,
+ ASI_BACKEND_PAGE_ENTRY(addr, level),
+ GFP_KERNEL);
+ if (xa_is_err(old_entry))
+ return xa_err(old_entry);
+ if (old_entry)
+ return -EBUSY;
+
+ asi->backend_pages_count++;
+
+ return 0;
+}
+
+void asi_init_backend(struct asi *asi)
+{
+ xa_init(&asi->backend_pages);
+}
+
+void asi_fini_backend(struct asi *asi)
+{
+ unsigned long index;
+ void *entry;
+
+ if (asi->backend_pages_count) {
+ xa_for_each(&asi->backend_pages, index, entry)
+ free_page((unsigned long)ASI_BACKEND_PAGE_ADDR(entry));
+ }
+}
+
+/*
+ * Check if an offset in the address space isolation page-table is valid,
+ * i.e. check that the offset is on a page effectively belonging to the
+ * address space isolation page-table.
+ */
+static bool asi_valid_offset(struct asi *asi, void *offset)
+{
+ unsigned long index;
+ void *addr, *entry;
+ bool valid;
+
+ addr = ASI_BACKEND_PAGE_ALIGN(offset);
+ valid = false;
+
+ lockdep_assert_held(&asi->lock);
+ xa_for_each(&asi->backend_pages, index, entry) {
+ if (ASI_BACKEND_PAGE_ADDR(entry) == addr) {
+ valid = true;
+ break;
+ }
+ }
+
+ return valid;
+}
--
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 ` [RFC v2 01/26] mm/x86: Introduce kernel address space isolation Alexandre Chartre
2019-07-11 21:33 ` 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 ` Alexandre Chartre [this message]
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=1562855138-19507-5-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).