aboutsummaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/powerpc/include/asm/mmu_context.h5
-rw-r--r--arch/um/include/asm/mmu_context.h5
-rw-r--r--arch/unicore32/include/asm/mmu_context.h5
-rw-r--r--arch/x86/Kconfig28
-rw-r--r--arch/x86/include/asm/bugs.h6
-rw-r--r--arch/x86/include/asm/disabled-features.h8
-rw-r--r--arch/x86/include/asm/mmu.h4
-rw-r--r--arch/x86/include/asm/mmu_context.h26
-rw-r--r--arch/x86/include/asm/mpx.h116
-rw-r--r--arch/x86/include/asm/processor.h18
-rw-r--r--arch/x86/include/asm/trace/mpx.h134
-rw-r--r--arch/x86/kernel/alternative.c1
-rw-r--r--arch/x86/kernel/cpu/common.c18
-rw-r--r--arch/x86/kernel/cpu/intel.c36
-rw-r--r--arch/x86/kernel/setup.c2
-rw-r--r--arch/x86/kernel/sys_x86_64.c9
-rw-r--r--arch/x86/kernel/traps.c74
-rw-r--r--arch/x86/mm/Makefile1
-rw-r--r--arch/x86/mm/hugetlbpage.c5
-rw-r--r--arch/x86/mm/mmap.c2
-rw-r--r--arch/x86/mm/mpx.c938
21 files changed, 2 insertions, 1439 deletions
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 58efca934311..360367c579de 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -238,11 +238,6 @@ static inline void arch_unmap(struct mm_struct *mm,
mm->context.vdso_base = 0;
}
-static inline void arch_bprm_mm_init(struct mm_struct *mm,
- struct vm_area_struct *vma)
-{
-}
-
#ifdef CONFIG_PPC_MEM_KEYS
bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write,
bool execute, bool foreign);
diff --git a/arch/um/include/asm/mmu_context.h b/arch/um/include/asm/mmu_context.h
index 5aee0626e390..b4deb1bfbb68 100644
--- a/arch/um/include/asm/mmu_context.h
+++ b/arch/um/include/asm/mmu_context.h
@@ -25,11 +25,6 @@ static inline void arch_unmap(struct mm_struct *mm,
unsigned long start, unsigned long end)
{
}
-static inline void arch_bprm_mm_init(struct mm_struct *mm,
- struct vm_area_struct *vma)
-{
-}
-
static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
bool write, bool execute, bool foreign)
{
diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h
index 247a07ae2cdc..388c0c811c68 100644
--- a/arch/unicore32/include/asm/mmu_context.h
+++ b/arch/unicore32/include/asm/mmu_context.h
@@ -89,11 +89,6 @@ static inline void arch_unmap(struct mm_struct *mm,
{
}
-static inline void arch_bprm_mm_init(struct mm_struct *mm,
- struct vm_area_struct *vma)
-{
-}
-
static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
bool write, bool execute, bool foreign)
{
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index a283336bb5d5..90288ab1b99e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1888,34 +1888,6 @@ config X86_UMIP
specific cases in protected and virtual-8086 modes. Emulated
results are dummy.
-config X86_INTEL_MPX
- prompt "Intel MPX (Memory Protection Extensions)"
- def_bool n
- # Note: only available in 64-bit mode due to VMA flags shortage
- depends on CPU_SUP_INTEL && X86_64
- select ARCH_USES_HIGH_VMA_FLAGS
- ---help---
- MPX provides hardware features that can be used in
- conjunction with compiler-instrumented code to check
- memory references. It is designed to detect buffer
- overflow or underflow bugs.
-
- This option enables running applications which are
- instrumented or otherwise use MPX. It does not use MPX
- itself inside the kernel or to protect the kernel
- against bad memory references.
-
- Enabling this option will make the kernel larger:
- ~8k of kernel text and 36 bytes of data on a 64-bit
- defconfig. It adds a long to the 'mm_struct' which
- will increase the kernel memory overhead of each
- process and adds some branches to paths used during
- exec() and munmap().
-
- For details, see Documentation/x86/intel_mpx.rst
-
- If unsure, say N.
-
config X86_INTEL_MEMORY_PROTECTION_KEYS
prompt "Intel Memory Protection Keys"
def_bool y
diff --git a/arch/x86/include/asm/bugs.h b/arch/x86/include/asm/bugs.h
index 794eb2129bc6..92ae28389940 100644
--- a/arch/x86/include/asm/bugs.h
+++ b/arch/x86/include/asm/bugs.h
@@ -6,12 +6,6 @@
extern void check_bugs(void);
-#if defined(CONFIG_CPU_SUP_INTEL)
-void check_mpx_erratum(struct cpuinfo_x86 *c);
-#else
-static inline void check_mpx_erratum(struct cpuinfo_x86 *c) {}
-#endif
-
#if defined(CONFIG_CPU_SUP_INTEL) && defined(CONFIG_X86_32)
int ppro_with_ram_bug(void);
#else
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 8e1d0bb46361..4ea8584682f9 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -10,12 +10,6 @@
* 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_SMAP
# define DISABLE_SMAP 0
#else
@@ -74,7 +68,7 @@
#define DISABLED_MASK6 0
#define DISABLED_MASK7 (DISABLE_PTI)
#define DISABLED_MASK8 0
-#define DISABLED_MASK9 (DISABLE_MPX|DISABLE_SMAP)
+#define DISABLED_MASK9 (DISABLE_SMAP)
#define DISABLED_MASK10 0
#define DISABLED_MASK11 0
#define DISABLED_MASK12 0
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index e78c7db87801..bdeae9291e5c 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -50,10 +50,6 @@ typedef struct {
u16 pkey_allocation_map;
s16 execute_only_pkey;
#endif
-#ifdef CONFIG_X86_INTEL_MPX
- /* address of the bounds directory */
- void __user *bd_addr;
-#endif
} mm_context_t;
#define INIT_MM_CONTEXT(mm) \
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index b243234e90cb..b538d9ddee9c 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -12,7 +12,6 @@
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include <asm/paravirt.h>
-#include <asm/mpx.h>
#include <asm/debugreg.h>
extern atomic64_t last_mm_ctx_id;
@@ -200,34 +199,9 @@ static inline bool is_64bit_mm(struct mm_struct *mm)
}
#endif
-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, unsigned long start,
unsigned long end)
{
- /*
- * mpx_notify_unmap() goes and reads a rarely-hot
- * cacheline in the mm_struct. That can be expensive
- * enough to be seen in profiles.
- *
- * The mpx_notify_unmap() call and its contents have been
- * observed to affect munmap() performance on hardware
- * where MPX is not present.
- *
- * The unlikely() optimizes for the fast case: no MPX
- * in the CPU, or no MPX use in the process. Even if
- * we get this wrong (in the unlikely event that MPX
- * is widely enabled on some system) the overhead of
- * MPX itself (reading bounds tables) is expected to
- * overwhelm the overhead of getting this unlikely()
- * consistently wrong.
- */
- if (unlikely(cpu_feature_enabled(X86_FEATURE_MPX)))
- mpx_notify_unmap(mm, start, end);
}
/*
diff --git a/arch/x86/include/asm/mpx.h b/arch/x86/include/asm/mpx.h
deleted file mode 100644
index 143a5c193ed3..000000000000
--- a/arch/x86/include/asm/mpx.h
+++ /dev/null
@@ -1,116 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_MPX_H
-#define _ASM_X86_MPX_H
-
-#include <linux/types.h>
-#include <linux/mm_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
-
-/*
- * The upper 28 bits [47:20] of the virtual address in 64-bit
- * are used to index into bounds directory (BD).
- *
- * The directory is 2G (2^31) in size, and with 8-byte entries
- * it has 2^28 entries.
- */
-#define MPX_BD_SIZE_BYTES_64 (1UL<<31)
-#define MPX_BD_ENTRY_BYTES_64 8
-#define MPX_BD_NR_ENTRIES_64 (MPX_BD_SIZE_BYTES_64/MPX_BD_ENTRY_BYTES_64)
-
-/*
- * The 32-bit directory is 4MB (2^22) in size, and with 4-byte
- * entries it has 2^20 entries.
- */
-#define MPX_BD_SIZE_BYTES_32 (1UL<<22)
-#define MPX_BD_ENTRY_BYTES_32 4
-#define MPX_BD_NR_ENTRIES_32 (MPX_BD_SIZE_BYTES_32/MPX_BD_ENTRY_BYTES_32)
-
-/*
- * A 64-bit table is 4MB total in size, and an entry is
- * 4 64-bit pointers in size.
- */
-#define MPX_BT_SIZE_BYTES_64 (1UL<<22)
-#define MPX_BT_ENTRY_BYTES_64 32
-#define MPX_BT_NR_ENTRIES_64 (MPX_BT_SIZE_BYTES_64/MPX_BT_ENTRY_BYTES_64)
-
-/*
- * A 32-bit table is 16kB total in size, and an entry is
- * 4 32-bit pointers in size.
- */
-#define MPX_BT_SIZE_BYTES_32 (1UL<<14)
-#define MPX_BT_ENTRY_BYTES_32 16
-#define MPX_BT_NR_ENTRIES_32 (MPX_BT_SIZE_BYTES_32/MPX_BT_ENTRY_BYTES_32)
-
-#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_BNDSTA_ERROR_CODE 0x3
-
-struct mpx_fault_info {
- void __user *addr;
- void __user *lower;
- void __user *upper;
-};
-
-#ifdef CONFIG_X86_INTEL_MPX
-
-extern int mpx_fault_info(struct mpx_fault_info *info, struct pt_regs *regs);
-extern int mpx_handle_bd_fault(void);
-
-static inline int kernel_managing_mpx_tables(struct mm_struct *mm)
-{
- return (mm->context.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->context.bd_addr = MPX_INVALID_BOUNDS_DIR;
-}
-
-extern void mpx_notify_unmap(struct mm_struct *mm, unsigned long start, unsigned long end);
-extern unsigned long mpx_unmapped_area_check(unsigned long addr, unsigned long len, unsigned long flags);
-
-#else
-static inline int mpx_fault_info(struct mpx_fault_info *info, struct pt_regs *regs)
-{
- return -EINVAL;
-}
-static inline int mpx_handle_bd_fault(void)
-{
- 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,
- unsigned long start, unsigned long end)
-{
-}
-
-static inline unsigned long mpx_unmapped_area_check(unsigned long addr,
- unsigned long len, unsigned long flags)
-{
- return addr;
-}
-#endif /* CONFIG_X86_INTEL_MPX */
-
-#endif /* _ASM_X86_MPX_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 6fb4870ed759..09705ccc393c 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -947,24 +947,6 @@ extern int set_tsc_mode(unsigned int val);
DECLARE_PER_CPU(u64, msr_misc_features_shadow);
-/* Register/unregister a process' MPX related resource */
-#define MPX_ENABLE_MANAGEMENT() mpx_enable_management()
-#define MPX_DISABLE_MANAGEMENT() mpx_disable_management()
-
-#ifdef CONFIG_X86_INTEL_MPX
-extern int mpx_enable_management(void);
-extern int mpx_disable_management(void);
-#else
-static inline int mpx_enable_management(void)
-{
- return -EINVAL;
-}
-static inline int mpx_disable_management(void)
-{
- return -EINVAL;
-}
-#endif /* CONFIG_X86_INTEL_MPX */
-
#ifdef CONFIG_CPU_SUP_AMD
extern u16 amd_get_nb_id(int cpu);
extern u32 amd_get_nodes_per_socket(void);
diff --git a/arch/x86/include/asm/trace/mpx.h b/arch/x86/include/asm/trace/mpx.h
deleted file mode 100644
index 54133017267c..000000000000
--- a/arch/x86/include/asm/trace/mpx.h
+++ /dev/null
@@ -1,134 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM mpx
-
-#if !defined(_TRACE_MPX_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_MPX_H
-
-#include <linux/tracepoint.h>
-
-#ifdef CONFIG_X86_INTEL_MPX
-
-TRACE_EVENT(mpx_bounds_register_exception,
-
- TP_PROTO(void __user *addr_referenced,
- const struct mpx_bndreg *bndreg),
- TP_ARGS(addr_referenced, bndreg),
-
- TP_STRUCT__entry(
- __field(void __user *, addr_referenced)
- __field(u64, lower_bound)
- __field(u64, upper_bound)
- ),
-
- TP_fast_assign(
- __entry->addr_referenced = addr_referenced;
- __entry->lower_bound = bndreg->lower_bound;
- __entry->upper_bound = bndreg->upper_bound;
- ),
- /*
- * Note that we are printing out the '~' of the upper
- * bounds register here. It is actually stored in its
- * one's complement form so that its 'init' state
- * corresponds to all 0's. But, that looks like
- * gibberish when printed out, so print out the 1's
- * complement instead of the actual value here. Note
- * though that you still need to specify filters for the
- * actual value, not the displayed one.
- */
- TP_printk("address referenced: 0x%p bounds: lower: 0x%llx ~upper: 0x%llx",
- __entry->addr_referenced,
- __entry->lower_bound,
- ~__entry->upper_bound
- )
-);
-
-TRACE_EVENT(bounds_exception_mpx,
-
- TP_PROTO(const struct mpx_bndcsr *bndcsr),
- TP_ARGS(bndcsr),
-
- TP_STRUCT__entry(
- __field(u64, bndcfgu)
- __field(u64, bndstatus)
- ),
-
- TP_fast_assign(
- /* need to get rid of the 'const' on bndcsr */
- __entry->bndcfgu = (u64)bndcsr->bndcfgu;
- __entry->bndstatus = (u64)bndcsr->bndstatus;
- ),
-
- TP_printk("bndcfgu:0x%llx bndstatus:0x%llx",
- __entry->bndcfgu,
- __entry->bndstatus)
-);
-
-DECLARE_EVENT_CLASS(mpx_range_trace,
-
- TP_PROTO(unsigned long start,
- unsigned long end),
- TP_ARGS(start, end),
-
- TP_STRUCT__entry(
- __field(unsigned long, start)
- __field(unsigned long, end)
- ),
-
- TP_fast_assign(
- __entry->start = start;
- __entry->end = end;
- ),
-
- TP_printk("[0x%p:0x%p]",
- (void *)__entry->start,
- (void *)__entry->end
- )
-);
-
-DEFINE_EVENT(mpx_range_trace, mpx_unmap_zap,
- TP_PROTO(unsigned long start, unsigned long end),
- TP_ARGS(start, end)
-);
-
-DEFINE_EVENT(mpx_range_trace, mpx_unmap_search,
- TP_PROTO(unsigned long start, unsigned long end),
- TP_ARGS(start, end)
-);
-
-TRACE_EVENT(mpx_new_bounds_table,
-
- TP_PROTO(unsigned long table_vaddr),
- TP_ARGS(table_vaddr),
-
- TP_STRUCT__entry(
- __field(unsigned long, table_vaddr)
- ),
-
- TP_fast_assign(
- __entry->table_vaddr = table_vaddr;
- ),
-
- TP_printk("table vaddr:%p", (void *)__entry->table_vaddr)
-);
-
-#else
-
-/*
- * This gets used outside of MPX-specific code, so we need a stub.
- */
-static inline
-void trace_bounds_exception_mpx(const struct mpx_bndcsr *bndcsr)
-{
-}
-
-#endif /* CONFIG_X86_INTEL_MPX */
-
-#undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH asm/trace/
-#undef TRACE_INCLUDE_FILE
-#define TRACE_INCLUDE_FILE mpx
-#endif /* _TRACE_MPX_H */
-
-/* This part must be outside protection */
-#include <trace/define_trace.h>
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 34360ca301a2..15ac0d5f4b40 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -23,6 +23,7 @@
#include <asm/nmi.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
+#include <asm/insn.h>
#include <asm/io.h>
#include <asm/fixmap.h>
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 86b8241c8209..52c9bfbbdb2a 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -164,22 +164,6 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
} };
EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
-static int __init x86_mpx_setup(char *s)
-{
- /* require an exact match without trailing characters */
- if (strlen(s))
- return 0;
-
- /* do not emit a message if the feature is not present */
- if (!boot_cpu_has(X86_FEATURE_MPX))
- return 1;
-
- setup_clear_cpu_cap(X86_FEATURE_MPX);
- pr_info("nompx: Intel Memory Protection Extensions (MPX) disabled\n");
- return 1;
-}
-__setup("nompx", x86_mpx_setup);
-
#ifdef CONFIG_X86_64
static int __init x86_nopcid_setup(char *s)
{
@@ -306,8 +290,6 @@ static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
static __init int setup_disable_smep(char *arg)
{
setup_clear_cpu_cap(X86_FEATURE_SMEP);
- /* Check for things that depend on SMEP being enabled: */
- check_mpx_erratum(&boot_cpu_data);
return 1;
}
__setup("nosmep", setup_disable_smep);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 57473e2c0869..be82cd5841c3 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -32,41 +32,6 @@
#endif
/*
- * Just in case our CPU detection goes bad, or you have a weird system,
- * allow a way to override the automatic disabling of MPX.
- */
-static int forcempx;
-
-static int __init forcempx_setup(char *__unused)
-{
- forcempx = 1;
-
- return 1;
-}
-__setup("intel-skd-046-workaround=disable", forcempx_setup);
-
-void check_mpx_erratum(struct cpuinfo_x86 *c)
-{
- if (forcempx)
- return;
- /*
- * Turn off the MPX feature on CPUs where SMEP is not
- * available or disabled.
- *
- * Works around Intel Erratum SKD046: "Branch Instructions
- * May Initialize MPX Bound Registers Incorrectly".
- *
- * This might falsely disable MPX on systems without
- * SMEP, like Atom processors without SMEP. But there
- * is no such hardware known at the moment.
- */
- if (cpu_has(c, X86_FEATURE_MPX) && !cpu_has(c, X86_FEATURE_SMEP)) {
- setup_clear_cpu_cap(X86_FEATURE_MPX);
- pr_warn("x86/mpx: Disabling MPX since SMEP not present\n");
- }
-}
-
-/*
* Processors which have self-snooping capability can handle conflicting
* memory type across CPUs by snooping its own cache. However, there exists
* CPU models in which having conflicting memory types still leads to
@@ -330,7 +295,6 @@ static void early_init_intel(struct cpuinfo_x86 *c)
c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff);
}
- check_mpx_erratum(c);
check_memory_type_self_snoop_errata(c);
/*
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 1e4c20a1efec..a74262c71484 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -893,8 +893,6 @@ 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;
rodata_resource.start = __pa_symbol(__start_rodata);
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index f7476ce23b6e..ca3c11a17b5a 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -22,7 +22,6 @@
#include <asm/elf.h>
#include <asm/ia32.h>
#include <asm/syscalls.h>
-#include <asm/mpx.h>
/*
* Align a virtual address to avoid aliasing in the I$ on AMD F15h.
@@ -137,10 +136,6 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
struct vm_unmapped_area_info info;
unsigned long begin, end;
- addr = mpx_unmapped_area_check(addr, len, flags);
- if (IS_ERR_VALUE(addr))
- return addr;
-
if (flags & MAP_FIXED)
return addr;
@@ -180,10 +175,6 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
unsigned long addr = addr0;
struct vm_unmapped_area_info info;
- addr = mpx_unmapped_area_check(addr, len, flags);
- if (IS_ERR_VALUE(addr))
- return addr;
-
/* requested length too big for entire address space */
if (len > TASK_SIZE)
return -ENOMEM;
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 9e6f822922a3..6ef00eb6fbb9 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -52,8 +52,6 @@
#include <asm/mach_traps.h>
#include <asm/alternative.h>
#include <asm/fpu/xstate.h>
-#include <asm/trace/mpx.h>
-#include <asm/mpx.h>
#include <asm/vm86.h>
#include <asm/umip.h>
#include <asm/insn.h>
@@ -436,8 +434,6 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsign
dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
{
- const struct mpx_bndcsr *bndcsr;
-
RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
if (notify_die(DIE_TRAP, "bounds", regs, error_code,
X86_TRAP_BR, SIGSEGV) == NOTIFY_STOP)
@@ -447,76 +443,6 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
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.
- * A NULL here might mean that it is in its 'init state',
- * which is all zeros which indicates MPX was not
- * responsible for the exception.
- */
- bndcsr = get_xsave_field_ptr(XFEATURE_BNDCSR);
- if (!bndcsr)
- goto exit_trap;
-
- trace_bounds_exception_mpx(bndcsr);
- /*
- * 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())
- goto exit_trap;
- break; /* Success, it was handled */
- case 1: /* Bound violation. */
- {
- struct task_struct *tsk = current;
- struct mpx_fault_info mpx;
-
- if (mpx_fault_info(&mpx, regs)) {
- /*
- * 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 'mpx' containing the address being accessed
- * which caused the exception. This information
- * allows and application to possibly handle the
- * #BR exception itself.
- */
- if (!do_trap_no_signal(tsk, X86_TRAP_BR, "bounds", regs,
- error_code))
- break;
-
- show_signal(tsk, SIGSEGV, "trap ", "bounds", regs, error_code);
-
- force_sig_bnderr(mpx.addr, mpx.lower, mpx.upper);
- break;
- }
- case 0: /* No exception caused by Intel MPX operations. */
- goto exit_trap;
- default:
- die("bounds", regs, error_code);
- }
-
- 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, 0, NULL);
}
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 345848f270e3..98aecb14fbcc 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -45,7 +45,6 @@ obj-$(CONFIG_AMD_NUMA) += amdtopology.o
obj-$(CONFIG_ACPI_NUMA) += srat.o
obj-$(CONFIG_NUMA_EMU) += numa_emulation.o
-obj-$(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
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index fab095362c50..5bfd5aef5378 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -19,7 +19,6 @@
#include <asm/tlbflush.h>
#include <asm/pgalloc.h>
#include <asm/elf.h>
-#include <asm/mpx.h>
#if 0 /* This is just for testing */
struct page *
@@ -151,10 +150,6 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
if (len & ~huge_page_mask(h))
return -EINVAL;
- addr = mpx_unmapped_area_check(addr, len, flags);
- if (IS_ERR_VALUE(addr))
- return addr;
-
if (len > TASK_SIZE)
return -ENOMEM;
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index aae9a933dfd4..cb91eccc4960 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -163,8 +163,6 @@ unsigned long get_mmap_base(int is_legacy)
const char *arch_vma_name(struct vm_area_struct *vma)
{
- if (vma->vm_flags & VM_MPX)
- return "[mpx]";
return NULL;
}
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
deleted file mode 100644
index 895fb7a9294d..000000000000
--- a/arch/x86/mm/mpx.c
+++ /dev/null
@@ -1,938 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * 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/mm_types.h>
-#include <linux/mman.h>
-#include <linux/syscalls.h>
-#include <linux/sched/sysctl.h>
-
-#include <asm/insn.h>
-#include <asm/insn-eval.h>
-#include <asm/mmu_context.h>
-#include <asm/mpx.h>
-#include <asm/processor.h>
-#include <asm/fpu/internal.h>
-
-#define CREATE_TRACE_POINTS
-#include <asm/trace/mpx.h>
-
-static inline unsigned long mpx_bd_size_bytes(struct mm_struct *mm)
-{
- if (is_64bit_mm(mm))
- return MPX_BD_SIZE_BYTES_64;
- else
- return MPX_BD_SIZE_BYTES_32;
-}
-
-static inline unsigned long mpx_bt_size_bytes(struct mm_struct *mm)
-{
- if (is_64bit_mm(mm))
- return MPX_BT_SIZE_BYTES_64;
- else
- return MPX_BT_SIZE_BYTES_32;
-}
-
-/*
- * This is really a simplified "vm_mmap". it only handles MPX
- * bounds tables (the bounds directory is user-allocated).
- */
-static unsigned long mpx_mmap(unsigned long len)
-{
- struct mm_struct *mm = current->mm;
- unsigned long addr, populate;
-
- /* Only bounds table can be allocated here */
- if (len != mpx_bt_size_bytes(mm))
- return -EINVAL;
-
- down_write(&mm->mmap_sem);
- addr = do_mmap(NULL, 0, len, PROT_READ | PROT_WRITE,
- MAP_ANONYMOUS | MAP_PRIVATE, VM_MPX, 0, &populate, NULL);
- up_write(&mm->mmap_sem);
- if (populate)
- mm_populate(addr, populate);
-
- return addr;
-}
-
-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...
- */
-int mpx_fault_info(struct mpx_fault_info *info, struct pt_regs *regs)
-{
- const struct mpx_bndreg_state *bndregs;
- const struct mpx_bndreg *bndreg;
- 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 bndregs field from current task's xsave area */
- bndregs = get_xsave_field_ptr(XFEATURE_BNDREGS);
- if (!bndregs) {
- err = -EINVAL;
- goto err_out;
- }
- /* now go select the individual register in the set of 4 */
- bndreg = &bndregs->bndreg[bndregno];
-
- /*
- * 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->lower = (void __user *)(unsigned long)bndreg->lower_bound;
- info->upper = (void __user *)(unsigned long)~bndreg->upper_bound;
- info->addr = insn_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->addr == (void __user *)-1) {
- err = -EINVAL;
- goto err_out;
- }
- trace_mpx_bounds_register_exception(info->addr, bndreg);
- return 0;
-err_out:
- /* info might be NULL, but kfree() handles that */
- return err;
-}
-
-static __user void *mpx_get_bounds_dir(void)
-{
- const struct mpx_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.
- */
- bndcsr = get_xsave_field_ptr(XFEATURE_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(void)
-{
- void __user *bd_base = MPX_INVALID_BOUNDS_DIR;
- struct mm_struct *mm = current->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.
- *
- * The copy_xregs_to_kernel() beneath get_xsave_field_ptr() is
- * expected to be relatively expensive. Storing the bounds
- * directory here means that we do not have to do xsave in the
- * unmap path; we can just use mm->context.bd_addr instead.
- */
- bd_base = mpx_get_bounds_dir();
- down_write(&mm->mmap_sem);
-
- /* MPX doesn't support addresses above 47 bits yet. */
- if (find_vma(mm, DEFAULT_MAP_WINDOW)) {
- pr_warn_once("%s (%d): MPX cannot handle addresses "
- "above 47-bits. Disabling.",
- current->comm, current->pid);
- ret = -ENXIO;
- goto out;
- }
- mm->context.bd_addr = bd_base;
- if (mm->context.bd_addr == MPX_INVALID_BOUNDS_DIR)
- ret = -ENXIO;
-out:
- up_write(&mm->mmap_sem);
- return ret;
-}
-
-int mpx_disable_management(void)
-{
- struct mm_struct *mm = current->mm;
-
- if (!cpu_feature_enabled(X86_FEATURE_MPX))
- return -ENXIO;
-
- down_write(&mm->mmap_sem);
- mm->context.bd_addr = MPX_INVALID_BOUNDS_DIR;
- up_write(&mm->mmap_sem);
- return 0;
-}
-
-static int mpx_cmpxchg_bd_entry(struct mm_struct *mm,
- unsigned long *curval,
- unsigned long __user *addr,
- unsigned long old_val, unsigned long new_val)
-{
- int ret;
- /*
- * user_atomic_cmpxchg_inatomic() actually uses sizeof()
- * the pointer that we pass to it to figure out how much
- * data to cmpxchg. We have to be careful here not to
- * pass a pointer to a 64-bit data type when we only want
- * a 32-bit copy.
- */
- if (is_64bit_mm(mm)) {
- ret = user_atomic_cmpxchg_inatomic(curval,
- addr, old_val, new_val);
- } else {
- u32 uninitialized_var(curval_32);
- u32 old_val_32 = old_val;
- u32 new_val_32 = new_val;
- u32 __user *addr_32 = (u32 __user *)addr;
-
- ret = user_atomic_cmpxchg_inatomic(&curval_32,
- addr_32, old_val_32, new_val_32);
- *curval = curval_32;
- }
- return ret;
-}
-
-/*
- * With 32-bit mode, a bounds directory is 4MB, and the size of each
- * bounds table is 16KB. With 64-bit mode, a bounds directory is 2GB,
- * and the size of each bounds table is 4MB.
- */
-static int allocate_bt(struct mm_struct *mm, long __user *bd_entry)
-{
- unsigned long expected_old_val = 0;
- unsigned long actual_old_val = 0;
- unsigned long bt_addr;
- unsigned long bd_new_entry;
- int ret = 0;
-
- /*
- * Carve the virtual space out of userspace for the new
- * bounds table:
- */
- bt_addr = mpx_mmap(mpx_bt_size_bytes(mm));
- if (IS_ERR((void *)bt_addr))
- return PTR_ERR((void *)bt_addr);
- /*
- * Set the valid flag (kinda like _PAGE_PRESENT in a pte)
- */
- bd_new_entry = 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 = mpx_cmpxchg_bd_entry(mm, &actual_old_val, bd_entry,
- expected_old_val, bd_new_entry);
- 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;
- }
- trace_mpx_new_bounds_table(bt_addr);
- return 0;
-out_unmap:
- vm_munmap(bt_addr, mpx_bt_size_bytes(mm));
- 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(void)
-{
- unsigned long bd_entry, bd_base;
- const struct mpx_bndcsr *bndcsr;
- struct mm_struct *mm = current->mm;
-
- bndcsr = get_xsave_field_ptr(XFEATURE_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(mm)))
- return -EINVAL;
-
- return allocate_bt(mm, (long __user *)bd_entry);
-}
-
-int mpx_handle_bd_fault(void)
-{
- /*
- * Userspace never asked us to manage the bounds tables,
- * so refuse to help.
- */
- if (!kernel_managing_mpx_tables(current->mm))
- return -EINVAL;
-
- return do_mpx_bt_fault();
-}
-
-/*
- * 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;
-
- gup_ret = get_user_pages((unsigned long)addr, nr_pages,
- write ? FOLL_WRITE : 0, 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;
-}
-
-static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm,
- unsigned long bd_entry)
-{
- unsigned long bt_addr = bd_entry;
- int align_to_bytes;
- /*
- * Bit 0 in a bt_entry is always the valid bit.
- */
- bt_addr &= ~MPX_BD_ENTRY_VALID_FLAG;
- /*
- * Tables are naturally aligned at 8-byte boundaries
- * on 64-bit and 4-byte boundaries on 32-bit. The
- * documentation makes it appear that the low bits
- * are ignored by the hardware, so we do the same.
- */
- if (is_64bit_mm(mm))
- align_to_bytes = 8;
- else
- align_to_bytes = 4;
- bt_addr &= ~(align_to_bytes-1);
- return bt_addr;
-}
-
-/*
- * We only want to do a 4-byte get_user() on 32-bit. Otherwise,
- * we might run off the end of the bounds table if we are on
- * a 64-bit kernel and try to get 8 bytes.
- */
-static int get_user_bd_entry(struct mm_struct *mm, unsigned long *bd_entry_ret,
- long __user *bd_entry_ptr)
-{
- u32 bd_entry_32;
- int ret;
-
- if (is_64bit_mm(mm))
- return get_user(*bd_entry_ret, bd_entry_ptr);
-
- /*
- * Note that get_user() uses the type of the *pointer* to
- * establish the size of the get, not the destination.
- */
- ret = get_user(bd_entry_32, (u32 __user *)bd_entry_ptr);
- *bd_entry_ret = bd_entry_32;
- return ret;
-}
-
-/*
- * 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_ptr,
- unsigned long *bt_addr_result)
-{
- int ret;
- int valid_bit;
- unsigned long bd_entry;
- unsigned long bt_addr;
-
- if (!access_ok((bd_entry_ptr), sizeof(*bd_entry_ptr)))
- return -EFAULT;
-
- while (1) {
- int need_write = 0;
-
- pagefault_disable();
- ret = get_user_bd_entry(mm, &bd_entry, bd_entry_ptr);
- pagefault_enable();
- if (!ret)
- break;
- if (ret == -EFAULT)
- ret = mpx_resolve_fault(bd_entry_ptr, need_write);
- /*
- * If we could not resolve the fault, consider it
- * userspace's fault and error out.
- */
- if (ret)
- return ret;
- }
-
- valid_bit = bd_entry & MPX_BD_ENTRY_VALID_FLAG;
- bt_addr = mpx_bd_entry_to_bt_addr(mm, bd_entry);
-
- /*
- * 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;
-
- *bt_addr_result = bt_addr;
- return 0;
-}
-
-static inline int bt_entry_size_bytes(struct mm_struct *mm)
-{
- if (is_64bit_mm(mm))
- return MPX_BT_ENTRY_BYTES_64;
- else
- return MPX_BT_ENTRY_BYTES_32;
-}
-
-/*
- * Take a virtual address and turns it in to the offset in bytes
- * inside of the bounds table where the bounds table entry
- * controlling 'addr' can be found.
- */
-static unsigned long mpx_get_bt_entry_offset_bytes(struct mm_struct *mm,
- unsigned long addr)
-{
- unsigned long bt_table_nr_entries;
- unsigned long offset = addr;
-
- if (is_64bit_mm(mm)) {
- /* Bottom 3 bits are ignored on 64-bit */
- offset >>= 3;
- bt_table_nr_entries = MPX_BT_NR_ENTRIES_64;
- } else {
- /* Bottom 2 bits are ignored on 32-bit */
- offset >>= 2;
- bt_table_nr_entries = MPX_BT_NR_ENTRIES_32;
- }
- /*
- * We know the size of the table in to which we are
- * indexing, and we have eliminated all the low bits
- * which are ignored for indexing.
- *
- * Mask out all the high bits which we do not need
- * to index in to the table. Note that the tables
- * are always powers of two so this gives us a proper
- * mask.
- */
- offset &= (bt_table_nr_entries-1);
- /*
- * We now have an entry offset in terms of *entries* in
- * the table. We need to scale it back up to bytes.
- */
- offset *= bt_entry_size_bytes(mm);
- return offset;
-}
-
-/*
- * How much virtual address space does a single bounds
- * directory entry cover?
- *
- * Note, we need a long long because 4GB doesn't fit in
- * to a long on 32-bit.
- */
-static inline unsigned long bd_entry_virt_space(struct mm_struct *mm)
-{
- unsigned long long virt_space;
- unsigned long long GB = (1ULL << 30);
-
- /*
- * This covers 32-bit emulation as well as 32-bit kernels
- * running on 64-bit hardware.
- */
- if (!is_64bit_mm(mm))
- return (4ULL * GB) / MPX_BD_NR_ENTRIES_32;
-
- /*
- * 'x86_virt_bits' returns what the hardware is capable
- * of, and returns the full >32-bit address space when
- * running 32-bit kernels on 64-bit hardware.
- */
- virt_space = (1ULL << boot_cpu_data.x86_virt_bits);
- return virt_space / MPX_BD_NR_ENTRIES_64;
-}
-
-/*
- * Free the backing physical pages of bounds table 'bt_addr'.
- * Assume start...end is within that bounds table.
- */
-static noinline int zap_bt_entries_mapping(struct mm_struct *mm,
- unsigned long bt_addr,
- unsigned long start_mapping, unsigned long end_mapping)
-{
- struct vm_area_struct *vma;
- unsigned long addr, len;
- unsigned long start;
- unsigned long end;
-
- /*
- * if we 'end' on a boundary, the offset will be 0 which
- * is not what we want. Back it up a byte to get the
- * last bt entry. Then once we have the entry itself,
- * move 'end' back up by the table entry size.
- */
- start = bt_addr + mpx_get_bt_entry_offset_bytes(mm, start_mapping);
- end = bt_addr + mpx_get_bt_entry_offset_bytes(mm, end_mapping - 1);
- /*
- * Move end back up by one entry. Among other things
- * this ensures that it remains page-aligned and does
- * not screw up zap_page_range()
- */
- end += bt_entry_size_bytes(mm);
-
- /*
- * 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 bounds 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 (!(vma->vm_flags & VM_MPX))
- return -EINVAL;
-
- len = min(vma->vm_end, end) - addr;
- zap_page_range(vma, addr, len);
- trace_mpx_unmap_zap(addr, addr+len);
-
- vma = vma->vm_next;
- addr = vma->vm_start;
- }
- return 0;
-}
-
-static unsigned long mpx_get_bd_entry_offset(struct mm_struct *mm,
- unsigned long addr)
-{
- /*
- * There are several ways to derive the bd offsets. We
- * use the following approach here:
- * 1. We know the size of the virtual address space
- * 2. We know the number of entries in a bounds table
- * 3. We know that each entry covers a fixed amount of
- * virtual address space.
- * So, we can just divide the virtual address by the
- * virtual space used by one entry to determine which
- * entry "controls" the given virtual address.
- */
- if (is_64bit_mm(mm)) {
- int bd_entry_size = 8; /* 64-bit pointer */
- /*
- * Take the 64-bit addressing hole in to account.
- */
- addr &= ((1UL << boot_cpu_data.x86_virt_bits) - 1);
- return (addr / bd_entry_virt_space(mm)) * bd_entry_size;
- } else {
- int bd_entry_size = 4; /* 32-bit pointer */
- /*
- * 32-bit has no hole so this case needs no mask
- */
- return (addr / bd_entry_virt_space(mm)) * bd_entry_size;
- }
- /*
- * The two return calls above are exact copies. If we
- * pull out a single copy and put it in here, gcc won't
- * realize that we're doing a power-of-2 divide and use
- * shifts. It uses a real divide. If we put them up
- * there, it manages to figure it out (gcc 4.8.3).
- */
-}
-
-static int unmap_entire_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 uninitialized_var(actual_old_val);
- int ret;
-
- while (1) {
- int need_write = 1;
- unsigned long cleared_bd_entry = 0;
-
- pagefault_disable();
- ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val,
- bd_entry, expected_old_val, cleared_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;
- }
- /*
- * The cmpxchg was performed, check the results.
- */
- if (actual_old_val != expected_old_val) {
- /*
- * Someone else raced with us to unmap the table.
- * That is OK, since we were both trying to do
- * the same thing. Declare success.
- */
- 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(mm), NULL);
-}
-
-static int try_unmap_single_bt(struct mm_struct *mm,
- unsigned long start, unsigned long end)
-{
- struct vm_area_struct *next;
- struct vm_area_struct *prev;
- /*
- * "bta" == Bounds Table Area: the area controlled by the
- * bounds table that we are unmapping.
- */
- unsigned long bta_start_vaddr = start & ~(bd_entry_virt_space(mm)-1);
- unsigned long bta_end_vaddr = bta_start_vaddr + bd_entry_virt_space(mm);
- unsigned long uninitialized_var(bt_addr);
- void __user *bde_vaddr;
- int ret;
- /*
- * We already unlinked 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);
- /*
- * Do not count other MPX bounds table VMAs as neighbors.
- * Although theoretically possible, we do not allow bounds
- * tables for bounds tables so our heads do not explode.
- * If we count them as neighbors here, we may end up with
- * lots of tables even though we have no actual table
- * entries in use.
- */
- while (next && (next->vm_flags & VM_MPX))
- next = next->vm_next;
- while (prev && (prev->vm_flags & VM_MPX))
- prev = prev->vm_prev;
- /*
- * We know 'start' and 'end' lie within an area controlled
- * by a single bounds table. See if there are any other
- * VMAs controlled by that bounds table. If there are not
- * then we can "expand" the are we are unmapping to possibly
- * cover the entire table.
- */
- next = find_vma_prev(mm, start, &prev);
- if ((!prev || prev->vm_end <= bta_start_vaddr) &&
- (!next || next->vm_start >= bta_end_vaddr)) {
- /*
- * No neighbor VMAs controlled by same bounds
- * table. Try to unmap the whole thing
- */
- start = bta_start_vaddr;
- end = bta_end_vaddr;
- }
-
- bde_vaddr = mm->context.bd_addr + mpx_get_bd_entry_offset(mm, start);
- ret = get_bt_addr(mm, bde_vaddr, &bt_addr);
- /*
- * No bounds table there, so nothing to unmap.
- */
- if (ret == -ENOENT) {
- ret = 0;
- return 0;
- }
- if (ret)
- return ret;
- /*
- * We are unmapping an entire table. Either because the
- * unmap that started this whole process was large enough
- * to cover an entire table, or that the unmap was small
- * but was the area covered by a bounds table.
- */
- if ((start == bta_start_vaddr) &&
- (end == bta_end_vaddr))
- return unmap_entire_bt(mm, bde_vaddr, bt_addr);
- return zap_bt_entries_mapping(mm, bt_addr, start, end);
-}
-
-static int mpx_unmap_tables(struct mm_struct *mm,
- unsigned long start, unsigned long end)
-{
- unsigned long one_unmap_start;
- trace_mpx_unmap_search(start, end);
-
- one_unmap_start = start;
- while (one_unmap_start < end) {
- int ret;
- unsigned long next_unmap_start = ALIGN(one_unmap_start+1,
- bd_entry_virt_space(mm));
- unsigned long one_unmap_end = end;
- /*
- * if the end is beyond the current bounds table,
- * move it back so we only deal with a single one
- * at a time
- */
- if (one_unmap_end > next_unmap_start)
- one_unmap_end = next_unmap_start;
- ret = try_unmap_single_bt(mm, one_unmap_start, one_unmap_end);
- if (ret)
- return ret;
-
- one_unmap_start = next_unmap_start;
- }
- 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, unsigned long start,
- unsigned long end)
-{
- struct vm_area_struct *vma;
- 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.
- */
- vma = find_vma(mm, start);
- while (vma && vma->vm_start < end) {
- if (vma->vm_flags & VM_MPX)
- return;
- vma = vma->vm_next;
- }
-
- ret = mpx_unmap_tables(mm, start, end);
- if (ret)
- force_sig(SIGSEGV);
-}
-
-/* MPX cannot handle addresses above 47 bits yet. */
-unsigned long mpx_unmapped_area_check(unsigned long addr, unsigned long len,
- unsigned long flags)
-{
- if (!kernel_managing_mpx_tables(current->mm))
- return addr;
- if (addr + len <= DEFAULT_MAP_WINDOW)
- return addr;
- if (flags & MAP_FIXED)
- return -ENOMEM;
-
- /*
- * Requested len is larger than the whole area we're allowed to map in.
- * Resetting hinting address wouldn't do much good -- fail early.
- */
- if (len > DEFAULT_MAP_WINDOW)
- return -ENOMEM;
-
- /* Look for unmap area within DEFAULT_MAP_WINDOW */
- return 0;
-}

Privacy Policy