This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

copy_from_user (and a few other similar functions) are used to copy data from user memory into the kernel memory or vice versa. Since a user can provided a tagged pointer to one of the syscalls that use copy_from_user, we need to correctly handle such pointers.

Do this by untagging user pointers in access_ok and in __uaccess_mask_ptr, before performing access validity checks.

Note, that this patch only temporarily untags the pointers to perform the checks, but then passes them as is into the kernel internals.

Reviewed-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Andrey Konovalov andreyknvl@google.com --- arch/arm64/include/asm/uaccess.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index e5d5f31c6d36..9164ecb5feca 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -94,7 +94,7 @@ static inline unsigned long __range_ok(const void __user *addr, unsigned long si return ret; }

-#define access_ok(addr, size) __range_ok(addr, size) +#define access_ok(addr, size) __range_ok(untagged_addr(addr), size) #define user_addr_max get_fs

#define _ASM_EXTABLE(from, to) \ @@ -226,7 +226,8 @@ static inline void uaccess_enable_not_uao(void)

/* * Sanitise a uaccess pointer such that it becomes NULL if above the - * current addr_limit. + * current addr_limit. In case the pointer is tagged (has the top byte set), + * untag the pointer before checking. */ #define uaccess_mask_ptr(ptr) (__typeof__(ptr))__uaccess_mask_ptr(ptr) static inline void __user *__uaccess_mask_ptr(const void __user *ptr) @@ -234,10 +235,11 @@ static inline void __user *__uaccess_mask_ptr(const void __user *ptr) void __user *safe_ptr;

asm volatile( - " bics xzr, %1, %2\n" + " bics xzr, %3, %2\n" " csel %0, %1, xzr, eq\n" : "=&r" (safe_ptr) - : "r" (ptr), "r" (current_thread_info()->addr_limit) + : "r" (ptr), "r" (current_thread_info()->addr_limit), + "r" (untagged_addr(ptr)) : "cc");

csdb();

This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

This patch adds ksys_ wrappers to the following memory syscalls:

brk, get_mempolicy (renamed kernel_get_mempolicy -> ksys_get_mempolicy), madvise, mbind (renamed kernel_mbind -> ksys_mbind), mincore, mlock (renamed do_mlock -> ksys_mlock), mlock2, mmap_pgoff, mprotect (renamed do_mprotect_pkey -> ksys_mprotect_pkey), mremap, msync, munlock, munmap, remap_file_pages, shmat, shmdt.

The next patch in this series will add a custom implementation for these syscalls that makes them accept tagged pointers on arm64.

Signed-off-by: Andrey Konovalov andreyknvl@google.com --- include/linux/syscalls.h | 22 +++++++ ipc/shm.c | 7 ++- mm/madvise.c | 129 ++++++++++++++++++++------------------- mm/mempolicy.c | 21 +++---- mm/mincore.c | 57 +++++++++-------- mm/mlock.c | 20 ++++-- mm/mmap.c | 30 ++++++--- mm/mprotect.c | 6 +- mm/mremap.c | 27 +++++--- mm/msync.c | 35 ++++++----- 10 files changed, 213 insertions(+), 141 deletions(-)

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index e446806a561f..70008f5ed84f 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1260,6 +1260,28 @@ int ksys_ipc(unsigned int call, int first, unsigned long second, unsigned long third, void __user * ptr, long fifth); int compat_ksys_ipc(u32 call, int first, int second, u32 third, u32 ptr, u32 fifth); +unsigned long ksys_mremap(unsigned long addr, unsigned long old_len, + unsigned long new_len, unsigned long flags, + unsigned long new_addr); +int ksys_munmap(unsigned long addr, size_t len); +unsigned long ksys_brk(unsigned long brk); +int ksys_get_mempolicy(int __user *policy, unsigned long __user *nmask, + unsigned long maxnode, unsigned long addr, unsigned long flags); +int ksys_madvise(unsigned long start, size_t len_in, int behavior); +long ksys_mbind(unsigned long start, unsigned long len, + unsigned long mode, const unsigned long __user *nmask, + unsigned long maxnode, unsigned int flags); +__must_check int ksys_mlock(unsigned long start, size_t len, vm_flags_t flags); +__must_check int ksys_mlock2(unsigned long start, size_t len, vm_flags_t flags); +int ksys_munlock(unsigned long start, size_t len); +int ksys_mprotect_pkey(unsigned long start, size_t len, + unsigned long prot, int pkey); +int ksys_msync(unsigned long start, size_t len, int flags); +long ksys_mincore(unsigned long start, size_t len, unsigned char __user *vec); +unsigned long ksys_remap_file_pages(unsigned long start, unsigned long size, + unsigned long prot, unsigned long pgoff, unsigned long flags); +long ksys_shmat(int shmid, char __user *shmaddr, int shmflg); +long ksys_shmdt(char __user *shmaddr);

/* * The following kernel syscall equivalents are just wrappers to fs-internal diff --git a/ipc/shm.c b/ipc/shm.c index ce1ca9f7c6e9..557b43968c0e 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -1588,7 +1588,7 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, return err; }

-SYSCALL_DEFINE3(shmat, int, shmid, char __user *, shmaddr, int, shmflg) +long ksys_shmat(int shmid, char __user *shmaddr, int shmflg) { unsigned long ret; long err; @@ -1600,6 +1600,11 @@ SYSCALL_DEFINE3(shmat, int, shmid, char __user *, shmaddr, int, shmflg) return (long)ret; }

+SYSCALL_DEFINE3(shmat, int, shmid, char __user *, shmaddr, int, shmflg) +{ + return ksys_shmat(shmid, shmaddr, shmflg); +} + #ifdef CONFIG_COMPAT

#ifndef COMPAT_SHMLBA diff --git a/mm/madvise.c b/mm/madvise.c index 21a7881a2db4..c27f5f14e2ee 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -738,68 +738,7 @@ madvise_behavior_valid(int behavior) } }

-/* - * The madvise(2) system call. - * - * Applications can use madvise() to advise the kernel how it should - * handle paging I/O in this VM area. The idea is to help the kernel - * use appropriate read-ahead and caching techniques. The information - * provided is advisory only, and can be safely disregarded by the - * kernel without affecting the correct operation of the application. - * - * behavior values: - * MADV_NORMAL - the default behavior is to read clusters. This - * results in some read-ahead and read-behind. - * MADV_RANDOM - the system should read the minimum amount of data - * on any access, since it is unlikely that the appli- - * cation will need more than what it asks for. - * MADV_SEQUENTIAL - pages in the given range will probably be accessed - * once, so they can be aggressively read ahead, and - * can be freed soon after they are accessed. - * MADV_WILLNEED - the application is notifying the system to read - * some pages ahead. - * MADV_DONTNEED - the application is finished with the given range, - * so the kernel can free resources associated with it. - * MADV_FREE - the application marks pages in the given range as lazy free, - * where actual purges are postponed until memory pressure happens. - * MADV_REMOVE - the application wants to free up the given range of - * pages and associated backing store. - * MADV_DONTFORK - omit this area from child's address space when forking: - * typically, to avoid COWing pages pinned by get_user_pages(). - * MADV_DOFORK - cancel MADV_DONTFORK: no longer omit this area when forking. - * MADV_WIPEONFORK - present the child process with zero-filled memory in this - * range after a fork. - * MADV_KEEPONFORK - undo the effect of MADV_WIPEONFORK - * MADV_HWPOISON - trigger memory error handler as if the given memory range - * were corrupted by unrecoverable hardware memory failure. - * MADV_SOFT_OFFLINE - try to soft-offline the given range of memory. - * MADV_MERGEABLE - the application recommends that KSM try to merge pages in - * this area with pages of identical content from other such areas. - * MADV_UNMERGEABLE- cancel MADV_MERGEABLE: no longer merge pages with others. - * MADV_HUGEPAGE - the application wants to back the given range by transparent - * huge pages in the future. Existing pages might be coalesced and - * new pages might be allocated as THP. - * MADV_NOHUGEPAGE - mark the given range as not worth being backed by - * transparent huge pages so the existing pages will not be - * coalesced into THP and new pages will not be allocated as THP. - * MADV_DONTDUMP - the application wants to prevent pages in the given range - * from being included in its core dump. - * MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump. - * - * return values: - * zero - success - * -EINVAL - start + len < 0, start is not page-aligned, - * "behavior" is not a valid value, or application - * is attempting to release locked or shared pages, - * or the specified address range includes file, Huge TLB, - * MAP_SHARED or VMPFNMAP range. - * -ENOMEM - addresses in the specified range are not currently - * mapped, or are outside the AS of the process. - * -EIO - an I/O error occurred while paging in data. - * -EBADF - map exists, but area maps something that isn't a file. - * -EAGAIN - a kernel resource was temporarily unavailable. - */ -SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) +int ksys_madvise(unsigned long start, size_t len_in, int behavior) { unsigned long end, tmp; struct vm_area_struct *vma, *prev; @@ -894,3 +833,69 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)

return error; } + +/* + * The madvise(2) system call. + * + * Applications can use madvise() to advise the kernel how it should + * handle paging I/O in this VM area. The idea is to help the kernel + * use appropriate read-ahead and caching techniques. The information + * provided is advisory only, and can be safely disregarded by the + * kernel without affecting the correct operation of the application. + * + * behavior values: + * MADV_NORMAL - the default behavior is to read clusters. This + * results in some read-ahead and read-behind. + * MADV_RANDOM - the system should read the minimum amount of data + * on any access, since it is unlikely that the appli- + * cation will need more than what it asks for. + * MADV_SEQUENTIAL - pages in the given range will probably be accessed + * once, so they can be aggressively read ahead, and + * can be freed soon after they are accessed. + * MADV_WILLNEED - the application is notifying the system to read + * some pages ahead. + * MADV_DONTNEED - the application is finished with the given range, + * so the kernel can free resources associated with it. + * MADV_FREE - the application marks pages in the given range as lazy free, + * where actual purges are postponed until memory pressure happens. + * MADV_REMOVE - the application wants to free up the given range of + * pages and associated backing store. + * MADV_DONTFORK - omit this area from child's address space when forking: + * typically, to avoid COWing pages pinned by get_user_pages(). + * MADV_DOFORK - cancel MADV_DONTFORK: no longer omit this area when forking. + * MADV_WIPEONFORK - present the child process with zero-filled memory in this + * range after a fork. + * MADV_KEEPONFORK - undo the effect of MADV_WIPEONFORK + * MADV_HWPOISON - trigger memory error handler as if the given memory range + * were corrupted by unrecoverable hardware memory failure. + * MADV_SOFT_OFFLINE - try to soft-offline the given range of memory. + * MADV_MERGEABLE - the application recommends that KSM try to merge pages in + * this area with pages of identical content from other such areas. + * MADV_UNMERGEABLE- cancel MADV_MERGEABLE: no longer merge pages with others. + * MADV_HUGEPAGE - the application wants to back the given range by transparent + * huge pages in the future. Existing pages might be coalesced and + * new pages might be allocated as THP. + * MADV_NOHUGEPAGE - mark the given range as not worth being backed by + * transparent huge pages so the existing pages will not be + * coalesced into THP and new pages will not be allocated as THP. + * MADV_DONTDUMP - the application wants to prevent pages in the given range + * from being included in its core dump. + * MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump. + * + * return values: + * zero - success + * -EINVAL - start + len < 0, start is not page-aligned, + * "behavior" is not a valid value, or application + * is attempting to release locked or shared pages, + * or the specified address range includes file, Huge TLB, + * MAP_SHARED or VMPFNMAP range. + * -ENOMEM - addresses in the specified range are not currently + * mapped, or are outside the AS of the process. + * -EIO - an I/O error occurred while paging in data. + * -EBADF - map exists, but area maps something that isn't a file. + * -EAGAIN - a kernel resource was temporarily unavailable. + */ +SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) +{ + return ksys_madvise(start, len_in, behavior); +} diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 2219e747df49..c2f82a045ceb 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1352,9 +1352,9 @@ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0; }

-static long kernel_mbind(unsigned long start, unsigned long len, - unsigned long mode, const unsigned long __user *nmask, - unsigned long maxnode, unsigned int flags) +long ksys_mbind(unsigned long start, unsigned long len, + unsigned long mode, const unsigned long __user *nmask, + unsigned long maxnode, unsigned int flags) { nodemask_t nodes; int err; @@ -1377,7 +1377,7 @@ SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, unsigned long, mode, const unsigned long __user *, nmask, unsigned long, maxnode, unsigned int, flags) { - return kernel_mbind(start, len, mode, nmask, maxnode, flags); + return ksys_mbind(start, len, mode, nmask, maxnode, flags); }

/* Set the process memory policy */ @@ -1507,11 +1507,8 @@ SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode,

/* Retrieve NUMA policy */ -static int kernel_get_mempolicy(int __user *policy, - unsigned long __user *nmask, - unsigned long maxnode, - unsigned long addr, - unsigned long flags) +int ksys_get_mempolicy(int __user *policy, unsigned long __user *nmask, + unsigned long maxnode, unsigned long addr, unsigned long flags) { int err; int uninitialized_var(pval); @@ -1538,7 +1535,7 @@ SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, unsigned long __user *, nmask, unsigned long, maxnode, unsigned long, addr, unsigned long, flags) { - return kernel_get_mempolicy(policy, nmask, maxnode, addr, flags); + return ksys_get_mempolicy(policy, nmask, maxnode, addr, flags); }

#ifdef CONFIG_COMPAT @@ -1559,7 +1556,7 @@ COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, if (nmask) nm = compat_alloc_user_space(alloc_size);

- err = kernel_get_mempolicy(policy, nm, nr_bits+1, addr, flags); + err = ksys_get_mempolicy(policy, nm, nr_bits+1, addr, flags);

if (!err && nmask) { unsigned long copy_size; @@ -1613,7 +1610,7 @@ COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len, return -EFAULT; }

- return kernel_mbind(start, len, mode, nm, nr_bits+1, flags); + return ksys_mbind(start, len, mode, nm, nr_bits+1, flags); }

COMPAT_SYSCALL_DEFINE4(migrate_pages, compat_pid_t, pid, diff --git a/mm/mincore.c b/mm/mincore.c index 218099b5ed31..a609bd8128da 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -197,32 +197,7 @@ static long do_mincore(unsigned long addr, unsigned long pages, unsigned char *v return (end - addr) >> PAGE_SHIFT; }

-/* - * The mincore(2) system call. - * - * mincore() returns the memory residency status of the pages in the - * current process's address space specified by [addr, addr + len). - * The status is returned in a vector of bytes. The least significant - * bit of each byte is 1 if the referenced page is in memory, otherwise - * it is zero. - * - * Because the status of a page can change after mincore() checks it - * but before it returns to the application, the returned vector may - * contain stale information. Only locked pages are guaranteed to - * remain in memory. - * - * return values: - * zero - success - * -EFAULT - vec points to an illegal address - * -EINVAL - addr is not a multiple of PAGE_SIZE - * -ENOMEM - Addresses in the range [addr, addr + len] are - * invalid for the address space of this process, or - * specify one or more pages which are not currently - * mapped - * -EAGAIN - A kernel resource was temporarily unavailable. - */ -SYSCALL_DEFINE3(mincore, unsigned long, start, size_t, len, - unsigned char __user *, vec) +long ksys_mincore(unsigned long start, size_t len, unsigned char __user *vec) { long retval; unsigned long pages; @@ -271,3 +246,33 @@ SYSCALL_DEFINE3(mincore, unsigned long, start, size_t, len, free_page((unsigned long) tmp); return retval; } + +/* + * The mincore(2) system call. + * + * mincore() returns the memory residency status of the pages in the + * current process's address space specified by [addr, addr + len). + * The status is returned in a vector of bytes. The least significant + * bit of each byte is 1 if the referenced page is in memory, otherwise + * it is zero. + * + * Because the status of a page can change after mincore() checks it + * but before it returns to the application, the returned vector may + * contain stale information. Only locked pages are guaranteed to + * remain in memory. + * + * return values: + * zero - success + * -EFAULT - vec points to an illegal address + * -EINVAL - addr is not a multiple of PAGE_SIZE + * -ENOMEM - Addresses in the range [addr, addr + len] are + * invalid for the address space of this process, or + * specify one or more pages which are not currently + * mapped + * -EAGAIN - A kernel resource was temporarily unavailable. + */ +SYSCALL_DEFINE3(mincore, unsigned long, start, size_t, len, + unsigned char __user *, vec) +{ + return ksys_mincore(start, len, vec); +} diff --git a/mm/mlock.c b/mm/mlock.c index 080f3b36415b..09e449447539 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -668,7 +668,7 @@ static int count_mm_mlocked_page_nr(struct mm_struct *mm, return count >> PAGE_SHIFT; }

-static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t flags) +__must_check int ksys_mlock(unsigned long start, size_t len, vm_flags_t flags) { unsigned long locked; unsigned long lock_limit; @@ -715,10 +715,10 @@ static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t fla

SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len) { - return do_mlock(start, len, VM_LOCKED); + return ksys_mlock(start, len, VM_LOCKED); }

-SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags) +__must_check int ksys_mlock2(unsigned long start, size_t len, vm_flags_t flags) { vm_flags_t vm_flags = VM_LOCKED;

@@ -728,10 +728,15 @@ SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags) if (flags & MLOCK_ONFAULT) vm_flags |= VM_LOCKONFAULT;

- return do_mlock(start, len, vm_flags); + return ksys_mlock(start, len, vm_flags); }

-SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) +SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags) +{ + return ksys_mlock2(start, len, flags); +} + +int ksys_munlock(unsigned long start, size_t len) { int ret;

@@ -746,6 +751,11 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) return ret; }

+SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) +{ + return ksys_munlock(start, len); +} + /* * Take the MCL_* flags passed into mlockall (or 0 if called from munlockall) * and translate into the appropriate modifications to mm->def_flags and/or the diff --git a/mm/mmap.c b/mm/mmap.c index bd7b9f293b39..09bfaf36b961 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -189,7 +189,8 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)

static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long flags, struct list_head *uf); -SYSCALL_DEFINE1(brk, unsigned long, brk) + +unsigned long ksys_brk(unsigned long brk) { unsigned long retval; unsigned long newbrk, oldbrk, origbrk; @@ -288,6 +289,11 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) return retval; }

+SYSCALL_DEFINE1(brk, unsigned long, brk) +{ + return ksys_brk(brk); +} + static long vma_compute_subtree_gap(struct vm_area_struct *vma) { unsigned long max, prev_end, subtree_gap; @@ -2870,18 +2876,19 @@ int vm_munmap(unsigned long start, size_t len) } EXPORT_SYMBOL(vm_munmap);

-SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) +int ksys_munmap(unsigned long addr, size_t len) { profile_munmap(addr); return __vm_munmap(addr, len, true); }

+SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) +{ + return ksys_munmap(addr, len); +}

-/* - * Emulation of deprecated remap_file_pages() syscall. - */ -SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, - unsigned long, prot, unsigned long, pgoff, unsigned long, flags) +unsigned long ksys_remap_file_pages(unsigned long start, unsigned long size, + unsigned long prot, unsigned long pgoff, unsigned long flags) {

struct mm_struct *mm = current->mm; @@ -2976,6 +2983,15 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, return ret; }

+/* + * Emulation of deprecated remap_file_pages() syscall. + */ +SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, + unsigned long, prot, unsigned long, pgoff, unsigned long, flags) +{ + return ksys_remap_file_pages(start, size, prot, pgoff, flags); +} + /* * this is really a simplified "do_mmap". it only handles * anonymous maps. eventually we may be able to do some diff --git a/mm/mprotect.c b/mm/mprotect.c index 028c724dcb1a..07344bdd7a04 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -454,7 +454,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, /* * pkey==-1 when doing a legacy mprotect() */ -static int do_mprotect_pkey(unsigned long start, size_t len, +int ksys_mprotect_pkey(unsigned long start, size_t len, unsigned long prot, int pkey) { unsigned long nstart, end, tmp, reqprot; @@ -578,7 +578,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len, SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len, unsigned long, prot) { - return do_mprotect_pkey(start, len, prot, -1); + return ksys_mprotect_pkey(start, len, prot, -1); }

#ifdef CONFIG_ARCH_HAS_PKEYS @@ -586,7 +586,7 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len, SYSCALL_DEFINE4(pkey_mprotect, unsigned long, start, size_t, len, unsigned long, prot, int, pkey) { - return do_mprotect_pkey(start, len, prot, pkey); + return ksys_mprotect_pkey(start, len, prot, pkey); }

SYSCALL_DEFINE2(pkey_alloc, unsigned long, flags, unsigned long, init_val) diff --git a/mm/mremap.c b/mm/mremap.c index e3edef6b7a12..fec1f9911388 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -584,16 +584,9 @@ static int vma_expandable(struct vm_area_struct *vma, unsigned long delta) return 1; }

-/* - * Expand (or shrink) an existing mapping, potentially moving it at the - * same time (controlled by the MREMAP_MAYMOVE flag and available VM space) - * - * MREMAP_FIXED option added 5-Dec-1999 by Benjamin LaHaise - * This option implies MREMAP_MAYMOVE. - */ -SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, - unsigned long, new_len, unsigned long, flags, - unsigned long, new_addr) +unsigned long ksys_mremap(unsigned long addr, unsigned long old_len, + unsigned long new_len, unsigned long flags, + unsigned long new_addr) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; @@ -726,3 +719,17 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, userfaultfd_unmap_complete(mm, &uf_unmap); return ret; } + +/* + * Expand (or shrink) an existing mapping, potentially moving it at the + * same time (controlled by the MREMAP_MAYMOVE flag and available VM space) + * + * MREMAP_FIXED option added 5-Dec-1999 by Benjamin LaHaise + * This option implies MREMAP_MAYMOVE. + */ +SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, + unsigned long, new_len, unsigned long, flags, + unsigned long, new_addr) +{ + return ksys_mremap(addr, old_len, new_len, flags, new_addr); +} diff --git a/mm/msync.c b/mm/msync.c index ef30a429623a..b5a013549626 100644 --- a/mm/msync.c +++ b/mm/msync.c @@ -15,21 +15,7 @@ #include <linux/syscalls.h> #include <linux/sched.h>

-/* - * MS_SYNC syncs the entire file - including mappings. - * - * MS_ASYNC does not start I/O (it used to, up to 2.5.67). - * Nor does it marks the relevant pages dirty (it used to up to 2.6.17). - * Now it doesn't do anything, since dirty pages are properly tracked. - * - * The application may now run fsync() to - * write out the dirty pages and wait on the writeout and check the result. - * Or the application may run fadvise(FADV_DONTNEED) against the fd to start - * async writeout immediately. - * So by _not_ starting I/O in MS_ASYNC we provide complete flexibility to - * applications. - */ -SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags) +int ksys_msync(unsigned long start, size_t len, int flags) { unsigned long end; struct mm_struct *mm = current->mm; @@ -106,3 +92,22 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags) out: return error ? : unmapped_error; } + +/* + * MS_SYNC syncs the entire file - including mappings. + * + * MS_ASYNC does not start I/O (it used to, up to 2.5.67). + * Nor does it marks the relevant pages dirty (it used to up to 2.6.17). + * Now it doesn't do anything, since dirty pages are properly tracked. + * + * The application may now run fsync() to + * write out the dirty pages and wait on the writeout and check the result. + * Or the application may run fadvise(FADV_DONTNEED) against the fd to start + * async writeout immediately. + * So by _not_ starting I/O in MS_ASYNC we provide complete flexibility to + * applications. + */ +SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags) +{ + return ksys_msync(start, len, flags); +}

This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

do_pages_move() is used in the implementation of the move_pages syscall.

Untag user pointers in this function.

Signed-off-by: Andrey Konovalov andreyknvl@google.com --- mm/migrate.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/mm/migrate.c b/mm/migrate.c index 663a5449367a..c014a07135f0 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1617,6 +1617,7 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, if (get_user(node, nodes + i)) goto out_flush; addr = (unsigned long)p; + addr = untagged_addr(addr);

err = -ENODEV; if (node < 0 || node >= MAX_NUMNODES)

This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

get_vaddr_frames uses provided user pointers for vma lookups, which can only by done with untagged pointers. Instead of locating and changing all callers of this function, perform untagging in it.

Signed-off-by: Andrey Konovalov andreyknvl@google.com --- mm/frame_vector.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/mm/frame_vector.c b/mm/frame_vector.c index c64dca6e27c2..c431ca81dad5 100644 --- a/mm/frame_vector.c +++ b/mm/frame_vector.c @@ -46,6 +46,8 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, if (WARN_ON_ONCE(nr_frames > vec->nr_allocated)) nr_frames = vec->nr_allocated;

+ start = untagged_addr(start); + down_read(&mm->mmap_sem); locked = 1; vma = find_vma_intersection(mm, start, start + 1);

This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

userfaultfd_register() and userfaultfd_unregister() use provided user pointers for vma lookups, which can only by done with untagged pointers.

Untag user pointers in these functions.

Signed-off-by: Andrey Konovalov andreyknvl@google.com --- fs/userfaultfd.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index f5de1e726356..fdee0db0e847 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1325,6 +1325,9 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, goto out; }

+ uffdio_register.range.start = + untagged_addr(uffdio_register.range.start); + ret = validate_range(mm, uffdio_register.range.start, uffdio_register.range.len); if (ret) @@ -1514,6 +1517,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister))) goto out;

+ uffdio_unregister.start = untagged_addr(uffdio_unregister.start); + ret = validate_range(mm, uffdio_unregister.start, uffdio_unregister.len); if (ret)

This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

radeon_ttm_tt_pin_userptr() uses provided user pointers for vma lookups, which can only by done with untagged pointers. This patch untags user pointers when they are being set in radeon_ttm_tt_pin_userptr().

In amdgpu_gem_userptr_ioctl() an MMU notifier is set up with a (tagged) userspace pointer. The untagged address should be used so that MMU notifiers for the untagged address get correctly matched up with the right BO. This patch untags user pointers in radeon_gem_userptr_ioctl().

Signed-off-by: Andrey Konovalov andreyknvl@google.com --- drivers/gpu/drm/radeon/radeon_gem.c | 2 ++ drivers/gpu/drm/radeon/radeon_ttm.c | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index 44617dec8183..90eb78fb5eb2 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -291,6 +291,8 @@ int radeon_gem_userptr_ioctl(struct drm_device *dev, void *data, uint32_t handle; int r;

+ args->addr = untagged_addr(args->addr); + if (offset_in_page(args->addr | args->size)) return -EINVAL;

diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 9920a6fc11bf..dce722c494c1 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -742,7 +742,7 @@ int radeon_ttm_tt_set_userptr(struct ttm_tt *ttm, uint64_t addr, if (gtt == NULL) return -EINVAL;

- gtt->userptr = addr; + gtt->userptr = untagged_addr(addr); gtt->usermm = current->mm; gtt->userflags = flags; return 0;

This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

videobuf_dma_contig_user_get() uses provided user pointers for vma lookups, which can only by done with untagged pointers.

Untag the pointers in this function.

Signed-off-by: Andrey Konovalov andreyknvl@google.com --- drivers/media/v4l2-core/videobuf-dma-contig.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/media/v4l2-core/videobuf-dma-contig.c b/drivers/media/v4l2-core/videobuf-dma-contig.c index e1bf50df4c70..8a1ddd146b17 100644 --- a/drivers/media/v4l2-core/videobuf-dma-contig.c +++ b/drivers/media/v4l2-core/videobuf-dma-contig.c @@ -160,6 +160,7 @@ static void videobuf_dma_contig_user_put(struct videobuf_dma_contig_memory *mem) static int videobuf_dma_contig_user_get(struct videobuf_dma_contig_memory *mem, struct videobuf_buffer *vb) { + unsigned long untagged_baddr = untagged_addr(vb->baddr); struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long prev_pfn, this_pfn; @@ -167,22 +168,22 @@ static int videobuf_dma_contig_user_get(struct videobuf_dma_contig_memory *mem, unsigned int offset; int ret;

- offset = vb->baddr & ~PAGE_MASK; + offset = untagged_baddr & ~PAGE_MASK; mem->size = PAGE_ALIGN(vb->size + offset); ret = -EINVAL;

down_read(&mm->mmap_sem);

- vma = find_vma(mm, vb->baddr); + vma = find_vma(mm, untagged_baddr); if (!vma) goto out_up;

- if ((vb->baddr + mem->size) > vma->vm_end) + if ((untagged_baddr + mem->size) > vma->vm_end) goto out_up;

pages_done = 0; prev_pfn = 0; /* kill warning */ - user_address = vb->baddr; + user_address = untagged_baddr;

while (pages_done < (mem->size >> PAGE_SHIFT)) { ret = follow_pfn(vma, user_address, &this_pfn);

This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

vaddr_get_pfn() uses provided user pointers for vma lookups, which can only by done with untagged pointers.

Untag user pointers in this function.

Signed-off-by: Andrey Konovalov andreyknvl@google.com --- drivers/vfio/vfio_iommu_type1.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index d0f731c9920a..5daa966d799e 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -382,6 +382,8 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,

down_read(&mm->mmap_sem);

+ vaddr = untagged_addr(vaddr); + vma = find_vma_intersection(mm, vaddr, vaddr + 1);

if (vma && vma->vm_flags & VM_PFNMAP) {