diff --git a/Documentation/filesystems/erofs.txt b/Documentation/filesystems/erofs.txt new file mode 100644 index 000000000000..38aa9126ec98 --- /dev/null +++ b/Documentation/filesystems/erofs.txt @@ -0,0 +1,219 @@ +Overview +======== + +EROFS file-system stands for Enhanced Read-Only File System. Different +from other read-only file systems, it aims to be designed for flexibility, +scalability, but be kept simple and high performance. + +It is designed as a better filesystem solution for the following scenarios: + - read-only storage media or + + - part of a fully trusted read-only solution, which means it needs to be + immutable and bit-for-bit identical to the official golden image for + their releases due to security and other considerations and + + - hope to save some extra storage space with guaranteed end-to-end performance + by using reduced metadata and transparent file compression, especially + for those embedded devices with limited memory (ex, smartphone); + +Here is the main features of EROFS: + - Little endian on-disk design; + + - Currently 4KB block size (nobh) and therefore maximum 16TB address space; + + - Metadata & data could be mixed by design; + + - 2 inode versions for different requirements: + v1 v2 + Inode metadata size: 32 bytes 64 bytes + Max file size: 4 GB 16 EB (also limited by max. vol size) + Max uids/gids: 65536 4294967296 + File creation time: no yes (64 + 32-bit timestamp) + Max hardlinks: 65536 4294967296 + Metadata reserved: 4 bytes 14 bytes + + - Support extended attributes (xattrs) as an option; + + - Support xattr inline and tail-end data inline for all files; + + - Support POSIX.1e ACLs by using xattrs; + + - Support transparent file compression as an option: + LZ4 algorithm with 4 KB fixed-output compression for high performance; + +The following git tree provides the file system user-space tools under +development (ex, formatting tool mkfs.erofs): +>> git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs-utils.git + +Bugs and patches are welcome, please kindly help us and send to the following +linux-erofs mailing list: +>> linux-erofs mailing list + +Mount options +============= + +fault_injection=%d Enable fault injection in all supported types with + specified injection rate. Supported injection type: + Type_Name Type_Value + FAULT_KMALLOC 0x000000001 + FAULT_READ_IO 0x000000002 +(no)user_xattr Setup Extended User Attributes. Note: xattr is enabled + by default if CONFIG_EROFS_FS_XATTR is selected. +(no)acl Setup POSIX Access Control List. Note: acl is enabled + by default if CONFIG_EROFS_FS_POSIX_ACL is selected. +cache_strategy=%s Select a strategy for cached decompression from now on: + disabled: In-place I/O decompression only; + readahead: Cache the last incomplete compressed physical + cluster for further reading. It still does + in-place I/O decompression for the rest + compressed physical clusters; + readaround: Cache the both ends of incomplete compressed + physical clusters for further reading. + It still does in-place I/O decompression + for the rest compressed physical clusters. + +Module parameters +================= +use_vmap=[0|1] Use vmap() instead of vm_map_ram() (default 0). + +On-disk details +=============== + +Summary +------- +Different from other read-only file systems, an EROFS volume is designed +to be as simple as possible: + + |-> aligned with the block size + ____________________________________________________________ + | |SB| | ... | Metadata | ... | Data | Metadata | ... | Data | + |_|__|_|_____|__________|_____|______|__________|_____|______| + 0 +1K + +All data areas should be aligned with the block size, but metadata areas +may not. All metadatas can be now observed in two different spaces (views): + 1. Inode metadata space + Each valid inode should be aligned with an inode slot, which is a fixed + value (32 bytes) and designed to be kept in line with v1 inode size. + + Each inode can be directly found with the following formula: + inode offset = meta_blkaddr * block_size + 32 * nid + + |-> aligned with 8B + |-> followed closely + + meta_blkaddr blocks |-> another slot + _____________________________________________________________________ + | ... | inode | xattrs | extents | data inline | ... | inode ... + |________|_______|(optional)|(optional)|__(optional)_|_____|__________ + |-> aligned with the inode slot size + . . + . . + . . + . . + . . + . . + .____________________________________________________|-> aligned with 4B + | xattr_ibody_header | shared xattrs | inline xattrs | + |____________________|_______________|_______________| + |-> 12 bytes <-|->x * 4 bytes<-| . + . . . + . . . + . . . + ._______________________________.______________________. + | id | id | id | id | ... | id | ent | ... | ent| ... | + |____|____|____|____|______|____|_____|_____|____|_____| + |-> aligned with 4B + |-> aligned with 4B + + Inode could be 32 or 64 bytes, which can be distinguished from a common + field which all inode versions have -- i_advise: + + __________________ __________________ + | i_advise | | i_advise | + |__________________| |__________________| + | ... | | ... | + | | | | + |__________________| 32 bytes | | + | | + |__________________| 64 bytes + + Xattrs, extents, data inline are followed by the corresponding inode with + proper alignes, and they could be optional for different data mappings, + _currently_ there are totally 3 valid data mappings supported: + + 1) flat file data without data inline (no extent); + 2) fixed-output size data compression (must have extents); + 3) flat file data with tail-end data inline (no extent); + + The size of the optional xattrs is indicated by i_xattr_count in inode + header. Large xattrs or xattrs shared by many different files can be + stored in shared xattrs metadata rather than inlined right after inode. + + 2. Shared xattrs metadata space + Shared xattrs space is similar to the above inode space, started with + a specific block indicated by xattr_blkaddr, organized one by one with + proper align. + + Each share xattr can also be directly found by the following formula: + xattr offset = xattr_blkaddr * block_size + 4 * xattr_id + + |-> aligned by 4 bytes + + xattr_blkaddr blocks |-> aligned with 4 bytes + _________________________________________________________________________ + | ... | xattr_entry | xattr data | ... | xattr_entry | xattr data ... + |________|_____________|_____________|_____|______________|_______________ + +Directories +----------- +All directories are now organized in a compact on-disk format. Note that +each directory block is divided into index and name areas in order to support +random file lookup, and all directory entries are _strictly_ recorded in +alphabetical order in order to support improved prefix binary search +algorithm (could refer to the related source code). + + ___________________________ + / | + / ______________|________________ + / / | nameoff1 | nameoffN-1 + ____________.______________._______________v________________v__________ +| dirent | dirent | ... | dirent | filename | filename | ... | filename | +|___.0___|____1___|_____|___N-1__|____0_____|____1_____|_____|___N-1____| + \ ^ + \ | * could have + \ | trailing '\0' + \________________________| nameoff0 + + Directory block + +Note that apart from the offset of the first filename, nameoff0 also indicates +the total number of directory entries in this block since it is no need to +introduce another on-disk field at all. + +Compression +----------- +Currently, EROFS supports 4KB fixed-output clustersize transparent file +compression, as illustrated below: + + |---- Variant-Length Extent ----|-------- VLE --------|----- VLE ----- + clusterofs clusterofs clusterofs + | | | logical data +_________v_______________________________v_____________________v_______________ +... | . | | . | | . | ... +____|____.________|_____________|________.____|_____________|__.__________|____ + |-> cluster <-|-> cluster <-|-> cluster <-|-> cluster <-|-> cluster <-| + size size size size size + . . . . + . . . . + . . . . + _______._____________._____________._____________._____________________ + ... | | | | ... physical data + _______|_____________|_____________|_____________|_____________________ + |-> cluster <-|-> cluster <-|-> cluster <-| + size size size + +Currently each on-disk physical cluster can contain 4KB (un)compressed data +at most. For each logical cluster, there is a corresponding on-disk index to +describe its cluster type, physical cluster address, etc. + +See "struct z_erofs_vle_decompressed_index" in erofs_fs.h for more details. + diff --git a/MAINTAINERS b/MAINTAINERS index 75aec8d6f154..65dd8fc47008 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5488,6 +5488,16 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/kristoffer/linux-hpc.git F: drivers/video/fbdev/s1d13xxxfb.c F: include/video/s1d13xxxfb.h +EROFS FILE SYSTEM +M: Gao Xiang +M: Chao Yu +L: linux-erofs@lists.ozlabs.org +S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs.git +F: Documentation/filesystems/erofs.txt +F: fs/erofs/ +F: include/trace/events/erofs.h + ERRSEQ ERROR TRACKING INFRASTRUCTURE M: Jeff Layton S: Maintained @@ -13829,13 +13839,6 @@ M: H Hartley Sweeten S: Odd Fixes F: drivers/staging/comedi/ -STAGING - EROFS FILE SYSTEM -M: Gao Xiang -M: Chao Yu -L: linux-erofs@lists.ozlabs.org -S: Maintained -F: drivers/staging/erofs/ - STAGING - FLARION FT1000 DRIVERS M: Marek Belisko S: Odd Fixes diff --git a/arch/arm64/configs/gki_defconfig b/arch/arm64/configs/gki_defconfig index b094b4f26a2d..d43010fc8dea 100644 --- a/arch/arm64/configs/gki_defconfig +++ b/arch/arm64/configs/gki_defconfig @@ -438,6 +438,9 @@ CONFIG_TMPFS_POSIX_ACL=y CONFIG_PSTORE=y CONFIG_PSTORE_CONSOLE=y CONFIG_PSTORE_RAM=y +CONFIG_EROFS_FS=y +CONFIG_EROFS_FS_PCPU_KTHREAD=y +CONFIG_EROFS_FS_PCPU_KTHREAD_HIPRI=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_CODEPAGE_737=y CONFIG_NLS_CODEPAGE_775=y diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index 906b7c882587..82f264621845 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -127,10 +127,10 @@ static unsigned long f_extend(unsigned long address) #ifdef CONFIG_64BIT if(unlikely(parisc_narrow_firmware)) { if((address & 0xff000000) == 0xf0000000) - return 0xf0f0f0f000000000UL | (u32)address; + return (0xfffffff0UL << 32) | (u32)address; if((address & 0xf0000000) == 0xf0000000) - return 0xffffffff00000000UL | (u32)address; + return (0xffffffffUL << 32) | (u32)address; } #endif return address; diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 6f1e57182876..f0aa6fc8c6b2 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -21,8 +21,8 @@ obj-$(CONFIG_PPC32) += div64.o copy_32.o crtsavres.o strlen_32.o # 64-bit linker creates .sfpr on demand for final link (vmlinux), # so it is only needed for modules, and only for older linkers which # do not support --save-restore-funcs -ifeq ($(call ld-ifversion, -lt, 225000000, y),y) -always-$(CONFIG_PPC64) += crtsavres.o +ifeq ($(call ld-ifversion, -lt, 225000000, y)$(CONFIG_PPC64),yy) +always += crtsavres.o endif obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \ diff --git a/arch/x86/configs/gki_defconfig b/arch/x86/configs/gki_defconfig index 95288e35d135..32390caf4b8e 100644 --- a/arch/x86/configs/gki_defconfig +++ b/arch/x86/configs/gki_defconfig @@ -373,6 +373,9 @@ CONFIG_TMPFS_POSIX_ACL=y CONFIG_PSTORE=y CONFIG_PSTORE_CONSOLE=y CONFIG_PSTORE_RAM=y +CONFIG_EROFS_FS=y +CONFIG_EROFS_FS_PCPU_KTHREAD=y +CONFIG_EROFS_FS_PCPU_KTHREAD_HIPRI=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_CODEPAGE_737=y CONFIG_NLS_CODEPAGE_775=y diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 84667781c41d..5b75a4ff6802 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -271,15 +271,6 @@ static void init_amd_k6(struct cpuinfo_x86 *c) return; } #endif - /* - * Work around Erratum 1386. The XSAVES instruction malfunctions in - * certain circumstances on Zen1/2 uarch, and not all parts have had - * updated microcode at the time of writing (March 2023). - * - * Affected parts all have no supervisor XSAVE states, meaning that - * the XSAVEC instruction (which works fine) is equivalent. - */ - clear_cpu_cap(c, X86_FEATURE_XSAVES); } static void init_amd_k7(struct cpuinfo_x86 *c) @@ -979,6 +970,17 @@ static void init_amd_zn(struct cpuinfo_x86 *c) if (c->x86 == 0x19 && !cpu_has(c, X86_FEATURE_BTC_NO)) set_cpu_cap(c, X86_FEATURE_BTC_NO); } + + /* + * Work around Erratum 1386. The XSAVES instruction malfunctions in + * certain circumstances on Zen1/2 uarch, and not all parts have had + * updated microcode at the time of writing (March 2023). + * + * Affected parts all have no supervisor XSAVE states, meaning that + * the XSAVEC instruction (which works fine) is equivalent. + */ + if (c->x86 == 0x17) + clear_cpu_cap(c, X86_FEATURE_XSAVES); } static bool cpu_has_zenbleed_microcode(void) diff --git a/block/bio.c b/block/bio.c index 74e646154517..de7a82f57fae 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1596,8 +1596,7 @@ void bio_set_pages_dirty(struct bio *bio) int i; bio_for_each_segment_all(bvec, bio, i) { - if (!PageCompound(bvec->bv_page)) - set_page_dirty_lock(bvec->bv_page); + set_page_dirty_lock(bvec->bv_page); } } EXPORT_SYMBOL_GPL(bio_set_pages_dirty); @@ -1656,7 +1655,7 @@ void bio_check_pages_dirty(struct bio *bio) int i; bio_for_each_segment_all(bvec, bio, i) { - if (!PageDirty(bvec->bv_page) && !PageCompound(bvec->bv_page)) + if (!PageDirty(bvec->bv_page)) goto defer; } diff --git a/crypto/algapi.c b/crypto/algapi.c index c95abdcad84b..4653ff4705d3 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -236,6 +236,7 @@ static struct crypto_larval *__crypto_register_alg(struct crypto_alg *alg) } if (!strcmp(q->cra_driver_name, alg->cra_name) || + !strcmp(q->cra_driver_name, alg->cra_driver_name) || !strcmp(q->cra_name, alg->cra_driver_name)) goto err; } diff --git a/drivers/base/core.c b/drivers/base/core.c index 18b08b4cb760..56ce64e9b926 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -3805,6 +3805,50 @@ define_dev_printk_level(_dev_info, KERN_INFO); #endif +/** + * dev_err_probe - probe error check and log helper + * @dev: the pointer to the struct device + * @err: error value to test + * @fmt: printf-style format string + * @...: arguments as specified in the format string + * + * This helper implements common pattern present in probe functions for error + * checking: print debug or error message depending if the error value is + * -EPROBE_DEFER and propagate error upwards. + * It replaces code sequence:: + * if (err != -EPROBE_DEFER) + * dev_err(dev, ...); + * else + * dev_dbg(dev, ...); + * return err; + * + * with:: + * + * return dev_err_probe(dev, err, ...); + * + * Returns @err. + * + */ +int dev_err_probe(const struct device *dev, int err, const char *fmt, ...) +{ + struct va_format vaf; + va_list args; + + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + + if (err != -EPROBE_DEFER) + dev_err(dev, "error %pe: %pV", ERR_PTR(err), &vaf); + else + dev_dbg(dev, "error %pe: %pV", ERR_PTR(err), &vaf); + + va_end(args); + + return err; +} +EXPORT_SYMBOL_GPL(dev_err_probe); + static inline bool fwnode_is_primary(struct fwnode_handle *fwnode) { return fwnode && !IS_ERR(fwnode->secondary); diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c index c9757fa2d308..d932dd95b04e 100644 --- a/drivers/char/hw_random/core.c +++ b/drivers/char/hw_random/core.c @@ -24,10 +24,13 @@ #include #include #include +#include #include #define RNG_MODULE_NAME "hw_random" +#define RNG_BUFFER_SIZE (SMP_CACHE_BYTES < 32 ? 32 : SMP_CACHE_BYTES) + static struct hwrng *current_rng; /* the current rng has been explicitly chosen by user via sysfs */ static int cur_rng_set_by_user; @@ -59,7 +62,7 @@ static inline int rng_get_data(struct hwrng *rng, u8 *buffer, size_t size, static size_t rng_buffer_size(void) { - return SMP_CACHE_BYTES < 32 ? 32 : SMP_CACHE_BYTES; + return RNG_BUFFER_SIZE; } static void add_early_randomness(struct hwrng *rng) @@ -202,6 +205,7 @@ static inline int rng_get_data(struct hwrng *rng, u8 *buffer, size_t size, static ssize_t rng_dev_read(struct file *filp, char __user *buf, size_t size, loff_t *offp) { + u8 buffer[RNG_BUFFER_SIZE]; ssize_t ret = 0; int err = 0; int bytes_read, len; @@ -229,34 +233,37 @@ static ssize_t rng_dev_read(struct file *filp, char __user *buf, if (bytes_read < 0) { err = bytes_read; goto out_unlock_reading; - } - data_avail = bytes_read; - } - - if (!data_avail) { - if (filp->f_flags & O_NONBLOCK) { + } else if (bytes_read == 0 && + (filp->f_flags & O_NONBLOCK)) { err = -EAGAIN; goto out_unlock_reading; } - } else { - len = data_avail; + + data_avail = bytes_read; + } + + len = data_avail; + if (len) { if (len > size) len = size; data_avail -= len; - if (copy_to_user(buf + ret, rng_buffer + data_avail, - len)) { + memcpy(buffer, rng_buffer + data_avail, len); + } + mutex_unlock(&reading_mutex); + put_rng(rng); + + if (len) { + if (copy_to_user(buf + ret, buffer, len)) { err = -EFAULT; - goto out_unlock_reading; + goto out; } size -= len; ret += len; } - mutex_unlock(&reading_mutex); - put_rng(rng); if (need_resched()) schedule_timeout_interruptible(1); @@ -267,6 +274,7 @@ static ssize_t rng_dev_read(struct file *filp, char __user *buf, } } out: + memzero_explicit(buffer, sizeof(buffer)); return ret ? : err; out_unlock_reading: diff --git a/drivers/clk/qcom/gcc-sdm660.c b/drivers/clk/qcom/gcc-sdm660.c index ea79f1386629..e344dec1b532 100644 --- a/drivers/clk/qcom/gcc-sdm660.c +++ b/drivers/clk/qcom/gcc-sdm660.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2016-2017, 2019-2021, The Linux Foundation. All rights reserved. + * Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved. */ #include @@ -2679,6 +2680,7 @@ static struct clk_regmap *gcc_660_clocks[] = { static const struct qcom_reset_map gcc_660_resets[] = { [GCC_QUSB2PHY_PRIM_BCR] = { 0x12000 }, [GCC_QUSB2PHY_SEC_BCR] = { 0x12004 }, + [GCC_SDCC1_BCR] = { 0x16000 }, [GCC_UFS_BCR] = { 0x75000 }, [GCC_USB3_DP_PHY_BCR] = { 0x50028 }, [GCC_USB3_PHY_BCR] = { 0x50020 }, diff --git a/drivers/gpu/drm/nouveau/nouveau_vmm.c b/drivers/gpu/drm/nouveau/nouveau_vmm.c index 2032c3e4f6e5..fe8b88c6e2f9 100644 --- a/drivers/gpu/drm/nouveau/nouveau_vmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_vmm.c @@ -107,6 +107,9 @@ nouveau_vma_new(struct nouveau_bo *nvbo, struct nouveau_vmm *vmm, } else { ret = nvif_vmm_get(&vmm->vmm, PTES, false, mem->mem.page, 0, mem->mem.size, &tmp); + if (ret) + goto done; + vma->addr = tmp.addr; } diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c index 066e9e00de11..0d5be37660aa 100644 --- a/drivers/pci/controller/pcie-mediatek.c +++ b/drivers/pci/controller/pcie-mediatek.c @@ -605,14 +605,20 @@ static void mtk_pcie_intr_handler(struct irq_desc *desc) if (status & MSI_STATUS){ unsigned long imsi_status; + /* + * The interrupt status can be cleared even if the + * MSI status remains pending. As such, given the + * edge-triggered interrupt type, its status should + * be cleared before being dispatched to the + * handler of the underlying device. + */ + writel(MSI_STATUS, port->base + PCIE_INT_STATUS); while ((imsi_status = readl(port->base + PCIE_IMSI_STATUS))) { for_each_set_bit(bit, &imsi_status, MTK_MSI_IRQS_NUM) { virq = irq_find_mapping(port->inner_domain, bit); generic_handle_irq(virq); } } - /* Clear MSI interrupt status */ - writel(MSI_STATUS, port->base + PCIE_INT_STATUS); } } diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c index 664f957012cd..aab990339051 100644 --- a/drivers/rpmsg/virtio_rpmsg_bus.c +++ b/drivers/rpmsg/virtio_rpmsg_bus.c @@ -381,6 +381,7 @@ static void virtio_rpmsg_release_device(struct device *dev) struct rpmsg_device *rpdev = to_rpmsg_device(dev); struct virtio_rpmsg_channel *vch = to_virtio_rpmsg_channel(rpdev); + kfree(rpdev->driver_override); kfree(vch); } diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index c65f9194abb0..800cb94e4b91 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #define SC16IS7XX_NAME "sc16is7xx" @@ -1406,9 +1407,12 @@ static int sc16is7xx_spi_probe(struct spi_device *spi) /* Setup SPI bus */ spi->bits_per_word = 8; - /* only supports mode 0 on SC16IS762 */ + /* For all variants, only mode 0 is supported */ + if ((spi->mode & SPI_MODE_X_MASK) != SPI_MODE_0) + return dev_err_probe(&spi->dev, -EINVAL, "Unsupported SPI mode\n"); + spi->mode = spi->mode ? : SPI_MODE_0; - spi->max_speed_hz = spi->max_speed_hz ? : 15000000; + spi->max_speed_hz = spi->max_speed_hz ? : 4 * HZ_PER_MHZ; ret = spi_setup(spi); if (ret) return ret; diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig index 858b3339f381..662660852397 100644 --- a/fs/erofs/Kconfig +++ b/fs/erofs/Kconfig @@ -76,3 +76,20 @@ config EROFS_FS_ZIP If you don't want to enable compression feature, say N. +config EROFS_FS_PCPU_KTHREAD + bool "EROFS per-cpu decompression kthread workers" + depends on EROFS_FS_ZIP + help + Saying Y here enables per-CPU kthread workers pool to carry out + async decompression for low latencies on some architectures. + + If unsure, say N. + +config EROFS_FS_PCPU_KTHREAD_HIPRI + bool "EROFS high priority per-CPU kthread workers" + depends on EROFS_FS_ZIP && EROFS_FS_PCPU_KTHREAD + help + This permits EROFS to configure per-CPU kthread workers to run + at higher priority. + + If unsure, say N. diff --git a/fs/erofs/TODO b/fs/erofs/TODO deleted file mode 100644 index f99ddb842f99..000000000000 --- a/fs/erofs/TODO +++ /dev/null @@ -1,45 +0,0 @@ - -EROFS is still working in progress, thus it is not suitable -for all productive uses. play at your own risk :) - -TODO List: - - add the missing error handling code - (mainly existed in xattr and decompression submodules); - - - finalize erofs ondisk format design (which means that - minor on-disk revisions could happen later); - - - documentation and detailed technical analysis; - - - general code review and clean up - (including confusing variable names and code snippets); - - - support larger compressed clustersizes for selection - (currently erofs only works as expected with the page-sized - compressed cluster configuration, usually 4KB); - - - support more lossless data compression algorithms - in addition to LZ4 algorithms in VLE approach; - - - data deduplication and other useful features. - -erofs-mkfs (preview version) binaries for i386 / x86_64 are available at: - - https://github.com/hsiangkao/erofs_mkfs_binary - -It is still in progress opening mkfs source code to public, -in any case an open-source mkfs will be released in the near future. - - -Code, suggestions, etc, are welcome. Please feel free to -ask and send patches, - -To: - linux-erofs mailing list - Gao Xiang - Chao Yu - -Cc: (for linux-kernel upstream patches) - Greg Kroah-Hartman - linux-staging mailing list - diff --git a/fs/erofs/data.c b/fs/erofs/data.c index dc264a819dc2..06a3d672ab46 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -208,7 +208,7 @@ submit_bio_retry: bio_set_dev(bio, sb->s_bdev); bio->bi_iter.bi_sector = (sector_t)blknr << LOG_SECTORS_PER_BLOCK; - bio->bi_opf = REQ_OP_READ | (ra ? REQ_RAHEAD : 0); + bio->bi_opf = REQ_OP_READ; } err = bio_add_page(bio, page, PAGE_SIZE, 0); diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c index 04468c05cba7..fbf646e9c70e 100644 --- a/fs/erofs/decompressor.c +++ b/fs/erofs/decompressor.c @@ -23,8 +23,7 @@ struct z_erofs_decompressor { */ int (*prepare_destpages)(struct z_erofs_decompress_req *rq, struct list_head *pagepool); - int (*decompress)(struct z_erofs_decompress_req *rq, u8 *out, - u8 *obase); + int (*decompress)(struct z_erofs_decompress_req *rq, u8 *dst); char *name; }; @@ -124,48 +123,85 @@ static int z_erofs_lz4_prepare_destpages(struct z_erofs_decompress_req *rq, return kaddr ? 1 : 0; } -static void *generic_copy_inplace_data(struct z_erofs_decompress_req *rq, - u8 *src, unsigned int pageofs_in) +static void *z_erofs_handle_inplace_io(struct z_erofs_decompress_req *rq, + void *inpage, void *out, unsigned int *inputmargin, + int *maptype, bool support_0padding) { - /* - * if in-place decompression is ongoing, those decompressed - * pages should be copied in order to avoid being overlapped. - */ - struct page **in = rq->in; - u8 *const tmp = erofs_get_pcpubuf(1); - u8 *tmpp = tmp; - unsigned int inlen = rq->inputsize - pageofs_in; - unsigned int count = min_t(uint, inlen, PAGE_SIZE - pageofs_in); + unsigned int nrpages_in, nrpages_out; + unsigned int ofull, oend, inputsize, total, i; + struct page **in; + void *src, *tmp; - while (tmpp < tmp + inlen) { - if (!src) - src = kmap_atomic(*in); - memcpy(tmpp, src + pageofs_in, count); - kunmap_atomic(src); - src = NULL; - tmpp += count; - pageofs_in = 0; - count = PAGE_SIZE; - ++in; + inputsize = rq->inputsize; + nrpages_in = PAGE_ALIGN(inputsize) >> PAGE_SHIFT; + oend = rq->pageofs_out + rq->outputsize; + ofull = PAGE_ALIGN(oend); + nrpages_out = ofull >> PAGE_SHIFT; + + if (rq->inplace_io) { + if (rq->partial_decoding || !support_0padding || + ofull - oend < LZ4_DECOMPRESS_INPLACE_MARGIN(inputsize)) + goto docopy; + + for (i = 0; i < nrpages_in; ++i) + if (rq->out[nrpages_out - nrpages_in + i] != + rq->in[i]) + goto docopy; + kunmap_atomic(inpage); + *maptype = 3; + return out + ((nrpages_out - nrpages_in) << PAGE_SHIFT); } - return tmp; + + if (nrpages_in <= 1) { + *maptype = 0; + return inpage; + } + kunmap_atomic(inpage); + src = erofs_vm_map_ram(rq->in, nrpages_in); + if (!src) + return ERR_PTR(-ENOMEM); + *maptype = 1; + return src; + +docopy: + /* Or copy compressed data which can be overlapped to per-CPU buffer */ + in = rq->in; + src = erofs_get_pcpubuf(nrpages_in); + if (!src) { + DBG_BUGON(1); + kunmap_atomic(inpage); + return ERR_PTR(-EFAULT); + } + + tmp = src; + total = rq->inputsize; + while (total) { + unsigned int page_copycnt = + min_t(unsigned int, total, PAGE_SIZE - *inputmargin); + + if (!inpage) + inpage = kmap_atomic(*in); + memcpy(tmp, inpage + *inputmargin, page_copycnt); + kunmap_atomic(inpage); + inpage = NULL; + tmp += page_copycnt; + total -= page_copycnt; + ++in; + *inputmargin = 0; + } + *maptype = 2; + return src; } -static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out, - u8 *obase) +static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *dst) { - const uint nrpages_out = PAGE_ALIGN(rq->pageofs_out + - rq->outputsize) >> PAGE_SHIFT; - unsigned int inputmargin, inlen; - u8 *src, *src2; - bool copied, support_0padding; - int ret; + unsigned int inputmargin; + u8 *out, *headpage, *src; + bool support_0padding; + int ret, maptype; - if (rq->inputsize > PAGE_SIZE) - return -EOPNOTSUPP; - - src = kmap_atomic(*rq->in); - src2 = src; + DBG_BUGON(*rq->in == NULL); + headpage = kmap_atomic(*rq->in); inputmargin = 0; support_0padding = false; @@ -173,48 +209,37 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out, if (erofs_sb_has_lz4_0padding(EROFS_SB(rq->sb))) { support_0padding = true; - while (!src[inputmargin & ~PAGE_MASK]) + while (!headpage[inputmargin & ~PAGE_MASK]) if (!(++inputmargin & ~PAGE_MASK)) break; if (inputmargin >= rq->inputsize) { - kunmap_atomic(src); + kunmap_atomic(headpage); return -EIO; } } - copied = false; - inlen = rq->inputsize - inputmargin; - if (rq->inplace_io) { - const uint oend = (rq->pageofs_out + - rq->outputsize) & ~PAGE_MASK; - if (rq->partial_decoding || !support_0padding || - rq->out[nrpages_out - 1] != rq->in[0] || - rq->inputsize - oend < - LZ4_DECOMPRESS_INPLACE_MARGIN(inlen)) { - src = generic_copy_inplace_data(rq, src, inputmargin); - inputmargin = 0; - copied = true; - } else { - src = obase + ((nrpages_out - 1) << PAGE_SHIFT); - } - } + rq->inputsize -= inputmargin; + src = z_erofs_handle_inplace_io(rq, headpage, dst, &inputmargin, + &maptype, support_0padding); + if (IS_ERR(src)) + return PTR_ERR(src); + out = dst + rq->pageofs_out; /* legacy format could compress extra data in a pcluster. */ if (rq->partial_decoding || !support_0padding) ret = LZ4_decompress_safe_partial(src + inputmargin, out, - inlen, rq->outputsize, - rq->outputsize); + rq->inputsize, rq->outputsize, rq->outputsize); else ret = LZ4_decompress_safe(src + inputmargin, out, - inlen, rq->outputsize); + rq->inputsize, rq->outputsize); if (ret != rq->outputsize) { erofs_err(rq->sb, "failed to decompress %d in[%u, %u] out[%u]", - ret, inlen, inputmargin, rq->outputsize); + ret, rq->inputsize, inputmargin, rq->outputsize); print_hex_dump(KERN_DEBUG, "[ in]: ", DUMP_PREFIX_OFFSET, - 16, 1, src + inputmargin, inlen, true); + 16, 1, src + inputmargin, rq->inputsize, true); print_hex_dump(KERN_DEBUG, "[out]: ", DUMP_PREFIX_OFFSET, 16, 1, out, rq->outputsize, true); @@ -223,10 +248,16 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out, ret = -EIO; } - if (copied) + if (maptype == 0) { + kunmap_atomic(src); + } else if (maptype == 1) { + vm_unmap_ram(src, PAGE_ALIGN(rq->inputsize) >> PAGE_SHIFT); + } else if (maptype == 2) { erofs_put_pcpubuf(src); - else - kunmap_atomic(src2); + } else if (maptype != 3) { + DBG_BUGON(1); + return -EFAULT; + } return ret; } @@ -276,61 +307,55 @@ static int z_erofs_decompress_generic(struct z_erofs_decompress_req *rq, const struct z_erofs_decompressor *alg = decompressors + rq->alg; unsigned int dst_maptype; void *dst; - int ret, i; + int ret; - if (nrpages_out == 1 && !rq->inplace_io) { - DBG_BUGON(!*rq->out); - dst = kmap_atomic(*rq->out); - dst_maptype = 0; - goto dstmap_out; - } + /* two optimized fast paths only for non bigpcluster cases yet */ + if (rq->inputsize <= PAGE_SIZE) { + if (nrpages_out == 1 && !rq->inplace_io) { + DBG_BUGON(!*rq->out); + dst = kmap_atomic(*rq->out); + dst_maptype = 0; + goto dstmap_out; + } - /* - * For the case of small output size (especially much less - * than PAGE_SIZE), memcpy the decompressed data rather than - * compressed data is preferred. - */ - if (rq->outputsize <= PAGE_SIZE * 7 / 8) { - dst = erofs_get_pcpubuf(1); - if (IS_ERR(dst)) - return PTR_ERR(dst); + /* + * For the case of small output size (especially much less + * than PAGE_SIZE), memcpy the decompressed data rather than + * compressed data is preferred. + */ + if (rq->outputsize <= PAGE_SIZE * 7 / 8) { + dst = erofs_get_pcpubuf(1); + if (IS_ERR(dst)) + return PTR_ERR(dst); - rq->inplace_io = false; - ret = alg->decompress(rq, dst, NULL); - if (!ret) - copy_from_pcpubuf(rq->out, dst, rq->pageofs_out, - rq->outputsize); + rq->inplace_io = false; + ret = alg->decompress(rq, dst); + if (!ret) + copy_from_pcpubuf(rq->out, dst, rq->pageofs_out, + rq->outputsize); - erofs_put_pcpubuf(dst); - return ret; + erofs_put_pcpubuf(dst); + return ret; + } } + /* general decoding path which can be used for all cases */ ret = alg->prepare_destpages(rq, pagepool); - if (ret < 0) { + if (ret < 0) return ret; - } else if (ret) { + if (ret) { dst = page_address(*rq->out); dst_maptype = 1; goto dstmap_out; } - i = 0; - while (1) { - dst = vm_map_ram(rq->out, nrpages_out, -1, PAGE_KERNEL); - - /* retry two more times (totally 3 times) */ - if (dst || ++i >= 3) - break; - vm_unmap_aliases(); - } - + dst = erofs_vm_map_ram(rq->out, nrpages_out); if (!dst) return -ENOMEM; - dst_maptype = 2; dstmap_out: - ret = alg->decompress(rq, dst + rq->pageofs_out, dst); + ret = alg->decompress(rq, dst); if (!dst_maptype) kunmap_atomic(dst); diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h index 32f79b14ef50..799a119af165 100644 --- a/fs/erofs/erofs_fs.h +++ b/fs/erofs/erofs_fs.h @@ -8,7 +8,6 @@ #ifndef __EROFS_FS_H #define __EROFS_FS_H -#define EROFS_SUPER_MAGIC_V1 0xE0F5E1E2 #define EROFS_SUPER_OFFSET 1024 #define EROFS_FEATURE_COMPAT_SB_CHKSUM 0x00000001 diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 814541bf0cce..50d359101642 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -396,6 +396,21 @@ int erofs_namei(struct inode *dir, struct qstr *name, /* dir.c */ extern const struct file_operations erofs_dir_fops; +static inline void *erofs_vm_map_ram(struct page **pages, unsigned int count) +{ + int retried = 0; + + while (1) { + void *p = vm_map_ram(pages, count, -1, PAGE_KERNEL); + + /* retry two more times (totally 3 times) */ + if (p || ++retried >= 3) + return p; + vm_unmap_aliases(); + } + return NULL; +} + /* pcpubuf.c */ void *erofs_get_pcpubuf(unsigned int requiredpages); void erofs_put_pcpubuf(void *ptr); diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 35a08f3a53d0..c2f566b06e78 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -6,7 +6,7 @@ #include "zdata.h" #include "compress.h" #include - +#include #include /* @@ -124,24 +124,128 @@ typedef tagptr1_t compressed_page_t; static struct workqueue_struct *z_erofs_workqueue __read_mostly; -void z_erofs_exit_zip_subsystem(void) +#ifdef CONFIG_EROFS_FS_PCPU_KTHREAD +static struct kthread_worker __rcu **z_erofs_pcpu_workers; + +static void erofs_destroy_percpu_workers(void) { - destroy_workqueue(z_erofs_workqueue); - z_erofs_destroy_pcluster_pool(); + struct kthread_worker *worker; + unsigned int cpu; + + for_each_possible_cpu(cpu) { + worker = rcu_dereference_protected( + z_erofs_pcpu_workers[cpu], 1); + rcu_assign_pointer(z_erofs_pcpu_workers[cpu], NULL); + if (worker) + kthread_destroy_worker(worker); + } + kfree(z_erofs_pcpu_workers); } -static inline int z_erofs_init_workqueue(void) +static struct kthread_worker *erofs_init_percpu_worker(int cpu) { - const unsigned int onlinecpus = num_possible_cpus(); + struct kthread_worker *worker = + kthread_create_worker_on_cpu(cpu, 0, "erofs_worker/%u", cpu); - /* - * no need to spawn too many threads, limiting threads could minimum - * scheduling overhead, perhaps per-CPU threads should be better? - */ - z_erofs_workqueue = alloc_workqueue("erofs_unzipd", - WQ_UNBOUND | WQ_HIGHPRI, - onlinecpus + onlinecpus / 4); - return z_erofs_workqueue ? 0 : -ENOMEM; + if (IS_ERR(worker)) + return worker; + if (IS_ENABLED(CONFIG_EROFS_FS_PCPU_KTHREAD_HIPRI)) + sched_set_fifo_low(worker->task); + else + sched_set_normal(worker->task, 0); + return worker; +} + +static int erofs_init_percpu_workers(void) +{ + struct kthread_worker *worker; + unsigned int cpu; + + z_erofs_pcpu_workers = kcalloc(num_possible_cpus(), + sizeof(struct kthread_worker *), GFP_ATOMIC); + if (!z_erofs_pcpu_workers) + return -ENOMEM; + + for_each_online_cpu(cpu) { /* could miss cpu{off,on}line? */ + worker = erofs_init_percpu_worker(cpu); + if (!IS_ERR(worker)) + rcu_assign_pointer(z_erofs_pcpu_workers[cpu], worker); + } + return 0; +} +#else +static inline void erofs_destroy_percpu_workers(void) {} +static inline int erofs_init_percpu_workers(void) { return 0; } +#endif + +#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_EROFS_FS_PCPU_KTHREAD) +static DEFINE_SPINLOCK(z_erofs_pcpu_worker_lock); +static enum cpuhp_state erofs_cpuhp_state; + +static int erofs_cpu_online(unsigned int cpu) +{ + struct kthread_worker *worker, *old; + + worker = erofs_init_percpu_worker(cpu); + if (IS_ERR(worker)) + return PTR_ERR(worker); + + spin_lock(&z_erofs_pcpu_worker_lock); + old = rcu_dereference_protected(z_erofs_pcpu_workers[cpu], + lockdep_is_held(&z_erofs_pcpu_worker_lock)); + if (!old) + rcu_assign_pointer(z_erofs_pcpu_workers[cpu], worker); + spin_unlock(&z_erofs_pcpu_worker_lock); + if (old) + kthread_destroy_worker(worker); + return 0; +} + +static int erofs_cpu_offline(unsigned int cpu) +{ + struct kthread_worker *worker; + + spin_lock(&z_erofs_pcpu_worker_lock); + worker = rcu_dereference_protected(z_erofs_pcpu_workers[cpu], + lockdep_is_held(&z_erofs_pcpu_worker_lock)); + rcu_assign_pointer(z_erofs_pcpu_workers[cpu], NULL); + spin_unlock(&z_erofs_pcpu_worker_lock); + + synchronize_rcu(); + if (worker) + kthread_destroy_worker(worker); + return 0; +} + +static int erofs_cpu_hotplug_init(void) +{ + int state; + + state = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "fs/erofs:online", erofs_cpu_online, erofs_cpu_offline); + if (state < 0) + return state; + + erofs_cpuhp_state = state; + return 0; +} + +static void erofs_cpu_hotplug_destroy(void) +{ + if (erofs_cpuhp_state) + cpuhp_remove_state_nocalls(erofs_cpuhp_state); +} +#else /* !CONFIG_HOTPLUG_CPU || !CONFIG_EROFS_FS_PCPU_KTHREAD */ +static inline int erofs_cpu_hotplug_init(void) { return 0; } +static inline void erofs_cpu_hotplug_destroy(void) {} +#endif + +void z_erofs_exit_zip_subsystem(void) +{ + erofs_cpu_hotplug_destroy(); + erofs_destroy_percpu_workers(); + destroy_workqueue(z_erofs_workqueue); + z_erofs_destroy_pcluster_pool(); } int __init z_erofs_init_zip_subsystem(void) @@ -149,10 +253,31 @@ int __init z_erofs_init_zip_subsystem(void) int err = z_erofs_create_pcluster_pool(); if (err) - return err; - err = z_erofs_init_workqueue(); + goto out_error_pcluster_pool; + + z_erofs_workqueue = alloc_workqueue("erofs_worker", + WQ_UNBOUND | WQ_HIGHPRI, num_possible_cpus()); + if (!z_erofs_workqueue) { + err = -ENOMEM; + goto out_error_workqueue_init; + } + + err = erofs_init_percpu_workers(); if (err) - z_erofs_destroy_pcluster_pool(); + goto out_error_pcpu_worker; + + err = erofs_cpu_hotplug_init(); + if (err < 0) + goto out_error_cpuhp_init; + return err; + +out_error_cpuhp_init: + erofs_destroy_percpu_workers(); +out_error_pcpu_worker: + destroy_workqueue(z_erofs_workqueue); +out_error_workqueue_init: + z_erofs_destroy_pcluster_pool(); +out_error_pcluster_pool: return err; } @@ -216,7 +341,6 @@ struct z_erofs_decompress_frontend { struct z_erofs_collector clt; struct erofs_map_blocks map; - bool readahead; /* used for applying cache strategy on the fly */ bool backmost; erofs_off_t headoffset; @@ -331,11 +455,8 @@ int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi, /* barrier is implied in the following 'unlock_page' */ WRITE_ONCE(pcl->compressed_pages[i], NULL); - - set_page_private(page, 0); - ClearPagePrivate(page); + detach_page_private(page); unlock_page(page); - put_page(page); } return 0; } @@ -358,11 +479,8 @@ int erofs_try_to_free_cached_page(struct address_space *mapping, } erofs_workgroup_unfreeze(&pcl->obj, 1); - if (ret) { - set_page_private(page, 0); - ClearPagePrivate(page); - put_page(page); - } + if (ret) + detach_page_private(page); } return ret; } @@ -779,6 +897,12 @@ err_out: } static void z_erofs_decompressqueue_work(struct work_struct *work); +#ifdef CONFIG_EROFS_FS_PCPU_KTHREAD +static void z_erofs_decompressqueue_kthread_work(struct kthread_work *work) +{ + z_erofs_decompressqueue_work((struct work_struct *)work); +} +#endif static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, bool sync, int bios) { @@ -786,12 +910,9 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, /* wake up the caller thread for sync decompression */ if (sync) { - unsigned long flags; - - spin_lock_irqsave(&io->u.wait.lock, flags); if (!atomic_add_return(bios, &io->pending_bios)) - wake_up_locked(&io->u.wait); - spin_unlock_irqrestore(&io->u.wait.lock, flags); + complete(&io->u.done); + return; } @@ -799,7 +920,22 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, return; /* Use workqueue and sync decompression for atomic contexts only */ if (in_atomic() || irqs_disabled()) { +#ifdef CONFIG_EROFS_FS_PCPU_KTHREAD + struct kthread_worker *worker; + + rcu_read_lock(); + worker = rcu_dereference( + z_erofs_pcpu_workers[raw_smp_processor_id()]); + if (!worker) { + INIT_WORK(&io->u.work, z_erofs_decompressqueue_work); + queue_work(z_erofs_workqueue, &io->u.work); + } else { + kthread_queue_work(worker, &io->u.kthread_work); + } + rcu_read_unlock(); +#else queue_work(z_erofs_workqueue, &io->u.work); +#endif sbi->readahead_sync_decompress = true; return; } @@ -1187,8 +1323,9 @@ out_tocache: set_page_private(page, Z_EROFS_SHORTLIVED_PAGE); goto out; } - set_page_private(page, (unsigned long)pcl); - SetPagePrivate(page); + attach_page_private(page, pcl); + /* drop a refcount added by allocpage (then we have 2 refs here) */ + put_page(page); out: /* the only exit (for tracing and debugging) */ return page; @@ -1206,11 +1343,16 @@ jobqueue_init(struct super_block *sb, *fg = true; goto fg_out; } +#ifdef CONFIG_EROFS_FS_PCPU_KTHREAD + kthread_init_work(&q->u.kthread_work, + z_erofs_decompressqueue_kthread_work); +#else INIT_WORK(&q->u.work, z_erofs_decompressqueue_work); +#endif } else { fg_out: q = fgq; - init_waitqueue_head(&fgq->u.wait); + init_completion(&fgq->u.done); atomic_set(&fgq->pending_bios, 0); } q->sb = sb; @@ -1259,7 +1401,7 @@ static void move_to_bypass_jobqueue(struct z_erofs_pcluster *pcl, } static void z_erofs_submit_queue(struct super_block *sb, - struct z_erofs_decompress_frontend *f, + z_erofs_next_pcluster_t owned_head, struct list_head *pagepool, struct z_erofs_decompressqueue *fgq, bool *force_fg) @@ -1268,7 +1410,6 @@ static void z_erofs_submit_queue(struct super_block *sb, z_erofs_next_pcluster_t qtail[NR_JOBQUEUES]; struct z_erofs_decompressqueue *q[NR_JOBQUEUES]; void *bi_private; - z_erofs_next_pcluster_t owned_head = f->clt.owned_head; /* since bio will be NULL, no need to initialize last_index */ pgoff_t last_index; unsigned int nr_bios = 0; @@ -1324,8 +1465,6 @@ submit_bio_retry: LOG_SECTORS_PER_BLOCK; bio->bi_private = bi_private; bio->bi_opf = REQ_OP_READ; - if (f->readahead) - bio->bi_opf |= REQ_RAHEAD; ++nr_bios; } @@ -1347,7 +1486,7 @@ submit_bio_retry: /* * although background is preferred, no one is pending for submission. - * don't issue workqueue for decompression but drop it directly instead. + * don't issue decompression but drop it directly instead. */ if (!*force_fg && !nr_bios) { kvfree(q[JQ_SUBMIT]); @@ -1357,14 +1496,14 @@ submit_bio_retry: } static void z_erofs_runqueue(struct super_block *sb, - struct z_erofs_decompress_frontend *f, + struct z_erofs_collector *clt, struct list_head *pagepool, bool force_fg) { struct z_erofs_decompressqueue io[NR_JOBQUEUES]; - if (f->clt.owned_head == Z_EROFS_PCLUSTER_TAIL) + if (clt->owned_head == Z_EROFS_PCLUSTER_TAIL) return; - z_erofs_submit_queue(sb, f, pagepool, io, &force_fg); + z_erofs_submit_queue(sb, clt->owned_head, pagepool, io, &force_fg); /* handle bypass queue (no i/o pclusters) immediately */ z_erofs_decompress_queue(&io[JQ_BYPASS], pagepool); @@ -1373,8 +1512,7 @@ static void z_erofs_runqueue(struct super_block *sb, return; /* wait until all bios are completed */ - io_wait_event(io[JQ_SUBMIT].u.wait, - !atomic_read(&io[JQ_SUBMIT].pending_bios)); + wait_for_completion_io(&io[JQ_SUBMIT].u.done); /* handle synchronous decompress queue in the caller context */ z_erofs_decompress_queue(&io[JQ_SUBMIT], pagepool); @@ -1395,7 +1533,7 @@ static int z_erofs_readpage(struct file *file, struct page *page) (void)z_erofs_collector_end(&f.clt); /* if some compressed cluster ready, need submit them anyway */ - z_erofs_runqueue(inode->i_sb, &f, &pagepool, true); + z_erofs_runqueue(inode->i_sb, &f.clt, &pagepool, true); if (err) erofs_err(inode->i_sb, "failed to read, err [%d]", err); @@ -1465,7 +1603,7 @@ static int z_erofs_readpages(struct file *filp, struct address_space *mapping, (void)z_erofs_collector_end(&f.clt); - z_erofs_runqueue(inode->i_sb, &f, &pagepool, sync); + z_erofs_runqueue(inode->i_sb, &f.clt, &pagepool, sync); if (f.map.mpage) put_page(f.map.mpage); diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h index 3a008f1b9f78..3ada1ae86b38 100644 --- a/fs/erofs/zdata.h +++ b/fs/erofs/zdata.h @@ -6,6 +6,7 @@ #ifndef __EROFS_FS_ZDATA_H #define __EROFS_FS_ZDATA_H +#include #include "internal.h" #include "zpvec.h" @@ -89,8 +90,9 @@ struct z_erofs_decompressqueue { z_erofs_next_pcluster_t head; union { - wait_queue_head_t wait; + struct completion done; struct work_struct work; + struct kthread_work kthread_work; } u; }; diff --git a/fs/exfat/.github/workflows/c-cpp.yml b/fs/exfat/.github/workflows/c-cpp.yml index 375c800ac23c..277727301c8e 100644 --- a/fs/exfat/.github/workflows/c-cpp.yml +++ b/fs/exfat/.github/workflows/c-cpp.yml @@ -2,9 +2,9 @@ name: linux-exfat-oot CI on: push: - branches: [ "master" ] + branches: [ "for-kernel-version-from-4.1.0" ] pull_request: - branches: [ "master" ] + branches: [ "for-kernel-version-from-4.1.0" ] jobs: build: @@ -20,6 +20,7 @@ jobs: wget https://mirrors.edge.kernel.org/pub/linux/kernel/v4.x/linux-4.1.36.tar.gz tar xf linux-4.1.36.tar.gz mv linux-4.1.36 linux-stable + rm -rf linux-4.1.36.tar.gz - name: Prerequisite for xfstests testing run: | sudo apt-get install linux-headers-$(uname -r) @@ -47,7 +48,9 @@ jobs: make -j$((`nproc`+1)) fs/exfat/exfat.ko - name: Run xfstests testsuite run: | - cd ../linux-exfat-oot + cd .. + rm -rf linux-stable + cd linux-exfat-oot make > /dev/null sudo make install > /dev/null sudo insmod exfat.ko diff --git a/fs/exfat/Kconfig b/fs/exfat/Kconfig index b3e5e9ebabc8..e298907a829a 100644 --- a/fs/exfat/Kconfig +++ b/fs/exfat/Kconfig @@ -2,6 +2,7 @@ config EXFAT_FS tristate "exFAT filesystem support" + select BUFFER_HEAD select NLS select LEGACY_DIRECT_IO help diff --git a/fs/exfat/balloc.c b/fs/exfat/balloc.c index c226d5d1c36b..5aa9b4ab80de 100644 --- a/fs/exfat/balloc.c +++ b/fs/exfat/balloc.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 11, 0) #include @@ -17,37 +18,21 @@ #include "exfat_raw.h" #include "exfat_fs.h" -static const unsigned char free_bit[] = { - 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, 4, 0, 1, 0, 2,/* 0 ~ 19*/ - 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, 5, 0, 1, 0, 2, 0, 1, 0, 3,/* 20 ~ 39*/ - 0, 1, 0, 2, 0, 1, 0, 4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2,/* 40 ~ 59*/ - 0, 1, 0, 6, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, 4,/* 60 ~ 79*/ - 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, 5, 0, 1, 0, 2,/* 80 ~ 99*/ - 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, 4, 0, 1, 0, 2, 0, 1, 0, 3,/*100 ~ 119*/ - 0, 1, 0, 2, 0, 1, 0, 7, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2,/*120 ~ 139*/ - 0, 1, 0, 4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, 5,/*140 ~ 159*/ - 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, 4, 0, 1, 0, 2,/*160 ~ 179*/ - 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, 6, 0, 1, 0, 2, 0, 1, 0, 3,/*180 ~ 199*/ - 0, 1, 0, 2, 0, 1, 0, 4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2,/*200 ~ 219*/ - 0, 1, 0, 5, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, 4,/*220 ~ 239*/ - 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0 /*240 ~ 254*/ -}; +#if BITS_PER_LONG == 32 +#define __le_long __le32 +#define lel_to_cpu(A) le32_to_cpu(A) +#define cpu_to_lel(A) cpu_to_le32(A) +#elif BITS_PER_LONG == 64 +#define __le_long __le64 +#define lel_to_cpu(A) le64_to_cpu(A) +#define cpu_to_lel(A) cpu_to_le64(A) +#else +#error "BITS_PER_LONG not 32 or 64" +#endif -static const unsigned char used_bit[] = { - 0, 1, 1, 2, 1, 2, 2, 3, 1, 2, 2, 3, 2, 3, 3, 4, 1, 2, 2, 3,/* 0 ~ 19*/ - 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5, 1, 2, 2, 3, 2, 3, 3, 4,/* 20 ~ 39*/ - 2, 3, 3, 4, 3, 4, 4, 5, 2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5,/* 40 ~ 59*/ - 4, 5, 5, 6, 1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,/* 60 ~ 79*/ - 2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6, 2, 3, 3, 4,/* 80 ~ 99*/ - 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6, 3, 4, 4, 5, 4, 5, 5, 6,/*100 ~ 119*/ - 4, 5, 5, 6, 5, 6, 6, 7, 1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4,/*120 ~ 139*/ - 3, 4, 4, 5, 2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,/*140 ~ 159*/ - 2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6, 3, 4, 4, 5,/*160 ~ 179*/ - 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7, 2, 3, 3, 4, 3, 4, 4, 5,/*180 ~ 199*/ - 3, 4, 4, 5, 4, 5, 5, 6, 3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6,/*200 ~ 219*/ - 5, 6, 6, 7, 3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,/*220 ~ 239*/ - 4, 5, 5, 6, 5, 6, 6, 7, 5, 6, 6, 7, 6, 7, 7, 8 /*240 ~ 255*/ -}; +#ifndef ALIGN_DOWN +#define ALIGN_DOWN(x, a) __ALIGN_KERNEL((x) - ((a) - 1), (a)) +#endif /* * Allocation Bitmap Management Functions @@ -211,32 +196,35 @@ unsigned int exfat_find_free_bitmap(struct super_block *sb, unsigned int clu) { unsigned int i, map_i, map_b, ent_idx; unsigned int clu_base, clu_free; - unsigned char k, clu_mask; + unsigned long clu_bits, clu_mask; struct exfat_sb_info *sbi = EXFAT_SB(sb); + __le_long bitval; WARN_ON(clu < EXFAT_FIRST_CLUSTER); - ent_idx = CLUSTER_TO_BITMAP_ENT(clu); - clu_base = BITMAP_ENT_TO_CLUSTER(ent_idx & ~(BITS_PER_BYTE_MASK)); + ent_idx = ALIGN_DOWN(CLUSTER_TO_BITMAP_ENT(clu), BITS_PER_LONG); + clu_base = BITMAP_ENT_TO_CLUSTER(ent_idx); clu_mask = IGNORED_BITS_REMAINED(clu, clu_base); map_i = BITMAP_OFFSET_SECTOR_INDEX(sb, ent_idx); map_b = BITMAP_OFFSET_BYTE_IN_SECTOR(sb, ent_idx); for (i = EXFAT_FIRST_CLUSTER; i < sbi->num_clusters; - i += BITS_PER_BYTE) { - k = *(sbi->vol_amap[map_i]->b_data + map_b); + i += BITS_PER_LONG) { + bitval = *(__le_long *)(sbi->vol_amap[map_i]->b_data + map_b); if (clu_mask > 0) { - k |= clu_mask; + bitval |= cpu_to_lel(clu_mask); clu_mask = 0; } - if (k < 0xFF) { - clu_free = clu_base + free_bit[k]; + if (lel_to_cpu(bitval) != ULONG_MAX) { + clu_bits = lel_to_cpu(bitval); + clu_free = clu_base + ffz(clu_bits); if (clu_free < sbi->num_clusters) return clu_free; } - clu_base += BITS_PER_BYTE; + clu_base += BITS_PER_LONG; + map_b += sizeof(long); - if (++map_b >= sb->s_blocksize || + if (map_b >= sb->s_blocksize || clu_base >= sbi->num_clusters) { if (++map_i >= sbi->map_sectors) { clu_base = EXFAT_FIRST_CLUSTER; @@ -255,25 +243,24 @@ int exfat_count_used_clusters(struct super_block *sb, unsigned int *ret_count) unsigned int count = 0; unsigned int i, map_i = 0, map_b = 0; unsigned int total_clus = EXFAT_DATA_CLUSTER_COUNT(sbi); - unsigned int last_mask = total_clus & BITS_PER_BYTE_MASK; - unsigned char clu_bits; - const unsigned char last_bit_mask[] = {0, 0b00000001, 0b00000011, - 0b00000111, 0b00001111, 0b00011111, 0b00111111, 0b01111111}; + unsigned int last_mask = total_clus & (BITS_PER_LONG - 1); + unsigned long *bitmap, clu_bits; total_clus &= ~last_mask; - for (i = 0; i < total_clus; i += BITS_PER_BYTE) { - clu_bits = *(sbi->vol_amap[map_i]->b_data + map_b); - count += used_bit[clu_bits]; - if (++map_b >= (unsigned int)sb->s_blocksize) { + for (i = 0; i < total_clus; i += BITS_PER_LONG) { + bitmap = (void *)(sbi->vol_amap[map_i]->b_data + map_b); + count += hweight_long(*bitmap); + map_b += sizeof(long); + if (map_b >= (unsigned int)sb->s_blocksize) { map_i++; map_b = 0; } } if (last_mask) { - clu_bits = *(sbi->vol_amap[map_i]->b_data + map_b); - clu_bits &= last_bit_mask[last_mask]; - count += used_bit[clu_bits]; + bitmap = (void *)(sbi->vol_amap[map_i]->b_data + map_b); + clu_bits = lel_to_cpu(*(__le_long *)bitmap); + count += hweight_long(clu_bits & BITMAP_LAST_WORD_MASK(last_mask)); } *ret_count = count; diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c index bf8eb5d1b1c2..4d5b863b4fde 100644 --- a/fs/exfat/dir.c +++ b/fs/exfat/dir.c @@ -288,7 +288,7 @@ get_new: mutex_unlock(&EXFAT_SB(sb)->s_lock); if (!dir_emit(ctx, nb->lfn, strlen(nb->lfn), inum, - (de.attr & ATTR_SUBDIR) ? DT_DIR : DT_REG)) + (de.attr & EXFAT_ATTR_SUBDIR) ? DT_DIR : DT_REG)) goto out; ctx->pos = cpos; goto get_new; @@ -307,10 +307,17 @@ out: return err; } +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 5, 0) +WRAP_DIR_ITER(exfat_iterate) // FIXME! +#endif const struct file_operations exfat_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 5, 0) + .iterate_shared = shared_exfat_iterate, +#else .iterate = exfat_iterate, +#endif .unlocked_ioctl = exfat_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = exfat_compat_ioctl, @@ -359,7 +366,7 @@ unsigned int exfat_get_entry_type(struct exfat_dentry *ep) if (ep->type == EXFAT_VOLUME) return TYPE_VOLUME; if (ep->type == EXFAT_FILE) { - if (le16_to_cpu(ep->dentry.file.attr) & ATTR_SUBDIR) + if (le16_to_cpu(ep->dentry.file.attr) & EXFAT_ATTR_SUBDIR) return TYPE_DIR; return TYPE_FILE; } @@ -410,19 +417,21 @@ static void exfat_set_entry_type(struct exfat_dentry *ep, unsigned int type) ep->type = EXFAT_VOLUME; } else if (type == TYPE_DIR) { ep->type = EXFAT_FILE; - ep->dentry.file.attr = cpu_to_le16(ATTR_SUBDIR); + ep->dentry.file.attr = cpu_to_le16(EXFAT_ATTR_SUBDIR); } else if (type == TYPE_FILE) { ep->type = EXFAT_FILE; - ep->dentry.file.attr = cpu_to_le16(ATTR_ARCHIVE); + ep->dentry.file.attr = cpu_to_le16(EXFAT_ATTR_ARCHIVE); } } static void exfat_init_stream_entry(struct exfat_dentry *ep, - unsigned char flags, unsigned int start_clu, - unsigned long long size) + unsigned int start_clu, unsigned long long size) { exfat_set_entry_type(ep, TYPE_STREAM); - ep->dentry.stream.flags = flags; + if (size == 0) + ep->dentry.stream.flags = ALLOC_FAT_CHAIN; + else + ep->dentry.stream.flags = ALLOC_NO_FAT_CHAIN; ep->dentry.stream.start_clu = cpu_to_le32(start_clu); ep->dentry.stream.valid_size = cpu_to_le64(size); ep->dentry.stream.size = cpu_to_le64(size); @@ -498,9 +507,7 @@ int exfat_init_dir_entry(struct inode *inode, struct exfat_chain *p_dir, if (!ep) return -EIO; - exfat_init_stream_entry(ep, - (type == TYPE_FILE) ? ALLOC_FAT_CHAIN : ALLOC_NO_FAT_CHAIN, - start_clu, size); + exfat_init_stream_entry(ep, start_clu, size); exfat_update_bh(bh, IS_DIRSYNC(inode)); brelse(bh); diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h index b79f2fe2bea5..6bf1c67daefb 100644 --- a/fs/exfat/exfat_fs.h +++ b/fs/exfat/exfat_fs.h @@ -148,8 +148,7 @@ enum { #define BITMAP_OFFSET_BIT_IN_SECTOR(sb, ent) (ent & BITS_PER_SECTOR_MASK(sb)) #define BITMAP_OFFSET_BYTE_IN_SECTOR(sb, ent) \ ((ent / BITS_PER_BYTE) & ((sb)->s_blocksize - 1)) -#define BITS_PER_BYTE_MASK 0x7 -#define IGNORED_BITS_REMAINED(clu, clu_base) ((1 << ((clu) - (clu_base))) - 1) +#define IGNORED_BITS_REMAINED(clu, clu_base) ((1UL << ((clu) - (clu_base))) - 1) #define ES_ENTRY_NUM(name_len) (ES_IDX_LAST_FILENAME(name_len) + 1) /* 19 entries = 1 file entry + 1 stream entry + 17 filename entries */ @@ -253,6 +252,8 @@ struct exfat_mount_options { discard:1, /* Issue discard requests on deletions */ keep_last_dots:1; /* Keep trailing periods in paths */ int time_offset; /* Offset of timestamps from UTC (in minutes) */ + /* Support creating zero-size directory, default: false */ + bool zero_size_dir; }; /* @@ -382,10 +383,10 @@ static inline int exfat_mode_can_hold_ro(struct inode *inode) static inline mode_t exfat_make_mode(struct exfat_sb_info *sbi, unsigned short attr, mode_t mode) { - if ((attr & ATTR_READONLY) && !(attr & ATTR_SUBDIR)) + if ((attr & EXFAT_ATTR_READONLY) && !(attr & EXFAT_ATTR_SUBDIR)) mode &= ~0222; - if (attr & ATTR_SUBDIR) + if (attr & EXFAT_ATTR_SUBDIR) return (mode & ~sbi->options.fs_dmask) | S_IFDIR; return (mode & ~sbi->options.fs_fmask) | S_IFREG; @@ -397,18 +398,18 @@ static inline unsigned short exfat_make_attr(struct inode *inode) unsigned short attr = EXFAT_I(inode)->attr; if (S_ISDIR(inode->i_mode)) - attr |= ATTR_SUBDIR; + attr |= EXFAT_ATTR_SUBDIR; if (exfat_mode_can_hold_ro(inode) && !(inode->i_mode & 0222)) - attr |= ATTR_READONLY; + attr |= EXFAT_ATTR_READONLY; return attr; } static inline void exfat_save_attr(struct inode *inode, unsigned short attr) { if (exfat_mode_can_hold_ro(inode)) - EXFAT_I(inode)->attr = attr & (ATTR_RWMASK | ATTR_READONLY); + EXFAT_I(inode)->attr = attr & (EXFAT_ATTR_RWMASK | EXFAT_ATTR_READONLY); else - EXFAT_I(inode)->attr = attr & ATTR_RWMASK; + EXFAT_I(inode)->attr = attr & EXFAT_ATTR_RWMASK; } static inline bool exfat_is_last_sector_in_cluster(struct exfat_sb_info *sbi, @@ -596,6 +597,9 @@ void __exfat_fs_error(struct super_block *sb, int report, const char *fmt, ...) void exfat_get_entry_time(struct exfat_sb_info *sbi, struct timespec64 *ts, u8 tz, __le16 time, __le16 date, u8 time_cs); void exfat_truncate_atime(struct timespec64 *ts); +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 7, 0) +void exfat_truncate_inode_atime(struct inode *inode); +#endif void exfat_set_entry_time(struct exfat_sb_info *sbi, struct timespec64 *ts, u8 *tz, __le16 *time, __le16 *date, u8 *time_cs); #else diff --git a/fs/exfat/exfat_raw.h b/fs/exfat/exfat_raw.h index 0ece2e43cf49..971a1ccd0e89 100644 --- a/fs/exfat/exfat_raw.h +++ b/fs/exfat/exfat_raw.h @@ -64,15 +64,16 @@ #define CS_DEFAULT 2 /* file attributes */ -#define ATTR_READONLY 0x0001 -#define ATTR_HIDDEN 0x0002 -#define ATTR_SYSTEM 0x0004 -#define ATTR_VOLUME 0x0008 -#define ATTR_SUBDIR 0x0010 -#define ATTR_ARCHIVE 0x0020 +#define EXFAT_ATTR_READONLY 0x0001 +#define EXFAT_ATTR_HIDDEN 0x0002 +#define EXFAT_ATTR_SYSTEM 0x0004 +#define EXFAT_ATTR_VOLUME 0x0008 +#define EXFAT_ATTR_SUBDIR 0x0010 +#define EXFAT_ATTR_ARCHIVE 0x0020 -#define ATTR_RWMASK (ATTR_HIDDEN | ATTR_SYSTEM | ATTR_VOLUME | \ - ATTR_SUBDIR | ATTR_ARCHIVE) +#define EXFAT_ATTR_RWMASK (EXFAT_ATTR_HIDDEN | EXFAT_ATTR_SYSTEM | \ + EXFAT_ATTR_VOLUME | EXFAT_ATTR_SUBDIR | \ + EXFAT_ATTR_ARCHIVE) #define BOOTSEC_JUMP_BOOT_LEN 3 #define BOOTSEC_FS_NAME_LEN 8 diff --git a/fs/exfat/file.c b/fs/exfat/file.c index e35998f5aa8c..749c349cbfba 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -9,8 +9,12 @@ #if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 11, 0) #include #endif +#include #include #include +#include +#include +#include #include "exfat_raw.h" #include "exfat_fs.h" @@ -26,7 +30,15 @@ static int exfat_cont_expand(struct inode *inode, loff_t size) return err; #if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 10, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 6, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 7, 0) + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); +#else + inode->i_mtime = inode_set_ctime_current(inode); +#endif +#else inode->i_ctime = inode->i_mtime = current_time(inode); +#endif #else inode->i_ctime = inode->i_mtime = CURRENT_TIME_SEC; #endif @@ -151,7 +163,7 @@ int __exfat_truncate(struct inode *inode) } if (ei->type == TYPE_FILE) - ei->attr |= ATTR_ARCHIVE; + ei->attr |= EXFAT_ATTR_ARCHIVE; /* * update the directory entry @@ -265,7 +277,11 @@ int exfat_getattr(struct vfsmount *mnt, struct dentry *dentry, #if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 12, 0) #if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 3, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 6, 0) + generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); +#else generic_fillattr(&nop_mnt_idmap, inode, stat); +#endif #else generic_fillattr(&init_user_ns, inode, stat); #endif @@ -355,11 +371,23 @@ int exfat_setattr(struct dentry *dentry, struct iattr *attr) if (attr->ia_valid & ATTR_SIZE) #if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 10, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 6, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 7, 0) + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); +#else + inode->i_mtime = inode_set_ctime_current(inode); +#endif +#else inode->i_mtime = inode->i_ctime = current_time(inode); +#endif #else inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC; #endif +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 7, 0) + setattr_copy(&nop_mnt_idmap, inode, attr); + exfat_truncate_inode_atime(inode); +#else #if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 12, 0) #if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 3, 0) setattr_copy(&nop_mnt_idmap, inode, attr); @@ -370,6 +398,7 @@ int exfat_setattr(struct dentry *dentry, struct iattr *attr) setattr_copy(inode, attr); #endif exfat_truncate_atime(&inode->i_atime); +#endif if (attr->ia_valid & ATTR_SIZE) { error = exfat_block_truncate_page(inode, attr->ia_size); @@ -390,6 +419,131 @@ out: return error; } +/* + * modified ioctls from fat/file.c by Welmer Almesberger + */ +static int exfat_ioctl_get_attributes(struct inode *inode, u32 __user *user_attr) +{ + u32 attr; + +#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 7, 0) + inode_lock_shared(inode); +#else + mutex_lock(&inode->i_mutex); +#endif + attr = exfat_make_attr(inode); +#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 7, 0) + inode_unlock_shared(inode); +#else + mutex_unlock(&inode->i_mutex); +#endif + + return put_user(attr, user_attr); +} + +static int exfat_ioctl_set_attributes(struct file *file, u32 __user *user_attr) +{ + struct inode *inode = file_inode(file); + struct exfat_sb_info *sbi = EXFAT_SB(inode->i_sb); + int is_dir = S_ISDIR(inode->i_mode); + u32 attr, oldattr; + struct iattr ia; + int err; + + err = get_user(attr, user_attr); + if (err) + goto out; + + err = mnt_want_write_file(file); + if (err) + goto out; + +#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 4, 0) + inode_lock(inode); +#else + mutex_lock(&inode->i_mutex); +#endif + + oldattr = exfat_make_attr(inode); + + /* + * Mask attributes so we don't set reserved fields. + */ + attr &= (EXFAT_ATTR_READONLY | EXFAT_ATTR_HIDDEN | EXFAT_ATTR_SYSTEM | + EXFAT_ATTR_ARCHIVE); + attr |= (is_dir ? EXFAT_ATTR_SUBDIR : 0); + + /* Equivalent to a chmod() */ + ia.ia_valid = ATTR_MODE | ATTR_CTIME; +#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 12, 0) + ia.ia_ctime = current_time(inode); +#else + ia.ia_ctime = current_fs_time(inode->i_sb); +#endif + if (is_dir) + ia.ia_mode = exfat_make_mode(sbi, attr, 0777); + else + ia.ia_mode = exfat_make_mode(sbi, attr, 0666 | (inode->i_mode & 0111)); + + /* The root directory has no attributes */ + if (inode->i_ino == EXFAT_ROOT_INO && attr != EXFAT_ATTR_SUBDIR) { + err = -EINVAL; + goto out_unlock_inode; + } + + if (((attr | oldattr) & EXFAT_ATTR_SYSTEM) && + !capable(CAP_LINUX_IMMUTABLE)) { + err = -EPERM; + goto out_unlock_inode; + } + + /* + * The security check is questionable... We single + * out the RO attribute for checking by the security + * module, just because it maps to a file mode. + */ +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 0, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 3, 0) + err = security_inode_setattr(file_mnt_idmap(file), + file->f_path.dentry, &ia); +#else + err = security_inode_setattr(file_mnt_user_ns(file), + file->f_path.dentry, &ia); +#endif +#else + err = security_inode_setattr(file->f_path.dentry, &ia); +#endif + if (err) + goto out_unlock_inode; + +#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 12, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 3, 0) + /* This MUST be done before doing anything irreversible... */ + err = exfat_setattr(file_mnt_idmap(file), file->f_path.dentry, &ia); +#else + err = exfat_setattr(file_mnt_user_ns(file), file->f_path.dentry, &ia); +#endif +#else + err = exfat_setattr(file->f_path.dentry, &ia); +#endif + if (err) + goto out_unlock_inode; + + fsnotify_change(file->f_path.dentry, ia.ia_valid); + + exfat_save_attr(inode, attr); + mark_inode_dirty(inode); +out_unlock_inode: +#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 4, 0) + inode_unlock(inode); +#else + mutex_unlock(&inode->i_mutex); +#endif + mnt_drop_write_file(file); +out: + return err; +} + static int exfat_ioctl_fitrim(struct inode *inode, unsigned long arg) { #if LINUX_VERSION_CODE < KERNEL_VERSION(5, 19, 0) @@ -432,8 +586,13 @@ static int exfat_ioctl_fitrim(struct inode *inode, unsigned long arg) long exfat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); + u32 __user *user_attr = (u32 __user *)arg; switch (cmd) { + case FAT_IOCTL_GET_ATTRIBUTES: + return exfat_ioctl_get_attributes(inode, user_attr); + case FAT_IOCTL_SET_ATTRIBUTES: + return exfat_ioctl_set_attributes(filp, user_attr); case FITRIM: return exfat_ioctl_fitrim(inode, arg); default: diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c index 4d4449e1df3d..479db4299c83 100644 --- a/fs/exfat/inode.c +++ b/fs/exfat/inode.c @@ -28,6 +28,9 @@ int __exfat_write_inode(struct inode *inode, int sync) struct exfat_sb_info *sbi = EXFAT_SB(sb); struct exfat_inode_info *ei = EXFAT_I(inode); bool is_dir = (ei->type == TYPE_DIR) ? true : false; +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 7, 0) + struct timespec64 ts; +#endif if (inode->i_ino == EXFAT_ROOT_INO) return 0; @@ -57,6 +60,20 @@ int __exfat_write_inode(struct inode *inode, int sync) &ep->dentry.file.create_time, &ep->dentry.file.create_date, &ep->dentry.file.create_time_cs); +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 7, 0) + ts = inode_get_mtime(inode); + exfat_set_entry_time(sbi, &ts, + &ep->dentry.file.modify_tz, + &ep->dentry.file.modify_time, + &ep->dentry.file.modify_date, + &ep->dentry.file.modify_time_cs); + ts = inode_get_atime(inode); + exfat_set_entry_time(sbi, &ts, + &ep->dentry.file.access_tz, + &ep->dentry.file.access_time, + &ep->dentry.file.access_date, + NULL); +#else exfat_set_entry_time(sbi, &inode->i_mtime, &ep->dentry.file.modify_tz, &ep->dentry.file.modify_time, @@ -67,6 +84,7 @@ int __exfat_write_inode(struct inode *inode, int sync) &ep->dentry.file.access_time, &ep->dentry.file.access_date, NULL); +#endif /* File size should be zero if there is no cluster allocated */ on_disk_size = i_size_read(inode); @@ -380,7 +398,15 @@ static void exfat_write_failed(struct address_space *mapping, loff_t to) if (to > i_size_read(inode)) { truncate_pagecache(inode, i_size_read(inode)); #if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 10, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 6, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 7, 0) + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); +#else + inode->i_mtime = inode_set_ctime_current(inode); +#endif +#else inode->i_mtime = inode->i_ctime = current_time(inode); +#endif #else inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC; #endif @@ -436,13 +462,21 @@ static int exfat_write_end(struct file *file, struct address_space *mapping, if (err < len) exfat_write_failed(mapping, pos+len); - if (!(err < 0) && !(ei->attr & ATTR_ARCHIVE)) { + if (!(err < 0) && !(ei->attr & EXFAT_ATTR_ARCHIVE)) { #if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 10, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 6, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 7, 0) + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); +#else + inode->i_mtime = inode_set_ctime_current(inode); +#endif +#else inode->i_mtime = inode->i_ctime = current_time(inode); +#endif #else inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC; #endif - ei->attr |= ATTR_ARCHIVE; + ei->attr |= EXFAT_ATTR_ARCHIVE; mark_inode_dirty(inode); } @@ -629,7 +663,7 @@ static int exfat_fill_inode(struct inode *inode, struct exfat_dir_entry *info) inode->i_generation = prandom_u32(); #endif - if (info->attr & ATTR_SUBDIR) { /* directory */ + if (info->attr & EXFAT_ATTR_SUBDIR) { /* directory */ inode->i_generation &= ~1; inode->i_mode = exfat_make_mode(sbi, info->attr, 0777); inode->i_op = &exfat_dir_inode_operations; @@ -658,10 +692,22 @@ static int exfat_fill_inode(struct inode *inode, struct exfat_dir_entry *info) exfat_save_attr(inode, info->attr); inode->i_blocks = round_up(i_size_read(inode), sbi->cluster_size) >> 9; +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 7, 0) + inode_set_mtime_to_ts(inode, info->mtime); +#else inode->i_mtime = info->mtime; +#endif +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 6, 0) + inode_set_ctime_to_ts(inode, info->mtime); +#else inode->i_ctime = info->mtime; +#endif ei->i_crtime = info->crtime; +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 7, 0) + inode_set_atime_to_ts(inode, info->atime); +#else inode->i_atime = info->atime; +#endif return 0; } diff --git a/fs/exfat/misc.c b/fs/exfat/misc.c index e7ae6f629d6e..a744a1fb1e33 100644 --- a/fs/exfat/misc.c +++ b/fs/exfat/misc.c @@ -163,6 +163,16 @@ void exfat_truncate_atime(struct timespec *ts) ts->tv_nsec = 0; } +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 7, 0) +void exfat_truncate_inode_atime(struct inode *inode) +{ + struct timespec64 atime = inode_get_atime(inode); + + exfat_truncate_atime(&atime); + inode_set_atime_to_ts(inode, atime); +} +#endif + u16 exfat_calc_chksum16(void *data, int len, u16 chksum, int type) { int i; diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index e6971c758892..ef9a6df20998 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -378,14 +378,20 @@ static int exfat_find_empty_entry(struct inode *inode, if (exfat_check_max_dentries(inode)) return -ENOSPC; - /* we trust p_dir->size regardless of FAT type */ - if (exfat_find_last_cluster(sb, p_dir, &last_clu)) - return -EIO; - /* * Allocate new cluster to this directory */ - exfat_chain_set(&clu, last_clu + 1, 0, p_dir->flags); + if (ei->start_clu != EXFAT_EOF_CLUSTER) { + /* we trust p_dir->size regardless of FAT type */ + if (exfat_find_last_cluster(sb, p_dir, &last_clu)) + return -EIO; + + exfat_chain_set(&clu, last_clu + 1, 0, p_dir->flags); + } else { + /* This directory is empty */ + exfat_chain_set(&clu, EXFAT_EOF_CLUSTER, 0, + ALLOC_NO_FAT_CHAIN); + } /* allocate a cluster */ ret = exfat_alloc_cluster(inode, 1, &clu, IS_DIRSYNC(inode)); @@ -395,6 +401,11 @@ static int exfat_find_empty_entry(struct inode *inode, if (exfat_zeroed_cluster(inode, clu.dir)) return -EIO; + if (ei->start_clu == EXFAT_EOF_CLUSTER) { + ei->start_clu = clu.dir; + p_dir->dir = clu.dir; + } + /* append to the FAT chain */ if (clu.flags != p_dir->flags) { /* no-fat-chain bit is disabled, @@ -534,7 +545,7 @@ static int exfat_add_entry(struct inode *inode, const char *path, goto out; } - if (type == TYPE_DIR) { + if (type == TYPE_DIR && !sbi->options.zero_size_dir) { ret = exfat_alloc_new_dir(inode, &clu); if (ret) goto out; @@ -561,13 +572,16 @@ static int exfat_add_entry(struct inode *inode, const char *path, info->type = type; if (type == TYPE_FILE) { - info->attr = ATTR_ARCHIVE; + info->attr = EXFAT_ATTR_ARCHIVE; info->start_clu = EXFAT_EOF_CLUSTER; info->size = 0; info->num_subdirs = 0; } else { - info->attr = ATTR_SUBDIR; - info->start_clu = start_clu; + info->attr = EXFAT_ATTR_SUBDIR; + if (sbi->options.zero_size_dir) + info->start_clu = EXFAT_EOF_CLUSTER; + else + info->start_clu = start_clu; info->size = clu_size; info->num_subdirs = EXFAT_MIN_SUBDIR; } @@ -611,7 +625,15 @@ static int exfat_create(struct inode *dir, struct dentry *dentry, umode_t mode, dir->i_version++; #endif #if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 10, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 6, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 7, 0) + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); +#else + dir->i_mtime = inode_set_ctime_current(dir); +#endif +#else dir->i_ctime = dir->i_mtime = current_time(dir); +#endif #else dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC; #endif @@ -632,14 +654,23 @@ static int exfat_create(struct inode *dir, struct dentry *dentry, umode_t mode, inode->i_version++; #endif +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 7, 0) + EXFAT_I(inode)->i_crtime = simple_inode_init_ts(inode); + exfat_truncate_inode_atime(inode); +#else #if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 10, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 6, 0) + inode->i_mtime = inode->i_atime = EXFAT_I(inode)->i_crtime = inode_set_ctime_current(inode); +#else inode->i_mtime = inode->i_atime = inode->i_ctime = EXFAT_I(inode)->i_crtime = current_time(inode); +#endif #else inode->i_mtime = inode->i_atime = inode->i_ctime = EXFAT_I(inode)->i_crtime = CURRENT_TIME_SEC; #endif exfat_truncate_atime(&inode->i_atime); +#endif /* timestamp is already written, so mark_inode_dirty() is unneeded. */ d_instantiate(dentry, inode); @@ -709,7 +740,7 @@ static int exfat_find(struct inode *dir, struct qstr *qname, info->type = exfat_get_entry_type(ep); info->attr = le16_to_cpu(ep->dentry.file.attr); info->size = le64_to_cpu(ep2->dentry.stream.valid_size); - if ((info->type == TYPE_FILE) && (info->size == 0)) { + if (info->size == 0) { info->flags = ALLOC_NO_FAT_CHAIN; info->start_clu = EXFAT_EOF_CLUSTER; } else { @@ -888,24 +919,43 @@ static int exfat_unlink(struct inode *dir, struct dentry *dentry) #else dir->i_version++; #endif -#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 10, 0) - dir->i_mtime = dir->i_atime = current_time(dir); + +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 7, 0) + simple_inode_init_ts(dir); + exfat_truncate_inode_atime(dir); #else - dir->i_mtime = dir->i_atime = CURRENT_TIME_SEC; +#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 10, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 6, 0) + dir->i_mtime = dir->i_atime = inode_set_ctime_current(dir); +#else + dir->i_mtime = dir->i_atime = dir->i_ctime = current_time(dir); +#endif +#else + dir->i_mtime = dir->i_atime = dir->i_ctime = CURRENT_TIME_SEC; #endif exfat_truncate_atime(&dir->i_atime); +#endif if (IS_DIRSYNC(dir)) exfat_sync_inode(dir); else mark_inode_dirty(dir); clear_nlink(inode); -#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 10, 0) - inode->i_mtime = inode->i_atime = current_time(inode); +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 7, 0) + simple_inode_init_ts(inode); + exfat_truncate_inode_atime(inode); #else - inode->i_mtime = inode->i_atime = CURRENT_TIME_SEC; +#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 10, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 6, 0) + inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); +#else + inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); +#endif +#else + inode->i_mtime = inode->i_atime = dir->i_ctime = CURRENT_TIME_SEC; #endif exfat_truncate_atime(&inode->i_atime); +#endif exfat_unhash_inode(inode); #if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 16, 0) exfat_d_version_set(dentry, inode_query_iversion(dir)); @@ -950,7 +1000,15 @@ static int exfat_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) #endif #if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 10, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 6, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 7, 0) + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); +#else + dir->i_mtime = inode_set_ctime_current(dir); +#endif +#else dir->i_ctime = dir->i_mtime = current_time(dir); +#endif #else dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC; #endif @@ -971,14 +1029,23 @@ static int exfat_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) #else inode->i_version++; #endif +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 7, 0) + EXFAT_I(inode)->i_crtime = simple_inode_init_ts(inode); + exfat_truncate_inode_atime(inode); +#else #if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 10, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 6, 0) + inode->i_mtime = inode->i_atime = EXFAT_I(inode)->i_crtime = inode_set_ctime_current(inode); +#else inode->i_mtime = inode->i_atime = inode->i_ctime = EXFAT_I(inode)->i_crtime = current_time(inode); +#endif #else inode->i_mtime = inode->i_atime = inode->i_ctime = EXFAT_I(inode)->i_crtime = CURRENT_TIME_SEC; #endif exfat_truncate_atime(&inode->i_atime); +#endif /* timestamp is already written, so mark_inode_dirty() is unneeded. */ d_instantiate(dentry, inode); @@ -1000,6 +1067,9 @@ static int exfat_check_dir_empty(struct super_block *sb, dentries_per_clu = sbi->dentries_per_clu; + if (p_dir->dir == EXFAT_EOF_CLUSTER) + return 0; + exfat_chain_dup(&clu, p_dir); while (clu.dir != EXFAT_EOF_CLUSTER) { @@ -1093,12 +1163,21 @@ static int exfat_rmdir(struct inode *dir, struct dentry *dentry) #else dir->i_version++; #endif -#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 10, 0) - dir->i_mtime = dir->i_atime = current_time(dir); +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 7, 0) + simple_inode_init_ts(dir); + exfat_truncate_inode_atime(dir); #else - dir->i_mtime = dir->i_atime = CURRENT_TIME_SEC; +#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 10, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 6, 0) + dir->i_mtime = dir->i_atime = inode_set_ctime_current(dir); +#else + dir->i_mtime = dir->i_atime = dir->i_ctime = current_time(dir); +#endif +#else + dir->i_mtime = dir->i_atime = inode->i_ctime = CURRENT_TIME_SEC; #endif exfat_truncate_atime(&dir->i_atime); +#endif if (IS_DIRSYNC(dir)) exfat_sync_inode(dir); else @@ -1106,12 +1185,21 @@ static int exfat_rmdir(struct inode *dir, struct dentry *dentry) drop_nlink(dir); clear_nlink(inode); -#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 10, 0) - inode->i_mtime = inode->i_atime = current_time(inode); +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 7, 0) + simple_inode_init_ts(inode); + exfat_truncate_inode_atime(inode); #else - inode->i_mtime = inode->i_atime = CURRENT_TIME_SEC; +#if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 10, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 6, 0) + inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); +#else + inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); +#endif +#else + inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; #endif exfat_truncate_atime(&inode->i_atime); +#endif exfat_unhash_inode(inode); #if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 16, 0) exfat_d_version_set(dentry, inode_query_iversion(dir)); @@ -1160,8 +1248,8 @@ static int exfat_rename_file(struct inode *inode, struct exfat_chain *p_dir, *epnew = *epold; if (exfat_get_entry_type(epnew) == TYPE_FILE) { - epnew->dentry.file.attr |= cpu_to_le16(ATTR_ARCHIVE); - ei->attr |= ATTR_ARCHIVE; + epnew->dentry.file.attr |= cpu_to_le16(EXFAT_ATTR_ARCHIVE); + ei->attr |= EXFAT_ATTR_ARCHIVE; } exfat_update_bh(new_bh, sync); brelse(old_bh); @@ -1192,8 +1280,8 @@ static int exfat_rename_file(struct inode *inode, struct exfat_chain *p_dir, ei->entry = newentry; } else { if (exfat_get_entry_type(epold) == TYPE_FILE) { - epold->dentry.file.attr |= cpu_to_le16(ATTR_ARCHIVE); - ei->attr |= ATTR_ARCHIVE; + epold->dentry.file.attr |= cpu_to_le16(EXFAT_ATTR_ARCHIVE); + ei->attr |= EXFAT_ATTR_ARCHIVE; } exfat_update_bh(old_bh, sync); brelse(old_bh); @@ -1241,8 +1329,8 @@ static int exfat_move_file(struct inode *inode, struct exfat_chain *p_olddir, *epnew = *epmov; if (exfat_get_entry_type(epnew) == TYPE_FILE) { - epnew->dentry.file.attr |= cpu_to_le16(ATTR_ARCHIVE); - ei->attr |= ATTR_ARCHIVE; + epnew->dentry.file.attr |= cpu_to_le16(EXFAT_ATTR_ARCHIVE); + ei->attr |= EXFAT_ATTR_ARCHIVE; } exfat_update_bh(new_bh, IS_DIRSYNC(inode)); brelse(mov_bh); @@ -1383,7 +1471,8 @@ static int __exfat_rename(struct inode *old_parent_inode, } /* Free the clusters if new_inode is a dir(as if exfat_rmdir) */ - if (new_entry_type == TYPE_DIR) { + if (new_entry_type == TYPE_DIR && + new_ei->start_clu != EXFAT_EOF_CLUSTER) { /* new_ei, new_clu_to_free */ struct exfat_chain new_clu_to_free; @@ -1463,13 +1552,22 @@ static int exfat_rename(struct inode *old_dir, struct dentry *old_dentry, new_dir->i_version++; #endif #if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 10, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 6, 0) + simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry); + EXFAT_I(new_dir)->i_crtime = current_time(new_dir); +#else new_dir->i_ctime = new_dir->i_mtime = new_dir->i_atime = EXFAT_I(new_dir)->i_crtime = current_time(new_dir); +#endif #else new_dir->i_ctime = new_dir->i_mtime = new_dir->i_atime = EXFAT_I(new_dir)->i_crtime = CURRENT_TIME_SEC; #endif +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 7, 0) + exfat_truncate_inode_atime(new_dir); +#else exfat_truncate_atime(&new_dir->i_atime); +#endif if (IS_DIRSYNC(new_dir)) exfat_sync_inode(new_dir); else @@ -1496,7 +1594,9 @@ static int exfat_rename(struct inode *old_dir, struct dentry *old_dentry, old_dir->i_version++; #endif #if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 10, 0) +#if LINUX_VERSION_CODE <= KERNEL_VERSION(6, 6, 0) old_dir->i_ctime = old_dir->i_mtime = current_time(old_dir); +#endif #else old_dir->i_ctime = old_dir->i_mtime = CURRENT_TIME_SEC; #endif @@ -1518,8 +1618,12 @@ static int exfat_rename(struct inode *old_dir, struct dentry *old_dentry, WARN_ON(new_inode->i_nlink == 0); } #if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 10, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 6, 0) + EXFAT_I(new_inode)->i_crtime = current_time(new_inode); +#else new_inode->i_ctime = EXFAT_I(new_inode)->i_crtime = current_time(new_inode); +#endif #else new_inode->i_ctime = EXFAT_I(new_inode)->i_crtime = CURRENT_TIME_SEC; diff --git a/fs/exfat/super.c b/fs/exfat/super.c index 665c296e4ad4..decf1c68323b 100644 --- a/fs/exfat/super.c +++ b/fs/exfat/super.c @@ -195,6 +195,8 @@ static int exfat_show_options(struct seq_file *m, struct dentry *root) seq_puts(m, ",sys_tz"); else if (opts->time_offset) seq_printf(m, ",time_offset=%d", opts->time_offset); + if (opts->zero_size_dir) + seq_puts(m, ",zero_size_dir"); return 0; } @@ -278,6 +280,7 @@ enum { Opt_keep_last_dots, Opt_sys_tz, Opt_time_offset, + Opt_zero_size_dir, /* Deprecated options */ Opt_utf8, @@ -323,6 +326,7 @@ static const struct fs_parameter_spec exfat_param_specs[] = { fsparam_flag("keep_last_dots", Opt_keep_last_dots), fsparam_flag("sys_tz", Opt_sys_tz), fsparam_s32("time_offset", Opt_time_offset), + fsparam_flag("zero_size_dir", Opt_zero_size_dir), __fsparam(NULL, "utf8", Opt_utf8, fs_param_deprecated, NULL), __fsparam(NULL, "debug", Opt_debug, fs_param_deprecated, @@ -403,6 +407,9 @@ static int exfat_parse_param(struct fs_context *fc, struct fs_parameter *param) return -EINVAL; opts->time_offset = result.int_32; break; + case Opt_zero_size_dir: + opts->zero_size_dir = true; + break; case Opt_utf8: case Opt_debug: case Opt_namecase: @@ -435,6 +442,7 @@ enum { Opt_debug, Opt_namecase, Opt_codepage, + Opt_zero_size_dir, Opt_fs, }; @@ -454,6 +462,7 @@ static const match_table_t exfat_tokens = { {Opt_namecase, "namecase=%u"}, {Opt_debug, "debug"}, {Opt_utf8, "utf8"}, + {Opt_zero_size_dir, "zero_size_dir"}, {Opt_err, NULL} }; @@ -545,6 +554,9 @@ static int parse_options(struct super_block *sb, char *options, int silent, case Opt_namecase: case Opt_codepage: break; + case Opt_zero_size_dir: + opts->zero_size_dir = true; + break; default: if (!silent) { exfat_err(sb, @@ -628,7 +640,7 @@ static int exfat_read_root(struct inode *inode) inode->i_version++; #endif inode->i_generation = 0; - inode->i_mode = exfat_make_mode(sbi, ATTR_SUBDIR, 0777); + inode->i_mode = exfat_make_mode(sbi, EXFAT_ATTR_SUBDIR, 0777); inode->i_op = &exfat_dir_inode_operations; inode->i_fop = &exfat_dir_operations; @@ -637,15 +649,24 @@ static int exfat_read_root(struct inode *inode) ei->i_size_aligned = i_size_read(inode); ei->i_size_ondisk = i_size_read(inode); - exfat_save_attr(inode, ATTR_SUBDIR); + exfat_save_attr(inode, EXFAT_ATTR_SUBDIR); +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 7, 0) + ei->i_crtime = simple_inode_init_ts(inode); + exfat_truncate_inode_atime(inode); +#else #if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 10, 0) +#if LINUX_VERSION_CODE >= KERNEL_VERSION(6, 6, 0) + inode->i_mtime = inode->i_atime = ei->i_crtime = inode_set_ctime_current(inode); +#else inode->i_mtime = inode->i_atime = inode->i_ctime = ei->i_crtime = current_time(inode); +#endif #else inode->i_mtime = inode->i_atime = inode->i_ctime = ei->i_crtime = CURRENT_TIME_SEC; #endif exfat_truncate_atime(&inode->i_atime); +#endif return 0; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 8875fac9f958..0572ae09c729 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5192,11 +5192,16 @@ __acquires(bitlock) static ext4_grpblk_t ext4_last_grp_cluster(struct super_block *sb, ext4_group_t grp) { - if (grp < ext4_get_groups_count(sb)) - return EXT4_CLUSTERS_PER_GROUP(sb) - 1; - return (ext4_blocks_count(EXT4_SB(sb)->s_es) - - ext4_group_first_block_no(sb, grp) - 1) >> - EXT4_CLUSTER_BITS(sb); + unsigned long nr_clusters_in_group; + + if (grp < (ext4_get_groups_count(sb) - 1)) + nr_clusters_in_group = EXT4_CLUSTERS_PER_GROUP(sb); + else + nr_clusters_in_group = (ext4_blocks_count(EXT4_SB(sb)->s_es) - + ext4_group_first_block_no(sb, grp)) + >> EXT4_CLUSTER_BITS(sb); + + return nr_clusters_in_group - 1; } static bool ext4_trim_interrupted(void) diff --git a/include/dt-bindings/clock/qcom,gcc-sdm660.h b/include/dt-bindings/clock/qcom,gcc-sdm660.h index 33c615c35ba2..05868793e44a 100644 --- a/include/dt-bindings/clock/qcom,gcc-sdm660.h +++ b/include/dt-bindings/clock/qcom,gcc-sdm660.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2016-2017, 2019-2020, The Linux Foundation. All rights reserved. + * Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved. */ #ifndef _DT_BINDINGS_CLK_MSM_GCC_660_H @@ -195,5 +196,6 @@ #define GCC_USB_20_BCR 6 #define GCC_USB_30_BCR 7 #define GCC_USB_PHY_CFG_AHB2PHY_BCR 8 +#define GCC_SDCC1_BCR 9 #endif diff --git a/include/linux/device.h b/include/linux/device.h index 11fb0bdce054..caceae0ac55b 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1678,6 +1678,9 @@ do { \ WARN_ONCE(condition, "%s %s: " format, \ dev_driver_string(dev), dev_name(dev), ## arg) +extern __printf(3, 4) +int dev_err_probe(const struct device *dev, int err, const char *fmt, ...); + /* Create alias, so I can be autoloaded. */ #define MODULE_ALIAS_CHARDEV(major,minor) \ MODULE_ALIAS("char-major-" __stringify(major) "-" __stringify(minor)) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index d9217645791a..659a40a9cabd 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -220,6 +220,43 @@ static inline int page_cache_add_speculative(struct page *page, int count) return 1; } +/** + * attach_page_private - Attach private data to a page. + * @page: Page to attach data to. + * @data: Data to attach to page. + * + * Attaching private data to a page increments the page's reference count. + * The data must be detached before the page will be freed. + */ +static inline void attach_page_private(struct page *page, void *data) +{ + get_page(page); + set_page_private(page, (unsigned long)data); + SetPagePrivate(page); +} + +/** + * detach_page_private - Detach private data from a page. + * @page: Page to detach data from. + * + * Removes the data that was previously attached to the page and decrements + * the refcount on the page. + * + * Return: Data that was attached to the page. + */ +static inline void *detach_page_private(struct page *page) +{ + void *data = (void *)page_private(page); + + if (!PagePrivate(page)) + return NULL; + ClearPagePrivate(page); + set_page_private(page, 0); + put_page(page); + + return data; +} + #ifdef CONFIG_NUMA extern struct page *__page_cache_alloc(gfp_t gfp); #else diff --git a/include/linux/sched.h b/include/linux/sched.h index b059c2cc221f..f3ffeba0e0ab 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1863,6 +1863,9 @@ extern int idle_cpu(int cpu); extern int available_idle_cpu(int cpu); extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *); extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *); +extern int sched_set_fifo(struct task_struct *p); +extern int sched_set_fifo_low(struct task_struct *p); +extern int sched_set_normal(struct task_struct *p, int nice); extern int sched_setattr(struct task_struct *, const struct sched_attr *); extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *); extern struct task_struct *idle_task(int cpu); diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 8ceba9b8e51e..e235de96962e 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -153,6 +153,7 @@ struct spi_device { #define SPI_MODE_1 (0|SPI_CPHA) #define SPI_MODE_2 (SPI_CPOL|0) #define SPI_MODE_3 (SPI_CPOL|SPI_CPHA) +#define SPI_MODE_X_MASK (SPI_CPOL|SPI_CPHA) #define SPI_CS_HIGH 0x04 /* chipselect active high? */ #define SPI_LSB_FIRST 0x08 /* per-word bits-on-wire */ #define SPI_3WIRE 0x10 /* SI/SO signals shared */ diff --git a/include/linux/units.h b/include/linux/units.h new file mode 100644 index 000000000000..a0af6d2ef4e5 --- /dev/null +++ b/include/linux/units.h @@ -0,0 +1,92 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_UNITS_H +#define _LINUX_UNITS_H + +#include + +#define HZ_PER_KHZ 1000UL +#define KHZ_PER_MHZ 1000UL +#define HZ_PER_MHZ 1000000UL + +#define MILLIWATT_PER_WATT 1000UL +#define MICROWATT_PER_MILLIWATT 1000UL +#define MICROWATT_PER_WATT 1000000UL + +#define ABSOLUTE_ZERO_MILLICELSIUS -273150 + +static inline long milli_kelvin_to_millicelsius(long t) +{ + return t + ABSOLUTE_ZERO_MILLICELSIUS; +} + +static inline long millicelsius_to_milli_kelvin(long t) +{ + return t - ABSOLUTE_ZERO_MILLICELSIUS; +} + +#define MILLIDEGREE_PER_DEGREE 1000 +#define MILLIDEGREE_PER_DECIDEGREE 100 + +static inline long kelvin_to_millicelsius(long t) +{ + return milli_kelvin_to_millicelsius(t * MILLIDEGREE_PER_DEGREE); +} + +static inline long millicelsius_to_kelvin(long t) +{ + t = millicelsius_to_milli_kelvin(t); + + return DIV_ROUND_CLOSEST(t, MILLIDEGREE_PER_DEGREE); +} + +static inline long deci_kelvin_to_celsius(long t) +{ + t = milli_kelvin_to_millicelsius(t * MILLIDEGREE_PER_DECIDEGREE); + + return DIV_ROUND_CLOSEST(t, MILLIDEGREE_PER_DEGREE); +} + +static inline long celsius_to_deci_kelvin(long t) +{ + t = millicelsius_to_milli_kelvin(t * MILLIDEGREE_PER_DEGREE); + + return DIV_ROUND_CLOSEST(t, MILLIDEGREE_PER_DECIDEGREE); +} + +/** + * deci_kelvin_to_millicelsius_with_offset - convert Kelvin to Celsius + * @t: temperature value in decidegrees Kelvin + * @offset: difference between Kelvin and Celsius in millidegrees + * + * Return: temperature value in millidegrees Celsius + */ +static inline long deci_kelvin_to_millicelsius_with_offset(long t, long offset) +{ + return t * MILLIDEGREE_PER_DECIDEGREE - offset; +} + +static inline long deci_kelvin_to_millicelsius(long t) +{ + return milli_kelvin_to_millicelsius(t * MILLIDEGREE_PER_DECIDEGREE); +} + +static inline long millicelsius_to_deci_kelvin(long t) +{ + t = millicelsius_to_milli_kelvin(t); + + return DIV_ROUND_CLOSEST(t, MILLIDEGREE_PER_DECIDEGREE); +} + +static inline long kelvin_to_celsius(long t) +{ + return t + DIV_ROUND_CLOSEST(ABSOLUTE_ZERO_MILLICELSIUS, + MILLIDEGREE_PER_DEGREE); +} + +static inline long celsius_to_kelvin(long t) +{ + return t - DIV_ROUND_CLOSEST(ABSOLUTE_ZERO_MILLICELSIUS, + MILLIDEGREE_PER_DEGREE); +} + +#endif /* _LINUX_UNITS_H */ diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h index 49aa79c7b278..581cd37aa98b 100644 --- a/include/net/llc_pdu.h +++ b/include/net/llc_pdu.h @@ -262,8 +262,7 @@ static inline void llc_pdu_header_init(struct sk_buff *skb, u8 type, */ static inline void llc_pdu_decode_sa(struct sk_buff *skb, u8 *sa) { - if (skb->protocol == htons(ETH_P_802_2)) - memcpy(sa, eth_hdr(skb)->h_source, ETH_ALEN); + memcpy(sa, eth_hdr(skb)->h_source, ETH_ALEN); } /** @@ -275,8 +274,7 @@ static inline void llc_pdu_decode_sa(struct sk_buff *skb, u8 *sa) */ static inline void llc_pdu_decode_da(struct sk_buff *skb, u8 *da) { - if (skb->protocol == htons(ETH_P_802_2)) - memcpy(da, eth_hdr(skb)->h_dest, ETH_ALEN); + memcpy(da, eth_hdr(skb)->h_dest, ETH_ALEN); } /** diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index 291f3f49d8ab..7b5252f1595d 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -19,6 +19,7 @@ #define SQUASHFS_MAGIC 0x73717368 #define ECRYPTFS_SUPER_MAGIC 0xf15f #define EFS_SUPER_MAGIC 0x414A53 +#define EROFS_SUPER_MAGIC_V1 0xE0F5E1E2 #define EXT2_SUPER_MAGIC 0xEF53 #define EXT3_SUPER_MAGIC 0xEF53 #define XENFS_SUPER_MAGIC 0xabba1974 diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 9db7f2f93fae..a818ad6ade9c 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -596,11 +596,11 @@ static int crc32_threadfn(void *data) unsigned i; while (1) { - wait_event(d->go, atomic_read(&d->ready) || + wait_event(d->go, atomic_read_acquire(&d->ready) || kthread_should_stop()); if (kthread_should_stop()) { d->thr = NULL; - atomic_set(&d->stop, 1); + atomic_set_release(&d->stop, 1); wake_up(&d->done); break; } @@ -609,7 +609,7 @@ static int crc32_threadfn(void *data) for (i = 0; i < d->run_threads; i++) *d->crc32 = crc32_le(*d->crc32, d->unc[i], *d->unc_len[i]); - atomic_set(&d->stop, 1); + atomic_set_release(&d->stop, 1); wake_up(&d->done); } return 0; @@ -639,12 +639,12 @@ static int lzo_compress_threadfn(void *data) struct cmp_data *d = data; while (1) { - wait_event(d->go, atomic_read(&d->ready) || + wait_event(d->go, atomic_read_acquire(&d->ready) || kthread_should_stop()); if (kthread_should_stop()) { d->thr = NULL; d->ret = -1; - atomic_set(&d->stop, 1); + atomic_set_release(&d->stop, 1); wake_up(&d->done); break; } @@ -653,7 +653,7 @@ static int lzo_compress_threadfn(void *data) d->ret = lzo1x_1_compress(d->unc, d->unc_len, d->cmp + LZO_HEADER, &d->cmp_len, d->wrk); - atomic_set(&d->stop, 1); + atomic_set_release(&d->stop, 1); wake_up(&d->done); } return 0; @@ -791,7 +791,7 @@ static int save_image_lzo(struct swap_map_handle *handle, data[thr].unc_len = off; - atomic_set(&data[thr].ready, 1); + atomic_set_release(&data[thr].ready, 1); wake_up(&data[thr].go); } @@ -799,12 +799,12 @@ static int save_image_lzo(struct swap_map_handle *handle, break; crc->run_threads = thr; - atomic_set(&crc->ready, 1); + atomic_set_release(&crc->ready, 1); wake_up(&crc->go); for (run_threads = thr, thr = 0; thr < run_threads; thr++) { wait_event(data[thr].done, - atomic_read(&data[thr].stop)); + atomic_read_acquire(&data[thr].stop)); atomic_set(&data[thr].stop, 0); ret = data[thr].ret; @@ -843,7 +843,7 @@ static int save_image_lzo(struct swap_map_handle *handle, } } - wait_event(crc->done, atomic_read(&crc->stop)); + wait_event(crc->done, atomic_read_acquire(&crc->stop)); atomic_set(&crc->stop, 0); } @@ -1124,12 +1124,12 @@ static int lzo_decompress_threadfn(void *data) struct dec_data *d = data; while (1) { - wait_event(d->go, atomic_read(&d->ready) || + wait_event(d->go, atomic_read_acquire(&d->ready) || kthread_should_stop()); if (kthread_should_stop()) { d->thr = NULL; d->ret = -1; - atomic_set(&d->stop, 1); + atomic_set_release(&d->stop, 1); wake_up(&d->done); break; } @@ -1142,7 +1142,7 @@ static int lzo_decompress_threadfn(void *data) flush_icache_range((unsigned long)d->unc, (unsigned long)d->unc + d->unc_len); - atomic_set(&d->stop, 1); + atomic_set_release(&d->stop, 1); wake_up(&d->done); } return 0; @@ -1330,7 +1330,7 @@ static int load_image_lzo(struct swap_map_handle *handle, } if (crc->run_threads) { - wait_event(crc->done, atomic_read(&crc->stop)); + wait_event(crc->done, atomic_read_acquire(&crc->stop)); atomic_set(&crc->stop, 0); crc->run_threads = 0; } @@ -1366,7 +1366,7 @@ static int load_image_lzo(struct swap_map_handle *handle, pg = 0; } - atomic_set(&data[thr].ready, 1); + atomic_set_release(&data[thr].ready, 1); wake_up(&data[thr].go); } @@ -1385,7 +1385,7 @@ static int load_image_lzo(struct swap_map_handle *handle, for (run_threads = thr, thr = 0; thr < run_threads; thr++) { wait_event(data[thr].done, - atomic_read(&data[thr].stop)); + atomic_read_acquire(&data[thr].stop)); atomic_set(&data[thr].stop, 0); ret = data[thr].ret; @@ -1416,7 +1416,7 @@ static int load_image_lzo(struct swap_map_handle *handle, ret = snapshot_write_next(snapshot); if (ret <= 0) { crc->run_threads = thr + 1; - atomic_set(&crc->ready, 1); + atomic_set_release(&crc->ready, 1); wake_up(&crc->go); goto out_finish; } @@ -1424,13 +1424,13 @@ static int load_image_lzo(struct swap_map_handle *handle, } crc->run_threads = thr; - atomic_set(&crc->ready, 1); + atomic_set_release(&crc->ready, 1); wake_up(&crc->go); } out_finish: if (crc->run_threads) { - wait_event(crc->done, atomic_read(&crc->stop)); + wait_event(crc->done, atomic_read_acquire(&crc->stop)); atomic_set(&crc->stop, 0); } stop = ktime_get(); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 244a3029cac3..2c83af037acf 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5312,6 +5312,8 @@ static int _sched_setscheduler(struct task_struct *p, int policy, * @policy: new policy. * @param: structure containing the new RT priority. * + * Use sched_set_fifo(), read its comment. + * * Return: 0 on success. An error code otherwise. * * NOTE that the task may be already dead. @@ -5354,6 +5356,51 @@ int sched_setscheduler_nocheck(struct task_struct *p, int policy, } EXPORT_SYMBOL_GPL(sched_setscheduler_nocheck); +/* + * SCHED_FIFO is a broken scheduler model; that is, it is fundamentally + * incapable of resource management, which is the one thing an OS really should + * be doing. + * + * This is of course the reason it is limited to privileged users only. + * + * Worse still; it is fundamentally impossible to compose static priority + * workloads. You cannot take two correctly working static prio workloads + * and smash them together and still expect them to work. + * + * For this reason 'all' FIFO tasks the kernel creates are basically at: + * + * MAX_RT_PRIO / 2 + * + * The administrator _MUST_ configure the system, the kernel simply doesn't + * know enough information to make a sensible choice. + */ +int sched_set_fifo(struct task_struct *p) +{ + struct sched_param sp = { .sched_priority = MAX_RT_PRIO / 2 }; + return sched_setscheduler_nocheck(p, SCHED_FIFO, &sp); +} +EXPORT_SYMBOL_GPL(sched_set_fifo); + +/* + * For when you don't much care about FIFO, but want to be above SCHED_NORMAL. + */ +int sched_set_fifo_low(struct task_struct *p) +{ + struct sched_param sp = { .sched_priority = 1 }; + return sched_setscheduler_nocheck(p, SCHED_FIFO, &sp); +} +EXPORT_SYMBOL_GPL(sched_set_fifo_low); + +int sched_set_normal(struct task_struct *p, int nice) +{ + struct sched_attr attr = { + .sched_policy = SCHED_NORMAL, + .sched_nice = nice, + }; + return sched_setattr_nocheck(p, &attr); +} +EXPORT_SYMBOL_GPL(sched_set_normal); + static int do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) { diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index 83c2a0598c64..33c463967bb3 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -574,7 +574,12 @@ __tracing_map_insert(struct tracing_map *map, void *key, bool lookup_only) } memcpy(elt->key, key, map->key_size); - entry->val = elt; + /* + * Ensure the initialization is visible and + * publish the elt. + */ + smp_wmb(); + WRITE_ONCE(entry->val, elt); atomic64_inc(&map->hits); return entry->val; diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 74042b9d7f73..231eae2f1685 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -120,12 +120,16 @@ static int vlan_changelink(struct net_device *dev, struct nlattr *tb[], } if (data[IFLA_VLAN_INGRESS_QOS]) { nla_for_each_nested(attr, data[IFLA_VLAN_INGRESS_QOS], rem) { + if (nla_type(attr) != IFLA_VLAN_QOS_MAPPING) + continue; m = nla_data(attr); vlan_dev_set_ingress_priority(dev, m->to, m->from); } } if (data[IFLA_VLAN_EGRESS_QOS]) { nla_for_each_nested(attr, data[IFLA_VLAN_EGRESS_QOS], rem) { + if (nla_type(attr) != IFLA_VLAN_QOS_MAPPING) + continue; m = nla_data(attr); err = vlan_dev_set_egress_priority(dev, m->from, m->to); if (err) diff --git a/net/core/sock.c b/net/core/sock.c index cbe5aa14b427..d29d06b5c242 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -531,7 +531,7 @@ static int sock_setbindtodevice(struct sock *sk, char __user *optval, /* Sorry... */ ret = -EPERM; - if (!ns_capable(net->user_ns, CAP_NET_RAW)) + if (sk->sk_bound_dev_if && !ns_capable(net->user_ns, CAP_NET_RAW)) goto out; ret = -EINVAL; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index a96f42054df5..7479979e1125 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -736,6 +736,7 @@ static void tcp_push(struct sock *sk, int flags, int mss_now, if (!test_bit(TSQ_THROTTLED, &sk->sk_tsq_flags)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING); set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); + smp_mb__after_atomic(); } /* It is possible TX completion already happened * before we set TSQ_THROTTLED. diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 5cba9199c3c9..a5c104ea477c 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -926,14 +926,15 @@ copy_uaddr: */ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { + DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name); struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); - DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name); int flags = msg->msg_flags; int noblock = flags & MSG_DONTWAIT; + int rc = -EINVAL, copied = 0, hdrlen, hh_len; struct sk_buff *skb = NULL; + struct net_device *dev; size_t size = 0; - int rc = -EINVAL, copied = 0, hdrlen; dprintk("%s: sending from %02X to %02X\n", __func__, llc->laddr.lsap, llc->daddr.lsap); @@ -953,22 +954,29 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (rc) goto out; } - hdrlen = llc->dev->hard_header_len + llc_ui_header_len(sk, addr); + dev = llc->dev; + hh_len = LL_RESERVED_SPACE(dev); + hdrlen = llc_ui_header_len(sk, addr); size = hdrlen + len; - if (size > llc->dev->mtu) - size = llc->dev->mtu; + size = min_t(size_t, size, READ_ONCE(dev->mtu)); copied = size - hdrlen; rc = -EINVAL; if (copied < 0) goto out; release_sock(sk); - skb = sock_alloc_send_skb(sk, size, noblock, &rc); + skb = sock_alloc_send_skb(sk, hh_len + size, noblock, &rc); lock_sock(sk); if (!skb) goto out; - skb->dev = llc->dev; + if (sock_flag(sk, SOCK_ZAPPED) || + llc->dev != dev || + hdrlen != llc_ui_header_len(sk, addr) || + hh_len != LL_RESERVED_SPACE(dev) || + size > READ_ONCE(dev->mtu)) + goto out; + skb->dev = dev; skb->protocol = llc_proto_type(addr->sllc_arphrd); - skb_reserve(skb, hdrlen); + skb_reserve(skb, hh_len + hdrlen); rc = memcpy_from_msg(skb_put(skb, copied), msg, copied); if (rc) goto out; diff --git a/net/llc/llc_core.c b/net/llc/llc_core.c index 64d4bef04e73..4900a27b5176 100644 --- a/net/llc/llc_core.c +++ b/net/llc/llc_core.c @@ -135,22 +135,15 @@ static struct packet_type llc_packet_type __read_mostly = { .func = llc_rcv, }; -static struct packet_type llc_tr_packet_type __read_mostly = { - .type = cpu_to_be16(ETH_P_TR_802_2), - .func = llc_rcv, -}; - static int __init llc_init(void) { dev_add_pack(&llc_packet_type); - dev_add_pack(&llc_tr_packet_type); return 0; } static void __exit llc_exit(void) { dev_remove_pack(&llc_packet_type); - dev_remove_pack(&llc_tr_packet_type); } module_init(llc_init); diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index cd7e01ea8144..5eb71d276706 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -385,7 +385,7 @@ static int rds_recv_track_latency(struct rds_sock *rs, char __user *optval, rs->rs_rx_traces = trace.rx_traces; for (i = 0; i < rs->rs_rx_traces; i++) { - if (trace.rx_trace_pos[i] > RDS_MSG_RX_DGRAM_TRACE_MAX) { + if (trace.rx_trace_pos[i] >= RDS_MSG_RX_DGRAM_TRACE_MAX) { rs->rs_rx_traces = 0; return -EFAULT; } diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index 6c4a7a5938b7..3ab14678afff 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -167,7 +167,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, } if (smc->conn.lgr && smc->conn.lgr->is_smcd && (req->diag_ext & (1 << (SMC_DIAG_DMBINFO - 1))) && - !list_empty(&smc->conn.lgr->list)) { + !list_empty(&smc->conn.lgr->list) && smc->conn.rmb_desc) { struct smc_connection *conn = &smc->conn; struct smcd_diag_dmbinfo dinfo;