diff options
36 files changed, 422 insertions, 299 deletions
diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt index 65b3eac8856c..e8d25e784214 100644 --- a/Documentation/cgroup-v2.txt +++ b/Documentation/cgroup-v2.txt @@ -843,6 +843,10 @@ PAGE_SIZE multiple when read back. Amount of memory used to cache filesystem data, including tmpfs and shared memory. + sock + + Amount of memory used in network transmission buffers + file_mapped Amount of cached filesystem data mapped with mmap() diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index fde9fd06fa98..843b045b4069 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -240,8 +240,8 @@ Table 1-2: Contents of the status files (as of 4.1) RssFile size of resident file mappings RssShmem size of resident shmem memory (includes SysV shm, mapping of tmpfs and shared anonymous mappings) - VmData size of data, stack, and text segments - VmStk size of data, stack, and text segments + VmData size of private data segments + VmStk size of stack segments VmExe size of text segment VmLib size of shared library code VmPTE size of page table entries @@ -356,7 +356,7 @@ address perms offset dev inode pathname a7cb1000-a7cb2000 ---p 00000000 00:00 0 a7cb2000-a7eb2000 rw-p 00000000 00:00 0 a7eb2000-a7eb3000 ---p 00000000 00:00 0 -a7eb3000-a7ed5000 rw-p 00000000 00:00 0 [stack:1001] +a7eb3000-a7ed5000 rw-p 00000000 00:00 0 a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6 a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6 a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6 @@ -388,7 +388,6 @@ is not associated with a file: [heap] = the heap of the program [stack] = the stack of the main process - [stack:1001] = the stack of the thread with tid 1001 [vdso] = the "virtual dynamic shared object", the kernel system call handler @@ -396,10 +395,8 @@ is not associated with a file: The /proc/PID/task/TID/maps is a view of the virtual memory from the viewpoint of the individual tasks of a process. In this file you will see a mapping marked -as [stack] if that task sees it as a stack. This is a key difference from the -content of /proc/PID/maps, where you will see all mappings that are being used -as stack by all of those tasks. Hence, for the example above, the task-level -map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this: +as [stack] if that task sees it as a stack. Hence, for the example above, the +task-level map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this: 08048000-08049000 r-xp 00000000 03:00 8312 /opt/test 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 87d40a72f6a1..551ecf09c8dd 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1496,6 +1496,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. could change it dynamically, usually by /sys/module/printk/parameters/ignore_loglevel. + ignore_rlimit_data + Ignore RLIMIT_DATA setting for data mappings, + print warning at first misuse. Can be changed via + /sys/module/kernel/parameters/ignore_rlimit_data. + ihash_entries= [KNL] Set number of hash buckets for inode cache. diff --git a/MAINTAINERS b/MAINTAINERS index f678c37107f5..24c5b9a29670 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -967,6 +967,8 @@ M: Rob Herring <robh@kernel.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/mach-highbank/ +F: arch/arm/boot/dts/highbank.dts +F: arch/arm/boot/dts/ecx-*.dts* ARM/CAVIUM NETWORKS CNS3XXX MACHINE SUPPORT M: Krzysztof Halasa <khalasa@piap.pl> @@ -1042,6 +1044,7 @@ M: Barry Song <baohua@kernel.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) T: git git://git.kernel.org/pub/scm/linux/kernel/git/baohua/linux.git S: Maintained +F: arch/arm/boot/dts/prima2* F: arch/arm/mach-prima2/ F: drivers/clk/sirf/ F: drivers/clocksource/timer-prima2.c @@ -1143,6 +1146,10 @@ W: http://www.hisilicon.com S: Supported T: git git://github.com/hisilicon/linux-hisi.git F: arch/arm/mach-hisi/ +F: arch/arm/boot/dts/hi3* +F: arch/arm/boot/dts/hip* +F: arch/arm/boot/dts/hisi* +F: arch/arm64/boot/dts/hisilicon/ ARM/HP JORNADA 7XX MACHINE SUPPORT M: Kristoffer Ericson <kristoffer.ericson@gmail.com> @@ -1219,6 +1226,7 @@ M: Santosh Shilimkar <ssantosh@kernel.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/mach-keystone/ +F: arch/arm/boot/dts/k2* T: git git://git.kernel.org/pub/scm/linux/kernel/git/ssantosh/linux-keystone.git ARM/TEXAS INSTRUMENT KEYSTONE CLOCK FRAMEWORK @@ -1287,6 +1295,7 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/mach-berlin/ F: arch/arm/boot/dts/berlin* +F: arch/arm64/boot/dts/marvell/berlin* ARM/Marvell Dove/MV78xx0/Orion SOC support @@ -1425,6 +1434,7 @@ S: Maintained F: arch/arm/boot/dts/qcom-*.dts F: arch/arm/boot/dts/qcom-*.dtsi F: arch/arm/mach-qcom/ +F: arch/arm64/boot/dts/qcom/* F: drivers/soc/qcom/ F: drivers/tty/serial/msm_serial.h F: drivers/tty/serial/msm_serial.c @@ -1484,6 +1494,8 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-samsung-soc@vger.kernel.org (moderated for non-subscribers) S: Maintained F: arch/arm/boot/dts/s3c* +F: arch/arm/boot/dts/s5p* +F: arch/arm/boot/dts/samsung* F: arch/arm/boot/dts/exynos* F: arch/arm64/boot/dts/exynos/ F: arch/arm/plat-samsung/ @@ -1563,6 +1575,7 @@ S: Maintained F: arch/arm/mach-socfpga/ F: arch/arm/boot/dts/socfpga* F: arch/arm/configs/socfpga_defconfig +F: arch/arm64/boot/dts/altera/ W: http://www.rocketboards.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/dinguyen/linux.git @@ -1716,7 +1729,7 @@ M: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/boot/dts/vexpress* -F: arch/arm64/boot/dts/arm/vexpress* +F: arch/arm64/boot/dts/arm/ F: arch/arm/mach-vexpress/ F: */*/vexpress* F: */*/*/vexpress* @@ -2343,6 +2356,7 @@ F: arch/arm/mach-bcm/ F: arch/arm/boot/dts/bcm113* F: arch/arm/boot/dts/bcm216* F: arch/arm/boot/dts/bcm281* +F: arch/arm64/boot/dts/broadcom/ F: arch/arm/configs/bcm_defconfig F: drivers/mmc/host/sdhci-bcm-kona.c F: drivers/clocksource/bcm_kona_timer.c @@ -8818,6 +8832,7 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) T: git git://github.com/hzhuang1/linux.git T: git git://github.com/rjarzmik/linux.git S: Maintained +F: arch/arm/boot/dts/pxa* F: arch/arm/mach-pxa/ F: drivers/dma/pxa* F: drivers/pcmcia/pxa2xx* @@ -8847,6 +8862,7 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) T: git git://github.com/hzhuang1/linux.git T: git git://git.linaro.org/people/ycmiao/pxa-linux.git S: Maintained +F: arch/arm/boot/dts/mmp* F: arch/arm/mach-mmp/ PXA MMCI DRIVER @@ -10291,6 +10307,7 @@ L: spear-devel@list.st.com L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) W: http://www.st.com/spear S: Maintained +F: arch/arm/boot/dts/spear* F: arch/arm/mach-spear/ SPEAR CLOCK FRAMEWORK SUPPORT @@ -12133,7 +12150,7 @@ F: drivers/net/hamradio/*scc.c F: drivers/net/hamradio/z8530.h ZBUD COMPRESSED PAGE ALLOCATOR -M: Seth Jennings <sjennings@variantweb.net> +M: Seth Jennings <sjenning@redhat.com> L: linux-mm@kvack.org S: Maintained F: mm/zbud.c @@ -12188,7 +12205,7 @@ F: include/linux/zsmalloc.h F: Documentation/vm/zsmalloc.txt ZSWAP COMPRESSED SWAP CACHING -M: Seth Jennings <sjennings@variantweb.net> +M: Seth Jennings <sjenning@redhat.com> L: linux-mm@kvack.org S: Maintained F: mm/zswap.c diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index 9fda22e3387e..7fddd8696211 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -68,6 +68,7 @@ #include <linux/of_platform.h> #include <linux/of_address.h> #include <linux/of_irq.h> +#include <linux/acpi.h> #ifdef CONFIG_PARISC #include <asm/hardware.h> /* for register_parisc_driver() stuff */ @@ -2054,8 +2055,6 @@ static int hardcode_find_bmc(void) #ifdef CONFIG_ACPI -#include <linux/acpi.h> - /* * Once we get an ACPI failure, we don't try any more, because we go * through the tables sequentially. Once we don't find a table, there diff --git a/drivers/hwspinlock/hwspinlock_core.c b/drivers/hwspinlock/hwspinlock_core.c index 52f708bcf77f..d50c701b19d6 100644 --- a/drivers/hwspinlock/hwspinlock_core.c +++ b/drivers/hwspinlock/hwspinlock_core.c @@ -313,6 +313,10 @@ int of_hwspin_lock_get_id(struct device_node *np, int index) hwlock = radix_tree_deref_slot(slot); if (unlikely(!hwlock)) continue; + if (radix_tree_is_indirect_ptr(hwlock)) { + slot = radix_tree_iter_retry(&iter); + continue; + } if (hwlock->bank->dev->of_node == args.np) { ret = 0; diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 503ab8b46c0b..5e820674432c 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1261,7 +1261,7 @@ sg_mmap(struct file *filp, struct vm_area_struct *vma) } sfp->mmap_called = 1; - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP; vma->vm_private_data = sfp; vma->vm_ops = &sg_mmap_vm_ops; return 0; diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 5bcd92d50e82..0cb1abd535e3 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1215,7 +1215,7 @@ static int ff_layout_read_done_cb(struct rpc_task *task, hdr->pgio_mirror_idx + 1, &hdr->pgio_mirror_idx)) goto out_eagain; - set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + set_bit(NFS_LAYOUT_RETURN_REQUESTED, &hdr->lseg->pls_layout->plh_flags); pnfs_read_resend_pnfs(hdr); return task->tk_status; diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index 29898a9550fa..eb370460ce20 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -412,7 +412,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx, OP_ILLEGAL, GFP_NOIO); if (!fail_return) { if (ff_layout_has_available_ds(lseg)) - set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + set_bit(NFS_LAYOUT_RETURN_REQUESTED, &lseg->pls_layout->plh_flags); else pnfs_error_mark_layout_for_return(ino, lseg); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index a3592cc34a20..482b6e94bb37 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -52,9 +52,7 @@ static DEFINE_SPINLOCK(pnfs_spinlock); */ static LIST_HEAD(pnfs_modules_tbl); -static int -pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, const nfs4_stateid *stateid, - enum pnfs_iomode iomode, bool sync); +static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo); /* Return the registered pnfs layout driver module matching given id */ static struct pnfs_layoutdriver_type * @@ -243,6 +241,8 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo) { struct inode *inode = lo->plh_inode; + pnfs_layoutreturn_before_put_layout_hdr(lo); + if (atomic_dec_and_lock(&lo->plh_refcount, &inode->i_lock)) { if (!list_empty(&lo->plh_segs)) WARN_ONCE(1, "NFS: BUG unfreed layout segments.\n"); @@ -345,58 +345,6 @@ pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo, rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq); } -/* Return true if layoutreturn is needed */ -static bool -pnfs_layout_need_return(struct pnfs_layout_hdr *lo, - struct pnfs_layout_segment *lseg) -{ - struct pnfs_layout_segment *s; - - if (!test_and_clear_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags)) - return false; - - list_for_each_entry(s, &lo->plh_segs, pls_list) - if (s != lseg && test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags)) - return false; - - return true; -} - -static bool -pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo) -{ - if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) - return false; - lo->plh_return_iomode = 0; - pnfs_get_layout_hdr(lo); - clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags); - return true; -} - -static void pnfs_layoutreturn_before_put_lseg(struct pnfs_layout_segment *lseg, - struct pnfs_layout_hdr *lo, struct inode *inode) -{ - lo = lseg->pls_layout; - inode = lo->plh_inode; - - spin_lock(&inode->i_lock); - if (pnfs_layout_need_return(lo, lseg)) { - nfs4_stateid stateid; - enum pnfs_iomode iomode; - bool send; - - nfs4_stateid_copy(&stateid, &lo->plh_stateid); - iomode = lo->plh_return_iomode; - send = pnfs_prepare_layoutreturn(lo); - spin_unlock(&inode->i_lock); - if (send) { - /* Send an async layoutreturn so we dont deadlock */ - pnfs_send_layoutreturn(lo, &stateid, iomode, false); - } - } else - spin_unlock(&inode->i_lock); -} - void pnfs_put_lseg(struct pnfs_layout_segment *lseg) { @@ -410,15 +358,8 @@ pnfs_put_lseg(struct pnfs_layout_segment *lseg) atomic_read(&lseg->pls_refcount), test_bit(NFS_LSEG_VALID, &lseg->pls_flags)); - /* Handle the case where refcount != 1 */ - if (atomic_add_unless(&lseg->pls_refcount, -1, 1)) - return; - lo = lseg->pls_layout; inode = lo->plh_inode; - /* Do we need a layoutreturn? */ - if (test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags)) - pnfs_layoutreturn_before_put_lseg(lseg, lo, inode); if (atomic_dec_and_lock(&lseg->pls_refcount, &inode->i_lock)) { if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags)) { @@ -937,6 +878,17 @@ void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo) rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq); } +static bool +pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo) +{ + if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) + return false; + lo->plh_return_iomode = 0; + pnfs_get_layout_hdr(lo); + clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags); + return true; +} + static int pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, const nfs4_stateid *stateid, enum pnfs_iomode iomode, bool sync) @@ -971,6 +923,48 @@ out: return status; } +/* Return true if layoutreturn is needed */ +static bool +pnfs_layout_need_return(struct pnfs_layout_hdr *lo) +{ + struct pnfs_layout_segment *s; + + if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) + return false; + + /* Defer layoutreturn until all lsegs are done */ + list_for_each_entry(s, &lo->plh_segs, pls_list) { + if (test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags)) + return false; + } + + return true; +} + +static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo) +{ + struct inode *inode= lo->plh_inode; + + if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) + return; + spin_lock(&inode->i_lock); + if (pnfs_layout_need_return(lo)) { + nfs4_stateid stateid; + enum pnfs_iomode iomode; + bool send; + + nfs4_stateid_copy(&stateid, &lo->plh_stateid); + iomode = lo->plh_return_iomode; + send = pnfs_prepare_layoutreturn(lo); + spin_unlock(&inode->i_lock); + if (send) { + /* Send an async layoutreturn so we dont deadlock */ + pnfs_send_layoutreturn(lo, &stateid, iomode, false); + } + } else + spin_unlock(&inode->i_lock); +} + /* * Initiates a LAYOUTRETURN(FILE), and removes the pnfs_layout_hdr * when the layout segment list is empty. @@ -1091,7 +1085,7 @@ bool pnfs_roc(struct inode *ino) nfs4_stateid_copy(&stateid, &lo->plh_stateid); /* always send layoutreturn if being marked so */ - if (test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + if (test_and_clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) layoutreturn = pnfs_prepare_layoutreturn(lo); @@ -1772,7 +1766,7 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, pnfs_set_plh_return_iomode(lo, return_range->iomode); if (!mark_lseg_invalid(lseg, tmp_list)) remaining++; - set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + set_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags); } return remaining; diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 9f4e2a47f4aa..1ac1db5f6dad 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -94,8 +94,8 @@ enum { NFS_LAYOUT_RO_FAILED = 0, /* get ro layout failed stop trying */ NFS_LAYOUT_RW_FAILED, /* get rw layout failed stop trying */ NFS_LAYOUT_BULK_RECALL, /* bulk recall affecting layout */ - NFS_LAYOUT_RETURN, /* Return this layout ASAP */ - NFS_LAYOUT_RETURN_BEFORE_CLOSE, /* Return this layout before close */ + NFS_LAYOUT_RETURN, /* layoutreturn in progress */ + NFS_LAYOUT_RETURN_REQUESTED, /* Return this layout ASAP */ NFS_LAYOUT_INVALID_STID, /* layout stateid id is invalid */ NFS_LAYOUT_FIRST_LAYOUTGET, /* Serialize first layoutget */ }; diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index a3cc6d2fc896..a76b9ea7722e 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -1254,15 +1254,15 @@ static const struct file_operations o2hb_debug_fops = { void o2hb_exit(void) { - kfree(o2hb_db_livenodes); - kfree(o2hb_db_liveregions); - kfree(o2hb_db_quorumregions); - kfree(o2hb_db_failedregions); debugfs_remove(o2hb_debug_failedregions); debugfs_remove(o2hb_debug_quorumregions); debugfs_remove(o2hb_debug_liveregions); debugfs_remove(o2hb_debug_livenodes); debugfs_remove(o2hb_debug_dir); + kfree(o2hb_db_livenodes); + kfree(o2hb_db_liveregions); + kfree(o2hb_db_quorumregions); + kfree(o2hb_db_failedregions); } static struct dentry *o2hb_debug_create(const char *name, struct dentry *dir, @@ -1438,13 +1438,15 @@ static void o2hb_region_release(struct config_item *item) kfree(reg->hr_slots); - kfree(reg->hr_db_regnum); - kfree(reg->hr_db_livenodes); debugfs_remove(reg->hr_debug_livenodes); debugfs_remove(reg->hr_debug_regnum); debugfs_remove(reg->hr_debug_elapsed_time); debugfs_remove(reg->hr_debug_pinned); debugfs_remove(reg->hr_debug_dir); + kfree(reg->hr_db_livenodes); + kfree(reg->hr_db_regnum); + kfree(reg->hr_debug_elapsed_time); + kfree(reg->hr_debug_pinned); spin_lock(&o2hb_live_lock); list_del(®->hr_all_item); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 85d16c67c33e..fa95ab2d3674 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -259,23 +259,29 @@ static int do_maps_open(struct inode *inode, struct file *file, sizeof(struct proc_maps_private)); } -static pid_t pid_of_stack(struct proc_maps_private *priv, - struct vm_area_struct *vma, bool is_pid) +/* + * Indicate if the VMA is a stack for the given task; for + * /proc/PID/maps that is the stack of the main task. + */ +static int is_stack(struct proc_maps_private *priv, + struct vm_area_struct *vma, int is_pid) { - struct inode *inode = priv->inode; - struct task_struct *task; - pid_t ret = 0; + int stack = 0; + + if (is_pid) { + stack = vma->vm_start <= vma->vm_mm->start_stack && + vma->vm_end >= vma->vm_mm->start_stack; + } else { + struct inode *inode = priv->inode; + struct task_struct *task; - rcu_read_lock(); - task = pid_task(proc_pid(inode), PIDTYPE_PID); - if (task) { - task = task_of_stack(task, vma, is_pid); + rcu_read_lock(); + task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) - ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info); + stack = vma_is_stack_for_task(vma, task); + rcu_read_unlock(); } - rcu_read_unlock(); - - return ret; + return stack; } static void @@ -335,8 +341,6 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) name = arch_vma_name(vma); if (!name) { - pid_t tid; - if (!mm) { name = "[vdso]"; goto done; @@ -348,21 +352,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) goto done; } - tid = pid_of_stack(priv, vma, is_pid); - if (tid != 0) { - /* - * Thread stack in /proc/PID/task/TID/maps or - * the main process stack. - */ - if (!is_pid || (vma->vm_start <= mm->start_stack && - vma->vm_end >= mm->start_stack)) { - name = "[stack]"; - } else { - /* Thread stack in /proc/PID/maps */ - seq_pad(m, ' '); - seq_printf(m, "[stack:%d]", tid); - } - } + if (is_stack(priv, vma, is_pid)) + name = "[stack]"; } done: @@ -1552,18 +1543,19 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { + pte_t huge_pte = huge_ptep_get(pte); struct numa_maps *md; struct page *page; - if (!pte_present(*pte)) + if (!pte_present(huge_pte)) return 0; - page = pte_page(*pte); + page = pte_page(huge_pte); if (!page) return 0; md = walk->private; - gather_stats(page, md, pte_dirty(*pte), 1); + gather_stats(page, md, pte_dirty(huge_pte), 1); return 0; } @@ -1617,19 +1609,8 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) seq_file_path(m, file, "\n\t= "); } else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) { seq_puts(m, " heap"); - } else { - pid_t tid = pid_of_stack(proc_priv, vma, is_pid); - if (tid != 0) { - /* - * Thread stack in /proc/PID/task/TID/maps or - * the main process stack. - */ - if (!is_pid || (vma->vm_start <= mm->start_stack && - vma->vm_end >= mm->start_stack)) - seq_puts(m, " stack"); - else - seq_printf(m, " stack:%d", tid); - } + } else if (is_stack(proc_priv, vma, is_pid)) { + seq_puts(m, " stack"); } if (is_vm_hugetlb_page(vma)) diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index e0d64c92e4f6..faacb0c0d857 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -123,23 +123,26 @@ unsigned long task_statm(struct mm_struct *mm, return size; } -static pid_t pid_of_stack(struct proc_maps_private *priv, - struct vm_area_struct *vma, bool is_pid) +static int is_stack(struct proc_maps_private *priv, + struct vm_area_struct *vma, int is_pid) { - struct inode *inode = priv->inode; - struct task_struct *task; - pid_t ret = 0; - - rcu_read_lock(); - task = pid_task(proc_pid(inode), PIDTYPE_PID); - if (task) { - task = task_of_stack(task, vma, is_pid); + struct mm_struct *mm = vma->vm_mm; + int stack = 0; + + if (is_pid) { + stack = vma->vm_start <= mm->start_stack && + vma->vm_end >= mm->start_stack; + } else { + struct inode *inode = priv->inode; + struct task_struct *task; + + rcu_read_lock(); + task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) - ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info); + stack = vma_is_stack_for_task(vma, task); + rcu_read_unlock(); } - rcu_read_unlock(); - - return ret; + return stack; } /* @@ -181,21 +184,9 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma, if (file) { seq_pad(m, ' '); seq_file_path(m, file, ""); - } else if (mm) { - pid_t tid = pid_of_stack(priv, vma, is_pid); - - if (tid != 0) { - seq_pad(m, ' '); - /* - * Thread stack in /proc/PID/task/TID/maps or - * the main process stack. - */ - if (!is_pid || (vma->vm_start <= mm->start_stack && - vma->vm_end >= mm->start_stack)) - seq_printf(m, "[stack]"); - else - seq_printf(m, "[stack:%d]", tid); - } + } else if (mm && is_stack(priv, vma, is_pid)) { + seq_pad(m, ' '); + seq_printf(m, "[stack]"); } seq_putc(m, '\n'); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 9ae48d4aeb5e..792c8981e633 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -51,7 +51,7 @@ enum mem_cgroup_stat_index { MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */ MEM_CGROUP_STAT_NSTATS, /* default hierarchy stats */ - MEMCG_SOCK, + MEMCG_SOCK = MEM_CGROUP_STAT_NSTATS, MEMCG_NR_STAT, }; diff --git a/include/linux/mm.h b/include/linux/mm.h index f1cd22f2df1a..516e14944339 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -201,11 +201,13 @@ extern unsigned int kobjsize(const void *objp); #endif #ifdef CONFIG_STACK_GROWSUP -#define VM_STACK_FLAGS (VM_GROWSUP | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) +#define VM_STACK VM_GROWSUP #else -#define VM_STACK_FLAGS (VM_GROWSDOWN | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) +#define VM_STACK VM_GROWSDOWN #endif +#define VM_STACK_FLAGS (VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) + /* * Special vmas that are non-mergable, non-mlock()able. * Note: mm/huge_memory.c VM_NO_THP depends on this definition. @@ -1341,8 +1343,7 @@ static inline int stack_guard_page_end(struct vm_area_struct *vma, !vma_growsup(vma->vm_next, addr); } -extern struct task_struct *task_of_stack(struct task_struct *task, - struct vm_area_struct *vma, bool in_group); +int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t); extern unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index d3ebb9d21a53..624b78b848b8 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -424,9 +424,9 @@ struct mm_struct { unsigned long total_vm; /* Total pages mapped */ unsigned long locked_vm; /* Pages that have PG_mlocked set */ unsigned long pinned_vm; /* Refcount permanently increased */ - unsigned long data_vm; /* VM_WRITE & ~VM_SHARED/GROWSDOWN */ - unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE */ - unsigned long stack_vm; /* VM_GROWSUP/DOWN */ + unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */ + unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */ + unsigned long stack_vm; /* VM_STACK */ unsigned long def_flags; unsigned long start_code, end_code, start_data, end_data; unsigned long start_brk, brk, start_stack; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 33bb1b19273e..7b6c2cfee390 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -682,6 +682,12 @@ typedef struct pglist_data { */ unsigned long first_deferred_pfn; #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + spinlock_t split_queue_lock; + struct list_head split_queue; + unsigned long split_queue_len; +#endif } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) diff --git a/include/linux/of.h b/include/linux/of.h index dd10626a615f..dc6e39696b64 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -929,7 +929,7 @@ static inline int of_get_available_child_count(const struct device_node *np) return num; } -#ifdef CONFIG_OF +#if defined(CONFIG_OF) && !defined(MODULE) #define _OF_DECLARE(table, name, compat, fn, fn_type) \ static const struct of_device_id __of_table_##name \ __used __section(__##table##_of_table) \ diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 7c88ad156a29..00b17c526c1f 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -379,6 +379,22 @@ void **radix_tree_next_chunk(struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned flags); /** + * radix_tree_iter_retry - retry this chunk of the iteration + * @iter: iterator state + * + * If we iterate over a tree protected only by the RCU lock, a race + * against deletion or creation may result in seeing a slot for which + * radix_tree_deref_retry() returns true. If so, call this function + * and continue the iteration. + */ +static inline __must_check +void **radix_tree_iter_retry(struct radix_tree_iter *iter) +{ + iter->next_index = iter->index; + return NULL; +} + +/** * radix_tree_chunk_size - get current chunk size * * @iter: pointer to radix tree iterator diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index dda9e6742950..202df6cffcca 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -126,6 +126,13 @@ check_stack(unsigned long ip, unsigned long *stack) } /* + * Some archs may not have the passed in ip in the dump. + * If that happens, we need to show everything. + */ + if (i == stack_trace_max.nr_entries) + i = 0; + + /* * Now find where in the stack these are. */ x = 0; diff --git a/lib/radix-tree.c b/lib/radix-tree.c index fcf5d98574ce..6b79e9026e24 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1019,9 +1019,13 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results, return 0; radix_tree_for_each_slot(slot, root, &iter, first_index) { - results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot)); + results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; + if (radix_tree_is_indirect_ptr(results[ret])) { + slot = radix_tree_iter_retry(&iter); + continue; + } if (++ret == max_items) break; } @@ -1098,9 +1102,13 @@ radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results, return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { - results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot)); + results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; + if (radix_tree_is_indirect_ptr(results[ret])) { + slot = radix_tree_iter_retry(&iter); + continue; + } if (++ret == max_items) break; } diff --git a/lib/test-string_helpers.c b/lib/test-string_helpers.c index 98866a770770..25b5cbfb7615 100644 --- a/lib/test-string_helpers.c +++ b/lib/test-string_helpers.c @@ -327,36 +327,67 @@ out: } #define string_get_size_maxbuf 16 -#define test_string_get_size_one(size, blk_size, units, exp_result) \ +#define test_string_get_size_one(size, blk_size, exp_result10, exp_result2) \ do { \ - BUILD_BUG_ON(sizeof(exp_result) >= string_get_size_maxbuf); \ - __test_string_get_size((size), (blk_size), (units), \ - (exp_result)); \ + BUILD_BUG_ON(sizeof(exp_result10) >= string_get_size_maxbuf); \ + BUILD_BUG_ON(sizeof(exp_result2) >= string_get_size_maxbuf); \ + __test_string_get_size((size), (blk_size), (exp_result10), \ + (exp_result2)); \ } while (0) -static __init void __test_string_get_size(const u64 size, const u64 blk_size, - const enum string_size_units units, - const char *exp_result) +static __init void test_string_get_size_check(const char *units, + const char *exp, + char *res, + const u64 size, + const u64 blk_size) { - char buf[string_get_size_maxbuf]; - - string_get_size(size, blk_size, units, buf, sizeof(buf)); - if (!memcmp(buf, exp_result, strlen(exp_result) + 1)) + if (!memcmp(res, exp, strlen(exp) + 1)) return; - buf[sizeof(buf) - 1] = '\0'; - pr_warn("Test 'test_string_get_size_one' failed!\n"); - pr_warn("string_get_size(size = %llu, blk_size = %llu, units = %d\n", + res[string_get_size_maxbuf - 1] = '\0'; + + pr_warn("Test 'test_string_get_size' failed!\n"); + pr_warn("string_get_size(size = %llu, blk_size = %llu, units = %s)\n", size, blk_size, units); - pr_warn("expected: '%s', got '%s'\n", exp_result, buf); + pr_warn("expected: '%s', got '%s'\n", exp, res); +} + +static __init void __test_string_get_size(const u64 size, const u64 blk_size, + const char *exp_result10, + const char *exp_result2) +{ + char buf10[string_get_size_maxbuf]; + char buf2[string_get_size_maxbuf]; + + string_get_size(size, blk_size, STRING_UNITS_10, buf10, sizeof(buf10)); + string_get_size(size, blk_size, STRING_UNITS_2, buf2, sizeof(buf2)); + + test_string_get_size_check("STRING_UNITS_10", exp_result10, buf10, + size, blk_size); + + test_string_get_size_check("STRING_UNITS_2", exp_result2, buf2, + size, blk_size); } static __init void test_string_get_size(void) { - test_string_get_size_one(16384, 512, STRING_UNITS_2, "8.00 MiB"); - test_string_get_size_one(8192, 4096, STRING_UNITS_10, "32.7 MB"); - test_string_get_size_one(1, 512, STRING_UNITS_10, "512 B"); + /* small values */ + test_string_get_size_one(0, 512, "0 B", "0 B"); + test_string_get_size_one(1, 512, "512 B", "512 B"); + test_string_get_size_one(1100, 1, "1.10 kB", "1.07 KiB"); + + /* normal values */ + test_string_get_size_one(16384, 512, "8.39 MB", "8.00 MiB"); + test_string_get_size_one(500118192, 512, "256 GB", "238 GiB"); + test_string_get_size_one(8192, 4096, "33.6 MB", "32.0 MiB"); + + /* weird block sizes */ + test_string_get_size_one(3000, 1900, "5.70 MB", "5.44 MiB"); + + /* huge values */ + test_string_get_size_one(U64_MAX, 4096, "75.6 ZB", "64.0 ZiB"); + test_string_get_size_one(4096, U64_MAX, "75.6 ZB", "64.0 ZiB"); } static int __init test_string_helpers_init(void) @@ -430,10 +430,8 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) * Anon pages in shared mappings are surprising: now * just reject it. */ - if (!is_cow_mapping(vm_flags)) { - WARN_ON_ONCE(vm_flags & VM_MAYWRITE); + if (!is_cow_mapping(vm_flags)) return -EFAULT; - } } } else if (!(vm_flags & VM_READ)) { if (!(gup_flags & FOLL_FORCE)) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index fd3a07b3e6f4..36c070167b71 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -138,9 +138,6 @@ static struct khugepaged_scan khugepaged_scan = { .mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head), }; -static DEFINE_SPINLOCK(split_queue_lock); -static LIST_HEAD(split_queue); -static unsigned long split_queue_len; static struct shrinker deferred_split_shrinker; static void set_recommended_min_free_kbytes(void) @@ -861,7 +858,8 @@ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, return false; entry = mk_pmd(zero_page, vma->vm_page_prot); entry = pmd_mkhuge(entry); - pgtable_trans_huge_deposit(mm, pmd, pgtable); + if (pgtable) + pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, haddr, pmd, entry); atomic_long_inc(&mm->nr_ptes); return true; @@ -1039,13 +1037,15 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, spinlock_t *dst_ptl, *src_ptl; struct page *src_page; pmd_t pmd; - pgtable_t pgtable; + pgtable_t pgtable = NULL; int ret; - ret = -ENOMEM; - pgtable = pte_alloc_one(dst_mm, addr); - if (unlikely(!pgtable)) - goto out; + if (!vma_is_dax(vma)) { + ret = -ENOMEM; + pgtable = pte_alloc_one(dst_mm, addr); + if (unlikely(!pgtable)) + goto out; + } dst_ptl = pmd_lock(dst_mm, dst_pmd); src_ptl = pmd_lockptr(src_mm, src_pmd); @@ -1076,7 +1076,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, goto out_unlock; } - if (pmd_trans_huge(pmd)) { + if (!vma_is_dax(vma)) { /* thp accounting separate from pmd_devmap accounting */ src_page = pmd_page(pmd); VM_BUG_ON_PAGE(!PageHead(src_page), src_page); @@ -3358,6 +3358,7 @@ int total_mapcount(struct page *page) int split_huge_page_to_list(struct page *page, struct list_head *list) { struct page *head = compound_head(page); + struct pglist_data *pgdata = NODE_DATA(page_to_nid(head)); struct anon_vma *anon_vma; int count, mapcount, ret; bool mlocked; @@ -3401,19 +3402,19 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) lru_add_drain(); /* Prevent deferred_split_scan() touching ->_count */ - spin_lock_irqsave(&split_queue_lock, flags); + spin_lock_irqsave(&pgdata->split_queue_lock, flags); count = page_count(head); mapcount = total_mapcount(head); if (!mapcount && count == 1) { if (!list_empty(page_deferred_list(head))) { - split_queue_len--; + pgdata->split_queue_len--; list_del(page_deferred_list(head)); } - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); __split_huge_page(page, list); ret = 0; } else if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) { - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); pr_alert("total_mapcount: %u, page_count(): %u\n", mapcount, count); if (PageTail(page)) @@ -3421,7 +3422,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) dump_page(page, "total_mapcount(head) > 0"); BUG(); } else { - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); unfreeze_page(anon_vma, head); ret = -EBUSY; } @@ -3436,64 +3437,65 @@ out: void free_transhuge_page(struct page *page) { + struct pglist_data *pgdata = NODE_DATA(page_to_nid(page)); unsigned long flags; - spin_lock_irqsave(&split_queue_lock, flags); + spin_lock_irqsave(&pgdata->split_queue_lock, flags); if (!list_empty(page_deferred_list(page))) { - split_queue_len--; + pgdata->split_queue_len--; list_del(page_deferred_list(page)); } - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); free_compound_page(page); } void deferred_split_huge_page(struct page *page) { + struct pglist_data *pgdata = NODE_DATA(page_to_nid(page)); unsigned long flags; VM_BUG_ON_PAGE(!PageTransHuge(page), page); - spin_lock_irqsave(&split_queue_lock, flags); + spin_lock_irqsave(&pgdata->split_queue_lock, flags); if (list_empty(page_deferred_list(page))) { - list_add_tail(page_deferred_list(page), &split_queue); - split_queue_len++; + list_add_tail(page_deferred_list(page), &pgdata->split_queue); + pgdata->split_queue_len++; } - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); } static unsigned long deferred_split_count(struct shrinker *shrink, struct shrink_control *sc) { - /* - * Split a page from split_queue will free up at least one page, - * at most HPAGE_PMD_NR - 1. We don't track exact number. - * Let's use HPAGE_PMD_NR / 2 as ballpark. - */ - return ACCESS_ONCE(split_queue_len) * HPAGE_PMD_NR / 2; + struct pglist_data *pgdata = NODE_DATA(sc->nid); + return ACCESS_ONCE(pgdata->split_queue_len); } static unsigned long deferred_split_scan(struct shrinker *shrink, struct shrink_control *sc) { + struct pglist_data *pgdata = NODE_DATA(sc->nid); unsigned long flags; LIST_HEAD(list), *pos, *next; struct page *page; int split = 0; - spin_lock_irqsave(&split_queue_lock, flags); - list_splice_init(&split_queue, &list); - + spin_lock_irqsave(&pgdata->split_queue_lock, flags); /* Take pin on all head pages to avoid freeing them under us */ list_for_each_safe(pos, next, &list) { page = list_entry((void *)pos, struct page, mapping); page = compound_head(page); - /* race with put_compound_page() */ - if (!get_page_unless_zero(page)) { + if (get_page_unless_zero(page)) { + list_move(page_deferred_list(page), &list); + } else { + /* We lost race with put_compound_page() */ list_del_init(page_deferred_list(page)); - split_queue_len--; + pgdata->split_queue_len--; } + if (!--sc->nr_to_scan) + break; } - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); list_for_each_safe(pos, next, &list) { page = list_entry((void *)pos, struct page, mapping); @@ -3505,17 +3507,24 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, put_page(page); } - spin_lock_irqsave(&split_queue_lock, flags); - list_splice_tail(&list, &split_queue); - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_lock_irqsave(&pgdata->split_queue_lock, flags); + list_splice_tail(&list, &pgdata->split_queue); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); - return split * HPAGE_PMD_NR / 2; + /* + * Stop shrinker if we didn't split any page, but the queue is empty. + * This can happen if pages were freed under us. + */ + if (!split && list_empty(&pgdata->split_queue)) + return SHRINK_STOP; + return split; } static struct shrinker deferred_split_shrinker = { .count_objects = deferred_split_count, .scan_objects = deferred_split_scan, .seeks = DEFAULT_SEEKS, + .flags = SHRINKER_NUMA_AWARE, }; #ifdef CONFIG_DEBUG_FS diff --git a/mm/internal.h b/mm/internal.h index ed8b5ffcf9b1..a38a21ebddb4 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -216,6 +216,37 @@ static inline bool is_cow_mapping(vm_flags_t flags) return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; } +/* + * These three helpers classifies VMAs for virtual memory accounting. + */ + +/* + * Executable code area - executable, not writable, not stack + */ +static inline bool is_exec_mapping(vm_flags_t flags) +{ + return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC; +} + +/* + * Stack area - atomatically grows in one direction + * + * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous: + * do_mmap() forbids all other combinations. + */ +static inline bool is_stack_mapping(vm_flags_t flags) +{ + return (flags & VM_STACK) == VM_STACK; +} + +/* + * Data area - private, writable, not stack + */ +static inline bool is_data_mapping(vm_flags_t flags) +{ + return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE; +} + /* mm/util.c */ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, struct rb_node *rb_parent); diff --git a/mm/memory.c b/mm/memory.c index 93ce37989471..635451abc8f7 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2237,11 +2237,6 @@ static int wp_page_shared(struct mm_struct *mm, struct vm_area_struct *vma, page_cache_get(old_page); - /* - * Only catch write-faults on shared writable pages, - * read-only shared pages can get COWed by - * get_user_pages(.write=1, .force=1). - */ if (vma->vm_ops && vma->vm_ops->page_mkwrite) { int tmp; diff --git a/mm/mmap.c b/mm/mmap.c index 84b12624ceb0..cfc0cdca421e 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -42,6 +42,7 @@ #include <linux/memory.h> #include <linux/printk.h> #include <linux/userfaultfd_k.h> +#include <linux/moduleparam.h> #include <asm/uaccess.h> #include <asm/cacheflush.h> @@ -69,6 +70,8 @@ const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX; int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS; #endif +static bool ignore_rlimit_data = true; +core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644); static void unmap_region(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, @@ -2982,9 +2985,17 @@ bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, unsigned long npages) if (mm->total_vm + npages > rlimit(RLIMIT_AS) >> PAGE_SHIFT) return false; - if ((flags & (VM_WRITE | VM_SHARED | (VM_STACK_FLAGS & - (VM_GROWSUP | VM_GROWSDOWN)))) == VM_WRITE) - return mm->data_vm + npages <= rlimit(RLIMIT_DATA); + if (is_data_mapping(flags) && + mm->data_vm + npages > rlimit(RLIMIT_DATA) >> PAGE_SHIFT) { + if (ignore_rlimit_data) + pr_warn_once("%s (%d): VmData %lu exceed data ulimit " + "%lu. Will be forbidden soon.\n", + current->comm, current->pid, + (mm->data_vm + npages) << PAGE_SHIFT, + rlimit(RLIMIT_DATA)); + else + return false; + } return true; } @@ -2993,11 +3004,11 @@ void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages) { mm->total_vm += npages; - if ((flags & (VM_EXEC | VM_WRITE)) == VM_EXEC) + if (is_exec_mapping(flags)) mm->exec_vm += npages; - else if (flags & (VM_STACK_FLAGS & (VM_GROWSUP | VM_GROWSDOWN))) + else if (is_stack_mapping(flags)) mm->stack_vm += npages; - else if ((flags & (VM_WRITE | VM_SHARED)) == VM_WRITE) + else if (is_data_mapping(flags)) mm->data_vm += npages; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 63358d9f9aa9..ea2c4d3e0c03 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5210,6 +5210,11 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat) pgdat->numabalancing_migrate_nr_pages = 0; pgdat->numabalancing_migrate_next_window = jiffies; #endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + spin_lock_init(&pgdat->split_queue_lock); + INIT_LIST_HEAD(&pgdat->split_queue); + pgdat->split_queue_len = 0; +#endif init_waitqueue_head(&pgdat->kswapd_wait); init_waitqueue_head(&pgdat->pfmemalloc_wait); pgdat_page_ext_init(pgdat); diff --git a/mm/util.c b/mm/util.c index c108a6542d05..4fb14ca5a419 100644 --- a/mm/util.c +++ b/mm/util.c @@ -230,36 +230,11 @@ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, } /* Check if the vma is being used as a stack by this task */ -static int vm_is_stack_for_task(struct task_struct *t, - struct vm_area_struct *vma) +int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t) { return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t)); } -/* - * Check if the vma is being used as a stack. - * If is_group is non-zero, check in the entire thread group or else - * just check in the current task. Returns the task_struct of the task - * that the vma is stack for. Must be called under rcu_read_lock(). - */ -struct task_struct *task_of_stack(struct task_struct *task, - struct vm_area_struct *vma, bool in_group) -{ - if (vm_is_stack_for_task(task, vma)) - return task; - - if (in_group) { - struct task_struct *t; - - for_each_thread(task, t) { - if (vm_is_stack_for_task(t, vma)) - return t; - } - } - - return NULL; -} - #if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT) void arch_pick_mmap_layout(struct mm_struct *mm) { diff --git a/mm/vmpressure.c b/mm/vmpressure.c index 9a6c0704211c..149fdf6c5c56 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -248,9 +248,8 @@ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree, if (tree) { spin_lock(&vmpr->sr_lock); - vmpr->tree_scanned += scanned; + scanned = vmpr->tree_scanned += scanned; vmpr->tree_reclaimed += reclaimed; - scanned = vmpr->scanned; spin_unlock(&vmpr->sr_lock); if (scanned < vmpressure_win) diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 81a2eb77ba7f..05d815851be1 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -2068,6 +2068,15 @@ int intel_pt_process_auxtrace_info(union perf_event *event, err = -ENOMEM; goto err_free_queues; } + + /* + * Since this thread will not be kept in any rbtree not in a + * list, initialize its list node so that at thread__put() the + * current thread lifetime assuption is kept and we don't segfault + * at list_del_init(). + */ + INIT_LIST_HEAD(&pt->unknown_thread->node); + err = thread__set_comm(pt->unknown_thread, "unknown", 0); if (err) goto err_delete_thread; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 4f7b0efdde2f..813d9b272c81 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -399,6 +399,9 @@ static void tracepoint_error(struct parse_events_error *e, int err, { char help[BUFSIZ]; + if (!e) + return; + /* * We get error directly from syscall errno ( > 0), * or from encoded pointer's error ( < 0). diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 2be10fb27172..4ce5c5e18f48 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -686,8 +686,9 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf) pf->fb_ops = NULL; #if _ELFUTILS_PREREQ(0, 142) } else if (nops == 1 && pf->fb_ops[0].atom == DW_OP_call_frame_cfa && - pf->cfi != NULL) { - if (dwarf_cfi_addrframe(pf->cfi, pf->addr, &frame) != 0 || + (pf->cfi_eh != NULL || pf->cfi_dbg != NULL)) { + if ((dwarf_cfi_addrframe(pf->cfi_eh, pf->addr, &frame) != 0 && + (dwarf_cfi_addrframe(pf->cfi_dbg, pf->addr, &frame) != 0)) || dwarf_frame_cfa(frame, &pf->fb_ops, &nops) != 0) { pr_warning("Failed to get call frame on 0x%jx\n", (uintmax_t)pf->addr); @@ -1015,8 +1016,7 @@ static int pubname_search_cb(Dwarf *dbg, Dwarf_Global *gl, void *data) return DWARF_CB_OK; } -/* Find probe points from debuginfo */ -static int debuginfo__find_probes(struct debuginfo *dbg, +static int debuginfo__find_probe_location(struct debuginfo *dbg, struct probe_finder *pf) { struct perf_probe_point *pp = &pf->pev->point; @@ -1025,27 +1025,6 @@ static int debuginfo__find_probes(struct debuginfo *dbg, Dwarf_Die *diep; int ret = 0; -#if _ELFUTILS_PREREQ(0, 142) - Elf *elf; - GElf_Ehdr ehdr; - GElf_Shdr shdr; - - /* Get the call frame information from this dwarf */ - elf = dwarf_getelf(dbg->dbg); - if (elf == NULL) - return -EINVAL; - - if (gelf_getehdr(elf, &ehdr) == NULL) - return -EINVAL; - - if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) && - shdr.sh_type == SHT_PROGBITS) { - pf->cfi = dwarf_getcfi_elf(elf); - } else { - pf->cfi = dwarf_getcfi(dbg->dbg); - } -#endif - off = 0; pf->lcache = intlist__new(NULL); if (!pf->lcache) @@ -1108,6 +1087,39 @@ found: return ret; } +/* Find probe points from debuginfo */ +static int debuginfo__find_probes(struct debuginfo *dbg, + struct probe_finder *pf) +{ + int ret = 0; + +#if _ELFUTILS_PREREQ(0, 142) + Elf *elf; + GElf_Ehdr ehdr; + GElf_Shdr shdr; + + if (pf->cfi_eh || pf->cfi_dbg) + return debuginfo__find_probe_location(dbg, pf); + + /* Get the call frame information from this dwarf */ + elf = dwarf_getelf(dbg->dbg); + if (elf == NULL) + return -EINVAL; + + if (gelf_getehdr(elf, &ehdr) == NULL) + return -EINVAL; + + if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) && + shdr.sh_type == SHT_PROGBITS) + pf->cfi_eh = dwarf_getcfi_elf(elf); + + pf->cfi_dbg = dwarf_getcfi(dbg->dbg); +#endif + + ret = debuginfo__find_probe_location(dbg, pf); + return ret; +} + struct local_vars_finder { struct probe_finder *pf; struct perf_probe_arg *args; diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index bed82716e1b4..0aec7704e395 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -76,7 +76,10 @@ struct probe_finder { /* For variable searching */ #if _ELFUTILS_PREREQ(0, 142) - Dwarf_CFI *cfi; /* Call Frame Information */ + /* Call Frame Information from .eh_frame */ + Dwarf_CFI *cfi_eh; + /* Call Frame Information from .debug_frame */ + Dwarf_CFI *cfi_dbg; #endif Dwarf_Op *fb_ops; /* Frame base attribute */ struct perf_probe_arg *pvar; /* Current target variable */ diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index beeed0bd3bee..4d9b481cf3b6 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -311,6 +311,16 @@ int perf_stat_process_counter(struct perf_stat_config *config, aggr->val = aggr->ena = aggr->run = 0; + /* + * We calculate counter's data every interval, + * and the display code shows ps->res_stats + * avg value. We need to zero the stats for + * interval mode, otherwise overall avg running + * averages will be shown for each interval. + */ + if (config->interval) + init_stats(ps->res_stats); + if (counter->per_pkg) zero_per_pkg(counter); |