diff options
35 files changed, 221 insertions, 124 deletions
diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst index b72d07d70239..525296121d89 100644 --- a/Documentation/dev-tools/kasan.rst +++ b/Documentation/dev-tools/kasan.rst @@ -41,6 +41,9 @@ smaller binary while the latter is 1.1 - 2 times faster. Both KASAN modes work with both SLUB and SLAB memory allocators. For better bug detection and nicer reporting, enable CONFIG_STACKTRACE. +To augment reports with last allocation and freeing stack of the physical page, +it is recommended to enable also CONFIG_PAGE_OWNER and boot with page_owner=on. + To disable instrumentation for specific files or directories, add a line similar to the following to the respective kernel Makefile: diff --git a/MAINTAINERS b/MAINTAINERS index a69e6db80c79..0154674cbad3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12312,12 +12312,15 @@ F: arch/parisc/ F: Documentation/parisc/ F: drivers/parisc/ F: drivers/char/agp/parisc-agp.c +F: drivers/input/misc/hp_sdc_rtc.c F: drivers/input/serio/gscps2.c +F: drivers/input/serio/hp_sdc* F: drivers/parport/parport_gsc.* F: drivers/tty/serial/8250/8250_gsc.c F: drivers/video/fbdev/sti* F: drivers/video/console/sti* F: drivers/video/logo/logo_parisc* +F: include/linux/hp_sdc.h PARMAN M: Jiri Pirko <[email protected]> @@ -13361,7 +13364,7 @@ S: Maintained F: drivers/scsi/qla1280.[ch] QLOGIC QLA2XXX FC-SCSI DRIVER S: Supported F: Documentation/scsi/LICENSE.qla2xxx diff --git a/arch/parisc/include/asm/cache.h b/arch/parisc/include/asm/cache.h index 73ca89a47f49..e5de3f897633 100644 --- a/arch/parisc/include/asm/cache.h +++ b/arch/parisc/include/asm/cache.h @@ -22,7 +22,7 @@ #define ARCH_DMA_MINALIGN L1_CACHE_BYTES -#define __read_mostly __attribute__((__section__(".data..read_mostly"))) +#define __read_mostly __section(.data..read_mostly) void parisc_cache_init(void); /* initializes cache-flushing */ void disable_sr_hashing_asm(int); /* low level support for above */ diff --git a/arch/parisc/include/asm/ldcw.h b/arch/parisc/include/asm/ldcw.h index 3eb4bfc1fb36..e080143e79a3 100644 --- a/arch/parisc/include/asm/ldcw.h +++ b/arch/parisc/include/asm/ldcw.h @@ -52,7 +52,7 @@ }) #ifdef CONFIG_SMP -# define __lock_aligned __attribute__((__section__(".data..lock_aligned"))) +# define __lock_aligned __section(.data..lock_aligned) #endif #endif /* __PARISC_LDCW_H */ diff --git a/arch/parisc/mm/ioremap.c b/arch/parisc/mm/ioremap.c index 92a9b5f12f98..f29f682352f0 100644 --- a/arch/parisc/mm/ioremap.c +++ b/arch/parisc/mm/ioremap.c @@ -3,7 +3,7 @@ * arch/parisc/mm/ioremap.c * * (C) Copyright 1995 1996 Linus Torvalds - * (C) Copyright 2001-2006 Helge Deller <[email protected]> + * (C) Copyright 2001-2019 Helge Deller <[email protected]> * (C) Copyright 2005 Kyle McMartin <[email protected]> */ @@ -84,7 +84,7 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l addr = (void __iomem *) area->addr; if (ioremap_page_range((unsigned long)addr, (unsigned long)addr + size, phys_addr, pgprot)) { - vfree(addr); + vunmap(addr); return NULL; } @@ -92,9 +92,11 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l } EXPORT_SYMBOL(__ioremap); -void iounmap(const volatile void __iomem *addr) +void iounmap(const volatile void __iomem *io_addr) { - if (addr > high_memory) - return vfree((void *) (PAGE_MASK & (unsigned long __force) addr)); + unsigned long addr = (unsigned long)io_addr & PAGE_MASK; + + if (is_vmalloc_addr((void *)addr)) + vunmap((void *)addr); } EXPORT_SYMBOL(iounmap); diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index fbc1aecf0f94..eb24cb1afc11 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -29,7 +29,6 @@ config SPARC select RTC_DRV_M48T59 select RTC_SYSTOHC select HAVE_ARCH_JUMP_LABEL if SPARC64 - select HAVE_FAST_GUP if SPARC64 select GENERIC_IRQ_SHOW select ARCH_WANT_IPC_PARSE_VERSION select GENERIC_PCI_IOMAP diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index 35ed56b9c34f..1e21fc3e9851 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -408,7 +408,7 @@ static void __init save_mem_devices(const struct dmi_header *dm, void *v) bytes = ~0ull; else if (size & 0x8000) bytes = (u64)(size & 0x7fff) << 10; - else if (size != 0x7fff) + else if (size != 0x7fff || dm->length < 0x20) bytes = (u64)size << 20; else bytes = (u64)get_unaligned((u32 *)&d[0x1C]) << 20; diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c index ed50502cc65a..de8e4e347249 100644 --- a/drivers/parisc/sba_iommu.c +++ b/drivers/parisc/sba_iommu.c @@ -678,14 +678,6 @@ static int sba_dma_supported( struct device *dev, u64 mask) return(0); } - /* Documentation/DMA-API-HOWTO.txt tells drivers to try 64-bit - * first, then fall back to 32-bit if that fails. - * We are just "encouraging" 32-bit DMA masks here since we can - * never allow IOMMU bypass unless we add special support for ZX1. - */ - if (mask > ~0U) - return 0; - ioc = GET_IOC(dev); if (!ioc) return 0; diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c index 296bbc3c4606..cf63916814cc 100644 --- a/drivers/s390/scsi/zfcp_fsf.c +++ b/drivers/s390/scsi/zfcp_fsf.c @@ -27,6 +27,11 @@ struct kmem_cache *zfcp_fsf_qtcb_cache; +static bool ber_stop = true; +module_param(ber_stop, bool, 0600); +MODULE_PARM_DESC(ber_stop, + "Shuts down FCP devices for FCP channels that report a bit-error count in excess of its threshold (default on)"); + static void zfcp_fsf_request_timeout_handler(struct timer_list *t) { struct zfcp_fsf_req *fsf_req = from_timer(fsf_req, t, timer); @@ -236,10 +241,15 @@ static void zfcp_fsf_status_read_handler(struct zfcp_fsf_req *req) case FSF_STATUS_READ_SENSE_DATA_AVAIL: break; case FSF_STATUS_READ_BIT_ERROR_THRESHOLD: - dev_warn(&adapter->ccw_device->dev, - "The error threshold for checksum statistics " - "has been exceeded\n"); zfcp_dbf_hba_bit_err("fssrh_3", req); + if (ber_stop) { + dev_warn(&adapter->ccw_device->dev, + "All paths over this FCP device are disused because of excessive bit errors\n"); + zfcp_erp_adapter_shutdown(adapter, 0, "fssrh_b"); + } else { + dev_warn(&adapter->ccw_device->dev, + "The error threshold for checksum statistics has been exceeded\n"); + } break; case FSF_STATUS_READ_LINK_DOWN: zfcp_fsf_status_read_link_down(req); diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 4c26630c1c3e..009fd5a33fcd 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -2837,8 +2837,6 @@ qla2x00_status_cont_entry(struct rsp_que *rsp, sts_cont_entry_t *pkt) if (sense_len == 0) { rsp->status_srb = NULL; sp->done(sp, cp->result); - } else { - WARN_ON_ONCE(true); } } diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 1c470e31ae81..ae2fa170f6ad 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -967,6 +967,7 @@ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses, ses->data_direction = scmd->sc_data_direction; ses->sdb = scmd->sdb; ses->result = scmd->result; + ses->resid_len = scmd->req.resid_len; ses->underflow = scmd->underflow; ses->prot_op = scmd->prot_op; ses->eh_eflags = scmd->eh_eflags; @@ -977,6 +978,7 @@ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses, memset(scmd->cmnd, 0, BLK_MAX_CDB); memset(&scmd->sdb, 0, sizeof(scmd->sdb)); scmd->result = 0; + scmd->req.resid_len = 0; if (sense_bytes) { scmd->sdb.length = min_t(unsigned, SCSI_SENSE_BUFFERSIZE, @@ -1029,6 +1031,7 @@ void scsi_eh_restore_cmnd(struct scsi_cmnd* scmd, struct scsi_eh_save *ses) scmd->sc_data_direction = ses->data_direction; scmd->sdb = ses->sdb; scmd->result = ses->result; + scmd->req.resid_len = ses->resid_len; scmd->underflow = ses->underflow; scmd->prot_op = ses->prot_op; scmd->eh_eflags = ses->eh_eflags; diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 50928bc266eb..03163ac5fe95 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1654,7 +1654,8 @@ static int sd_sync_cache(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr) /* we need to evaluate the error return */ if (scsi_sense_valid(sshdr) && (sshdr->asc == 0x3a || /* medium not present */ - sshdr->asc == 0x20)) /* invalid command */ + sshdr->asc == 0x20 || /* invalid command */ + (sshdr->asc == 0x74 && sshdr->ascq == 0x71))) /* drive is password locked */ /* this is no error here */ return 0; diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c index 7804869c6a31..056308008288 100644 --- a/drivers/vhost/test.c +++ b/drivers/vhost/test.c @@ -161,6 +161,7 @@ static int vhost_test_release(struct inode *inode, struct file *f) vhost_test_stop(n, &private); vhost_test_flush(n); + vhost_dev_stop(&n->dev); vhost_dev_cleanup(&n->dev); /* We do an extra flush before freeing memory, * since jobs can re-queue themselves. */ @@ -237,6 +238,7 @@ static long vhost_test_reset_owner(struct vhost_test *n) } vhost_test_stop(n, &priv); vhost_test_flush(n); + vhost_dev_stop(&n->dev); vhost_dev_reset_owner(&n->dev, umem); done: mutex_unlock(&n->dev.mutex); diff --git a/fs/direct-io.c b/fs/direct-io.c index ae196784f487..9329ced91f1d 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -241,9 +241,8 @@ void dio_warn_stale_pagecache(struct file *filp) } } -/** +/* * dio_complete() - called when all DIO BIO I/O has been completed - * @offset: the byte offset in the file of the completed operation * * This drops i_dio_count, lets interested parties know that a DIO operation * has completed, and calculates the resulting return code for the operation. diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index e88421d9a48d..8461a6322039 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -905,7 +905,7 @@ restart: * cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs * @bdi_id: target bdi id * @memcg_id: target memcg css id - * @nr_pages: number of pages to write, 0 for best-effort dirty flushing + * @nr: number of pages to write, 0 for best-effort dirty flushing * @reason: reason why some writeback work initiated * @done: target wb_completion * diff --git a/fs/libfs.c b/fs/libfs.c index 540611b99b9a..1463b038ffc4 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -473,8 +473,7 @@ EXPORT_SYMBOL(simple_write_begin); /** * simple_write_end - .write_end helper for non-block-device FSes - * @available: See .write_end of address_space_operations - * @file: " + * @file: See .write_end of address_space_operations * @mapping: " * @pos: " * @len: " diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 90528f12bdfa..29fc933df3bf 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -326,10 +326,11 @@ static inline int bitmap_equal(const unsigned long *src1, } /** - * bitmap_or_equal - Check whether the or of two bitnaps is equal to a third + * bitmap_or_equal - Check whether the or of two bitmaps is equal to a third * @src1: Pointer to bitmap 1 * @src2: Pointer to bitmap 2 will be or'ed with bitmap 1 * @src3: Pointer to bitmap 3. Compare to the result of *@src1 | *@src2 + * @nbits: number of bits in each of these bitmaps * * Returns: True if (*@src1 | *@src2) == *@src3, false otherwise */ diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index 682fd465df06..cfce186f0c4e 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -18,7 +18,7 @@ struct page_ext_operations { enum page_ext_flags { PAGE_EXT_OWNER, - PAGE_EXT_OWNER_ACTIVE, + PAGE_EXT_OWNER_ALLOCATED, #if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT) PAGE_EXT_YOUNG, PAGE_EXT_IDLE, @@ -36,6 +36,7 @@ struct page_ext { unsigned long flags; }; +extern unsigned long page_ext_size; extern void pgdat_page_ext_init(struct pglist_data *pgdat); #ifdef CONFIG_SPARSEMEM @@ -52,6 +53,13 @@ static inline void page_ext_init(void) struct page_ext *lookup_page_ext(const struct page *page); +static inline struct page_ext *page_ext_next(struct page_ext *curr) +{ + void *next = curr; + next += page_ext_size; + return next; +} + #else /* !CONFIG_PAGE_EXTENSION */ struct page_ext; diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 5921599b6dc4..86eecbd98e84 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -230,8 +230,8 @@ static inline int xa_err(void *entry) * This structure is used either directly or via the XA_LIMIT() macro * to communicate the range of IDs that are valid for allocation. * Two common ranges are predefined for you: - * * xa_limit_32b - [0 - UINT_MAX] - * * xa_limit_31b - [0 - INT_MAX] + * * xa_limit_32b - [0 - UINT_MAX] + * * xa_limit_31b - [0 - INT_MAX] */ struct xa_limit { u32 max; diff --git a/include/scsi/scsi_eh.h b/include/scsi/scsi_eh.h index 3810b340551c..6bd5ed695a5e 100644 --- a/include/scsi/scsi_eh.h +++ b/include/scsi/scsi_eh.h @@ -32,6 +32,7 @@ extern int scsi_ioctl_reset(struct scsi_device *, int __user *); struct scsi_eh_save { /* saved state */ int result; + unsigned int resid_len; int eh_eflags; enum dma_data_direction data_direction; unsigned underflow; diff --git a/kernel/kthread.c b/kernel/kthread.c index 621467c33fef..b262f47046ca 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -866,9 +866,9 @@ void kthread_delayed_work_timer_fn(struct timer_list *t) } EXPORT_SYMBOL(kthread_delayed_work_timer_fn); -void __kthread_queue_delayed_work(struct kthread_worker *worker, - struct kthread_delayed_work *dwork, - unsigned long delay) +static void __kthread_queue_delayed_work(struct kthread_worker *worker, + struct kthread_delayed_work *dwork, + unsigned long delay) { struct timer_list *timer = &dwork->timer; struct kthread_work *work = &dwork->work; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 00fcea236eba..b6f2f35d0bcf 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -163,7 +163,7 @@ static unsigned long hung_task_timeout_max = (LONG_MAX/HZ); #ifdef CONFIG_SPARC #endif -#ifdef __hppa__ +#ifdef CONFIG_PARISC extern int pwrsw_enabled; #endif @@ -620,7 +620,7 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, #endif -#ifdef __hppa__ +#ifdef CONFIG_PARISC { .procname = "soft-power", .data = &pwrsw_enabled, diff --git a/lib/generic-radix-tree.c b/lib/generic-radix-tree.c index ae25e2fa2187..f25eb111c051 100644 --- a/lib/generic-radix-tree.c +++ b/lib/generic-radix-tree.c @@ -2,6 +2,7 @@ #include <linux/export.h> #include <linux/generic-radix-tree.h> #include <linux/gfp.h> +#include <linux/kmemleak.h> #define GENRADIX_ARY (PAGE_SIZE / sizeof(struct genradix_node *)) #define GENRADIX_ARY_SHIFT ilog2(GENRADIX_ARY) @@ -75,6 +76,27 @@ void *__genradix_ptr(struct __genradix *radix, size_t offset) } EXPORT_SYMBOL(__genradix_ptr); +static inline struct genradix_node *genradix_alloc_node(gfp_t gfp_mask) +{ + struct genradix_node *node; + + node = (struct genradix_node *)__get_free_page(gfp_mask|__GFP_ZERO); + + /* + * We're using pages (not slab allocations) directly for kernel data + * structures, so we need to explicitly inform kmemleak of them in order + * to avoid false positive memory leak reports. + */ + kmemleak_alloc(node, PAGE_SIZE, 1, gfp_mask); + return node; +} + +static inline void genradix_free_node(struct genradix_node *node) +{ + kmemleak_free(node); + free_page((unsigned long)node); +} + /* * Returns pointer to the specified byte @offset within @radix, allocating it if * necessary - newly allocated slots are always zeroed out: @@ -97,8 +119,7 @@ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset, break; if (!new_node) { - new_node = (void *) - __get_free_page(gfp_mask|__GFP_ZERO); + new_node = genradix_alloc_node(gfp_mask); if (!new_node) return NULL; } @@ -121,8 +142,7 @@ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset, n = READ_ONCE(*p); if (!n) { if (!new_node) { - new_node = (void *) - __get_free_page(gfp_mask|__GFP_ZERO); + new_node = genradix_alloc_node(gfp_mask); if (!new_node) return NULL; } @@ -133,7 +153,7 @@ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset, } if (new_node) - free_page((unsigned long) new_node); + genradix_free_node(new_node); return &n->data[offset]; } @@ -191,7 +211,7 @@ static void genradix_free_recurse(struct genradix_node *n, unsigned level) genradix_free_recurse(n->children[i], level - 1); } - free_page((unsigned long) n); + genradix_free_node(n); } int __genradix_prealloc(struct __genradix *radix, size_t size, diff --git a/lib/test_meminit.c b/lib/test_meminit.c index 9729f271d150..9742e5cb853a 100644 --- a/lib/test_meminit.c +++ b/lib/test_meminit.c @@ -297,6 +297,32 @@ out: return 1; } +static int __init do_kmem_cache_size_bulk(int size, int *total_failures) +{ + struct kmem_cache *c; + int i, iter, maxiter = 1024; + int num, bytes; + bool fail = false; + void *objects[10]; + + c = kmem_cache_create("test_cache", size, size, 0, NULL); + for (iter = 0; (iter < maxiter) && !fail; iter++) { + num = kmem_cache_alloc_bulk(c, GFP_KERNEL, ARRAY_SIZE(objects), + objects); + for (i = 0; i < num; i++) { + bytes = count_nonzero_bytes(objects[i], size); + if (bytes) + fail = true; + fill_with_garbage(objects[i], size); + } + + if (num) + kmem_cache_free_bulk(c, num, objects); + } + *total_failures += fail; + return 1; +} + /* * Test kmem_cache allocation by creating caches of different sizes, with and * without constructors, with and without SLAB_TYPESAFE_BY_RCU. @@ -318,6 +344,7 @@ static int __init test_kmemcache(int *total_failures) num_tests += do_kmem_cache_size(size, ctor, rcu, zero, &failures); } + num_tests += do_kmem_cache_size_bulk(size, &failures); } REPORT_FAILURES_IN_FN(); *total_failures += failures; diff --git a/mm/compaction.c b/mm/compaction.c index ce08b39d85d4..672d3c78c6ab 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -270,14 +270,15 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source, /* Ensure the start of the pageblock or zone is online and valid */ block_pfn = pageblock_start_pfn(pfn); - block_page = pfn_to_online_page(max(block_pfn, zone->zone_start_pfn)); + block_pfn = max(block_pfn, zone->zone_start_pfn); + block_page = pfn_to_online_page(block_pfn); if (block_page) { page = block_page; pfn = block_pfn; } /* Ensure the end of the pageblock or zone is online and valid */ - block_pfn += pageblock_nr_pages; + block_pfn = pageblock_end_pfn(pfn) - 1; block_pfn = min(block_pfn, zone_end_pfn(zone) - 1); end_page = pfn_to_online_page(block_pfn); if (!end_page) @@ -303,7 +304,7 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source, page += (1 << PAGE_ALLOC_COSTLY_ORDER); pfn += (1 << PAGE_ALLOC_COSTLY_ORDER); - } while (page < end_page); + } while (page <= end_page); return false; } diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 03a8d84badad..244607663363 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -527,6 +527,16 @@ static struct kmemleak_object *find_and_get_object(unsigned long ptr, int alias) } /* + * Remove an object from the object_tree_root and object_list. Must be called + * with the kmemleak_lock held _if_ kmemleak is still enabled. + */ +static void __remove_object(struct kmemleak_object *object) +{ + rb_erase(&object->rb_node, &object_tree_root); + list_del_rcu(&object->object_list); +} + +/* * Look up an object in the object search tree and remove it from both * object_tree_root and object_list. The returned object's use_count should be * at least 1, as initially set by create_object(). @@ -538,10 +548,8 @@ static struct kmemleak_object *find_and_remove_object(unsigned long ptr, int ali write_lock_irqsave(&kmemleak_lock, flags); object = lookup_object(ptr, alias); - if (object) { - rb_erase(&object->rb_node, &object_tree_root); - list_del_rcu(&object->object_list); - } + if (object) + __remove_object(object); write_unlock_irqrestore(&kmemleak_lock, flags); return object; @@ -1834,12 +1842,16 @@ static const struct file_operations kmemleak_fops = { static void __kmemleak_do_cleanup(void) { - struct kmemleak_object *object; + struct kmemleak_object *object, *tmp; - rcu_read_lock(); - list_for_each_entry_rcu(object, &object_list, object_list) - delete_object_full(object->pointer); - rcu_read_unlock(); + /* + * Kmemleak has already been disabled, no need for RCU list traversal + * or kmemleak_lock held. + */ + list_for_each_entry_safe(object, tmp, &object_list, object_list) { + __remove_object(object); + __delete_object(object); + } } /* diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 7ef849da8278..0ae72b6acee7 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -199,7 +199,6 @@ struct to_kill { struct task_struct *tsk; unsigned long addr; short size_shift; - char addr_valid; }; /* @@ -324,22 +323,27 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, } } tk->addr = page_address_in_vma(p, vma); - tk->addr_valid = 1; if (is_zone_device_page(p)) tk->size_shift = dev_pagemap_mapping_shift(p, vma); else tk->size_shift = compound_order(compound_head(p)) + PAGE_SHIFT; /* - * In theory we don't have to kill when the page was - * munmaped. But it could be also a mremap. Since that's - * likely very rare kill anyways just out of paranoia, but use - * a SIGKILL because the error is not contained anymore. + * Send SIGKILL if "tk->addr == -EFAULT". Also, as + * "tk->size_shift" is always non-zero for !is_zone_device_page(), + * so "tk->size_shift == 0" effectively checks no mapping on + * ZONE_DEVICE. Indeed, when a devdax page is mmapped N times + * to a process' address space, it's possible not all N VMAs + * contain mappings for the page, but at least one VMA does. + * Only deliver SIGBUS with payload derived from the VMA that + * has a mapping for the page. */ - if (tk->addr == -EFAULT || tk->size_shift == 0) { + if (tk->addr == -EFAULT) { pr_info("Memory failure: Unable to find user space address %lx in %s\n", page_to_pfn(p), tsk->comm); - tk->addr_valid = 0; + } else if (tk->size_shift == 0) { + kfree(tk); + return; } get_task_struct(tsk); tk->tsk = tsk; @@ -366,7 +370,7 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail, * make sure the process doesn't catch the * signal and then access the memory. Just kill it. */ - if (fail || tk->addr_valid == 0) { + if (fail || tk->addr == -EFAULT) { pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n", pfn, tk->tsk->comm, tk->tsk->pid); do_send_sig_info(SIGKILL, SEND_SIG_PRIV, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c0b2e0306720..ecc3dbad606b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4473,12 +4473,14 @@ retry_cpuset: if (page) goto got_pg; - if (order >= pageblock_order && (gfp_mask & __GFP_IO)) { + if (order >= pageblock_order && (gfp_mask & __GFP_IO) && + !(gfp_mask & __GFP_RETRY_MAYFAIL)) { /* * If allocating entire pageblock(s) and compaction * failed because all zones are below low watermarks * or is prohibited because it recently failed at this - * order, fail immediately. + * order, fail immediately unless the allocator has + * requested compaction and reclaim retry. * * Reclaim is * - potentially very expensive because zones are far diff --git a/mm/page_ext.c b/mm/page_ext.c index 5f5769c7db3b..4ade843ff588 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -67,8 +67,9 @@ static struct page_ext_operations *page_ext_ops[] = { #endif }; +unsigned long page_ext_size = sizeof(struct page_ext); + static unsigned long total_usage; -static unsigned long extra_mem; static bool __init invoke_need_callbacks(void) { @@ -78,9 +79,8 @@ static bool __init invoke_need_callbacks(void) for (i = 0; i < entries; i++) { if (page_ext_ops[i]->need && page_ext_ops[i]->need()) { - page_ext_ops[i]->offset = sizeof(struct page_ext) + - extra_mem; - extra_mem += page_ext_ops[i]->size; + page_ext_ops[i]->offset = page_ext_size; + page_ext_size += page_ext_ops[i]->size; need = true; } } @@ -99,14 +99,9 @@ static void __init invoke_init_callbacks(void) } } -static unsigned long get_entry_size(void) -{ - return sizeof(struct page_ext) + extra_mem; -} - static inline struct page_ext *get_entry(void *base, unsigned long index) { - return base + get_entry_size() * index; + return base + page_ext_size * index; } #if !defined(CONFIG_SPARSEMEM) @@ -156,7 +151,7 @@ static int __init alloc_node_page_ext(int nid) !IS_ALIGNED(node_end_pfn(nid), MAX_ORDER_NR_PAGES)) nr_pages += MAX_ORDER_NR_PAGES; - table_size = get_entry_size() * nr_pages; + table_size = page_ext_size * nr_pages; base = memblock_alloc_try_nid( table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), @@ -234,7 +229,7 @@ static int __meminit init_section_page_ext(unsigned long pfn, int nid) if (section->page_ext) return 0; - table_size = get_entry_size() * PAGES_PER_SECTION; + table_size = page_ext_size * PAGES_PER_SECTION; base = alloc_page_ext(table_size, nid); /* @@ -254,7 +249,7 @@ static int __meminit init_section_page_ext(unsigned long pfn, int nid) * we need to apply a mask. */ pfn &= PAGE_SECTION_MASK; - section->page_ext = (void *)base - get_entry_size() * pfn; + section->page_ext = (void *)base - page_ext_size * pfn; total_usage += table_size; return 0; } @@ -267,7 +262,7 @@ static void free_page_ext(void *addr) struct page *page = virt_to_page(addr); size_t table_size; - table_size = get_entry_size() * PAGES_PER_SECTION; + table_size = page_ext_size * PAGES_PER_SECTION; BUG_ON(PageReserved(page)); kmemleak_free(addr); diff --git a/mm/page_owner.c b/mm/page_owner.c index dee931184788..e327bcd0380e 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -24,12 +24,10 @@ struct page_owner { short last_migrate_reason; gfp_t gfp_mask; depot_stack_handle_t handle; -#ifdef CONFIG_DEBUG_PAGEALLOC depot_stack_handle_t free_handle; -#endif }; -static bool page_owner_disabled = true; +static bool page_owner_enabled = false; DEFINE_STATIC_KEY_FALSE(page_owner_inited); static depot_stack_handle_t dummy_handle; @@ -44,7 +42,7 @@ static int __init early_page_owner_param(char *buf) return -EINVAL; if (strcmp(buf, "on") == 0) - page_owner_disabled = false; + page_owner_enabled = true; return 0; } @@ -52,10 +50,7 @@ early_param("page_owner", early_page_owner_param); static bool need_page_owner(void) { - if (page_owner_disabled) - return false; - - return true; + return page_owner_enabled; } static __always_inline depot_stack_handle_t create_dummy_stack(void) @@ -84,7 +79,7 @@ static noinline void register_early_stack(void) static void init_page_owner(void) { - if (page_owner_disabled) + if (!page_owner_enabled) return; register_dummy_stack(); @@ -148,25 +143,19 @@ void __reset_page_owner(struct page *page, unsigned int order) { int i; struct page_ext *page_ext; -#ifdef CONFIG_DEBUG_PAGEALLOC depot_stack_handle_t handle = 0; struct page_owner *page_owner; - if (debug_pagealloc_enabled()) - handle = save_stack(GFP_NOWAIT | __GFP_NOWARN); -#endif + handle = save_stack(GFP_NOWAIT | __GFP_NOWARN); + page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + return; for (i = 0; i < (1 << order); i++) { - page_ext = lookup_page_ext(page + i); - if (unlikely(!page_ext)) - continue; - __clear_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags); -#ifdef CONFIG_DEBUG_PAGEALLOC - if (debug_pagealloc_enabled()) { - page_owner = get_page_owner(page_ext); - page_owner->free_handle = handle; - } -#endif + __clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); + page_owner = get_page_owner(page_ext); + page_owner->free_handle = handle; + page_ext = page_ext_next(page_ext); } } @@ -184,9 +173,9 @@ static inline void __set_page_owner_handle(struct page *page, page_owner->gfp_mask = gfp_mask; page_owner->last_migrate_reason = -1; __set_bit(PAGE_EXT_OWNER, &page_ext->flags); - __set_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags); + __set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); - page_ext = lookup_page_ext(page + i); + page_ext = page_ext_next(page_ext); } } @@ -224,12 +213,10 @@ void __split_page_owner(struct page *page, unsigned int order) if (unlikely(!page_ext)) return; - page_owner = get_page_owner(page_ext); - page_owner->order = 0; - for (i = 1; i < (1 << order); i++) { - page_ext = lookup_page_ext(page + i); + for (i = 0; i < (1 << order); i++) { page_owner = get_page_owner(page_ext); page_owner->order = 0; + page_ext = page_ext_next(page_ext); } } @@ -260,7 +247,7 @@ void __copy_page_owner(struct page *oldpage, struct page *newpage) * the new page, which will be freed. */ __set_bit(PAGE_EXT_OWNER, &new_ext->flags); - __set_bit(PAGE_EXT_OWNER_ACTIVE, &new_ext->flags); + __set_bit(PAGE_EXT_OWNER_ALLOCATED, &new_ext->flags); } void pagetypeinfo_showmixedcount_print(struct seq_file *m, @@ -320,7 +307,7 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m, if (unlikely(!page_ext)) continue; - if (!test_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags)) + if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) continue; page_owner = get_page_owner(page_ext); @@ -435,7 +422,7 @@ void __dump_page_owner(struct page *page) return; } - if (test_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags)) + if (test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) pr_alert("page_owner tracks the page as allocated\n"); else pr_alert("page_owner tracks the page as freed\n"); @@ -451,7 +438,6 @@ void __dump_page_owner(struct page *page) stack_trace_print(entries, nr_entries, 0); } -#ifdef CONFIG_DEBUG_PAGEALLOC handle = READ_ONCE(page_owner->free_handle); if (!handle) { pr_alert("page_owner free stack trace missing\n"); @@ -460,7 +446,6 @@ void __dump_page_owner(struct page *page) pr_alert("page last free stack trace:\n"); stack_trace_print(entries, nr_entries, 0); } -#endif if (page_owner->last_migrate_reason != -1) pr_alert("page has been migrated, last migrate reason: %s\n", @@ -527,7 +512,7 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos) * Although we do have the info about past allocation of free * pages, it's not relevant for current memory usage. */ - if (!test_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags)) + if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) continue; page_owner = get_page_owner(page_ext); diff --git a/mm/slab.c b/mm/slab.c index 9df370558e5d..66e5d8032bae 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -4206,9 +4206,12 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, /** * __ksize -- Uninstrumented ksize. + * @objp: pointer to the object * * Unlike ksize(), __ksize() is uninstrumented, and does not provide the same * safety checks as ksize() with KASAN instrumentation enabled. + * + * Return: size of the actual memory used by @objp in bytes */ size_t __ksize(const void *objp) { diff --git a/mm/slub.c b/mm/slub.c index 3d63ae320d31..b25c807a111f 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2672,6 +2672,17 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, } /* + * If the object has been wiped upon free, make sure it's fully initialized by + * zeroing out freelist pointer. + */ +static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s, + void *obj) +{ + if (unlikely(slab_want_init_on_free(s)) && obj) + memset((void *)((char *)obj + s->offset), 0, sizeof(void *)); +} + +/* * Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc) * have the fastpath folded into their functions. So no function call * overhead for requests that can be satisfied on the fastpath. @@ -2759,12 +2770,8 @@ redo: prefetch_freepointer(s, next_object); stat(s, ALLOC_FASTPATH); } - /* - * If the object has been wiped upon free, make sure it's fully - * initialized by zeroing out freelist pointer. - */ - if (unlikely(slab_want_init_on_free(s)) && object) - memset(object + s->offset, 0, sizeof(void *)); + + maybe_wipe_obj_freeptr(s, object); if (unlikely(slab_want_init_on_alloc(gfpflags, s)) && object) memset(object, 0, s->object_size); @@ -3178,10 +3185,13 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, goto error; c = this_cpu_ptr(s->cpu_slab); + maybe_wipe_obj_freeptr(s, p[i]); + continue; /* goto for-loop */ } c->freelist = get_freepointer(s, object); p[i] = object; + maybe_wipe_obj_freeptr(s, p[i]); } c->tid = next_tid(c->tid); local_irq_enable(); @@ -4846,7 +4856,17 @@ static ssize_t show_slab_objects(struct kmem_cache *s, } } - get_online_mems(); + /* + * It is impossible to take "mem_hotplug_lock" here with "kernfs_mutex" + * already held which will conflict with an existing lock order: + * + * mem_hotplug_lock->slab_mutex->kernfs_mutex + * + * We don't really need mem_hotplug_lock (to hold off + * slab_mem_going_offline_callback) here because slab's memory hot + * unplug code doesn't destroy the kmem_cache->node[] data. + */ + #ifdef CONFIG_SLUB_DEBUG if (flags & SO_ALL) { struct kmem_cache_node *n; @@ -4887,7 +4907,6 @@ static ssize_t show_slab_objects(struct kmem_cache *s, x += sprintf(buf + x, " N%d=%lu", node, nodes[node]); #endif - put_online_mems(); kfree(nodes); return x + sprintf(buf + x, "\n"); } diff --git a/tools/virtio/crypto/hash.h b/tools/virtio/crypto/hash.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/virtio/crypto/hash.h diff --git a/tools/virtio/linux/dma-mapping.h b/tools/virtio/linux/dma-mapping.h index f91aeb5fe571..8f41cd6bd5c0 100644 --- a/tools/virtio/linux/dma-mapping.h +++ b/tools/virtio/linux/dma-mapping.h @@ -29,4 +29,6 @@ enum dma_data_direction { #define dma_unmap_single(...) do { } while (0) #define dma_unmap_page(...) do { } while (0) +#define dma_max_mapping_size(...) SIZE_MAX + #endif diff --git a/tools/virtio/xen/xen.h b/tools/virtio/xen/xen.h new file mode 100644 index 000000000000..f569387d1403 --- /dev/null +++ b/tools/virtio/xen/xen.h @@ -0,0 +1,6 @@ +#ifndef XEN_XEN_STUB_H +#define XEN_XEN_STUB_H + +#define xen_domain() 0 + +#endif |