diff options
38 files changed, 357 insertions, 282 deletions
@@ -322,6 +322,7 @@ Jayachandran C <c.jayachandran@gmail.com> <jchandra@broadcom.com> Jayachandran C <c.jayachandran@gmail.com> <jchandra@digeo.com> Jayachandran C <c.jayachandran@gmail.com> <jnair@caviumnetworks.com> <jean-philippe@linaro.org> <jean-philippe.brucker@arm.com> +Jean-Michel Hautbois <jeanmichel.hautbois@yoseli.org> <jeanmichel.hautbois@ideasonboard.com> Jean Tourrilhes <jt@hpl.hp.com> Jeevan Shriram <quic_jshriram@quicinc.com> <jshriram@codeaurora.org> Jeff Garzik <jgarzik@pretzel.yyz.us> @@ -438,6 +439,8 @@ Linus Lüssing <linus.luessing@c0d3.blue> <ll@simonwunderlich.de> Li Yang <leoyang.li@nxp.com> <leoli@freescale.com> Li Yang <leoyang.li@nxp.com> <leo@zh-kernel.org> Lior David <quic_liord@quicinc.com> <liord@codeaurora.org> +Loic Poulain <loic.poulain@oss.qualcomm.com> <loic.poulain@linaro.org> +Loic Poulain <loic.poulain@oss.qualcomm.com> <loic.poulain@intel.com> Lorenzo Pieralisi <lpieralisi@kernel.org> <lorenzo.pieralisi@arm.com> Lorenzo Stoakes <lorenzo.stoakes@oracle.com> <lstoakes@gmail.com> Luca Ceresoli <luca.ceresoli@bootlin.com> <luca@lucaceresoli.net> diff --git a/Documentation/userspace-api/mseal.rst b/Documentation/userspace-api/mseal.rst index 1dabfc29be0d..7195a7f91107 100644 --- a/Documentation/userspace-api/mseal.rst +++ b/Documentation/userspace-api/mseal.rst @@ -27,7 +27,7 @@ SYSCALL ======= mseal syscall signature ----------------------- - ``int mseal(void \* addr, size_t len, unsigned long flags)`` + ``int mseal(void *addr, size_t len, unsigned long flags)`` **addr**/**len**: virtual memory address range. The address range set by **addr**/**len** must meet: diff --git a/MAINTAINERS b/MAINTAINERS index c59316109e3f..47df41261dc1 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10956,6 +10956,7 @@ F: include/linux/platform_data/huawei-gaokun-ec.h HUGETLB SUBSYSTEM M: Muchun Song <muchun.song@linux.dev> +R: Oscar Salvador <osalvador@suse.de> L: linux-mm@kvack.org S: Maintained F: Documentation/ABI/testing/sysfs-kernel-mm-hugepages @@ -12812,6 +12813,7 @@ F: lib/Kconfig.kcsan F: scripts/Makefile.kcsan KDUMP +M: Andrew Morton <akpm@linux-foundation.org> M: Baoquan He <bhe@redhat.com> R: Vivek Goyal <vgoyal@redhat.com> R: Dave Young <dyoung@redhat.com> @@ -13113,6 +13115,8 @@ F: fs/kernfs/ F: include/linux/kernfs.h KEXEC +M: Andrew Morton <akpm@linux-foundation.org> +M: Baoquan He <bhe@redhat.com> L: kexec@lists.infradead.org W: http://kernel.org/pub/linux/utils/kernel/kexec/ F: include/linux/kexec.h diff --git a/drivers/fpga/tests/fpga-bridge-test.c b/drivers/fpga/tests/fpga-bridge-test.c index b9ab29809e96..124ba40e32b1 100644 --- a/drivers/fpga/tests/fpga-bridge-test.c +++ b/drivers/fpga/tests/fpga-bridge-test.c @@ -170,4 +170,5 @@ static struct kunit_suite fpga_bridge_suite = { kunit_test_suite(fpga_bridge_suite); +MODULE_DESCRIPTION("KUnit test for the FPGA Bridge"); MODULE_LICENSE("GPL"); diff --git a/drivers/fpga/tests/fpga-mgr-test.c b/drivers/fpga/tests/fpga-mgr-test.c index 9cb37aefbac4..8748babb0504 100644 --- a/drivers/fpga/tests/fpga-mgr-test.c +++ b/drivers/fpga/tests/fpga-mgr-test.c @@ -330,4 +330,5 @@ static struct kunit_suite fpga_mgr_suite = { kunit_test_suite(fpga_mgr_suite); +MODULE_DESCRIPTION("KUnit test for the FPGA Manager"); MODULE_LICENSE("GPL"); diff --git a/drivers/fpga/tests/fpga-region-test.c b/drivers/fpga/tests/fpga-region-test.c index 6a108cafded8..020ceac48509 100644 --- a/drivers/fpga/tests/fpga-region-test.c +++ b/drivers/fpga/tests/fpga-region-test.c @@ -214,4 +214,5 @@ static struct kunit_suite fpga_region_suite = { kunit_test_suite(fpga_region_suite); +MODULE_DESCRIPTION("KUnit test for the FPGA Region"); MODULE_LICENSE("GPL"); diff --git a/include/linux/local_lock.h b/include/linux/local_lock.h index 1a0bc35839e3..16a2ee4f8310 100644 --- a/include/linux/local_lock.h +++ b/include/linux/local_lock.h @@ -52,44 +52,23 @@ __local_unlock_irqrestore(lock, flags) /** - * localtry_lock_init - Runtime initialize a lock instance - */ -#define localtry_lock_init(lock) __localtry_lock_init(lock) - -/** - * localtry_lock - Acquire a per CPU local lock - * @lock: The lock variable - */ -#define localtry_lock(lock) __localtry_lock(lock) - -/** - * localtry_lock_irq - Acquire a per CPU local lock and disable interrupts - * @lock: The lock variable - */ -#define localtry_lock_irq(lock) __localtry_lock_irq(lock) - -/** - * localtry_lock_irqsave - Acquire a per CPU local lock, save and disable - * interrupts - * @lock: The lock variable - * @flags: Storage for interrupt flags + * local_lock_init - Runtime initialize a lock instance */ -#define localtry_lock_irqsave(lock, flags) \ - __localtry_lock_irqsave(lock, flags) +#define local_trylock_init(lock) __local_trylock_init(lock) /** - * localtry_trylock - Try to acquire a per CPU local lock. + * local_trylock - Try to acquire a per CPU local lock * @lock: The lock variable * * The function can be used in any context such as NMI or HARDIRQ. Due to * locking constrains it will _always_ fail to acquire the lock in NMI or * HARDIRQ context on PREEMPT_RT. */ -#define localtry_trylock(lock) __localtry_trylock(lock) +#define local_trylock(lock) __local_trylock(lock) /** - * localtry_trylock_irqsave - Try to acquire a per CPU local lock, save and disable - * interrupts if acquired + * local_trylock_irqsave - Try to acquire a per CPU local lock, save and disable + * interrupts if acquired * @lock: The lock variable * @flags: Storage for interrupt flags * @@ -97,29 +76,8 @@ * locking constrains it will _always_ fail to acquire the lock in NMI or * HARDIRQ context on PREEMPT_RT. */ -#define localtry_trylock_irqsave(lock, flags) \ - __localtry_trylock_irqsave(lock, flags) - -/** - * local_unlock - Release a per CPU local lock - * @lock: The lock variable - */ -#define localtry_unlock(lock) __localtry_unlock(lock) - -/** - * local_unlock_irq - Release a per CPU local lock and enable interrupts - * @lock: The lock variable - */ -#define localtry_unlock_irq(lock) __localtry_unlock_irq(lock) - -/** - * localtry_unlock_irqrestore - Release a per CPU local lock and restore - * interrupt flags - * @lock: The lock variable - * @flags: Interrupt flags to restore - */ -#define localtry_unlock_irqrestore(lock, flags) \ - __localtry_unlock_irqrestore(lock, flags) +#define local_trylock_irqsave(lock, flags) \ + __local_trylock_irqsave(lock, flags) DEFINE_GUARD(local_lock, local_lock_t __percpu*, local_lock(_T), diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index 67bd13d142fa..bf2bf40d7b18 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -15,10 +15,11 @@ typedef struct { #endif } local_lock_t; +/* local_trylock() and local_trylock_irqsave() only work with local_trylock_t */ typedef struct { local_lock_t llock; - unsigned int acquired; -} localtry_lock_t; + u8 acquired; +} local_trylock_t; #ifdef CONFIG_DEBUG_LOCK_ALLOC # define LOCAL_LOCK_DEBUG_INIT(lockname) \ @@ -29,6 +30,9 @@ typedef struct { }, \ .owner = NULL, +# define LOCAL_TRYLOCK_DEBUG_INIT(lockname) \ + .llock = { LOCAL_LOCK_DEBUG_INIT((lockname).llock) }, + static inline void local_lock_acquire(local_lock_t *l) { lock_map_acquire(&l->dep_map); @@ -56,6 +60,7 @@ static inline void local_lock_debug_init(local_lock_t *l) } #else /* CONFIG_DEBUG_LOCK_ALLOC */ # define LOCAL_LOCK_DEBUG_INIT(lockname) +# define LOCAL_TRYLOCK_DEBUG_INIT(lockname) static inline void local_lock_acquire(local_lock_t *l) { } static inline void local_trylock_acquire(local_lock_t *l) { } static inline void local_lock_release(local_lock_t *l) { } @@ -63,7 +68,7 @@ static inline void local_lock_debug_init(local_lock_t *l) { } #endif /* !CONFIG_DEBUG_LOCK_ALLOC */ #define INIT_LOCAL_LOCK(lockname) { LOCAL_LOCK_DEBUG_INIT(lockname) } -#define INIT_LOCALTRY_LOCK(lockname) { .llock = { LOCAL_LOCK_DEBUG_INIT(lockname.llock) }} +#define INIT_LOCAL_TRYLOCK(lockname) { LOCAL_TRYLOCK_DEBUG_INIT(lockname) } #define __local_lock_init(lock) \ do { \ @@ -76,6 +81,8 @@ do { \ local_lock_debug_init(lock); \ } while (0) +#define __local_trylock_init(lock) __local_lock_init(lock.llock) + #define __spinlock_nested_bh_init(lock) \ do { \ static struct lock_class_key __key; \ @@ -87,149 +94,117 @@ do { \ local_lock_debug_init(lock); \ } while (0) +#define __local_lock_acquire(lock) \ + do { \ + local_trylock_t *tl; \ + local_lock_t *l; \ + \ + l = (local_lock_t *)this_cpu_ptr(lock); \ + tl = (local_trylock_t *)l; \ + _Generic((lock), \ + local_trylock_t *: ({ \ + lockdep_assert(tl->acquired == 0); \ + WRITE_ONCE(tl->acquired, 1); \ + }), \ + default:(void)0); \ + local_lock_acquire(l); \ + } while (0) + #define __local_lock(lock) \ do { \ preempt_disable(); \ - local_lock_acquire(this_cpu_ptr(lock)); \ + __local_lock_acquire(lock); \ } while (0) #define __local_lock_irq(lock) \ do { \ local_irq_disable(); \ - local_lock_acquire(this_cpu_ptr(lock)); \ + __local_lock_acquire(lock); \ } while (0) #define __local_lock_irqsave(lock, flags) \ do { \ local_irq_save(flags); \ - local_lock_acquire(this_cpu_ptr(lock)); \ - } while (0) - -#define __local_unlock(lock) \ - do { \ - local_lock_release(this_cpu_ptr(lock)); \ - preempt_enable(); \ + __local_lock_acquire(lock); \ } while (0) -#define __local_unlock_irq(lock) \ - do { \ - local_lock_release(this_cpu_ptr(lock)); \ - local_irq_enable(); \ - } while (0) - -#define __local_unlock_irqrestore(lock, flags) \ - do { \ - local_lock_release(this_cpu_ptr(lock)); \ - local_irq_restore(flags); \ - } while (0) - -#define __local_lock_nested_bh(lock) \ - do { \ - lockdep_assert_in_softirq(); \ - local_lock_acquire(this_cpu_ptr(lock)); \ - } while (0) - -#define __local_unlock_nested_bh(lock) \ - local_lock_release(this_cpu_ptr(lock)) - -/* localtry_lock_t variants */ - -#define __localtry_lock_init(lock) \ -do { \ - __local_lock_init(&(lock)->llock); \ - WRITE_ONCE((lock)->acquired, 0); \ -} while (0) - -#define __localtry_lock(lock) \ - do { \ - localtry_lock_t *lt; \ - preempt_disable(); \ - lt = this_cpu_ptr(lock); \ - local_lock_acquire(<->llock); \ - WRITE_ONCE(lt->acquired, 1); \ - } while (0) - -#define __localtry_lock_irq(lock) \ - do { \ - localtry_lock_t *lt; \ - local_irq_disable(); \ - lt = this_cpu_ptr(lock); \ - local_lock_acquire(<->llock); \ - WRITE_ONCE(lt->acquired, 1); \ - } while (0) - -#define __localtry_lock_irqsave(lock, flags) \ - do { \ - localtry_lock_t *lt; \ - local_irq_save(flags); \ - lt = this_cpu_ptr(lock); \ - local_lock_acquire(<->llock); \ - WRITE_ONCE(lt->acquired, 1); \ - } while (0) - -#define __localtry_trylock(lock) \ +#define __local_trylock(lock) \ ({ \ - localtry_lock_t *lt; \ - bool _ret; \ + local_trylock_t *tl; \ \ preempt_disable(); \ - lt = this_cpu_ptr(lock); \ - if (!READ_ONCE(lt->acquired)) { \ - WRITE_ONCE(lt->acquired, 1); \ - local_trylock_acquire(<->llock); \ - _ret = true; \ - } else { \ - _ret = false; \ + tl = this_cpu_ptr(lock); \ + if (READ_ONCE(tl->acquired)) { \ preempt_enable(); \ + tl = NULL; \ + } else { \ + WRITE_ONCE(tl->acquired, 1); \ + local_trylock_acquire( \ + (local_lock_t *)tl); \ } \ - _ret; \ + !!tl; \ }) -#define __localtry_trylock_irqsave(lock, flags) \ +#define __local_trylock_irqsave(lock, flags) \ ({ \ - localtry_lock_t *lt; \ - bool _ret; \ + local_trylock_t *tl; \ \ local_irq_save(flags); \ - lt = this_cpu_ptr(lock); \ - if (!READ_ONCE(lt->acquired)) { \ - WRITE_ONCE(lt->acquired, 1); \ - local_trylock_acquire(<->llock); \ - _ret = true; \ - } else { \ - _ret = false; \ + tl = this_cpu_ptr(lock); \ + if (READ_ONCE(tl->acquired)) { \ local_irq_restore(flags); \ + tl = NULL; \ + } else { \ + WRITE_ONCE(tl->acquired, 1); \ + local_trylock_acquire( \ + (local_lock_t *)tl); \ } \ - _ret; \ + !!tl; \ }) -#define __localtry_unlock(lock) \ +#define __local_lock_release(lock) \ + do { \ + local_trylock_t *tl; \ + local_lock_t *l; \ + \ + l = (local_lock_t *)this_cpu_ptr(lock); \ + tl = (local_trylock_t *)l; \ + local_lock_release(l); \ + _Generic((lock), \ + local_trylock_t *: ({ \ + lockdep_assert(tl->acquired == 1); \ + WRITE_ONCE(tl->acquired, 0); \ + }), \ + default:(void)0); \ + } while (0) + +#define __local_unlock(lock) \ do { \ - localtry_lock_t *lt; \ - lt = this_cpu_ptr(lock); \ - WRITE_ONCE(lt->acquired, 0); \ - local_lock_release(<->llock); \ + __local_lock_release(lock); \ preempt_enable(); \ } while (0) -#define __localtry_unlock_irq(lock) \ +#define __local_unlock_irq(lock) \ do { \ - localtry_lock_t *lt; \ - lt = this_cpu_ptr(lock); \ - WRITE_ONCE(lt->acquired, 0); \ - local_lock_release(<->llock); \ + __local_lock_release(lock); \ local_irq_enable(); \ } while (0) -#define __localtry_unlock_irqrestore(lock, flags) \ +#define __local_unlock_irqrestore(lock, flags) \ do { \ - localtry_lock_t *lt; \ - lt = this_cpu_ptr(lock); \ - WRITE_ONCE(lt->acquired, 0); \ - local_lock_release(<->llock); \ + __local_lock_release(lock); \ local_irq_restore(flags); \ } while (0) +#define __local_lock_nested_bh(lock) \ + do { \ + lockdep_assert_in_softirq(); \ + local_lock_acquire(this_cpu_ptr(lock)); \ + } while (0) + +#define __local_unlock_nested_bh(lock) \ + local_lock_release(this_cpu_ptr(lock)) + #else /* !CONFIG_PREEMPT_RT */ /* @@ -237,16 +212,18 @@ do { \ * critical section while staying preemptible. */ typedef spinlock_t local_lock_t; -typedef spinlock_t localtry_lock_t; +typedef spinlock_t local_trylock_t; #define INIT_LOCAL_LOCK(lockname) __LOCAL_SPIN_LOCK_UNLOCKED((lockname)) -#define INIT_LOCALTRY_LOCK(lockname) INIT_LOCAL_LOCK(lockname) +#define INIT_LOCAL_TRYLOCK(lockname) __LOCAL_SPIN_LOCK_UNLOCKED((lockname)) #define __local_lock_init(l) \ do { \ local_spin_lock_init((l)); \ } while (0) +#define __local_trylock_init(l) __local_lock_init(l) + #define __local_lock(__lock) \ do { \ migrate_disable(); \ @@ -283,17 +260,7 @@ do { \ spin_unlock(this_cpu_ptr((lock))); \ } while (0) -/* localtry_lock_t variants */ - -#define __localtry_lock_init(lock) __local_lock_init(lock) -#define __localtry_lock(lock) __local_lock(lock) -#define __localtry_lock_irq(lock) __local_lock(lock) -#define __localtry_lock_irqsave(lock, flags) __local_lock_irqsave(lock, flags) -#define __localtry_unlock(lock) __local_unlock(lock) -#define __localtry_unlock_irq(lock) __local_unlock(lock) -#define __localtry_unlock_irqrestore(lock, flags) __local_unlock_irqrestore(lock, flags) - -#define __localtry_trylock(lock) \ +#define __local_trylock(lock) \ ({ \ int __locked; \ \ @@ -308,11 +275,11 @@ do { \ __locked; \ }) -#define __localtry_trylock_irqsave(lock, flags) \ +#define __local_trylock_irqsave(lock, flags) \ ({ \ typecheck(unsigned long, flags); \ flags = 0; \ - __localtry_trylock(lock); \ + __local_trylock(lock); \ }) #endif /* CONFIG_PREEMPT_RT */ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index e2b705c14945..b50447ef1c92 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1511,8 +1511,9 @@ static inline void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, /* * track_pfn_copy is called when a VM_PFNMAP VMA is about to get the page - * tables copied during copy_page_range(). On success, stores the pfn to be - * passed to untrack_pfn_copy(). + * tables copied during copy_page_range(). Will store the pfn to be + * passed to untrack_pfn_copy() only if there is something to be untracked. + * Callers should initialize the pfn to 0. */ static inline int track_pfn_copy(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, unsigned long *pfn) @@ -1522,7 +1523,9 @@ static inline int track_pfn_copy(struct vm_area_struct *dst_vma, /* * untrack_pfn_copy is called when a VM_PFNMAP VMA failed to copy during - * copy_page_range(), but after track_pfn_copy() was already called. + * copy_page_range(), but after track_pfn_copy() was already called. Can + * be called even if track_pfn_copy() did not actually track anything: + * handled internally. */ static inline void untrack_pfn_copy(struct vm_area_struct *dst_vma, unsigned long pfn) diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index 1d893e313614..25ecc1334b67 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -422,11 +422,20 @@ static int vm_module_tags_populate(void) unsigned long old_shadow_end = ALIGN(phys_end, MODULE_ALIGN); unsigned long new_shadow_end = ALIGN(new_end, MODULE_ALIGN); unsigned long more_pages; - unsigned long nr; + unsigned long nr = 0; more_pages = ALIGN(new_end - phys_end, PAGE_SIZE) >> PAGE_SHIFT; - nr = alloc_pages_bulk_node(GFP_KERNEL | __GFP_NOWARN, - NUMA_NO_NODE, more_pages, next_page); + while (nr < more_pages) { + unsigned long allocated; + + allocated = alloc_pages_bulk_node(GFP_KERNEL | __GFP_NOWARN, + NUMA_NO_NODE, more_pages - nr, next_page + nr); + + if (!allocated) + break; + nr += allocated; + } + if (nr < more_pages || vmap_pages_range(phys_end, phys_end + (nr << PAGE_SHIFT), PAGE_KERNEL, next_page, PAGE_SHIFT) < 0) { diff --git a/lib/asn1_decoder.c b/lib/asn1_decoder.c index 13da529e2e72..5738ae286b41 100644 --- a/lib/asn1_decoder.c +++ b/lib/asn1_decoder.c @@ -518,4 +518,5 @@ error: } EXPORT_SYMBOL_GPL(asn1_ber_decoder); +MODULE_DESCRIPTION("Decoder for ASN.1 BER/DER/CER encoded bytestream"); MODULE_LICENSE("GPL"); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 8c7fdb7d8c8f..bc9391e55d57 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1191,7 +1191,7 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i, return -ENOMEM; p = *pages; for (int k = 0; k < n; k++) { - struct folio *folio = page_folio(page); + struct folio *folio = page_folio(page + k); p[k] = page + k; if (!folio_test_slab(folio)) folio_get(folio); diff --git a/lib/tests/slub_kunit.c b/lib/tests/slub_kunit.c index d47c472b0520..848b682a2d70 100644 --- a/lib/tests/slub_kunit.c +++ b/lib/tests/slub_kunit.c @@ -325,4 +325,5 @@ static struct kunit_suite test_suite = { }; kunit_test_suite(test_suite); +MODULE_DESCRIPTION("Kunit tests for slub allocator"); MODULE_LICENSE("GPL"); diff --git a/lib/ucs2_string.c b/lib/ucs2_string.c index 9308bcfb2ad5..dfb4f2358cab 100644 --- a/lib/ucs2_string.c +++ b/lib/ucs2_string.c @@ -165,4 +165,5 @@ ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, unsigned long maxlength) } EXPORT_SYMBOL(ucs2_as_utf8); +MODULE_DESCRIPTION("UCS2 string handling"); MODULE_LICENSE("GPL v2"); diff --git a/lib/zlib_inflate/inflate_syms.c b/lib/zlib_inflate/inflate_syms.c index 9720114c0672..b8996d90e8bc 100644 --- a/lib/zlib_inflate/inflate_syms.c +++ b/lib/zlib_inflate/inflate_syms.c @@ -18,4 +18,5 @@ EXPORT_SYMBOL(zlib_inflateEnd); EXPORT_SYMBOL(zlib_inflateReset); EXPORT_SYMBOL(zlib_inflateIncomp); EXPORT_SYMBOL(zlib_inflate_blob); +MODULE_DESCRIPTION("Data decompression using the deflation algorithm"); MODULE_LICENSE("GPL"); @@ -35,7 +35,7 @@ struct cma cma_areas[MAX_CMA_AREAS]; unsigned int cma_area_count; -static int __init __cma_declare_contiguous_nid(phys_addr_t base, +static int __init __cma_declare_contiguous_nid(phys_addr_t *basep, phys_addr_t size, phys_addr_t limit, phys_addr_t alignment, unsigned int order_per_bit, bool fixed, const char *name, struct cma **res_cma, @@ -370,7 +370,7 @@ int __init cma_declare_contiguous_multi(phys_addr_t total_size, phys_addr_t align, unsigned int order_per_bit, const char *name, struct cma **res_cma, int nid) { - phys_addr_t start, end; + phys_addr_t start = 0, end; phys_addr_t size, sizesum, sizeleft; struct cma_init_memrange *mrp, *mlp, *failed; struct cma_memrange *cmrp; @@ -384,7 +384,7 @@ int __init cma_declare_contiguous_multi(phys_addr_t total_size, /* * First, try it the normal way, producing just one range. */ - ret = __cma_declare_contiguous_nid(0, total_size, 0, align, + ret = __cma_declare_contiguous_nid(&start, total_size, 0, align, order_per_bit, false, name, res_cma, nid); if (ret != -ENOMEM) goto out; @@ -580,7 +580,7 @@ int __init cma_declare_contiguous_nid(phys_addr_t base, { int ret; - ret = __cma_declare_contiguous_nid(base, size, limit, alignment, + ret = __cma_declare_contiguous_nid(&base, size, limit, alignment, order_per_bit, fixed, name, res_cma, nid); if (ret != 0) pr_err("Failed to reserve %ld MiB\n", @@ -592,14 +592,14 @@ int __init cma_declare_contiguous_nid(phys_addr_t base, return ret; } -static int __init __cma_declare_contiguous_nid(phys_addr_t base, +static int __init __cma_declare_contiguous_nid(phys_addr_t *basep, phys_addr_t size, phys_addr_t limit, phys_addr_t alignment, unsigned int order_per_bit, bool fixed, const char *name, struct cma **res_cma, int nid) { phys_addr_t memblock_end = memblock_end_of_DRAM(); - phys_addr_t highmem_start; + phys_addr_t highmem_start, base = *basep; int ret; /* @@ -722,12 +722,15 @@ static int __init __cma_declare_contiguous_nid(phys_addr_t base, } ret = cma_init_reserved_mem(base, size, order_per_bit, name, res_cma); - if (ret) + if (ret) { memblock_phys_free(base, size); + return ret; + } (*res_cma)->nid = nid; + *basep = base; - return ret; + return 0; } static void cma_debug_show_areas(struct cma *cma) diff --git a/mm/compaction.c b/mm/compaction.c index 139f00c0308a..ca71fd3c3181 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -981,13 +981,13 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, } if (PageHuge(page)) { + const unsigned int order = compound_order(page); /* * skip hugetlbfs if we are not compacting for pages * bigger than its order. THPs and other compound pages * are handled below. */ if (!cc->alloc_contig) { - const unsigned int order = compound_order(page); if (order <= MAX_PAGE_ORDER) { low_pfn += (1UL << order) - 1; @@ -1011,8 +1011,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, /* Do not report -EBUSY down the chain */ if (ret == -EBUSY) ret = 0; - low_pfn += compound_nr(page) - 1; - nr_scanned += compound_nr(page) - 1; + low_pfn += (1UL << order) - 1; + nr_scanned += (1UL << order) - 1; goto isolate_fail; } diff --git a/mm/filemap.c b/mm/filemap.c index b5e784f34d98..7b90cbeb4a1a 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2244,6 +2244,7 @@ unsigned filemap_get_folios_contig(struct address_space *mapping, *start = folio->index + nr; goto out; } + xas_advance(&xas, folio_next_index(folio) - 1); continue; put_folio: folio_put(folio); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 39f92aad7bd1..e3e6ac991b9c 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2271,7 +2271,7 @@ static struct folio *alloc_surplus_hugetlb_folio(struct hstate *h, * as surplus_pages, otherwise it might confuse * persistent_huge_pages() momentarily. */ - __prep_account_new_huge_page(h, nid); + __prep_account_new_huge_page(h, folio_nid(folio)); /* * We could have raced with the pool size change. @@ -3825,6 +3825,7 @@ found: static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, nodemask_t *nodes_allowed) { + unsigned long persistent_free_count; unsigned long min_count; unsigned long allocated; struct folio *folio; @@ -3959,8 +3960,24 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, * though, we'll note that we're not allowed to exceed surplus * and won't grow the pool anywhere else. Not until one of the * sysctls are changed, or the surplus pages go out of use. + * + * min_count is the expected number of persistent pages, we + * shouldn't calculate min_count by using + * resv_huge_pages + persistent_huge_pages() - free_huge_pages, + * because there may exist free surplus huge pages, and this will + * lead to subtracting twice. Free surplus huge pages come from HVO + * failing to restore vmemmap, see comments in the callers of + * hugetlb_vmemmap_restore_folio(). Thus, we should calculate + * persistent free count first. */ - min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages; + persistent_free_count = h->free_huge_pages; + if (h->free_huge_pages > persistent_huge_pages(h)) { + if (h->free_huge_pages > h->surplus_huge_pages) + persistent_free_count -= h->surplus_huge_pages; + else + persistent_free_count = 0; + } + min_count = h->resv_huge_pages + persistent_huge_pages(h) - persistent_free_count; min_count = max(count, min_count); try_to_free_low(h, min_count, nodes_allowed); @@ -4630,7 +4647,7 @@ static void __init hugetlb_sysfs_init(void) err = hugetlb_sysfs_add_hstate(h, hugepages_kobj, hstate_kobjs, &hstate_attr_group); if (err) - pr_err("HugeTLB: Unable to add hstate %s", h->name); + pr_err("HugeTLB: Unable to add hstate %s\n", h->name); } #ifdef CONFIG_NUMA diff --git a/mm/kasan/kasan_test_c.c b/mm/kasan/kasan_test_c.c index 3ea317837c2d..f24e3bef72a4 100644 --- a/mm/kasan/kasan_test_c.c +++ b/mm/kasan/kasan_test_c.c @@ -2127,4 +2127,5 @@ static struct kunit_suite kasan_kunit_test_suite = { kunit_test_suite(kasan_kunit_test_suite); +MODULE_DESCRIPTION("KUnit tests for checking KASAN bug-detection capabilities"); MODULE_LICENSE("GPL"); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 421740f1bcdc..c96c1f2b9cf5 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1759,7 +1759,7 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) } struct memcg_stock_pcp { - localtry_lock_t stock_lock; + local_trylock_t stock_lock; struct mem_cgroup *cached; /* this never be root cgroup */ unsigned int nr_pages; @@ -1774,7 +1774,7 @@ struct memcg_stock_pcp { #define FLUSHING_CACHED_CHARGE 0 }; static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock) = { - .stock_lock = INIT_LOCALTRY_LOCK(stock_lock), + .stock_lock = INIT_LOCAL_TRYLOCK(stock_lock), }; static DEFINE_MUTEX(percpu_charge_mutex); @@ -1805,11 +1805,10 @@ static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages, if (nr_pages > MEMCG_CHARGE_BATCH) return ret; - if (!localtry_trylock_irqsave(&memcg_stock.stock_lock, flags)) { - if (!gfpflags_allow_spinning(gfp_mask)) - return ret; - localtry_lock_irqsave(&memcg_stock.stock_lock, flags); - } + if (gfpflags_allow_spinning(gfp_mask)) + local_lock_irqsave(&memcg_stock.stock_lock, flags); + else if (!local_trylock_irqsave(&memcg_stock.stock_lock, flags)) + return ret; stock = this_cpu_ptr(&memcg_stock); stock_pages = READ_ONCE(stock->nr_pages); @@ -1818,7 +1817,7 @@ static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages, ret = true; } - localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags); + local_unlock_irqrestore(&memcg_stock.stock_lock, flags); return ret; } @@ -1857,14 +1856,14 @@ static void drain_local_stock(struct work_struct *dummy) * drain_stock races is that we always operate on local CPU stock * here with IRQ disabled */ - localtry_lock_irqsave(&memcg_stock.stock_lock, flags); + local_lock_irqsave(&memcg_stock.stock_lock, flags); stock = this_cpu_ptr(&memcg_stock); old = drain_obj_stock(stock); drain_stock(stock); clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags); - localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags); + local_unlock_irqrestore(&memcg_stock.stock_lock, flags); obj_cgroup_put(old); } @@ -1894,7 +1893,7 @@ static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages) { unsigned long flags; - if (!localtry_trylock_irqsave(&memcg_stock.stock_lock, flags)) { + if (!local_trylock_irqsave(&memcg_stock.stock_lock, flags)) { /* * In case of unlikely failure to lock percpu stock_lock * uncharge memcg directly. @@ -1907,7 +1906,7 @@ static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages) return; } __refill_stock(memcg, nr_pages); - localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags); + local_unlock_irqrestore(&memcg_stock.stock_lock, flags); } /* @@ -1964,9 +1963,9 @@ static int memcg_hotplug_cpu_dead(unsigned int cpu) stock = &per_cpu(memcg_stock, cpu); /* drain_obj_stock requires stock_lock */ - localtry_lock_irqsave(&memcg_stock.stock_lock, flags); + local_lock_irqsave(&memcg_stock.stock_lock, flags); old = drain_obj_stock(stock); - localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags); + local_unlock_irqrestore(&memcg_stock.stock_lock, flags); drain_stock(stock); obj_cgroup_put(old); @@ -2787,7 +2786,7 @@ static void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat, unsigned long flags; int *bytes; - localtry_lock_irqsave(&memcg_stock.stock_lock, flags); + local_lock_irqsave(&memcg_stock.stock_lock, flags); stock = this_cpu_ptr(&memcg_stock); /* @@ -2836,7 +2835,7 @@ static void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat, if (nr) __mod_objcg_mlstate(objcg, pgdat, idx, nr); - localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags); + local_unlock_irqrestore(&memcg_stock.stock_lock, flags); obj_cgroup_put(old); } @@ -2846,7 +2845,7 @@ static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes) unsigned long flags; bool ret = false; - localtry_lock_irqsave(&memcg_stock.stock_lock, flags); + local_lock_irqsave(&memcg_stock.stock_lock, flags); stock = this_cpu_ptr(&memcg_stock); if (objcg == READ_ONCE(stock->cached_objcg) && stock->nr_bytes >= nr_bytes) { @@ -2854,7 +2853,7 @@ static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes) ret = true; } - localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags); + local_unlock_irqrestore(&memcg_stock.stock_lock, flags); return ret; } @@ -2946,7 +2945,7 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes, unsigned long flags; unsigned int nr_pages = 0; - localtry_lock_irqsave(&memcg_stock.stock_lock, flags); + local_lock_irqsave(&memcg_stock.stock_lock, flags); stock = this_cpu_ptr(&memcg_stock); if (READ_ONCE(stock->cached_objcg) != objcg) { /* reset if necessary */ @@ -2960,7 +2959,7 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes, stock->nr_bytes &= (PAGE_SIZE - 1); } - localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags); + local_unlock_irqrestore(&memcg_stock.stock_lock, flags); obj_cgroup_put(old); if (nr_pages) diff --git a/mm/memory.c b/mm/memory.c index 2d8c265fc7d6..44481fe7c629 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1361,7 +1361,7 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; struct mmu_notifier_range range; - unsigned long next, pfn; + unsigned long next, pfn = 0; bool is_cow; int ret; @@ -2938,11 +2938,11 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, if (fn) { do { if (create || !pte_none(ptep_get(pte))) { - err = fn(pte++, addr, data); + err = fn(pte, addr, data); if (err) break; } - } while (addr += PAGE_SIZE, addr != end); + } while (pte++, addr += PAGE_SIZE, addr != end); } *mask |= PGTBL_PTE_MODIFIED; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index fd6b865cb1ab..1715e34b91af 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1400,11 +1400,12 @@ static void free_one_page(struct zone *zone, struct page *page, struct llist_head *llhead; unsigned long flags; - if (!spin_trylock_irqsave(&zone->lock, flags)) { - if (unlikely(fpi_flags & FPI_TRYLOCK)) { + if (unlikely(fpi_flags & FPI_TRYLOCK)) { + if (!spin_trylock_irqsave(&zone->lock, flags)) { add_page_to_zone_llist(zone, page, order); return; } + } else { spin_lock_irqsave(&zone->lock, flags); } @@ -2182,23 +2183,15 @@ try_to_claim_block(struct zone *zone, struct page *page, } /* - * Try finding a free buddy page on the fallback list. - * - * This will attempt to claim a whole pageblock for the requested type - * to ensure grouping of such requests in the future. - * - * If a whole block cannot be claimed, steal an individual page, regressing to - * __rmqueue_smallest() logic to at least break up as little contiguity as - * possible. + * Try to allocate from some fallback migratetype by claiming the entire block, + * i.e. converting it to the allocation's start migratetype. * * The use of signed ints for order and current_order is a deliberate * deviation from the rest of this file, to make the for loop * condition simpler. - * - * Return the stolen page, or NULL if none can be found. */ static __always_inline struct page * -__rmqueue_fallback(struct zone *zone, int order, int start_migratetype, +__rmqueue_claim(struct zone *zone, int order, int start_migratetype, unsigned int alloc_flags) { struct free_area *area; @@ -2236,14 +2229,29 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype, page = try_to_claim_block(zone, page, current_order, order, start_migratetype, fallback_mt, alloc_flags); - if (page) - goto got_one; + if (page) { + trace_mm_page_alloc_extfrag(page, order, current_order, + start_migratetype, fallback_mt); + return page; + } } - if (alloc_flags & ALLOC_NOFRAGMENT) - return NULL; + return NULL; +} + +/* + * Try to steal a single page from some fallback migratetype. Leave the rest of + * the block as its current migratetype, potentially causing fragmentation. + */ +static __always_inline struct page * +__rmqueue_steal(struct zone *zone, int order, int start_migratetype) +{ + struct free_area *area; + int current_order; + struct page *page; + int fallback_mt; + bool claim_block; - /* No luck claiming pageblock. Find the smallest fallback page */ for (current_order = order; current_order < NR_PAGE_ORDERS; current_order++) { area = &(zone->free_area[current_order]); fallback_mt = find_suitable_fallback(area, current_order, @@ -2253,25 +2261,28 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype, page = get_page_from_free_area(area, fallback_mt); page_del_and_expand(zone, page, order, current_order, fallback_mt); - goto got_one; + trace_mm_page_alloc_extfrag(page, order, current_order, + start_migratetype, fallback_mt); + return page; } return NULL; - -got_one: - trace_mm_page_alloc_extfrag(page, order, current_order, - start_migratetype, fallback_mt); - - return page; } +enum rmqueue_mode { + RMQUEUE_NORMAL, + RMQUEUE_CMA, + RMQUEUE_CLAIM, + RMQUEUE_STEAL, +}; + /* * Do the hard work of removing an element from the buddy allocator. * Call me with the zone->lock already held. */ static __always_inline struct page * __rmqueue(struct zone *zone, unsigned int order, int migratetype, - unsigned int alloc_flags) + unsigned int alloc_flags, enum rmqueue_mode *mode) { struct page *page; @@ -2290,16 +2301,48 @@ __rmqueue(struct zone *zone, unsigned int order, int migratetype, } } - page = __rmqueue_smallest(zone, order, migratetype); - if (unlikely(!page)) { - if (alloc_flags & ALLOC_CMA) + /* + * First try the freelists of the requested migratetype, then try + * fallbacks modes with increasing levels of fragmentation risk. + * + * The fallback logic is expensive and rmqueue_bulk() calls in + * a loop with the zone->lock held, meaning the freelists are + * not subject to any outside changes. Remember in *mode where + * we found pay dirt, to save us the search on the next call. + */ + switch (*mode) { + case RMQUEUE_NORMAL: + page = __rmqueue_smallest(zone, order, migratetype); + if (page) + return page; + fallthrough; + case RMQUEUE_CMA: + if (alloc_flags & ALLOC_CMA) { page = __rmqueue_cma_fallback(zone, order); - - if (!page) - page = __rmqueue_fallback(zone, order, migratetype, - alloc_flags); + if (page) { + *mode = RMQUEUE_CMA; + return page; + } + } + fallthrough; + case RMQUEUE_CLAIM: + page = __rmqueue_claim(zone, order, migratetype, alloc_flags); + if (page) { + /* Replenished preferred freelist, back to normal mode. */ + *mode = RMQUEUE_NORMAL; + return page; + } + fallthrough; + case RMQUEUE_STEAL: + if (!(alloc_flags & ALLOC_NOFRAGMENT)) { + page = __rmqueue_steal(zone, order, migratetype); + if (page) { + *mode = RMQUEUE_STEAL; + return page; + } + } } - return page; + return NULL; } /* @@ -2311,17 +2354,19 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, unsigned long count, struct list_head *list, int migratetype, unsigned int alloc_flags) { + enum rmqueue_mode rmqm = RMQUEUE_NORMAL; unsigned long flags; int i; - if (!spin_trylock_irqsave(&zone->lock, flags)) { - if (unlikely(alloc_flags & ALLOC_TRYLOCK)) + if (unlikely(alloc_flags & ALLOC_TRYLOCK)) { + if (!spin_trylock_irqsave(&zone->lock, flags)) return 0; + } else { spin_lock_irqsave(&zone->lock, flags); } for (i = 0; i < count; ++i) { struct page *page = __rmqueue(zone, order, migratetype, - alloc_flags); + alloc_flags, &rmqm); if (unlikely(page == NULL)) break; @@ -2937,15 +2982,18 @@ struct page *rmqueue_buddy(struct zone *preferred_zone, struct zone *zone, do { page = NULL; - if (!spin_trylock_irqsave(&zone->lock, flags)) { - if (unlikely(alloc_flags & ALLOC_TRYLOCK)) + if (unlikely(alloc_flags & ALLOC_TRYLOCK)) { + if (!spin_trylock_irqsave(&zone->lock, flags)) return NULL; + } else { spin_lock_irqsave(&zone->lock, flags); } if (alloc_flags & ALLOC_HIGHATOMIC) page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC); if (!page) { - page = __rmqueue(zone, order, migratetype, alloc_flags); + enum rmqueue_mode rmqm = RMQUEUE_NORMAL; + + page = __rmqueue(zone, order, migratetype, alloc_flags, &rmqm); /* * If the allocation fails, allow OOM handling and diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index fbf2cf62ab9f..7d5d709cc838 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -1902,6 +1902,14 @@ struct vm_area_struct *userfaultfd_clear_vma(struct vma_iterator *vmi, unsigned long end) { struct vm_area_struct *ret; + bool give_up_on_oom = false; + + /* + * If we are modifying only and not splitting, just give up on the merge + * if OOM prevents us from merging successfully. + */ + if (start == vma->vm_start && end == vma->vm_end) + give_up_on_oom = true; /* Reset ptes for the whole vma range if wr-protected */ if (userfaultfd_wp(vma)) @@ -1909,7 +1917,7 @@ struct vm_area_struct *userfaultfd_clear_vma(struct vma_iterator *vmi, ret = vma_modify_flags_uffd(vmi, prev, vma, start, end, vma->vm_flags & ~__VM_UFFD_FLAGS, - NULL_VM_UFFD_CTX); + NULL_VM_UFFD_CTX, give_up_on_oom); /* * In the vma_merge() successful mprotect-like case 8: @@ -1960,7 +1968,8 @@ int userfaultfd_register_range(struct userfaultfd_ctx *ctx, new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags; vma = vma_modify_flags_uffd(&vmi, prev, vma, start, vma_end, new_flags, - (struct vm_userfaultfd_ctx){ctx}); + (struct vm_userfaultfd_ctx){ctx}, + /* give_up_on_oom = */false); if (IS_ERR(vma)) return PTR_ERR(vma); @@ -666,6 +666,9 @@ static void vmg_adjust_set_range(struct vma_merge_struct *vmg) /* * Actually perform the VMA merge operation. * + * IMPORTANT: We guarantee that, should vmg->give_up_on_oom is set, to not + * modify any VMAs or cause inconsistent state should an OOM condition arise. + * * Returns 0 on success, or an error value on failure. */ static int commit_merge(struct vma_merge_struct *vmg) @@ -685,6 +688,12 @@ static int commit_merge(struct vma_merge_struct *vmg) init_multi_vma_prep(&vp, vma, vmg); + /* + * If vmg->give_up_on_oom is set, we're safe, because we don't actually + * manipulate any VMAs until we succeed at preallocation. + * + * Past this point, we will not return an error. + */ if (vma_iter_prealloc(vmg->vmi, vma)) return -ENOMEM; @@ -915,7 +924,13 @@ static __must_check struct vm_area_struct *vma_merge_existing_range( if (anon_dup) unlink_anon_vmas(anon_dup); - vmg->state = VMA_MERGE_ERROR_NOMEM; + /* + * We've cleaned up any cloned anon_vma's, no VMAs have been + * modified, no harm no foul if the user requests that we not + * report this and just give up, leaving the VMAs unmerged. + */ + if (!vmg->give_up_on_oom) + vmg->state = VMA_MERGE_ERROR_NOMEM; return NULL; } @@ -926,7 +941,15 @@ static __must_check struct vm_area_struct *vma_merge_existing_range( abort: vma_iter_set(vmg->vmi, start); vma_iter_load(vmg->vmi); - vmg->state = VMA_MERGE_ERROR_NOMEM; + + /* + * This means we have failed to clone anon_vma's correctly, but no + * actual changes to VMAs have occurred, so no harm no foul - if the + * user doesn't want this reported and instead just wants to give up on + * the merge, allow it. + */ + if (!vmg->give_up_on_oom) + vmg->state = VMA_MERGE_ERROR_NOMEM; return NULL; } @@ -1068,6 +1091,10 @@ int vma_expand(struct vma_merge_struct *vmg) /* This should already have been checked by this point. */ VM_WARN_ON_VMG(!can_merge_remove_vma(next), vmg); vma_start_write(next); + /* + * In this case we don't report OOM, so vmg->give_up_on_mm is + * safe. + */ ret = dup_anon_vma(middle, next, &anon_dup); if (ret) return ret; @@ -1090,9 +1117,15 @@ int vma_expand(struct vma_merge_struct *vmg) return 0; nomem: - vmg->state = VMA_MERGE_ERROR_NOMEM; if (anon_dup) unlink_anon_vmas(anon_dup); + /* + * If the user requests that we just give upon OOM, we are safe to do so + * here, as commit merge provides this contract to us. Nothing has been + * changed - no harm no foul, just don't report it. + */ + if (!vmg->give_up_on_oom) + vmg->state = VMA_MERGE_ERROR_NOMEM; return -ENOMEM; } @@ -1534,6 +1567,13 @@ static struct vm_area_struct *vma_modify(struct vma_merge_struct *vmg) if (vmg_nomem(vmg)) return ERR_PTR(-ENOMEM); + /* + * Split can fail for reasons other than OOM, so if the user requests + * this it's probably a mistake. + */ + VM_WARN_ON(vmg->give_up_on_oom && + (vma->vm_start != start || vma->vm_end != end)); + /* Split any preceding portion of the VMA. */ if (vma->vm_start < start) { int err = split_vma(vmg->vmi, vma, start, 1); @@ -1602,12 +1642,15 @@ struct vm_area_struct struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long new_flags, - struct vm_userfaultfd_ctx new_ctx) + struct vm_userfaultfd_ctx new_ctx, + bool give_up_on_oom) { VMG_VMA_STATE(vmg, vmi, prev, vma, start, end); vmg.flags = new_flags; vmg.uffd_ctx = new_ctx; + if (give_up_on_oom) + vmg.give_up_on_oom = true; return vma_modify(&vmg); } @@ -114,6 +114,12 @@ struct vma_merge_struct { */ bool just_expand :1; + /* + * If a merge is possible, but an OOM error occurs, give up and don't + * execute the merge, returning NULL. + */ + bool give_up_on_oom :1; + /* Internal flags set during merge process: */ /* @@ -255,7 +261,8 @@ __must_check struct vm_area_struct struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long new_flags, - struct vm_userfaultfd_ctx new_ctx); + struct vm_userfaultfd_ctx new_ctx, + bool give_up_on_oom); __must_check struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg); diff --git a/samples/livepatch/livepatch-callbacks-busymod.c b/samples/livepatch/livepatch-callbacks-busymod.c index 69105596e72e..fadc2a85cb35 100644 --- a/samples/livepatch/livepatch-callbacks-busymod.c +++ b/samples/livepatch/livepatch-callbacks-busymod.c @@ -56,4 +56,5 @@ static void livepatch_callbacks_mod_exit(void) module_init(livepatch_callbacks_mod_init); module_exit(livepatch_callbacks_mod_exit); +MODULE_DESCRIPTION("Live patching demo for (un)patching callbacks, support module"); MODULE_LICENSE("GPL"); diff --git a/samples/livepatch/livepatch-callbacks-demo.c b/samples/livepatch/livepatch-callbacks-demo.c index 11c3f4357812..9e69d9caed25 100644 --- a/samples/livepatch/livepatch-callbacks-demo.c +++ b/samples/livepatch/livepatch-callbacks-demo.c @@ -192,5 +192,6 @@ static void livepatch_callbacks_demo_exit(void) module_init(livepatch_callbacks_demo_init); module_exit(livepatch_callbacks_demo_exit); +MODULE_DESCRIPTION("Live patching demo for (un)patching callbacks"); MODULE_LICENSE("GPL"); MODULE_INFO(livepatch, "Y"); diff --git a/samples/livepatch/livepatch-callbacks-mod.c b/samples/livepatch/livepatch-callbacks-mod.c index 2a074f422a51..d1851b471ad9 100644 --- a/samples/livepatch/livepatch-callbacks-mod.c +++ b/samples/livepatch/livepatch-callbacks-mod.c @@ -38,4 +38,5 @@ static void livepatch_callbacks_mod_exit(void) module_init(livepatch_callbacks_mod_init); module_exit(livepatch_callbacks_mod_exit); +MODULE_DESCRIPTION("Live patching demo for (un)patching callbacks, support module"); MODULE_LICENSE("GPL"); diff --git a/samples/livepatch/livepatch-sample.c b/samples/livepatch/livepatch-sample.c index cd76d7ebe598..5263a2f31c48 100644 --- a/samples/livepatch/livepatch-sample.c +++ b/samples/livepatch/livepatch-sample.c @@ -66,5 +66,6 @@ static void livepatch_exit(void) module_init(livepatch_init); module_exit(livepatch_exit); +MODULE_DESCRIPTION("Kernel Live Patching Sample Module"); MODULE_LICENSE("GPL"); MODULE_INFO(livepatch, "Y"); diff --git a/samples/livepatch/livepatch-shadow-fix1.c b/samples/livepatch/livepatch-shadow-fix1.c index f3f153895d6c..cbf68ca40097 100644 --- a/samples/livepatch/livepatch-shadow-fix1.c +++ b/samples/livepatch/livepatch-shadow-fix1.c @@ -168,5 +168,6 @@ static void livepatch_shadow_fix1_exit(void) module_init(livepatch_shadow_fix1_init); module_exit(livepatch_shadow_fix1_exit); +MODULE_DESCRIPTION("Live patching demo for shadow variables"); MODULE_LICENSE("GPL"); MODULE_INFO(livepatch, "Y"); diff --git a/samples/livepatch/livepatch-shadow-fix2.c b/samples/livepatch/livepatch-shadow-fix2.c index 361046a4f10c..b99122cb221f 100644 --- a/samples/livepatch/livepatch-shadow-fix2.c +++ b/samples/livepatch/livepatch-shadow-fix2.c @@ -128,5 +128,6 @@ static void livepatch_shadow_fix2_exit(void) module_init(livepatch_shadow_fix2_init); module_exit(livepatch_shadow_fix2_exit); +MODULE_DESCRIPTION("Live patching demo for shadow variables"); MODULE_LICENSE("GPL"); MODULE_INFO(livepatch, "Y"); diff --git a/tools/testing/selftests/mincore/mincore_selftest.c b/tools/testing/selftests/mincore/mincore_selftest.c index efabfcbe0b49..17ed3e9917ca 100644 --- a/tools/testing/selftests/mincore/mincore_selftest.c +++ b/tools/testing/selftests/mincore/mincore_selftest.c @@ -283,8 +283,7 @@ out_free: /* * Test mincore() behavior on a page backed by a tmpfs file. This test - * performs the same steps as the previous one. However, we don't expect - * any readahead in this case. + * performs the same steps as the previous one. */ TEST(check_tmpfs_mmap) { @@ -295,7 +294,6 @@ TEST(check_tmpfs_mmap) int page_size; int fd; int i; - int ra_pages = 0; page_size = sysconf(_SC_PAGESIZE); vec_size = FILE_SIZE / page_size; @@ -338,8 +336,7 @@ TEST(check_tmpfs_mmap) } /* - * Touch a page in the middle of the mapping. We expect only - * that page to be fetched into memory. + * Touch a page in the middle of the mapping. */ addr[FILE_SIZE / 2] = 1; retval = mincore(addr, FILE_SIZE, vec); @@ -348,15 +345,6 @@ TEST(check_tmpfs_mmap) TH_LOG("Page not found in memory after use"); } - i = FILE_SIZE / 2 / page_size + 1; - while (i < vec_size && vec[i]) { - ra_pages++; - i++; - } - ASSERT_EQ(ra_pages, 0) { - TH_LOG("Read-ahead pages found in memory"); - } - munmap(addr, FILE_SIZE); close(fd); free(vec); diff --git a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh index 67df7b47087f..e1fe16bcbbe8 100755 --- a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh +++ b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh @@ -29,7 +29,7 @@ fi if [[ $cgroup2 ]]; then cgroup_path=$(mount -t cgroup2 | head -1 | awk '{print $3}') if [[ -z "$cgroup_path" ]]; then - cgroup_path=/dev/cgroup/memory + cgroup_path=$(mktemp -d) mount -t cgroup2 none $cgroup_path do_umount=1 fi @@ -37,7 +37,7 @@ if [[ $cgroup2 ]]; then else cgroup_path=$(mount -t cgroup | grep ",hugetlb" | awk '{print $3}') if [[ -z "$cgroup_path" ]]; then - cgroup_path=/dev/cgroup/memory + cgroup_path=$(mktemp -d) mount -t cgroup memory,hugetlb $cgroup_path do_umount=1 fi diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index f0cb14ea8608..b6cfe0a4b7df 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -293,7 +293,7 @@ static void do_test_vmsplice_in_parent(char *mem, size_t size, .iov_base = mem, .iov_len = size, }; - ssize_t cur, total, transferred; + ssize_t cur, total, transferred = 0; struct comm_pipes comm_pipes; char *old, *new; int ret, fds[2]; diff --git a/tools/testing/selftests/mm/hugetlb_reparenting_test.sh b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh index 11f9bbe7dc22..0b0d4ba1af27 100755 --- a/tools/testing/selftests/mm/hugetlb_reparenting_test.sh +++ b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh @@ -23,7 +23,7 @@ fi if [[ $cgroup2 ]]; then CGROUP_ROOT=$(mount -t cgroup2 | head -1 | awk '{print $3}') if [[ -z "$CGROUP_ROOT" ]]; then - CGROUP_ROOT=/dev/cgroup/memory + CGROUP_ROOT=$(mktemp -d) mount -t cgroup2 none $CGROUP_ROOT do_umount=1 fi diff --git a/tools/testing/shared/linux.c b/tools/testing/shared/linux.c index 66dbb362385f..0f97fb0d19e1 100644 --- a/tools/testing/shared/linux.c +++ b/tools/testing/shared/linux.c @@ -150,7 +150,7 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp) void kmem_cache_free_bulk(struct kmem_cache *cachep, size_t size, void **list) { if (kmalloc_verbose) - pr_debug("Bulk free %p[0-%lu]\n", list, size - 1); + pr_debug("Bulk free %p[0-%zu]\n", list, size - 1); pthread_mutex_lock(&cachep->lock); for (int i = 0; i < size; i++) @@ -168,7 +168,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size, size_t i; if (kmalloc_verbose) - pr_debug("Bulk alloc %lu\n", size); + pr_debug("Bulk alloc %zu\n", size); pthread_mutex_lock(&cachep->lock); if (cachep->nr_objs >= size) { diff --git a/tools/testing/shared/linux/cleanup.h b/tools/testing/shared/linux/cleanup.h new file mode 100644 index 000000000000..ea3081426ee9 --- /dev/null +++ b/tools/testing/shared/linux/cleanup.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include "../../../../include/linux/cleanup.h" |