Message ID | 20211104195804.83240-3-posk@google.com (mailing list archive) |
---|---|
State | New |
Headers | show |
Series | sched,mm,x86/uaccess: implement User Managed Concurrency Groups | expand |
Hi Peter, Thank you for the patch! Perhaps something to improve: [auto build test WARNING on 8ea9183db4ad8afbcb7089a77c23eaf965b0cacd] url: https://github.com/0day-ci/linux/commits/Peter-Oskolkov/sched-mm-x86-uaccess-implement-User-Managed-Concurrency-Groups/20211105-035945 base: 8ea9183db4ad8afbcb7089a77c23eaf965b0cacd config: arm-randconfig-r026-20211105 (attached as .config) compiler: clang version 14.0.0 (https://github.com/llvm/llvm-project 847a6807332b13f43704327c2d30103ec0347c77) reproduce (this is a W=1 build): wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross chmod +x ~/bin/make.cross # install arm cross compiling tool for clang build # apt-get install binutils-arm-linux-gnueabi # https://github.com/0day-ci/linux/commit/23012d2a531975af519f3a7c7a3152197efcbe13 git remote add linux-review https://github.com/0day-ci/linux git fetch --no-tags linux-review Peter-Oskolkov/sched-mm-x86-uaccess-implement-User-Managed-Concurrency-Groups/20211105-035945 git checkout 23012d2a531975af519f3a7c7a3152197efcbe13 # save the attached .config to linux build tree COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross W=1 ARCH=arm If you fix the issue, kindly add following tag as appropriate Reported-by: kernel test robot <lkp@intel.com> All warnings (new ones prefixed by >>): >> mm/maccess.c:491: warning: expecting prototype for xchg_user_[32|64][_nofault|]() - exchange 32/64(). Prototype was for xchg_user_32_nofault() instead vim +491 mm/maccess.c 474 475 /** 476 * xchg_user_[32|64][_nofault|]() - exchange 32/64-bit values 477 * @uaddr: Destination address, in user space; 478 * @val: Source address, in kernel space. 479 * 480 * This is the standard atomic xchg: exchange values pointed to by @uaddr and @val. 481 * 482 * The _nofault versions don't fault and can be used in 483 * atomic/preempt-disabled contexts. 484 * 485 * Return: 486 * 0 : OK/success; 487 * -EINVAL: @uaddr is not properly aligned ('may fault' versions only); 488 * -EFAULT: memory access error (including mis-aligned @uaddr in _nofault). 489 */ 490 int xchg_user_32_nofault(u32 __user *uaddr, u32 *val) > 491 { 492 int ret; 493 494 if (unlikely(!access_ok(uaddr, sizeof(*uaddr)))) 495 return -EFAULT; 496 497 pagefault_disable(); 498 499 if (!user_access_begin(uaddr, sizeof(*uaddr))) { 500 pagefault_enable(); 501 return -EFAULT; 502 } 503 504 ret = __try_xchg_user_32(val, uaddr, *val); 505 user_access_end(); 506 507 pagefault_enable(); 508 509 return ret; 510 } 511 --- 0-DAY CI Kernel Test Service, Intel Corporation https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
On Thu, Nov 04, 2021 at 12:58:00PM -0700, Peter Oskolkov wrote: > In addition to futexes needing to do atomic operations in the userspace, > a second use case is now in the works (UMCG, see > https://lore.kernel.org/all/20210917180323.278250-1-posk@google.com/), > so a generic facility to perform these operations has been called for > (see https://lore.kernel.org/all/87ilyk9xc0.ffs@tglx/). > > Add a set of generic helpers to perform 32/64-bit xchg and cmpxchg > operations in the userspace. Also implement the required > architecture-specific support on x86_64. > > Signed-off-by: Peter Oskolkov <posk@google.com> > --- > arch/x86/include/asm/uaccess_64.h | 93 +++++++++++ > include/linux/uaccess.h | 46 ++++++ > mm/maccess.c | 264 ++++++++++++++++++++++++++++++ > 3 files changed, 403 insertions(+) > > diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h > index 45697e04d771..41e2f96d3ec4 100644 > --- a/arch/x86/include/asm/uaccess_64.h > +++ b/arch/x86/include/asm/uaccess_64.h > @@ -79,4 +79,97 @@ __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size) > kasan_check_write(dst, size); > return __copy_user_flushcache(dst, src, size); > } > + > +#define ARCH_HAS_ATOMIC_UACCESS_HELPERS 1 > + > +static inline int __try_cmpxchg_user_32(u32 *uval, u32 __user *uaddr, > + u32 oldval, u32 newval) > +{ > + int ret = 0; > + > + asm volatile("\n" > + "1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n" > + "2:\n" > + "\t.section .fixup, \"ax\"\n" > + "3:\tmov %3, %0\n" > + "\tjmp 2b\n" > + "\t.previous\n" > + _ASM_EXTABLE_UA(1b, 3b) > + : "+r" (ret), "=a" (oldval), "+m" (*uaddr) > + : "i" (-EFAULT), "r" (newval), "1" (oldval) > + : "memory" > + ); > + *uval = oldval; > + return ret; > +} > + > +static inline int __try_cmpxchg_user_64(u64 *uval, u64 __user *uaddr, > + u64 oldval, u64 newval) > +{ > + int ret = 0; > + > + asm volatile("\n" > + "1:\t" LOCK_PREFIX "cmpxchgq %4, %2\n" > + "2:\n" > + "\t.section .fixup, \"ax\"\n" > + "3:\tmov %3, %0\n" > + "\tjmp 2b\n" > + "\t.previous\n" > + _ASM_EXTABLE_UA(1b, 3b) > + : "+r" (ret), "=a" (oldval), "+m" (*uaddr) > + : "i" (-EFAULT), "r" (newval), "1" (oldval) > + : "memory" > + ); > + *uval = oldval; > + return ret; > +} > + > +static inline int __try_xchg_user_32(u32 *oval, u32 __user *uaddr, u32 newval) > +{ > + u32 oldval = 0; > + int ret = 0; > + > + asm volatile("\n" > + "1:\txchgl %0, %2\n" > + "2:\n" > + "\t.section .fixup, \"ax\"\n" > + "3:\tmov %3, %1\n" > + "\tjmp 2b\n" > + "\t.previous\n" > + _ASM_EXTABLE_UA(1b, 3b) > + : "=r" (oldval), "=r" (ret), "+m" (*uaddr) > + : "i" (-EFAULT), "0" (newval), "1" (0) "1"(0) can be omitted, that ret is initialized. And the initialization of oldval not need. > + ); > + > + if (ret) > + return ret; > + > + *oval = oldval; > + return 0; > +} > + > +static inline int __try_xchg_user_64(u64 *oval, u64 __user *uaddr, u64 newval) > +{ > + u64 oldval = 0; > + int ret = 0; > + > + asm volatile("\n" > + "1:\txchgq %0, %2\n" > + "2:\n" > + "\t.section .fixup, \"ax\"\n" > + "3:\tmov %3, %1\n" > + "\tjmp 2b\n" > + "\t.previous\n" > + _ASM_EXTABLE_UA(1b, 3b) > + : "=r" (oldval), "=r" (ret), "+m" (*uaddr) > + : "i" (-EFAULT), "0" (newval), "1" (0) Same of above. > + ); > + > + if (ret) > + return ret; > + > + *oval = oldval; > + return 0; > +} > + > #endif /* _ASM_X86_UACCESS_64_H */ > diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h > index ac0394087f7d..dcb3ac093075 100644 > --- a/include/linux/uaccess.h > +++ b/include/linux/uaccess.h > @@ -408,4 +408,50 @@ void __noreturn usercopy_abort(const char *name, const char *detail, > unsigned long len); > #endif > > +#ifdef ARCH_HAS_ATOMIC_UACCESS_HELPERS > +/** > + * cmpxchg_user_[32|64][_nofault|]() - compare_exchange 32/64-bit values > + * @uaddr: Destination address, in user space; > + * @curr_val: Source address, in kernel space; > + * @new_val: The value to write to the destination address. > + * > + * This is the standard cmpxchg: atomically: compare *@uaddr to *@curr_val; > + * if the values match, write @new_val to @uaddr, return 0; if the values > + * do not match, write *@uaddr to @curr_val, return -EAGAIN. > + * > + * The _nofault versions don't fault and can be used in > + * atomic/preempt-disabled contexts. > + * > + * Return: > + * 0 : OK/success; > + * -EINVAL: @uaddr is not properly aligned ('may fault' versions only); > + * -EFAULT: memory access error (including mis-aligned @uaddr in _nofault); (including mis-aligned @uaddr in _fault) > + * -EAGAIN: @old did not match. > + */ > +int cmpxchg_user_32_nofault(u32 __user *uaddr, u32 *curr_val, u32 new_val); > +int cmpxchg_user_64_nofault(u64 __user *uaddr, u64 *curr_val, u64 new_val); > +int cmpxchg_user_32(u32 __user *uaddr, u32 *curr_val, u32 new_val); > +int cmpxchg_user_64(u64 __user *uaddr, u64 *curr_val, u64 new_val); > + > +/** > + * xchg_user_[32|64][_nofault|]() - exchange 32/64-bit values > + * @uaddr: Destination address, in user space; > + * @val: Source address, in kernel space. > + * > + * This is the standard atomic xchg: exchange values pointed to by @uaddr and @val. > + * > + * The _nofault versions don't fault and can be used in > + * atomic/preempt-disabled contexts. > + * > + * Return: > + * 0 : OK/success; > + * -EINVAL: @uaddr is not properly aligned ('may fault' versions only); > + * -EFAULT: memory access error (including mis-aligned @uaddr in _nofault). (including mis-aligned @uaddr in _fault) > + */ > +int xchg_user_32_nofault(u32 __user *uaddr, u32 *val); > +int xchg_user_64_nofault(u64 __user *uaddr, u64 *val); > +int xchg_user_32(u32 __user *uaddr, u32 *val); > +int xchg_user_64(u64 __user *uaddr, u64 *val); > +#endif /* ARCH_HAS_ATOMIC_UACCESS_HELPERS */ > + > #endif /* __LINUX_UACCESS_H__ */ > diff --git a/mm/maccess.c b/mm/maccess.c > index d3f1a1f0b1c1..620556b11550 100644 > --- a/mm/maccess.c > +++ b/mm/maccess.c > @@ -335,3 +335,267 @@ long strnlen_user_nofault(const void __user *unsafe_addr, long count) > > return ret; > } > + > +#ifdef ARCH_HAS_ATOMIC_UACCESS_HELPERS > + > +static int fix_pagefault(unsigned long uaddr, bool write_fault, int bytes) > +{ > + struct mm_struct *mm = current->mm; > + int ret; > + > + mmap_read_lock(mm); > + ret = fixup_user_fault(mm, uaddr, write_fault ? FAULT_FLAG_WRITE : 0, > + NULL); > + mmap_read_unlock(mm); > + > + return ret < 0 ? ret : 0; > +} > + > +int cmpxchg_user_32_nofault(u32 __user *uaddr, u32 *curr_val, u32 new_val) > +{ > + int ret = -EFAULT; > + u32 __old = *curr_val; > + > + if (unlikely(!access_ok(uaddr, sizeof(*uaddr)))) > + return -EFAULT; > + > + pagefault_disable(); > + > + if (!user_access_begin(uaddr, sizeof(*uaddr))) { > + pagefault_enable(); > + return -EFAULT; > + } > + ret = __try_cmpxchg_user_32(curr_val, uaddr, __old, new_val); > + user_access_end(); > + > + if (!ret) > + ret = *curr_val == __old ? 0 : -EAGAIN; > + > + pagefault_enable(); May this can be moved to be sibling to user_access_end() even do not know much about this to me. > + return ret; > +} > + > +int cmpxchg_user_64_nofault(u64 __user *uaddr, u64 *curr_val, u64 new_val) > +{ > + int ret = -EFAULT; > + u64 __old = *curr_val; > + > + if (unlikely(!access_ok(uaddr, sizeof(*uaddr)))) > + return -EFAULT; > + > + pagefault_disable(); > + > + if (!user_access_begin(uaddr, sizeof(*uaddr))) { > + pagefault_enable(); > + return -EFAULT; > + } > + ret = __try_cmpxchg_user_64(curr_val, uaddr, __old, new_val); > + user_access_end(); > + > + if (!ret) > + ret = *curr_val == __old ? 0 : -EAGAIN; > + > + pagefault_enable(); The same. > + return ret; > +} > + > +int cmpxchg_user_32(u32 __user *uaddr, u32 *curr_val, u32 new_val) > +{ > + int ret = -EFAULT; > + u32 __old = *curr_val; > + > + /* Validate proper alignment. */ > + if (unlikely(((unsigned long)uaddr % sizeof(*uaddr)) || See address. sizeof(*uaddr) --> sizeof(uaddr). The size of address length. > + ((unsigned long)curr_val % sizeof(*curr_val)))) Same. sizeof(*curr_val) --> sizeof(curr_val) > + return -EINVAL; This return should be -EFAULT accord to the comment above if not wrong to me. > + if (unlikely(!access_ok(uaddr, sizeof(*uaddr)))) > + return -EFAULT; > + > + pagefault_disable(); > + > + while (true) { > + ret = -EFAULT; > + if (!user_access_begin(uaddr, sizeof(*uaddr))) > + break; > + > + ret = __try_cmpxchg_user_32(curr_val, uaddr, __old, new_val); > + user_access_end(); > + > + if (!ret) { > + ret = *curr_val == __old ? 0 : -EAGAIN; > + break; > + } > + > + if (fix_pagefault((unsigned long)uaddr, true, sizeof(*uaddr)) < 0) > + break; > + } > + > + pagefault_enable(); > + return ret; > +} > + > +int cmpxchg_user_64(u64 __user *uaddr, u64 *curr_val, u64 new_val) > +{ > + int ret = -EFAULT; > + u64 __old = *curr_val; > + > + /* Validate proper alignment. */ > + if (unlikely(((unsigned long)uaddr % sizeof(*uaddr)) || > + ((unsigned long)curr_val % sizeof(*curr_val)))) > + return -EINVAL; The same as above.. even the address size is equal to the value size. Not use value size here. > + if (unlikely(!access_ok(uaddr, sizeof(*uaddr)))) > + return -EFAULT; > + > + pagefault_disable(); > + > + while (true) { > + ret = -EFAULT; > + if (!user_access_begin(uaddr, sizeof(*uaddr))) > + break; > + > + ret = __try_cmpxchg_user_64(curr_val, uaddr, __old, new_val); > + user_access_end(); > + > + if (!ret) { > + ret = *curr_val == __old ? 0 : -EAGAIN; > + break; > + } > + > + if (fix_pagefault((unsigned long)uaddr, true, sizeof(*uaddr)) < 0) > + break; > + } > + > + pagefault_enable(); > + return ret; > +} > + > +/** > + * xchg_user_[32|64][_nofault|]() - exchange 32/64-bit values > + * @uaddr: Destination address, in user space; > + * @val: Source address, in kernel space. > + * > + * This is the standard atomic xchg: exchange values pointed to by @uaddr and @val. > + * > + * The _nofault versions don't fault and can be used in > + * atomic/preempt-disabled contexts. > + * > + * Return: > + * 0 : OK/success; > + * -EINVAL: @uaddr is not properly aligned ('may fault' versions only); > + * -EFAULT: memory access error (including mis-aligned @uaddr in _nofault). > + */ > +int xchg_user_32_nofault(u32 __user *uaddr, u32 *val) > +{ > + int ret; > + > + if (unlikely(!access_ok(uaddr, sizeof(*uaddr)))) > + return -EFAULT; > + > + pagefault_disable(); > + > + if (!user_access_begin(uaddr, sizeof(*uaddr))) { > + pagefault_enable(); > + return -EFAULT; > + } > + > + ret = __try_xchg_user_32(val, uaddr, *val); > + user_access_end(); > + > + pagefault_enable(); > + > + return ret; > +} > + > +int xchg_user_64_nofault(u64 __user *uaddr, u64 *val) > +{ > + int ret; > + > + if (unlikely(!access_ok(uaddr, sizeof(*uaddr)))) > + return -EFAULT; > + > + pagefault_disable(); > + > + if (!user_access_begin(uaddr, sizeof(*uaddr))) { > + pagefault_enable(); > + return -EFAULT; > + } > + > + ret = __try_xchg_user_64(val, uaddr, *val); > + user_access_end(); > + > + pagefault_enable(); > + > + return ret; > +} > + > +int xchg_user_32(u32 __user *uaddr, u32 *val) > +{ > + int ret = -EFAULT; > + > + /* Validate proper alignment. */ > + if (unlikely(((unsigned long)uaddr % sizeof(*uaddr)) || > + ((unsigned long)val % sizeof(*val)))) > + return -EINVAL; The same as above. > + if (unlikely(!access_ok(uaddr, sizeof(*uaddr)))) > + return -EFAULT; > + > + pagefault_disable(); > + > + while (true) { > + ret = -EFAULT; > + if (!user_access_begin(uaddr, sizeof(*uaddr))) > + break; > + > + ret = __try_xchg_user_32(val, uaddr, *val); > + user_access_end(); > + > + if (!ret) > + break; > + > + if (fix_pagefault((unsigned long)uaddr, true, sizeof(*uaddr)) < 0) > + break; > + } > + > + pagefault_enable(); > + > + return ret; > +} > + > +int xchg_user_64(u64 __user *uaddr, u64 *val) > +{ > + int ret = -EFAULT; > + > + /* Validate proper alignment. */ > + if (unlikely(((unsigned long)uaddr % sizeof(*uaddr)) || > + ((unsigned long)val % sizeof(*val)))) > + return -EINVAL; The same as above.. > + if (unlikely(!access_ok(uaddr, sizeof(*uaddr)))) > + return -EFAULT; > + > + pagefault_disable(); > + > + while (true) { > + ret = -EFAULT; > + if (!user_access_begin(uaddr, sizeof(*uaddr))) > + break; > + > + ret = __try_xchg_user_64(val, uaddr, *val); > + user_access_end(); > + > + if (!ret) > + break; > + > + if (fix_pagefault((unsigned long)uaddr, true, sizeof(*uaddr)) < 0) > + break; > + } > + > + pagefault_enable(); > + > + return ret; > +} > +#endif /* ARCH_HAS_ATOMIC_UACCESS_HELPERS */ > -- > 2.25.1 >
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 45697e04d771..41e2f96d3ec4 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -79,4 +79,97 @@ __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size) kasan_check_write(dst, size); return __copy_user_flushcache(dst, src, size); } + +#define ARCH_HAS_ATOMIC_UACCESS_HELPERS 1 + +static inline int __try_cmpxchg_user_32(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) +{ + int ret = 0; + + asm volatile("\n" + "1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n" + "2:\n" + "\t.section .fixup, \"ax\"\n" + "3:\tmov %3, %0\n" + "\tjmp 2b\n" + "\t.previous\n" + _ASM_EXTABLE_UA(1b, 3b) + : "+r" (ret), "=a" (oldval), "+m" (*uaddr) + : "i" (-EFAULT), "r" (newval), "1" (oldval) + : "memory" + ); + *uval = oldval; + return ret; +} + +static inline int __try_cmpxchg_user_64(u64 *uval, u64 __user *uaddr, + u64 oldval, u64 newval) +{ + int ret = 0; + + asm volatile("\n" + "1:\t" LOCK_PREFIX "cmpxchgq %4, %2\n" + "2:\n" + "\t.section .fixup, \"ax\"\n" + "3:\tmov %3, %0\n" + "\tjmp 2b\n" + "\t.previous\n" + _ASM_EXTABLE_UA(1b, 3b) + : "+r" (ret), "=a" (oldval), "+m" (*uaddr) + : "i" (-EFAULT), "r" (newval), "1" (oldval) + : "memory" + ); + *uval = oldval; + return ret; +} + +static inline int __try_xchg_user_32(u32 *oval, u32 __user *uaddr, u32 newval) +{ + u32 oldval = 0; + int ret = 0; + + asm volatile("\n" + "1:\txchgl %0, %2\n" + "2:\n" + "\t.section .fixup, \"ax\"\n" + "3:\tmov %3, %1\n" + "\tjmp 2b\n" + "\t.previous\n" + _ASM_EXTABLE_UA(1b, 3b) + : "=r" (oldval), "=r" (ret), "+m" (*uaddr) + : "i" (-EFAULT), "0" (newval), "1" (0) + ); + + if (ret) + return ret; + + *oval = oldval; + return 0; +} + +static inline int __try_xchg_user_64(u64 *oval, u64 __user *uaddr, u64 newval) +{ + u64 oldval = 0; + int ret = 0; + + asm volatile("\n" + "1:\txchgq %0, %2\n" + "2:\n" + "\t.section .fixup, \"ax\"\n" + "3:\tmov %3, %1\n" + "\tjmp 2b\n" + "\t.previous\n" + _ASM_EXTABLE_UA(1b, 3b) + : "=r" (oldval), "=r" (ret), "+m" (*uaddr) + : "i" (-EFAULT), "0" (newval), "1" (0) + ); + + if (ret) + return ret; + + *oval = oldval; + return 0; +} + #endif /* _ASM_X86_UACCESS_64_H */ diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index ac0394087f7d..dcb3ac093075 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -408,4 +408,50 @@ void __noreturn usercopy_abort(const char *name, const char *detail, unsigned long len); #endif +#ifdef ARCH_HAS_ATOMIC_UACCESS_HELPERS +/** + * cmpxchg_user_[32|64][_nofault|]() - compare_exchange 32/64-bit values + * @uaddr: Destination address, in user space; + * @curr_val: Source address, in kernel space; + * @new_val: The value to write to the destination address. + * + * This is the standard cmpxchg: atomically: compare *@uaddr to *@curr_val; + * if the values match, write @new_val to @uaddr, return 0; if the values + * do not match, write *@uaddr to @curr_val, return -EAGAIN. + * + * The _nofault versions don't fault and can be used in + * atomic/preempt-disabled contexts. + * + * Return: + * 0 : OK/success; + * -EINVAL: @uaddr is not properly aligned ('may fault' versions only); + * -EFAULT: memory access error (including mis-aligned @uaddr in _nofault); + * -EAGAIN: @old did not match. + */ +int cmpxchg_user_32_nofault(u32 __user *uaddr, u32 *curr_val, u32 new_val); +int cmpxchg_user_64_nofault(u64 __user *uaddr, u64 *curr_val, u64 new_val); +int cmpxchg_user_32(u32 __user *uaddr, u32 *curr_val, u32 new_val); +int cmpxchg_user_64(u64 __user *uaddr, u64 *curr_val, u64 new_val); + +/** + * xchg_user_[32|64][_nofault|]() - exchange 32/64-bit values + * @uaddr: Destination address, in user space; + * @val: Source address, in kernel space. + * + * This is the standard atomic xchg: exchange values pointed to by @uaddr and @val. + * + * The _nofault versions don't fault and can be used in + * atomic/preempt-disabled contexts. + * + * Return: + * 0 : OK/success; + * -EINVAL: @uaddr is not properly aligned ('may fault' versions only); + * -EFAULT: memory access error (including mis-aligned @uaddr in _nofault). + */ +int xchg_user_32_nofault(u32 __user *uaddr, u32 *val); +int xchg_user_64_nofault(u64 __user *uaddr, u64 *val); +int xchg_user_32(u32 __user *uaddr, u32 *val); +int xchg_user_64(u64 __user *uaddr, u64 *val); +#endif /* ARCH_HAS_ATOMIC_UACCESS_HELPERS */ + #endif /* __LINUX_UACCESS_H__ */ diff --git a/mm/maccess.c b/mm/maccess.c index d3f1a1f0b1c1..620556b11550 100644 --- a/mm/maccess.c +++ b/mm/maccess.c @@ -335,3 +335,267 @@ long strnlen_user_nofault(const void __user *unsafe_addr, long count) return ret; } + +#ifdef ARCH_HAS_ATOMIC_UACCESS_HELPERS + +static int fix_pagefault(unsigned long uaddr, bool write_fault, int bytes) +{ + struct mm_struct *mm = current->mm; + int ret; + + mmap_read_lock(mm); + ret = fixup_user_fault(mm, uaddr, write_fault ? FAULT_FLAG_WRITE : 0, + NULL); + mmap_read_unlock(mm); + + return ret < 0 ? ret : 0; +} + +int cmpxchg_user_32_nofault(u32 __user *uaddr, u32 *curr_val, u32 new_val) +{ + int ret = -EFAULT; + u32 __old = *curr_val; + + if (unlikely(!access_ok(uaddr, sizeof(*uaddr)))) + return -EFAULT; + + pagefault_disable(); + + if (!user_access_begin(uaddr, sizeof(*uaddr))) { + pagefault_enable(); + return -EFAULT; + } + ret = __try_cmpxchg_user_32(curr_val, uaddr, __old, new_val); + user_access_end(); + + if (!ret) + ret = *curr_val == __old ? 0 : -EAGAIN; + + pagefault_enable(); + return ret; +} + +int cmpxchg_user_64_nofault(u64 __user *uaddr, u64 *curr_val, u64 new_val) +{ + int ret = -EFAULT; + u64 __old = *curr_val; + + if (unlikely(!access_ok(uaddr, sizeof(*uaddr)))) + return -EFAULT; + + pagefault_disable(); + + if (!user_access_begin(uaddr, sizeof(*uaddr))) { + pagefault_enable(); + return -EFAULT; + } + ret = __try_cmpxchg_user_64(curr_val, uaddr, __old, new_val); + user_access_end(); + + if (!ret) + ret = *curr_val == __old ? 0 : -EAGAIN; + + pagefault_enable(); + + return ret; +} + +int cmpxchg_user_32(u32 __user *uaddr, u32 *curr_val, u32 new_val) +{ + int ret = -EFAULT; + u32 __old = *curr_val; + + /* Validate proper alignment. */ + if (unlikely(((unsigned long)uaddr % sizeof(*uaddr)) || + ((unsigned long)curr_val % sizeof(*curr_val)))) + return -EINVAL; + + if (unlikely(!access_ok(uaddr, sizeof(*uaddr)))) + return -EFAULT; + + pagefault_disable(); + + while (true) { + ret = -EFAULT; + if (!user_access_begin(uaddr, sizeof(*uaddr))) + break; + + ret = __try_cmpxchg_user_32(curr_val, uaddr, __old, new_val); + user_access_end(); + + if (!ret) { + ret = *curr_val == __old ? 0 : -EAGAIN; + break; + } + + if (fix_pagefault((unsigned long)uaddr, true, sizeof(*uaddr)) < 0) + break; + } + + pagefault_enable(); + return ret; +} + +int cmpxchg_user_64(u64 __user *uaddr, u64 *curr_val, u64 new_val) +{ + int ret = -EFAULT; + u64 __old = *curr_val; + + /* Validate proper alignment. */ + if (unlikely(((unsigned long)uaddr % sizeof(*uaddr)) || + ((unsigned long)curr_val % sizeof(*curr_val)))) + return -EINVAL; + + if (unlikely(!access_ok(uaddr, sizeof(*uaddr)))) + return -EFAULT; + + pagefault_disable(); + + while (true) { + ret = -EFAULT; + if (!user_access_begin(uaddr, sizeof(*uaddr))) + break; + + ret = __try_cmpxchg_user_64(curr_val, uaddr, __old, new_val); + user_access_end(); + + if (!ret) { + ret = *curr_val == __old ? 0 : -EAGAIN; + break; + } + + if (fix_pagefault((unsigned long)uaddr, true, sizeof(*uaddr)) < 0) + break; + } + + pagefault_enable(); + return ret; +} + +/** + * xchg_user_[32|64][_nofault|]() - exchange 32/64-bit values + * @uaddr: Destination address, in user space; + * @val: Source address, in kernel space. + * + * This is the standard atomic xchg: exchange values pointed to by @uaddr and @val. + * + * The _nofault versions don't fault and can be used in + * atomic/preempt-disabled contexts. + * + * Return: + * 0 : OK/success; + * -EINVAL: @uaddr is not properly aligned ('may fault' versions only); + * -EFAULT: memory access error (including mis-aligned @uaddr in _nofault). + */ +int xchg_user_32_nofault(u32 __user *uaddr, u32 *val) +{ + int ret; + + if (unlikely(!access_ok(uaddr, sizeof(*uaddr)))) + return -EFAULT; + + pagefault_disable(); + + if (!user_access_begin(uaddr, sizeof(*uaddr))) { + pagefault_enable(); + return -EFAULT; + } + + ret = __try_xchg_user_32(val, uaddr, *val); + user_access_end(); + + pagefault_enable(); + + return ret; +} + +int xchg_user_64_nofault(u64 __user *uaddr, u64 *val) +{ + int ret; + + if (unlikely(!access_ok(uaddr, sizeof(*uaddr)))) + return -EFAULT; + + pagefault_disable(); + + if (!user_access_begin(uaddr, sizeof(*uaddr))) { + pagefault_enable(); + return -EFAULT; + } + + ret = __try_xchg_user_64(val, uaddr, *val); + user_access_end(); + + pagefault_enable(); + + return ret; +} + +int xchg_user_32(u32 __user *uaddr, u32 *val) +{ + int ret = -EFAULT; + + /* Validate proper alignment. */ + if (unlikely(((unsigned long)uaddr % sizeof(*uaddr)) || + ((unsigned long)val % sizeof(*val)))) + return -EINVAL; + + if (unlikely(!access_ok(uaddr, sizeof(*uaddr)))) + return -EFAULT; + + pagefault_disable(); + + while (true) { + ret = -EFAULT; + if (!user_access_begin(uaddr, sizeof(*uaddr))) + break; + + ret = __try_xchg_user_32(val, uaddr, *val); + user_access_end(); + + if (!ret) + break; + + if (fix_pagefault((unsigned long)uaddr, true, sizeof(*uaddr)) < 0) + break; + } + + pagefault_enable(); + + return ret; +} + +int xchg_user_64(u64 __user *uaddr, u64 *val) +{ + int ret = -EFAULT; + + /* Validate proper alignment. */ + if (unlikely(((unsigned long)uaddr % sizeof(*uaddr)) || + ((unsigned long)val % sizeof(*val)))) + return -EINVAL; + + if (unlikely(!access_ok(uaddr, sizeof(*uaddr)))) + return -EFAULT; + + pagefault_disable(); + + while (true) { + ret = -EFAULT; + if (!user_access_begin(uaddr, sizeof(*uaddr))) + break; + + ret = __try_xchg_user_64(val, uaddr, *val); + user_access_end(); + + if (!ret) + break; + + if (fix_pagefault((unsigned long)uaddr, true, sizeof(*uaddr)) < 0) + break; + } + + pagefault_enable(); + + return ret; +} +#endif /* ARCH_HAS_ATOMIC_UACCESS_HELPERS */
In addition to futexes needing to do atomic operations in the userspace, a second use case is now in the works (UMCG, see https://lore.kernel.org/all/20210917180323.278250-1-posk@google.com/), so a generic facility to perform these operations has been called for (see https://lore.kernel.org/all/87ilyk9xc0.ffs@tglx/). Add a set of generic helpers to perform 32/64-bit xchg and cmpxchg operations in the userspace. Also implement the required architecture-specific support on x86_64. Signed-off-by: Peter Oskolkov <posk@google.com> --- arch/x86/include/asm/uaccess_64.h | 93 +++++++++++ include/linux/uaccess.h | 46 ++++++ mm/maccess.c | 264 ++++++++++++++++++++++++++++++ 3 files changed, 403 insertions(+) -- 2.25.1