From 4b692e861619353ce069e547a67c8d0e32d9ef3d Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 8 Sep 2021 15:18:10 -0700 Subject: kexec: move locking into do_kexec_load Patch series "compat: remove compat_alloc_user_space", v5. Going through compat_alloc_user_space() to convert indirect system call arguments tends to add complexity compared to handling the native and compat logic in the same code. This patch (of 6): The locking is the same between the native and compat version of sys_kexec_load(), so it can be done in the common implementation to reduce duplication. Link: https://lkml.kernel.org/r/20210727144859.4150043-1-arnd@kernel.org Link: https://lkml.kernel.org/r/20210727144859.4150043-2-arnd@kernel.org Signed-off-by: Arnd Bergmann Co-developed-by: Eric Biederman Co-developed-by: Christoph Hellwig Acked-by: "Eric W. Biederman" Cc: Catalin Marinas Cc: Will Deacon Cc: Thomas Bogendoerfer Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: "David S. Miller" Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Al Viro Cc: Feng Tang Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/kexec.c | 44 ++++++++++++++++---------------------------- 1 file changed, 16 insertions(+), 28 deletions(-) (limited to 'kernel') diff --git a/kernel/kexec.c b/kernel/kexec.c index c82c6c06f051..9c7aef8f4bb6 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -110,6 +110,17 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments, unsigned long i; int ret; + /* + * Because we write directly to the reserved memory region when loading + * crash kernels we need a mutex here to prevent multiple crash kernels + * from attempting to load simultaneously, and to prevent a crash kernel + * from loading over the top of a in use crash kernel. + * + * KISS: always take the mutex. + */ + if (!mutex_trylock(&kexec_mutex)) + return -EBUSY; + if (flags & KEXEC_ON_CRASH) { dest_image = &kexec_crash_image; if (kexec_crash_image) @@ -121,7 +132,8 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments, if (nr_segments == 0) { /* Uninstall image */ kimage_free(xchg(dest_image, NULL)); - return 0; + ret = 0; + goto out_unlock; } if (flags & KEXEC_ON_CRASH) { /* @@ -134,7 +146,7 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments, ret = kimage_alloc_init(&image, entry, nr_segments, segments, flags); if (ret) - return ret; + goto out_unlock; if (flags & KEXEC_PRESERVE_CONTEXT) image->preserve_context = 1; @@ -171,6 +183,8 @@ out: arch_kexec_protect_crashkres(); kimage_free(image); +out_unlock: + mutex_unlock(&kexec_mutex); return ret; } @@ -247,21 +261,8 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments, ((flags & KEXEC_ARCH_MASK) != KEXEC_ARCH_DEFAULT)) return -EINVAL; - /* Because we write directly to the reserved memory - * region when loading crash kernels we need a mutex here to - * prevent multiple crash kernels from attempting to load - * simultaneously, and to prevent a crash kernel from loading - * over the top of a in use crash kernel. - * - * KISS: always take the mutex. - */ - if (!mutex_trylock(&kexec_mutex)) - return -EBUSY; - result = do_kexec_load(entry, nr_segments, segments, flags); - mutex_unlock(&kexec_mutex); - return result; } @@ -301,21 +302,8 @@ COMPAT_SYSCALL_DEFINE4(kexec_load, compat_ulong_t, entry, return -EFAULT; } - /* Because we write directly to the reserved memory - * region when loading crash kernels we need a mutex here to - * prevent multiple crash kernels from attempting to load - * simultaneously, and to prevent a crash kernel from loading - * over the top of a in use crash kernel. - * - * KISS: always take the mutex. - */ - if (!mutex_trylock(&kexec_mutex)) - return -EBUSY; - result = do_kexec_load(entry, nr_segments, ksegments, flags); - mutex_unlock(&kexec_mutex); - return result; } #endif -- cgit v1.2.3 From 5d700a0fd71ded7096b97f01d276efc1a6579613 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 8 Sep 2021 15:18:13 -0700 Subject: kexec: avoid compat_alloc_user_space kimage_alloc_init() expects a __user pointer, so compat_sys_kexec_load() uses compat_alloc_user_space() to convert the layout and put it back onto the user space caller stack. Moving the user space access into the syscall handler directly actually makes the code simpler, as the conversion for compat mode can now be done on kernel memory. Link: https://lkml.kernel.org/r/20210727144859.4150043-3-arnd@kernel.org Link: https://lore.kernel.org/lkml/YPbtsU4GX6PL7%2F42@infradead.org/ Link: https://lore.kernel.org/lkml/m1y2cbzmnw.fsf@fess.ebiederm.org/ Signed-off-by: Arnd Bergmann Co-developed-by: Eric Biederman Co-developed-by: Christoph Hellwig Acked-by: "Eric W. Biederman" Cc: Al Viro Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Christoph Hellwig Cc: "David S. Miller" Cc: Feng Tang Cc: Heiko Carstens Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Michael Ellerman Cc: Paul Mackerras Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/kexec.c | 61 ++++++++++++++++++++++++---------------------------------- 1 file changed, 25 insertions(+), 36 deletions(-) (limited to 'kernel') diff --git a/kernel/kexec.c b/kernel/kexec.c index 9c7aef8f4bb6..b5e40f069768 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -19,26 +19,9 @@ #include "kexec_internal.h" -static int copy_user_segment_list(struct kimage *image, - unsigned long nr_segments, - struct kexec_segment __user *segments) -{ - int ret; - size_t segment_bytes; - - /* Read in the segments */ - image->nr_segments = nr_segments; - segment_bytes = nr_segments * sizeof(*segments); - ret = copy_from_user(image->segment, segments, segment_bytes); - if (ret) - ret = -EFAULT; - - return ret; -} - static int kimage_alloc_init(struct kimage **rimage, unsigned long entry, unsigned long nr_segments, - struct kexec_segment __user *segments, + struct kexec_segment *segments, unsigned long flags) { int ret; @@ -58,10 +41,8 @@ static int kimage_alloc_init(struct kimage **rimage, unsigned long entry, return -ENOMEM; image->start = entry; - - ret = copy_user_segment_list(image, nr_segments, segments); - if (ret) - goto out_free_image; + image->nr_segments = nr_segments; + memcpy(image->segment, segments, nr_segments * sizeof(*segments)); if (kexec_on_panic) { /* Enable special crash kernel control page alloc policy. */ @@ -104,7 +85,7 @@ out_free_image: } static int do_kexec_load(unsigned long entry, unsigned long nr_segments, - struct kexec_segment __user *segments, unsigned long flags) + struct kexec_segment *segments, unsigned long flags) { struct kimage **dest_image, *image; unsigned long i; @@ -250,7 +231,8 @@ static inline int kexec_load_check(unsigned long nr_segments, SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments, struct kexec_segment __user *, segments, unsigned long, flags) { - int result; + struct kexec_segment *ksegments; + unsigned long result; result = kexec_load_check(nr_segments, flags); if (result) @@ -261,7 +243,12 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments, ((flags & KEXEC_ARCH_MASK) != KEXEC_ARCH_DEFAULT)) return -EINVAL; - result = do_kexec_load(entry, nr_segments, segments, flags); + ksegments = memdup_user(segments, nr_segments * sizeof(ksegments[0])); + if (IS_ERR(ksegments)) + return PTR_ERR(ksegments); + + result = do_kexec_load(entry, nr_segments, ksegments, flags); + kfree(ksegments); return result; } @@ -273,7 +260,7 @@ COMPAT_SYSCALL_DEFINE4(kexec_load, compat_ulong_t, entry, compat_ulong_t, flags) { struct compat_kexec_segment in; - struct kexec_segment out, __user *ksegments; + struct kexec_segment *ksegments; unsigned long i, result; result = kexec_load_check(nr_segments, flags); @@ -286,24 +273,26 @@ COMPAT_SYSCALL_DEFINE4(kexec_load, compat_ulong_t, entry, if ((flags & KEXEC_ARCH_MASK) == KEXEC_ARCH_DEFAULT) return -EINVAL; - ksegments = compat_alloc_user_space(nr_segments * sizeof(out)); + ksegments = kmalloc_array(nr_segments, sizeof(ksegments[0]), + GFP_KERNEL); + if (!ksegments) + return -ENOMEM; + for (i = 0; i < nr_segments; i++) { result = copy_from_user(&in, &segments[i], sizeof(in)); if (result) - return -EFAULT; + goto fail; - out.buf = compat_ptr(in.buf); - out.bufsz = in.bufsz; - out.mem = in.mem; - out.memsz = in.memsz; - - result = copy_to_user(&ksegments[i], &out, sizeof(out)); - if (result) - return -EFAULT; + ksegments[i].buf = compat_ptr(in.buf); + ksegments[i].bufsz = in.bufsz; + ksegments[i].mem = in.mem; + ksegments[i].memsz = in.memsz; } result = do_kexec_load(entry, nr_segments, ksegments, flags); +fail: + kfree(ksegments); return result; } #endif -- cgit v1.2.3 From 59ab844eed9c6b01d32dcb27b57accc23771b324 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 8 Sep 2021 15:18:25 -0700 Subject: compat: remove some compat entry points These are all handled correctly when calling the native system call entry point, so remove the special cases. Link: https://lkml.kernel.org/r/20210727144859.4150043-6-arnd@kernel.org Signed-off-by: Arnd Bergmann Reviewed-by: Christoph Hellwig Cc: Al Viro Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Christoph Hellwig Cc: "David S. Miller" Cc: Eric Biederman Cc: Feng Tang Cc: Heiko Carstens Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Michael Ellerman Cc: Paul Mackerras Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sys_ni.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'kernel') diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 64578adfe115..f43d89d92860 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -292,15 +292,10 @@ COND_SYSCALL(process_madvise); COND_SYSCALL(process_mrelease); COND_SYSCALL(remap_file_pages); COND_SYSCALL(mbind); -COND_SYSCALL_COMPAT(mbind); COND_SYSCALL(get_mempolicy); -COND_SYSCALL_COMPAT(get_mempolicy); COND_SYSCALL(set_mempolicy); -COND_SYSCALL_COMPAT(set_mempolicy); COND_SYSCALL(migrate_pages); -COND_SYSCALL_COMPAT(migrate_pages); COND_SYSCALL(move_pages); -COND_SYSCALL_COMPAT(move_pages); COND_SYSCALL(perf_event_open); COND_SYSCALL(accept4); -- cgit v1.2.3 From a7a08b275a8bbade798c4bdaad07ade68fe7003c Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 8 Sep 2021 15:18:29 -0700 Subject: arch: remove compat_alloc_user_space All users of compat_alloc_user_space() and copy_in_user() have been removed from the kernel, only a few functions in sparc remain that can be changed to calling arch_copy_in_user() instead. Link: https://lkml.kernel.org/r/20210727144859.4150043-7-arnd@kernel.org Signed-off-by: Arnd Bergmann Reviewed-by: Christoph Hellwig Cc: Al Viro Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Christoph Hellwig Cc: "David S. Miller" Cc: Eric Biederman Cc: Feng Tang Cc: Heiko Carstens Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Michael Ellerman Cc: Paul Mackerras Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/compat.c | 21 --------------------- 1 file changed, 21 deletions(-) (limited to 'kernel') diff --git a/kernel/compat.c b/kernel/compat.c index 05adfd6fa8bf..55551989d9da 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -269,24 +269,3 @@ get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat) return 0; } EXPORT_SYMBOL_GPL(get_compat_sigset); - -/* - * Allocate user-space memory for the duration of a single system call, - * in order to marshall parameters inside a compat thunk. - */ -void __user *compat_alloc_user_space(unsigned long len) -{ - void __user *ptr; - - /* If len would occupy more than half of the entire compat space... */ - if (unlikely(len > (((compat_uptr_t)~0) >> 1))) - return NULL; - - ptr = arch_compat_alloc_user_space(len); - - if (unlikely(!access_ok(ptr, len))) - return NULL; - - return ptr; -} -EXPORT_SYMBOL_GPL(compat_alloc_user_space); -- cgit v1.2.3 From 13db8c50477d83ad3e3b9b0ae247e5cd833a7ae4 Mon Sep 17 00:00:00 2001 From: Liu Zixian Date: Wed, 8 Sep 2021 18:10:05 -0700 Subject: mm/hugetlb: initialize hugetlb_usage in mm_init After fork, the child process will get incorrect (2x) hugetlb_usage. If a process uses 5 2MB hugetlb pages in an anonymous mapping, HugetlbPages: 10240 kB and then forks, the child will show, HugetlbPages: 20480 kB The reason for double the amount is because hugetlb_usage will be copied from the parent and then increased when we copy page tables from parent to child. Child will have 2x actual usage. Fix this by adding hugetlb_count_init in mm_init. Link: https://lkml.kernel.org/r/20210826071742.877-1-liuzixian4@huawei.com Fixes: 5d317b2b6536 ("mm: hugetlb: proc: add HugetlbPages field to /proc/PID/status") Signed-off-by: Liu Zixian Reviewed-by: Naoya Horiguchi Reviewed-by: Mike Kravetz Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index ff5be23800af..38681ad44c76 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1063,6 +1063,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm->pmd_huge_pte = NULL; #endif mm_init_uprobes_state(mm); + hugetlb_count_init(mm); if (current->mm) { mm->flags = current->mm->flags & MMF_INIT_MASK; -- cgit v1.2.3