diff options
51 files changed, 439 insertions, 232 deletions
diff --git a/.get_maintainer.ignore b/.get_maintainer.ignore index a64d21913745..c298bab3d320 100644 --- a/.get_maintainer.ignore +++ b/.get_maintainer.ignore @@ -1,2 +1,4 @@ +Alan Cox <alan@lxorguk.ukuu.org.uk> +Alan Cox <root@hraefn.swansea.linux.org.uk> Christoph Hellwig <hch@lst.de> Marc Gonzalez <marc.w.gonzalez@free.fr> diff --git a/MAINTAINERS b/MAINTAINERS index 9d7f64dc0efe..96f47a7865d6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9781,7 +9781,7 @@ M: Christian Brauner <brauner@kernel.org> M: Seth Forshee <sforshee@kernel.org> L: linux-fsdevel@vger.kernel.org S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux.git +T: git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping.git F: Documentation/filesystems/idmappings.rst F: tools/testing/selftests/mount_setattr/ F: include/linux/mnt_idmapping.h diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 7f059cd1196a..9aede2447011 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -146,10 +146,10 @@ menu "Processor type and features" choice prompt "Processor type" - default PA7000 + default PA7000 if "$(ARCH)" = "parisc" config PA7000 - bool "PA7000/PA7100" + bool "PA7000/PA7100" if "$(ARCH)" = "parisc" help This is the processor type of your CPU. This information is used for optimizing purposes. In order to compile a kernel @@ -160,21 +160,21 @@ config PA7000 which is required on some machines. config PA7100LC - bool "PA7100LC" + bool "PA7100LC" if "$(ARCH)" = "parisc" help Select this option for the PCX-L processor, as used in the 712, 715/64, 715/80, 715/100, 715/100XC, 725/100, 743, 748, D200, D210, D300, D310 and E-class config PA7200 - bool "PA7200" + bool "PA7200" if "$(ARCH)" = "parisc" help Select this option for the PCX-T' processor, as used in the C100, C110, J100, J110, J210XC, D250, D260, D350, D360, K100, K200, K210, K220, K400, K410 and K420 config PA7300LC - bool "PA7300LC" + bool "PA7300LC" if "$(ARCH)" = "parisc" help Select this option for the PCX-L2 processor, as used in the 744, A180, B132L, B160L, B180L, C132L, C160L, C180L, @@ -224,17 +224,8 @@ config MLONGCALLS Enabling this option will probably slow down your kernel. config 64BIT - bool "64-bit kernel" + def_bool "$(ARCH)" = "parisc64" depends on PA8X00 - help - Enable this if you want to support 64bit kernel on PA-RISC platform. - - At the moment, only people willing to use more than 2GB of RAM, - or having a 64bit-only capable PA-RISC machine should say Y here. - - Since there is no 64bit userland on PA-RISC, there is no point to - enable this option otherwise. The 64bit kernel is significantly bigger - and slower than the 32bit one. choice prompt "Kernel page size" diff --git a/arch/parisc/include/asm/bitops.h b/arch/parisc/include/asm/bitops.h index 56ffd260c669..0ec9cfc5131f 100644 --- a/arch/parisc/include/asm/bitops.h +++ b/arch/parisc/include/asm/bitops.h @@ -12,14 +12,6 @@ #include <asm/barrier.h> #include <linux/atomic.h> -/* compiler build environment sanity checks: */ -#if !defined(CONFIG_64BIT) && defined(__LP64__) -#error "Please use 'ARCH=parisc' to build the 32-bit kernel." -#endif -#if defined(CONFIG_64BIT) && !defined(__LP64__) -#error "Please use 'ARCH=parisc64' to build the 64-bit kernel." -#endif - /* See http://marc.theaimsgroup.com/?t=108826637900003 for discussion * on use of volatile and __*_bit() (set/clear/change): * *_bit() want use of volatile. diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S index e0a9e9657622..fd15fd4bbb61 100644 --- a/arch/parisc/kernel/head.S +++ b/arch/parisc/kernel/head.S @@ -22,7 +22,7 @@ #include <linux/init.h> #include <linux/pgtable.h> - .level PA_ASM_LEVEL + .level 1.1 __INITDATA ENTRY(boot_args) @@ -70,6 +70,47 @@ $bss_loop: stw,ma %arg2,4(%r1) stw,ma %arg3,4(%r1) +#if !defined(CONFIG_64BIT) && defined(CONFIG_PA20) + /* This 32-bit kernel was compiled for PA2.0 CPUs. Check current CPU + * and halt kernel if we detect a PA1.x CPU. */ + ldi 32,%r10 + mtctl %r10,%cr11 + .level 2.0 + mfctl,w %cr11,%r10 + .level 1.1 + comib,<>,n 0,%r10,$cpu_ok + + load32 PA(msg1),%arg0 + ldi msg1_end-msg1,%arg1 +$iodc_panic: + copy %arg0, %r10 + copy %arg1, %r11 + load32 PA(init_stack),%sp +#define MEM_CONS 0x3A0 + ldw MEM_CONS+32(%r0),%arg0 // HPA + ldi ENTRY_IO_COUT,%arg1 + ldw MEM_CONS+36(%r0),%arg2 // SPA + ldw MEM_CONS+8(%r0),%arg3 // layers + load32 PA(__bss_start),%r1 + stw %r1,-52(%sp) // arg4 + stw %r0,-56(%sp) // arg5 + stw %r10,-60(%sp) // arg6 = ptr to text + stw %r11,-64(%sp) // arg7 = len + stw %r0,-68(%sp) // arg8 + load32 PA(.iodc_panic_ret), %rp + ldw MEM_CONS+40(%r0),%r1 // ENTRY_IODC + bv,n (%r1) +.iodc_panic_ret: + b . /* wait endless with ... */ + or %r10,%r10,%r10 /* qemu idle sleep */ +msg1: .ascii "Can't boot kernel which was built for PA8x00 CPUs on this machine.\r\n" +msg1_end: + +$cpu_ok: +#endif + + .level PA_ASM_LEVEL + /* Initialize startup VM. Just map first 16/32 MB of memory */ load32 PA(swapper_pg_dir),%r4 mtctl %r4,%cr24 /* Initialize kernel root pointer */ diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c index bac581b5ecfc..e8a4d77cff53 100644 --- a/arch/parisc/kernel/unaligned.c +++ b/arch/parisc/kernel/unaligned.c @@ -93,7 +93,7 @@ #define R1(i) (((i)>>21)&0x1f) #define R2(i) (((i)>>16)&0x1f) #define R3(i) ((i)&0x1f) -#define FR3(i) ((((i)<<1)&0x1f)|(((i)>>6)&1)) +#define FR3(i) ((((i)&0x1f)<<1)|(((i)>>6)&1)) #define IM(i,n) (((i)>>1&((1<<(n-1))-1))|((i)&1?((0-1L)<<(n-1)):0)) #define IM5_2(i) IM((i)>>16,5) #define IM5_3(i) IM((i),5) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 92cb929a45b7..226ea76cc819 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1146,14 +1146,15 @@ static ssize_t bd_stat_show(struct device *dev, static ssize_t debug_stat_show(struct device *dev, struct device_attribute *attr, char *buf) { - int version = 2; + int version = 1; struct zram *zram = dev_to_zram(dev); ssize_t ret; down_read(&zram->init_lock); ret = scnprintf(buf, PAGE_SIZE, - "version: %d\n%8llu\n", + "version: %d\n%8llu %8llu\n", version, + (u64)atomic64_read(&zram->stats.writestall), (u64)atomic64_read(&zram->stats.miss_free)); up_read(&zram->init_lock); @@ -1351,7 +1352,7 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, { int ret = 0; unsigned long alloced_pages; - unsigned long handle = 0; + unsigned long handle = -ENOMEM; unsigned int comp_len = 0; void *src, *dst, *mem; struct zcomp_strm *zstrm; @@ -1369,6 +1370,7 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, } kunmap_atomic(mem); +compress_again: zstrm = zcomp_stream_get(zram->comp); src = kmap_atomic(page); ret = zcomp_compress(zstrm, src, &comp_len); @@ -1377,20 +1379,39 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, if (unlikely(ret)) { zcomp_stream_put(zram->comp); pr_err("Compression failed! err=%d\n", ret); + zs_free(zram->mem_pool, handle); return ret; } if (comp_len >= huge_class_size) comp_len = PAGE_SIZE; - - handle = zs_malloc(zram->mem_pool, comp_len, - __GFP_KSWAPD_RECLAIM | - __GFP_NOWARN | - __GFP_HIGHMEM | - __GFP_MOVABLE); - + /* + * handle allocation has 2 paths: + * a) fast path is executed with preemption disabled (for + * per-cpu streams) and has __GFP_DIRECT_RECLAIM bit clear, + * since we can't sleep; + * b) slow path enables preemption and attempts to allocate + * the page with __GFP_DIRECT_RECLAIM bit set. we have to + * put per-cpu compression stream and, thus, to re-do + * the compression once handle is allocated. + * + * if we have a 'non-null' handle here then we are coming + * from the slow path and handle has already been allocated. + */ + if (IS_ERR((void *)handle)) + handle = zs_malloc(zram->mem_pool, comp_len, + __GFP_KSWAPD_RECLAIM | + __GFP_NOWARN | + __GFP_HIGHMEM | + __GFP_MOVABLE); if (IS_ERR((void *)handle)) { zcomp_stream_put(zram->comp); + atomic64_inc(&zram->stats.writestall); + handle = zs_malloc(zram->mem_pool, comp_len, + GFP_NOIO | __GFP_HIGHMEM | + __GFP_MOVABLE); + if (!IS_ERR((void *)handle)) + goto compress_again; return PTR_ERR((void *)handle); } @@ -1948,6 +1969,7 @@ static int zram_add(void) if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE) blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX); + blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, zram->disk->queue); ret = device_add_disk(NULL, zram->disk, zram_disk_groups); if (ret) goto out_cleanup_disk; diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 158c91e54850..80c3b43b4828 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -81,6 +81,7 @@ struct zram_stats { atomic64_t huge_pages_since; /* no. of huge pages since zram set up */ atomic64_t pages_stored; /* no. of pages currently stored */ atomic_long_t max_used_pages; /* no. of maximum pages stored */ + atomic64_t writestall; /* no. of write slow paths */ atomic64_t miss_free; /* no. of missed free */ #ifdef CONFIG_ZRAM_WRITEBACK atomic64_t bd_count; /* no. of pages in backing device */ diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index f191a1f901ac..0eb6b617f709 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -630,7 +630,7 @@ static int __init dmi_smbios3_present(const u8 *buf) { if (memcmp(buf, "_SM3_", 5) == 0 && buf[6] < 32 && dmi_checksum(buf, buf[6])) { - dmi_ver = get_unaligned_be32(buf + 6) & 0xFFFFFF; + dmi_ver = get_unaligned_be24(buf + 7); dmi_num = 0; /* No longer specified */ dmi_len = get_unaligned_le32(buf + 12); dmi_base = get_unaligned_le64(buf + 16); diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig index 10c563999d3d..e63608834411 100644 --- a/drivers/mmc/host/Kconfig +++ b/drivers/mmc/host/Kconfig @@ -171,6 +171,7 @@ config MMC_SDHCI_OF_ASPEED config MMC_SDHCI_OF_ASPEED_TEST bool "Tests for the ASPEED SDHCI driver" if !KUNIT_ALL_TESTS depends on MMC_SDHCI_OF_ASPEED && KUNIT + depends on (MMC_SDHCI_OF_ASPEED=m || KUNIT=y) default KUNIT_ALL_TESTS help Enable KUnit tests for the ASPEED SDHCI driver. Select this diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c index 9be007c9420f..f223afe47d10 100644 --- a/drivers/parisc/ccio-dma.c +++ b/drivers/parisc/ccio-dma.c @@ -268,7 +268,7 @@ static int ioc_count; * Each bit can represent a number of pages. * LSbs represent lower addresses (IOVA's). * -* This was was copied from sba_iommu.c. Don't try to unify +* This was copied from sba_iommu.c. Don't try to unify * the two resource managers unless a way to have different * allocation policies is also adjusted. We'd like to avoid * I/O TLB thrashing by having resource allocation policy @@ -1380,15 +1380,17 @@ ccio_init_resource(struct resource *res, char *name, void __iomem *ioaddr) } } -static void __init ccio_init_resources(struct ioc *ioc) +static int __init ccio_init_resources(struct ioc *ioc) { struct resource *res = ioc->mmio_region; char *name = kmalloc(14, GFP_KERNEL); - + if (unlikely(!name)) + return -ENOMEM; snprintf(name, 14, "GSC Bus [%d/]", ioc->hw_path); ccio_init_resource(res, name, &ioc->ioc_regs->io_io_low); ccio_init_resource(res + 1, name, &ioc->ioc_regs->io_io_low_hv); + return 0; } static int new_ioc_area(struct resource *res, unsigned long size, @@ -1543,7 +1545,10 @@ static int __init ccio_probe(struct parisc_device *dev) return -ENOMEM; } ccio_ioc_init(ioc); - ccio_init_resources(ioc); + if (ccio_init_resources(ioc)) { + kfree(ioc); + return -ENOMEM; + } hppa_dma_ops = &ccio_ops; hba = kzalloc(sizeof(*hba), GFP_KERNEL); diff --git a/drivers/parisc/led.c b/drivers/parisc/led.c index 1e4a5663d011..d4be9d2ee74d 100644 --- a/drivers/parisc/led.c +++ b/drivers/parisc/led.c @@ -646,7 +646,7 @@ int lcd_print( const char *str ) cancel_delayed_work_sync(&led_task); /* copy display string to buffer for procfs */ - strlcpy(lcd_text, str, sizeof(lcd_text)); + strscpy(lcd_text, str, sizeof(lcd_text)); /* Set LCD Cursor to 1st character */ gsc_writeb(lcd_info.reset_cmd1, LCD_CMD_REG); diff --git a/fs/inode.c b/fs/inode.c index 6462276dfdf0..ba1de23c13c1 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2018,23 +2018,25 @@ static int __file_remove_privs(struct file *file, unsigned int flags) { struct dentry *dentry = file_dentry(file); struct inode *inode = file_inode(file); - int error; + int error = 0; int kill; if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode)) return 0; kill = dentry_needs_remove_privs(dentry); - if (kill <= 0) + if (kill < 0) return kill; - if (flags & IOCB_NOWAIT) - return -EAGAIN; + if (kill) { + if (flags & IOCB_NOWAIT) + return -EAGAIN; + + error = __remove_privs(file_mnt_user_ns(file), dentry, kill); + } - error = __remove_privs(file_mnt_user_ns(file), dentry, kill); if (!error) inode_has_no_xattr(inode); - return error; } diff --git a/fs/locks.c b/fs/locks.c index c266cfdc3291..607f94a0e789 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2129,6 +2129,7 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) else error = locks_lock_file_wait(f.file, &fl); + locks_release_private(&fl); out_putf: fdput(f); diff --git a/fs/namespace.c b/fs/namespace.c index 68789f896f08..df137ba19d37 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4238,6 +4238,13 @@ static int build_mount_idmapped(const struct mount_attr *attr, size_t usize, err = -EPERM; goto out_fput; } + + /* We're not controlling the target namespace. */ + if (!ns_capable(mnt_userns, CAP_SYS_ADMIN)) { + err = -EPERM; + goto out_fput; + } + kattr->mnt_userns = get_user_ns(mnt_userns); out_fput: diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index dbab3caa15ed..5d6c2ddc7ea6 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2382,7 +2382,8 @@ static void nfs_dentry_remove_handle_error(struct inode *dir, { switch (error) { case -ENOENT: - d_delete(dentry); + if (d_really_is_positive(dentry)) + d_delete(dentry); nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); break; case 0: @@ -2484,8 +2485,10 @@ int nfs_unlink(struct inode *dir, struct dentry *dentry) */ error = -ETXTBSY; if (WARN_ON(dentry->d_flags & DCACHE_NFSFS_RENAMED) || - WARN_ON(dentry->d_fsdata == NFS_FSDATA_BLOCKED)) + WARN_ON(dentry->d_fsdata == NFS_FSDATA_BLOCKED)) { + spin_unlock(&dentry->d_lock); goto out; + } if (dentry->d_fsdata) /* old devname */ kfree(dentry->d_fsdata); diff --git a/fs/nfs/file.c b/fs/nfs/file.c index d2bcd4834c0e..e032fe201a36 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -221,8 +221,10 @@ nfs_file_fsync_commit(struct file *file, int datasync) int nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) { - struct nfs_open_context *ctx = nfs_file_open_context(file); struct inode *inode = file_inode(file); + struct nfs_inode *nfsi = NFS_I(inode); + long save_nredirtied = atomic_long_read(&nfsi->redirtied_pages); + long nredirtied; int ret; trace_nfs_fsync_enter(inode); @@ -237,15 +239,10 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) ret = pnfs_sync_inode(inode, !!datasync); if (ret != 0) break; - if (!test_and_clear_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags)) + nredirtied = atomic_long_read(&nfsi->redirtied_pages); + if (nredirtied == save_nredirtied) break; - /* - * If nfs_file_fsync_commit detected a server reboot, then - * resend all dirty pages that might have been covered by - * the NFS_CONTEXT_RESEND_WRITES flag - */ - start = 0; - end = LLONG_MAX; + save_nredirtied = nredirtied; } trace_nfs_fsync_exit(inode, ret); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index b4e46b0ffa2d..bea7c005119c 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -426,6 +426,7 @@ nfs_ilookup(struct super_block *sb, struct nfs_fattr *fattr, struct nfs_fh *fh) static void nfs_inode_init_regular(struct nfs_inode *nfsi) { atomic_long_set(&nfsi->nrequests, 0); + atomic_long_set(&nfsi->redirtied_pages, 0); INIT_LIST_HEAD(&nfsi->commit_info.list); atomic_long_set(&nfsi->commit_info.ncommit, 0); atomic_set(&nfsi->commit_info.rpcs_out, 0); diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index e88f6b18445e..9eb181287879 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -340,6 +340,11 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt, goto out; } + if (!S_ISREG(fattr->mode)) { + res = ERR_PTR(-EBADF); + goto out; + } + res = ERR_PTR(-ENOMEM); len = strlen(SSC_READ_NAME_BODY) + 16; read_name = kzalloc(len, GFP_KERNEL); @@ -357,6 +362,7 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt, r_ino->i_fop); if (IS_ERR(filep)) { res = ERR_CAST(filep); + iput(r_ino); goto out_free_name; } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 41a9b6b58fb9..2613b7e36eb9 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -2817,7 +2817,6 @@ int pnfs_write_done_resend_to_mds(struct nfs_pgio_header *hdr) /* Resend all requests through the MDS */ nfs_pageio_init_write(&pgio, hdr->inode, FLUSH_STABLE, true, hdr->completion_ops); - set_bit(NFS_CONTEXT_RESEND_WRITES, &hdr->args.context->flags); return nfs_pageio_resend(&pgio, hdr); } EXPORT_SYMBOL_GPL(pnfs_write_done_resend_to_mds); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 51a7e202d6e5..1843fa235d9b 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1420,10 +1420,12 @@ static void nfs_initiate_write(struct nfs_pgio_header *hdr, */ static void nfs_redirty_request(struct nfs_page *req) { + struct nfs_inode *nfsi = NFS_I(page_file_mapping(req->wb_page)->host); + /* Bump the transmission count */ req->wb_nio++; nfs_mark_request_dirty(req); - set_bit(NFS_CONTEXT_RESEND_WRITES, &nfs_req_openctx(req)->flags); + atomic_long_inc(&nfsi->redirtied_pages); nfs_end_page_writeback(req); nfs_release_request(req); } @@ -1904,7 +1906,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) /* We have a mismatch. Write the page again */ dprintk_cont(" mismatch\n"); nfs_mark_request_dirty(req); - set_bit(NFS_CONTEXT_RESEND_WRITES, &nfs_req_openctx(req)->flags); + atomic_long_inc(&NFS_I(data->inode)->redirtied_pages); next: nfs_unlock_and_release_request(req); /* Latency breaker */ diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index 5bdff12a1232..6ae1f56b7358 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -483,8 +483,7 @@ out: } #ifdef CONFIG_NTFS3_FS_POSIX_ACL -static struct posix_acl *ntfs_get_acl_ex(struct user_namespace *mnt_userns, - struct inode *inode, int type, +static struct posix_acl *ntfs_get_acl_ex(struct inode *inode, int type, int locked) { struct ntfs_inode *ni = ntfs_i(inode); @@ -519,7 +518,7 @@ static struct posix_acl *ntfs_get_acl_ex(struct user_namespace *mnt_userns, /* Translate extended attribute to acl. */ if (err >= 0) { - acl = posix_acl_from_xattr(mnt_userns, buf, err); + acl = posix_acl_from_xattr(&init_user_ns, buf, err); } else if (err == -ENODATA) { acl = NULL; } else { @@ -542,8 +541,7 @@ struct posix_acl *ntfs_get_acl(struct inode *inode, int type, bool rcu) if (rcu) return ERR_PTR(-ECHILD); - /* TODO: init_user_ns? */ - return ntfs_get_acl_ex(&init_user_ns, inode, type, 0); + return ntfs_get_acl_ex(inode, type, 0); } static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns, @@ -595,7 +593,7 @@ static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns, value = kmalloc(size, GFP_NOFS); if (!value) return -ENOMEM; - err = posix_acl_to_xattr(mnt_userns, acl, value, size); + err = posix_acl_to_xattr(&init_user_ns, acl, value, size); if (err < 0) goto out; flags = 0; @@ -646,7 +644,7 @@ static int ntfs_xattr_get_acl(struct user_namespace *mnt_userns, if (!acl) return -ENODATA; - err = posix_acl_to_xattr(mnt_userns, acl, buffer, size); + err = posix_acl_to_xattr(&init_user_ns, acl, buffer, size); posix_acl_release(acl); return err; @@ -670,12 +668,12 @@ static int ntfs_xattr_set_acl(struct user_namespace *mnt_userns, if (!value) { acl = NULL; } else { - acl = posix_acl_from_xattr(mnt_userns, value, size); + acl = posix_acl_from_xattr(&init_user_ns, value, size); if (IS_ERR(acl)) return PTR_ERR(acl); if (acl) { - err = posix_acl_valid(mnt_userns, acl); + err = posix_acl_valid(&init_user_ns, acl); if (err) goto release_and_out; } diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index b45fea69fff3..0fbcb590af84 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -460,9 +460,12 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) * of the POSIX ACLs retrieved from the lower layer to this function to not * alter the POSIX ACLs for the underlying filesystem. */ -static void ovl_idmap_posix_acl(struct user_namespace *mnt_userns, +static void ovl_idmap_posix_acl(struct inode *realinode, + struct user_namespace *mnt_userns, struct posix_acl *acl) { + struct user_namespace *fs_userns = i_user_ns(realinode); + for (unsigned int i = 0; i < acl->a_count; i++) { vfsuid_t vfsuid; vfsgid_t vfsgid; @@ -470,11 +473,11 @@ static void ovl_idmap_posix_acl(struct user_namespace *mnt_userns, struct posix_acl_entry *e = &acl->a_entries[i]; switch (e->e_tag) { case ACL_USER: - vfsuid = make_vfsuid(mnt_userns, &init_user_ns, e->e_uid); + vfsuid = make_vfsuid(mnt_userns, fs_userns, e->e_uid); e->e_uid = vfsuid_into_kuid(vfsuid); break; case ACL_GROUP: - vfsgid = make_vfsgid(mnt_userns, &init_user_ns, e->e_gid); + vfsgid = make_vfsgid(mnt_userns, fs_userns, e->e_gid); e->e_gid = vfsgid_into_kgid(vfsgid); break; } @@ -536,7 +539,7 @@ struct posix_acl *ovl_get_acl(struct inode *inode, int type, bool rcu) if (!clone) clone = ERR_PTR(-ENOMEM); else - ovl_idmap_posix_acl(mnt_user_ns(realpath.mnt), clone); + ovl_idmap_posix_acl(realinode, mnt_user_ns(realpath.mnt), clone); /* * Since we're not in RCU path walk we always need to release the * original ACLs. diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 1d17d7b13dcd..5af33800743e 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -361,6 +361,7 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode, const struct posix_acl *acl, int want) { const struct posix_acl_entry *pa, *pe, *mask_obj; + struct user_namespace *fs_userns = i_user_ns(inode); int found = 0; vfsuid_t vfsuid; vfsgid_t vfsgid; @@ -376,7 +377,7 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode, goto check_perm; break; case ACL_USER: - vfsuid = make_vfsuid(mnt_userns, &init_user_ns, + vfsuid = make_vfsuid(mnt_userns, fs_userns, pa->e_uid); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) goto mask; @@ -390,7 +391,7 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode, } break; case ACL_GROUP: - vfsgid = make_vfsgid(mnt_userns, &init_user_ns, + vfsgid = make_vfsgid(mnt_userns, fs_userns, pa->e_gid); if (vfsgid_in_group_p(vfsgid)) { found = 1; @@ -736,6 +737,7 @@ void posix_acl_getxattr_idmapped_mnt(struct user_namespace *mnt_userns, { struct posix_acl_xattr_header *header = value; struct posix_acl_xattr_entry *entry = (void *)(header + 1), *end; + struct user_namespace *fs_userns = i_user_ns(inode); int count; vfsuid_t vfsuid; vfsgid_t vfsgid; @@ -753,13 +755,13 @@ void posix_acl_getxattr_idmapped_mnt(struct user_namespace *mnt_userns, switch (le16_to_cpu(entry->e_tag)) { case ACL_USER: uid = make_kuid(&init_user_ns, le32_to_cpu(entry->e_id)); - vfsuid = make_vfsuid(mnt_userns, &init_user_ns, uid); + vfsuid = make_vfsuid(mnt_userns, fs_userns, uid); entry->e_id = cpu_to_le32(from_kuid(&init_user_ns, vfsuid_into_kuid(vfsuid))); break; case ACL_GROUP: gid = make_kgid(&init_user_ns, le32_to_cpu(entry->e_id)); - vfsgid = make_vfsgid(mnt_userns, &init_user_ns, gid); + vfsgid = make_vfsgid(mnt_userns, fs_userns, gid); entry->e_id = cpu_to_le32(from_kgid(&init_user_ns, vfsgid_into_kgid(vfsgid))); break; @@ -775,6 +777,7 @@ void posix_acl_setxattr_idmapped_mnt(struct user_namespace *mnt_userns, { struct posix_acl_xattr_header *header = value; struct posix_acl_xattr_entry *entry = (void *)(header + 1), *end; + struct user_namespace *fs_userns = i_user_ns(inode); int count; vfsuid_t vfsuid; vfsgid_t vfsgid; @@ -793,13 +796,13 @@ void posix_acl_setxattr_idmapped_mnt(struct user_namespace *mnt_userns, case ACL_USER: uid = make_kuid(&init_user_ns, le32_to_cpu(entry->e_id)); vfsuid = VFSUIDT_INIT(uid); - uid = from_vfsuid(mnt_userns, &init_user_ns, vfsuid); + uid = from_vfsuid(mnt_userns, fs_userns, vfsuid); entry->e_id = cpu_to_le32(from_kuid(&init_user_ns, uid)); break; case ACL_GROUP: gid = make_kgid(&init_user_ns, le32_to_cpu(entry->e_id)); vfsgid = VFSGIDT_INIT(gid); - gid = from_vfsgid(mnt_userns, &init_user_ns, vfsgid); + gid = from_vfsgid(mnt_userns, fs_userns, vfsgid); entry->e_id = cpu_to_le32(from_kgid(&init_user_ns, gid)); break; default: diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index a3398d0f1927..4e0023643f8b 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -527,10 +527,12 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, struct vm_area_struct *vma = walk->vma; bool locked = !!(vma->vm_flags & VM_LOCKED); struct page *page = NULL; - bool migration = false; + bool migration = false, young = false, dirty = false; if (pte_present(*pte)) { page = vm_normal_page(vma, addr, *pte); + young = pte_young(*pte); + dirty = pte_dirty(*pte); } else if (is_swap_pte(*pte)) { swp_entry_t swpent = pte_to_swp_entry(*pte); @@ -560,8 +562,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, if (!page) return; - smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte), - locked, migration); + smaps_account(mss, page, false, young, dirty, locked, migration); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 1c44bf75f916..175de70e3adf 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1601,6 +1601,10 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range); } + /* Reset ptes for the whole vma range if wr-protected */ + if (userfaultfd_wp(vma)) + uffd_wp_range(mm, vma, start, vma_end - start, false); + new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index ed53bfe7c46c..ac5d0515680e 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -734,11 +734,6 @@ static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) return NULL; } -static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) -{ - return NULL; -} - static inline bool cgroup_psi_enabled(void) { return false; diff --git a/include/linux/mm.h b/include/linux/mm.h index 3bedc449c14d..982f2607180b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2885,7 +2885,6 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */ #define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */ #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ -#define FOLL_COW 0x4000 /* internal GUP flag */ #define FOLL_ANON 0x8000 /* don't do file mappings */ #define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */ #define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index b32ed68e7dc4..7931fa472561 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -83,7 +83,6 @@ struct nfs_open_context { fmode_t mode; unsigned long flags; -#define NFS_CONTEXT_RESEND_WRITES (1) #define NFS_CONTEXT_BAD (2) #define NFS_CONTEXT_UNLOCK (3) #define NFS_CONTEXT_FILE_OPEN (4) @@ -182,6 +181,7 @@ struct nfs_inode { /* Regular file */ struct { atomic_long_t nrequests; + atomic_long_t redirtied_pages; struct nfs_mds_commit_info commit_info; struct mutex commit_mutex; }; diff --git a/include/linux/psi.h b/include/linux/psi.h index 89784763d19e..dd74411ac21d 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -27,7 +27,7 @@ void psi_memstall_leave(unsigned long *flags); int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); struct psi_trigger *psi_trigger_create(struct psi_group *group, - char *buf, size_t nbytes, enum psi_res res); + char *buf, enum psi_res res); void psi_trigger_destroy(struct psi_trigger *t); __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 1b6c4013f691..ff0b990de83d 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -29,15 +29,10 @@ struct shmem_inode_info { struct inode vfs_inode; }; -#define SHMEM_FL_USER_VISIBLE FS_FL_USER_VISIBLE -#define SHMEM_FL_USER_MODIFIABLE FS_FL_USER_MODIFIABLE -#define SHMEM_FL_INHERITED FS_FL_USER_MODIFIABLE - -/* Flags that are appropriate for regular files (all but dir-specific ones). */ -#define SHMEM_REG_FLMASK (~(FS_DIRSYNC_FL | FS_TOPDIR_FL)) - -/* Flags that are appropriate for non-directories/regular files. */ -#define SHMEM_OTHER_FLMASK (FS_NODUMP_FL | FS_NOATIME_FL) +#define SHMEM_FL_USER_VISIBLE FS_FL_USER_VISIBLE +#define SHMEM_FL_USER_MODIFIABLE \ + (FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NODUMP_FL | FS_NOATIME_FL) +#define SHMEM_FL_INHERITED (FS_NODUMP_FL | FS_NOATIME_FL) struct shmem_sb_info { unsigned long max_blocks; /* How many blocks are allowed */ diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 732b522bacb7..e1b8a915e9e9 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -73,6 +73,8 @@ extern ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long dst_start, extern int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, unsigned long len, bool enable_wp, atomic_t *mmap_changing); +extern void uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *vma, + unsigned long start, unsigned long len, bool enable_wp); /* mm helpers */ static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 404024486fa5..f3fc36cd2276 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -20,12 +20,19 @@ #define HIGHMEM_ZONE(xx) #endif -#define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL, HIGHMEM_ZONE(xx) xx##_MOVABLE +#ifdef CONFIG_ZONE_DEVICE +#define DEVICE_ZONE(xx) xx##_DEVICE, +#else +#define DEVICE_ZONE(xx) +#endif + +#define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL, \ + HIGHMEM_ZONE(xx) xx##_MOVABLE, DEVICE_ZONE(xx) enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, - FOR_ALL_ZONES(PGALLOC), - FOR_ALL_ZONES(ALLOCSTALL), - FOR_ALL_ZONES(PGSCAN_SKIP), + FOR_ALL_ZONES(PGALLOC) + FOR_ALL_ZONES(ALLOCSTALL) + FOR_ALL_ZONES(PGSCAN_SKIP) PGFREE, PGACTIVATE, PGDEACTIVATE, PGLAZYFREE, PGFAULT, PGMAJFAULT, PGLAZYFREED, diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c index 6432a37ac1c9..c565fbf66ac8 100644 --- a/kernel/audit_fsnotify.c +++ b/kernel/audit_fsnotify.c @@ -102,6 +102,7 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa ret = fsnotify_add_inode_mark(&audit_mark->mark, inode, 0); if (ret < 0) { + audit_mark->path = NULL; fsnotify_put_mark(&audit_mark->mark); audit_mark = ERR_PTR(ret); } diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index ffaccd6373f1..e4bb5d57f4d1 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1820,6 +1820,7 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) if (ss->css_rstat_flush) { list_del_rcu(&css->rstat_css_node); + synchronize_rcu(); list_add_rcu(&css->rstat_css_node, &dcgrp->rstat_css_list); } @@ -2370,6 +2371,47 @@ int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) EXPORT_SYMBOL_GPL(task_cgroup_path); /** + * cgroup_attach_lock - Lock for ->attach() + * @lock_threadgroup: whether to down_write cgroup_threadgroup_rwsem + * + * cgroup migration sometimes needs to stabilize threadgroups against forks and + * exits by write-locking cgroup_threadgroup_rwsem. However, some ->attach() + * implementations (e.g. cpuset), also need to disable CPU hotplug. + * Unfortunately, letting ->attach() operations acquire cpus_read_lock() can + * lead to deadlocks. + * + * Bringing up a CPU may involve creating and destroying tasks which requires + * read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside + * cpus_read_lock(). If we call an ->attach() which acquires the cpus lock while + * write-locking threadgroup_rwsem, the locking order is reversed and we end up + * waiting for an on-going CPU hotplug operation which in turn is waiting for + * the threadgroup_rwsem to be released to create new tasks. For more details: + * + * http://lkml.kernel.org/r/20220711174629.uehfmqegcwn2lqzu@wubuntu + * + * Resolve the situation by always acquiring cpus_read_lock() before optionally + * write-locking cgroup_threadgroup_rwsem. This allows ->attach() to assume that + * CPU hotplug is disabled on entry. + */ +static void cgroup_attach_lock(bool lock_threadgroup) +{ + cpus_read_lock(); + if (lock_threadgroup) + percpu_down_write(&cgroup_threadgroup_rwsem); +} + +/** + * cgroup_attach_unlock - Undo cgroup_attach_lock() + * @lock_threadgroup: whether to up_write cgroup_threadgroup_rwsem + */ +static void cgroup_attach_unlock(bool lock_threadgroup) +{ + if (lock_threadgroup) + percpu_up_write(&cgroup_threadgroup_rwsem); + cpus_read_unlock(); +} + +/** * cgroup_migrate_add_task - add a migration target task to a migration context * @task: target task * @mgctx: target migration context @@ -2841,8 +2883,7 @@ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, } struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, - bool *locked) - __acquires(&cgroup_threadgroup_rwsem) + bool *threadgroup_locked) { struct task_struct *tsk; pid_t pid; @@ -2859,12 +2900,8 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, * Therefore, we can skip the global lock. */ lockdep_assert_held(&cgroup_mutex); - if (pid || threadgroup) { - percpu_down_write(&cgroup_threadgroup_rwsem); - *locked = true; - } else { - *locked = false; - } + *threadgroup_locked = pid || threadgroup; + cgroup_attach_lock(*threadgroup_locked); rcu_read_lock(); if (pid) { @@ -2895,17 +2932,14 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, goto out_unlock_rcu; out_unlock_threadgroup: - if (*locked) { - percpu_up_write(&cgroup_threadgroup_rwsem); - *locked = false; - } + cgroup_attach_unlock(*threadgroup_locked); + *threadgroup_locked = false; out_unlock_rcu: rcu_read_unlock(); return tsk; } -void cgroup_procs_write_finish(struct task_struct *task, bool locked) - __releases(&cgroup_threadgroup_rwsem) +void cgroup_procs_write_finish(struct task_struct *task, bool threadgroup_locked) { struct cgroup_subsys *ss; int ssid; @@ -2913,8 +2947,8 @@ void cgroup_procs_write_finish(struct task_struct *task, bool locked) /* release reference from cgroup_procs_write_start() */ put_task_struct(task); - if (locked) - percpu_up_write(&cgroup_threadgroup_rwsem); + cgroup_attach_unlock(threadgroup_locked); + for_each_subsys(ss, ssid) if (ss->post_attach) ss->post_attach(); @@ -3000,8 +3034,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) * write-locking can be skipped safely. */ has_tasks = !list_empty(&mgctx.preloaded_src_csets); - if (has_tasks) - percpu_down_write(&cgroup_threadgroup_rwsem); + cgroup_attach_lock(has_tasks); /* NULL dst indicates self on default hierarchy */ ret = cgroup_migrate_prepare_dst(&mgctx); @@ -3022,8 +3055,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) ret = cgroup_migrate_execute(&mgctx); out_finish: cgroup_migrate_finish(&mgctx); - if (has_tasks) - percpu_up_write(&cgroup_threadgroup_rwsem); + cgroup_attach_unlock(has_tasks); return ret; } @@ -3698,7 +3730,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, } psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; - new = psi_trigger_create(psi, buf, nbytes, res); + new = psi_trigger_create(psi, buf, res); if (IS_ERR(new)) { cgroup_put(cgrp); return PTR_ERR(new); @@ -4971,13 +5003,13 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, struct task_struct *task; const struct cred *saved_cred; ssize_t ret; - bool locked; + bool threadgroup_locked; dst_cgrp = cgroup_kn_lock_live(of->kn, false); if (!dst_cgrp) return -ENODEV; - task = cgroup_procs_write_start(buf, threadgroup, &locked); + task = cgroup_procs_write_start(buf, threadgroup, &threadgroup_locked); ret = PTR_ERR_OR_ZERO(task); if (ret) goto out_unlock; @@ -5003,7 +5035,7 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, ret = cgroup_attach_task(dst_cgrp, task, threadgroup); out_finish: - cgroup_procs_write_finish(task, locked); + cgroup_procs_write_finish(task, threadgroup_locked); out_unlock: cgroup_kn_unlock(of->kn); diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 58aadfda9b8b..1f3a55297f39 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -2289,7 +2289,7 @@ static void cpuset_attach(struct cgroup_taskset *tset) cgroup_taskset_first(tset, &css); cs = css_cs(css); - cpus_read_lock(); + lockdep_assert_cpus_held(); /* see cgroup_attach_lock() */ percpu_down_write(&cpuset_rwsem); guarantee_online_mems(cs, &cpuset_attach_nodemask_to); @@ -2343,7 +2343,6 @@ static void cpuset_attach(struct cgroup_taskset *tset) wake_up(&cpuset_attach_wq); percpu_up_write(&cpuset_rwsem); - cpus_read_unlock(); } /* The various types of files and directories in a cpuset file system */ diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 80697e5e03e4..08350e35aba2 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1707,11 +1707,12 @@ static struct kprobe *__disable_kprobe(struct kprobe *p) /* Try to disarm and disable this/parent probe */ if (p == orig_p || aggr_kprobe_disabled(orig_p)) { /* - * If 'kprobes_all_disarmed' is set, 'orig_p' - * should have already been disarmed, so - * skip unneed disarming process. + * Don't be lazy here. Even if 'kprobes_all_disarmed' + * is false, 'orig_p' might not have been armed yet. + * Note arm_all_kprobes() __tries__ to arm all kprobes + * on the best effort basis. */ - if (!kprobes_all_disarmed) { + if (!kprobes_all_disarmed && !kprobe_disabled(orig_p)) { ret = disarm_kprobe(orig_p, true); if (ret) { p->flags &= ~KPROBE_FLAG_DISABLED; diff --git a/kernel/module/main.c b/kernel/module/main.c index 6a477c622544..a4e4d84b6f4e 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2099,7 +2099,7 @@ static int find_module_sections(struct module *mod, struct load_info *info) sizeof(*mod->static_call_sites), &mod->num_static_call_sites); #endif -#ifdef CONFIG_KUNIT +#if IS_ENABLED(CONFIG_KUNIT) mod->kunit_suites = section_objs(info, ".kunit_test_suites", sizeof(*mod->kunit_suites), &mod->num_kunit_suites); diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index ec66b40bdd40..ecb4b4ff4ce0 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -190,12 +190,8 @@ static void group_init(struct psi_group *group) /* Init trigger-related members */ mutex_init(&group->trigger_lock); INIT_LIST_HEAD(&group->triggers); - memset(group->nr_triggers, 0, sizeof(group->nr_triggers)); - group->poll_states = 0; group->poll_min_period = U32_MAX; - memset(group->polling_total, 0, sizeof(group->polling_total)); group->polling_next_update = ULLONG_MAX; - group->polling_until = 0; init_waitqueue_head(&group->poll_wait); timer_setup(&group->poll_timer, poll_timer_fn, 0); rcu_assign_pointer(group->poll_task, NULL); @@ -957,7 +953,7 @@ int psi_cgroup_alloc(struct cgroup *cgroup) if (static_branch_likely(&psi_disabled)) return 0; - cgroup->psi = kmalloc(sizeof(struct psi_group), GFP_KERNEL); + cgroup->psi = kzalloc(sizeof(struct psi_group), GFP_KERNEL); if (!cgroup->psi) return -ENOMEM; @@ -1091,7 +1087,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) } struct psi_trigger *psi_trigger_create(struct psi_group *group, - char *buf, size_t nbytes, enum psi_res res) + char *buf, enum psi_res res) { struct psi_trigger *t; enum psi_states state; @@ -1320,7 +1316,7 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf, return -EBUSY; } - new = psi_trigger_create(&psi_system, buf, nbytes, res); + new = psi_trigger_create(&psi_system, buf, res); if (IS_ERR(new)) { mutex_unlock(&seq->lock); return PTR_ERR(new); diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index a492f159624f..860b2dcf3ac4 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -277,6 +277,7 @@ COND_SYSCALL(landlock_restrict_self); /* mm/fadvise.c */ COND_SYSCALL(fadvise64_64); +COND_SYSCALL_COMPAT(fadvise64_64); /* mm/, CONFIG_MMU only */ COND_SYSCALL(swapon); @@ -478,14 +478,42 @@ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address, return -EEXIST; } -/* - * FOLL_FORCE can write to even unwritable pte's, but only - * after we've gone through a COW cycle and they are dirty. - */ -static inline bool can_follow_write_pte(pte_t pte, unsigned int flags) +/* FOLL_FORCE can write to even unwritable PTEs in COW mappings. */ +static inline bool can_follow_write_pte(pte_t pte, struct page *page, + struct vm_area_struct *vma, + unsigned int flags) { - return pte_write(pte) || - ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte)); + /* If the pte is writable, we can write to the page. */ + if (pte_write(pte)) + return true; + + /* Maybe FOLL_FORCE is set to override it? */ + if (!(flags & FOLL_FORCE)) + return false; + + /* But FOLL_FORCE has no effect on shared mappings */ + if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) + return false; + + /* ... or read-only private ones */ + if (!(vma->vm_flags & VM_MAYWRITE)) + return false; + + /* ... or already writable ones that just need to take a write fault */ + if (vma->vm_flags & VM_WRITE) + return false; + + /* + * See can_change_pte_writable(): we broke COW and could map the page + * writable if we have an exclusive anonymous page ... + */ + if (!page || !PageAnon(page) || !PageAnonExclusive(page)) + return false; + + /* ... and a write-fault isn't required for other reasons. */ + if (vma_soft_dirty_enabled(vma) && !pte_soft_dirty(pte)) + return false; + return !userfaultfd_pte_wp(vma, pte); } static struct page *follow_page_pte(struct vm_area_struct *vma, @@ -528,12 +556,19 @@ retry: } if ((flags & FOLL_NUMA) && pte_protnone(pte)) goto no_page; - if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) { - pte_unmap_unlock(ptep, ptl); - return NULL; - } page = vm_normal_page(vma, address, pte); + + /* + * We only care about anon pages in can_follow_write_pte() and don't + * have to worry about pte_devmap() because they are never anon. + */ + if ((flags & FOLL_WRITE) && + !can_follow_write_pte(pte, page, vma, flags)) { + page = NULL; + goto out; + } + if (!page && pte_devmap(pte) && (flags & (FOLL_GET | FOLL_PIN))) { /* * Only return device mapping pages in the FOLL_GET or FOLL_PIN @@ -986,17 +1021,6 @@ static int faultin_page(struct vm_area_struct *vma, return -EBUSY; } - /* - * The VM_FAULT_WRITE bit tells us that do_wp_page has broken COW when - * necessary, even if maybe_mkwrite decided not to set pte_write. We - * can thus safely do subsequent page lookups as if they were reads. - * But only do so when looping for pte_write is futile: in some cases - * userspace may also be wanting to write to the gotten user page, - * which a read fault here might prevent (a readonly page might get - * reCOWed by userspace write). - */ - if ((ret & VM_FAULT_WRITE) && !(vma->vm_flags & VM_WRITE)) - *flags |= FOLL_COW; return 0; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 8a7c1b344abe..e9414ee57c5b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1040,12 +1040,6 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, assert_spin_locked(pmd_lockptr(mm, pmd)); - /* - * When we COW a devmap PMD entry, we split it into PTEs, so we should - * not be in this function with `flags & FOLL_COW` set. - */ - WARN_ONCE(flags & FOLL_COW, "mm: In follow_devmap_pmd with FOLL_COW set"); - /* FOLL_GET and FOLL_PIN are mutually exclusive. */ if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) @@ -1395,14 +1389,42 @@ fallback: return VM_FAULT_FALLBACK; } -/* - * FOLL_FORCE can write to even unwritable pmd's, but only - * after we've gone through a COW cycle and they are dirty. - */ -static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags) +/* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */ +static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page, + struct vm_area_struct *vma, + unsigned int flags) { - return pmd_write(pmd) || - ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd)); + /* If the pmd is writable, we can write to the page. */ + if (pmd_write(pmd)) + return true; + + /* Maybe FOLL_FORCE is set to override it? */ + if (!(flags & FOLL_FORCE)) + return false; + + /* But FOLL_FORCE has no effect on shared mappings */ + if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) + return false; + + /* ... or read-only private ones */ + if (!(vma->vm_flags & VM_MAYWRITE)) + return false; + + /* ... or already writable ones that just need to take a write fault */ + if (vma->vm_flags & VM_WRITE) + return false; + + /* + * See can_change_pte_writable(): we broke COW and could map the page + * writable if we have an exclusive anonymous page ... + */ + if (!page || !PageAnon(page) || !PageAnonExclusive(page)) + return false; + + /* ... and a write-fault isn't required for other reasons. */ + if (vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd)) + return false; + return !userfaultfd_huge_pmd_wp(vma, pmd); } struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, @@ -1411,12 +1433,16 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned int flags) { struct mm_struct *mm = vma->vm_mm; - struct page *page = NULL; + struct page *page; assert_spin_locked(pmd_lockptr(mm, pmd)); - if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, flags)) - goto out; + page = pmd_page(*pmd); + VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page); + + if ((flags & FOLL_WRITE) && + !can_follow_write_pmd(*pmd, page, vma, flags)) + return NULL; /* Avoid dumping huge zero page */ if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd)) @@ -1424,10 +1450,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, /* Full NUMA hinting faults to serialise migration in fault paths */ if ((flags & FOLL_NUMA) && pmd_protnone(*pmd)) - goto out; - - page = pmd_page(*pmd); - VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page); + return NULL; if (!pmd_write(*pmd) && gup_must_unshare(flags, page)) return ERR_PTR(-EMLINK); @@ -1444,7 +1467,6 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page); -out: return page; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 0aee2f3ae15c..2480ba627aa5 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5241,6 +5241,21 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma, VM_BUG_ON(unshare && (flags & FOLL_WRITE)); VM_BUG_ON(!unshare && !(flags & FOLL_WRITE)); + /* + * hugetlb does not support FOLL_FORCE-style write faults that keep the + * PTE mapped R/O such as maybe_mkwrite() would do. + */ + if (WARN_ON_ONCE(!unshare && !(vma->vm_flags & VM_WRITE))) + return VM_FAULT_SIGSEGV; + + /* Let's take out MAP_SHARED mappings first. */ + if (vma->vm_flags & VM_MAYSHARE) { + if (unlikely(unshare)) + return 0; + set_huge_ptep_writable(vma, haddr, ptep); + return 0; + } + pte = huge_ptep_get(ptep); old_page = pte_page(pte); @@ -5781,12 +5796,11 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, * If we are going to COW/unshare the mapping later, we examine the * pending reservations for this page now. This will ensure that any * allocations necessary to record that reservation occur outside the - * spinlock. For private mappings, we also lookup the pagecache - * page now as it is used to determine if a reservation has been - * consumed. + * spinlock. Also lookup the pagecache page now as it is used to + * determine if a reservation has been consumed. */ if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && - !huge_pte_write(entry)) { + !(vma->vm_flags & VM_MAYSHARE) && !huge_pte_write(entry)) { if (vma_needs_reservation(h, vma, haddr) < 0) { ret = VM_FAULT_OOM; goto out_mutex; @@ -5794,9 +5808,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, /* Just decrements count, does not deallocate */ vma_end_reservation(h, vma, haddr); - if (!(vma->vm_flags & VM_MAYSHARE)) - pagecache_page = hugetlbfs_pagecache_page(h, - vma, haddr); + pagecache_page = hugetlbfs_pagecache_page(h, vma, haddr); } ptl = huge_pte_lock(h, mm, ptep); diff --git a/mm/mmap.c b/mm/mmap.c index c035020d0c89..9d780f415be3 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1646,8 +1646,11 @@ int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) pgprot_val(vm_pgprot_modify(vm_page_prot, vm_flags))) return 0; - /* Do we need to track softdirty? */ - if (vma_soft_dirty_enabled(vma)) + /* + * Do we need to track softdirty? hugetlb does not support softdirty + * tracking yet. + */ + if (vma_soft_dirty_enabled(vma) && !is_vm_hugetlb_page(vma)) return 1; /* Specialty mapping? */ diff --git a/mm/shmem.c b/mm/shmem.c index 5783f11351bb..d075dd2dcc48 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1659,7 +1659,9 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, new = page_folio(newpage); mem_cgroup_migrate(old, new); __inc_lruvec_page_state(newpage, NR_FILE_PAGES); + __inc_lruvec_page_state(newpage, NR_SHMEM); __dec_lruvec_page_state(oldpage, NR_FILE_PAGES); + __dec_lruvec_page_state(oldpage, NR_SHMEM); } xa_unlock_irq(&swap_mapping->i_pages); @@ -2281,16 +2283,34 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma) return 0; } -/* Mask out flags that are inappropriate for the given type of inode. */ -static unsigned shmem_mask_flags(umode_t mode, __u32 flags) +#ifdef CONFIG_TMPFS_XATTR +static int shmem_initxattrs(struct inode *, const struct xattr *, void *); + +/* + * chattr's fsflags are unrelated to extended attributes, + * but tmpfs has chosen to enable them under the same config option. + */ +static void shmem_set_inode_flags(struct inode *inode, unsigned int fsflags) +{ + unsigned int i_flags = 0; + + if (fsflags & FS_NOATIME_FL) + i_flags |= S_NOATIME; + if (fsflags & FS_APPEND_FL) + i_flags |= S_APPEND; + if (fsflags & FS_IMMUTABLE_FL) + i_flags |= S_IMMUTABLE; + /* + * But FS_NODUMP_FL does not require any action in i_flags. + */ + inode_set_flags(inode, i_flags, S_NOATIME | S_APPEND | S_IMMUTABLE); +} +#else +static void shmem_set_inode_flags(struct inode *inode, unsigned int fsflags) { - if (S_ISDIR(mode)) - return flags; - else if (S_ISREG(mode)) - return flags & SHMEM_REG_FLMASK; - else - return flags & SHMEM_OTHER_FLMASK; } +#define shmem_initxattrs NULL +#endif static struct inode *shmem_get_inode(struct super_block *sb, struct inode *dir, umode_t mode, dev_t dev, unsigned long flags) @@ -2319,7 +2339,8 @@ static struct inode *shmem_get_inode(struct super_block *sb, struct inode *dir, info->i_crtime = inode->i_mtime; info->fsflags = (dir == NULL) ? 0 : SHMEM_I(dir)->fsflags & SHMEM_FL_INHERITED; - info->fsflags = shmem_mask_flags(mode, info->fsflags); + if (info->fsflags) + shmem_set_inode_flags(inode, info->fsflags); INIT_LIST_HEAD(&info->shrinklist); INIT_LIST_HEAD(&info->swaplist); simple_xattrs_init(&info->xattrs); @@ -2468,12 +2489,6 @@ out_unacct_blocks: static const struct inode_operations shmem_symlink_inode_operations; static const struct inode_operations shmem_short_symlink_operations; -#ifdef CONFIG_TMPFS_XATTR -static int shmem_initxattrs(struct inode *, const struct xattr *, void *); -#else -#define shmem_initxattrs NULL -#endif - static int shmem_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, @@ -2826,12 +2841,13 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) i_size_write(inode, offset + len); - inode->i_ctime = current_time(inode); undone: spin_lock(&inode->i_lock); inode->i_private = NULL; spin_unlock(&inode->i_lock); out: + if (!error) + file_modified(file); inode_unlock(inode); return error; } @@ -3179,18 +3195,13 @@ static int shmem_fileattr_set(struct user_namespace *mnt_userns, if (fileattr_has_fsx(fa)) return -EOPNOTSUPP; + if (fa->flags & ~SHMEM_FL_USER_MODIFIABLE) + return -EOPNOTSUPP; info->fsflags = (info->fsflags & ~SHMEM_FL_USER_MODIFIABLE) | (fa->flags & SHMEM_FL_USER_MODIFIABLE); - inode->i_flags &= ~(S_APPEND | S_IMMUTABLE | S_NOATIME); - if (info->fsflags & FS_APPEND_FL) - inode->i_flags |= S_APPEND; - if (info->fsflags & FS_IMMUTABLE_FL) - inode->i_flags |= S_IMMUTABLE; - if (info->fsflags & FS_NOATIME_FL) - inode->i_flags |= S_NOATIME; - + shmem_set_inode_flags(inode, info->fsflags); inode->i_ctime = current_time(inode); return 0; } diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 07d3befc80e4..7327b2573f7c 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -703,14 +703,29 @@ ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long start, mmap_changing, 0); } +void uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma, + unsigned long start, unsigned long len, bool enable_wp) +{ + struct mmu_gather tlb; + pgprot_t newprot; + + if (enable_wp) + newprot = vm_get_page_prot(dst_vma->vm_flags & ~(VM_WRITE)); + else + newprot = vm_get_page_prot(dst_vma->vm_flags); + + tlb_gather_mmu(&tlb, dst_mm); + change_protection(&tlb, dst_vma, start, start + len, newprot, + enable_wp ? MM_CP_UFFD_WP : MM_CP_UFFD_WP_RESOLVE); + tlb_finish_mmu(&tlb); +} + int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, unsigned long len, bool enable_wp, atomic_t *mmap_changing) { struct vm_area_struct *dst_vma; unsigned long page_mask; - struct mmu_gather tlb; - pgprot_t newprot; int err; /* @@ -750,15 +765,7 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, goto out_unlock; } - if (enable_wp) - newprot = vm_get_page_prot(dst_vma->vm_flags & ~(VM_WRITE)); - else - newprot = vm_get_page_prot(dst_vma->vm_flags); - - tlb_gather_mmu(&tlb, dst_mm); - change_protection(&tlb, dst_vma, start, start + len, newprot, - enable_wp ? MM_CP_UFFD_WP : MM_CP_UFFD_WP_RESOLVE); - tlb_finish_mmu(&tlb); + uffd_wp_range(dst_mm, dst_vma, start, len, enable_wp); err = 0; out_unlock: diff --git a/mm/vmstat.c b/mm/vmstat.c index 373d2730fcf2..90af9a8572f5 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1168,8 +1168,15 @@ int fragmentation_index(struct zone *zone, unsigned int order) #define TEXT_FOR_HIGHMEM(xx) #endif +#ifdef CONFIG_ZONE_DEVICE +#define TEXT_FOR_DEVICE(xx) xx "_device", +#else +#define TEXT_FOR_DEVICE(xx) +#endif + #define TEXTS_FOR_ZONES(xx) TEXT_FOR_DMA(xx) TEXT_FOR_DMA32(xx) xx "_normal", \ - TEXT_FOR_HIGHMEM(xx) xx "_movable", + TEXT_FOR_HIGHMEM(xx) xx "_movable", \ + TEXT_FOR_DEVICE(xx) const char * const vmstat_text[] = { /* enum zone_stat_item counters */ diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index b098e707ad41..7d268a291486 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1902,7 +1902,7 @@ call_encode(struct rpc_task *task) break; case -EKEYEXPIRED: if (!task->tk_cred_retry) { - rpc_exit(task, task->tk_status); + rpc_call_rpcerror(task, task->tk_status); } else { task->tk_action = call_refresh; task->tk_cred_retry--; diff --git a/tools/include/linux/compiler_types.h b/tools/include/linux/compiler_types.h index 24ae3054f304..1bdd834bdd57 100644 --- a/tools/include/linux/compiler_types.h +++ b/tools/include/linux/compiler_types.h @@ -36,4 +36,8 @@ #include <linux/compiler-gcc.h> #endif +#ifndef asm_volatile_goto +#define asm_volatile_goto(x...) asm goto(x) +#endif + #endif /* __LINUX_COMPILER_TYPES_H */ diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 947fc72413e9..d44c72b3abe3 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -40,6 +40,7 @@ ifeq (0,$(MAKELEVEL)) endif endif selfdir = $(realpath $(dir $(filter %/lib.mk,$(MAKEFILE_LIST)))) +top_srcdir = $(selfdir)/../../.. # The following are built by lib.mk common compile rules. # TEST_CUSTOM_PROGS should be used by tests that require diff --git a/tools/testing/selftests/sgx/sigstruct.c b/tools/testing/selftests/sgx/sigstruct.c index 50c5ab1aa6fa..a07896a46364 100644 --- a/tools/testing/selftests/sgx/sigstruct.c +++ b/tools/testing/selftests/sgx/sigstruct.c @@ -17,6 +17,12 @@ #include "defines.h" #include "main.h" +/* + * FIXME: OpenSSL 3.0 has deprecated some functions. For now just ignore + * the warnings. + */ +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + struct q1q2_ctx { BN_CTX *bn_ctx; BIGNUM *m; |