LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Andy Lutomirski <luto@kernel.org>
To: X86 ML <x86@kernel.org>, Borislav Petkov <bp@alien8.de>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>,
	Steven Rostedt <rostedt@goodmis.org>,
	"security@kernel.org" <security@kernel.org>,
	Sasha Levin <sasha.levin@oracle.com>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	Boris Ostrovsky <boris.ostrovsky@oracle.com>,
	Andrew Cooper <andrew.cooper3@citrix.com>,
	Jan Beulich <jbeulich@suse.com>,
	xen-devel <xen-devel@lists.xen.org>,
	Andy Lutomirski <luto@kernel.org>
Subject: [PATCH v6 4/4] x86/ldt: Make modify_ldt optional
Date: Thu, 30 Jul 2015 14:31:34 -0700
Message-ID: <a605166a771c343fd64802dece77a903507333bd.1438291540.git.luto@kernel.org> (raw)
In-Reply-To: <cover.1438291540.git.luto@kernel.org>
In-Reply-To: <cover.1438291540.git.luto@kernel.org>

The modify_ldt syscall exposes a large attack surface and is
unnecessary for modern userspace.  Make it optional.

Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Andy Lutomirski <luto@kernel.org>
---
 arch/x86/Kconfig                   | 17 +++++++++++++++++
 arch/x86/include/asm/mmu.h         |  2 ++
 arch/x86/include/asm/mmu_context.h | 28 +++++++++++++++++++++-------
 arch/x86/kernel/Makefile           |  3 ++-
 arch/x86/kernel/cpu/perf_event.c   |  4 ++++
 arch/x86/kernel/process_64.c       |  2 ++
 arch/x86/kernel/step.c             |  2 ++
 kernel/sys_ni.c                    |  1 +
 8 files changed, 51 insertions(+), 8 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index b3a1a5d77d92..beabf30c7b52 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1015,6 +1015,7 @@ config VM86
 config X86_16BIT
 	bool "Enable support for 16-bit segments" if EXPERT
 	default y
+	depends on MODIFY_LDT_SYSCALL
 	---help---
 	  This option is required by programs like Wine to run 16-bit
 	  protected mode legacy code on x86 processors.  Disabling
@@ -2053,6 +2054,22 @@ config CMDLINE_OVERRIDE
 	  This is used to work around broken boot loaders.  This should
 	  be set to 'N' under normal conditions.
 
+config MODIFY_LDT_SYSCALL
+	bool "Enable the LDT (local descriptor table)" if EXPERT
+	default y
+	---help---
+	  Linux can allow user programs to install a per-process x86
+	  Local Descriptor Table (LDT) using the modify_ldt(2) system
+	  call.  This is required to run 16-bit or segmented code such as
+	  DOSEMU or some Wine programs.  It is also used by some very old
+	  threading libraries.
+
+	  Enabling this feature adds a small amount of overhead to
+	  context switches and increases the low-level kernel attack
+	  surface.  Disabling it removes the modify_ldt(2) system call.
+
+	  Saying 'N' here may make sense for embedded or server kernels.
+
 source "kernel/livepatch/Kconfig"
 
 endmenu
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 364d27481a52..55234d5e7160 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -9,7 +9,9 @@
  * we put the segment information here.
  */
 typedef struct {
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
 	struct ldt_struct *ldt;
+#endif
 
 #ifdef CONFIG_X86_64
 	/* True if mm supports a task running in 32 bit compatibility mode. */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 984abfe47edc..379cd3658799 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -33,6 +33,7 @@ static inline void load_mm_cr4(struct mm_struct *mm)
 static inline void load_mm_cr4(struct mm_struct *mm) {}
 #endif
 
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
 /*
  * ldt_structs can be allocated, used, and freed, but they are never
  * modified while live.
@@ -48,8 +49,23 @@ struct ldt_struct {
 	int size;
 };
 
+/*
+ * Used for LDT copy/destruction.
+ */
+int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
+void destroy_context(struct mm_struct *mm);
+#else	/* CONFIG_MODIFY_LDT_SYSCALL */
+static inline int init_new_context(struct task_struct *tsk,
+				   struct mm_struct *mm)
+{
+	return 0;
+}
+static inline void destroy_context(struct mm_struct *mm) {}
+#endif
+
 static inline void load_mm_ldt(struct mm_struct *mm)
 {
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
 	struct ldt_struct *ldt;
 
 	/* lockless_dereference synchronizes with smp_store_release */
@@ -73,17 +89,13 @@ static inline void load_mm_ldt(struct mm_struct *mm)
 		set_ldt(ldt->entries, ldt->size);
 	else
 		clear_LDT();
+#else
+	clear_LDT();
+#endif
 
 	DEBUG_LOCKS_WARN_ON(preemptible());
 }
 
-/*
- * Used for LDT copy/destruction.
- */
-int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
-void destroy_context(struct mm_struct *mm);
-
-
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
 #ifdef CONFIG_SMP
@@ -114,6 +126,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		/* Load per-mm CR4 state */
 		load_mm_cr4(next);
 
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
 		/*
 		 * Load the LDT, if the LDT is different.
 		 *
@@ -128,6 +141,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		 */
 		if (unlikely(prev->context.ldt != next->context.ldt))
 			load_mm_ldt(next);
+#endif
 	}
 #ifdef CONFIG_SMP
 	  else {
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 0f15af41bd80..2b507befcd3f 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -24,7 +24,8 @@ CFLAGS_irq.o := -I$(src)/../include/asm/trace
 
 obj-y			:= process_$(BITS).o signal.o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
-obj-y			+= time.o ioport.o ldt.o dumpstack.o nmi.o
+obj-y			+= time.o ioport.o dumpstack.o nmi.o
+obj-$(CONFIG_MODIFY_LDT_SYSCALL)	+= ldt.o
 obj-y			+= setup.o x86_init.o i8259.o irqinit.o jump_label.o
 obj-$(CONFIG_IRQ_WORK)  += irq_work.o
 obj-y			+= probe_roms.o
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 9469dfa55607..58b872ef2329 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -2179,6 +2179,7 @@ static unsigned long get_segment_base(unsigned int segment)
 	int idx = segment >> 3;
 
 	if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) {
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
 		struct ldt_struct *ldt;
 
 		if (idx > LDT_ENTRIES)
@@ -2190,6 +2191,9 @@ static unsigned long get_segment_base(unsigned int segment)
 			return 0;
 
 		desc = &ldt->entries[idx];
+#else
+		return 0;
+#endif
 	} else {
 		if (idx > GDT_ENTRIES)
 			return 0;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index f6b916387590..941295ddf802 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -121,6 +121,7 @@ void __show_regs(struct pt_regs *regs, int all)
 void release_thread(struct task_struct *dead_task)
 {
 	if (dead_task->mm) {
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
 		if (dead_task->mm->context.ldt) {
 			pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n",
 				dead_task->comm,
@@ -128,6 +129,7 @@ void release_thread(struct task_struct *dead_task)
 				dead_task->mm->context.ldt->size);
 			BUG();
 		}
+#endif
 	}
 }
 
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index 6273324186ac..fd88e152d584 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -18,6 +18,7 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re
 		return addr;
 	}
 
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
 	/*
 	 * We'll assume that the code segments in the GDT
 	 * are all zero-based. That is largely true: the
@@ -45,6 +46,7 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re
 		}
 		mutex_unlock(&child->mm->context.lock);
 	}
+#endif
 
 	return addr;
 }
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 7995ef5868d8..ca7d84f438f1 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -140,6 +140,7 @@ cond_syscall(sys_sgetmask);
 cond_syscall(sys_ssetmask);
 cond_syscall(sys_vm86old);
 cond_syscall(sys_vm86);
+cond_syscall(sys_modify_ldt);
 cond_syscall(sys_ipc);
 cond_syscall(compat_sys_ipc);
 cond_syscall(compat_sys_sysctl);
-- 
2.4.3


  parent reply index

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-07-30 21:31 [PATCH v6 0/4] x86: modify_ldt improvement, test, and config option Andy Lutomirski
2015-07-30 21:31 ` [PATCH v6 1/4] x86/xen: Probe target addresses in set_aliased_prot before the hypercall Andy Lutomirski
2015-07-31  9:41   ` [Xen-devel] " David Vrabel
2015-07-31 13:56   ` [tip:x86/asm] x86/xen: Probe target addresses in set_aliased_prot () " tip-bot for Andy Lutomirski
2015-07-30 21:31 ` [PATCH v6 2/4] x86/ldt: Make modify_ldt synchronous Andy Lutomirski
2015-07-30 22:50   ` Andrew Cooper
2015-07-31  3:15     ` Andy Lutomirski
2015-07-31 13:56   ` [tip:x86/asm] " tip-bot for Andy Lutomirski
2015-07-30 21:31 ` [PATCH v6 3/4] selftests/x86, x86/ldt: Add a selftest for modify_ldt Andy Lutomirski
2015-07-31 13:57   ` [tip:x86/asm] selftests/x86, x86/ldt: Add a selftest for modify_ldt() tip-bot for Andy Lutomirski
2015-07-30 21:31 ` Andy Lutomirski [this message]
2015-07-31 13:49   ` [PATCH v6 4/4] x86/ldt: Make modify_ldt optional Ingo Molnar
2015-07-31 14:02   ` [tip:x86/asm] x86/ldt: Make modify_ldt() optional tip-bot for Andy Lutomirski
2015-07-31  9:10 ` [PATCH v6 0/4] x86: modify_ldt improvement, test, and config option Andrew Cooper
2015-07-31 13:44   ` Boris Ostrovsky
2015-07-31 14:02     ` Andrew Cooper

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=a605166a771c343fd64802dece77a903507333bd.1438291540.git.luto@kernel.org \
    --to=luto@kernel.org \
    --cc=andrew.cooper3@citrix.com \
    --cc=boris.ostrovsky@oracle.com \
    --cc=bp@alien8.de \
    --cc=jbeulich@suse.com \
    --cc=konrad.wilk@oracle.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=sasha.levin@oracle.com \
    --cc=security@kernel.org \
    --cc=x86@kernel.org \
    --cc=xen-devel@lists.xen.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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git