diff options
| -rw-r--r-- | Documentation/ABI/testing/sysfs-kernel-mm-swap | 10 | ||||
| -rw-r--r-- | drivers/base/node.c | 12 | ||||
| -rw-r--r-- | drivers/tty/tty_ldisc.c | 11 | ||||
| -rw-r--r-- | fs/binfmt_misc.c | 2 | ||||
| -rw-r--r-- | fs/block_dev.c | 6 | ||||
| -rw-r--r-- | fs/mpage.c | 14 | ||||
| -rw-r--r-- | include/linux/buffer_head.h | 1 | ||||
| -rw-r--r-- | include/linux/kernel.h | 90 | ||||
| -rw-r--r-- | include/linux/of.h | 10 | ||||
| -rw-r--r-- | include/linux/thread_info.h | 2 | ||||
| -rw-r--r-- | kernel/fork.c | 4 | ||||
| -rw-r--r-- | lib/Kconfig.debug | 143 | ||||
| -rw-r--r-- | mm/cma.c | 2 | ||||
| -rw-r--r-- | mm/madvise.c | 7 | ||||
| -rw-r--r-- | mm/mempolicy.c | 7 | ||||
| -rw-r--r-- | mm/migrate.c | 3 | ||||
| -rw-r--r-- | mm/page_vma_mapped.c | 28 | ||||
| -rw-r--r-- | mm/swap_state.c | 41 | ||||
| -rw-r--r-- | mm/vmalloc.c | 6 | ||||
| -rw-r--r-- | scripts/kallsyms.c | 2 | ||||
| -rw-r--r-- | tools/testing/selftests/vm/userfaultfd.c | 25 |
21 files changed, 245 insertions, 181 deletions
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-swap b/Documentation/ABI/testing/sysfs-kernel-mm-swap index 587db52084c7..94672016c268 100644 --- a/Documentation/ABI/testing/sysfs-kernel-mm-swap +++ b/Documentation/ABI/testing/sysfs-kernel-mm-swap @@ -14,13 +14,3 @@ Description: Enable/disable VMA based swap readahead. still used for tmpfs etc. other users. If set to false, the global swap readahead algorithm will be used for all swappable pages. - -What: /sys/kernel/mm/swap/vma_ra_max_order -Date: August 2017 -Contact: Linux memory management mailing list <linux-mm@kvack.org> -Description: The max readahead size in order for VMA based swap readahead - - VMA based swap readahead algorithm will readahead at - most 1 << max_order pages for each readahead. The - real readahead size for each readahead will be scaled - according to the estimation algorithm. diff --git a/drivers/base/node.c b/drivers/base/node.c index 3855902f2c5b..aae2402f3791 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -27,13 +27,21 @@ static struct bus_type node_subsys = { static ssize_t node_read_cpumap(struct device *dev, bool list, char *buf) { + ssize_t n; + cpumask_var_t mask; struct node *node_dev = to_node(dev); - const struct cpumask *mask = cpumask_of_node(node_dev->dev.id); /* 2008/04/07: buf currently PAGE_SIZE, need 9 chars per 32 bits. */ BUILD_BUG_ON((NR_CPUS/32 * 9) > (PAGE_SIZE-1)); - return cpumap_print_to_pagebuf(list, buf, mask); + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return 0; + + cpumask_and(mask, cpumask_of_node(node_dev->dev.id), cpu_online_mask); + n = cpumap_print_to_pagebuf(list, buf, mask); + free_cpumask_var(mask); + + return n; } static inline ssize_t node_read_cpumask(struct device *dev, diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c index 2fe216b276e2..84a8ac2a779f 100644 --- a/drivers/tty/tty_ldisc.c +++ b/drivers/tty/tty_ldisc.c @@ -694,10 +694,8 @@ int tty_ldisc_reinit(struct tty_struct *tty, int disc) tty_set_termios_ldisc(tty, disc); retval = tty_ldisc_open(tty, tty->ldisc); if (retval) { - if (!WARN_ON(disc == N_TTY)) { - tty_ldisc_put(tty->ldisc); - tty->ldisc = NULL; - } + tty_ldisc_put(tty->ldisc); + tty->ldisc = NULL; } return retval; } @@ -752,8 +750,9 @@ void tty_ldisc_hangup(struct tty_struct *tty, bool reinit) if (tty->ldisc) { if (reinit) { - if (tty_ldisc_reinit(tty, tty->termios.c_line) < 0) - tty_ldisc_reinit(tty, N_TTY); + if (tty_ldisc_reinit(tty, tty->termios.c_line) < 0 && + tty_ldisc_reinit(tty, N_TTY) < 0) + WARN_ON(tty_ldisc_reinit(tty, N_NULL) < 0); } else tty_ldisc_kill(tty); } diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 2a46762def31..a7c5a9861bef 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -596,7 +596,7 @@ static void bm_evict_inode(struct inode *inode) { Node *e = inode->i_private; - if (e->flags & MISC_FMT_OPEN_FILE) + if (e && e->flags & MISC_FMT_OPEN_FILE) filp_close(e->interp_file, NULL); clear_inode(inode); diff --git a/fs/block_dev.c b/fs/block_dev.c index 93d088ffc05c..789f55e851ae 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -716,10 +716,12 @@ int bdev_write_page(struct block_device *bdev, sector_t sector, set_page_writeback(page); result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, true); - if (result) + if (result) { end_page_writeback(page); - else + } else { + clean_page_buffers(page); unlock_page(page); + } blk_queue_exit(bdev->bd_queue); return result; } diff --git a/fs/mpage.c b/fs/mpage.c index 37bb77c1302c..c991faec70b9 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -468,6 +468,16 @@ static void clean_buffers(struct page *page, unsigned first_unmapped) try_to_free_buffers(page); } +/* + * For situations where we want to clean all buffers attached to a page. + * We don't need to calculate how many buffers are attached to the page, + * we just need to specify a number larger than the maximum number of buffers. + */ +void clean_page_buffers(struct page *page) +{ + clean_buffers(page, ~0U); +} + static int __mpage_writepage(struct page *page, struct writeback_control *wbc, void *data) { @@ -605,10 +615,8 @@ alloc_new: if (bio == NULL) { if (first_unmapped == blocks_per_page) { if (!bdev_write_page(bdev, blocks[0] << (blkbits - 9), - page, wbc)) { - clean_buffers(page, first_unmapped); + page, wbc)) goto out; - } } bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9), BIO_MAX_PAGES, GFP_NOFS|__GFP_HIGH); diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index c8dae555eccf..446b24cac67d 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -232,6 +232,7 @@ int generic_write_end(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page *, void *); void page_zero_new_buffers(struct page *page, unsigned from, unsigned to); +void clean_page_buffers(struct page *page); int cont_write_begin(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t *, loff_t *); diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 0ad4c3044cf9..91189bb0c818 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -44,6 +44,12 @@ #define STACK_MAGIC 0xdeadbeef +/** + * REPEAT_BYTE - repeat the value @x multiple times as an unsigned long value + * @x: value to repeat + * + * NOTE: @x is not checked for > 0xff; larger values produce odd results. + */ #define REPEAT_BYTE(x) ((~0ul / 0xff) * (x)) /* @a is a power of 2 value */ @@ -57,6 +63,10 @@ #define READ 0 #define WRITE 1 +/** + * ARRAY_SIZE - get the number of elements in array @arr + * @arr: array to be sized + */ #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr)) #define u64_to_user_ptr(x) ( \ @@ -76,7 +86,15 @@ #define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1) #define round_down(x, y) ((x) & ~__round_mask(x, y)) +/** + * FIELD_SIZEOF - get the size of a struct's field + * @t: the target struct + * @f: the target struct's field + * Return: the size of @f in the struct definition without having a + * declared instance of @t. + */ #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) + #define DIV_ROUND_UP __KERNEL_DIV_ROUND_UP #define DIV_ROUND_DOWN_ULL(ll, d) \ @@ -107,7 +125,7 @@ /* * Divide positive or negative dividend by positive or negative divisor * and round to closest integer. Result is undefined for negative - * divisors if he dividend variable type is unsigned and for negative + * divisors if the dividend variable type is unsigned and for negative * dividends if the divisor variable type is unsigned. */ #define DIV_ROUND_CLOSEST(x, divisor)( \ @@ -247,13 +265,13 @@ extern int _cond_resched(void); * @ep_ro: right open interval endpoint * * Perform a "reciprocal multiplication" in order to "scale" a value into - * range [0, ep_ro), where the upper interval endpoint is right-open. + * range [0, @ep_ro), where the upper interval endpoint is right-open. * This is useful, e.g. for accessing a index of an array containing - * ep_ro elements, for example. Think of it as sort of modulus, only that + * @ep_ro elements, for example. Think of it as sort of modulus, only that * the result isn't that of modulo. ;) Note that if initial input is a * small value, then result will return 0. * - * Return: a result based on val in interval [0, ep_ro). + * Return: a result based on @val in interval [0, @ep_ro). */ static inline u32 reciprocal_scale(u32 val, u32 ep_ro) { @@ -618,8 +636,8 @@ do { \ * trace_printk - printf formatting in the ftrace buffer * @fmt: the printf format for printing * - * Note: __trace_printk is an internal function for trace_printk and - * the @ip is passed in via the trace_printk macro. + * Note: __trace_printk is an internal function for trace_printk() and + * the @ip is passed in via the trace_printk() macro. * * This function allows a kernel developer to debug fast path sections * that printk is not appropriate for. By scattering in various @@ -629,7 +647,7 @@ do { \ * This is intended as a debugging tool for the developer only. * Please refrain from leaving trace_printks scattered around in * your code. (Extra memory is used for special buffers that are - * allocated when trace_printk() is used) + * allocated when trace_printk() is used.) * * A little optization trick is done here. If there's only one * argument, there's no need to scan the string for printf formats. @@ -681,7 +699,7 @@ int __trace_printk(unsigned long ip, const char *fmt, ...); * the @ip is passed in via the trace_puts macro. * * This is similar to trace_printk() but is made for those really fast - * paths that a developer wants the least amount of "Heisenbug" affects, + * paths that a developer wants the least amount of "Heisenbug" effects, * where the processing of the print format is still too much. * * This function allows a kernel developer to debug fast path sections @@ -692,7 +710,7 @@ int __trace_printk(unsigned long ip, const char *fmt, ...); * This is intended as a debugging tool for the developer only. * Please refrain from leaving trace_puts scattered around in * your code. (Extra memory is used for special buffers that are - * allocated when trace_puts() is used) + * allocated when trace_puts() is used.) * * Returns: 0 if nothing was written, positive # if string was. * (1 when __trace_bputs is used, strlen(str) when __trace_puts is used) @@ -771,6 +789,12 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } t2 min2 = (y); \ (void) (&min1 == &min2); \ min1 < min2 ? min1 : min2; }) + +/** + * min - return minimum of two values of the same or compatible types + * @x: first value + * @y: second value + */ #define min(x, y) \ __min(typeof(x), typeof(y), \ __UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \ @@ -781,12 +805,31 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } t2 max2 = (y); \ (void) (&max1 == &max2); \ max1 > max2 ? max1 : max2; }) + +/** + * max - return maximum of two values of the same or compatible types + * @x: first value + * @y: second value + */ #define max(x, y) \ __max(typeof(x), typeof(y), \ __UNIQUE_ID(max1_), __UNIQUE_ID(max2_), \ x, y) +/** + * min3 - return minimum of three values + * @x: first value + * @y: second value + * @z: third value + */ #define min3(x, y, z) min((typeof(x))min(x, y), z) + +/** + * max3 - return maximum of three values + * @x: first value + * @y: second value + * @z: third value + */ #define max3(x, y, z) max((typeof(x))max(x, y), z) /** @@ -805,8 +848,8 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * @lo: lowest allowable value * @hi: highest allowable value * - * This macro does strict typechecking of lo/hi to make sure they are of the - * same type as val. See the unnecessary pointer comparisons. + * This macro does strict typechecking of @lo/@hi to make sure they are of the + * same type as @val. See the unnecessary pointer comparisons. */ #define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi) @@ -816,11 +859,24 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * * Or not use min/max/clamp at all, of course. */ + +/** + * min_t - return minimum of two values, using the specified type + * @type: data type to use + * @x: first value + * @y: second value + */ #define min_t(type, x, y) \ __min(type, type, \ __UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \ x, y) +/** + * max_t - return maximum of two values, using the specified type + * @type: data type to use + * @x: first value + * @y: second value + */ #define max_t(type, x, y) \ __max(type, type, \ __UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \ @@ -834,7 +890,7 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * @hi: maximum allowable value * * This macro does no typechecking and uses temporary variables of type - * 'type' to make all the comparisons. + * @type to make all the comparisons. */ #define clamp_t(type, val, lo, hi) min_t(type, max_t(type, val, lo), hi) @@ -845,15 +901,17 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * @hi: maximum allowable value * * This macro does no typechecking and uses temporary variables of whatever - * type the input argument 'val' is. This is useful when val is an unsigned - * type and min and max are literals that will otherwise be assigned a signed + * type the input argument @val is. This is useful when @val is an unsigned + * type and @lo and @hi are literals that will otherwise be assigned a signed * integer type. */ #define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi) -/* - * swap - swap value of @a and @b +/** + * swap - swap values of @a and @b + * @a: first value + * @b: second value */ #define swap(a, b) \ do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) diff --git a/include/linux/of.h b/include/linux/of.h index cfc34117fc92..b240ed69dc96 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -734,6 +734,16 @@ static inline struct device_node *of_get_cpu_node(int cpu, return NULL; } +static inline int of_n_addr_cells(struct device_node *np) +{ + return 0; + +} +static inline int of_n_size_cells(struct device_node *np) +{ + return 0; +} + static inline int of_property_read_u64(const struct device_node *np, const char *propname, u64 *out_value) { diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 905d769d8ddc..5f7eeab990fe 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -42,7 +42,7 @@ enum { #define THREAD_ALIGN THREAD_SIZE #endif -#ifdef CONFIG_DEBUG_STACK_USAGE +#if IS_ENABLED(CONFIG_DEBUG_STACK_USAGE) || IS_ENABLED(CONFIG_DEBUG_KMEMLEAK) # define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_NOTRACK | \ __GFP_ZERO) #else diff --git a/kernel/fork.c b/kernel/fork.c index e702cb9ffbd8..07cc743698d3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -215,6 +215,10 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) if (!s) continue; +#ifdef CONFIG_DEBUG_KMEMLEAK + /* Clear stale pointers from reused stack. */ + memset(s->addr, 0, THREAD_SIZE); +#endif tsk->stack_vm_area = s; return s->addr; } diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 2689b7c50c52..c1e720a22c71 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1590,6 +1590,54 @@ config LATENCYTOP source kernel/trace/Kconfig +config PROVIDE_OHCI1394_DMA_INIT + bool "Remote debugging over FireWire early on boot" + depends on PCI && X86 + help + If you want to debug problems which hang or crash the kernel early + on boot and the crashing machine has a FireWire port, you can use + this feature to remotely access the memory of the crashed machine + over FireWire. This employs remote DMA as part of the OHCI1394 + specification which is now the standard for FireWire controllers. + + With remote DMA, you can monitor the printk buffer remotely using + firescope and access all memory below 4GB using fireproxy from gdb. + Even controlling a kernel debugger is possible using remote DMA. + + Usage: + + If ohci1394_dma=early is used as boot parameter, it will initialize + all OHCI1394 controllers which are found in the PCI config space. + + As all changes to the FireWire bus such as enabling and disabling + devices cause a bus reset and thereby disable remote DMA for all + devices, be sure to have the cable plugged and FireWire enabled on + the debugging host before booting the debug target for debugging. + + This code (~1k) is freed after boot. By then, the firewire stack + in charge of the OHCI-1394 controllers should be used instead. + + See Documentation/debugging-via-ohci1394.txt for more information. + +config DMA_API_DEBUG + bool "Enable debugging of DMA-API usage" + depends on HAVE_DMA_API_DEBUG + help + Enable this option to debug the use of the DMA API by device drivers. + With this option you will be able to detect common bugs in device + drivers like double-freeing of DMA mappings or freeing mappings that + were never allocated. + + This also attempts to catch cases where a page owned by DMA is + accessed by the cpu in a way that could cause data corruption. For + example, this enables cow_user_page() to check that the source page is + not undergoing DMA. + + This option causes a performance degradation. Use only if you want to + debug device drivers and dma interactions. + + If unsure, say N. + menu "Runtime Testing" config LKDTM @@ -1749,56 +1797,6 @@ config TEST_PARMAN If unsure, say N. -endmenu # runtime tests - -config PROVIDE_OHCI1394_DMA_INIT - bool "Remote debugging over FireWire early on boot" - depends on PCI && X86 - help - If you want to debug problems which hang or crash the kernel early - on boot and the crashing machine has a FireWire port, you can use - this feature to remotely access the memory of the crashed machine - over FireWire. This employs remote DMA as part of the OHCI1394 - specification which is now the standard for FireWire controllers. - - With remote DMA, you can monitor the printk buffer remotely using - firescope and access all memory below 4GB using fireproxy from gdb. - Even controlling a kernel debugger is possible using remote DMA. - - Usage: - - If ohci1394_dma=early is used as boot parameter, it will initialize - all OHCI1394 controllers which are found in the PCI config space. - - As all changes to the FireWire bus such as enabling and disabling - devices cause a bus reset and thereby disable remote DMA for all - devices, be sure to have the cable plugged and FireWire enabled on - the debugging host before booting the debug target for debugging. - - This code (~1k) is freed after boot. By then, the firewire stack - in charge of the OHCI-1394 controllers should be used instead. - - See Documentation/debugging-via-ohci1394.txt for more information. - -config DMA_API_DEBUG - bool "Enable debugging of DMA-API usage" - depends on HAVE_DMA_API_DEBUG - help - Enable this option to debug the use of the DMA API by device drivers. - With this option you will be able to detect common bugs in device - drivers like double-freeing of DMA mappings or freeing mappings that - were never allocated. - - This also attempts to catch cases where a page owned by DMA is - accessed by the cpu in a way that could cause data corruption. For - example, this enables cow_user_page() to check that the source page is - not undergoing DMA. - - This option causes a performance degradation. Use only if you want to - debug device drivers and dma interactions. - - If unsure, say N. - config TEST_LKM tristate "Test module loading with 'hello world' module" default n @@ -1873,18 +1871,6 @@ config TEST_UDELAY If unsure, say N. -config MEMTEST - bool "Memtest" - depends on HAVE_MEMBLOCK - ---help--- - This option adds a kernel parameter 'memtest', which allows memtest - to be set. - memtest=0, mean disabled; -- default - memtest=1, mean do 1 test pattern; - ... - memtest=17, mean do 17 test patterns. - If you are unsure how to answer this question, answer N. - config TEST_STATIC_KEYS tristate "Test static keys" default n @@ -1894,16 +1880,6 @@ config TEST_STATIC_KEYS If unsure, say N. -config BUG_ON_DATA_CORRUPTION - bool "Trigger a BUG when data corruption is detected" - select DEBUG_LIST - help - Select this option if the kernel should BUG when it encounters - data corruption in kernel memory structures when they get checked - for validity. - - If unsure, say N. - config TEST_KMOD tristate "kmod stress tester" default n @@ -1941,6 +1917,29 @@ config TEST_DEBUG_VIRTUAL If unsure, say N. +endmenu # runtime tests + +config MEMTEST + bool "Memtest" + depends on HAVE_MEMBLOCK + ---help--- + This option adds a kernel parameter 'memtest', which allows memtest + to be set. + memtest=0, mean disabled; -- default + memtest=1, mean do 1 test pattern; + ... + memtest=17, mean do 17 test patterns. + If you are unsure how to answer this question, answer N. + +config BUG_ON_DATA_CORRUPTION + bool "Trigger a BUG when data corruption is detected" + select DEBUG_LIST + help + Select this option if the kernel should BUG when it encounters + data corruption in kernel memory structures when they get checked + for validity. + + If unsure, say N. source "samples/Kconfig" @@ -460,7 +460,7 @@ struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align, trace_cma_alloc(pfn, page, count, align); - if (ret) { + if (ret && !(gfp_mask & __GFP_NOWARN)) { pr_info("%s: alloc failed, req-size: %zu pages, ret: %d\n", __func__, count, ret); cma_debug_show_areas(cma); diff --git a/mm/madvise.c b/mm/madvise.c index 25bade36e9ca..fd70d6aabc3e 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -757,6 +757,9 @@ madvise_behavior_valid(int behavior) * MADV_DONTFORK - omit this area from child's address space when forking: * typically, to avoid COWing pages pinned by get_user_pages(). * MADV_DOFORK - cancel MADV_DONTFORK: no longer omit this area when forking. + * MADV_WIPEONFORK - present the child process with zero-filled memory in this + * range after a fork. + * MADV_KEEPONFORK - undo the effect of MADV_WIPEONFORK * MADV_HWPOISON - trigger memory error handler as if the given memory range * were corrupted by unrecoverable hardware memory failure. * MADV_SOFT_OFFLINE - try to soft-offline the given range of memory. @@ -777,7 +780,9 @@ madvise_behavior_valid(int behavior) * zero - success * -EINVAL - start + len < 0, start is not page-aligned, * "behavior" is not a valid value, or application - * is attempting to release locked or shared pages. + * is attempting to release locked or shared pages, + * or the specified address range includes file, Huge TLB, + * MAP_SHARED or VMPFNMAP range. * -ENOMEM - addresses in the specified range are not currently * mapped, or are outside the AS of the process. * -EIO - an I/O error occurred while paging in data. diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 006ba625c0b8..a2af6d58a68f 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1920,8 +1920,11 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, struct page *page; page = __alloc_pages(gfp, order, nid); - if (page && page_to_nid(page) == nid) - inc_zone_page_state(page, NUMA_INTERLEAVE_HIT); + if (page && page_to_nid(page) == nid) { + preempt_disable(); + __inc_numa_state(page_zone(page), NUMA_INTERLEAVE_HIT); + preempt_enable(); + } return page; } diff --git a/mm/migrate.c b/mm/migrate.c index 6954c1435833..e00814ca390e 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2146,8 +2146,9 @@ static int migrate_vma_collect_hole(unsigned long start, unsigned long addr; for (addr = start & PAGE_MASK; addr < end; addr += PAGE_SIZE) { - migrate->src[migrate->npages++] = MIGRATE_PFN_MIGRATE; + migrate->src[migrate->npages] = MIGRATE_PFN_MIGRATE; migrate->dst[migrate->npages] = 0; + migrate->npages++; migrate->cpages++; } diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 6a03946469a9..53afbb919a1c 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -6,17 +6,6 @@ #include "internal.h" -static inline bool check_pmd(struct page_vma_mapped_walk *pvmw) -{ - pmd_t pmde; - /* - * Make sure we don't re-load pmd between present and !trans_huge check. - * We need a consistent view. - */ - pmde = READ_ONCE(*pvmw->pmd); - return pmd_present(pmde) && !pmd_trans_huge(pmde); -} - static inline bool not_found(struct page_vma_mapped_walk *pvmw) { page_vma_mapped_walk_done(pvmw); @@ -116,6 +105,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) pgd_t *pgd; p4d_t *p4d; pud_t *pud; + pmd_t pmde; /* The only possible pmd mapping has been handled on last iteration */ if (pvmw->pmd && !pvmw->pte) @@ -148,7 +138,13 @@ restart: if (!pud_present(*pud)) return false; pvmw->pmd = pmd_offset(pud, pvmw->address); - if (pmd_trans_huge(*pvmw->pmd) || is_pmd_migration_entry(*pvmw->pmd)) { + /* + * Make sure the pmd value isn't cached in a register by the + * compiler and used as a stale value after we've observed a + * subsequent update. + */ + pmde = READ_ONCE(*pvmw->pmd); + if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) { pvmw->ptl = pmd_lock(mm, pvmw->pmd); if (likely(pmd_trans_huge(*pvmw->pmd))) { if (pvmw->flags & PVMW_MIGRATION) @@ -167,17 +163,15 @@ restart: return not_found(pvmw); return true; } - } else - WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!"); + } return not_found(pvmw); } else { /* THP pmd was split under us: handle on pte level */ spin_unlock(pvmw->ptl); pvmw->ptl = NULL; } - } else { - if (!check_pmd(pvmw)) - return false; + } else if (!pmd_present(pmde)) { + return false; } if (!map_pte(pvmw)) goto next_pte; diff --git a/mm/swap_state.c b/mm/swap_state.c index ed91091d1e68..05b6803f0cce 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -39,10 +39,6 @@ struct address_space *swapper_spaces[MAX_SWAPFILES]; static unsigned int nr_swapper_spaces[MAX_SWAPFILES]; bool swap_vma_readahead = true; -#define SWAP_RA_MAX_ORDER_DEFAULT 3 - -static int swap_ra_max_order = SWAP_RA_MAX_ORDER_DEFAULT; - #define SWAP_RA_WIN_SHIFT (PAGE_SHIFT / 2) #define SWAP_RA_HITS_MASK ((1UL << SWAP_RA_WIN_SHIFT) - 1) #define SWAP_RA_HITS_MAX SWAP_RA_HITS_MASK @@ -664,6 +660,13 @@ struct page *swap_readahead_detect(struct vm_fault *vmf, pte_t *tpte; #endif + max_win = 1 << min_t(unsigned int, READ_ONCE(page_cluster), + SWAP_RA_ORDER_CEILING); + if (max_win == 1) { + swap_ra->win = 1; + return NULL; + } + faddr = vmf->address; entry = pte_to_swp_entry(vmf->orig_pte); if ((unlikely(non_swap_entry(entry)))) @@ -672,12 +675,6 @@ struct page *swap_readahead_detect(struct vm_fault *vmf, if (page) return page; - max_win = 1 << READ_ONCE(swap_ra_max_order); - if (max_win == 1) { - swap_ra->win = 1; - return NULL; - } - fpfn = PFN_DOWN(faddr); swap_ra_info = GET_SWAP_RA_VAL(vma); pfn = PFN_DOWN(SWAP_RA_ADDR(swap_ra_info)); @@ -786,32 +783,8 @@ static struct kobj_attribute vma_ra_enabled_attr = __ATTR(vma_ra_enabled, 0644, vma_ra_enabled_show, vma_ra_enabled_store); -static ssize_t vma_ra_max_order_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) -{ - return sprintf(buf, "%d\n", swap_ra_max_order); -} -static ssize_t vma_ra_max_order_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) -{ - int err, v; - - err = kstrtoint(buf, 10, &v); - if (err || v > SWAP_RA_ORDER_CEILING || v <= 0) - return -EINVAL; - - swap_ra_max_order = v; - - return count; -} -static struct kobj_attribute vma_ra_max_order_attr = - __ATTR(vma_ra_max_order, 0644, vma_ra_max_order_show, - vma_ra_max_order_store); - static struct attribute *swap_attrs[] = { &vma_ra_enabled_attr.attr, - &vma_ra_max_order_attr.attr, NULL, }; diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 8a43db6284eb..673942094328 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1695,11 +1695,6 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, for (i = 0; i < area->nr_pages; i++) { struct page *page; - if (fatal_signal_pending(current)) { - area->nr_pages = i; - goto fail_no_warn; - } - if (node == NUMA_NO_NODE) page = alloc_page(alloc_mask|highmem_mask); else @@ -1723,7 +1718,6 @@ fail: warn_alloc(gfp_mask, NULL, "vmalloc: allocation failure, allocated %ld of %ld bytes", (area->nr_pages*PAGE_SIZE), area->size); -fail_no_warn: vfree(area->addr); return NULL; } diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 5d554419170b..9ee9bf7fd1a2 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -158,7 +158,7 @@ static int read_symbol(FILE *in, struct sym_entry *s) else if (str[0] == '$') return -1; /* exclude debugging symbols */ - else if (stype == 'N') + else if (stype == 'N' || stype == 'n') return -1; /* include the type field in the symbol name, so that it gets diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index a2c53a3d223d..de2f9ec8a87f 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -397,7 +397,7 @@ static void retry_copy_page(int ufd, struct uffdio_copy *uffdio_copy, } } -static int copy_page(int ufd, unsigned long offset) +static int __copy_page(int ufd, unsigned long offset, bool retry) { struct uffdio_copy uffdio_copy; @@ -418,7 +418,7 @@ static int copy_page(int ufd, unsigned long offset) fprintf(stderr, "UFFDIO_COPY unexpected copy %Ld\n", uffdio_copy.copy), exit(1); } else { - if (test_uffdio_copy_eexist) { + if (test_uffdio_copy_eexist && retry) { test_uffdio_copy_eexist = false; retry_copy_page(ufd, &uffdio_copy, offset); } @@ -427,6 +427,16 @@ static int copy_page(int ufd, unsigned long offset) return 0; } +static int copy_page_retry(int ufd, unsigned long offset) +{ + return __copy_page(ufd, offset, true); +} + +static int copy_page(int ufd, unsigned long offset) +{ + return __copy_page(ufd, offset, false); +} + static void *uffd_poll_thread(void *arg) { unsigned long cpu = (unsigned long) arg; @@ -544,7 +554,7 @@ static void *background_thread(void *arg) for (page_nr = cpu * nr_pages_per_cpu; page_nr < (cpu+1) * nr_pages_per_cpu; page_nr++) - copy_page(uffd, page_nr * page_size); + copy_page_retry(uffd, page_nr * page_size); return NULL; } @@ -779,7 +789,7 @@ static void retry_uffdio_zeropage(int ufd, } } -static int uffdio_zeropage(int ufd, unsigned long offset) +static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry) { struct uffdio_zeropage uffdio_zeropage; int ret; @@ -814,7 +824,7 @@ static int uffdio_zeropage(int ufd, unsigned long offset) fprintf(stderr, "UFFDIO_ZEROPAGE unexpected %Ld\n", uffdio_zeropage.zeropage), exit(1); } else { - if (test_uffdio_zeropage_eexist) { + if (test_uffdio_zeropage_eexist && retry) { test_uffdio_zeropage_eexist = false; retry_uffdio_zeropage(ufd, &uffdio_zeropage, offset); @@ -830,6 +840,11 @@ static int uffdio_zeropage(int ufd, unsigned long offset) return 0; } +static int uffdio_zeropage(int ufd, unsigned long offset) +{ + return __uffdio_zeropage(ufd, offset, false); +} + /* exercise UFFDIO_ZEROPAGE */ static int userfaultfd_zeropage_test(void) { |