summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2014-12-10 09:34:43 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2014-12-10 09:34:43 -0800
commit3eb5b893ebec7325ac9e6b8e4864af89a9ca1ed1 (patch)
treec1ced8c2c3eb68f14001fcca35d5b0eed8277a52
parent9e66645d72d3c395da92b0f8855c787f4b5f0e89 (diff)
parent9f7789f845cc100dd0d94fa1aa083e3373dc03db (diff)
Merge branch 'x86-mpx-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 MPX support from Thomas Gleixner: "This enables support for x86 MPX. MPX is a new debug feature for bound checking in user space. It requires kernel support to handle the bound tables and decode the bound violating instruction in the trap handler" * 'x86-mpx-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: asm-generic: Remove asm-generic arch_bprm_mm_init() mm: Make arch_unmap()/bprm_mm_init() available to all architectures x86: Cleanly separate use of asm-generic/mm_hooks.h x86 mpx: Change return type of get_reg_offset() fs: Do not include mpx.h in exec.c x86, mpx: Add documentation on Intel MPX x86, mpx: Cleanup unused bound tables x86, mpx: On-demand kernel allocation of bounds tables x86, mpx: Decode MPX instruction to get bound violation information x86, mpx: Add MPX-specific mmap interface x86, mpx: Introduce VM_MPX to indicate that a VMA is MPX specific x86, mpx: Add MPX to disabled features ia64: Sync struct siginfo with general version mips: Sync struct siginfo with general version mpx: Extend siginfo structure to include bound violation information x86, mpx: Rename cfg_reg_u and status_reg x86: mpx: Give bndX registers actual names x86: Remove arbitrary instruction size limit in instruction decoder
-rw-r--r--Documentation/x86/intel_mpx.txt234
-rw-r--r--arch/ia64/include/uapi/asm/siginfo.h8
-rw-r--r--arch/mips/include/uapi/asm/siginfo.h4
-rw-r--r--arch/s390/include/asm/mmu_context.h11
-rw-r--r--arch/um/include/asm/mmu_context.h24
-rw-r--r--arch/unicore32/include/asm/mmu_context.h11
-rw-r--r--arch/x86/Kconfig4
-rw-r--r--arch/x86/include/asm/disabled-features.h8
-rw-r--r--arch/x86/include/asm/insn.h10
-rw-r--r--arch/x86/include/asm/mmu_context.h26
-rw-r--r--arch/x86/include/asm/mpx.h103
-rw-r--r--arch/x86/include/asm/paravirt.h16
-rw-r--r--arch/x86/include/asm/processor.h33
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c17
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_lbr.c25
-rw-r--r--arch/x86/kernel/kprobes/core.c8
-rw-r--r--arch/x86/kernel/kprobes/opt.c4
-rw-r--r--arch/x86/kernel/setup.c2
-rw-r--r--arch/x86/kernel/traps.c85
-rw-r--r--arch/x86/kernel/uprobes.c2
-rw-r--r--arch/x86/lib/insn.c5
-rw-r--r--arch/x86/mm/Makefile2
-rw-r--r--arch/x86/mm/mpx.c928
-rw-r--r--arch/x86/tools/insn_sanity.c2
-rw-r--r--arch/x86/tools/test_get_len.c2
-rw-r--r--fs/exec.c1
-rw-r--r--fs/proc/task_mmu.c3
-rw-r--r--include/asm-generic/mm_hooks.h17
-rw-r--r--include/linux/mm.h6
-rw-r--r--include/linux/mm_types.h4
-rw-r--r--include/uapi/asm-generic/siginfo.h9
-rw-r--r--include/uapi/linux/prctl.h6
-rw-r--r--kernel/signal.c4
-rw-r--r--kernel/sys.c12
-rw-r--r--mm/mmap.c2
35 files changed, 1591 insertions, 47 deletions
diff --git a/Documentation/x86/intel_mpx.txt b/Documentation/x86/intel_mpx.txt
new file mode 100644
index 000000000000..4472ed2ad921
--- /dev/null
+++ b/Documentation/x86/intel_mpx.txt
@@ -0,0 +1,234 @@
+1. Intel(R) MPX Overview
+========================
+
+Intel(R) Memory Protection Extensions (Intel(R) MPX) is a new capability
+introduced into Intel Architecture. Intel MPX provides hardware features
+that can be used in conjunction with compiler changes to check memory
+references, for those references whose compile-time normal intentions are
+usurped at runtime due to buffer overflow or underflow.
+
+For more information, please refer to Intel(R) Architecture Instruction
+Set Extensions Programming Reference, Chapter 9: Intel(R) Memory Protection
+Extensions.
+
+Note: Currently no hardware with MPX ISA is available but it is always
+possible to use SDE (Intel(R) Software Development Emulator) instead, which
+can be downloaded from
+http://software.intel.com/en-us/articles/intel-software-development-emulator
+
+
+2. How to get the advantage of MPX
+==================================
+
+For MPX to work, changes are required in the kernel, binutils and compiler.
+No source changes are required for applications, just a recompile.
+
+There are a lot of moving parts of this to all work right. The following
+is how we expect the compiler, application and kernel to work together.
+
+1) Application developer compiles with -fmpx. The compiler will add the
+ instrumentation as well as some setup code called early after the app
+ starts. New instruction prefixes are noops for old CPUs.
+2) That setup code allocates (virtual) space for the "bounds directory",
+ points the "bndcfgu" register to the directory and notifies the kernel
+ (via the new prctl(PR_MPX_ENABLE_MANAGEMENT)) that the app will be using
+ MPX.
+3) The kernel detects that the CPU has MPX, allows the new prctl() to
+ succeed, and notes the location of the bounds directory. Userspace is
+ expected to keep the bounds directory at that locationWe note it
+ instead of reading it each time because the 'xsave' operation needed
+ to access the bounds directory register is an expensive operation.
+4) If the application needs to spill bounds out of the 4 registers, it
+ issues a bndstx instruction. Since the bounds directory is empty at
+ this point, a bounds fault (#BR) is raised, the kernel allocates a
+ bounds table (in the user address space) and makes the relevant entry
+ in the bounds directory point to the new table.
+5) If the application violates the bounds specified in the bounds registers,
+ a separate kind of #BR is raised which will deliver a signal with
+ information about the violation in the 'struct siginfo'.
+6) Whenever memory is freed, we know that it can no longer contain valid
+ pointers, and we attempt to free the associated space in the bounds
+ tables. If an entire table becomes unused, we will attempt to free
+ the table and remove the entry in the directory.
+
+To summarize, there are essentially three things interacting here:
+
+GCC with -fmpx:
+ * enables annotation of code with MPX instructions and prefixes
+ * inserts code early in the application to call in to the "gcc runtime"
+GCC MPX Runtime:
+ * Checks for hardware MPX support in cpuid leaf
+ * allocates virtual space for the bounds directory (malloc() essentially)
+ * points the hardware BNDCFGU register at the directory
+ * calls a new prctl(PR_MPX_ENABLE_MANAGEMENT) to notify the kernel to
+ start managing the bounds directories
+Kernel MPX Code:
+ * Checks for hardware MPX support in cpuid leaf
+ * Handles #BR exceptions and sends SIGSEGV to the app when it violates
+ bounds, like during a buffer overflow.
+ * When bounds are spilled in to an unallocated bounds table, the kernel
+ notices in the #BR exception, allocates the virtual space, then
+ updates the bounds directory to point to the new table. It keeps
+ special track of the memory with a VM_MPX flag.
+ * Frees unused bounds tables at the time that the memory they described
+ is unmapped.
+
+
+3. How does MPX kernel code work
+================================
+
+Handling #BR faults caused by MPX
+---------------------------------
+
+When MPX is enabled, there are 2 new situations that can generate
+#BR faults.
+ * new bounds tables (BT) need to be allocated to save bounds.
+ * bounds violation caused by MPX instructions.
+
+We hook #BR handler to handle these two new situations.
+
+On-demand kernel allocation of bounds tables
+--------------------------------------------
+
+MPX only has 4 hardware registers for storing bounds information. If
+MPX-enabled code needs more than these 4 registers, it needs to spill
+them somewhere. It has two special instructions for this which allow
+the bounds to be moved between the bounds registers and some new "bounds
+tables".
+
+#BR exceptions are a new class of exceptions just for MPX. They are
+similar conceptually to a page fault and will be raised by the MPX
+hardware during both bounds violations or when the tables are not
+present. The kernel handles those #BR exceptions for not-present tables
+by carving the space out of the normal processes address space and then
+pointing the bounds-directory over to it.
+
+The tables need to be accessed and controlled by userspace because
+the instructions for moving bounds in and out of them are extremely
+frequent. They potentially happen every time a register points to
+memory. Any direct kernel involvement (like a syscall) to access the
+tables would obviously destroy performance.
+
+Why not do this in userspace? MPX does not strictly require anything in
+the kernel. It can theoretically be done completely from userspace. Here
+are a few ways this could be done. We don't think any of them are practical
+in the real-world, but here they are.
+
+Q: Can virtual space simply be reserved for the bounds tables so that we
+ never have to allocate them?
+A: MPX-enabled application will possibly create a lot of bounds tables in
+ process address space to save bounds information. These tables can take
+ up huge swaths of memory (as much as 80% of the memory on the system)
+ even if we clean them up aggressively. In the worst-case scenario, the
+ tables can be 4x the size of the data structure being tracked. IOW, a
+ 1-page structure can require 4 bounds-table pages. An X-GB virtual
+ area needs 4*X GB of virtual space, plus 2GB for the bounds directory.
+ If we were to preallocate them for the 128TB of user virtual address
+ space, we would need to reserve 512TB+2GB, which is larger than the
+ entire virtual address space today. This means they can not be reserved
+ ahead of time. Also, a single process's pre-popualated bounds directory
+ consumes 2GB of virtual *AND* physical memory. IOW, it's completely
+ infeasible to prepopulate bounds directories.
+
+Q: Can we preallocate bounds table space at the same time memory is
+ allocated which might contain pointers that might eventually need
+ bounds tables?
+A: This would work if we could hook the site of each and every memory
+ allocation syscall. This can be done for small, constrained applications.
+ But, it isn't practical at a larger scale since a given app has no
+ way of controlling how all the parts of the app might allocate memory
+ (think libraries). The kernel is really the only place to intercept
+ these calls.
+
+Q: Could a bounds fault be handed to userspace and the tables allocated
+ there in a signal handler intead of in the kernel?
+A: mmap() is not on the list of safe async handler functions and even
+ if mmap() would work it still requires locking or nasty tricks to
+ keep track of the allocation state there.
+
+Having ruled out all of the userspace-only approaches for managing
+bounds tables that we could think of, we create them on demand in
+the kernel.
+
+Decoding MPX instructions
+-------------------------
+
+If a #BR is generated due to a bounds violation caused by MPX.
+We need to decode MPX instructions to get violation address and
+set this address into extended struct siginfo.
+
+The _sigfault feild of struct siginfo is extended as follow:
+
+87 /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
+88 struct {
+89 void __user *_addr; /* faulting insn/memory ref. */
+90 #ifdef __ARCH_SI_TRAPNO
+91 int _trapno; /* TRAP # which caused the signal */
+92 #endif
+93 short _addr_lsb; /* LSB of the reported address */
+94 struct {
+95 void __user *_lower;
+96 void __user *_upper;
+97 } _addr_bnd;
+98 } _sigfault;
+
+The '_addr' field refers to violation address, and new '_addr_and'
+field refers to the upper/lower bounds when a #BR is caused.
+
+Glibc will be also updated to support this new siginfo. So user
+can get violation address and bounds when bounds violations occur.
+
+Cleanup unused bounds tables
+----------------------------
+
+When a BNDSTX instruction attempts to save bounds to a bounds directory
+entry marked as invalid, a #BR is generated. This is an indication that
+no bounds table exists for this entry. In this case the fault handler
+will allocate a new bounds table on demand.
+
+Since the kernel allocated those tables on-demand without userspace
+knowledge, it is also responsible for freeing them when the associated
+mappings go away.
+
+Here, the solution for this issue is to hook do_munmap() to check
+whether one process is MPX enabled. If yes, those bounds tables covered
+in the virtual address region which is being unmapped will be freed also.
+
+Adding new prctl commands
+-------------------------
+
+Two new prctl commands are added to enable and disable MPX bounds tables
+management in kernel.
+
+155 #define PR_MPX_ENABLE_MANAGEMENT 43
+156 #define PR_MPX_DISABLE_MANAGEMENT 44
+
+Runtime library in userspace is responsible for allocation of bounds
+directory. So kernel have to use XSAVE instruction to get the base
+of bounds directory from BNDCFG register.
+
+But XSAVE is expected to be very expensive. In order to do performance
+optimization, we have to get the base of bounds directory and save it
+into struct mm_struct to be used in future during PR_MPX_ENABLE_MANAGEMENT
+command execution.
+
+
+4. Special rules
+================
+
+1) If userspace is requesting help from the kernel to do the management
+of bounds tables, it may not create or modify entries in the bounds directory.
+
+Certainly users can allocate bounds tables and forcibly point the bounds
+directory at them through XSAVE instruction, and then set valid bit
+of bounds entry to have this entry valid. But, the kernel will decline
+to assist in managing these tables.
+
+2) Userspace may not take multiple bounds directory entries and point
+them at the same bounds table.
+
+This is allowed architecturally. See more information "Intel(R) Architecture
+Instruction Set Extensions Programming Reference" (9.3.4).
+
+However, if users did this, the kernel might be fooled in to unmaping an
+in-use bounds table since it does not recognize sharing.
diff --git a/arch/ia64/include/uapi/asm/siginfo.h b/arch/ia64/include/uapi/asm/siginfo.h
index 4ea6225196bb..bce9bc1a66c4 100644
--- a/arch/ia64/include/uapi/asm/siginfo.h
+++ b/arch/ia64/include/uapi/asm/siginfo.h
@@ -63,6 +63,10 @@ typedef struct siginfo {
unsigned int _flags; /* see below */
unsigned long _isr; /* isr */
short _addr_lsb; /* lsb of faulting address */
+ struct {
+ void __user *_lower;
+ void __user *_upper;
+ } _addr_bnd;
} _sigfault;
/* SIGPOLL */
@@ -110,9 +114,9 @@ typedef struct siginfo {
/*
* SIGSEGV si_codes
*/
-#define __SEGV_PSTKOVF (__SI_FAULT|3) /* paragraph stack overflow */
+#define __SEGV_PSTKOVF (__SI_FAULT|4) /* paragraph stack overflow */
#undef NSIGSEGV
-#define NSIGSEGV 3
+#define NSIGSEGV 4
#undef NSIGTRAP
#define NSIGTRAP 4
diff --git a/arch/mips/include/uapi/asm/siginfo.h b/arch/mips/include/uapi/asm/siginfo.h
index e81174432bab..d08f83f19db5 100644
--- a/arch/mips/include/uapi/asm/siginfo.h
+++ b/arch/mips/include/uapi/asm/siginfo.h
@@ -92,6 +92,10 @@ typedef struct siginfo {
int _trapno; /* TRAP # which caused the signal */
#endif
short _addr_lsb;
+ struct {
+ void __user *_lower;
+ void __user *_upper;
+ } _addr_bnd;
} _sigfault;
/* SIGPOLL, SIGXFSZ (To do ...) */
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 3815bfea1b2d..f49b71954654 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -120,4 +120,15 @@ static inline void arch_exit_mmap(struct mm_struct *mm)
{
}
+static inline void arch_unmap(struct mm_struct *mm,
+ struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+}
+
+static inline void arch_bprm_mm_init(struct mm_struct *mm,
+ struct vm_area_struct *vma)
+{
+}
+
#endif /* __S390_MMU_CONTEXT_H */
diff --git a/arch/um/include/asm/mmu_context.h b/arch/um/include/asm/mmu_context.h
index aa4a743dc4ab..941527e507f7 100644
--- a/arch/um/include/asm/mmu_context.h
+++ b/arch/um/include/asm/mmu_context.h
@@ -10,7 +10,26 @@
#include <asm/mmu.h>
extern void uml_setup_stubs(struct mm_struct *mm);
+/*
+ * Needed since we do not use the asm-generic/mm_hooks.h:
+ */
+static inline void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
+{
+ uml_setup_stubs(mm);
+}
extern void arch_exit_mmap(struct mm_struct *mm);
+static inline void arch_unmap(struct mm_struct *mm,
+ struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+}
+static inline void arch_bprm_mm_init(struct mm_struct *mm,
+ struct vm_area_struct *vma)
+{
+}
+/*
+ * end asm-generic/mm_hooks.h functions
+ */
#define deactivate_mm(tsk,mm) do { } while (0)
@@ -41,11 +60,6 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
}
}
-static inline void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
-{
- uml_setup_stubs(mm);
-}
-
static inline void enter_lazy_tlb(struct mm_struct *mm,
struct task_struct *tsk)
{
diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h
index ef470a7a3d0f..1cb5220afaf9 100644
--- a/arch/unicore32/include/asm/mmu_context.h
+++ b/arch/unicore32/include/asm/mmu_context.h
@@ -86,4 +86,15 @@ static inline void arch_dup_mmap(struct mm_struct *oldmm,
{
}
+static inline void arch_unmap(struct mm_struct *mm,
+ struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+}
+
+static inline void arch_bprm_mm_init(struct mm_struct *mm,
+ struct vm_area_struct *vma)
+{
+}
+
#endif
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 41a503c15862..666ac6651c17 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -248,6 +248,10 @@ config HAVE_INTEL_TXT
def_bool y
depends on INTEL_IOMMU && ACPI
+config X86_INTEL_MPX
+ def_bool y
+ depends on CPU_SUP_INTEL
+
config X86_32_SMP
def_bool y
depends on X86_32 && SMP
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 97534a7d38e3..f226df064660 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -10,6 +10,12 @@
* cpu_feature_enabled().
*/
+#ifdef CONFIG_X86_INTEL_MPX
+# define DISABLE_MPX 0
+#else
+# define DISABLE_MPX (1<<(X86_FEATURE_MPX & 31))
+#endif
+
#ifdef CONFIG_X86_64
# define DISABLE_VME (1<<(X86_FEATURE_VME & 31))
# define DISABLE_K6_MTRR (1<<(X86_FEATURE_K6_MTRR & 31))
@@ -34,6 +40,6 @@
#define DISABLED_MASK6 0
#define DISABLED_MASK7 0
#define DISABLED_MASK8 0
-#define DISABLED_MASK9 0
+#define DISABLED_MASK9 (DISABLE_MPX)
#endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 48eb30a86062..47f29b1d1846 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -65,6 +65,7 @@ struct insn {
unsigned char x86_64;
const insn_byte_t *kaddr; /* kernel address of insn to analyze */
+ const insn_byte_t *end_kaddr; /* kernel address of last insn in buffer */
const insn_byte_t *next_byte;
};
@@ -96,7 +97,7 @@ struct insn {
#define X86_VEX_P(vex) ((vex) & 0x03) /* VEX3 Byte2, VEX2 Byte1 */
#define X86_VEX_M_MAX 0x1f /* VEX3.M Maximum value */
-extern void insn_init(struct insn *insn, const void *kaddr, int x86_64);
+extern void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64);
extern void insn_get_prefixes(struct insn *insn);
extern void insn_get_opcode(struct insn *insn);
extern void insn_get_modrm(struct insn *insn);
@@ -115,12 +116,13 @@ static inline void insn_get_attribute(struct insn *insn)
extern int insn_rip_relative(struct insn *insn);
/* Init insn for kernel text */
-static inline void kernel_insn_init(struct insn *insn, const void *kaddr)
+static inline void kernel_insn_init(struct insn *insn,
+ const void *kaddr, int buf_len)
{
#ifdef CONFIG_X86_64
- insn_init(insn, kaddr, 1);
+ insn_init(insn, kaddr, buf_len, 1);
#else /* CONFIG_X86_32 */
- insn_init(insn, kaddr, 0);
+ insn_init(insn, kaddr, buf_len, 0);
#endif
}
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 166af2a8e865..be91d5736e08 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -10,9 +10,8 @@
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include <asm/paravirt.h>
+#include <asm/mpx.h>
#ifndef CONFIG_PARAVIRT
-#include <asm-generic/mm_hooks.h>
-
static inline void paravirt_activate_mm(struct mm_struct *prev,
struct mm_struct *next)
{
@@ -102,4 +101,27 @@ do { \
} while (0)
#endif
+static inline void arch_dup_mmap(struct mm_struct *oldmm,
+ struct mm_struct *mm)
+{
+ paravirt_arch_dup_mmap(oldmm, mm);
+}
+
+static inline void arch_exit_mmap(struct mm_struct *mm)
+{
+ paravirt_arch_exit_mmap(mm);
+}
+
+static inline void arch_bprm_mm_init(struct mm_struct *mm,
+ struct vm_area_struct *vma)
+{
+ mpx_mm_init(mm);
+}
+
+static inline void arch_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+ mpx_notify_unmap(mm, vma, start, end);
+}
+
#endif /* _ASM_X86_MMU_CONTEXT_H */
diff --git a/arch/x86/include/asm/mpx.h b/arch/x86/include/asm/mpx.h
new file mode 100644
index 000000000000..a952a13d59a7
--- /dev/null
+++ b/arch/x86/include/asm/mpx.h
@@ -0,0 +1,103 @@
+#ifndef _ASM_X86_MPX_H
+#define _ASM_X86_MPX_H
+
+#include <linux/types.h>
+#include <asm/ptrace.h>
+#include <asm/insn.h>
+
+/*
+ * NULL is theoretically a valid place to put the bounds
+ * directory, so point this at an invalid address.
+ */
+#define MPX_INVALID_BOUNDS_DIR ((void __user *)-1)
+#define MPX_BNDCFG_ENABLE_FLAG 0x1
+#define MPX_BD_ENTRY_VALID_FLAG 0x1
+
+#ifdef CONFIG_X86_64
+
+/* upper 28 bits [47:20] of the virtual address in 64-bit used to
+ * index into bounds directory (BD).
+ */
+#define MPX_BD_ENTRY_OFFSET 28
+#define MPX_BD_ENTRY_SHIFT 3
+/* bits [19:3] of the virtual address in 64-bit used to index into
+ * bounds table (BT).
+ */
+#define MPX_BT_ENTRY_OFFSET 17
+#define MPX_BT_ENTRY_SHIFT 5
+#define MPX_IGN_BITS 3
+#define MPX_BD_ENTRY_TAIL 3
+
+#else
+
+#define MPX_BD_ENTRY_OFFSET 20
+#define MPX_BD_ENTRY_SHIFT 2
+#define MPX_BT_ENTRY_OFFSET 10
+#define MPX_BT_ENTRY_SHIFT 4
+#define MPX_IGN_BITS 2
+#define MPX_BD_ENTRY_TAIL 2
+
+#endif
+
+#define MPX_BD_SIZE_BYTES (1UL<<(MPX_BD_ENTRY_OFFSET+MPX_BD_ENTRY_SHIFT))
+#define MPX_BT_SIZE_BYTES (1UL<<(MPX_BT_ENTRY_OFFSET+MPX_BT_ENTRY_SHIFT))
+
+#define MPX_BNDSTA_TAIL 2
+#define MPX_BNDCFG_TAIL 12
+#define MPX_BNDSTA_ADDR_MASK (~((1UL<<MPX_BNDSTA_TAIL)-1))
+#define MPX_BNDCFG_ADDR_MASK (~((1UL<<MPX_BNDCFG_TAIL)-1))
+#define MPX_BT_ADDR_MASK (~((1UL<<MPX_BD_ENTRY_TAIL)-1))
+
+#define MPX_BNDCFG_ADDR_MASK (~((1UL<<MPX_BNDCFG_TAIL)-1))
+#define MPX_BNDSTA_ERROR_CODE 0x3
+
+#define MPX_BD_ENTRY_MASK ((1<<MPX_BD_ENTRY_OFFSET)-1)
+#define MPX_BT_ENTRY_MASK ((1<<MPX_BT_ENTRY_OFFSET)-1)
+#define MPX_GET_BD_ENTRY_OFFSET(addr) ((((addr)>>(MPX_BT_ENTRY_OFFSET+ \
+ MPX_IGN_BITS)) & MPX_BD_ENTRY_MASK) << MPX_BD_ENTRY_SHIFT)
+#define MPX_GET_BT_ENTRY_OFFSET(addr) ((((addr)>>MPX_IGN_BITS) & \
+ MPX_BT_ENTRY_MASK) << MPX_BT_ENTRY_SHIFT)
+
+#ifdef CONFIG_X86_INTEL_MPX
+siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
+ struct xsave_struct *xsave_buf);
+int mpx_handle_bd_fault(struct xsave_struct *xsave_buf);
+static inline int kernel_managing_mpx_tables(struct mm_struct *mm)
+{
+ return (mm->bd_addr != MPX_INVALID_BOUNDS_DIR);
+}
+static inline void mpx_mm_init(struct mm_struct *mm)
+{
+ /*
+ * NULL is theoretically a valid place to put the bounds
+ * directory, so point this at an invalid address.
+ */
+ mm->bd_addr = MPX_INVALID_BOUNDS_DIR;
+}
+void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long start, unsigned long end);
+#else
+static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
+ struct xsave_struct *xsave_buf)
+{
+ return NULL;
+}
+static inline int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
+{
+ return -EINVAL;
+}
+static inline int kernel_managing_mpx_tables(struct mm_struct *mm)
+{
+ return 0;
+}
+static inline void mpx_mm_init(struct mm_struct *mm)
+{
+}
+static inline void mpx_notify_unmap(struct mm_struct *mm,
+ struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+}
+#endif /* CONFIG_X86_INTEL_MPX */
+
+#endif /* _ASM_X86_MPX_H */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index cd6e1610e29e..32444ae939ca 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -330,13 +330,13 @@ static inline void paravirt_activate_mm(struct mm_struct *prev,
PVOP_VCALL2(pv_mmu_ops.activate_mm, prev, next);
}
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
- struct mm_struct *mm)
+static inline void paravirt_arch_dup_mmap(struct mm_struct *oldmm,
+ struct mm_struct *mm)
{
PVOP_VCALL2(pv_mmu_ops.dup_mmap, oldmm, mm);
}
-static inline void arch_exit_mmap(struct mm_struct *mm)
+static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
{
PVOP_VCALL1(pv_mmu_ops.exit_mmap, mm);
}
@@ -986,5 +986,15 @@ extern void default_banner(void);
#endif /* __ASSEMBLY__ */
#else /* CONFIG_PARAVIRT */
# define default_banner x86_init_noop
+#ifndef __ASSEMBLY__
+static inline void paravirt_arch_dup_mmap(struct mm_struct *oldmm,
+ struct mm_struct *mm)
+{
+}
+
+static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
+{
+}
+#endif /* __ASSEMBLY__ */
#endif /* !CONFIG_PARAVIRT */
#endif /* _ASM_X86_PARAVIRT_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index eb71ec794732..9617a1716813 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -374,13 +374,14 @@ struct lwp_struct {
u8 reserved[128];
};
-struct bndregs_struct {
- u64 bndregs[8];
+struct bndreg {
+ u64 lower_bound;
+ u64 upper_bound;
} __packed;
-struct bndcsr_struct {
- u64 cfg_reg_u;
- u64 status_reg;
+struct bndcsr {
+ u64 bndcfgu;
+ u64 bndstatus;
} __packed;
struct xsave_hdr_struct {
@@ -394,8 +395,8 @@ struct xsave_struct {
struct xsave_hdr_struct xsave_hdr;
struct ymmh_struct ymmh;
struct lwp_struct lwp;
- struct bndregs_struct bndregs;
- struct bndcsr_struct bndcsr;
+ struct bndreg bndreg[4];
+ struct bndcsr bndcsr;
/* new processor state extensions will go here */
} __attribute__ ((packed, aligned (64)));
@@ -953,6 +954,24 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
extern int get_tsc_mode(unsigned long adr);
extern int set_tsc_mode(unsigned int val);
+/* Register/unregister a process' MPX related resource */
+#define MPX_ENABLE_MANAGEMENT(tsk) mpx_enable_management((tsk))
+#define MPX_DISABLE_MANAGEMENT(tsk) mpx_disable_management((tsk))
+
+#ifdef CONFIG_X86_INTEL_MPX
+extern int mpx_enable_management(struct task_struct *tsk);
+extern int mpx_disable_management(struct task_struct *tsk);
+#else
+static inline int mpx_enable_management(struct task_struct *tsk)
+{
+ return -EINVAL;
+}
+static inline int mpx_disable_management(struct task_struct *tsk)
+{
+ return -EINVAL;
+}
+#endif /* CONFIG_X86_INTEL_MPX */
+
extern u16 amd_get_nb_id(int cpu);
static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 495ae9793628..3c895d480cd7 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -724,6 +724,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
unsigned long ip = regs->ip;
int is_64bit = 0;
void *kaddr;
+ int size;
/*
* We don't need to fixup if the PEBS assist is fault like
@@ -758,11 +759,12 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
return 1;
}
+ size = ip - to;
if (!kernel_ip(ip)) {
- int size, bytes;
+ int bytes;
u8 *buf = this_cpu_read(insn_buffer);
- size = ip - to; /* Must fit our buffer, see above */
+ /* 'size' must fit our buffer, see above */
bytes = copy_from_user_nmi(buf, (void __user *)to, size);
if (bytes != 0)
return 0;
@@ -780,11 +782,20 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
#ifdef CONFIG_X86_64
is_64bit = kernel_ip(to) || !test_thread_flag(TIF_IA32);
#endif
- insn_init(&insn, kaddr, is_64bit);
+ insn_init(&insn, kaddr, size, is_64bit);
insn_get_length(&insn);
+ /*
+ * Make sure there was not a problem decoding the
+ * instruction and getting the length. This is
+ * doubly important because we have an infinite
+ * loop if insn.length=0.
+ */
+ if (!insn.length)
+ break;
to += insn.length;
kaddr += insn.length;
+ size -= insn.length;
} while (to < ip);
if (to == ip) {
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 45fa730a5283..58f1a94beaf0 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -465,7 +465,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
{
struct insn insn;
void *addr;
- int bytes, size = MAX_INSN_SIZE;
+ int bytes_read, bytes_left;
int ret = X86_BR_NONE;
int ext, to_plm, from_plm;
u8 buf[MAX_INSN_SIZE];
@@ -493,8 +493,10 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
return X86_BR_NONE;
/* may fail if text not present */
- bytes = copy_from_user_nmi(buf, (void __user *)from, size);
- if (bytes != 0)
+ bytes_left = copy_from_user_nmi(buf, (void __user *)from,
+ MAX_INSN_SIZE);
+ bytes_read = MAX_INSN_SIZE - bytes_left;
+ if (!bytes_read)
return X86_BR_NONE;
addr = buf;
@@ -505,10 +507,19 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
* Ensure we don't blindy read any address by validating it is
* a known text address.
*/
- if (kernel_text_address(from))
+ if (kernel_text_address(from)) {
addr = (void *)from;
- else
+ /*
+ * Assume we can get the maximum possible size
+ * when grabbing kernel data. This is not
+ * _strictly_ true since we could possibly be
+ * executing up next to a memory hole, but
+ * it is very unlikely to be a problem.
+ */
+ bytes_read = MAX_INSN_SIZE;
+ } else {
return X86_BR_NONE;
+ }
}
/*
@@ -518,8 +529,10 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
#ifdef CONFIG_X86_64
is64 = kernel_ip((unsigned long)addr) || !test_thread_flag(TIF_IA32);
#endif
- insn_init(&insn, addr, is64);
+ insn_init(&insn, addr, bytes_read, is64);
insn_get_opcode(&insn);
+ if (!insn.opcode.got)
+ return X86_BR_ABORT;
switch (insn.opcode.bytes[0]) {
case 0xf:
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 67e6d19ef1be..f7e3cd50ece0 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -285,7 +285,7 @@ static int can_probe(unsigned long paddr)
* normally used, we just go through if there is no kprobe.
*/
__addr = recover_probed_instruction(buf, addr);
- kernel_insn_init(&insn, (void *)__addr);
+ kernel_insn_init(&insn, (void *)__addr, MAX_INSN_SIZE);
insn_get_length(&insn);
/*
@@ -330,8 +330,10 @@ int __copy_instruction(u8 *dest, u8 *src)
{
struct insn insn;
kprobe_opcode_t buf[MAX_INSN_SIZE];
+ unsigned long recovered_insn =
+ recover_probed_instruction(buf, (unsigned long)src);
- kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, (unsigned long)src));
+ kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
insn_get_length(&insn);
/* Another subsystem puts a breakpoint, failed to recover */
if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
@@ -342,7 +344,7 @@ int __copy_instruction(u8 *dest, u8 *src)
if (insn_rip_relative(&insn)) {
s64 newdisp;
u8 *disp;
- kernel_insn_init(&insn, dest);
+ kernel_insn_init(&insn, dest, insn.length);
insn_get_displacement(&insn);
/*
* The copied instruction uses the %rip-relative addressing
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index f1314d0bcf0a..7c523bbf3dc8 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -251,13 +251,15 @@ static int can_optimize(unsigned long paddr)
/* Decode instructions */
addr = paddr - offset;
while (addr < paddr - offset + size) { /* Decode until function end */
+ unsigned long recovered_insn;
if (search_exception_tables(addr))
/*
* Since some fixup code will jumps into this function,
* we can't optimize kprobe in this function.
*/
return 0;
- kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, addr));
+ recovered_insn = recover_probed_instruction(buf, addr);
+ kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
insn_get_length(&insn);
/* Another subsystem puts a breakpoint */
if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index ab08aa2276fb..214245d6b996 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -960,6 +960,8 @@ void __init setup_arch(char **cmdline_p)
init_mm.end_data = (unsigned long) _edata;
init_mm.brk = _brk_end;
+ mpx_mm_init(&init_mm);
+
code_resource.start = __pa_symbol(_text);
code_resource.end = __pa_symbol(_etext)-1;
data_resource.start = __pa_symbol(_etext);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 07ab8e9733c5..a9ae20579895 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -60,6 +60,7 @@
#include <asm/fixmap.h>
#include <asm/mach_traps.h>
#include <asm/alternative.h>
+#include <asm/mpx.h>
#ifdef CONFIG_X86_64
#include <asm/x86_init.h>
@@ -228,7 +229,6 @@ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \
DO_ERROR(X86_TRAP_DE, SIGFPE, "divide error", divide_error)
DO_ERROR(X86_TRAP_OF, SIGSEGV, "overflow", overflow)
-DO_ERROR(X86_TRAP_BR, SIGSEGV, "bounds", bounds)
DO_ERROR(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op)
DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun",coprocessor_segment_overrun)
DO_ERROR(X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS)
@@ -286,6 +286,89 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
}
#endif
+dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
+{
+ struct task_struct *tsk = current;
+ struct xsave_struct *xsave_buf;
+ enum ctx_state prev_state;
+ struct bndcsr *bndcsr;
+ siginfo_t *info;
+
+ prev_state = exception_enter();
+ if (notify_die(DIE_TRAP, "bounds", regs, error_code,
+ X86_TRAP_BR, SIGSEGV) == NOTIFY_STOP)
+ goto exit;
+ conditional_sti(regs);
+
+ if (!user_mode(regs))
+ die("bounds", regs, error_code);
+
+ if (!cpu_feature_enabled(X86_FEATURE_MPX)) {
+ /* The exception is not from Intel MPX */
+ goto exit_trap;
+ }
+
+ /*
+ * We need to look at BNDSTATUS to resolve this exception.
+ * It is not directly accessible, though, so we need to
+ * do an xsave and then pull it out of the xsave buffer.
+ */
+ fpu_save_init(&tsk->thread.fpu);
+ xsave_buf = &(tsk->thread.fpu.state->xsave);
+ bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR);
+ if (!bndcsr)
+ goto exit_trap;
+
+ /*
+ * The error code field of the BNDSTATUS register communicates status
+ * information of a bound range exception #BR or operation involving
+ * bound directory.
+ */
+ switch (bndcsr->bndstatus & MPX_BNDSTA_ERROR_CODE) {
+ case 2: /* Bound directory has invalid entry. */
+ if (mpx_handle_bd_fault(xsave_buf))
+ goto exit_trap;
+ break; /* Success, it was handled */
+ case 1: /* Bound violation. */
+ info = mpx_generate_siginfo(regs, xsave_buf);
+ if (PTR_ERR(info)) {
+ /*
+ * We failed to decode the MPX instruction. Act as if
+ * the exception was not caused by MPX.
+ */
+ goto exit_trap;
+ }
+ /*
+ * Success, we decoded the instruction and retrieved
+ * an 'info' containing the address being accessed
+ * which caused the exception. This information
+ * allows and application to possibly handle the
+ * #BR exception itself.
+ */
+ do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, info);
+ kfree(info);
+ break;
+ case 0: /* No exception caused by Intel MPX operations. */
+ goto exit_trap;
+ default:
+ die("bounds", regs, error_code);
+ }
+
+exit:
+ exception_exit(prev_state);
+ return;
+exit_trap:
+ /*
+ * This path out is for all the cases where we could not
+ * handle the exception in some way (like allocating a
+ * table or telling userspace about it. We will also end
+ * up here if the kernel has MPX turned off at compile
+ * time..
+ */
+ do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, NULL);
+ exception_exit(prev_state);
+}
+
dotraplinkage void
do_general_protection(struct pt_regs *regs, long error_code)
{
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 5d1cbfe4ae58..8b96a947021f 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -219,7 +219,7 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool
{
u32 volatile *good_insns;
- insn_init(insn, auprobe->insn, x86_64);
+ insn_init(insn, auprobe->insn, sizeof(auprobe->insn), x86_64);
/* has the side-effect of processing the entire instruction */
insn_get_length(insn);
if (WARN_ON_ONCE(!insn_complete(insn)))
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 54fcffed28ed..2480978b31cc 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -28,7 +28,7 @@
/* Verify next sizeof(t) bytes can be on the same instruction */
#define validate_next(t, insn, n) \
- ((insn)->next_byte + sizeof(t) + n - (insn)->kaddr <= MAX_INSN_SIZE)
+ ((insn)->next_byte + sizeof(t) + n < (insn)->end_kaddr)
#define __get_next(t, insn) \
({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); r; })
@@ -50,10 +50,11 @@
* @kaddr: address (in kernel memory) of instruction (or copy thereof)
* @x86_64: !0 for 64-bit kernel or 64-bit app
*/
-void insn_init(struct insn *insn, const void *kaddr, int x86_64)
+void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64)
{
memset(insn, 0, sizeof(*insn));
insn->kaddr = kaddr;
+ insn->end_kaddr = kaddr + buf_len;
insn->next_byte = kaddr;
insn->x86_64 = x86_64 ? 1 : 0;
insn->opnd_bytes = 4;
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 6a19ad9f370d..ecfdc46a024a 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -30,3 +30,5 @@ obj-$(CONFIG_ACPI_NUMA) += srat.o
obj-$(CONFIG_NUMA_EMU) += numa_emulation.o
obj-$(CONFIG_MEMTEST) += memtest.o
+
+obj-$(CONFIG_X86_INTEL_MPX) += mpx.o
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
new file mode 100644
index 000000000000..67ebf5751222
--- /dev/null
+++ b/arch/x86/mm/mpx.c
@@ -0,0 +1,928 @@
+/*
+ * mpx.c - Memory Protection eXtensions
+ *
+ * Copyright (c) 2014, Intel Corporation.
+ * Qiaowei Ren <qiaowei.ren@intel.com>
+ * Dave Hansen <dave.hansen@intel.com>
+ */
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
+#include <linux/sched/sysctl.h>
+
+#include <asm/i387.h>
+#include <asm/insn.h>
+#include <asm/mman.h>
+#include <asm/mmu_context.h>
+#include <asm/mpx.h>
+#include <asm/processor.h>
+#include <asm/fpu-internal.h>
+
+static const char *mpx_mapping_name(struct vm_area_struct *vma)
+{
+ return "[mpx]";
+}
+
+static struct vm_operations_struct mpx_vma_ops = {
+ .name = mpx_mapping_name,
+};
+
+static int is_mpx_vma(struct vm_area_struct *vma)
+{
+ return (vma->vm_ops == &mpx_vma_ops);
+}
+
+/*
+ * This is really a simplified "vm_mmap". it only handles MPX
+ * bounds tables (the bounds directory is user-allocated).
+ *
+ * Later on, we use the vma->vm_ops to uniquely identify these
+ * VMAs.
+ */
+static unsigned long mpx_mmap(unsigned long len)
+{
+ unsigned long ret;
+ unsigned long addr, pgoff;
+ struct mm_struct *mm = current->mm;
+ vm_flags_t vm_flags;
+ struct vm_area_struct *vma;
+
+ /* Only bounds table and bounds directory can be allocated here */
+ if (len != MPX_BD_SIZE_BYTES && len != MPX_BT_SIZE_BYTES)
+ return -EINVAL;
+
+ down_write(&mm->mmap_sem);
+
+ /* Too many mappings? */
+ if (mm->map_count > sysctl_max_map_count) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ /* Obtain the address to map to. we verify (or select) it and ensure
+ * that it represents a valid section of the address space.
+ */
+ addr = get_unmapped_area(NULL, 0, len, 0, MAP_ANONYMOUS | MAP_PRIVATE);
+ if (addr & ~PAGE_MASK) {
+ ret = addr;
+ goto out;
+ }
+
+ vm_flags = VM_READ | VM_WRITE | VM_MPX |
+ mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
+
+ /* Set pgoff according to addr for anon_vma */
+ pgoff = addr >> PAGE_SHIFT;
+
+ ret = mmap_region(NULL, addr, len, vm_flags, pgoff);
+ if (IS_ERR_VALUE(ret))
+ goto out;
+
+ vma = find_vma(mm, ret);
+ if (!vma) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ vma->vm_ops = &mpx_vma_ops;
+
+ if (vm_flags & VM_LOCKED) {
+ up_write(&mm->mmap_sem);
+ mm_populate(ret, len);
+ return ret;
+ }
+
+out:
+ up_write(&mm->mmap_sem);
+ return ret;
+}
+
+enum reg_type {
+ REG_TYPE_RM = 0,
+ REG_TYPE_INDEX,
+ REG_TYPE_BASE,
+};
+
+static int get_reg_offset(struct insn *insn, struct pt_regs *regs,
+ enum reg_type type)
+{
+ int regno = 0;
+
+ static const int regoff[] = {
+ offsetof(struct pt_regs, ax),
+ offsetof(struct pt_regs, cx),
+ offsetof(struct pt_regs, dx),
+ offsetof(struct pt_regs, bx),
+ offsetof(struct pt_regs, sp),
+ offsetof(struct pt_regs, bp),
+ offsetof(struct pt_regs, si),
+ offsetof(struct pt_regs, di),
+#ifdef CONFIG_X86_64
+ offsetof(struct pt_regs, r8),
+ offsetof(struct pt_regs, r9),
+ offsetof(struct pt_regs, r10),
+ offsetof(struct pt_regs, r11),
+ offsetof(struct pt_regs, r12),
+ offsetof(struct pt_regs, r13),
+ offsetof(struct pt_regs, r14),
+ offsetof(struct pt_regs, r15),
+#endif
+ };
+ int nr_registers = ARRAY_SIZE(regoff);
+ /*
+ * Don't possibly decode a 32-bit instructions as
+ * reading a 64-bit-only register.
+ */
+ if (IS_ENABLED(CONFIG_X86_64) && !insn->x86_64)
+ nr_registers -= 8;
+
+ switch (type) {
+ case REG_TYPE_RM:
+ regno = X86_MODRM_RM(insn->modrm.value);
+ if (X86_REX_B(insn->rex_prefix.value) == 1)
+ regno += 8;
+ break;
+
+ case REG_TYPE_INDEX:
+ regno = X86_SIB_INDEX(insn->sib.value);
+ if (X86_REX_X(insn->rex_prefix.value) == 1)
+ regno += 8;
+ break;
+
+ case REG_TYPE_BASE:
+ regno = X86_SIB_BASE(insn->sib.value);
+ if (X86_REX_B(insn->rex_prefix.value) == 1)
+ regno += 8;
+ break;
+
+ default:
+ pr_err("invalid register type");
+ BUG();
+ break;
+ }
+
+ if (regno > nr_registers) {
+ WARN_ONCE(1, "decoded an instruction with an invalid register");
+ return -EINVAL;
+ }
+ return regoff[regno];
+}
+
+/*
+ * return the address being referenced be instruction
+ * for rm=3 returning the content of the rm reg
+ * for rm!=3 calculates the address using SIB and Disp
+ */
+static void __user *mpx_get_addr_ref(struct insn *insn, struct pt_regs *regs)
+{
+ unsigned long addr, base, indx;
+ int addr_offset, base_offset, indx_offset;
+ insn_byte_t sib;
+
+ insn_get_modrm(insn);
+ insn_get_sib(insn);
+ sib = insn->sib.value;
+
+ if (X86_MODRM_MOD(insn->modrm.value) == 3) {
+ addr_offset = get_reg_offset(insn, regs, REG_TYPE_RM);
+ if (addr_offset < 0)
+ goto out_err;
+ addr = regs_get_register(regs, addr_offset);
+ } else {
+ if (insn->sib.nbytes) {
+ base_offset = get_reg_offset(insn, regs, REG_TYPE_BASE);
+ if (base_offset < 0)
+ goto out_err;
+
+ indx_offset = get_reg_offset(insn, regs, REG_TYPE_INDEX);
+ if (indx_offset < 0)
+ goto out_err;
+
+ base = regs_get_register(regs, base_offset);
+ indx = regs_get_register(regs, indx_offset);
+ addr = base + indx * (1 << X86_SIB_SCALE(sib));
+ } else {
+ addr_offset = get_reg_offset(insn, regs, REG_TYPE_RM);
+ if (addr_offset < 0)
+ goto out_err;
+ addr = regs_get_register(regs, addr_offset);
+ }
+ addr += insn->displacement.value;
+ }
+ return (void __user *)addr;
+out_err:
+ return (void __user *)-1;
+}
+
+static int mpx_insn_decode(struct insn *insn,
+ struct pt_regs *regs)
+{
+ unsigned char buf[MAX_INSN_SIZE];
+ int x86_64 = !test_thread_flag(TIF_IA32);
+ int not_copied;
+ int nr_copied;
+
+ not_copied = copy_from_user(buf, (void __user *)regs->ip, sizeof(buf));
+ nr_copied = sizeof(buf) - not_copied;
+ /*
+ * The decoder _should_ fail nicely if we pass it a short buffer.
+ * But, let's not depend on that implementation detail. If we
+ * did not get anything, just error out now.
+ */
+ if (!nr_copied)
+ return -EFAULT;
+ insn_init(insn, buf, nr_copied, x86_64);
+ insn_get_length(insn);
+ /*
+ * copy_from_user() tries to get as many bytes as we could see in
+ * the largest possible instruction. If the instruction we are
+ * after is shorter than that _and_ we attempt to copy from
+ * something unreadable, we might get a short read. This is OK
+ * as long as the read did not stop in the middle of the
+ * instruction. Check to see if we got a partial instruction.
+ */
+ if (nr_copied < insn->length)
+ return -EFAULT;
+
+ insn_get_opcode(insn);
+ /*
+ * We only _really_ need to decode bndcl/bndcn/bndcu
+ * Error out on anything else.
+ */
+ if (insn->opcode.bytes[0] != 0x0f)
+ goto bad_opcode;
+ if ((insn->opcode.bytes[1] != 0x1a) &&
+ (insn->opcode.bytes[1] != 0x1b))
+ goto bad_opcode;
+
+ return 0;
+bad_opcode:
+ return -EINVAL;
+}
+
+/*
+ * If a bounds overflow occurs then a #BR is generated. This
+ * function decodes MPX instructions to get violation address
+ * and set this address into extended struct siginfo.
+ *
+ * Note that this is not a super precise way of doing this.
+ * Userspace could have, by the time we get here, written
+ * anything it wants in to the instructions. We can not
+ * trust anything about it. They might not be valid
+ * instructions or might encode invalid registers, etc...
+ *
+ * The caller is expected to kfree() the returned siginfo_t.
+ */
+siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
+ struct xsave_struct *xsave_buf)
+{
+ struct bndreg *bndregs, *bndreg;
+ siginfo_t *info = NULL;
+ struct insn insn;
+ uint8_t bndregno;
+ int err;
+
+ err = mpx_insn_decode(&insn, regs);
+ if (err)
+ goto err_out;
+
+ /*
+ * We know at this point that we are only dealing with
+ * MPX instructions.
+ */
+ insn_get_modrm(&insn);
+ bndregno = X86_MODRM_REG(insn.modrm.value);
+ if (bndregno > 3) {
+ err = -EINVAL;
+ goto err_out;
+ }
+ /* get the bndregs _area_ of the xsave structure */
+ bndregs = get_xsave_addr(xsave_buf, XSTATE_BNDREGS);
+ if (!bndregs) {
+ err = -EINVAL;
+ goto err_out;
+ }
+ /* now go select the individual register in the set of 4 */
+ bndreg = &bndregs[bndregno];
+
+ info = kzalloc(sizeof(*info), GFP_KERNEL);
+ if (!info) {
+ err = -ENOMEM;
+ goto err_out;
+ }
+ /*
+ * The registers are always 64-bit, but the upper 32
+ * bits are ignored in 32-bit mode. Also, note that the
+ * upper bounds are architecturally represented in 1's
+ * complement form.
+ *
+ * The 'unsigned long' cast is because the compiler
+ * complains when casting from integers to different-size
+ * pointers.
+ */
+ info->si_lower = (void __user *)(unsigned long)bndreg->lower_bound;
+ info->si_upper = (void __user *)(unsigned long)~bndreg->upper_bound;
+ info->si_addr_lsb = 0;
+ info->si_signo = SIGSEGV;
+ info->si_errno = 0;
+ info->si_code = SEGV_BNDERR;
+ info->si_addr = mpx_get_addr_ref(&insn, regs);
+ /*
+ * We were not able to extract an address from the instruction,
+ * probably because there was something invalid in it.
+ */
+ if (info->si_addr == (void *)-1) {
+ err = -EINVAL;
+ goto err_out;
+ }
+ return info;
+err_out:
+ /* info might be NULL, but kfree() handles that */
+ kfree(info);
+ return ERR_PTR(err);
+}
+
+static __user void *task_get_bounds_dir(struct task_struct *tsk)
+{
+ struct bndcsr *bndcsr;
+
+ if (!cpu_feature_enabled(X86_FEATURE_MPX))
+ return MPX_INVALID_BOUNDS_DIR;
+
+ /*
+ * The bounds directory pointer is stored in a register
+ * only accessible if we first do an xsave.
+ */
+ fpu_save_init(&tsk->thread.fpu);
+ bndcsr = get_xsave_addr(&tsk->thread.fpu.state->xsave, XSTATE_BNDCSR);
+ if (!bndcsr)
+ return MPX_INVALID_BOUNDS_DIR;
+
+ /*
+ * Make sure the register looks valid by checking the
+ * enable bit.
+ */
+ if (!(bndcsr->bndcfgu & MPX_BNDCFG_ENABLE_FLAG))
+ return MPX_INVALID_BOUNDS_DIR;
+
+ /*
+ * Lastly, mask off the low bits used for configuration
+ * flags, and return the address of the bounds table.
+ */
+ return (void __user *)(unsigned long)
+ (bndcsr->bndcfgu & MPX_BNDCFG_ADDR_MASK);
+}
+
+int mpx_enable_management(struct task_struct *tsk)
+{
+ void __user *bd_base = MPX_INVALID_BOUNDS_DIR;
+ struct mm_struct *mm = tsk->mm;
+ int ret = 0;
+
+ /*
+ * runtime in the userspace will be responsible for allocation of
+ * the bounds directory. Then, it will save the base of the bounds
+ * directory into XSAVE/XRSTOR Save Area and enable MPX through
+ * XRSTOR instruction.
+ *
+ * fpu_xsave() is expected to be very expensive. Storing the bounds
+ * directory here means that we do not have to do xsave in the unmap
+ * path; we can just use mm->bd_addr instead.
+ */
+ bd_base = task_get_bounds_dir(tsk);
+ down_write(&mm->mmap_sem);
+ mm->bd_addr = bd_base;
+ if (mm->bd_addr == MPX_INVALID_BOUNDS_DIR)
+ ret = -ENXIO;
+
+ up_write(&mm->mmap_sem);
+ return ret;
+}
+
+int mpx_disable_management(struct task_struct *tsk)
+{
+ struct mm_struct *mm = current->mm;
+
+ if (!cpu_feature_enabled(X86_FEATURE_MPX))
+ return -ENXIO;
+
+ down_write(&mm->mmap_sem);
+ mm->bd_addr = MPX_INVALID_BOUNDS_DIR;
+ up_write(&mm->mmap_sem);
+ return 0;
+}
+
+/*
+ * With 32-bit mode, MPX_BT_SIZE_BYTES is 4MB, and the size of each
+ * bounds table is 16KB. With 64-bit mode, MPX_BT_SIZE_BYTES is 2GB,
+ * and the size of each bounds table is 4MB.
+ */
+static int allocate_bt(long __user *bd_entry)
+{
+ unsigned long expected_old_val = 0;
+ unsigned long actual_old_val = 0;
+ unsigned long bt_addr;
+ int ret = 0;
+
+ /*
+ * Carve the virtual space out of userspace for the new
+ * bounds table:
+ */
+ bt_addr = mpx_mmap(MPX_BT_SIZE_BYTES);
+ if (IS_ERR((void *)bt_addr))
+ return PTR_ERR((void *)bt_addr);
+ /*
+ * Set the valid flag (kinda like _PAGE_PRESENT in a pte)
+ */
+ bt_addr = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
+
+ /*
+ * Go poke the address of the new bounds table in to the
+ * bounds directory entry out in userspace memory. Note:
+ * we may race with another CPU instantiating the same table.
+ * In that case the cmpxchg will see an unexpected
+ * 'actual_old_val'.
+ *
+ * This can fault, but that's OK because we do not hold
+ * mmap_sem at this point, unlike some of the other part
+ * of the MPX code that have to pagefault_disable().
+ */
+ ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry,
+ expected_old_val, bt_addr);
+ if (ret)
+ goto out_unmap;
+
+ /*
+ * The user_atomic_cmpxchg_inatomic() will only return nonzero
+ * for faults, *not* if the cmpxchg itself fails. Now we must
+ * verify that the cmpxchg itself completed successfully.
+ */
+ /*
+ * We expected an empty 'expected_old_val', but instead found
+ * an apparently valid entry. Assume we raced with another
+ * thread to instantiate this table and desclare succecss.
+ */
+ if (actual_old_val & MPX_BD_ENTRY_VALID_FLAG) {
+ ret = 0;
+ goto out_unmap;
+ }
+ /*
+ * We found a non-empty bd_entry but it did not have the
+ * VALID_FLAG set. Return an error which will result in
+ * a SEGV since this probably means that somebody scribbled
+ * some invalid data in to a bounds table.
+ */
+ if (expected_old_val != actual_old_val) {
+ ret = -EINVAL;
+ goto out_unmap;
+ }
+ return 0;
+out_unmap:
+ vm_munmap(bt_addr & MPX_BT_ADDR_MASK, MPX_BT_SIZE_BYTES);
+ return ret;
+}
+
+/*
+ * When a BNDSTX instruction attempts to save bounds to a bounds
+ * table, it will first attempt to look up the table in the
+ * first-level bounds directory. If it does not find a table in
+ * the directory, a #BR is generated and we get here in order to
+ * allocate a new table.
+ *
+ * With 32-bit mode, the size of BD is 4MB, and the size of each
+ * bound table is 16KB. With 64-bit mode, the size of BD is 2GB,
+ * and the size of each bound table is 4MB.
+ */
+static int do_mpx_bt_fault(struct xsave_struct *xsave_buf)
+{
+ unsigned long bd_entry, bd_base;
+ struct bndcsr *bndcsr;
+
+ bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR);
+ if (!bndcsr)
+ return -EINVAL;
+ /*
+ * Mask off the preserve and enable bits
+ */
+ bd_base = bndcsr->bndcfgu & MPX_BNDCFG_ADDR_MASK;
+ /*
+ * The hardware provides the address of the missing or invalid
+ * entry via BNDSTATUS, so we don't have to go look it up.
+ */
+ bd_entry = bndcsr->bndstatus & MPX_BNDSTA_ADDR_MASK;
+ /*
+ * Make sure the directory entry is within where we think
+ * the directory is.
+ */
+ if ((bd_entry < bd_base) ||
+ (bd_entry >= bd_base + MPX_BD_SIZE_BYTES))
+ return -EINVAL;
+
+ return allocate_bt((long __user *)bd_entry);
+}
+
+int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
+{
+ /*
+ * Userspace never asked us to manage the bounds tables,
+ * so refuse to help.
+ */
+ if (!kernel_managing_mpx_tables(current->mm))
+ return -EINVAL;
+
+ if (do_mpx_bt_fault(xsave_buf)) {
+ force_sig(SIGSEGV, current);
+ /*
+ * The force_sig() is essentially "handling" this
+ * exception, so we do not pass up the error
+ * from do_mpx_bt_fault().
+ */
+ }
+ return 0;
+}
+
+/*
+ * A thin wrapper around get_user_pages(). Returns 0 if the
+ * fault was resolved or -errno if not.
+ */
+static int mpx_resolve_fault(long __user *addr, int write)
+{
+ long gup_ret;
+ int nr_pages = 1;
+ int force = 0;
+
+ gup_ret = get_user_pages(current, current->mm, (unsigned long)addr,
+ nr_pages, write, force, NULL, NULL);
+ /*
+ * get_user_pages() returns number of pages gotten.
+ * 0 means we failed to fault in and get anything,
+ * probably because 'addr' is bad.
+ */
+ if (!gup_ret)
+ return -EFAULT;
+ /* Other error, return it */
+ if (gup_ret < 0)
+ return gup_ret;
+ /* must have gup'd a page and gup_ret>0, success */
+ return 0;
+}
+
+/*
+ * Get the base of bounds tables pointed by specific bounds
+ * directory entry.
+ */
+static int get_bt_addr(struct mm_struct *mm,
+ long __user *bd_entry, unsigned long *bt_addr)
+{
+ int ret;
+ int valid_bit;
+
+ if (!access_ok(VERIFY_READ, (bd_entry), sizeof(*bd_entry)))
+ return -EFAULT;
+
+ while (1) {
+ int need_write = 0;
+
+ pagefault_disable();
+ ret = get_user(*bt_addr, bd_entry);
+ pagefault_enable();
+ if (!ret)
+ break;
+ if (ret == -EFAULT)
+ ret = mpx_resolve_fault(bd_entry, need_write);
+ /*
+ * If we could not resolve the fault, consider it
+ * userspace's fault and error out.
+ */
+ if (ret)
+ return ret;
+ }
+
+ valid_bit = *bt_addr & MPX_BD_ENTRY_VALID_FLAG;
+ *bt_addr &= MPX_BT_ADDR_MASK;
+
+ /*
+ * When the kernel is managing bounds tables, a bounds directory
+ * entry will either have a valid address (plus the valid bit)
+ * *OR* be completely empty. If we see a !valid entry *and* some
+ * data in the address field, we know something is wrong. This
+ * -EINVAL return will cause a SIGSEGV.
+ */
+ if (!valid_bit && *bt_addr)
+ return -EINVAL;
+ /*
+ * Do we have an completely zeroed bt entry? That is OK. It
+ * just means there was no bounds table for this memory. Make
+ * sure to distinguish this from -EINVAL, which will cause
+ * a SEGV.
+ */
+ if (!valid_bit)
+ return -ENOENT;
+
+ return 0;
+}
+
+/*
+ * Free the backing physical pages of bounds table 'bt_addr'.
+ * Assume start...end is within that bounds table.
+ */
+static int zap_bt_entries(struct mm_struct *mm,
+ unsigned long bt_addr,
+ unsigned long start, unsigned long end)
+{
+ struct vm_area_struct *vma;
+ unsigned long addr, len;
+
+ /*
+ * Find the first overlapping vma. If vma->vm_start > start, there
+ * will be a hole in the bounds table. This -EINVAL return will
+ * cause a SIGSEGV.
+ */
+ vma = find_vma(mm, start);
+ if (!vma || vma->vm_start > start)
+ return -EINVAL;
+
+ /*
+ * A NUMA policy on a VM_MPX VMA could cause this bouds table to
+ * be split. So we need to look across the entire 'start -> end'
+ * range of this bounds table, find all of the VM_MPX VMAs, and
+ * zap only those.
+ */
+ addr = start;
+ while (vma && vma->vm_start < end) {
+ /*
+ * We followed a bounds directory entry down
+ * here. If we find a non-MPX VMA, that's bad,
+ * so stop immediately and return an error. This
+ * probably results in a SIGSEGV.
+ */
+ if (!is_mpx_vma(vma))
+ return -EINVAL;
+
+ len = min(vma->vm_end, end) - addr;
+ zap_page_range(vma, addr, len, NULL);
+
+ vma = vma->vm_next;
+ addr = vma->vm_start;
+ }
+
+ return 0;
+}
+
+static int unmap_single_bt(struct mm_struct *mm,
+ long __user *bd_entry, unsigned long bt_addr)
+{
+ unsigned long expected_old_val = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
+ unsigned long actual_old_val = 0;
+ int ret;
+
+ while (1) {
+ int need_write = 1;
+
+ pagefault_disable();
+ ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry,
+ expected_old_val, 0);
+ pagefault_enable();
+ if (!ret)
+ break;
+ if (ret == -EFAULT)
+ ret = mpx_resolve_fault(bd_entry, need_write);
+ /*
+ * If we could not resolve the fault, consider it
+ * userspace's fault and error out.
+ */
+ if (ret)
+ return ret;
+ }
+ /*
+ * The cmpxchg was performed, check the results.
+ */
+ if (actual_old_val != expected_old_val) {
+ /*
+ * Someone else raced with us to unmap the table.
+ * There was no bounds table pointed to by the
+ * directory, so declare success. Somebody freed
+ * it.
+ */
+ if (!actual_old_val)
+ return 0;
+ /*
+ * Something messed with the bounds directory
+ * entry. We hold mmap_sem for read or write
+ * here, so it could not be a _new_ bounds table
+ * that someone just allocated. Something is
+ * wrong, so pass up the error and SIGSEGV.
+ */
+ return -EINVAL;
+ }
+
+ /*
+ * Note, we are likely being called under do_munmap() already. To
+ * avoid recursion, do_munmap() will check whether it comes
+ * from one bounds table through VM_MPX flag.
+ */
+ return do_munmap(mm, bt_addr, MPX_BT_SIZE_BYTES);
+}
+
+/*
+ * If the bounds table pointed by bounds directory 'bd_entry' is
+ * not shared, unmap this whole bounds table. Otherwise, only free
+ * those backing physical pages of bounds table entries covered
+ * in this virtual address region start...end.
+ */
+static int unmap_shared_bt(struct mm_struct *mm,
+ long __user *bd_entry, unsigned long start,
+ unsigned long end, bool prev_shared, bool next_shared)
+{
+ unsigned long bt_addr;
+ int ret;
+
+ ret = get_bt_addr(mm, bd_entry, &bt_addr);
+ /*
+ * We could see an "error" ret for not-present bounds
+ * tables (not really an error), or actual errors, but
+ * stop unmapping either way.
+ */
+ if (ret)
+ return ret;
+
+ if (prev_shared && next_shared)
+ ret = zap_bt_entries(mm, bt_addr,
+ bt_addr+MPX_GET_BT_ENTRY_OFFSET(start),
+ bt_addr+MPX_GET_BT_ENTRY_OFFSET(end));
+ else if (prev_shared)
+ ret = zap_bt_entries(mm, bt_addr,
+ bt_addr+MPX_GET_BT_ENTRY_OFFSET(start),
+ bt_addr+MPX_BT_SIZE_BYTES);
+ else if (next_shared)
+ ret = zap_bt_entries(mm, bt_addr, bt_addr,
+ bt_addr+MPX_GET_BT_ENTRY_OFFSET(end));
+ else
+ ret = unmap_single_bt(mm, bd_entry, bt_addr);
+
+ return ret;
+}
+
+/*
+ * A virtual address region being munmap()ed might share bounds table
+ * with adjacent VMAs. We only need to free the backing physical
+ * memory of these shared bounds tables entries covered in this virtual
+ * address region.
+ */
+static int unmap_edge_bts(struct mm_struct *mm,
+ unsigned long start, unsigned long end)
+{
+ int ret;
+ long __user *bde_start, *bde_end;
+ struct vm_area_struct *prev, *next;
+ bool prev_shared = false, next_shared = false;
+
+ bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start);
+ bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1);
+
+ /*
+ * Check whether bde_start and bde_end are shared with adjacent
+ * VMAs.
+ *
+ * We already unliked the VMAs from the mm's rbtree so 'start'
+ * is guaranteed to be in a hole. This gets us the first VMA
+ * before the hole in to 'prev' and the next VMA after the hole
+ * in to 'next'.
+ */
+ next = find_vma_prev(mm, start, &prev);
+ if (prev && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(prev->vm_end-1))
+ == bde_start)
+ prev_shared = true;
+ if (next && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(next->vm_start))
+ == bde_end)
+ next_shared = true;
+
+ /*
+ * This virtual address region being munmap()ed is only
+ * covered by one bounds table.
+ *
+ * In this case, if this table is also shared with adjacent
+ * VMAs, only part of the backing physical memory of the bounds
+ * table need be freeed. Otherwise the whole bounds table need
+ * be unmapped.
+ */
+ if (bde_start == bde_end) {
+ return unmap_shared_bt(mm, bde_start, start, end,
+ prev_shared, next_shared);
+ }
+
+ /*
+ * If more than one bounds tables are covered in this virtual
+ * address region being munmap()ed, we need to separately check
+ * whether bde_start and bde_end are shared with adjacent VMAs.
+ */
+ ret = unmap_shared_bt(mm, bde_start, start, end, prev_shared, false);
+ if (ret)
+ return ret;
+ ret = unmap_shared_bt(mm, bde_end, start, end, false, next_shared);
+ if (ret)
+ return ret;
+
+ return 0;
+}
+
+static int mpx_unmap_tables(struct mm_struct *mm,
+ unsigned long start, unsigned long end)
+{
+ int ret;
+ long __user *bd_entry, *bde_start, *bde_end;
+ unsigned long bt_addr;
+
+ /*
+ * "Edge" bounds tables are those which are being used by the region
+ * (start -> end), but that may be shared with adjacent areas. If they
+ * turn out to be completely unshared, they will be freed. If they are
+ * shared, we will free the backing store (like an MADV_DONTNEED) for
+ * areas used by this region.
+ */
+ ret = unmap_edge_bts(mm, start, end);
+ switch (ret) {
+ /* non-present tables are OK */
+ case 0:
+ case -ENOENT:
+ /* Success, or no tables to unmap */
+ break;
+ case -EINVAL:
+ case -EFAULT:
+ default:
+ return ret;
+ }
+
+ /*
+ * Only unmap the bounds table that are
+ * 1. fully covered
+ * 2. not at the edges of the mapping, even if full aligned
+ */
+ bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start);
+ bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1);
+ for (bd_entry = bde_start + 1; bd_entry < bde_end; bd_entry++) {
+ ret = get_bt_addr(mm, bd_entry, &bt_addr);
+ switch (ret) {
+ case 0:
+ break;
+ case -ENOENT:
+ /* No table here, try the next one */
+ continue;
+ case -EINVAL:
+ case -EFAULT:
+ default:
+ /*
+ * Note: we are being strict here.
+ * Any time we run in to an issue
+ * unmapping tables, we stop and
+ * SIGSEGV.
+ */
+ return ret;
+ }
+
+ ret = unmap_single_bt(mm, bd_entry, bt_addr);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+/*
+ * Free unused bounds tables covered in a virtual address region being
+ * munmap()ed. Assume end > start.
+ *
+ * This function will be called by do_munmap(), and the VMAs covering
+ * the virtual address region start...end have already been split if
+ * necessary, and the 'vma' is the first vma in this range (start -> end).
+ */
+void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+ int ret;
+
+ /*
+ * Refuse to do anything unless userspace has asked
+ * the kernel to help manage the bounds tables,
+ */
+ if (!kernel_managing_mpx_tables(current->mm))
+ return;
+ /*
+ * This will look across the entire 'start -> end' range,
+ * and find all of the non-VM_MPX VMAs.
+ *
+ * To avoid recursion, if a VM_MPX vma is found in the range
+ * (start->end), we will not continue follow-up work. This
+ * recursion represents having bounds tables for bounds tables,
+ * which should not occur normally. Being strict about it here
+ * helps ensure that we do not have an exploitable stack overflow.
+ */
+ do {
+ if (vma->vm_flags & VM_MPX)
+ return;
+ vma = vma->vm_next;
+ } while (vma && vma->vm_start < end);
+
+ ret = mpx_unmap_tables(mm, start, end);
+ if (ret)
+ force_sig(SIGSEGV, current);
+}
diff --git a/arch/x86/tools/insn_sanity.c b/arch/x86/tools/insn_sanity.c
index 872eb60e7806..ba70ff232917 100644
--- a/arch/x86/tools/insn_sanity.c
+++ b/arch/x86/tools/insn_sanity.c
@@ -254,7 +254,7 @@ int main(int argc, char **argv)
continue;
/* Decode an instruction */
- insn_init(&insn, insn_buf, x86_64);
+ insn_init(&insn, insn_buf, sizeof(insn_buf), x86_64);
insn_get_length(&insn);
if (insn.next_byte <= insn.kaddr ||
diff --git a/arch/x86/tools/test_get_len.c b/arch/x86/tools/test_get_len.c
index 13403fc95a96..56f04db0c9c0 100644
--- a/arch/x86/tools/test_get_len.c
+++ b/arch/x86/tools/test_get_len.c
@@ -149,7 +149,7 @@ int main(int argc, char **argv)
break;
}
/* Decode an instruction */
- insn_init(&insn, insn_buf, x86_64);
+ insn_init(&insn, insn_buf, sizeof(insn_buf), x86_64);
insn_get_length(&insn);
if (insn.length != nb) {
warnings++;
diff --git a/fs/exec.c b/fs/exec.c
index 7302b75a9820..01aebe300200 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -277,6 +277,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
goto err;
mm->stack_vm = mm->total_vm = 1;
+ arch_bprm_mm_init(mm, vma);
up_write(&mm->mmap_sem);
bprm->p = vma->vm_end - sizeof(void *);
return 0;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 4e0388cffe3d..f6734c6b66a6 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -552,6 +552,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
[ilog2(VM_GROWSDOWN)] = "gd",
[ilog2(VM_PFNMAP)] = "pf",
[ilog2(VM_DENYWRITE)] = "dw",
+#ifdef CONFIG_X86_INTEL_MPX
+ [ilog2(VM_MPX)] = "mp",
+#endif
[ilog2(VM_LOCKED)] = "lo",
[ilog2(VM_IO)] = "io",
[ilog2(VM_SEQ_READ)] = "sr",
diff --git a/include/asm-generic/mm_hooks.h b/include/asm-generic/mm_hooks.h
index 67dea8123683..866aa461efa5 100644
--- a/include/asm-generic/mm_hooks.h
+++ b/include/asm-generic/mm_hooks.h
@@ -1,7 +1,7 @@
/*
- * Define generic no-op hooks for arch_dup_mmap and arch_exit_mmap, to
- * be included in asm-FOO/mmu_context.h for any arch FOO which doesn't
- * need to hook these.
+ * Define generic no-op hooks for arch_dup_mmap, arch_exit_mmap
+ * and arch_unmap to be included in asm-FOO/mmu_context.h for any
+ * arch FOO which doesn't need to hook these.
*/
#ifndef _ASM_GENERIC_MM_HOOKS_H
#define _ASM_GENERIC_MM_HOOKS_H
@@ -15,4 +15,15 @@ static inline void arch_exit_mmap(struct mm_struct *mm)
{
}
+static inline void arch_unmap(struct mm_struct *mm,
+ struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+}
+
+static inline void arch_bprm_mm_init(struct mm_struct *mm,
+ struct vm_area_struct *vma)
+{
+}
+
#endif /* _ASM_GENERIC_MM_HOOKS_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index b46461116cd2..f7606d3a0915 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -128,6 +128,7 @@ extern unsigned int kobjsize(const void *objp);
#define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */
#define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */
#define VM_ARCH_1 0x01000000 /* Architecture-specific flag */
+#define VM_ARCH_2 0x02000000
#define VM_DONTDUMP 0x04000000 /* Do not include in the core dump */
#ifdef CONFIG_MEM_SOFT_DIRTY
@@ -155,6 +156,11 @@ extern unsigned int kobjsize(const void *objp);
# define VM_MAPPED_COPY VM_ARCH_1 /* T if mapped copy of data (nommu mmap) */
#endif
+#if defined(CONFIG_X86)
+/* MPX specific bounds table or bounds directory */
+# define VM_MPX VM_ARCH_2
+#endif
+
#ifndef VM_GROWSUP
# define VM_GROWSUP VM_NONE
#endif
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6e0b286649f1..004e9d17b47e 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -454,6 +454,10 @@ struct mm_struct {
bool tlb_flush_pending;
#endif
struct uprobes_state uprobes_state;
+#ifdef CONFIG_X86_INTEL_MPX
+ /* address of the bounds directory */
+ void __user *bd_addr;
+#endif
};
static inline void mm_init_cpumask(struct mm_struct *mm)
diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h
index ba5be7fdbdfe..1e3552037a5a 100644
--- a/include/uapi/asm-generic/siginfo.h
+++ b/include/uapi/asm-generic/siginfo.h
@@ -91,6 +91,10 @@ typedef struct siginfo {
int _trapno; /* TRAP # which caused the signal */
#endif
short _addr_lsb; /* LSB of the reported address */
+ struct {
+ void __user *_lower;
+ void __user *_upper;
+ } _addr_bnd;
} _sigfault;
/* SIGPOLL */
@@ -131,6 +135,8 @@ typedef struct siginfo {
#define si_trapno _sifields._sigfault._trapno
#endif
#define si_addr_lsb _sifields._sigfault._addr_lsb
+#define si_lower _sifields._sigfault._addr_bnd._lower
+#define si_upper _sifields._sigfault._addr_bnd._upper
#define si_band _sifields._sigpoll._band
#define si_fd _sifields._sigpoll._fd
#ifdef __ARCH_SIGSYS
@@ -199,7 +205,8 @@ typedef struct siginfo {
*/
#define SEGV_MAPERR (__SI_FAULT|1) /* address not mapped to object */
#define SEGV_ACCERR (__SI_FAULT|2) /* invalid permissions for mapped object */
-#define NSIGSEGV 2
+#define SEGV_BNDERR (__SI_FAULT|3) /* failed address bound checks */
+#define NSIGSEGV 3
/*
* SIGBUS si_codes
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 513df75d0fc9..89f63503f903 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -179,4 +179,10 @@ struct prctl_mm_map {
#define PR_SET_THP_DISABLE 41
#define PR_GET_THP_DISABLE 42
+/*
+ * Tell the kernel to start/stop helping userspace manage bounds tables.
+ */
+#define PR_MPX_ENABLE_MANAGEMENT 43
+#define PR_MPX_DISABLE_MANAGEMENT 44
+
#endif /* _LINUX_PRCTL_H */
diff --git a/kernel/signal.c b/kernel/signal.c
index 19e35135fc60..16a305295256 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2756,6 +2756,10 @@ int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from)
if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)
err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb);
#endif
+#ifdef SEGV_BNDERR
+ err |= __put_user(from->si_lower, &to->si_lower);
+ err |= __put_user(from->si_upper, &to->si_upper);
+#endif
break;
case __SI_CHLD:
err |= __put_user(from->si_pid, &to->si_pid);
diff --git a/kernel/sys.c b/kernel/sys.c
index 1eaa2f0b0246..a8c9f5a7dda6 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -91,6 +91,12 @@
#ifndef SET_TSC_CTL
# define SET_TSC_CTL(a) (-EINVAL)
#endif
+#ifndef MPX_ENABLE_MANAGEMENT
+# define MPX_ENABLE_MANAGEMENT(a) (-EINVAL)
+#endif
+#ifndef MPX_DISABLE_MANAGEMENT
+# define MPX_DISABLE_MANAGEMENT(a) (-EINVAL)
+#endif
/*
* this is where the system-wide overflow UID and GID are defined, for
@@ -2203,6 +2209,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
me->mm->def_flags &= ~VM_NOHUGEPAGE;
up_write(&me->mm->mmap_sem);
break;
+ case PR_MPX_ENABLE_MANAGEMENT:
+ error = MPX_ENABLE_MANAGEMENT(me);
+ break;
+ case PR_MPX_DISABLE_MANAGEMENT:
+ error = MPX_DISABLE_MANAGEMENT(me);
+ break;
default:
error = -EINVAL;
break;
diff --git a/mm/mmap.c b/mm/mmap.c
index ae919891a087..b6c0a77fc1c8 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2601,6 +2601,8 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
detach_vmas_to_be_unmapped(mm, vma, prev, end);
unmap_region(mm, vma, prev, start, end);
+ arch_unmap(mm, vma, start, end);
+
/* Fix up all other VM information */
remove_vma_list(mm, vma);