diff options
185 files changed, 3094 insertions, 1568 deletions
diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs index e916c1eddf1b..4c7324524b0f 100644 --- a/Documentation/ABI/testing/sysfs-fs-f2fs +++ b/Documentation/ABI/testing/sysfs-fs-f2fs @@ -243,3 +243,11 @@ Description: - Del: echo '[h/c]!extension' > /sys/fs/f2fs/<disk>/extension_list - [h] means add/del hot file extension - [c] means add/del cold file extension + +What: /sys/fs/f2fs/<disk>/unusable +Date April 2019 +Contact: "Daniel Rosenberg" <drosen@google.com> +Description: + If checkpoint=disable, it displays the number of blocks that are unusable. + If checkpoint=enable it displays the enumber of blocks that would be unusable + if checkpoint=disable were to be set. diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt index 564ccc6c7bad..c2e941317b87 100644 --- a/Documentation/filesystems/f2fs.txt +++ b/Documentation/filesystems/f2fs.txt @@ -214,11 +214,22 @@ fsync_mode=%s Control the policy of fsync. Currently supports "posix", non-atomic files likewise "nobarrier" mount option. test_dummy_encryption Enable dummy encryption, which provides a fake fscrypt context. The fake fscrypt context is used by xfstests. -checkpoint=%s Set to "disable" to turn off checkpointing. Set to "enable" +checkpoint=%s[:%u[%]] Set to "disable" to turn off checkpointing. Set to "enable" to reenable checkpointing. Is enabled by default. While disabled, any unmounting or unexpected shutdowns will cause the filesystem contents to appear as they did when the filesystem was mounted with that option. + While mounting with checkpoint=disabled, the filesystem must + run garbage collection to ensure that all available space can + be used. If this takes too much time, the mount may return + EAGAIN. You may optionally add a value to indicate how much + of the disk you would be willing to temporarily give up to + avoid additional garbage collection. This can be given as a + number of blocks, or as a percent. For instance, mounting + with checkpoint=disable:100% would always succeed, but it may + hide up to all remaining free space. The actual space that + would be unusable can be viewed at /sys/fs/f2fs/<disk>/unusable + This space is reclaimed once checkpoint=enable. ================================================================================ DEBUGFS ENTRIES @@ -246,11 +257,14 @@ Files in /sys/fs/f2fs/<devname> .............................................................................. File Content - gc_max_sleep_time This tuning parameter controls the maximum sleep + gc_urgent_sleep_time This parameter controls sleep time for gc_urgent. + 500 ms is set by default. See above gc_urgent. + + gc_min_sleep_time This tuning parameter controls the minimum sleep time for the garbage collection thread. Time is in milliseconds. - gc_min_sleep_time This tuning parameter controls the minimum sleep + gc_max_sleep_time This tuning parameter controls the maximum sleep time for the garbage collection thread. Time is in milliseconds. @@ -270,9 +284,6 @@ Files in /sys/fs/f2fs/<devname> to 1, background thread starts to do GC by given gc_urgent_sleep_time interval. - gc_urgent_sleep_time This parameter controls sleep time for gc_urgent. - 500 ms is set by default. See above gc_urgent. - reclaim_segments This parameter controls the number of prefree segments to be reclaimed. If the number of prefree segments is larger than the number of segments @@ -287,7 +298,16 @@ Files in /sys/fs/f2fs/<devname> checkpoint is triggered, and issued during the checkpoint. By default, it is disabled with 0. - trim_sections This parameter controls the number of sections + discard_granularity This parameter controls the granularity of discard + command size. It will issue discard commands iif + the size is larger than given granularity. Its + unit size is 4KB, and 4 (=16KB) is set by default. + The maximum value is 128 (=512KB). + + reserved_blocks This parameter indicates the number of blocks that + f2fs reserves internally for root. + + batched_trim_sections This parameter controls the number of sections to be trimmed out in batch mode when FITRIM conducts. 32 sections is set by default. @@ -309,11 +329,35 @@ Files in /sys/fs/f2fs/<devname> the number is less than this value, it triggers in-place-updates. + min_seq_blocks This parameter controls the threshold to serialize + write IOs issued by multiple threads in parallel. + + min_hot_blocks This parameter controls the threshold to allocate + a hot data log for pending data blocks to write. + + min_ssr_sections This parameter adds the threshold when deciding + SSR block allocation. If this is large, SSR mode + will be enabled early. + + ram_thresh This parameter controls the memory footprint used + by free nids and cached nat entries. By default, + 10 is set, which indicates 10 MB / 1 GB RAM. + + ra_nid_pages When building free nids, F2FS reads NAT blocks + ahead for speed up. Default is 0. + + dirty_nats_ratio Given dirty ratio of cached nat entries, F2FS + determines flushing them in background. + max_victim_search This parameter controls the number of trials to find a victim segment when conducting SSR and cleaning operations. The default value is 4096 which covers 8GB block address range. + migration_granularity For large-sized sections, F2FS can stop GC given + this granularity instead of reclaiming entire + section. + dir_level This parameter controls the directory level to support large directory. If a directory has a number of files, it can reduce the file lookup @@ -321,9 +365,53 @@ Files in /sys/fs/f2fs/<devname> Otherwise, it needs to decrease this value to reduce the space overhead. The default value is 0. - ram_thresh This parameter controls the memory footprint used - by free nids and cached nat entries. By default, - 10 is set, which indicates 10 MB / 1 GB RAM. + cp_interval F2FS tries to do checkpoint periodically, 60 secs + by default. + + idle_interval F2FS detects system is idle, if there's no F2FS + operations during given interval, 5 secs by + default. + + discard_idle_interval F2FS detects the discard thread is idle, given + time interval. Default is 5 secs. + + gc_idle_interval F2FS detects the GC thread is idle, given time + interval. Default is 5 secs. + + umount_discard_timeout When unmounting the disk, F2FS waits for finishing + queued discard commands which can take huge time. + This gives time out for it, 5 secs by default. + + iostat_enable This controls to enable/disable iostat in F2FS. + + readdir_ra This enables/disabled readahead of inode blocks + in readdir, and default is enabled. + + gc_pin_file_thresh This indicates how many GC can be failed for the + pinned file. If it exceeds this, F2FS doesn't + guarantee its pinning state. 2048 trials is set + by default. + + extension_list This enables to change extension_list for hot/cold + files in runtime. + + inject_rate This controls injection rate of arbitrary faults. + + inject_type This controls injection type of arbitrary faults. + + dirty_segments This shows # of dirty segments. + + lifetime_write_kbytes This shows # of data written to the disk. + + features This shows current features enabled on F2FS. + + current_reserved_blocks This shows # of blocks currently reserved. + + unusable If checkpoint=disable, this shows the number of + blocks that are unusable. + If checkpoint=enable it shows the number of blocks + that would be unusable if checkpoint=disable were + to be set. ================================================================================ USAGE @@ -656,3 +744,28 @@ algorithm. In order to identify whether the data in the victim segment are valid or not, F2FS manages a bitmap. Each bit represents the validity of a block, and the bitmap is composed of a bit stream covering whole blocks in main area. + +Fallocate(2) Policy +------------------- + +The default policy follows the below posix rule. + +Allocating disk space + The default operation (i.e., mode is zero) of fallocate() allocates + the disk space within the range specified by offset and len. The + file size (as reported by stat(2)) will be changed if offset+len is + greater than the file size. Any subregion within the range specified + by offset and len that did not contain data before the call will be + initialized to zero. This default behavior closely resembles the + behavior of the posix_fallocate(3) library function, and is intended + as a method of optimally implementing that function. + +However, once F2FS receives ioctl(fd, F2FS_IOC_SET_PIN_FILE) in prior to +fallocate(fd, DEFAULT_MODE), it allocates on-disk blocks addressess having +zero or random data, which is useful to the below scenario where: + 1. create(fd) + 2. ioctl(fd, F2FS_IOC_SET_PIN_FILE) + 3. fallocate(fd, 0, 0, size) + 4. address = fibmap(fd, offset) + 5. open(blkdev) + 6. write(blkdev, address) @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 4 -SUBLEVEL = 186 +SUBLEVEL = 187 EXTRAVERSION = NAME = Blurry Fish Butt diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c index ea319c055f5d..1b7b4684c35b 100644 --- a/arch/arm64/crypto/sha1-ce-glue.c +++ b/arch/arm64/crypto/sha1-ce-glue.c @@ -50,7 +50,7 @@ static int sha1_ce_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { struct sha1_ce_state *sctx = shash_desc_ctx(desc); - bool finalize = !sctx->sst.count && !(len % SHA1_BLOCK_SIZE); + bool finalize = !sctx->sst.count && !(len % SHA1_BLOCK_SIZE) && len; /* * Allow the asm code to perform the finalization if there is no diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c index 0ed9486f75dd..356ca9397a86 100644 --- a/arch/arm64/crypto/sha2-ce-glue.c +++ b/arch/arm64/crypto/sha2-ce-glue.c @@ -52,7 +52,7 @@ static int sha256_ce_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { struct sha256_ce_state *sctx = shash_desc_ctx(desc); - bool finalize = !sctx->sst.count && !(len % SHA256_BLOCK_SIZE); + bool finalize = !sctx->sst.count && !(len % SHA256_BLOCK_SIZE) && len; /* * Allow the asm code to perform the finalization if there is no diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index d1ce8e2f98b9..4d0577d09681 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -141,10 +141,14 @@ static int __init acpi_fadt_sanity_check(void) */ if (table->revision < 5 || (table->revision == 5 && fadt->minor_revision < 1)) { - pr_err("Unsupported FADT revision %d.%d, should be 5.1+\n", + pr_err(FW_BUG "Unsupported FADT revision %d.%d, should be 5.1+\n", table->revision, fadt->minor_revision); - ret = -EINVAL; - goto out; + + if (!fadt->arm_boot_flags) { + ret = -EINVAL; + goto out; + } + pr_err("FADT has ARM boot flags set, assuming 5.1\n"); } if (!(fadt->flags & ACPI_FADT_HW_REDUCED)) { diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile index d5bdee115f22..d4918a2bca1b 100644 --- a/arch/mips/boot/compressed/Makefile +++ b/arch/mips/boot/compressed/Makefile @@ -66,6 +66,8 @@ OBJCOPYFLAGS_piggy.o := --add-section=.image=$(obj)/vmlinux.bin.z \ $(obj)/piggy.o: $(obj)/dummy.o $(obj)/vmlinux.bin.z FORCE $(call if_changed,objcopy) +HOSTCFLAGS_calc_vmlinuz_load_addr.o += $(LINUXINCLUDE) + # Calculate the load address of the compressed kernel image hostprogs-y := calc_vmlinuz_load_addr diff --git a/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c b/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c index 542c3ede9722..d14f75ec8273 100644 --- a/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c +++ b/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c @@ -13,7 +13,7 @@ #include <stdint.h> #include <stdio.h> #include <stdlib.h> -#include "../../../../include/linux/sizes.h" +#include <linux/sizes.h> int main(int argc, char *argv[]) { diff --git a/arch/mips/include/asm/mach-ath79/ar933x_uart.h b/arch/mips/include/asm/mach-ath79/ar933x_uart.h index c2917b39966b..bba2c8837951 100644 --- a/arch/mips/include/asm/mach-ath79/ar933x_uart.h +++ b/arch/mips/include/asm/mach-ath79/ar933x_uart.h @@ -27,8 +27,8 @@ #define AR933X_UART_CS_PARITY_S 0 #define AR933X_UART_CS_PARITY_M 0x3 #define AR933X_UART_CS_PARITY_NONE 0 -#define AR933X_UART_CS_PARITY_ODD 1 -#define AR933X_UART_CS_PARITY_EVEN 2 +#define AR933X_UART_CS_PARITY_ODD 2 +#define AR933X_UART_CS_PARITY_EVEN 3 #define AR933X_UART_CS_IF_MODE_S 2 #define AR933X_UART_CS_IF_MODE_M 0x3 #define AR933X_UART_CS_IF_MODE_NONE 0 diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c index ce0b2b4075c7..c62522bda2db 100644 --- a/arch/parisc/kernel/ptrace.c +++ b/arch/parisc/kernel/ptrace.c @@ -156,6 +156,9 @@ long arch_ptrace(struct task_struct *child, long request, if ((addr & (sizeof(unsigned long)-1)) || addr >= sizeof(struct pt_regs)) break; + if (addr == PT_IAOQ0 || addr == PT_IAOQ1) { + data |= 3; /* ensure userspace privilege */ + } if ((addr >= PT_GR1 && addr <= PT_GR31) || addr == PT_IAOQ0 || addr == PT_IAOQ1 || (addr >= PT_FR0 && addr <= PT_FR31 + 4) || @@ -189,16 +192,18 @@ long arch_ptrace(struct task_struct *child, long request, static compat_ulong_t translate_usr_offset(compat_ulong_t offset) { - if (offset < 0) - return sizeof(struct pt_regs); - else if (offset <= 32*4) /* gr[0..31] */ - return offset * 2 + 4; - else if (offset <= 32*4+32*8) /* gr[0..31] + fr[0..31] */ - return offset + 32*4; - else if (offset < sizeof(struct pt_regs)/2 + 32*4) - return offset * 2 + 4 - 32*8; + compat_ulong_t pos; + + if (offset < 32*4) /* gr[0..31] */ + pos = offset * 2 + 4; + else if (offset < 32*4+32*8) /* fr[0] ... fr[31] */ + pos = (offset - 32*4) + PT_FR0; + else if (offset < sizeof(struct pt_regs)/2 + 32*4) /* sr[0] ... ipsw */ + pos = (offset - 32*4 - 32*8) * 2 + PT_SR0 + 4; else - return sizeof(struct pt_regs); + pos = sizeof(struct pt_regs); + + return pos; } long compat_arch_ptrace(struct task_struct *child, compat_long_t request, @@ -242,9 +247,12 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, addr = translate_usr_offset(addr); if (addr >= sizeof(struct pt_regs)) break; + if (addr == PT_IAOQ0+4 || addr == PT_IAOQ1+4) { + data |= 3; /* ensure userspace privilege */ + } if (addr >= PT_FR0 && addr <= PT_FR31 + 4) { /* Special case, fp regs are 64 bits anyway */ - *(__u64 *) ((char *) task_regs(child) + addr) = data; + *(__u32 *) ((char *) task_regs(child) + addr) = data; ret = 0; } else if ((addr >= PT_GR1+4 && addr <= PT_GR31+4) || diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 6696c1986844..16193d7b0635 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -363,10 +363,19 @@ static inline unsigned long eeh_token_to_phys(unsigned long token) NULL, &hugepage_shift); if (!ptep) return token; - WARN_ON(hugepage_shift); - pa = pte_pfn(*ptep) << PAGE_SHIFT; - return pa | (token & (PAGE_SIZE-1)); + pa = pte_pfn(*ptep); + + /* On radix we can do hugepage mappings for io, so handle that */ + if (hugepage_shift) { + pa <<= hugepage_shift; + pa |= token & ((1ul << hugepage_shift) - 1); + } else { + pa <<= PAGE_SHIFT; + pa |= token & (PAGE_SIZE - 1); + } + + return pa; } /* diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 10e7cec9553d..a44f1755dc4b 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1719,7 +1719,7 @@ handle_page_fault: addi r3,r1,STACK_FRAME_OVERHEAD bl do_page_fault cmpdi r3,0 - beq+ 12f + beq+ ret_from_except_lite bl save_nvgprs mr r5,r3 addi r3,r1,STACK_FRAME_OVERHEAD @@ -1734,7 +1734,12 @@ handle_dabr_fault: ld r5,_DSISR(r1) addi r3,r1,STACK_FRAME_OVERHEAD bl do_break -12: b ret_from_except_lite + /* + * do_break() may have changed the NV GPRS while handling a breakpoint. + * If so, we need to restore them with their updated values. Don't use + * ret_from_except_lite here. + */ + b ret_from_except /* We have a page fault that hash_page could handle but HV refused diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 2e710c15893f..a38d7293460d 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -45,6 +45,8 @@ static unsigned int pci_parse_of_flags(u32 addr0, int bridge) if (addr0 & 0x02000000) { flags = IORESOURCE_MEM | PCI_BASE_ADDRESS_SPACE_MEMORY; flags |= (addr0 >> 22) & PCI_BASE_ADDRESS_MEM_TYPE_64; + if (flags & PCI_BASE_ADDRESS_MEM_TYPE_64) + flags |= IORESOURCE_MEM_64; flags |= (addr0 >> 28) & PCI_BASE_ADDRESS_MEM_TYPE_1M; if (addr0 & 0x40000000) flags |= IORESOURCE_PREFETCH diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index ef7c24e84a62..46f8292e5212 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -1261,6 +1261,9 @@ long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, goto bad; if (MSR_TM_ACTIVE(msr_hi<<32)) { + /* Trying to start TM on non TM system */ + if (!cpu_has_feature(CPU_FTR_TM)) + goto bad; /* We only recheckpoint on return if we're * transaction. */ diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index c676ecec0869..8be659db0319 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -695,6 +695,11 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5, if (MSR_TM_ACTIVE(msr)) { /* We recheckpoint on return. */ struct ucontext __user *uc_transact; + + /* Trying to start TM on non TM system */ + if (!cpu_has_feature(CPU_FTR_TM)) + goto badframe; + if (__get_user(uc_transact, &uc->uc_link)) goto badframe; if (restore_tm_sigcontexts(regs, &uc->uc_mcontext, diff --git a/arch/powerpc/kernel/swsusp_32.S b/arch/powerpc/kernel/swsusp_32.S index ba4dee3d233f..884d1c3a187b 100644 --- a/arch/powerpc/kernel/swsusp_32.S +++ b/arch/powerpc/kernel/swsusp_32.S @@ -23,11 +23,19 @@ #define SL_IBAT2 0x48 #define SL_DBAT3 0x50 #define SL_IBAT3 0x58 -#define SL_TB 0x60 -#define SL_R2 0x68 -#define SL_CR 0x6c -#define SL_LR 0x70 -#define SL_R12 0x74 /* r12 to r31 */ +#define SL_DBAT4 0x60 +#define SL_IBAT4 0x68 +#define SL_DBAT5 0x70 +#define SL_IBAT5 0x78 +#define SL_DBAT6 0x80 +#define SL_IBAT6 0x88 +#define SL_DBAT7 0x90 +#define SL_IBAT7 0x98 +#define SL_TB 0xa0 +#define SL_R2 0xa8 +#define SL_CR 0xac +#define SL_LR 0xb0 +#define SL_R12 0xb4 /* r12 to r31 */ #define SL_SIZE (SL_R12 + 80) .section .data @@ -112,6 +120,41 @@ _GLOBAL(swsusp_arch_suspend) mfibatl r4,3 stw r4,SL_IBAT3+4(r11) +BEGIN_MMU_FTR_SECTION + mfspr r4,SPRN_DBAT4U + stw r4,SL_DBAT4(r11) + mfspr r4,SPRN_DBAT4L + stw r4,SL_DBAT4+4(r11) + mfspr r4,SPRN_DBAT5U + stw r4,SL_DBAT5(r11) + mfspr r4,SPRN_DBAT5L + stw r4,SL_DBAT5+4(r11) + mfspr r4,SPRN_DBAT6U + stw r4,SL_DBAT6(r11) + mfspr r4,SPRN_DBAT6L + stw r4,SL_DBAT6+4(r11) + mfspr r4,SPRN_DBAT7U + stw r4,SL_DBAT7(r11) + mfspr r4,SPRN_DBAT7L + stw r4,SL_DBAT7+4(r11) + mfspr r4,SPRN_IBAT4U + stw r4,SL_IBAT4(r11) + mfspr r4,SPRN_IBAT4L + stw r4,SL_IBAT4+4(r11) + mfspr r4,SPRN_IBAT5U + stw r4,SL_IBAT5(r11) + mfspr r4,SPRN_IBAT5L + stw r4,SL_IBAT5+4(r11) + mfspr r4,SPRN_IBAT6U + stw r4,SL_IBAT6(r11) + mfspr r4,SPRN_IBAT6L + stw r4,SL_IBAT6+4(r11) + mfspr r4,SPRN_IBAT7U + stw r4,SL_IBAT7(r11) + mfspr r4,SPRN_IBAT7L + stw r4,SL_IBAT7+4(r11) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) + #if 0 /* Backup various CPU config stuffs */ bl __save_cpu_setup @@ -277,27 +320,41 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) mtibatu 3,r4 lwz r4,SL_IBAT3+4(r11) mtibatl 3,r4 -#endif - BEGIN_MMU_FTR_SECTION - li r4,0 + lwz r4,SL_DBAT4(r11) mtspr SPRN_DBAT4U,r4 + lwz r4,SL_DBAT4+4(r11) mtspr SPRN_DBAT4L,r4 + lwz r4,SL_DBAT5(r11) mtspr SPRN_DBAT5U,r4 + lwz r4,SL_DBAT5+4(r11) mtspr SPRN_DBAT5L,r4 + lwz r4,SL_DBAT6(r11) mtspr SPRN_DBAT6U,r4 + lwz r4,SL_DBAT6+4(r11) mtspr SPRN_DBAT6L,r4 + lwz r4,SL_DBAT7(r11) mtspr SPRN_DBAT7U,r4 + lwz r4,SL_DBAT7+4(r11) mtspr SPRN_DBAT7L,r4 + lwz r4,SL_IBAT4(r11) mtspr SPRN_IBAT4U,r4 + lwz r4,SL_IBAT4+4(r11) mtspr SPRN_IBAT4L,r4 + lwz r4,SL_IBAT5(r11) mtspr SPRN_IBAT5U,r4 + lwz r4,SL_IBAT5+4(r11) mtspr SPRN_IBAT5L,r4 + lwz r4,SL_IBAT6(r11) mtspr SPRN_IBAT6U,r4 + lwz r4,SL_IBAT6+4(r11) mtspr SPRN_IBAT6L,r4 + lwz r4,SL_IBAT7(r11) mtspr SPRN_IBAT7U,r4 + lwz r4,SL_IBAT7+4(r11) mtspr SPRN_IBAT7L,r4 END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) +#endif /* Flush all TLBs */ lis r4,0x1000 diff --git a/arch/powerpc/platforms/powermac/sleep.S b/arch/powerpc/platforms/powermac/sleep.S index 1c2802fabd57..c856cd7fcdc4 100644 --- a/arch/powerpc/platforms/powermac/sleep.S +++ b/arch/powerpc/platforms/powermac/sleep.S @@ -37,10 +37,18 @@ #define SL_IBAT2 0x48 #define SL_DBAT3 0x50 #define SL_IBAT3 0x58 -#define SL_TB 0x60 -#define SL_R2 0x68 -#define SL_CR 0x6c -#define SL_R12 0x70 /* r12 to r31 */ +#define SL_DBAT4 0x60 +#define SL_IBAT4 0x68 +#define SL_DBAT5 0x70 +#define SL_IBAT5 0x78 +#define SL_DBAT6 0x80 +#define SL_IBAT6 0x88 +#define SL_DBAT7 0x90 +#define SL_IBAT7 0x98 +#define SL_TB 0xa0 +#define SL_R2 0xa8 +#define SL_CR 0xac +#define SL_R12 0xb0 /* r12 to r31 */ #define SL_SIZE (SL_R12 + 80) .section .text @@ -125,6 +133,41 @@ _GLOBAL(low_sleep_handler) mfibatl r4,3 stw r4,SL_IBAT3+4(r1) +BEGIN_MMU_FTR_SECTION + mfspr r4,SPRN_DBAT4U + stw r4,SL_DBAT4(r1) + mfspr r4,SPRN_DBAT4L + stw r4,SL_DBAT4+4(r1) + mfspr r4,SPRN_DBAT5U + stw r4,SL_DBAT5(r1) + mfspr r4,SPRN_DBAT5L + stw r4,SL_DBAT5+4(r1) + mfspr r4,SPRN_DBAT6U + stw r4,SL_DBAT6(r1) + mfspr r4,SPRN_DBAT6L + stw r4,SL_DBAT6+4(r1) + mfspr r4,SPRN_DBAT7U + stw r4,SL_DBAT7(r1) + mfspr r4,SPRN_DBAT7L + stw r4,SL_DBAT7+4(r1) + mfspr r4,SPRN_IBAT4U + stw r4,SL_IBAT4(r1) + mfspr r4,SPRN_IBAT4L + stw r4,SL_IBAT4+4(r1) + mfspr r4,SPRN_IBAT5U + stw r4,SL_IBAT5(r1) + mfspr r4,SPRN_IBAT5L + stw r4,SL_IBAT5+4(r1) + mfspr r4,SPRN_IBAT6U + stw r4,SL_IBAT6(r1) + mfspr r4,SPRN_IBAT6L + stw r4,SL_IBAT6+4(r1) + mfspr r4,SPRN_IBAT7U + stw r4,SL_IBAT7(r1) + mfspr r4,SPRN_IBAT7L + stw r4,SL_IBAT7+4(r1) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) + /* Backup various CPU config stuffs */ bl __save_cpu_setup @@ -325,22 +368,37 @@ grackle_wake_up: mtibatl 3,r4 BEGIN_MMU_FTR_SECTION - li r4,0 + lwz r4,SL_DBAT4(r1) mtspr SPRN_DBAT4U,r4 + lwz r4,SL_DBAT4+4(r1) mtspr SPRN_DBAT4L,r4 + lwz r4,SL_DBAT5(r1) mtspr SPRN_DBAT5U,r4 + lwz r4,SL_DBAT5+4(r1) mtspr SPRN_DBAT5L,r4 + lwz r4,SL_DBAT6(r1) mtspr SPRN_DBAT6U,r4 + lwz r4,SL_DBAT6+4(r1) mtspr SPRN_DBAT6L,r4 + lwz r4,SL_DBAT7(r1) mtspr SPRN_DBAT7U,r4 + lwz r4,SL_DBAT7+4(r1) mtspr SPRN_DBAT7L,r4 + lwz r4,SL_IBAT4(r1) mtspr SPRN_IBAT4U,r4 + lwz r4,SL_IBAT4+4(r1) mtspr SPRN_IBAT4L,r4 + lwz r4,SL_IBAT5(r1) mtspr SPRN_IBAT5U,r4 + lwz r4,SL_IBAT5+4(r1) mtspr SPRN_IBAT5L,r4 + lwz r4,SL_IBAT6(r1) mtspr SPRN_IBAT6U,r4 + lwz r4,SL_IBAT6+4(r1) mtspr SPRN_IBAT6L,r4 + lwz r4,SL_IBAT7(r1) mtspr SPRN_IBAT7U,r4 + lwz r4,SL_IBAT7+4(r1) mtspr SPRN_IBAT7L,r4 END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) diff --git a/arch/powerpc/sysdev/uic.c b/arch/powerpc/sysdev/uic.c index 6893d8f236df..225346dda151 100644 --- a/arch/powerpc/sysdev/uic.c +++ b/arch/powerpc/sysdev/uic.c @@ -158,6 +158,7 @@ static int uic_set_irq_type(struct irq_data *d, unsigned int flow_type) mtdcr(uic->dcrbase + UIC_PR, pr); mtdcr(uic->dcrbase + UIC_TR, tr); + mtdcr(uic->dcrbase + UIC_SR, ~mask); raw_spin_unlock_irqrestore(&uic->lock, flags); diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h index 3280a6bfa503..b2592c3864ad 100644 --- a/arch/sh/include/asm/io.h +++ b/arch/sh/include/asm/io.h @@ -370,7 +370,11 @@ static inline int iounmap_fixed(void __iomem *addr) { return -EINVAL; } #define ioremap_nocache ioremap #define ioremap_uc ioremap -#define iounmap __iounmap + +static inline void iounmap(void __iomem *addr) +{ + __iounmap(addr); +} /* * Convert a physical pointer to a virtual kernel pointer for /dev/mem diff --git a/arch/um/include/asm/mmu_context.h b/arch/um/include/asm/mmu_context.h index 941527e507f7..f618f45fc8e9 100644 --- a/arch/um/include/asm/mmu_context.h +++ b/arch/um/include/asm/mmu_context.h @@ -42,7 +42,7 @@ static inline void activate_mm(struct mm_struct *old, struct mm_struct *new) * when the new ->mm is used for the first time. */ __switch_mm(&new->context.id); - down_write(&new->mmap_sem); + down_write_nested(&new->mmap_sem, 1); uml_setup_stubs(new); up_write(&new->mmap_sem); } diff --git a/arch/x86/configs/x86_64_cuttlefish_defconfig b/arch/x86/configs/x86_64_cuttlefish_defconfig index 4c80a8b6f0ce..deaecb9a3f1c 100644 --- a/arch/x86/configs/x86_64_cuttlefish_defconfig +++ b/arch/x86/configs/x86_64_cuttlefish_defconfig @@ -382,6 +382,7 @@ CONFIG_USB_CONFIGFS_F_AUDIO_SRC=y CONFIG_USB_CONFIGFS_UEVENT=y CONFIG_USB_CONFIGFS_F_MIDI=y CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_TEST=y CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_BALLOON=y CONFIG_VIRTIO_INPUT=y diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 310e279be0d8..ab2df0f9ac45 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1094,7 +1094,7 @@ static void __init l1tf_select_mitigation(void) static ssize_t mds_show_state(char *buf) { #ifdef CONFIG_HYPERVISOR_GUEST - if (x86_hyper) { + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { return sprintf(buf, "%s; SMT Host state unknown\n", mds_strings[mds_mitigation]); } diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh index 6988c74409a8..711b74e0e623 100644 --- a/arch/x86/kernel/cpu/mkcapflags.sh +++ b/arch/x86/kernel/cpu/mkcapflags.sh @@ -3,6 +3,8 @@ # Generate the x86_cap/bug_flags[] arrays from include/asm/cpufeatures.h # +set -e + IN=$1 OUT=$2 diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c index 5da924bbf0a0..7cd61011ed26 100644 --- a/arch/x86/kernel/sysfb_efi.c +++ b/arch/x86/kernel/sysfb_efi.c @@ -216,9 +216,55 @@ static const struct dmi_system_id efifb_dmi_system_table[] __initconst = { {}, }; +/* + * Some devices have a portrait LCD but advertise a landscape resolution (and + * pitch). We simply swap width and height for these devices so that we can + * correctly deal with some of them coming with multiple resolutions. + */ +static const struct dmi_system_id efifb_dmi_swap_width_height[] __initconst = { + { + /* + * Lenovo MIIX310-10ICR, only some batches have the troublesome + * 800x1280 portrait screen. Luckily the portrait version has + * its own BIOS version, so we match on that. + */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "MIIX 310-10ICR"), + DMI_EXACT_MATCH(DMI_BIOS_VERSION, "1HCN44WW"), + }, + }, + { + /* Lenovo MIIX 320-10ICR with 800x1280 portrait screen */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, + "Lenovo MIIX 320-10ICR"), + }, + }, + { + /* Lenovo D330 with 800x1280 or 1200x1920 portrait screen */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, + "Lenovo ideapad D330-10IGM"), + }, + }, + {}, +}; + __init void sysfb_apply_efi_quirks(void) { if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || !(screen_info.capabilities & VIDEO_CAPABILITY_SKIP_QUIRKS)) dmi_check_system(efifb_dmi_system_table); + + if (screen_info.orig_video_isVGA == VIDEO_TYPE_EFI && + dmi_check_system(efifb_dmi_swap_width_height)) { + u16 temp = screen_info.lfb_width; + + screen_info.lfb_width = screen_info.lfb_height; + screen_info.lfb_height = temp; + screen_info.lfb_linelength = 4 * screen_info.lfb_width; + } } diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 31aa2c85dc97..f21d4df282fa 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -124,8 +124,8 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, intr ? kvm_perf_overflow_intr : kvm_perf_overflow, pmc); if (IS_ERR(event)) { - printk_once("kvm_pmu: event creation failed %ld\n", - PTR_ERR(event)); + pr_debug_ratelimited("kvm_pmu: event creation failed %ld for pmc->idx = %d\n", + PTR_ERR(event), pmc->idx); return; } diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c index f678c733df40..d2c46454ffa8 100644 --- a/block/compat_ioctl.c +++ b/block/compat_ioctl.c @@ -4,7 +4,6 @@ #include <linux/cdrom.h> #include <linux/compat.h> #include <linux/elevator.h> -#include <linux/fd.h> #include <linux/hdreg.h> #include <linux/slab.h> #include <linux/syscalls.h> @@ -209,318 +208,6 @@ static int compat_blkpg_ioctl(struct block_device *bdev, fmode_t mode, #define BLKBSZSET_32 _IOW(0x12, 113, int) #define BLKGETSIZE64_32 _IOR(0x12, 114, int) -struct compat_floppy_drive_params { - char cmos; - compat_ulong_t max_dtr; - compat_ulong_t hlt; - compat_ulong_t hut; - compat_ulong_t srt; - compat_ulong_t spinup; - compat_ulong_t spindown; - unsigned char spindown_offset; - unsigned char select_delay; - unsigned char rps; - unsigned char tracks; - compat_ulong_t timeout; - unsigned char interleave_sect; - struct floppy_max_errors max_errors; - char flags; - char read_track; - short autodetect[8]; - compat_int_t checkfreq; - compat_int_t native_format; -}; - -struct compat_floppy_drive_struct { - signed char flags; - compat_ulong_t spinup_date; - compat_ulong_t select_date; - compat_ulong_t first_read_date; - short probed_format; - short track; - short maxblock; - short maxtrack; - compat_int_t generation; - compat_int_t keep_data; - compat_int_t fd_ref; - compat_int_t fd_device; - compat_int_t last_checked; - compat_caddr_t dmabuf; - compat_int_t bufblocks; -}; - -struct compat_floppy_fdc_state { - compat_int_t spec1; - compat_int_t spec2; - compat_int_t dtr; - unsigned char version; - unsigned char dor; - compat_ulong_t address; - unsigned int rawcmd:2; - unsigned int reset:1; - unsigned int need_configure:1; - unsigned int perp_mode:2; - unsigned int has_fifo:1; - unsigned int driver_version; - unsigned char track[4]; -}; - -struct compat_floppy_write_errors { - unsigned int write_errors; - compat_ulong_t first_error_sector; - compat_int_t first_error_generation; - compat_ulong_t last_error_sector; - compat_int_t last_error_generation; - compat_uint_t badness; -}; - -#define FDSETPRM32 _IOW(2, 0x42, struct compat_floppy_struct) -#define FDDEFPRM32 _IOW(2, 0x43, struct compat_floppy_struct) -#define FDSETDRVPRM32 _IOW(2, 0x90, struct compat_floppy_drive_params) -#define FDGETDRVPRM32 _IOR(2, 0x11, struct compat_floppy_drive_params) -#define FDGETDRVSTAT32 _IOR(2, 0x12, struct compat_floppy_drive_struct) -#define FDPOLLDRVSTAT32 _IOR(2, 0x13, struct compat_floppy_drive_struct) -#define FDGETFDCSTAT32 _IOR(2, 0x15, struct compat_floppy_fdc_state) -#define FDWERRORGET32 _IOR(2, 0x17, struct compat_floppy_write_errors) - -static struct { - unsigned int cmd32; - unsigned int cmd; -} fd_ioctl_trans_table[] = { - { FDSETPRM32, FDSETPRM }, - { FDDEFPRM32, FDDEFPRM }, - { FDGETPRM32, FDGETPRM }, - { FDSETDRVPRM32, FDSETDRVPRM }, - { FDGETDRVPRM32, FDGETDRVPRM }, - { FDGETDRVSTAT32, FDGETDRVSTAT }, - { FDPOLLDRVSTAT32, FDPOLLDRVSTAT }, - { FDGETFDCSTAT32, FDGETFDCSTAT }, - { FDWERRORGET32, FDWERRORGET } -}; - -#define NR_FD_IOCTL_TRANS ARRAY_SIZE(fd_ioctl_trans_table) - -static int compat_fd_ioctl(struct block_device *bdev, fmode_t mode, - unsigned int cmd, unsigned long arg) -{ - mm_segment_t old_fs = get_fs(); - void *karg = NULL; - unsigned int kcmd = 0; - int i, err; - - for (i = 0; i < NR_FD_IOCTL_TRANS; i++) - if (cmd == fd_ioctl_trans_table[i].cmd32) { - kcmd = fd_ioctl_trans_table[i].cmd; - break; - } - if (!kcmd) - return -EINVAL; - - switch (cmd) { - case FDSETPRM32: - case FDDEFPRM32: - case FDGETPRM32: - { - compat_uptr_t name; - struct compat_floppy_struct __user *uf; - struct floppy_struct *f; - - uf = compat_ptr(arg); - f = karg = kmalloc(sizeof(struct floppy_struct), GFP_KERNEL); - if (!karg) - return -ENOMEM; - if (cmd == FDGETPRM32) - break; - err = __get_user(f->size, &uf->size); - err |= __get_user(f->sect, &uf->sect); - err |= __get_user(f->head, &uf->head); - err |= __get_user(f->track, &uf->track); - err |= __get_user(f->stretch, &uf->stretch); - err |= __get_user(f->gap, &uf->gap); - err |= __get_user(f->rate, &uf->rate); - err |= __get_user(f->spec1, &uf->spec1); - err |= __get_user(f->fmt_gap, &uf->fmt_gap); - err |= __get_user(name, &uf->name); - f->name = compat_ptr(name); - if (err) { - err = -EFAULT; - goto out; - } - break; - } - case FDSETDRVPRM32: - case FDGETDRVPRM32: - { - struct compat_floppy_drive_params __user *uf; - struct floppy_drive_params *f; - - uf = compat_ptr(arg); - f = karg = kmalloc(sizeof(struct floppy_drive_params), GFP_KERNEL); - if (!karg) - return -ENOMEM; - if (cmd == FDGETDRVPRM32) - break; - err = __get_user(f->cmos, &uf->cmos); - err |= __get_user(f->max_dtr, &uf->max_dtr); - err |= __get_user(f->hlt, &uf->hlt); - err |= __get_user(f->hut, &uf->hut); - err |= __get_user(f->srt, &uf->srt); - err |= __get_user(f->spinup, &uf->spinup); - err |= __get_user(f->spindown, &uf->spindown); - err |= __get_user(f->spindown_offset, &uf->spindown_offset); - err |= __get_user(f->select_delay, &uf->select_delay); - err |= __get_user(f->rps, &uf->rps); - err |= __get_user(f->tracks, &uf->tracks); - err |= __get_user(f->timeout, &uf->timeout); - err |= __get_user(f->interleave_sect, &uf->interleave_sect); - err |= __copy_from_user(&f->max_errors, &uf->max_errors, sizeof(f->max_errors)); - err |= __get_user(f->flags, &uf->flags); - err |= __get_user(f->read_track, &uf->read_track); - err |= __copy_from_user(f->autodetect, uf->autodetect, sizeof(f->autodetect)); - err |= __get_user(f->checkfreq, &uf->checkfreq); - err |= __get_user(f->native_format, &uf->native_format); - if (err) { - err = -EFAULT; - goto out; - } - break; - } - case FDGETDRVSTAT32: - case FDPOLLDRVSTAT32: - karg = kmalloc(sizeof(struct floppy_drive_struct), GFP_KERNEL); - if (!karg) - return -ENOMEM; - break; - case FDGETFDCSTAT32: - karg = kmalloc(sizeof(struct floppy_fdc_state), GFP_KERNEL); - if (!karg) - return -ENOMEM; - break; - case FDWERRORGET32: - karg = kmalloc(sizeof(struct floppy_write_errors), GFP_KERNEL); - if (!karg) - return -ENOMEM; - break; - default: - return -EINVAL; - } - set_fs(KERNEL_DS); - err = __blkdev_driver_ioctl(bdev, mode, kcmd, (unsigned long)karg); - set_fs(old_fs); - if (err) - goto out; - switch (cmd) { - case FDGETPRM32: - { - struct floppy_struct *f = karg; - struct compat_floppy_struct __user *uf = compat_ptr(arg); - - err = __put_user(f->size, &uf->size); - err |= __put_user(f->sect, &uf->sect); - err |= __put_user(f->head, &uf->head); - err |= __put_user(f->track, &uf->track); - err |= __put_user(f->stretch, &uf->stretch); - err |= __put_user(f->gap, &uf->gap); - err |= __put_user(f->rate, &uf->rate); - err |= __put_user(f->spec1, &uf->spec1); - err |= __put_user(f->fmt_gap, &uf->fmt_gap); - err |= __put_user((u64)f->name, (compat_caddr_t __user *)&uf->name); - break; - } - case FDGETDRVPRM32: - { - struct compat_floppy_drive_params __user *uf; - struct floppy_drive_params *f = karg; - - uf = compat_ptr(arg); - err = __put_user(f->cmos, &uf->cmos); - err |= __put_user(f->max_dtr, &uf->max_dtr); - err |= __put_user(f->hlt, &uf->hlt); - err |= __put_user(f->hut, &uf->hut); - err |= __put_user(f->srt, &uf->srt); - err |= __put_user(f->spinup, &uf->spinup); - err |= __put_user(f->spindown, &uf->spindown); - err |= __put_user(f->spindown_offset, &uf->spindown_offset); - err |= __put_user(f->select_delay, &uf->select_delay); - err |= __put_user(f->rps, &uf->rps); - err |= __put_user(f->tracks, &uf->tracks); - err |= __put_user(f->timeout, &uf->timeout); - err |= __put_user(f->interleave_sect, &uf->interleave_sect); - err |= __copy_to_user(&uf->max_errors, &f->max_errors, sizeof(f->max_errors)); - err |= __put_user(f->flags, &uf->flags); - err |= __put_user(f->read_track, &uf->read_track); - err |= __copy_to_user(uf->autodetect, f->autodetect, sizeof(f->autodetect)); - err |= __put_user(f->checkfreq, &uf->checkfreq); - err |= __put_user(f->native_format, &uf->native_format); - break; - } - case FDGETDRVSTAT32: - case FDPOLLDRVSTAT32: - { - struct compat_floppy_drive_struct __user *uf; - struct floppy_drive_struct *f = karg; - - uf = compat_ptr(arg); - err = __put_user(f->flags, &uf->flags); - err |= __put_user(f->spinup_date, &uf->spinup_date); - err |= __put_user(f->select_date, &uf->select_date); - err |= __put_user(f->first_read_date, &uf->first_read_date); - err |= __put_user(f->probed_format, &uf->probed_format); - err |= __put_user(f->track, &uf->track); - err |= __put_user(f->maxblock, &uf->maxblock); - err |= __put_user(f->maxtrack, &uf->maxtrack); - err |= __put_user(f->generation, &uf->generation); - err |= __put_user(f->keep_data, &uf->keep_data); - err |= __put_user(f->fd_ref, &uf->fd_ref); - err |= __put_user(f->fd_device, &uf->fd_device); - err |= __put_user(f->last_checked, &uf->last_checked); - err |= __put_user((u64)f->dmabuf, &uf->dmabuf); - err |= __put_user((u64)f->bufblocks, &uf->bufblocks); - break; - } - case FDGETFDCSTAT32: - { - struct compat_floppy_fdc_state __user *uf; - struct floppy_fdc_state *f = karg; - - uf = compat_ptr(arg); - err = __put_user(f->spec1, &uf->spec1); - err |= __put_user(f->spec2, &uf->spec2); - err |= __put_user(f->dtr, &uf->dtr); - err |= __put_user(f->version, &uf->version); - err |= __put_user(f->dor, &uf->dor); - err |= __put_user(f->address, &uf->address); - err |= __copy_to_user((char __user *)&uf->address + sizeof(uf->address), - (char *)&f->address + sizeof(f->address), sizeof(int)); - err |= __put_user(f->driver_version, &uf->driver_version); - err |= __copy_to_user(uf->track, f->track, sizeof(f->track)); - break; - } - case FDWERRORGET32: - { - struct compat_floppy_write_errors __user *uf; - struct floppy_write_errors *f = karg; - - uf = compat_ptr(arg); - err = __put_user(f->write_errors, &uf->write_errors); - err |= __put_user(f->first_error_sector, &uf->first_error_sector); - err |= __put_user(f->first_error_generation, &uf->first_error_generation); - err |= __put_user(f->last_error_sector, &uf->last_error_sector); - err |= __put_user(f->last_error_generation, &uf->last_error_generation); - err |= __put_user(f->badness, &uf->badness); - break; - } - default: - break; - } - if (err) - err = -EFAULT; - -out: - kfree(karg); - return err; -} - static int compat_blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, unsigned long arg) { @@ -537,16 +224,6 @@ static int compat_blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode, case HDIO_GET_ADDRESS: case HDIO_GET_BUSSTATE: return compat_hdio_ioctl(bdev, mode, cmd, arg); - case FDSETPRM32: - case FDDEFPRM32: - case FDGETPRM32: - case FDSETDRVPRM32: - case FDGETDRVPRM32: - case FDGETDRVSTAT32: - case FDPOLLDRVSTAT32: - case FDGETFDCSTAT32: - case FDWERRORGET32: - return compat_fd_ioctl(bdev, mode, cmd, arg); case CDROMREADAUDIO: return compat_cdrom_read_audio(bdev, mode, cmd, arg); case CDROM_SEND_PACKET: @@ -566,23 +243,6 @@ static int compat_blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode, case HDIO_DRIVE_CMD: /* 0x330 is reserved -- it used to be HDIO_GETGEO_BIG */ case 0x330: - /* 0x02 -- Floppy ioctls */ - case FDMSGON: - case FDMSGOFF: - case FDSETEMSGTRESH: - case FDFLUSH: - case FDWERRORCLR: - case FDSETMAXERRS: - case FDGETMAXERRS: - case FDGETDRVTYP: - case FDEJECT: - case FDCLRPRM: - case FDFMTBEG: - case FDFMTEND: - case FDRESET: - case FDTWADDLE: - case FDFMTTRK: - case FDRAWCMD: /* CDROM stuff */ case CDROMPAUSE: case CDROMRESUME: diff --git a/crypto/ghash-generic.c b/crypto/ghash-generic.c index 12ad3e3a84e3..73b56f2f44f1 100644 --- a/crypto/ghash-generic.c +++ b/crypto/ghash-generic.c @@ -34,6 +34,7 @@ static int ghash_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen) { struct ghash_ctx *ctx = crypto_shash_ctx(tfm); + be128 k; if (keylen != GHASH_BLOCK_SIZE) { crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); @@ -42,7 +43,12 @@ static int ghash_setkey(struct crypto_shash *tfm, if (ctx->gf128) gf128mul_free_4k(ctx->gf128); - ctx->gf128 = gf128mul_init_4k_lle((be128 *)key); + + BUILD_BUG_ON(sizeof(k) != GHASH_BLOCK_SIZE); + memcpy(&k, key, GHASH_BLOCK_SIZE); /* avoid violating alignment rules */ + ctx->gf128 = gf128mul_init_4k_lle(&k); + memzero_explicit(&k, GHASH_BLOCK_SIZE); + if (!ctx->gf128) return -ENOMEM; diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 91fe6c39c804..d726b03f19bc 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -3225,7 +3225,8 @@ static void binder_transaction(struct binder_proc *proc, } off_end = (void *)off_start + tr->offsets_size; sg_bufp = (u8 *)(PTR_ALIGN(off_end, sizeof(void *))); - sg_buf_end = sg_bufp + extra_buffers_size; + sg_buf_end = sg_bufp + extra_buffers_size - + ALIGN(secctx_sz, sizeof(u64)); off_min = 0; for (; offp < off_end; offp++) { struct binder_object_header *hdr; diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index b3a62e94d1f3..6b96ebb9b440 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -1358,6 +1358,8 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, map->format.reg_bytes + map->format.pad_bytes, val, val_len); + else + ret = -ENOTSUPP; /* If that didn't work fall back on linearising by hand. */ if (ret == -ENOTSUPP) { diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 2daa5b84abbc..a04810837234 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -192,6 +192,7 @@ static int print_unex = 1; #include <linux/io.h> #include <linux/uaccess.h> #include <linux/async.h> +#include <linux/compat.h> /* * PS/2 floppies have much slower step rates than regular floppies. @@ -2113,6 +2114,9 @@ static void setup_format_params(int track) raw_cmd->kernel_data = floppy_track_buffer; raw_cmd->length = 4 * F_SECT_PER_TRACK; + if (!F_SECT_PER_TRACK) + return; + /* allow for about 30ms for data transport per track */ head_shift = (F_SECT_PER_TRACK + 5) / 6; @@ -3233,8 +3237,12 @@ static int set_geometry(unsigned int cmd, struct floppy_struct *g, int cnt; /* sanity checking for parameters. */ - if (g->sect <= 0 || - g->head <= 0 || + if ((int)g->sect <= 0 || + (int)g->head <= 0 || + /* check for overflow in max_sector */ + (int)(g->sect * g->head) <= 0 || + /* check for zero in F_SECT_PER_TRACK */ + (unsigned char)((g->sect << 2) >> FD_SIZECODE(g)) == 0 || g->track <= 0 || g->track > UDP->tracks >> STRETCH(g) || /* check if reserved bits are set */ (g->stretch & ~(FD_STRETCH | FD_SWAPSIDES | FD_SECTBASEMASK)) != 0) @@ -3378,6 +3386,24 @@ static int fd_getgeo(struct block_device *bdev, struct hd_geometry *geo) return 0; } +static bool valid_floppy_drive_params(const short autodetect[8], + int native_format) +{ + size_t floppy_type_size = ARRAY_SIZE(floppy_type); + size_t i = 0; + + for (i = 0; i < 8; ++i) { + if (autodetect[i] < 0 || + autodetect[i] >= floppy_type_size) + return false; + } + + if (native_format < 0 || native_format >= floppy_type_size) + return false; + + return true; +} + static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long param) { @@ -3504,6 +3530,9 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int SUPBOUND(size, strlen((const char *)outparam) + 1); break; case FDSETDRVPRM: + if (!valid_floppy_drive_params(inparam.dp.autodetect, + inparam.dp.native_format)) + return -EINVAL; *UDP = inparam.dp; break; case FDGETDRVPRM: @@ -3569,6 +3598,332 @@ static int fd_ioctl(struct block_device *bdev, fmode_t mode, return ret; } +#ifdef CONFIG_COMPAT + +struct compat_floppy_drive_params { + char cmos; + compat_ulong_t max_dtr; + compat_ulong_t hlt; + compat_ulong_t hut; + compat_ulong_t srt; + compat_ulong_t spinup; + compat_ulong_t spindown; + unsigned char spindown_offset; + unsigned char select_delay; + unsigned char rps; + unsigned char tracks; + compat_ulong_t timeout; + unsigned char interleave_sect; + struct floppy_max_errors max_errors; + char flags; + char read_track; + short autodetect[8]; + compat_int_t checkfreq; + compat_int_t native_format; +}; + +struct compat_floppy_drive_struct { + signed char flags; + compat_ulong_t spinup_date; + compat_ulong_t select_date; + compat_ulong_t first_read_date; + short probed_format; + short track; + short maxblock; + short maxtrack; + compat_int_t generation; + compat_int_t keep_data; + compat_int_t fd_ref; + compat_int_t fd_device; + compat_int_t last_checked; + compat_caddr_t dmabuf; + compat_int_t bufblocks; +}; + +struct compat_floppy_fdc_state { + compat_int_t spec1; + compat_int_t spec2; + compat_int_t dtr; + unsigned char version; + unsigned char dor; + compat_ulong_t address; + unsigned int rawcmd:2; + unsigned int reset:1; + unsigned int need_configure:1; + unsigned int perp_mode:2; + unsigned int has_fifo:1; + unsigned int driver_version; + unsigned char track[4]; +}; + +struct compat_floppy_write_errors { + unsigned int write_errors; + compat_ulong_t first_error_sector; + compat_int_t first_error_generation; + compat_ulong_t last_error_sector; + compat_int_t last_error_generation; + compat_uint_t badness; +}; + +#define FDSETPRM32 _IOW(2, 0x42, struct compat_floppy_struct) +#define FDDEFPRM32 _IOW(2, 0x43, struct compat_floppy_struct) +#define FDSETDRVPRM32 _IOW(2, 0x90, struct compat_floppy_drive_params) +#define FDGETDRVPRM32 _IOR(2, 0x11, struct compat_floppy_drive_params) +#define FDGETDRVSTAT32 _IOR(2, 0x12, struct compat_floppy_drive_struct) +#define FDPOLLDRVSTAT32 _IOR(2, 0x13, struct compat_floppy_drive_struct) +#define FDGETFDCSTAT32 _IOR(2, 0x15, struct compat_floppy_fdc_state) +#define FDWERRORGET32 _IOR(2, 0x17, struct compat_floppy_write_errors) + +static int compat_set_geometry(struct block_device *bdev, fmode_t mode, unsigned int cmd, + struct compat_floppy_struct __user *arg) +{ + struct floppy_struct v; + int drive, type; + int err; + + BUILD_BUG_ON(offsetof(struct floppy_struct, name) != + offsetof(struct compat_floppy_struct, name)); + + if (!(mode & (FMODE_WRITE | FMODE_WRITE_IOCTL))) + return -EPERM; + + memset(&v, 0, sizeof(struct floppy_struct)); + if (copy_from_user(&v, arg, offsetof(struct floppy_struct, name))) + return -EFAULT; + + mutex_lock(&floppy_mutex); + drive = (long)bdev->bd_disk->private_data; + type = ITYPE(UDRS->fd_device); + err = set_geometry(cmd == FDSETPRM32 ? FDSETPRM : FDDEFPRM, + &v, drive, type, bdev); + mutex_unlock(&floppy_mutex); + return err; +} + +static int compat_get_prm(int drive, + struct compat_floppy_struct __user *arg) +{ + struct compat_floppy_struct v; + struct floppy_struct *p; + int err; + + memset(&v, 0, sizeof(v)); + mutex_lock(&floppy_mutex); + err = get_floppy_geometry(drive, ITYPE(UDRS->fd_device), &p); + if (err) { + mutex_unlock(&floppy_mutex); + return err; + } + memcpy(&v, p, offsetof(struct floppy_struct, name)); + mutex_unlock(&floppy_mutex); + if (copy_to_user(arg, &v, sizeof(struct compat_floppy_struct))) + return -EFAULT; + return 0; +} + +static int compat_setdrvprm(int drive, + struct compat_floppy_drive_params __user *arg) +{ + struct compat_floppy_drive_params v; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + if (copy_from_user(&v, arg, sizeof(struct compat_floppy_drive_params))) + return -EFAULT; + if (!valid_floppy_drive_params(v.autodetect, v.native_format)) + return -EINVAL; + mutex_lock(&floppy_mutex); + UDP->cmos = v.cmos; + UDP->max_dtr = v.max_dtr; + UDP->hlt = v.hlt; + UDP->hut = v.hut; + UDP->srt = v.srt; + UDP->spinup = v.spinup; + UDP->spindown = v.spindown; + UDP->spindown_offset = v.spindown_offset; + UDP->select_delay = v.select_delay; + UDP->rps = v.rps; + UDP->tracks = v.tracks; + UDP->timeout = v.timeout; + UDP->interleave_sect = v.interleave_sect; + UDP->max_errors = v.max_errors; + UDP->flags = v.flags; + UDP->read_track = v.read_track; + memcpy(UDP->autodetect, v.autodetect, sizeof(v.autodetect)); + UDP->checkfreq = v.checkfreq; + UDP->native_format = v.native_format; + mutex_unlock(&floppy_mutex); + return 0; +} + +static int compat_getdrvprm(int drive, + struct compat_floppy_drive_params __user *arg) +{ + struct compat_floppy_drive_params v; + + memset(&v, 0, sizeof(struct compat_floppy_drive_params)); + mutex_lock(&floppy_mutex); + v.cmos = UDP->cmos; + v.max_dtr = UDP->max_dtr; + v.hlt = UDP->hlt; + v.hut = UDP->hut; + v.srt = UDP->srt; + v.spinup = UDP->spinup; + v.spindown = UDP->spindown; + v.spindown_offset = UDP->spindown_offset; + v.select_delay = UDP->select_delay; + v.rps = UDP->rps; + v.tracks = UDP->tracks; + v.timeout = UDP->timeout; + v.interleave_sect = UDP->interleave_sect; + v.max_errors = UDP->max_errors; + v.flags = UDP->flags; + v.read_track = UDP->read_track; + memcpy(v.autodetect, UDP->autodetect, sizeof(v.autodetect)); + v.checkfreq = UDP->checkfreq; + v.native_format = UDP->native_format; + mutex_unlock(&floppy_mutex); + + if (copy_from_user(arg, &v, sizeof(struct compat_floppy_drive_params))) + return -EFAULT; + return 0; +} + +static int compat_getdrvstat(int drive, bool poll, + struct compat_floppy_drive_struct __user *arg) +{ + struct compat_floppy_drive_struct v; + + memset(&v, 0, sizeof(struct compat_floppy_drive_struct)); + mutex_lock(&floppy_mutex); + + if (poll) { + if (lock_fdc(drive, true)) + goto Eintr; + if (poll_drive(true, FD_RAW_NEED_DISK) == -EINTR) + goto Eintr; + process_fd_request(); + } + v.spinup_date = UDRS->spinup_date; + v.select_date = UDRS->select_date; + v.first_read_date = UDRS->first_read_date; + v.probed_format = UDRS->probed_format; + v.track = UDRS->track; + v.maxblock = UDRS->maxblock; + v.maxtrack = UDRS->maxtrack; + v.generation = UDRS->generation; + v.keep_data = UDRS->keep_data; + v.fd_ref = UDRS->fd_ref; + v.fd_device = UDRS->fd_device; + v.last_checked = UDRS->last_checked; + v.dmabuf = (uintptr_t)UDRS->dmabuf; + v.bufblocks = UDRS->bufblocks; + mutex_unlock(&floppy_mutex); + + if (copy_from_user(arg, &v, sizeof(struct compat_floppy_drive_struct))) + return -EFAULT; + return 0; +Eintr: + mutex_unlock(&floppy_mutex); + return -EINTR; +} + +static int compat_getfdcstat(int drive, + struct compat_floppy_fdc_state __user *arg) +{ + struct compat_floppy_fdc_state v32; + struct floppy_fdc_state v; + + mutex_lock(&floppy_mutex); + v = *UFDCS; + mutex_unlock(&floppy_mutex); + + memset(&v32, 0, sizeof(struct compat_floppy_fdc_state)); + v32.spec1 = v.spec1; + v32.spec2 = v.spec2; + v32.dtr = v.dtr; + v32.version = v.version; + v32.dor = v.dor; + v32.address = v.address; + v32.rawcmd = v.rawcmd; + v32.reset = v.reset; + v32.need_configure = v.need_configure; + v32.perp_mode = v.perp_mode; + v32.has_fifo = v.has_fifo; + v32.driver_version = v.driver_version; + memcpy(v32.track, v.track, 4); + if (copy_to_user(arg, &v32, sizeof(struct compat_floppy_fdc_state))) + return -EFAULT; + return 0; +} + +static int compat_werrorget(int drive, + struct compat_floppy_write_errors __user *arg) +{ + struct compat_floppy_write_errors v32; + struct floppy_write_errors v; + + memset(&v32, 0, sizeof(struct compat_floppy_write_errors)); + mutex_lock(&floppy_mutex); + v = *UDRWE; + mutex_unlock(&floppy_mutex); + v32.write_errors = v.write_errors; + v32.first_error_sector = v.first_error_sector; + v32.first_error_generation = v.first_error_generation; + v32.last_error_sector = v.last_error_sector; + v32.last_error_generation = v.last_error_generation; + v32.badness = v.badness; + if (copy_to_user(arg, &v32, sizeof(struct compat_floppy_write_errors))) + return -EFAULT; + return 0; +} + +static int fd_compat_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, + unsigned long param) +{ + int drive = (long)bdev->bd_disk->private_data; + switch (cmd) { + case FDMSGON: + case FDMSGOFF: + case FDSETEMSGTRESH: + case FDFLUSH: + case FDWERRORCLR: + case FDEJECT: + case FDCLRPRM: + case FDFMTBEG: + case FDRESET: + case FDTWADDLE: + return fd_ioctl(bdev, mode, cmd, param); + case FDSETMAXERRS: + case FDGETMAXERRS: + case FDGETDRVTYP: + case FDFMTEND: + case FDFMTTRK: + case FDRAWCMD: + return fd_ioctl(bdev, mode, cmd, + (unsigned long)compat_ptr(param)); + case FDSETPRM32: + case FDDEFPRM32: + return compat_set_geometry(bdev, mode, cmd, compat_ptr(param)); + case FDGETPRM32: + return compat_get_prm(drive, compat_ptr(param)); + case FDSETDRVPRM32: + return compat_setdrvprm(drive, compat_ptr(param)); + case FDGETDRVPRM32: + return compat_getdrvprm(drive, compat_ptr(param)); + case FDPOLLDRVSTAT32: + return compat_getdrvstat(drive, true, compat_ptr(param)); + case FDGETDRVSTAT32: + return compat_getdrvstat(drive, false, compat_ptr(param)); + case FDGETFDCSTAT32: + return compat_getfdcstat(drive, compat_ptr(param)); + case FDWERRORGET32: + return compat_werrorget(drive, compat_ptr(param)); + } + return -EINVAL; +} +#endif + static void __init config_types(void) { bool has_drive = false; @@ -3885,6 +4240,9 @@ static const struct block_device_operations floppy_fops = { .getgeo = fd_getgeo, .check_events = floppy_check_events, .revalidate_disk = floppy_revalidate, +#ifdef CONFIG_COMPAT + .compat_ioctl = fd_compat_ioctl, +#endif }; /* diff --git a/drivers/bluetooth/hci_ath.c b/drivers/bluetooth/hci_ath.c index d776dfd51478..16f2131687e5 100644 --- a/drivers/bluetooth/hci_ath.c +++ b/drivers/bluetooth/hci_ath.c @@ -101,6 +101,9 @@ static int ath_open(struct hci_uart *hu) BT_DBG("hu %p", hu); + if (!hci_uart_has_flow_control(hu)) + return -EOPNOTSUPP; + ath = kzalloc(sizeof(*ath), GFP_KERNEL); if (!ath) return -ENOMEM; diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c index f9b569ef3dd7..20a1b4d1fd09 100644 --- a/drivers/bluetooth/hci_bcm.c +++ b/drivers/bluetooth/hci_bcm.c @@ -279,6 +279,9 @@ static int bcm_open(struct hci_uart *hu) bt_dev_dbg(hu->hdev, "hu %p", hu); + if (!hci_uart_has_flow_control(hu)) + return -EOPNOTSUPP; + bcm = kzalloc(sizeof(*bcm), GFP_KERNEL); if (!bcm) return -ENOMEM; diff --git a/drivers/bluetooth/hci_bcsp.c b/drivers/bluetooth/hci_bcsp.c index d0b615a932d1..9833b53a8b50 100644 --- a/drivers/bluetooth/hci_bcsp.c +++ b/drivers/bluetooth/hci_bcsp.c @@ -729,6 +729,11 @@ static int bcsp_close(struct hci_uart *hu) skb_queue_purge(&bcsp->rel); skb_queue_purge(&bcsp->unrel); + if (bcsp->rx_skb) { + kfree_skb(bcsp->rx_skb); + bcsp->rx_skb = NULL; + } + kfree(bcsp); return 0; } diff --git a/drivers/bluetooth/hci_intel.c b/drivers/bluetooth/hci_intel.c index 0c63fce0c1e0..929674e6663e 100644 --- a/drivers/bluetooth/hci_intel.c +++ b/drivers/bluetooth/hci_intel.c @@ -407,6 +407,9 @@ static int intel_open(struct hci_uart *hu) BT_DBG("hu %p", hu); + if (!hci_uart_has_flow_control(hu)) + return -EOPNOTSUPP; + intel = kzalloc(sizeof(*intel), GFP_KERNEL); if (!intel) return -ENOMEM; diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index 85bb31b6052d..dd7f811e5805 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -276,6 +276,15 @@ static int hci_uart_send_frame(struct hci_dev *hdev, struct sk_buff *skb) return 0; } +/* Check the underlying device or tty has flow control support */ +bool hci_uart_has_flow_control(struct hci_uart *hu) +{ + if (hu->tty->driver->ops->tiocmget && hu->tty->driver->ops->tiocmset) + return true; + + return false; +} + /* Flow control or un-flow control the device */ void hci_uart_set_flow_control(struct hci_uart *hu, bool enable) { diff --git a/drivers/bluetooth/hci_uart.h b/drivers/bluetooth/hci_uart.h index 74237afd5bd2..b3a049afc21e 100644 --- a/drivers/bluetooth/hci_uart.h +++ b/drivers/bluetooth/hci_uart.h @@ -106,6 +106,7 @@ int hci_uart_tx_wakeup(struct hci_uart *hu); int hci_uart_init_ready(struct hci_uart *hu); void hci_uart_init_tty(struct hci_uart *hu); void hci_uart_set_baudrate(struct hci_uart *hu, unsigned int speed); +bool hci_uart_has_flow_control(struct hci_uart *hu); void hci_uart_set_flow_control(struct hci_uart *hu, bool enable); void hci_uart_set_speeds(struct hci_uart *hu, unsigned int init_speed, unsigned int oper_speed); diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index 72e073895ed9..5b38d7a8202a 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -569,8 +569,7 @@ static inline unsigned long hpet_time_div(struct hpets *hpets, unsigned long long m; m = hpets->hp_tick_freq + (dis >> 1); - do_div(m, dis); - return (unsigned long)m; + return div64_ul(m, dis); } static int diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c index 62ce93568e11..a000c2667392 100644 --- a/drivers/crypto/talitos.c +++ b/drivers/crypto/talitos.c @@ -1446,11 +1446,15 @@ static void ablkcipher_done(struct device *dev, int err) { struct ablkcipher_request *areq = context; + struct crypto_ablkcipher *cipher = crypto_ablkcipher_reqtfm(areq); + struct talitos_ctx *ctx = crypto_ablkcipher_ctx(cipher); + unsigned int ivsize = crypto_ablkcipher_ivsize(cipher); struct talitos_edesc *edesc; edesc = container_of(desc, struct talitos_edesc, desc); common_nonsnoop_unmap(dev, edesc, areq); + memcpy(areq->info, ctx->iv, ivsize); kfree(edesc); diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index 4054747af0cb..dd97dbf6618c 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -1786,27 +1786,6 @@ static int sdma_probe(struct platform_device *pdev) if (pdata && pdata->script_addrs) sdma_add_scripts(sdma, pdata->script_addrs); - if (pdata) { - ret = sdma_get_firmware(sdma, pdata->fw_name); - if (ret) - dev_warn(&pdev->dev, "failed to get firmware from platform data\n"); - } else { - /* - * Because that device tree does not encode ROM script address, - * the RAM script in firmware is mandatory for device tree - * probe, otherwise it fails. - */ - ret = of_property_read_string(np, "fsl,sdma-ram-script-name", - &fw_name); - if (ret) - dev_warn(&pdev->dev, "failed to get firmware name\n"); - else { - ret = sdma_get_firmware(sdma, fw_name); - if (ret) - dev_warn(&pdev->dev, "failed to get firmware from device tree\n"); - } - } - sdma->dma_device.dev = &pdev->dev; sdma->dma_device.device_alloc_chan_resources = sdma_alloc_chan_resources; @@ -1848,6 +1827,33 @@ static int sdma_probe(struct platform_device *pdev) of_node_put(spba_bus); } + /* + * Kick off firmware loading as the very last step: + * attempt to load firmware only if we're not on the error path, because + * the firmware callback requires a fully functional and allocated sdma + * instance. + */ + if (pdata) { + ret = sdma_get_firmware(sdma, pdata->fw_name); + if (ret) + dev_warn(&pdev->dev, "failed to get firmware from platform data\n"); + } else { + /* + * Because that device tree does not encode ROM script address, + * the RAM script in firmware is mandatory for device tree + * probe, otherwise it fails. + */ + ret = of_property_read_string(np, "fsl,sdma-ram-script-name", + &fw_name); + if (ret) { + dev_warn(&pdev->dev, "failed to get firmware name\n"); + } else { + ret = sdma_get_firmware(sdma, fw_name); + if (ret) + dev_warn(&pdev->dev, "failed to get firmware from device tree\n"); + } + } + return 0; err_register: diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index 3c8f19f5ac81..d459cf4b8579 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -26,7 +26,7 @@ static int edac_mc_log_ue = 1; static int edac_mc_log_ce = 1; static int edac_mc_panic_on_ue; -static int edac_mc_poll_msec = 1000; +static unsigned int edac_mc_poll_msec = 1000; /* Getter functions for above */ int edac_mc_get_log_ue(void) @@ -45,30 +45,30 @@ int edac_mc_get_panic_on_ue(void) } /* this is temporary */ -int edac_mc_get_poll_msec(void) +unsigned int edac_mc_get_poll_msec(void) { return edac_mc_poll_msec; } static int edac_set_poll_msec(const char *val, struct kernel_param *kp) { - unsigned long l; + unsigned int i; int ret; if (!val) return -EINVAL; - ret = kstrtoul(val, 0, &l); + ret = kstrtouint(val, 0, &i); if (ret) return ret; - if (l < 1000) + if (i < 1000) return -EINVAL; - *((unsigned long *)kp->arg) = l; + *((unsigned int *)kp->arg) = i; /* notify edac_mc engine to reset the poll period */ - edac_mc_reset_delay_period(l); + edac_mc_reset_delay_period(i); return 0; } @@ -82,7 +82,7 @@ MODULE_PARM_DESC(edac_mc_log_ue, module_param(edac_mc_log_ce, int, 0644); MODULE_PARM_DESC(edac_mc_log_ce, "Log correctable error to console: 0=off 1=on"); -module_param_call(edac_mc_poll_msec, edac_set_poll_msec, param_get_int, +module_param_call(edac_mc_poll_msec, edac_set_poll_msec, param_get_uint, &edac_mc_poll_msec, 0644); MODULE_PARM_DESC(edac_mc_poll_msec, "Polling period in milliseconds"); @@ -426,6 +426,8 @@ static inline int nr_pages_per_csrow(struct csrow_info *csrow) static int edac_create_csrow_object(struct mem_ctl_info *mci, struct csrow_info *csrow, int index) { + int err; + csrow->dev.type = &csrow_attr_type; csrow->dev.bus = mci->bus; csrow->dev.groups = csrow_dev_groups; @@ -438,7 +440,11 @@ static int edac_create_csrow_object(struct mem_ctl_info *mci, edac_dbg(0, "creating (virtual) csrow node %s\n", dev_name(&csrow->dev)); - return device_add(&csrow->dev); + err = device_add(&csrow->dev); + if (err) + put_device(&csrow->dev); + + return err; } /* Create a CSROW object under specifed edac_mc_device */ diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h index b95a48fc723d..c7a7a0891eb6 100644 --- a/drivers/edac/edac_module.h +++ b/drivers/edac/edac_module.h @@ -33,7 +33,7 @@ extern int edac_mc_get_log_ue(void); extern int edac_mc_get_log_ce(void); extern int edac_mc_get_panic_on_ue(void); extern int edac_get_poll_msec(void); -extern int edac_mc_get_poll_msec(void); +extern unsigned int edac_mc_get_poll_msec(void); unsigned edac_dimm_info_location(struct dimm_info *dimm, char *buf, unsigned len); diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c index c8c49b1d5f9f..6e65c02baad1 100644 --- a/drivers/gpio/gpio-omap.c +++ b/drivers/gpio/gpio-omap.c @@ -821,9 +821,9 @@ static void omap_gpio_irq_shutdown(struct irq_data *d) raw_spin_lock_irqsave(&bank->lock, flags); bank->irq_usage &= ~(BIT(offset)); - omap_set_gpio_irqenable(bank, offset, 0); - omap_clear_gpio_irqstatus(bank, offset); omap_set_gpio_triggering(bank, offset, IRQ_TYPE_NONE); + omap_clear_gpio_irqstatus(bank, offset); + omap_set_gpio_irqenable(bank, offset, 0); if (!LINE_USED(bank->mod_usage, offset)) omap_clear_gpio_debounce(bank, offset); omap_disable_gpio_module(bank, offset); @@ -865,8 +865,8 @@ static void omap_gpio_mask_irq(struct irq_data *d) unsigned long flags; raw_spin_lock_irqsave(&bank->lock, flags); - omap_set_gpio_irqenable(bank, offset, 0); omap_set_gpio_triggering(bank, offset, IRQ_TYPE_NONE); + omap_set_gpio_irqenable(bank, offset, 0); raw_spin_unlock_irqrestore(&bank->lock, flags); } @@ -878,9 +878,6 @@ static void omap_gpio_unmask_irq(struct irq_data *d) unsigned long flags; raw_spin_lock_irqsave(&bank->lock, flags); - if (trigger) - omap_set_gpio_triggering(bank, offset, trigger); - omap_set_gpio_irqenable(bank, offset, 1); /* @@ -888,9 +885,13 @@ static void omap_gpio_unmask_irq(struct irq_data *d) * is cleared, thus after the handler has run. OMAP4 needs this done * after enabing the interrupt to clear the wakeup status. */ - if (bank->level_mask & BIT(offset)) + if (bank->regs->leveldetect0 && bank->regs->wkup_en && + trigger & (IRQ_TYPE_LEVEL_HIGH | IRQ_TYPE_LEVEL_LOW)) omap_clear_gpio_irqstatus(bank, offset); + if (trigger) + omap_set_gpio_triggering(bank, offset, trigger); + raw_spin_unlock_irqrestore(&bank->lock, flags); } @@ -1611,6 +1612,8 @@ static struct omap_gpio_reg_offs omap4_gpio_regs = { .clr_dataout = OMAP4_GPIO_CLEARDATAOUT, .irqstatus = OMAP4_GPIO_IRQSTATUS0, .irqstatus2 = OMAP4_GPIO_IRQSTATUS1, + .irqstatus_raw0 = OMAP4_GPIO_IRQSTATUSRAW0, + .irqstatus_raw1 = OMAP4_GPIO_IRQSTATUSRAW1, .irqenable = OMAP4_GPIO_IRQSTATUSSET0, .irqenable2 = OMAP4_GPIO_IRQSTATUSSET1, .set_irqenable = OMAP4_GPIO_IRQSTATUSSET0, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/base.c index 2acc5cbcb6fb..30864de2f148 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/base.c @@ -185,6 +185,25 @@ nvkm_i2c_fini(struct nvkm_subdev *subdev, bool suspend) } static int +nvkm_i2c_preinit(struct nvkm_subdev *subdev) +{ + struct nvkm_i2c *i2c = nvkm_i2c(subdev); + struct nvkm_i2c_bus *bus; + struct nvkm_i2c_pad *pad; + + /* + * We init our i2c busses as early as possible, since they may be + * needed by the vbios init scripts on some cards + */ + list_for_each_entry(pad, &i2c->pad, head) + nvkm_i2c_pad_init(pad); + list_for_each_entry(bus, &i2c->bus, head) + nvkm_i2c_bus_init(bus); + + return 0; +} + +static int nvkm_i2c_init(struct nvkm_subdev *subdev) { struct nvkm_i2c *i2c = nvkm_i2c(subdev); @@ -238,6 +257,7 @@ nvkm_i2c_dtor(struct nvkm_subdev *subdev) static const struct nvkm_subdev_func nvkm_i2c = { .dtor = nvkm_i2c_dtor, + .preinit = nvkm_i2c_preinit, .init = nvkm_i2c_init, .fini = nvkm_i2c_fini, .intr = nvkm_i2c_intr, diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index f418c002d323..ecad4d7c6cd1 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -1389,7 +1389,14 @@ static int panel_simple_dsi_probe(struct mipi_dsi_device *dsi) dsi->format = desc->format; dsi->lanes = desc->lanes; - return mipi_dsi_attach(dsi); + err = mipi_dsi_attach(dsi); + if (err) { + struct panel_simple *panel = dev_get_drvdata(&dsi->dev); + + drm_panel_remove(&panel->base); + } + + return err; } static int panel_simple_dsi_remove(struct mipi_dsi_device *dsi) diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index 6296e9f270ca..0b8f8c10f2ed 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -535,6 +535,9 @@ static int virtio_gpu_get_caps_ioctl(struct drm_device *dev, ret = wait_event_timeout(vgdev->resp_wq, atomic_read(&cache_ent->is_valid), 5 * HZ); + /* is_valid check must proceed before copy of the cache entry. */ + smp_rmb(); + ptr = cache_ent->caps_cache; copy_exit: diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c index 52436b3c01bb..a1b3ea1ccb65 100644 --- a/drivers/gpu/drm/virtio/virtgpu_vq.c +++ b/drivers/gpu/drm/virtio/virtgpu_vq.c @@ -618,6 +618,8 @@ static void virtio_gpu_cmd_capset_cb(struct virtio_gpu_device *vgdev, cache_ent->id == le32_to_cpu(cmd->capset_id)) { memcpy(cache_ent->caps_cache, resp->capset_data, cache_ent->size); + /* Copy must occur before is_valid is signalled. */ + smp_wmb(); atomic_set(&cache_ent->is_valid, 1); break; } diff --git a/drivers/gpu/ipu-v3/ipu-ic.c b/drivers/gpu/ipu-v3/ipu-ic.c index 1dcb96ccda66..1f7b6023dcb4 100644 --- a/drivers/gpu/ipu-v3/ipu-ic.c +++ b/drivers/gpu/ipu-v3/ipu-ic.c @@ -255,7 +255,7 @@ static int init_csc(struct ipu_ic *ic, writel(param, base++); param = ((a[0] & 0x1fe0) >> 5) | (params->scale << 8) | - (params->sat << 9); + (params->sat << 10); writel(param, base++); param = ((a[1] & 0x1f) << 27) | ((c[0][1] & 0x1ff) << 18) | diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c index 7d5c53a1abe4..5fcdb2dbce68 100644 --- a/drivers/hwtracing/intel_th/msu.c +++ b/drivers/hwtracing/intel_th/msu.c @@ -625,7 +625,7 @@ static int msc_buffer_contig_alloc(struct msc *msc, unsigned long size) goto err_out; ret = -ENOMEM; - page = alloc_pages(GFP_KERNEL | __GFP_ZERO, order); + page = alloc_pages(GFP_KERNEL | __GFP_ZERO | GFP_DMA32, order); if (!page) goto err_free_sgt; diff --git a/drivers/input/tablet/gtco.c b/drivers/input/tablet/gtco.c index 8b68a210277b..5a0e4cd86353 100644 --- a/drivers/input/tablet/gtco.c +++ b/drivers/input/tablet/gtco.c @@ -78,6 +78,7 @@ Scott Hill shill@gtcocalcomp.com /* Max size of a single report */ #define REPORT_MAX_SIZE 10 +#define MAX_COLLECTION_LEVELS 10 /* Bitmask whether pen is in range */ @@ -224,8 +225,7 @@ static void parse_hid_report_descriptor(struct gtco *device, char * report, char maintype = 'x'; char globtype[12]; int indent = 0; - char indentstr[10] = ""; - + char indentstr[MAX_COLLECTION_LEVELS + 1] = { 0 }; dev_dbg(ddev, "======>>>>>>PARSE<<<<<<======\n"); @@ -351,6 +351,13 @@ static void parse_hid_report_descriptor(struct gtco *device, char * report, case TAG_MAIN_COL_START: maintype = 'S'; + if (indent == MAX_COLLECTION_LEVELS) { + dev_err(ddev, "Collection level %d would exceed limit of %d\n", + indent + 1, + MAX_COLLECTION_LEVELS); + break; + } + if (data == 0) { dev_dbg(ddev, "======>>>>>> Physical\n"); strcpy(globtype, "Physical"); @@ -370,8 +377,15 @@ static void parse_hid_report_descriptor(struct gtco *device, char * report, break; case TAG_MAIN_COL_END: - dev_dbg(ddev, "<<<<<<======\n"); maintype = 'E'; + + if (indent == 0) { + dev_err(ddev, "Collection level already at zero\n"); + break; + } + + dev_dbg(ddev, "<<<<<<======\n"); + indent--; for (x = 0; x < indent; x++) indentstr[x] = '-'; diff --git a/drivers/isdn/hardware/mISDN/hfcsusb.c b/drivers/isdn/hardware/mISDN/hfcsusb.c index 114f3bcba1b0..c60c7998af17 100644 --- a/drivers/isdn/hardware/mISDN/hfcsusb.c +++ b/drivers/isdn/hardware/mISDN/hfcsusb.c @@ -1963,6 +1963,9 @@ hfcsusb_probe(struct usb_interface *intf, const struct usb_device_id *id) /* get endpoint base */ idx = ((ep_addr & 0x7f) - 1) * 2; + if (idx > 15) + return -EIO; + if (ep_addr & 0x80) idx++; attr = ep->desc.bmAttributes; diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c index 9cf826df89b1..b4ad85251cf7 100644 --- a/drivers/mailbox/mailbox.c +++ b/drivers/mailbox/mailbox.c @@ -389,11 +389,13 @@ struct mbox_chan *mbox_request_channel_byname(struct mbox_client *cl, of_property_for_each_string(np, "mbox-names", prop, mbox_name) { if (!strncmp(name, mbox_name, strlen(name))) - break; + return mbox_request_channel(cl, index); index++; } - return mbox_request_channel(cl, index); + dev_err(cl->dev, "%s() could not locate channel named \"%s\"\n", + __func__, name); + return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(mbox_request_channel_byname); diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index bfbf5dd06ac5..adef364c2b8e 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1403,7 +1403,7 @@ static void cache_set_flush(struct closure *cl) kobject_put(&c->internal); kobject_del(&c->kobj); - if (c->gc_thread) + if (!IS_ERR_OR_NULL(c->gc_thread)) kthread_stop(c->gc_thread); if (!IS_ERR_OR_NULL(c->root)) diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index b1d5fa0bc8f7..8a6e7646e1c9 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1561,9 +1561,7 @@ dm_bufio_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) unsigned long freed; c = container_of(shrink, struct dm_bufio_client, shrinker); - if (sc->gfp_mask & __GFP_FS) - dm_bufio_lock(c); - else if (!dm_bufio_trylock(c)) + if (!dm_bufio_trylock(c)) return SHRINK_STOP; freed = __scan(c, sc->nr_to_scan, sc->gfp_mask); diff --git a/drivers/media/dvb-frontends/tua6100.c b/drivers/media/dvb-frontends/tua6100.c index 029384d1fddd..7a3e91cda5df 100644 --- a/drivers/media/dvb-frontends/tua6100.c +++ b/drivers/media/dvb-frontends/tua6100.c @@ -80,8 +80,8 @@ static int tua6100_set_params(struct dvb_frontend *fe) struct i2c_msg msg1 = { .addr = priv->i2c_address, .flags = 0, .buf = reg1, .len = 4 }; struct i2c_msg msg2 = { .addr = priv->i2c_address, .flags = 0, .buf = reg2, .len = 3 }; -#define _R 4 -#define _P 32 +#define _R_VAL 4 +#define _P_VAL 32 #define _ri 4000000 // setup register 0 @@ -96,14 +96,14 @@ static int tua6100_set_params(struct dvb_frontend *fe) else reg1[1] = 0x0c; - if (_P == 64) + if (_P_VAL == 64) reg1[1] |= 0x40; if (c->frequency >= 1525000) reg1[1] |= 0x80; // register 2 - reg2[1] = (_R >> 8) & 0x03; - reg2[2] = _R; + reg2[1] = (_R_VAL >> 8) & 0x03; + reg2[2] = _R_VAL; if (c->frequency < 1455000) reg2[1] |= 0x1c; else if (c->frequency < 1630000) @@ -115,18 +115,18 @@ static int tua6100_set_params(struct dvb_frontend *fe) * The N divisor ratio (note: c->frequency is in kHz, but we * need it in Hz) */ - prediv = (c->frequency * _R) / (_ri / 1000); - div = prediv / _P; + prediv = (c->frequency * _R_VAL) / (_ri / 1000); + div = prediv / _P_VAL; reg1[1] |= (div >> 9) & 0x03; reg1[2] = div >> 1; reg1[3] = (div << 7); - priv->frequency = ((div * _P) * (_ri / 1000)) / _R; + priv->frequency = ((div * _P_VAL) * (_ri / 1000)) / _R_VAL; // Finally, calculate and store the value for A - reg1[3] |= (prediv - (div*_P)) & 0x7f; + reg1[3] |= (prediv - (div*_P_VAL)) & 0x7f; -#undef _R -#undef _P +#undef _R_VAL +#undef _P_VAL #undef _ri if (fe->ops.i2c_gate_ctrl) diff --git a/drivers/media/i2c/Makefile b/drivers/media/i2c/Makefile index eec9e870755d..7f127e5b043d 100644 --- a/drivers/media/i2c/Makefile +++ b/drivers/media/i2c/Makefile @@ -41,7 +41,7 @@ endif obj-$(CONFIG_VIDEO_ADV7481) += adv7481.o obj-$(CONFIG_VIDEO_TVTUNER) += tvtuner.o obj-$(CONFIG_VIDEO_AD9389B) += ad9389b.o -obj-$(CONFIG_VIDEO_ADV7511) += adv7511.o +obj-$(CONFIG_VIDEO_ADV7511) += adv7511-v4l2.o obj-$(CONFIG_VIDEO_VPX3220) += vpx3220.o obj-$(CONFIG_VIDEO_VS6624) += vs6624.o obj-$(CONFIG_VIDEO_BT819) += bt819.o diff --git a/drivers/media/i2c/adv7511.c b/drivers/media/i2c/adv7511-v4l2.c index c24839cfcc35..b35400e4e9af 100644 --- a/drivers/media/i2c/adv7511.c +++ b/drivers/media/i2c/adv7511-v4l2.c @@ -17,6 +17,11 @@ * SOFTWARE. */ +/* + * This file is named adv7511-v4l2.c so it doesn't conflict with the Analog + * Device ADV7511 (config fragment CONFIG_DRM_I2C_ADV7511). + */ + #include <linux/kernel.h> #include <linux/module.h> diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c index a4639813cf35..439cb76d8e6f 100644 --- a/drivers/media/platform/coda/coda-bit.c +++ b/drivers/media/platform/coda/coda-bit.c @@ -1581,6 +1581,7 @@ static int __coda_start_decoding(struct coda_ctx *ctx) coda_write(dev, 0, CODA_REG_BIT_BIT_STREAM_PARAM); return -ETIMEDOUT; } + ctx->sequence_offset = ~0U; ctx->initialized = 1; /* Update kfifo out pointer from coda bitstream read pointer */ @@ -1966,12 +1967,17 @@ static void coda_finish_decode(struct coda_ctx *ctx) else if (ctx->display_idx < 0) ctx->hold = true; } else if (decoded_idx == -2) { + if (ctx->display_idx >= 0 && + ctx->display_idx < ctx->num_internal_frames) + ctx->sequence_offset++; /* no frame was decoded, we still return remaining buffers */ } else if (decoded_idx < 0 || decoded_idx >= ctx->num_internal_frames) { v4l2_err(&dev->v4l2_dev, "decoded frame index out of range: %d\n", decoded_idx); } else { - val = coda_read(dev, CODA_RET_DEC_PIC_FRAME_NUM) - 1; + val = coda_read(dev, CODA_RET_DEC_PIC_FRAME_NUM); + if (ctx->sequence_offset == -1) + ctx->sequence_offset = val; val -= ctx->sequence_offset; spin_lock_irqsave(&ctx->buffer_meta_lock, flags); if (!list_empty(&ctx->buffer_meta_list)) { @@ -2101,7 +2107,6 @@ irqreturn_t coda_irq_handler(int irq, void *data) if (ctx == NULL) { v4l2_err(&dev->v4l2_dev, "Instance released before the end of transaction\n"); - mutex_unlock(&dev->coda_mutex); return IRQ_HANDLED; } diff --git a/drivers/media/platform/davinci/vpss.c b/drivers/media/platform/davinci/vpss.c index fce86f17dffc..c2c68988e38a 100644 --- a/drivers/media/platform/davinci/vpss.c +++ b/drivers/media/platform/davinci/vpss.c @@ -523,6 +523,11 @@ static int __init vpss_init(void) return -EBUSY; oper_cfg.vpss_regs_base2 = ioremap(VPSS_CLK_CTRL, 4); + if (unlikely(!oper_cfg.vpss_regs_base2)) { + release_mem_region(VPSS_CLK_CTRL, 4); + return -ENOMEM; + } + writel(VPSS_CLK_CTRL_VENCCLKEN | VPSS_CLK_CTRL_DACCLKEN, oper_cfg.vpss_regs_base2); diff --git a/drivers/media/platform/marvell-ccic/mcam-core.c b/drivers/media/platform/marvell-ccic/mcam-core.c index aa2b44041d3f..22fe771d4dd2 100644 --- a/drivers/media/platform/marvell-ccic/mcam-core.c +++ b/drivers/media/platform/marvell-ccic/mcam-core.c @@ -209,7 +209,6 @@ struct mcam_vb_buffer { struct list_head queue; struct mcam_dma_desc *dma_desc; /* Descriptor virtual address */ dma_addr_t dma_desc_pa; /* Descriptor physical address */ - int dma_desc_nent; /* Number of mapped descriptors */ }; static inline struct mcam_vb_buffer *vb_to_mvb(struct vb2_v4l2_buffer *vb) @@ -616,9 +615,11 @@ static void mcam_dma_contig_done(struct mcam_camera *cam, int frame) static void mcam_sg_next_buffer(struct mcam_camera *cam) { struct mcam_vb_buffer *buf; + struct sg_table *sg_table; buf = list_first_entry(&cam->buffers, struct mcam_vb_buffer, queue); list_del_init(&buf->queue); + sg_table = vb2_dma_sg_plane_desc(&buf->vb_buf.vb2_buf, 0); /* * Very Bad Not Good Things happen if you don't clear * C1_DESC_ENA before making any descriptor changes. @@ -626,7 +627,7 @@ static void mcam_sg_next_buffer(struct mcam_camera *cam) mcam_reg_clear_bit(cam, REG_CTRL1, C1_DESC_ENA); mcam_reg_write(cam, REG_DMA_DESC_Y, buf->dma_desc_pa); mcam_reg_write(cam, REG_DESC_LEN_Y, - buf->dma_desc_nent*sizeof(struct mcam_dma_desc)); + sg_table->nents * sizeof(struct mcam_dma_desc)); mcam_reg_write(cam, REG_DESC_LEN_U, 0); mcam_reg_write(cam, REG_DESC_LEN_V, 0); mcam_reg_set_bit(cam, REG_CTRL1, C1_DESC_ENA); diff --git a/drivers/media/radio/radio-raremono.c b/drivers/media/radio/radio-raremono.c index bfb3a6d051ba..10958bac0ad9 100644 --- a/drivers/media/radio/radio-raremono.c +++ b/drivers/media/radio/radio-raremono.c @@ -283,6 +283,14 @@ static int vidioc_g_frequency(struct file *file, void *priv, return 0; } +static void raremono_device_release(struct v4l2_device *v4l2_dev) +{ + struct raremono_device *radio = to_raremono_dev(v4l2_dev); + + kfree(radio->buffer); + kfree(radio); +} + /* File system interface */ static const struct v4l2_file_operations usb_raremono_fops = { .owner = THIS_MODULE, @@ -307,12 +315,14 @@ static int usb_raremono_probe(struct usb_interface *intf, struct raremono_device *radio; int retval = 0; - radio = devm_kzalloc(&intf->dev, sizeof(struct raremono_device), GFP_KERNEL); - if (radio) - radio->buffer = devm_kmalloc(&intf->dev, BUFFER_LENGTH, GFP_KERNEL); - - if (!radio || !radio->buffer) + radio = kzalloc(sizeof(*radio), GFP_KERNEL); + if (!radio) + return -ENOMEM; + radio->buffer = kmalloc(BUFFER_LENGTH, GFP_KERNEL); + if (!radio->buffer) { + kfree(radio); return -ENOMEM; + } radio->usbdev = interface_to_usbdev(intf); radio->intf = intf; @@ -336,7 +346,8 @@ static int usb_raremono_probe(struct usb_interface *intf, if (retval != 3 || (get_unaligned_be16(&radio->buffer[1]) & 0xfff) == 0x0242) { dev_info(&intf->dev, "this is not Thanko's Raremono.\n"); - return -ENODEV; + retval = -ENODEV; + goto free_mem; } dev_info(&intf->dev, "Thanko's Raremono connected: (%04X:%04X)\n", @@ -345,7 +356,7 @@ static int usb_raremono_probe(struct usb_interface *intf, retval = v4l2_device_register(&intf->dev, &radio->v4l2_dev); if (retval < 0) { dev_err(&intf->dev, "couldn't register v4l2_device\n"); - return retval; + goto free_mem; } mutex_init(&radio->lock); @@ -357,6 +368,7 @@ static int usb_raremono_probe(struct usb_interface *intf, radio->vdev.ioctl_ops = &usb_raremono_ioctl_ops; radio->vdev.lock = &radio->lock; radio->vdev.release = video_device_release_empty; + radio->v4l2_dev.release = raremono_device_release; usb_set_intfdata(intf, &radio->v4l2_dev); @@ -372,6 +384,10 @@ static int usb_raremono_probe(struct usb_interface *intf, } dev_err(&intf->dev, "could not register video device\n"); v4l2_device_unregister(&radio->v4l2_dev); + +free_mem: + kfree(radio->buffer); + kfree(radio); return retval; } diff --git a/drivers/media/radio/wl128x/fmdrv_v4l2.c b/drivers/media/radio/wl128x/fmdrv_v4l2.c index fb42f0fd0c1f..add26eac1677 100644 --- a/drivers/media/radio/wl128x/fmdrv_v4l2.c +++ b/drivers/media/radio/wl128x/fmdrv_v4l2.c @@ -553,6 +553,7 @@ int fm_v4l2_init_video_device(struct fmdev *fmdev, int radio_nr) /* Register with V4L2 subsystem as RADIO device */ if (video_register_device(&gradio_dev, VFL_TYPE_RADIO, radio_nr)) { + v4l2_device_unregister(&fmdev->v4l2_dev); fmerr("Could not register video device\n"); return -ENOMEM; } @@ -566,6 +567,8 @@ int fm_v4l2_init_video_device(struct fmdev *fmdev, int radio_nr) if (ret < 0) { fmerr("(fmdev): Can't init ctrl handler\n"); v4l2_ctrl_handler_free(&fmdev->ctrl_handler); + video_unregister_device(fmdev->radio_dev); + v4l2_device_unregister(&fmdev->v4l2_dev); return -EBUSY; } diff --git a/drivers/media/usb/cpia2/cpia2_usb.c b/drivers/media/usb/cpia2/cpia2_usb.c index 351a78a84c3d..41ea00ac3a87 100644 --- a/drivers/media/usb/cpia2/cpia2_usb.c +++ b/drivers/media/usb/cpia2/cpia2_usb.c @@ -884,7 +884,6 @@ static void cpia2_usb_disconnect(struct usb_interface *intf) cpia2_unregister_camera(cam); v4l2_device_disconnect(&cam->v4l2_dev); mutex_unlock(&cam->v4l2_lock); - v4l2_device_put(&cam->v4l2_dev); if(cam->buffers) { DBG("Wakeup waiting processes\n"); @@ -897,6 +896,8 @@ static void cpia2_usb_disconnect(struct usb_interface *intf) DBG("Releasing interface\n"); usb_driver_release_interface(&cpia2_driver, intf); + v4l2_device_put(&cam->v4l2_dev); + LOG("CPiA2 camera disconnected.\n"); } diff --git a/drivers/media/usb/dvb-usb/dvb-usb-init.c b/drivers/media/usb/dvb-usb/dvb-usb-init.c index 1adf325012f7..97a89ef7e4c1 100644 --- a/drivers/media/usb/dvb-usb/dvb-usb-init.c +++ b/drivers/media/usb/dvb-usb/dvb-usb-init.c @@ -286,12 +286,15 @@ EXPORT_SYMBOL(dvb_usb_device_init); void dvb_usb_device_exit(struct usb_interface *intf) { struct dvb_usb_device *d = usb_get_intfdata(intf); - const char *name = "generic DVB-USB module"; + const char *default_name = "generic DVB-USB module"; + char name[40]; usb_set_intfdata(intf, NULL); if (d != NULL && d->desc != NULL) { - name = d->desc->name; + strscpy(name, d->desc->name, sizeof(name)); dvb_usb_exit(d); + } else { + strscpy(name, default_name, sizeof(name)); } info("%s successfully deinitialized and disconnected.", name); diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c index abf3c62c539b..6bb6d8a00247 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls.c +++ b/drivers/media/v4l2-core/v4l2-ctrls.c @@ -2078,16 +2078,15 @@ struct v4l2_ctrl *v4l2_ctrl_new_custom(struct v4l2_ctrl_handler *hdl, v4l2_ctrl_fill(cfg->id, &name, &type, &min, &max, &step, &def, &flags); - is_menu = (cfg->type == V4L2_CTRL_TYPE_MENU || - cfg->type == V4L2_CTRL_TYPE_INTEGER_MENU); + is_menu = (type == V4L2_CTRL_TYPE_MENU || + type == V4L2_CTRL_TYPE_INTEGER_MENU); if (is_menu) WARN_ON(step); else WARN_ON(cfg->menu_skip_mask); - if (cfg->type == V4L2_CTRL_TYPE_MENU && qmenu == NULL) + if (type == V4L2_CTRL_TYPE_MENU && !qmenu) { qmenu = v4l2_ctrl_get_menu(cfg->id); - else if (cfg->type == V4L2_CTRL_TYPE_INTEGER_MENU && - qmenu_int == NULL) { + } else if (type == V4L2_CTRL_TYPE_INTEGER_MENU && !qmenu_int) { handler_set_err(hdl, -EINVAL); return NULL; } diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c index 4d673a626db4..1041eb7a6167 100644 --- a/drivers/memstick/core/memstick.c +++ b/drivers/memstick/core/memstick.c @@ -629,13 +629,18 @@ static int __init memstick_init(void) return -ENOMEM; rc = bus_register(&memstick_bus_type); - if (!rc) - rc = class_register(&memstick_host_class); + if (rc) + goto error_destroy_workqueue; - if (!rc) - return 0; + rc = class_register(&memstick_host_class); + if (rc) + goto error_bus_unregister; + + return 0; +error_bus_unregister: bus_unregister(&memstick_bus_type); +error_destroy_workqueue: destroy_workqueue(workqueue); return rc; diff --git a/drivers/mfd/arizona-core.c b/drivers/mfd/arizona-core.c index d474732cc65c..fb54de5c1aba 100644 --- a/drivers/mfd/arizona-core.c +++ b/drivers/mfd/arizona-core.c @@ -967,7 +967,7 @@ int arizona_dev_init(struct arizona *arizona) unsigned int reg, val, mask; int (*apply_patch)(struct arizona *) = NULL; const struct mfd_cell *subdevs = NULL; - int n_subdevs, ret, i; + int n_subdevs = 0, ret, i; dev_set_drvdata(arizona->dev, arizona); mutex_init(&arizona->clk_lock); diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c index 022c9374ce8b..215bb5eeb5ac 100644 --- a/drivers/mfd/mfd-core.c +++ b/drivers/mfd/mfd-core.c @@ -178,6 +178,7 @@ static int mfd_add_device(struct device *parent, int id, for_each_child_of_node(parent->of_node, np) { if (of_device_is_compatible(np, cell->of_compatible)) { pdev->dev.of_node = np; + pdev->dev.fwnode = &np->fwnode; break; } } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 0397afccf3a2..ed80c973f546 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3714,8 +3714,8 @@ static u32 bond_rr_gen_slave_id(struct bonding *bond) static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - struct iphdr *iph = ip_hdr(skb); struct slave *slave; + int slave_cnt; u32 slave_id; /* Start with the curr_active_slave that joined the bond as the @@ -3724,23 +3724,32 @@ static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev * send the join/membership reports. The curr_active_slave found * will send all of this type of traffic. */ - if (iph->protocol == IPPROTO_IGMP && skb->protocol == htons(ETH_P_IP)) { - slave = rcu_dereference(bond->curr_active_slave); - if (slave) - bond_dev_queue_xmit(bond, skb, slave->dev); - else - bond_xmit_slave_id(bond, skb, 0); - } else { - int slave_cnt = ACCESS_ONCE(bond->slave_cnt); + if (skb->protocol == htons(ETH_P_IP)) { + int noff = skb_network_offset(skb); + struct iphdr *iph; - if (likely(slave_cnt)) { - slave_id = bond_rr_gen_slave_id(bond); - bond_xmit_slave_id(bond, skb, slave_id % slave_cnt); - } else { - bond_tx_drop(bond_dev, skb); + if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph)))) + goto non_igmp; + + iph = ip_hdr(skb); + if (iph->protocol == IPPROTO_IGMP) { + slave = rcu_dereference(bond->curr_active_slave); + if (slave) + bond_dev_queue_xmit(bond, skb, slave->dev); + else + bond_xmit_slave_id(bond, skb, 0); + return NETDEV_TX_OK; } } +non_igmp: + slave_cnt = ACCESS_ONCE(bond->slave_cnt); + if (likely(slave_cnt)) { + slave_id = bond_rr_gen_slave_id(bond); + bond_xmit_slave_id(bond, skb, slave_id % slave_cnt); + } else { + bond_tx_drop(bond_dev, skb); + } return NETDEV_TX_OK; } diff --git a/drivers/net/caif/caif_hsi.c b/drivers/net/caif/caif_hsi.c index 615c65da39be..055a4015ec3b 100644 --- a/drivers/net/caif/caif_hsi.c +++ b/drivers/net/caif/caif_hsi.c @@ -1467,7 +1467,7 @@ static void __exit cfhsi_exit_module(void) rtnl_lock(); list_for_each_safe(list_node, n, &cfhsi_list) { cfhsi = list_entry(list_node, struct cfhsi, list); - unregister_netdev(cfhsi->ndev); + unregister_netdevice(cfhsi->ndev); } rtnl_unlock(); } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index ebc4518d598a..4dc5e12dbfce 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -288,6 +288,9 @@ int bnx2x_tx_int(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata) hw_cons = le16_to_cpu(*txdata->tx_cons_sb); sw_cons = txdata->tx_pkt_cons; + /* Ensure subsequent loads occur after hw_cons */ + smp_rmb(); + while (sw_cons != hw_cons) { u16 pkt_cons; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 74dd48f2bd89..04fe570275cd 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3090,39 +3090,42 @@ static void bcmgenet_timeout(struct net_device *dev) netif_tx_wake_all_queues(dev); } -#define MAX_MC_COUNT 16 +#define MAX_MDF_FILTER 17 static inline void bcmgenet_set_mdf_addr(struct bcmgenet_priv *priv, unsigned char *addr, - int *i, - int *mc) + int *i) { - u32 reg; - bcmgenet_umac_writel(priv, addr[0] << 8 | addr[1], UMAC_MDF_ADDR + (*i * 4)); bcmgenet_umac_writel(priv, addr[2] << 24 | addr[3] << 16 | addr[4] << 8 | addr[5], UMAC_MDF_ADDR + ((*i + 1) * 4)); - reg = bcmgenet_umac_readl(priv, UMAC_MDF_CTRL); - reg |= (1 << (MAX_MC_COUNT - *mc)); - bcmgenet_umac_writel(priv, reg, UMAC_MDF_CTRL); *i += 2; - (*mc)++; } static void bcmgenet_set_rx_mode(struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); struct netdev_hw_addr *ha; - int i, mc; + int i, nfilter; u32 reg; netif_dbg(priv, hw, dev, "%s: %08X\n", __func__, dev->flags); - /* Promiscuous mode */ + /* Number of filters needed */ + nfilter = netdev_uc_count(dev) + netdev_mc_count(dev) + 2; + + /* + * Turn on promicuous mode for three scenarios + * 1. IFF_PROMISC flag is set + * 2. IFF_ALLMULTI flag is set + * 3. The number of filters needed exceeds the number filters + * supported by the hardware. + */ reg = bcmgenet_umac_readl(priv, UMAC_CMD); - if (dev->flags & IFF_PROMISC) { + if ((dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) || + (nfilter > MAX_MDF_FILTER)) { reg |= CMD_PROMISC; bcmgenet_umac_writel(priv, reg, UMAC_CMD); bcmgenet_umac_writel(priv, 0, UMAC_MDF_CTRL); @@ -3132,32 +3135,24 @@ static void bcmgenet_set_rx_mode(struct net_device *dev) bcmgenet_umac_writel(priv, reg, UMAC_CMD); } - /* UniMac doesn't support ALLMULTI */ - if (dev->flags & IFF_ALLMULTI) { - netdev_warn(dev, "ALLMULTI is not supported\n"); - return; - } - /* update MDF filter */ i = 0; - mc = 0; /* Broadcast */ - bcmgenet_set_mdf_addr(priv, dev->broadcast, &i, &mc); + bcmgenet_set_mdf_addr(priv, dev->broadcast, &i); /* my own address.*/ - bcmgenet_set_mdf_addr(priv, dev->dev_addr, &i, &mc); - /* Unicast list*/ - if (netdev_uc_count(dev) > (MAX_MC_COUNT - mc)) - return; + bcmgenet_set_mdf_addr(priv, dev->dev_addr, &i); - if (!netdev_uc_empty(dev)) - netdev_for_each_uc_addr(ha, dev) - bcmgenet_set_mdf_addr(priv, ha->addr, &i, &mc); - /* Multicast */ - if (netdev_mc_empty(dev) || netdev_mc_count(dev) >= (MAX_MC_COUNT - mc)) - return; + /* Unicast */ + netdev_for_each_uc_addr(ha, dev) + bcmgenet_set_mdf_addr(priv, ha->addr, &i); + /* Multicast */ netdev_for_each_mc_addr(ha, dev) - bcmgenet_set_mdf_addr(priv, ha->addr, &i, &mc); + bcmgenet_set_mdf_addr(priv, ha->addr, &i); + + /* Enable filters */ + reg = GENMASK(MAX_MDF_FILTER - 1, MAX_MDF_FILTER - nfilter); + bcmgenet_umac_writel(priv, reg, UMAC_MDF_CTRL); } /* Set the hardware MAC address. */ diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index ae8e4fc22e7b..0ee164d09f39 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1699,10 +1699,10 @@ static void fec_get_mac(struct net_device *ndev) */ if (!is_valid_ether_addr(iap)) { /* Report it and use a random ethernet address instead */ - netdev_err(ndev, "Invalid MAC address: %pM\n", iap); + dev_err(&fep->pdev->dev, "Invalid MAC address: %pM\n", iap); eth_hw_addr_random(ndev); - netdev_info(ndev, "Using random MAC address: %pM\n", - ndev->dev_addr); + dev_info(&fep->pdev->dev, "Using random MAC address: %pM\n", + ndev->dev_addr); return; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index d681273bd39d..9d38634071a4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -3133,7 +3133,8 @@ static int ixgbe_get_module_info(struct net_device *dev, page_swap = true; } - if (sff8472_rev == IXGBE_SFF_SFF_8472_UNSUP || page_swap) { + if (sff8472_rev == IXGBE_SFF_SFF_8472_UNSUP || page_swap || + !(addr_mode & IXGBE_SFF_DDM_IMPLEMENTED)) { /* We have a SFP, but it does not support SFF-8472 */ modinfo->type = ETH_MODULE_SFF_8079; modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h index 5abd66c84d00..7b7dc6d7d159 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h @@ -70,6 +70,7 @@ #define IXGBE_SFF_SOFT_RS_SELECT_10G 0x8 #define IXGBE_SFF_SOFT_RS_SELECT_1G 0x0 #define IXGBE_SFF_ADDRESSING_MODE 0x4 +#define IXGBE_SFF_DDM_IMPLEMENTED 0x40 #define IXGBE_SFF_QSFP_DA_ACTIVE_CABLE 0x1 #define IXGBE_SFF_QSFP_DA_PASSIVE_CABLE 0x8 #define IXGBE_SFF_QSFP_CONNECTOR_NOT_SEPARABLE 0x23 diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index 5cc05df69a86..dcd72b2a3715 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -4939,6 +4939,13 @@ static const struct dmi_system_id msi_blacklist[] = { DMI_MATCH(DMI_PRODUCT_NAME, "P-79"), }, }, + { + .ident = "ASUS P6T", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), + DMI_MATCH(DMI_BOARD_NAME, "P6T"), + }, + }, {} }; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index 371a669d69fd..1df84c8de9d7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -187,6 +187,12 @@ static void dwmac1000_set_filter(struct mac_device_info *hw, GMAC_ADDR_LOW(reg)); reg++; } + + while (reg <= perfect_addr_number) { + writel(0, ioaddr + GMAC_ADDR_HIGH(reg)); + writel(0, ioaddr + GMAC_ADDR_LOW(reg)); + reg++; + } } #ifdef FRAME_FILTER_DEBUG diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 58ba579793f8..f1e969128a4e 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -613,6 +613,10 @@ static void axienet_start_xmit_done(struct net_device *ndev) ndev->stats.tx_packets += packets; ndev->stats.tx_bytes += size; + + /* Matches barrier in axienet_start_xmit */ + smp_mb(); + netif_wake_queue(ndev); } @@ -667,9 +671,19 @@ static int axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev) cur_p = &lp->tx_bd_v[lp->tx_bd_tail]; if (axienet_check_tx_bd_space(lp, num_frag)) { - if (!netif_queue_stopped(ndev)) - netif_stop_queue(ndev); - return NETDEV_TX_BUSY; + if (netif_queue_stopped(ndev)) + return NETDEV_TX_BUSY; + + netif_stop_queue(ndev); + + /* Matches barrier in axienet_start_xmit_done */ + smp_mb(); + + /* Space might have just been freed - check again */ + if (axienet_check_tx_bd_space(lp, num_frag)) + return NETDEV_TX_BUSY; + + netif_wake_queue(ndev); } if (skb->ip_summed == CHECKSUM_PARTIAL) { diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 70f26b30729c..c6a87834723d 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -472,6 +472,9 @@ int phy_connect_direct(struct net_device *dev, struct phy_device *phydev, { int rc; + if (!dev) + return -EINVAL; + rc = phy_attach_direct(dev, phydev, phydev->dev_flags, interface); if (rc) return rc; @@ -704,6 +707,9 @@ struct phy_device *phy_attach(struct net_device *dev, const char *bus_id, struct device *d; int rc; + if (!dev) + return ERR_PTR(-EINVAL); + /* Search the list of PHY devices on the mdio bus for the * PHY with the requested name */ diff --git a/drivers/net/wireless/ath/ath10k/hw.c b/drivers/net/wireless/ath/ath10k/hw.c index 558214cef688..5b7faab1cf02 100644 --- a/drivers/net/wireless/ath/ath10k/hw.c +++ b/drivers/net/wireless/ath/ath10k/hw.c @@ -488,7 +488,7 @@ const struct ath10k_hw_values qca6174_values = { const struct ath10k_hw_values qca99x0_values = { .pdev_suspend_option = WMI_PDEV_SUSPEND_AND_DISABLE_INTR, - .rtc_state_val_on = 5, + .rtc_state_val_on = 7, .ce_count = 12, .msi_assign_ce_max = 12, .num_target_ce_config_wlan = 10, diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index 79c1a09a6965..803ec58ff20d 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -1615,6 +1615,10 @@ static int ath10k_mac_setup_prb_tmpl(struct ath10k_vif *arvif) if (arvif->vdev_type != WMI_VDEV_TYPE_AP) return 0; + /* For mesh, probe response and beacon share the same template */ + if (ieee80211_vif_is_mesh(vif)) + return 0; + prb = ieee80211_proberesp_get(hw, vif); if (!prb) { ath10k_warn(ar, "failed to get probe resp template from mac80211\n"); diff --git a/drivers/net/wireless/ath/ath6kl/wmi.c b/drivers/net/wireless/ath/ath6kl/wmi.c index a5e1de75a4a3..b2ec254f154e 100644 --- a/drivers/net/wireless/ath/ath6kl/wmi.c +++ b/drivers/net/wireless/ath/ath6kl/wmi.c @@ -1178,6 +1178,10 @@ static int ath6kl_wmi_pstream_timeout_event_rx(struct wmi *wmi, u8 *datap, return -EINVAL; ev = (struct wmi_pstream_timeout_event *) datap; + if (ev->traffic_class >= WMM_NUM_AC) { + ath6kl_err("invalid traffic class: %d\n", ev->traffic_class); + return -EINVAL; + } /* * When the pstream (fat pipe == AC) timesout, it means there were @@ -1519,6 +1523,10 @@ static int ath6kl_wmi_cac_event_rx(struct wmi *wmi, u8 *datap, int len, return -EINVAL; reply = (struct wmi_cac_event *) datap; + if (reply->ac >= WMM_NUM_AC) { + ath6kl_err("invalid AC: %d\n", reply->ac); + return -EINVAL; + } if ((reply->cac_indication == CAC_INDICATION_ADMISSION_RESP) && (reply->status_code != IEEE80211_TSPEC_STATUS_ADMISS_ACCEPTED)) { @@ -2631,7 +2639,7 @@ int ath6kl_wmi_delete_pstream_cmd(struct wmi *wmi, u8 if_idx, u8 traffic_class, u16 active_tsids = 0; int ret; - if (traffic_class > 3) { + if (traffic_class >= WMM_NUM_AC) { ath6kl_err("invalid traffic class: %d\n", traffic_class); return -EINVAL; } diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c index 4435c7bbb625..d50e2e8bd998 100644 --- a/drivers/net/wireless/ath/ath9k/hw.c +++ b/drivers/net/wireless/ath/ath9k/hw.c @@ -250,8 +250,9 @@ void ath9k_hw_get_channel_centers(struct ath_hw *ah, /* Chip Revisions */ /******************/ -static void ath9k_hw_read_revisions(struct ath_hw *ah) +static bool ath9k_hw_read_revisions(struct ath_hw *ah) { + u32 srev; u32 val; if (ah->get_mac_revision) @@ -267,25 +268,33 @@ static void ath9k_hw_read_revisions(struct ath_hw *ah) val = REG_READ(ah, AR_SREV); ah->hw_version.macRev = MS(val, AR_SREV_REVISION2); } - return; + return true; case AR9300_DEVID_AR9340: ah->hw_version.macVersion = AR_SREV_VERSION_9340; - return; + return true; case AR9300_DEVID_QCA955X: ah->hw_version.macVersion = AR_SREV_VERSION_9550; - return; + return true; case AR9300_DEVID_AR953X: ah->hw_version.macVersion = AR_SREV_VERSION_9531; - return; + return true; case AR9300_DEVID_QCA956X: ah->hw_version.macVersion = AR_SREV_VERSION_9561; - return; + return true; } - val = REG_READ(ah, AR_SREV) & AR_SREV_ID; + srev = REG_READ(ah, AR_SREV); + + if (srev == -EIO) { + ath_err(ath9k_hw_common(ah), + "Failed to read SREV register"); + return false; + } + + val = srev & AR_SREV_ID; if (val == 0xFF) { - val = REG_READ(ah, AR_SREV); + val = srev; ah->hw_version.macVersion = (val & AR_SREV_VERSION2) >> AR_SREV_TYPE2_S; ah->hw_version.macRev = MS(val, AR_SREV_REVISION2); @@ -304,6 +313,8 @@ static void ath9k_hw_read_revisions(struct ath_hw *ah) if (ah->hw_version.macVersion == AR_SREV_VERSION_5416_PCIE) ah->is_pciexpress = true; } + + return true; } /************************************/ @@ -556,7 +567,10 @@ static int __ath9k_hw_init(struct ath_hw *ah) struct ath_common *common = ath9k_hw_common(ah); int r = 0; - ath9k_hw_read_revisions(ah); + if (!ath9k_hw_read_revisions(ah)) { + ath_err(common, "Could not read hardware revisions"); + return -EOPNOTSUPP; + } switch (ah->hw_version.macVersion) { case AR_SREV_VERSION_5416_PCI: diff --git a/drivers/net/wireless/ath/dfs_pattern_detector.c b/drivers/net/wireless/ath/dfs_pattern_detector.c index 2303ef96299d..0835828ffed7 100644 --- a/drivers/net/wireless/ath/dfs_pattern_detector.c +++ b/drivers/net/wireless/ath/dfs_pattern_detector.c @@ -111,7 +111,7 @@ static const struct radar_detector_specs jp_radar_ref_types[] = { JP_PATTERN(0, 0, 1, 1428, 1428, 1, 18, 29, false), JP_PATTERN(1, 2, 3, 3846, 3846, 1, 18, 29, false), JP_PATTERN(2, 0, 1, 1388, 1388, 1, 18, 50, false), - JP_PATTERN(3, 1, 2, 4000, 4000, 1, 18, 50, false), + JP_PATTERN(3, 0, 4, 4000, 4000, 1, 18, 50, false), JP_PATTERN(4, 0, 5, 150, 230, 1, 23, 50, false), JP_PATTERN(5, 6, 10, 200, 500, 1, 16, 50, false), JP_PATTERN(6, 11, 20, 200, 500, 1, 12, 50, false), diff --git a/drivers/net/wireless/mediatek/mt7601u/dma.c b/drivers/net/wireless/mediatek/mt7601u/dma.c index 57a80cfa39b1..3d0b9324d5bf 100644 --- a/drivers/net/wireless/mediatek/mt7601u/dma.c +++ b/drivers/net/wireless/mediatek/mt7601u/dma.c @@ -193,10 +193,23 @@ static void mt7601u_complete_rx(struct urb *urb) struct mt7601u_rx_queue *q = &dev->rx_q; unsigned long flags; - spin_lock_irqsave(&dev->rx_lock, flags); + /* do no schedule rx tasklet if urb has been unlinked + * or the device has been removed + */ + switch (urb->status) { + case -ECONNRESET: + case -ESHUTDOWN: + case -ENOENT: + return; + default: + dev_err_ratelimited(dev->dev, "rx urb failed: %d\n", + urb->status); + /* fall through */ + case 0: + break; + } - if (mt7601u_urb_has_error(urb)) - dev_err(dev->dev, "Error: RX urb failed:%d\n", urb->status); + spin_lock_irqsave(&dev->rx_lock, flags); if (WARN_ONCE(q->e[q->end].urb != urb, "RX urb mismatch")) goto out; @@ -228,14 +241,25 @@ static void mt7601u_complete_tx(struct urb *urb) struct sk_buff *skb; unsigned long flags; - spin_lock_irqsave(&dev->tx_lock, flags); + switch (urb->status) { + case -ECONNRESET: + case -ESHUTDOWN: + case -ENOENT: + return; + default: + dev_err_ratelimited(dev->dev, "tx urb failed: %d\n", + urb->status); + /* fall through */ + case 0: + break; + } - if (mt7601u_urb_has_error(urb)) - dev_err(dev->dev, "Error: TX urb failed:%d\n", urb->status); + spin_lock_irqsave(&dev->tx_lock, flags); if (WARN_ONCE(q->e[q->start].urb != urb, "TX urb mismatch")) goto out; skb = q->e[q->start].skb; + q->e[q->start].skb = NULL; trace_mt_tx_dma_done(dev, skb); __skb_queue_tail(&dev->tx_skb_done, skb); @@ -363,19 +387,9 @@ int mt7601u_dma_enqueue_tx(struct mt7601u_dev *dev, struct sk_buff *skb, static void mt7601u_kill_rx(struct mt7601u_dev *dev) { int i; - unsigned long flags; - - spin_lock_irqsave(&dev->rx_lock, flags); - - for (i = 0; i < dev->rx_q.entries; i++) { - int next = dev->rx_q.end; - spin_unlock_irqrestore(&dev->rx_lock, flags); - usb_poison_urb(dev->rx_q.e[next].urb); - spin_lock_irqsave(&dev->rx_lock, flags); - } - - spin_unlock_irqrestore(&dev->rx_lock, flags); + for (i = 0; i < dev->rx_q.entries; i++) + usb_poison_urb(dev->rx_q.e[i].urb); } static int mt7601u_submit_rx_buf(struct mt7601u_dev *dev, @@ -445,10 +459,10 @@ static void mt7601u_free_tx_queue(struct mt7601u_tx_queue *q) { int i; - WARN_ON(q->used); - for (i = 0; i < q->entries; i++) { usb_poison_urb(q->e[i].urb); + if (q->e[i].skb) + mt7601u_tx_status(q->dev, q->e[i].skb); usb_free_urb(q->e[i].urb); } } diff --git a/drivers/net/wireless/mediatek/mt7601u/tx.c b/drivers/net/wireless/mediatek/mt7601u/tx.c index a0a33dc8f6bc..a1b6db2a8937 100644 --- a/drivers/net/wireless/mediatek/mt7601u/tx.c +++ b/drivers/net/wireless/mediatek/mt7601u/tx.c @@ -117,9 +117,9 @@ void mt7601u_tx_status(struct mt7601u_dev *dev, struct sk_buff *skb) info->status.rates[0].idx = -1; info->flags |= IEEE80211_TX_STAT_ACK; - spin_lock(&dev->mac_lock); + spin_lock_bh(&dev->mac_lock); ieee80211_tx_status(dev->hw, skb); - spin_unlock(&dev->mac_lock); + spin_unlock_bh(&dev->mac_lock); } static int mt7601u_skb_rooms(struct mt7601u_dev *dev, struct sk_buff *skb) diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 5fb4ed6ea322..6ac6618c1c10 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -371,7 +371,7 @@ static ssize_t remove_store(struct device *dev, struct device_attribute *attr, pci_stop_and_remove_bus_device_locked(to_pci_dev(dev)); return count; } -static struct device_attribute dev_remove_attr = __ATTR(remove, +static struct device_attribute dev_remove_attr = __ATTR_IGNORE_LOCKDEP(remove, (S_IWUSR|S_IWGRP), NULL, remove_store); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 5073ab023123..82b0c2cc2fd3 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1736,6 +1736,13 @@ static void pci_pme_list_scan(struct work_struct *work) */ if (bridge && bridge->current_state != PCI_D0) continue; + /* + * If the device is in D3cold it should not be + * polled either. + */ + if (pme_dev->dev->current_state == PCI_D3cold) + continue; + pci_pme_wakeup(pme_dev->dev, NULL); } else { list_del(&pme_dev->list); diff --git a/drivers/phy/phy-rcar-gen2.c b/drivers/phy/phy-rcar-gen2.c index c7a05996d5c1..99d2b73654f4 100644 --- a/drivers/phy/phy-rcar-gen2.c +++ b/drivers/phy/phy-rcar-gen2.c @@ -287,6 +287,7 @@ static int rcar_gen2_phy_probe(struct platform_device *pdev) error = of_property_read_u32(np, "reg", &channel_num); if (error || channel_num > 2) { dev_err(dev, "Invalid \"reg\" property\n"); + of_node_put(np); return error; } channel->select_mask = select_mask[channel_num]; @@ -302,6 +303,7 @@ static int rcar_gen2_phy_probe(struct platform_device *pdev) &rcar_gen2_phy_ops); if (IS_ERR(phy->phy)) { dev_err(dev, "Failed to create PHY\n"); + of_node_put(np); return PTR_ERR(phy->phy); } phy_set_drvdata(phy->phy, phy); diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index a0651128e23a..616055b5e996 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -1837,6 +1837,7 @@ static int rockchip_get_bank_data(struct rockchip_pin_bank *bank, base, &rockchip_regmap_config); } + of_node_put(node); } bank->irq = irq_of_parse_and_map(bank->of_node, 0); diff --git a/drivers/pps/pps.c b/drivers/pps/pps.c index 2f07cd615665..76ae38450aea 100644 --- a/drivers/pps/pps.c +++ b/drivers/pps/pps.c @@ -129,6 +129,14 @@ static long pps_cdev_ioctl(struct file *file, pps->params.mode |= PPS_CANWAIT; pps->params.api_version = PPS_API_VERS; + /* + * Clear unused fields of pps_kparams to avoid leaking + * uninitialized data of the PPS_SETPARAMS caller via + * PPS_GETPARAMS + */ + pps->params.assert_off_tu.flags = 0; + pps->params.clear_off_tu.flags = 0; + spin_unlock_irq(&pps->lock); break; diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c index 47694dd515ab..fa3a1243ff09 100644 --- a/drivers/regulator/s2mps11.c +++ b/drivers/regulator/s2mps11.c @@ -382,8 +382,8 @@ static const struct regulator_desc s2mps11_regulators[] = { regulator_desc_s2mps11_buck1_4(4), regulator_desc_s2mps11_buck5, regulator_desc_s2mps11_buck67810(6, MIN_600_MV, STEP_6_25_MV), - regulator_desc_s2mps11_buck67810(7, MIN_600_MV, STEP_12_5_MV), - regulator_desc_s2mps11_buck67810(8, MIN_600_MV, STEP_12_5_MV), + regulator_desc_s2mps11_buck67810(7, MIN_750_MV, STEP_12_5_MV), + regulator_desc_s2mps11_buck67810(8, MIN_750_MV, STEP_12_5_MV), regulator_desc_s2mps11_buck9, regulator_desc_s2mps11_buck67810(10, MIN_750_MV, STEP_12_5_MV), }; diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index d64b401f3d05..8d7fc3b6ca63 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -752,6 +752,7 @@ static int get_outbound_buffer_frontier(struct qdio_q *q) switch (state) { case SLSB_P_OUTPUT_EMPTY: + case SLSB_P_OUTPUT_PENDING: /* the adapter got it */ DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "out empty:%1d %02x", q->nr, count); diff --git a/drivers/staging/media/davinci_vpfe/vpfe_video.c b/drivers/staging/media/davinci_vpfe/vpfe_video.c index 0fdff91624fd..43474f562b43 100644 --- a/drivers/staging/media/davinci_vpfe/vpfe_video.c +++ b/drivers/staging/media/davinci_vpfe/vpfe_video.c @@ -406,6 +406,9 @@ static int vpfe_open(struct file *file) /* If decoder is not initialized. initialize it */ if (!video->initialized && vpfe_update_pipe_state(video)) { mutex_unlock(&video->lock); + v4l2_fh_del(&handle->vfh); + v4l2_fh_exit(&handle->vfh); + kfree(handle); return -ENODEV; } /* Increment device users counter */ diff --git a/drivers/tty/serial/cpm_uart/cpm_uart_core.c b/drivers/tty/serial/cpm_uart/cpm_uart_core.c index 0040c29f651a..b9e137c03fe3 100644 --- a/drivers/tty/serial/cpm_uart/cpm_uart_core.c +++ b/drivers/tty/serial/cpm_uart/cpm_uart_core.c @@ -421,7 +421,16 @@ static int cpm_uart_startup(struct uart_port *port) clrbits16(&pinfo->sccp->scc_sccm, UART_SCCM_RX); } cpm_uart_initbd(pinfo); - cpm_line_cr_cmd(pinfo, CPM_CR_INIT_TRX); + if (IS_SMC(pinfo)) { + out_be32(&pinfo->smcup->smc_rstate, 0); + out_be32(&pinfo->smcup->smc_tstate, 0); + out_be16(&pinfo->smcup->smc_rbptr, + in_be16(&pinfo->smcup->smc_rbase)); + out_be16(&pinfo->smcup->smc_tbptr, + in_be16(&pinfo->smcup->smc_tbase)); + } else { + cpm_line_cr_cmd(pinfo, CPM_CR_INIT_TRX); + } } /* Install interrupt handler. */ retval = request_irq(port->irq, cpm_uart_int, 0, "cpm_uart", port); @@ -875,16 +884,14 @@ static void cpm_uart_init_smc(struct uart_cpm_port *pinfo) (u8 __iomem *)pinfo->tx_bd_base - DPRAM_BASE); /* - * In case SMC1 is being relocated... + * In case SMC is being relocated... */ -#if defined (CONFIG_I2C_SPI_SMC1_UCODE_PATCH) out_be16(&up->smc_rbptr, in_be16(&pinfo->smcup->smc_rbase)); out_be16(&up->smc_tbptr, in_be16(&pinfo->smcup->smc_tbase)); out_be32(&up->smc_rstate, 0); out_be32(&up->smc_tstate, 0); out_be16(&up->smc_brkcr, 1); /* number of break chars */ out_be16(&up->smc_brkec, 0); -#endif /* Set up the uart parameters in the * parameter ram. @@ -898,8 +905,6 @@ static void cpm_uart_init_smc(struct uart_cpm_port *pinfo) out_be16(&up->smc_brkec, 0); out_be16(&up->smc_brkcr, 1); - cpm_line_cr_cmd(pinfo, CPM_CR_INIT_TRX); - /* Set UART mode, 8 bit, no parity, one stop. * Enable receive and transmit. */ diff --git a/drivers/tty/serial/digicolor-usart.c b/drivers/tty/serial/digicolor-usart.c index a80cdad114f3..d8cb94997487 100644 --- a/drivers/tty/serial/digicolor-usart.c +++ b/drivers/tty/serial/digicolor-usart.c @@ -544,7 +544,11 @@ static int __init digicolor_uart_init(void) if (ret) return ret; - return platform_driver_register(&digicolor_uart_platform); + ret = platform_driver_register(&digicolor_uart_platform); + if (ret) + uart_unregister_driver(&digicolor_uart); + + return ret; } module_init(digicolor_uart_init); diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c index 0ac0c618954e..a66fb7afecc7 100644 --- a/drivers/tty/serial/max310x.c +++ b/drivers/tty/serial/max310x.c @@ -486,37 +486,48 @@ static bool max310x_reg_precious(struct device *dev, unsigned int reg) static int max310x_set_baud(struct uart_port *port, int baud) { - unsigned int mode = 0, clk = port->uartclk, div = clk / baud; + unsigned int mode = 0, div = 0, frac = 0, c = 0, F = 0; - /* Check for minimal value for divider */ - if (div < 16) - div = 16; - - if (clk % baud && (div / 16) < 0x8000) { + /* + * Calculate the integer divisor first. Select a proper mode + * in case if the requested baud is too high for the pre-defined + * clocks frequency. + */ + div = port->uartclk / baud; + if (div < 8) { + /* Mode x4 */ + c = 4; + mode = MAX310X_BRGCFG_4XMODE_BIT; + } else if (div < 16) { /* Mode x2 */ + c = 8; mode = MAX310X_BRGCFG_2XMODE_BIT; - clk = port->uartclk * 2; - div = clk / baud; - - if (clk % baud && (div / 16) < 0x8000) { - /* Mode x4 */ - mode = MAX310X_BRGCFG_4XMODE_BIT; - clk = port->uartclk * 4; - div = clk / baud; - } + } else { + c = 16; } - max310x_port_write(port, MAX310X_BRGDIVMSB_REG, (div / 16) >> 8); - max310x_port_write(port, MAX310X_BRGDIVLSB_REG, div / 16); - max310x_port_write(port, MAX310X_BRGCFG_REG, (div % 16) | mode); + /* Calculate the divisor in accordance with the fraction coefficient */ + div /= c; + F = c*baud; + + /* Calculate the baud rate fraction */ + if (div > 0) + frac = (16*(port->uartclk % F)) / F; + else + div = 1; + + max310x_port_write(port, MAX310X_BRGDIVMSB_REG, div >> 8); + max310x_port_write(port, MAX310X_BRGDIVLSB_REG, div); + max310x_port_write(port, MAX310X_BRGCFG_REG, frac | mode); - return DIV_ROUND_CLOSEST(clk, div); + /* Return the actual baud rate we just programmed */ + return (16*port->uartclk) / (c*(16*div + frac)); } static int max310x_update_best_err(unsigned long f, long *besterr) { /* Use baudrate 115200 for calculate error */ - long err = f % (115200 * 16); + long err = f % (460800 * 16); if ((*besterr < 0) || (*besterr > err)) { *besterr = err; diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c index eb66f7a68dc4..924c50da9762 100644 --- a/drivers/tty/serial/msm_serial.c +++ b/drivers/tty/serial/msm_serial.c @@ -395,10 +395,14 @@ no_rx: static inline void msm_wait_for_xmitr(struct uart_port *port) { + unsigned int timeout = 500000; + while (!(msm_read(port, UART_SR) & UART_SR_TX_EMPTY)) { if (msm_read(port, UART_ISR) & UART_ISR_TX_READY) break; udelay(1); + if (!timeout--) + break; } msm_write(port, UART_CR_CMD_RESET_TX_READY, UART_CR); } diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 669134e27ed9..c450e32c153d 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -1203,6 +1203,7 @@ static void work_fn_tx(struct work_struct *work) struct uart_port *port = &s->port; struct circ_buf *xmit = &port->state->xmit; dma_addr_t buf; + int head, tail; /* * DMA is idle now. @@ -1212,16 +1213,23 @@ static void work_fn_tx(struct work_struct *work) * consistent xmit buffer state. */ spin_lock_irq(&port->lock); - buf = s->tx_dma_addr + (xmit->tail & (UART_XMIT_SIZE - 1)); + head = xmit->head; + tail = xmit->tail; + buf = s->tx_dma_addr + (tail & (UART_XMIT_SIZE - 1)); s->tx_dma_len = min_t(unsigned int, - CIRC_CNT(xmit->head, xmit->tail, UART_XMIT_SIZE), - CIRC_CNT_TO_END(xmit->head, xmit->tail, UART_XMIT_SIZE)); - spin_unlock_irq(&port->lock); + CIRC_CNT(head, tail, UART_XMIT_SIZE), + CIRC_CNT_TO_END(head, tail, UART_XMIT_SIZE)); + if (!s->tx_dma_len) { + /* Transmit buffer has been flushed */ + spin_unlock_irq(&port->lock); + return; + } desc = dmaengine_prep_slave_single(chan, buf, s->tx_dma_len, DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT | DMA_CTRL_ACK); if (!desc) { + spin_unlock_irq(&port->lock); dev_warn(port->dev, "Failed preparing Tx DMA descriptor\n"); /* switch to PIO */ sci_tx_dma_release(s, true); @@ -1231,20 +1239,20 @@ static void work_fn_tx(struct work_struct *work) dma_sync_single_for_device(chan->device->dev, buf, s->tx_dma_len, DMA_TO_DEVICE); - spin_lock_irq(&port->lock); desc->callback = sci_dma_tx_complete; desc->callback_param = s; - spin_unlock_irq(&port->lock); s->cookie_tx = dmaengine_submit(desc); if (dma_submit_error(s->cookie_tx)) { + spin_unlock_irq(&port->lock); dev_warn(port->dev, "Failed submitting Tx DMA descriptor\n"); /* switch to PIO */ sci_tx_dma_release(s, true); return; } + spin_unlock_irq(&port->lock); dev_dbg(port->dev, "%s: %p: %d...%d, cookie %d\n", - __func__, xmit->buf, xmit->tail, xmit->head, s->cookie_tx); + __func__, xmit->buf, tail, head, s->cookie_tx); dma_async_issue_pending(chan); } diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 9d46cb7cb21d..63f7364ac2ce 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -3492,6 +3492,7 @@ static int hub_handle_remote_wakeup(struct usb_hub *hub, unsigned int port, struct usb_device *hdev; struct usb_device *udev; int connect_change = 0; + u16 link_state; int ret; hdev = hub->hdev; @@ -3501,9 +3502,11 @@ static int hub_handle_remote_wakeup(struct usb_hub *hub, unsigned int port, return 0; usb_clear_port_feature(hdev, port, USB_PORT_FEAT_C_SUSPEND); } else { + link_state = portstatus & USB_PORT_STAT_LINK_STATE; if (!udev || udev->state != USB_STATE_SUSPENDED || - (portstatus & USB_PORT_STAT_LINK_STATE) != - USB_SS_PORT_LS_U0) + (link_state != USB_SS_PORT_LS_U0 && + link_state != USB_SS_PORT_LS_U1 && + link_state != USB_SS_PORT_LS_U2)) return 0; } @@ -3833,6 +3836,9 @@ static int usb_set_lpm_timeout(struct usb_device *udev, * control transfers to set the hub timeout or enable device-initiated U1/U2 * will be successful. * + * If the control transfer to enable device-initiated U1/U2 entry fails, then + * hub-initiated U1/U2 will be disabled. + * * If we cannot set the parent hub U1/U2 timeout, we attempt to let the xHCI * driver know about it. If that call fails, it should be harmless, and just * take up more slightly more bus bandwidth for unnecessary U1/U2 exit latency. @@ -3887,23 +3893,24 @@ static void usb_enable_link_state(struct usb_hcd *hcd, struct usb_device *udev, * host know that this link state won't be enabled. */ hcd->driver->disable_usb3_lpm_timeout(hcd, udev, state); - } else { - /* Only a configured device will accept the Set Feature - * U1/U2_ENABLE - */ - if (udev->actconfig) - usb_set_device_initiated_lpm(udev, state, true); + return; + } - /* As soon as usb_set_lpm_timeout(timeout) returns 0, the - * hub-initiated LPM is enabled. Thus, LPM is enabled no - * matter the result of usb_set_device_initiated_lpm(). - * The only difference is whether device is able to initiate - * LPM. - */ + /* Only a configured device will accept the Set Feature + * U1/U2_ENABLE + */ + if (udev->actconfig && + usb_set_device_initiated_lpm(udev, state, true) == 0) { if (state == USB3_LPM_U1) udev->usb3_lpm_u1_enabled = 1; else if (state == USB3_LPM_U2) udev->usb3_lpm_u2_enabled = 1; + } else { + /* Don't request U1/U2 entry if the device + * cannot transition to U1/U2. + */ + usb_set_lpm_timeout(udev, state, 0); + hcd->driver->disable_usb3_lpm_timeout(hcd, udev, state); } } diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index fd2150a8db2e..d2a119bb14d0 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -1167,11 +1167,12 @@ static ssize_t ffs_epfile_write_iter(struct kiocb *kiocb, struct iov_iter *from) ffs_log("enter"); if (!is_sync_kiocb(kiocb)) { - p = kmalloc(sizeof(io_data), GFP_KERNEL); + p = kzalloc(sizeof(io_data), GFP_KERNEL); if (unlikely(!p)) return -ENOMEM; p->aio = true; } else { + memset(p, 0, sizeof(*p)); p->aio = false; } @@ -1208,11 +1209,12 @@ static ssize_t ffs_epfile_read_iter(struct kiocb *kiocb, struct iov_iter *to) ffs_log("enter"); if (!is_sync_kiocb(kiocb)) { - p = kmalloc(sizeof(io_data), GFP_KERNEL); + p = kzalloc(sizeof(io_data), GFP_KERNEL); if (unlikely(!p)) return -ENOMEM; p->aio = true; } else { + memset(p, 0, sizeof(*p)); p->aio = false; } diff --git a/drivers/usb/host/hwa-hc.c b/drivers/usb/host/hwa-hc.c index 97750f162f01..c14e4a64b0e8 100644 --- a/drivers/usb/host/hwa-hc.c +++ b/drivers/usb/host/hwa-hc.c @@ -173,7 +173,7 @@ out: return result; error_set_cluster_id: - wusb_cluster_id_put(wusbhc->cluster_id); + wusb_cluster_id_put(addr); error_cluster_id_get: goto out; diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index 89e9494c3245..3ea435c2d1b7 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -178,7 +178,7 @@ int usb_amd_find_chipset_info(void) { unsigned long flags; struct amd_chipset_info info; - int ret; + int need_pll_quirk = 0; spin_lock_irqsave(&amd_lock, flags); @@ -192,21 +192,28 @@ int usb_amd_find_chipset_info(void) spin_unlock_irqrestore(&amd_lock, flags); if (!amd_chipset_sb_type_init(&info)) { - ret = 0; goto commit; } - /* Below chipset generations needn't enable AMD PLL quirk */ - if (info.sb_type.gen == AMD_CHIPSET_UNKNOWN || - info.sb_type.gen == AMD_CHIPSET_SB600 || - info.sb_type.gen == AMD_CHIPSET_YANGTZE || - (info.sb_type.gen == AMD_CHIPSET_SB700 && - info.sb_type.rev > 0x3b)) { + switch (info.sb_type.gen) { + case AMD_CHIPSET_SB700: + need_pll_quirk = info.sb_type.rev <= 0x3B; + break; + case AMD_CHIPSET_SB800: + case AMD_CHIPSET_HUDSON2: + case AMD_CHIPSET_BOLTON: + need_pll_quirk = 1; + break; + default: + need_pll_quirk = 0; + break; + } + + if (!need_pll_quirk) { if (info.smbus_dev) { pci_dev_put(info.smbus_dev); info.smbus_dev = NULL; } - ret = 0; goto commit; } @@ -225,7 +232,7 @@ int usb_amd_find_chipset_info(void) } } - ret = info.probe_result = 1; + need_pll_quirk = info.probe_result = 1; printk(KERN_DEBUG "QUIRK: Enable AMD PLL fix\n"); commit: @@ -236,7 +243,7 @@ commit: /* Mark that we where here */ amd_chipset.probe_count++; - ret = amd_chipset.probe_result; + need_pll_quirk = amd_chipset.probe_result; spin_unlock_irqrestore(&amd_lock, flags); @@ -250,7 +257,7 @@ commit: spin_unlock_irqrestore(&amd_lock, flags); } - return ret; + return need_pll_quirk; } EXPORT_SYMBOL_GPL(usb_amd_find_chipset_info); diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 53cf130922f3..5c7fe8457574 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -30,7 +30,7 @@ #include "vhost.h" -static int experimental_zcopytx = 1; +static int experimental_zcopytx = 0; module_param(experimental_zcopytx, int, 0444); MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;" " 1 -Enable; 0 - Disable"); diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index e9e04376c52c..e80ad0c7c2a9 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -49,8 +49,9 @@ * @page: structure to page * */ -static int v9fs_fid_readpage(struct p9_fid *fid, struct page *page) +static int v9fs_fid_readpage(void *data, struct page *page) { + struct p9_fid *fid = data; struct inode *inode = page->mapping->host; struct bio_vec bvec = {.bv_page = page, .bv_len = PAGE_SIZE}; struct iov_iter to; @@ -121,7 +122,8 @@ static int v9fs_vfs_readpages(struct file *filp, struct address_space *mapping, if (ret == 0) return ret; - ret = read_cache_pages(mapping, pages, (void *)v9fs_vfs_readpage, filp); + ret = read_cache_pages(mapping, pages, v9fs_fid_readpage, + filp->private_data); p9_debug(P9_DEBUG_VFS, " = %d\n", ret); return ret; } diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index e7b54514d99a..e137ff6cd9da 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1072,20 +1072,23 @@ static int send_cap_msg(struct ceph_mds_session *session, } /* - * Queue cap releases when an inode is dropped from our cache. Since - * inode is about to be destroyed, there is no need for i_ceph_lock. + * Queue cap releases when an inode is dropped from our cache. */ void ceph_queue_caps_release(struct inode *inode) { struct ceph_inode_info *ci = ceph_inode(inode); struct rb_node *p; + /* lock i_ceph_lock, because ceph_d_revalidate(..., LOOKUP_RCU) + * may call __ceph_caps_issued_mask() on a freeing inode. */ + spin_lock(&ci->i_ceph_lock); p = rb_first(&ci->i_caps); while (p) { struct ceph_cap *cap = rb_entry(p, struct ceph_cap, ci_node); p = rb_next(p); __ceph_remove_cap(cap, true); } + spin_unlock(&ci->i_ceph_lock); } /* diff --git a/fs/coda/file.c b/fs/coda/file.c index 1da3805f3ddc..cbbd76f4098e 100644 --- a/fs/coda/file.c +++ b/fs/coda/file.c @@ -81,6 +81,41 @@ coda_file_write_iter(struct kiocb *iocb, struct iov_iter *to) return ret; } +struct coda_vm_ops { + atomic_t refcnt; + struct file *coda_file; + const struct vm_operations_struct *host_vm_ops; + struct vm_operations_struct vm_ops; +}; + +static void +coda_vm_open(struct vm_area_struct *vma) +{ + struct coda_vm_ops *cvm_ops = + container_of(vma->vm_ops, struct coda_vm_ops, vm_ops); + + atomic_inc(&cvm_ops->refcnt); + + if (cvm_ops->host_vm_ops && cvm_ops->host_vm_ops->open) + cvm_ops->host_vm_ops->open(vma); +} + +static void +coda_vm_close(struct vm_area_struct *vma) +{ + struct coda_vm_ops *cvm_ops = + container_of(vma->vm_ops, struct coda_vm_ops, vm_ops); + + if (cvm_ops->host_vm_ops && cvm_ops->host_vm_ops->close) + cvm_ops->host_vm_ops->close(vma); + + if (atomic_dec_and_test(&cvm_ops->refcnt)) { + vma->vm_ops = cvm_ops->host_vm_ops; + fput(cvm_ops->coda_file); + kfree(cvm_ops); + } +} + static int coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma) { @@ -88,6 +123,8 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma) struct coda_inode_info *cii; struct file *host_file; struct inode *coda_inode, *host_inode; + struct coda_vm_ops *cvm_ops; + int ret; cfi = CODA_FTOC(coda_file); BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC); @@ -96,6 +133,13 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma) if (!host_file->f_op->mmap) return -ENODEV; + if (WARN_ON(coda_file != vma->vm_file)) + return -EIO; + + cvm_ops = kmalloc(sizeof(struct coda_vm_ops), GFP_KERNEL); + if (!cvm_ops) + return -ENOMEM; + coda_inode = file_inode(coda_file); host_inode = file_inode(host_file); @@ -109,6 +153,7 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma) * the container file on us! */ else if (coda_inode->i_mapping != host_inode->i_mapping) { spin_unlock(&cii->c_lock); + kfree(cvm_ops); return -EBUSY; } @@ -117,7 +162,29 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma) cfi->cfi_mapcount++; spin_unlock(&cii->c_lock); - return host_file->f_op->mmap(host_file, vma); + vma->vm_file = get_file(host_file); + ret = host_file->f_op->mmap(host_file, vma); + + if (ret) { + /* if call_mmap fails, our caller will put coda_file so we + * should drop the reference to the host_file that we got. + */ + fput(host_file); + kfree(cvm_ops); + } else { + /* here we add redirects for the open/close vm_operations */ + cvm_ops->host_vm_ops = vma->vm_ops; + if (vma->vm_ops) + cvm_ops->vm_ops = *vma->vm_ops; + + cvm_ops->vm_ops.open = coda_vm_open; + cvm_ops->vm_ops.close = coda_vm_close; + cvm_ops->coda_file = coda_file; + atomic_set(&cvm_ops->refcnt, 1); + + vma->vm_ops = &cvm_ops->vm_ops; + } + return ret; } int coda_open(struct inode *coda_inode, struct file *coda_file) diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index cf0186fd9bfe..27d1db57f578 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -1171,8 +1171,10 @@ int ecryptfs_read_and_validate_header_region(struct inode *inode) lower_file->f_ra.ra_pages = ra_pages_org; /* restore read a head mechanism */ - if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES) - return rc >= 0 ? -EINVAL : rc; + if (rc < 0) + return rc; + else if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES) + return -EINVAL; rc = ecryptfs_validate_marker(marker); if (!rc) ecryptfs_i_size_init(file_size, inode); @@ -1530,8 +1532,10 @@ int ecryptfs_read_and_validate_xattr_region(struct dentry *dentry, rc = ecryptfs_getxattr_lower(ecryptfs_dentry_to_lower(dentry), ECRYPTFS_XATTR_NAME, file_size, ECRYPTFS_SIZE_AND_MARKER_BYTES); - if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES) - return rc >= 0 ? -EINVAL : rc; + if (rc < 0) + return rc; + else if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES) + return -EINVAL; rc = ecryptfs_validate_marker(marker); if (!rc) ecryptfs_i_size_init(file_size, inode); diff --git a/fs/exec.c b/fs/exec.c index ab6e34e1de21..eba40240c0c5 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1644,7 +1644,7 @@ static int do_execveat_common(int fd, struct filename *filename, current->fs->in_exec = 0; current->in_execve = 0; acct_update_integrals(current); - task_numa_free(current); + task_numa_free(current, false); free_bprm(bprm); kfree(pathbuf); putname(filename); diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index b3cd53acbcd4..1e27252368c8 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -146,8 +146,8 @@ static bool __is_bitmap_valid(struct f2fs_sb_info *sbi, block_t blkaddr, exist = f2fs_test_bit(offset, se->cur_valid_map); if (!exist && type == DATA_GENERIC_ENHANCE) { - f2fs_msg(sbi->sb, KERN_ERR, "Inconsistent error " - "blkaddr:%u, sit bitmap:%d", blkaddr, exist); + f2fs_err(sbi, "Inconsistent error blkaddr:%u, sit bitmap:%d", + blkaddr, exist); set_sbi_flag(sbi, SBI_NEED_FSCK); WARN_ON(1); } @@ -184,8 +184,8 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, case DATA_GENERIC_ENHANCE_READ: if (unlikely(blkaddr >= MAX_BLKADDR(sbi) || blkaddr < MAIN_BLKADDR(sbi))) { - f2fs_msg(sbi->sb, KERN_WARNING, - "access invalid blkaddr:%u", blkaddr); + f2fs_warn(sbi, "access invalid blkaddr:%u", + blkaddr); set_sbi_flag(sbi, SBI_NEED_FSCK); WARN_ON(1); return false; @@ -658,9 +658,8 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) err_out: set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_msg(sbi->sb, KERN_WARNING, - "%s: orphan failed (ino=%x), run fsck to fix.", - __func__, ino); + f2fs_warn(sbi, "%s: orphan failed (ino=%x), run fsck to fix.", + __func__, ino); return err; } @@ -677,13 +676,12 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi) return 0; if (bdev_read_only(sbi->sb->s_bdev)) { - f2fs_msg(sbi->sb, KERN_INFO, "write access " - "unavailable, skipping orphan cleanup"); + f2fs_info(sbi, "write access unavailable, skipping orphan cleanup"); return 0; } if (s_flags & MS_RDONLY) { - f2fs_msg(sbi->sb, KERN_INFO, "orphan cleanup on readonly fs"); + f2fs_info(sbi, "orphan cleanup on readonly fs"); sbi->sb->s_flags &= ~MS_RDONLY; } @@ -828,26 +826,14 @@ static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr, if (crc_offset < CP_MIN_CHKSUM_OFFSET || crc_offset > CP_CHKSUM_OFFSET) { f2fs_put_page(*cp_page, 1); - f2fs_msg(sbi->sb, KERN_WARNING, - "invalid crc_offset: %zu", crc_offset); + f2fs_warn(sbi, "invalid crc_offset: %zu", crc_offset); return -EINVAL; } - if (__is_set_ckpt_flags(*cp_block, CP_LARGE_NAT_BITMAP_FLAG)) { - if (crc_offset != CP_MIN_CHKSUM_OFFSET) { - f2fs_put_page(*cp_page, 1); - f2fs_msg(sbi->sb, KERN_WARNING, - "layout of large_nat_bitmap is deprecated, " - "run fsck to repair, chksum_offset: %zu", - crc_offset); - return -EINVAL; - } - } - crc = f2fs_checkpoint_chksum(sbi, *cp_block); if (crc != cur_cp_crc(*cp_block)) { f2fs_put_page(*cp_page, 1); - f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value"); + f2fs_warn(sbi, "invalid crc value"); return -EINVAL; } @@ -870,9 +856,8 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi, if (le32_to_cpu(cp_block->cp_pack_total_block_count) > sbi->blocks_per_seg) { - f2fs_msg(sbi->sb, KERN_WARNING, - "invalid cp_pack_total_block_count:%u", - le32_to_cpu(cp_block->cp_pack_total_block_count)); + f2fs_warn(sbi, "invalid cp_pack_total_block_count:%u", + le32_to_cpu(cp_block->cp_pack_total_block_count)); goto invalid_cp; } pre_version = *version; @@ -906,6 +891,7 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi) unsigned int cp_blks = 1 + __cp_payload(sbi); block_t cp_blk_no; int i; + int err; sbi->ckpt = f2fs_kzalloc(sbi, array_size(blk_size, cp_blks), GFP_KERNEL); @@ -933,6 +919,7 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi) } else if (cp2) { cur_page = cp2; } else { + err = -EFSCORRUPTED; goto fail_no_cp; } @@ -945,8 +932,10 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi) sbi->cur_cp_pack = 2; /* Sanity checking of checkpoint */ - if (f2fs_sanity_check_ckpt(sbi)) + if (f2fs_sanity_check_ckpt(sbi)) { + err = -EFSCORRUPTED; goto free_fail_no_cp; + } if (cp_blks <= 1) goto done; @@ -960,8 +949,10 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi) unsigned char *ckpt = (unsigned char *)sbi->ckpt; cur_page = f2fs_get_meta_page(sbi, cp_blk_no + i); - if (IS_ERR(cur_page)) + if (IS_ERR(cur_page)) { + err = PTR_ERR(cur_page); goto free_fail_no_cp; + } sit_bitmap_ptr = page_address(cur_page); memcpy(ckpt + i * blk_size, sit_bitmap_ptr, blk_size); f2fs_put_page(cur_page, 1); @@ -976,7 +967,7 @@ free_fail_no_cp: f2fs_put_page(cp2, 1); fail_no_cp: kvfree(sbi->ckpt); - return -EINVAL; + return err; } static void __add_dirty_inode(struct inode *inode, enum inode_type type) @@ -1143,17 +1134,24 @@ static void __prepare_cp_block(struct f2fs_sb_info *sbi) static bool __need_flush_quota(struct f2fs_sb_info *sbi) { + bool ret = false; + if (!is_journalled_quota(sbi)) return false; - if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH)) - return false; - if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR)) - return false; - if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_FLUSH)) - return true; - if (get_pages(sbi, F2FS_DIRTY_QDATA)) - return true; - return false; + + down_write(&sbi->quota_sem); + if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH)) { + ret = false; + } else if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR)) { + ret = false; + } else if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_FLUSH)) { + clear_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH); + ret = true; + } else if (get_pages(sbi, F2FS_DIRTY_QDATA)) { + ret = true; + } + up_write(&sbi->quota_sem); + return ret; } /* @@ -1172,26 +1170,22 @@ static int block_operations(struct f2fs_sb_info *sbi) blk_start_plug(&plug); retry_flush_quotas: + f2fs_lock_all(sbi); if (__need_flush_quota(sbi)) { int locked; if (++cnt > DEFAULT_RETRY_QUOTA_FLUSH_COUNT) { set_sbi_flag(sbi, SBI_QUOTA_SKIP_FLUSH); - f2fs_lock_all(sbi); + set_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH); goto retry_flush_dents; } - clear_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH); + f2fs_unlock_all(sbi); /* only failed during mount/umount/freeze/quotactl */ locked = down_read_trylock(&sbi->sb->s_umount); f2fs_quota_sync(sbi->sb, -1); if (locked) up_read(&sbi->sb->s_umount); - } - - f2fs_lock_all(sbi); - if (__need_flush_quota(sbi)) { - f2fs_unlock_all(sbi); cond_resched(); goto retry_flush_quotas; } @@ -1213,12 +1207,6 @@ retry_flush_dents: */ down_write(&sbi->node_change); - if (__need_flush_quota(sbi)) { - up_write(&sbi->node_change); - f2fs_unlock_all(sbi); - goto retry_flush_quotas; - } - if (get_pages(sbi, F2FS_DIRTY_IMETA)) { up_write(&sbi->node_change); f2fs_unlock_all(sbi); @@ -1314,7 +1302,8 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc) else __clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG); - if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) + if (is_sbi_flag_set(sbi, SBI_NEED_FSCK) || + is_sbi_flag_set(sbi, SBI_IS_RESIZEFS)) __set_ckpt_flags(ckpt, CP_FSCK_FLAG); if (is_sbi_flag_set(sbi, SBI_CP_DISABLED)) @@ -1570,8 +1559,7 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { if (cpc->reason != CP_PAUSE) return 0; - f2fs_msg(sbi->sb, KERN_WARNING, - "Start checkpoint disabled!"); + f2fs_warn(sbi, "Start checkpoint disabled!"); } mutex_lock(&sbi->cp_mutex); @@ -1637,8 +1625,7 @@ stop: stat_inc_cp_count(sbi->stat_info); if (cpc->reason & CP_RECOVERY) - f2fs_msg(sbi->sb, KERN_NOTICE, - "checkpoint: version = %llx", ckpt_ver); + f2fs_notice(sbi, "checkpoint: version = %llx", ckpt_ver); /* do checkpoint periodically */ f2fs_update_time(sbi, CP_TIME); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 380d5b5eec41..568aabab15a4 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -14,6 +14,7 @@ #include <linux/pagevec.h> #include <linux/blkdev.h> #include <linux/bio.h> +#include <linux/swap.h> #include <linux/prefetch.h> #include <linux/uio.h> #include <linux/cleancache.h> @@ -54,7 +55,7 @@ static bool __is_cp_guaranteed(struct page *page) static enum count_type __read_io_type(struct page *page) { - struct address_space *mapping = page->mapping; + struct address_space *mapping = page_file_mapping(page); if (mapping) { struct inode *inode = mapping->host; @@ -380,20 +381,20 @@ static void __submit_merged_bio(struct f2fs_bio_info *io) io->bio = NULL; } -static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode, +static bool __has_merged_page(struct bio *bio, struct inode *inode, struct page *page, nid_t ino) { struct bio_vec *bvec; struct page *target; int i; - if (!io->bio) + if (!bio) return false; if (!inode && !page && !ino) return true; - bio_for_each_segment_all(bvec, io->bio, i) { + bio_for_each_segment_all(bvec, bio, i) { if (bvec->bv_page->mapping) target = bvec->bv_page; @@ -444,7 +445,7 @@ static void __submit_merged_write_cond(struct f2fs_sb_info *sbi, struct f2fs_bio_info *io = sbi->write_io[btype] + temp; down_read(&io->io_rwsem); - ret = __has_merged_page(io, inode, page, ino); + ret = __has_merged_page(io->bio, inode, page, ino); up_read(&io->io_rwsem); } if (ret) @@ -488,7 +489,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr, fio->is_por ? META_POR : (__is_meta_io(fio) ? META_GENERIC : DATA_GENERIC_ENHANCE))) - return -EFAULT; + return -EFSCORRUPTED; trace_f2fs_submit_page_bio(page, fio); f2fs_trace_ios(fio, 0); @@ -514,6 +515,61 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) return 0; } +int f2fs_merge_page_bio(struct f2fs_io_info *fio) +{ + struct bio *bio = *fio->bio; + struct page *page = fio->encrypted_page ? + fio->encrypted_page : fio->page; + + if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr, + __is_meta_io(fio) ? META_GENERIC : DATA_GENERIC)) + return -EFSCORRUPTED; + + trace_f2fs_submit_page_bio(page, fio); + f2fs_trace_ios(fio, 0); + + if (bio && (*fio->last_block + 1 != fio->new_blkaddr || + !__same_bdev(fio->sbi, fio->new_blkaddr, bio))) { + __submit_bio(fio->sbi, bio, fio->type); + bio = NULL; + } +alloc_new: + if (!bio) { + bio = __bio_alloc(fio->sbi, fio->new_blkaddr, fio->io_wbc, + BIO_MAX_PAGES, false, fio->type, fio->temp); + bio_set_op_attrs(bio, fio->op, fio->op_flags); + } + + if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { + __submit_bio(fio->sbi, bio, fio->type); + bio = NULL; + goto alloc_new; + } + + if (fio->io_wbc) + wbc_account_io(fio->io_wbc, page, PAGE_SIZE); + + inc_page_count(fio->sbi, WB_DATA_TYPE(page)); + + *fio->last_block = fio->new_blkaddr; + *fio->bio = bio; + + return 0; +} + +static void f2fs_submit_ipu_bio(struct f2fs_sb_info *sbi, struct bio **bio, + struct page *page) +{ + if (!bio) + return; + + if (!__has_merged_page(*bio, NULL, page, 0)) + return; + + __submit_bio(sbi, *bio, DATA); + *bio = NULL; +} + void f2fs_submit_page_write(struct f2fs_io_info *fio) { struct f2fs_sb_info *sbi = fio->sbi; @@ -767,7 +823,7 @@ struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index, dn.data_blkaddr = ei.blk + index - ei.fofs; if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), dn.data_blkaddr, DATA_GENERIC_ENHANCE_READ)) { - err = -EFAULT; + err = -EFSCORRUPTED; goto put_err; } goto got_it; @@ -787,7 +843,7 @@ struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index, !f2fs_is_valid_blkaddr(F2FS_I_SB(inode), dn.data_blkaddr, DATA_GENERIC_ENHANCE)) { - err = -EFAULT; + err = -EFSCORRUPTED; goto put_err; } got_it: @@ -1133,7 +1189,7 @@ next_block: if (__is_valid_data_blkaddr(blkaddr) && !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) { - err = -EFAULT; + err = -EFSCORRUPTED; goto sync_out; } @@ -1563,7 +1619,7 @@ static int f2fs_read_single_page(struct inode *inode, struct page *page, sector_t block_nr; int ret = 0; - block_in_file = (sector_t)page->index; + block_in_file = (sector_t)page_index(page); last_block = block_in_file + nr_pages; last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits; @@ -1596,14 +1652,15 @@ got_it: block_nr = map->m_pblk + block_in_file - map->m_lblk; SetPageMappedToDisk(page); - if (!PageUptodate(page) && !cleancache_get_page(page)) { + if (!PageUptodate(page) && (!PageSwapCache(page) && + !cleancache_get_page(page))) { SetPageUptodate(page); goto confused; } if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr, DATA_GENERIC_ENHANCE_READ)) { - ret = -EFAULT; + ret = -EFSCORRUPTED; goto out; } } else { @@ -1694,7 +1751,7 @@ static int f2fs_mpage_readpages(struct address_space *mapping, prefetchw(&page->flags); list_del(&page->lru); if (add_to_page_cache_lru(page, mapping, - page->index, GFP_KERNEL)) + page_index(page), GFP_KERNEL)) goto next_page; } @@ -1717,7 +1774,7 @@ next_page: static int f2fs_read_data_page(struct file *file, struct page *page) { - struct inode *inode = page->mapping->host; + struct inode *inode = page_file_mapping(page)->host; int ret = -EAGAIN; trace_f2fs_readpage(page, DATA); @@ -1726,7 +1783,8 @@ static int f2fs_read_data_page(struct file *file, struct page *page) if (f2fs_has_inline_data(inode)) ret = f2fs_read_inline_data(inode, page); if (ret == -EAGAIN) - ret = f2fs_mpage_readpages(page->mapping, NULL, page, 1, false); + ret = f2fs_mpage_readpages(page_file_mapping(page), + NULL, page, 1, false); return ret; } @@ -1883,7 +1941,7 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio) if (!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr, DATA_GENERIC_ENHANCE)) - return -EFAULT; + return -EFSCORRUPTED; ipu_force = true; fio->need_lock = LOCK_DONE; @@ -1910,7 +1968,7 @@ got_it: if (__is_valid_data_blkaddr(fio->old_blkaddr) && !f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr, DATA_GENERIC_ENHANCE)) { - err = -EFAULT; + err = -EFSCORRUPTED; goto out_writepage; } /* @@ -1979,6 +2037,8 @@ out: } static int __write_data_page(struct page *page, bool *submitted, + struct bio **bio, + sector_t *last_block, struct writeback_control *wbc, enum iostat_type io_type) { @@ -2004,6 +2064,8 @@ static int __write_data_page(struct page *page, bool *submitted, .need_lock = LOCK_RETRY, .io_type = io_type, .io_wbc = wbc, + .bio = bio, + .last_block = last_block, }; trace_f2fs_writepage(page, DATA); @@ -2102,10 +2164,13 @@ out: unlock_page(page); if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode) && - !F2FS_I(inode)->cp_task) + !F2FS_I(inode)->cp_task) { + f2fs_submit_ipu_bio(sbi, bio, page); f2fs_balance_fs(sbi, need_balance_fs); + } if (unlikely(f2fs_cp_error(sbi))) { + f2fs_submit_ipu_bio(sbi, bio, page); f2fs_submit_merged_write(sbi, DATA); submitted = NULL; } @@ -2132,7 +2197,7 @@ redirty_out: static int f2fs_write_data_page(struct page *page, struct writeback_control *wbc) { - return __write_data_page(page, NULL, wbc, FS_DATA_IO); + return __write_data_page(page, NULL, NULL, NULL, wbc, FS_DATA_IO); } /* @@ -2148,6 +2213,8 @@ static int f2fs_write_cache_pages(struct address_space *mapping, int done = 0; struct pagevec pvec; struct f2fs_sb_info *sbi = F2FS_M_SB(mapping); + struct bio *bio = NULL; + sector_t last_block; int nr_pages; pgoff_t uninitialized_var(writeback_index); pgoff_t index; @@ -2224,17 +2291,20 @@ continue_unlock: } if (PageWriteback(page)) { - if (wbc->sync_mode != WB_SYNC_NONE) + if (wbc->sync_mode != WB_SYNC_NONE) { f2fs_wait_on_page_writeback(page, DATA, true, true); - else + f2fs_submit_ipu_bio(sbi, &bio, page); + } else { goto continue_unlock; + } } if (!clear_page_dirty_for_io(page)) goto continue_unlock; - ret = __write_data_page(page, &submitted, wbc, io_type); + ret = __write_data_page(page, &submitted, &bio, + &last_block, wbc, io_type); if (unlikely(ret)) { /* * keep nr_to_write, since vfs uses this to @@ -2283,6 +2353,9 @@ continue_unlock: if (nwritten) f2fs_submit_merged_write_cond(F2FS_M_SB(mapping), mapping->host, NULL, 0, DATA); + /* submit cached bio of IPU write */ + if (bio) + __submit_bio(sbi, bio, DATA); return ret; } @@ -2294,6 +2367,9 @@ static inline bool __should_serialize_io(struct inode *inode, return false; if (IS_NOQUOTA(inode)) return false; + /* to avoid deadlock in path of data flush */ + if (F2FS_I(inode)->cp_task) + return false; if (wbc->sync_mode != WB_SYNC_ALL) return true; if (get_dirty_pages(inode) >= SM_I(F2FS_I_SB(inode))->min_seq_blocks) @@ -2575,7 +2651,7 @@ repeat: } else { if (!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE_READ)) { - err = -EFAULT; + err = -EFSCORRUPTED; goto fail; } err = f2fs_submit_page_read(inode, page, blkaddr); @@ -2851,13 +2927,14 @@ int f2fs_release_page(struct page *page, gfp_t wait) static int f2fs_set_data_page_dirty(struct page *page) { - struct address_space *mapping = page->mapping; - struct inode *inode = mapping->host; + struct inode *inode = page_file_mapping(page)->host; trace_f2fs_set_page_dirty(page, DATA); if (!PageUptodate(page)) SetPageUptodate(page); + if (PageSwapCache(page)) + return __set_page_dirty_nobuffers(page); if (f2fs_is_atomic_file(inode) && !f2fs_is_commit_atomic_write(inode)) { if (!IS_ATOMIC_WRITTEN_PAGE(page)) { @@ -2946,6 +3023,126 @@ int f2fs_migrate_page(struct address_space *mapping, } #endif +#ifdef CONFIG_SWAP +/* Copied from generic_swapfile_activate() to check any holes */ +static int check_swap_activate(struct file *swap_file, unsigned int max) +{ + struct address_space *mapping = swap_file->f_mapping; + struct inode *inode = mapping->host; + unsigned blocks_per_page; + unsigned long page_no; + unsigned blkbits; + sector_t probe_block; + sector_t last_block; + sector_t lowest_block = -1; + sector_t highest_block = 0; + + blkbits = inode->i_blkbits; + blocks_per_page = PAGE_SIZE >> blkbits; + + /* + * Map all the blocks into the extent list. This code doesn't try + * to be very smart. + */ + probe_block = 0; + page_no = 0; + last_block = i_size_read(inode) >> blkbits; + while ((probe_block + blocks_per_page) <= last_block && page_no < max) { + unsigned block_in_page; + sector_t first_block; + + cond_resched(); + + first_block = bmap(inode, probe_block); + if (first_block == 0) + goto bad_bmap; + + /* + * It must be PAGE_SIZE aligned on-disk + */ + if (first_block & (blocks_per_page - 1)) { + probe_block++; + goto reprobe; + } + + for (block_in_page = 1; block_in_page < blocks_per_page; + block_in_page++) { + sector_t block; + + block = bmap(inode, probe_block + block_in_page); + if (block == 0) + goto bad_bmap; + if (block != first_block + block_in_page) { + /* Discontiguity */ + probe_block++; + goto reprobe; + } + } + + first_block >>= (PAGE_SHIFT - blkbits); + if (page_no) { /* exclude the header page */ + if (first_block < lowest_block) + lowest_block = first_block; + if (first_block > highest_block) + highest_block = first_block; + } + + page_no++; + probe_block += blocks_per_page; +reprobe: + continue; + } + return 0; + +bad_bmap: + pr_err("swapon: swapfile has holes\n"); + return -EINVAL; +} + +static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file, + sector_t *span) +{ + struct inode *inode = file_inode(file); + int ret; + + if (!S_ISREG(inode->i_mode)) + return -EINVAL; + + if (f2fs_readonly(F2FS_I_SB(inode)->sb)) + return -EROFS; + + ret = f2fs_convert_inline_inode(inode); + if (ret) + return ret; + + ret = check_swap_activate(file, sis->max); + if (ret) + return ret; + + set_inode_flag(inode, FI_PIN_FILE); + f2fs_precache_extents(inode); + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); + return 0; +} + +static void f2fs_swap_deactivate(struct file *file) +{ + struct inode *inode = file_inode(file); + + clear_inode_flag(inode, FI_PIN_FILE); +} +#else +static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file, + sector_t *span) +{ + return -EOPNOTSUPP; +} + +static void f2fs_swap_deactivate(struct file *file) +{ +} +#endif + const struct address_space_operations f2fs_dblock_aops = { .readpage = f2fs_read_data_page, .readpages = f2fs_read_data_pages, @@ -2958,6 +3155,8 @@ const struct address_space_operations f2fs_dblock_aops = { .releasepage = f2fs_release_page, .direct_IO = f2fs_direct_IO, .bmap = f2fs_bmap, + .swap_activate = f2fs_swap_activate, + .swap_deactivate = f2fs_swap_deactivate, #ifdef CONFIG_MIGRATION .migratepage = f2fs_migrate_page, #endif diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index d00ba9b711a4..9cadcf9f1ecf 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -27,8 +27,15 @@ static DEFINE_MUTEX(f2fs_stat_mutex); static void update_general_status(struct f2fs_sb_info *sbi) { struct f2fs_stat_info *si = F2FS_STAT(sbi); + struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); int i; + /* these will be changed if online resize is done */ + si->main_area_segs = le32_to_cpu(raw_super->segment_count_main); + si->main_area_sections = le32_to_cpu(raw_super->section_count); + si->main_area_zones = si->main_area_sections / + le32_to_cpu(raw_super->secs_per_zone); + /* validation check of the segment numbers */ si->hit_largest = atomic64_read(&sbi->read_hit_largest); si->hit_cached = atomic64_read(&sbi->read_hit_cached); diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 988af0b594a7..d01f376291a3 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -218,9 +218,8 @@ struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir, max_depth = F2FS_I(dir)->i_current_depth; if (unlikely(max_depth > MAX_DIR_HASH_DEPTH)) { - f2fs_msg(F2FS_I_SB(dir)->sb, KERN_WARNING, - "Corrupted max_depth of %lu: %u", - dir->i_ino, max_depth); + f2fs_warn(F2FS_I_SB(dir), "Corrupted max_depth of %lu: %u", + dir->i_ino, max_depth); max_depth = MAX_DIR_HASH_DEPTH; f2fs_i_depth_write(dir, max_depth); } @@ -816,11 +815,10 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len)); if (unlikely(bit_pos > d->max || le16_to_cpu(de->name_len) > F2FS_NAME_LEN)) { - f2fs_msg(sbi->sb, KERN_WARNING, - "%s: corrupted namelen=%d, run fsck to fix.", - __func__, le16_to_cpu(de->name_len)); + f2fs_warn(sbi, "%s: corrupted namelen=%d, run fsck to fix.", + __func__, le16_to_cpu(de->name_len)); set_sbi_flag(sbi, SBI_NEED_FSCK); - err = -EINVAL; + err = -EFSCORRUPTED; goto out; } @@ -828,8 +826,8 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, int save_len = fstr->len; err = fscrypt_fname_disk_to_usr(d->inode, - (u32)de->hash_code, 0, - &de_name, fstr); + (u32)le32_to_cpu(de->hash_code), + 0, &de_name, fstr); if (err) goto out; diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index 904ad7ba5a45..a77022601bed 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -175,10 +175,9 @@ bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi, next_re = rb_entry(next, struct rb_entry, rb_node); if (cur_re->ofs + cur_re->len > next_re->ofs) { - f2fs_msg(sbi->sb, KERN_INFO, "inconsistent rbtree, " - "cur(%u, %u) next(%u, %u)", - cur_re->ofs, cur_re->len, - next_re->ofs, next_re->len); + f2fs_info(sbi, "inconsistent rbtree, cur(%u, %u) next(%u, %u)", + cur_re->ofs, cur_re->len, + next_re->ofs, next_re->len); return false; } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index b70d99f6ff18..ae98cdf21f55 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -139,6 +139,9 @@ struct f2fs_mount_info { int alloc_mode; /* segment allocation policy */ int fsync_mode; /* fsync policy */ bool test_dummy_encryption; /* test dummy encryption */ + block_t unusable_cap; /* Amount of space allowed to be + * unusable when disabling checkpoint + */ }; #define F2FS_FEATURE_ENCRYPT 0x0001 @@ -476,6 +479,7 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal, #define F2FS_IOC_SET_PIN_FILE _IOW(F2FS_IOCTL_MAGIC, 13, __u32) #define F2FS_IOC_GET_PIN_FILE _IOR(F2FS_IOCTL_MAGIC, 14, __u32) #define F2FS_IOC_PRECACHE_EXTENTS _IO(F2FS_IOCTL_MAGIC, 15) +#define F2FS_IOC_RESIZE_FS _IOW(F2FS_IOCTL_MAGIC, 16, __u64) #define F2FS_IOC_SET_ENCRYPTION_POLICY FS_IOC_SET_ENCRYPTION_POLICY #define F2FS_IOC_GET_ENCRYPTION_POLICY FS_IOC_GET_ENCRYPTION_POLICY @@ -537,8 +541,8 @@ static inline int get_inline_xattr_addrs(struct inode *inode); #define NR_INLINE_DENTRY(inode) (MAX_INLINE_DATA(inode) * BITS_PER_BYTE / \ ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \ BITS_PER_BYTE + 1)) -#define INLINE_DENTRY_BITMAP_SIZE(inode) ((NR_INLINE_DENTRY(inode) + \ - BITS_PER_BYTE - 1) / BITS_PER_BYTE) +#define INLINE_DENTRY_BITMAP_SIZE(inode) \ + DIV_ROUND_UP(NR_INLINE_DENTRY(inode), BITS_PER_BYTE) #define INLINE_RESERVED_SIZE(inode) (MAX_INLINE_DATA(inode) - \ ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \ NR_INLINE_DENTRY(inode) + \ @@ -1113,6 +1117,8 @@ struct f2fs_io_info { bool retry; /* need to reallocate block address */ enum iostat_type io_type; /* io type */ struct writeback_control *io_wbc; /* writeback control */ + struct bio **bio; /* bio for ipu */ + sector_t *last_block; /* last block number in bio */ unsigned char version; /* version of the node */ }; @@ -1172,6 +1178,7 @@ enum { SBI_QUOTA_NEED_FLUSH, /* need to flush quota info in CP */ SBI_QUOTA_SKIP_FLUSH, /* skip flushing quota in current CP */ SBI_QUOTA_NEED_REPAIR, /* quota file may be corrupted */ + SBI_IS_RESIZEFS, /* resizefs is in process */ }; enum { @@ -1268,6 +1275,7 @@ struct f2fs_sb_info { /* for inode management */ struct list_head inode_list[NR_INODE_TYPE]; /* dirty inode list */ spinlock_t inode_lock[NR_INODE_TYPE]; /* for dirty inode list lock */ + struct mutex flush_lock; /* for flush exclusion */ /* for extent tree cache */ struct radix_tree_root extent_tree_root;/* cache extent cache entries */ @@ -1291,6 +1299,7 @@ struct f2fs_sb_info { unsigned int segs_per_sec; /* segments per section */ unsigned int secs_per_zone; /* sections per zone */ unsigned int total_sections; /* total section count */ + struct mutex resize_mutex; /* for resize exclusion */ unsigned int total_node_count; /* total node block count */ unsigned int total_valid_node_count; /* valid node block count */ loff_t max_file_blocks; /* max block index of file */ @@ -1308,6 +1317,7 @@ struct f2fs_sb_info { block_t unusable_block_count; /* # of blocks saved by last cp */ unsigned int nquota_files; /* # of quota sysfile */ + struct rw_semaphore quota_sem; /* blocking cp for flags */ /* # of pages, see count_type */ atomic_t nr_pages[NR_COUNT_TYPE]; @@ -1550,7 +1560,7 @@ static inline struct f2fs_sb_info *F2FS_M_SB(struct address_space *mapping) static inline struct f2fs_sb_info *F2FS_P_SB(struct page *page) { - return F2FS_M_SB(page->mapping); + return F2FS_M_SB(page_file_mapping(page)); } static inline struct f2fs_super_block *F2FS_RAW_SUPER(struct f2fs_sb_info *sbi) @@ -1828,8 +1838,12 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, if (!__allow_reserved_blocks(sbi, inode, true)) avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks; - if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) - avail_user_block_count -= sbi->unusable_block_count; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + if (avail_user_block_count > sbi->unusable_block_count) + avail_user_block_count -= sbi->unusable_block_count; + else + avail_user_block_count = 0; + } if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) { diff = sbi->total_valid_block_count - avail_user_block_count; if (diff > *count) @@ -1857,7 +1871,20 @@ enospc: return -ENOSPC; } -void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...); +__printf(2, 3) +void f2fs_printk(struct f2fs_sb_info *sbi, const char *fmt, ...); + +#define f2fs_err(sbi, fmt, ...) \ + f2fs_printk(sbi, KERN_ERR fmt, ##__VA_ARGS__) +#define f2fs_warn(sbi, fmt, ...) \ + f2fs_printk(sbi, KERN_WARNING fmt, ##__VA_ARGS__) +#define f2fs_notice(sbi, fmt, ...) \ + f2fs_printk(sbi, KERN_NOTICE fmt, ##__VA_ARGS__) +#define f2fs_info(sbi, fmt, ...) \ + f2fs_printk(sbi, KERN_INFO fmt, ##__VA_ARGS__) +#define f2fs_debug(sbi, fmt, ...) \ + f2fs_printk(sbi, KERN_DEBUG fmt, ##__VA_ARGS__) + static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, struct inode *inode, block_t count) @@ -1873,11 +1900,10 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, sbi->current_reserved_blocks + count); spin_unlock(&sbi->stat_lock); if (unlikely(inode->i_blocks < sectors)) { - f2fs_msg(sbi->sb, KERN_WARNING, - "Inconsistent i_blocks, ino:%lu, iblocks:%llu, sectors:%llu", - inode->i_ino, - (unsigned long long)inode->i_blocks, - (unsigned long long)sectors); + f2fs_warn(sbi, "Inconsistent i_blocks, ino:%lu, iblocks:%llu, sectors:%llu", + inode->i_ino, + (unsigned long long)inode->i_blocks, + (unsigned long long)sectors); set_sbi_flag(sbi, SBI_NEED_FSCK); return; } @@ -2029,7 +2055,7 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, struct inode *inode, bool is_inode) { block_t valid_block_count; - unsigned int valid_node_count; + unsigned int valid_node_count, user_block_count; int err; if (is_inode) { @@ -2056,10 +2082,11 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, if (!__allow_reserved_blocks(sbi, inode, false)) valid_block_count += F2FS_OPTION(sbi).root_reserved_blocks; + user_block_count = sbi->user_block_count; if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) - valid_block_count += sbi->unusable_block_count; + user_block_count -= sbi->unusable_block_count; - if (unlikely(valid_block_count > sbi->user_block_count)) { + if (unlikely(valid_block_count > user_block_count)) { spin_unlock(&sbi->stat_lock); goto enospc; } @@ -2114,10 +2141,9 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi, dquot_free_inode(inode); } else { if (unlikely(inode->i_blocks == 0)) { - f2fs_msg(sbi->sb, KERN_WARNING, - "Inconsistent i_blocks, ino:%lu, iblocks:%llu", - inode->i_ino, - (unsigned long long)inode->i_blocks); + f2fs_warn(sbi, "Inconsistent i_blocks, ino:%lu, iblocks:%llu", + inode->i_ino, + (unsigned long long)inode->i_blocks); set_sbi_flag(sbi, SBI_NEED_FSCK); return; } @@ -2253,6 +2279,9 @@ static inline struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, static inline bool is_idle(struct f2fs_sb_info *sbi, int type) { + if (sbi->gc_mode == GC_URGENT) + return true; + if (get_pages(sbi, F2FS_RD_DATA) || get_pages(sbi, F2FS_RD_NODE) || get_pages(sbi, F2FS_RD_META) || get_pages(sbi, F2FS_WB_DATA) || get_pages(sbi, F2FS_WB_CP_DATA) || @@ -2260,7 +2289,7 @@ static inline bool is_idle(struct f2fs_sb_info *sbi, int type) get_pages(sbi, F2FS_DIO_WRITE)) return false; - if (SM_I(sbi) && SM_I(sbi)->dcc_info && + if (type != DISCARD_TIME && SM_I(sbi) && SM_I(sbi)->dcc_info && atomic_read(&SM_I(sbi)->dcc_info->queued_discard)) return false; @@ -2382,57 +2411,23 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr) } /* - * Inode flags + * On-disk inode flags (f2fs_inode::i_flags) */ -#define F2FS_SECRM_FL 0x00000001 /* Secure deletion */ -#define F2FS_UNRM_FL 0x00000002 /* Undelete */ -#define F2FS_COMPR_FL 0x00000004 /* Compress file */ #define F2FS_SYNC_FL 0x00000008 /* Synchronous updates */ #define F2FS_IMMUTABLE_FL 0x00000010 /* Immutable file */ #define F2FS_APPEND_FL 0x00000020 /* writes to file may only append */ #define F2FS_NODUMP_FL 0x00000040 /* do not dump file */ #define F2FS_NOATIME_FL 0x00000080 /* do not update atime */ -/* Reserved for compression usage... */ -#define F2FS_DIRTY_FL 0x00000100 -#define F2FS_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */ -#define F2FS_NOCOMPR_FL 0x00000400 /* Don't compress */ -#define F2FS_ENCRYPT_FL 0x00000800 /* encrypted file */ -/* End compression flags --- maybe not all used */ #define F2FS_INDEX_FL 0x00001000 /* hash-indexed directory */ -#define F2FS_IMAGIC_FL 0x00002000 /* AFS directory */ -#define F2FS_JOURNAL_DATA_FL 0x00004000 /* file data should be journaled */ -#define F2FS_NOTAIL_FL 0x00008000 /* file tail should not be merged */ #define F2FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ -#define F2FS_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ -#define F2FS_HUGE_FILE_FL 0x00040000 /* Set to each huge file */ -#define F2FS_EXTENTS_FL 0x00080000 /* Inode uses extents */ -#define F2FS_EA_INODE_FL 0x00200000 /* Inode used for large EA */ -#define F2FS_EOFBLOCKS_FL 0x00400000 /* Blocks allocated beyond EOF */ -#define F2FS_NOCOW_FL 0x00800000 /* Do not cow file */ -#define F2FS_INLINE_DATA_FL 0x10000000 /* Inode has inline data. */ #define F2FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ -#define F2FS_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ - -#define F2FS_FL_USER_VISIBLE 0x30CBDFFF /* User visible flags */ -#define F2FS_FL_USER_MODIFIABLE 0x204BC0FF /* User modifiable flags */ - -/* Flags we can manipulate with through F2FS_IOC_FSSETXATTR */ -#define F2FS_FL_XFLAG_VISIBLE (F2FS_SYNC_FL | \ - F2FS_IMMUTABLE_FL | \ - F2FS_APPEND_FL | \ - F2FS_NODUMP_FL | \ - F2FS_NOATIME_FL | \ - F2FS_PROJINHERIT_FL) /* Flags that should be inherited by new inodes from their parent. */ -#define F2FS_FL_INHERITED (F2FS_SECRM_FL | F2FS_UNRM_FL | F2FS_COMPR_FL |\ - F2FS_SYNC_FL | F2FS_NODUMP_FL | F2FS_NOATIME_FL |\ - F2FS_NOCOMPR_FL | F2FS_JOURNAL_DATA_FL |\ - F2FS_NOTAIL_FL | F2FS_DIRSYNC_FL |\ - F2FS_PROJINHERIT_FL) +#define F2FS_FL_INHERITED (F2FS_SYNC_FL | F2FS_NODUMP_FL | F2FS_NOATIME_FL | \ + F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL) /* Flags that are appropriate for regular files (all but dir-specific ones). */ -#define F2FS_REG_FLMASK (~(F2FS_DIRSYNC_FL | F2FS_TOPDIR_FL)) +#define F2FS_REG_FLMASK (~(F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL)) /* Flags that are appropriate for non-directories/regular files. */ #define F2FS_OTHER_FLMASK (F2FS_NODUMP_FL | F2FS_NOATIME_FL) @@ -2940,9 +2935,8 @@ static inline void verify_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type) { if (!f2fs_is_valid_blkaddr(sbi, blkaddr, type)) { - f2fs_msg(sbi->sb, KERN_ERR, - "invalid blkaddr: %u, type: %d, run fsck to fix.", - blkaddr, type); + f2fs_err(sbi, "invalid blkaddr: %u, type: %d, run fsck to fix.", + blkaddr, type); f2fs_bug_on(sbi, 1); } } @@ -3072,8 +3066,6 @@ int f2fs_quota_sync(struct super_block *sb, int type); void f2fs_quota_off_umount(struct super_block *sb); int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover); int f2fs_sync_fs(struct super_block *sb, int sync); -extern __printf(3, 4) -void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...); int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi); /* @@ -3157,9 +3149,12 @@ bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi); void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc); void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi); -int f2fs_disable_cp_again(struct f2fs_sb_info *sbi); +block_t f2fs_get_unusable_blocks(struct f2fs_sb_info *sbi); +int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable); void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi); int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra); +void allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type, + unsigned int start, unsigned int end); void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi); int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range); bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi, @@ -3252,6 +3247,7 @@ void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi, nid_t ino, enum page_type type); void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi); int f2fs_submit_page_bio(struct f2fs_io_info *fio); +int f2fs_merge_page_bio(struct f2fs_io_info *fio); void f2fs_submit_page_write(struct f2fs_io_info *fio); struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi, block_t blk_addr, struct bio *bio); @@ -3297,6 +3293,7 @@ block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode); int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background, unsigned int segno); void f2fs_build_gc_manager(struct f2fs_sb_info *sbi); +int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count); /* * recovery.c @@ -3777,7 +3774,8 @@ static inline bool f2fs_force_buffered_io(struct inode *inode, if (test_opt(sbi, LFS) && (rw == WRITE) && block_unaligned_IO(inode, iocb, iter)) return true; - if (is_sbi_flag_set(F2FS_I_SB(inode), SBI_CP_DISABLED)) + if (is_sbi_flag_set(F2FS_I_SB(inode), SBI_CP_DISABLED) && + !(inode->i_flags & S_SWAPFILE)) return true; return false; @@ -3803,4 +3801,7 @@ static inline bool is_journalled_quota(struct f2fs_sb_info *sbi) return false; } +#define EFSBADCRC EBADMSG /* Bad CRC detected */ +#define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ + #endif /* _LINUX_F2FS_H */ diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 8a1ad6cd63c5..c51d0c531213 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -711,12 +711,12 @@ int f2fs_getattr(struct vfsmount *mnt, stat->btime.tv_nsec = fi->i_crtime.tv_nsec; } - flags = fi->i_flags & F2FS_FL_USER_VISIBLE; + flags = fi->i_flags; if (flags & F2FS_APPEND_FL) stat->attributes |= STATX_ATTR_APPEND; if (flags & F2FS_COMPR_FL) stat->attributes |= STATX_ATTR_COMPRESSED; - if (f2fs_encrypted_inode(inode)) + if (IS_ENCRYPTED(inode)) stat->attributes |= STATX_ATTR_ENCRYPTED; if (flags & F2FS_IMMUTABLE_FL) stat->attributes |= STATX_ATTR_IMMUTABLE; @@ -724,7 +724,6 @@ int f2fs_getattr(struct vfsmount *mnt, stat->attributes |= STATX_ATTR_NODUMP; stat->attributes_mask |= (STATX_ATTR_APPEND | - STATX_ATTR_COMPRESSED | STATX_ATTR_ENCRYPTED | STATX_ATTR_IMMUTABLE | STATX_ATTR_NODUMP); @@ -1033,7 +1032,7 @@ next_dnode: !f2fs_is_valid_blkaddr(sbi, *blkaddr, DATA_GENERIC_ENHANCE)) { f2fs_put_dnode(&dn); - return -EFAULT; + return -EFSCORRUPTED; } if (!f2fs_is_checkpointed_data(sbi, *blkaddr)) { @@ -1221,7 +1220,7 @@ roll_back: static int f2fs_do_collapse(struct inode *inode, loff_t offset, loff_t len) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - pgoff_t nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE; + pgoff_t nrpages = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); pgoff_t start = offset >> PAGE_SHIFT; pgoff_t end = (offset + len) >> PAGE_SHIFT; int ret; @@ -1474,7 +1473,7 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) pg_start = offset >> PAGE_SHIFT; pg_end = (offset + len) >> PAGE_SHIFT; delta = pg_end - pg_start; - idx = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE; + idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); /* avoid gc operation during block exchange */ down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); @@ -1538,7 +1537,12 @@ static int expand_inode_data(struct inode *inode, loff_t offset, if (off_end) map.m_len++; - err = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO); + if (f2fs_is_pinned_file(inode)) + map.m_seg_type = CURSEG_COLD_DATA; + + err = f2fs_map_blocks(inode, &map, 1, (f2fs_is_pinned_file(inode) ? + F2FS_GET_BLOCK_PRE_DIO : + F2FS_GET_BLOCK_PRE_AIO)); if (err) { pgoff_t last_off; @@ -1655,69 +1659,152 @@ static int f2fs_file_flush(struct file *file, fl_owner_t id) return 0; } +static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + + /* Is it quota file? Do not allow user to mess with it */ + if (IS_NOQUOTA(inode)) + return -EPERM; + + fi->i_flags = iflags | (fi->i_flags & ~mask); + + if (fi->i_flags & F2FS_PROJINHERIT_FL) + set_inode_flag(inode, FI_PROJ_INHERIT); + else + clear_inode_flag(inode, FI_PROJ_INHERIT); + + inode->i_ctime = current_time(inode); + f2fs_set_inode_flags(inode); + f2fs_mark_inode_dirty_sync(inode, true); + return 0; +} + +/* FS_IOC_GETFLAGS and FS_IOC_SETFLAGS support */ + +/* + * To make a new on-disk f2fs i_flag gettable via FS_IOC_GETFLAGS, add an entry + * for it to f2fs_fsflags_map[], and add its FS_*_FL equivalent to + * F2FS_GETTABLE_FS_FL. To also make it settable via FS_IOC_SETFLAGS, also add + * its FS_*_FL equivalent to F2FS_SETTABLE_FS_FL. + */ + +static const struct { + u32 iflag; + u32 fsflag; +} f2fs_fsflags_map[] = { + { F2FS_SYNC_FL, FS_SYNC_FL }, + { F2FS_IMMUTABLE_FL, FS_IMMUTABLE_FL }, + { F2FS_APPEND_FL, FS_APPEND_FL }, + { F2FS_NODUMP_FL, FS_NODUMP_FL }, + { F2FS_NOATIME_FL, FS_NOATIME_FL }, + { F2FS_INDEX_FL, FS_INDEX_FL }, + { F2FS_DIRSYNC_FL, FS_DIRSYNC_FL }, + { F2FS_PROJINHERIT_FL, FS_PROJINHERIT_FL }, +}; + +#define F2FS_GETTABLE_FS_FL ( \ + FS_SYNC_FL | \ + FS_IMMUTABLE_FL | \ + FS_APPEND_FL | \ + FS_NODUMP_FL | \ + FS_NOATIME_FL | \ + FS_INDEX_FL | \ + FS_DIRSYNC_FL | \ + FS_PROJINHERIT_FL | \ + FS_ENCRYPT_FL | \ + FS_INLINE_DATA_FL | \ + FS_NOCOW_FL) + +#define F2FS_SETTABLE_FS_FL ( \ + FS_SYNC_FL | \ + FS_IMMUTABLE_FL | \ + FS_APPEND_FL | \ + FS_NODUMP_FL | \ + FS_NOATIME_FL | \ + FS_DIRSYNC_FL | \ + FS_PROJINHERIT_FL) + +/* Convert f2fs on-disk i_flags to FS_IOC_{GET,SET}FLAGS flags */ +static inline u32 f2fs_iflags_to_fsflags(u32 iflags) +{ + u32 fsflags = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(f2fs_fsflags_map); i++) + if (iflags & f2fs_fsflags_map[i].iflag) + fsflags |= f2fs_fsflags_map[i].fsflag; + + return fsflags; +} + +/* Convert FS_IOC_{GET,SET}FLAGS flags to f2fs on-disk i_flags */ +static inline u32 f2fs_fsflags_to_iflags(u32 fsflags) +{ + u32 iflags = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(f2fs_fsflags_map); i++) + if (fsflags & f2fs_fsflags_map[i].fsflag) + iflags |= f2fs_fsflags_map[i].iflag; + + return iflags; +} + static int f2fs_ioc_getflags(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_inode_info *fi = F2FS_I(inode); - unsigned int flags = fi->i_flags; + u32 fsflags = f2fs_iflags_to_fsflags(fi->i_flags); - if (f2fs_encrypted_inode(inode)) - flags |= F2FS_ENCRYPT_FL; + if (IS_ENCRYPTED(inode)) + fsflags |= FS_ENCRYPT_FL; if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) - flags |= F2FS_INLINE_DATA_FL; + fsflags |= FS_INLINE_DATA_FL; if (is_inode_flag_set(inode, FI_PIN_FILE)) - flags |= F2FS_NOCOW_FL; + fsflags |= FS_NOCOW_FL; - flags &= F2FS_FL_USER_VISIBLE; + fsflags &= F2FS_GETTABLE_FS_FL; - return put_user(flags, (int __user *)arg); + return put_user(fsflags, (int __user *)arg); } static int f2fs_ioc_setflags(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_inode_info *fi = F2FS_I(inode); - unsigned int flags; - unsigned int oldflags; + u32 fsflags, old_fsflags; + u32 iflags; int ret; if (!inode_owner_or_capable(inode)) return -EACCES; - if (get_user(flags, (int __user *)arg)) + if (get_user(fsflags, (int __user *)arg)) return -EFAULT; + if (fsflags & ~F2FS_GETTABLE_FS_FL) + return -EOPNOTSUPP; + fsflags &= F2FS_SETTABLE_FS_FL; + + iflags = f2fs_fsflags_to_iflags(fsflags); + if (f2fs_mask_flags(inode->i_mode, iflags) != iflags) + return -EOPNOTSUPP; + ret = mnt_want_write_file(filp); if (ret) return ret; inode_lock(inode); - /* Is it quota file? Do not allow user to mess with it */ - if (IS_NOQUOTA(inode)) { - ret = -EPERM; - goto unlock_out; - } - - flags = f2fs_mask_flags(inode->i_mode, flags); - - oldflags = fi->i_flags; - - if ((flags ^ oldflags) & (F2FS_APPEND_FL | F2FS_IMMUTABLE_FL)) { - if (!capable(CAP_LINUX_IMMUTABLE)) { - ret = -EPERM; - goto unlock_out; - } - } - - flags = flags & (F2FS_FL_USER_MODIFIABLE); - flags |= oldflags & ~(F2FS_FL_USER_MODIFIABLE); - fi->i_flags = flags; + old_fsflags = f2fs_iflags_to_fsflags(fi->i_flags); + ret = vfs_ioc_setflags_prepare(inode, old_fsflags, fsflags); + if (ret) + goto out; - inode->i_ctime = current_time(inode); - f2fs_set_inode_flags(inode); - f2fs_mark_inode_dirty_sync(inode, false); -unlock_out: + ret = f2fs_setflags_common(inode, iflags, + f2fs_fsflags_to_iflags(F2FS_SETTABLE_FS_FL)); +out: inode_unlock(inode); mnt_drop_write_file(filp); return ret; @@ -1764,9 +1851,8 @@ static int f2fs_ioc_start_atomic_write(struct file *filp) * f2fs_is_atomic_file. */ if (get_dirty_pages(inode)) - f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING, - "Unexpected flush for atomic writes: ino=%lu, npages=%u", - inode->i_ino, get_dirty_pages(inode)); + f2fs_warn(F2FS_I_SB(inode), "Unexpected flush for atomic writes: ino=%lu, npages=%u", + inode->i_ino, get_dirty_pages(inode)); ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX); if (ret) { up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); @@ -2201,8 +2287,7 @@ static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg) return -EROFS; if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { - f2fs_msg(sbi->sb, KERN_INFO, - "Skipping Checkpoint. Checkpoints currently disabled."); + f2fs_info(sbi, "Skipping Checkpoint. Checkpoints currently disabled."); return -EINVAL; } @@ -2291,7 +2376,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, if (!fragmented) goto out; - sec_num = (total + BLKS_PER_SEC(sbi) - 1) / BLKS_PER_SEC(sbi); + sec_num = DIV_ROUND_UP(total, BLKS_PER_SEC(sbi)); /* * make sure there are enough free section for LFS allocation, this can @@ -2587,10 +2672,8 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg) if (!f2fs_is_multi_device(sbi) || sbi->s_ndevs - 1 <= range.dev_num || __is_large_section(sbi)) { - f2fs_msg(sbi->sb, KERN_WARNING, - "Can't flush %u in %d for segs_per_sec %u != 1", - range.dev_num, sbi->s_ndevs, - sbi->segs_per_sec); + f2fs_warn(sbi, "Can't flush %u in %d for segs_per_sec %u != 1", + range.dev_num, sbi->s_ndevs, sbi->segs_per_sec); return -EINVAL; } @@ -2649,10 +2732,9 @@ int f2fs_pin_file_control(struct inode *inode, bool inc) fi->i_gc_failures[GC_FAILURE_PIN] + 1); if (fi->i_gc_failures[GC_FAILURE_PIN] > sbi->gc_pin_file_threshold) { - f2fs_msg(sbi->sb, KERN_WARNING, - "%s: Enable GC = ino %lx after %x GC trials", - __func__, inode->i_ino, - fi->i_gc_failures[GC_FAILURE_PIN]); + f2fs_warn(sbi, "%s: Enable GC = ino %lx after %x GC trials", + __func__, inode->i_ino, + fi->i_gc_failures[GC_FAILURE_PIN]); clear_inode_flag(inode, FI_PIN_FILE); return -EAGAIN; } @@ -2665,9 +2747,6 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg) __u32 pin; int ret = 0; - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - if (get_user(pin, (__u32 __user *)arg)) return -EFAULT; @@ -2760,6 +2839,27 @@ static int f2fs_ioc_precache_extents(struct file *filp, unsigned long arg) return f2fs_precache_extents(file_inode(filp)); } +static int f2fs_ioc_resize_fs(struct file *filp, unsigned long arg) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(file_inode(filp)); + __u64 block_count; + int ret; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (f2fs_readonly(sbi->sb)) + return -EROFS; + + if (copy_from_user(&block_count, (void __user *)arg, + sizeof(block_count))) + return -EFAULT; + + ret = f2fs_resize_fs(sbi, block_count); + + return ret; +} + long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(filp))))) @@ -2812,6 +2912,8 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_ioc_set_pin_file(filp, arg); case F2FS_IOC_PRECACHE_EXTENTS: return f2fs_ioc_precache_extents(filp, arg); + case F2FS_IOC_RESIZE_FS: + return f2fs_ioc_resize_fs(filp, arg); default: return -ENOTTY; } @@ -2928,6 +3030,7 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case F2FS_IOC_GET_PIN_FILE: case F2FS_IOC_SET_PIN_FILE: case F2FS_IOC_PRECACHE_EXTENTS: + case F2FS_IOC_RESIZE_FS: break; default: return -ENOIOCTLCMD; diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index e610a94c7da7..bac60511c9a2 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -311,10 +311,11 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, struct sit_info *sm = SIT_I(sbi); struct victim_sel_policy p; unsigned int secno, last_victim; - unsigned int last_segment = MAIN_SEGS(sbi); + unsigned int last_segment; unsigned int nsearched = 0; mutex_lock(&dirty_i->seglist_lock); + last_segment = MAIN_SECS(sbi) * sbi->segs_per_sec; p.alloc_mode = alloc_mode; select_policy(sbi, gc_type, type, &p); @@ -387,7 +388,8 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, goto next; /* Don't touch checkpointed data */ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) && - get_ckpt_valid_blocks(sbi, segno))) + get_ckpt_valid_blocks(sbi, segno) && + p.alloc_mode != SSR)) goto next; if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap)) goto next; @@ -404,7 +406,8 @@ next: sm->last_victim[p.gc_mode] = last_victim + 1; else sm->last_victim[p.gc_mode] = segno + 1; - sm->last_victim[p.gc_mode] %= MAIN_SEGS(sbi); + sm->last_victim[p.gc_mode] %= + (MAIN_SECS(sbi) * sbi->segs_per_sec); break; } } @@ -615,9 +618,8 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, } if (sum->version != dni->version) { - f2fs_msg(sbi->sb, KERN_WARNING, - "%s: valid data with mismatched node version.", - __func__); + f2fs_warn(sbi, "%s: valid data with mismatched node version.", + __func__); set_sbi_flag(sbi, SBI_NEED_FSCK); } @@ -658,7 +660,7 @@ static int ra_data_block(struct inode *inode, pgoff_t index) dn.data_blkaddr = ei.blk + index - ei.fofs; if (unlikely(!f2fs_is_valid_blkaddr(sbi, dn.data_blkaddr, DATA_GENERIC_ENHANCE_READ))) { - err = -EFAULT; + err = -EFSCORRUPTED; goto put_page; } goto got_it; @@ -676,7 +678,7 @@ static int ra_data_block(struct inode *inode, pgoff_t index) } if (unlikely(!f2fs_is_valid_blkaddr(sbi, dn.data_blkaddr, DATA_GENERIC_ENHANCE))) { - err = -EFAULT; + err = -EFSCORRUPTED; goto put_page; } got_it: @@ -794,6 +796,29 @@ static int move_data_block(struct inode *inode, block_t bidx, if (lfs_mode) down_write(&fio.sbi->io_order_lock); + mpage = f2fs_grab_cache_page(META_MAPPING(fio.sbi), + fio.old_blkaddr, false); + if (!mpage) + goto up_out; + + fio.encrypted_page = mpage; + + /* read source block in mpage */ + if (!PageUptodate(mpage)) { + err = f2fs_submit_page_bio(&fio); + if (err) { + f2fs_put_page(mpage, 1); + goto up_out; + } + lock_page(mpage); + if (unlikely(mpage->mapping != META_MAPPING(fio.sbi) || + !PageUptodate(mpage))) { + err = -EIO; + f2fs_put_page(mpage, 1); + goto up_out; + } + } + f2fs_allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr, &sum, CURSEG_COLD_DATA, NULL, false); @@ -801,44 +826,18 @@ static int move_data_block(struct inode *inode, block_t bidx, newaddr, FGP_LOCK | FGP_CREAT, GFP_NOFS); if (!fio.encrypted_page) { err = -ENOMEM; - goto recover_block; - } - - mpage = f2fs_pagecache_get_page(META_MAPPING(fio.sbi), - fio.old_blkaddr, FGP_LOCK, GFP_NOFS); - if (mpage) { - bool updated = false; - - if (PageUptodate(mpage)) { - memcpy(page_address(fio.encrypted_page), - page_address(mpage), PAGE_SIZE); - updated = true; - } f2fs_put_page(mpage, 1); - invalidate_mapping_pages(META_MAPPING(fio.sbi), - fio.old_blkaddr, fio.old_blkaddr); - if (updated) - goto write_page; - } - - err = f2fs_submit_page_bio(&fio); - if (err) - goto put_page_out; - - /* write page */ - lock_page(fio.encrypted_page); - - if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi))) { - err = -EIO; - goto put_page_out; - } - if (unlikely(!PageUptodate(fio.encrypted_page))) { - err = -EIO; - goto put_page_out; + goto recover_block; } -write_page: + /* write target block */ f2fs_wait_on_page_writeback(fio.encrypted_page, DATA, true, true); + memcpy(page_address(fio.encrypted_page), + page_address(mpage), PAGE_SIZE); + f2fs_put_page(mpage, 1); + invalidate_mapping_pages(META_MAPPING(fio.sbi), + fio.old_blkaddr, fio.old_blkaddr); + set_page_dirty(fio.encrypted_page); if (clear_page_dirty_for_io(fio.encrypted_page)) dec_page_count(fio.sbi, F2FS_DIRTY_META); @@ -869,11 +868,12 @@ write_page: put_page_out: f2fs_put_page(fio.encrypted_page, 1); recover_block: - if (lfs_mode) - up_write(&fio.sbi->io_order_lock); if (err) f2fs_do_replace_block(fio.sbi, &sum, newaddr, fio.old_blkaddr, true, true); +up_out: + if (lfs_mode) + up_write(&fio.sbi->io_order_lock); put_out: f2fs_put_dnode(&dn); out: @@ -1180,9 +1180,8 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, sum = page_address(sum_page); if (type != GET_SUM_TYPE((&sum->footer))) { - f2fs_msg(sbi->sb, KERN_ERR, "Inconsistent segment (%u) " - "type [%d, %d] in SSA and SIT", - segno, type, GET_SUM_TYPE((&sum->footer))); + f2fs_err(sbi, "Inconsistent segment (%u) type [%d, %d] in SSA and SIT", + segno, type, GET_SUM_TYPE((&sum->footer))); set_sbi_flag(sbi, SBI_NEED_FSCK); f2fs_stop_checkpoint(sbi, false); goto skip; @@ -1360,3 +1359,176 @@ void f2fs_build_gc_manager(struct f2fs_sb_info *sbi) SIT_I(sbi)->last_victim[ALLOC_NEXT] = GET_SEGNO(sbi, FDEV(0).end_blk) + 1; } + +static int free_segment_range(struct f2fs_sb_info *sbi, unsigned int start, + unsigned int end) +{ + int type; + unsigned int segno, next_inuse; + int err = 0; + + /* Move out cursegs from the target range */ + for (type = CURSEG_HOT_DATA; type < NR_CURSEG_TYPE; type++) + allocate_segment_for_resize(sbi, type, start, end); + + /* do GC to move out valid blocks in the range */ + for (segno = start; segno <= end; segno += sbi->segs_per_sec) { + struct gc_inode_list gc_list = { + .ilist = LIST_HEAD_INIT(gc_list.ilist), + .iroot = RADIX_TREE_INIT(GFP_NOFS), + }; + + mutex_lock(&sbi->gc_mutex); + do_garbage_collect(sbi, segno, &gc_list, FG_GC); + mutex_unlock(&sbi->gc_mutex); + put_gc_inode(&gc_list); + + if (get_valid_blocks(sbi, segno, true)) + return -EAGAIN; + } + + err = f2fs_sync_fs(sbi->sb, 1); + if (err) + return err; + + next_inuse = find_next_inuse(FREE_I(sbi), end + 1, start); + if (next_inuse <= end) { + f2fs_err(sbi, "segno %u should be free but still inuse!", + next_inuse); + f2fs_bug_on(sbi, 1); + } + return err; +} + +static void update_sb_metadata(struct f2fs_sb_info *sbi, int secs) +{ + struct f2fs_super_block *raw_sb = F2FS_RAW_SUPER(sbi); + int section_count = le32_to_cpu(raw_sb->section_count); + int segment_count = le32_to_cpu(raw_sb->segment_count); + int segment_count_main = le32_to_cpu(raw_sb->segment_count_main); + long long block_count = le64_to_cpu(raw_sb->block_count); + int segs = secs * sbi->segs_per_sec; + + raw_sb->section_count = cpu_to_le32(section_count + secs); + raw_sb->segment_count = cpu_to_le32(segment_count + segs); + raw_sb->segment_count_main = cpu_to_le32(segment_count_main + segs); + raw_sb->block_count = cpu_to_le64(block_count + + (long long)segs * sbi->blocks_per_seg); +} + +static void update_fs_metadata(struct f2fs_sb_info *sbi, int secs) +{ + int segs = secs * sbi->segs_per_sec; + long long user_block_count = + le64_to_cpu(F2FS_CKPT(sbi)->user_block_count); + + SM_I(sbi)->segment_count = (int)SM_I(sbi)->segment_count + segs; + MAIN_SEGS(sbi) = (int)MAIN_SEGS(sbi) + segs; + FREE_I(sbi)->free_sections = (int)FREE_I(sbi)->free_sections + secs; + FREE_I(sbi)->free_segments = (int)FREE_I(sbi)->free_segments + segs; + F2FS_CKPT(sbi)->user_block_count = cpu_to_le64(user_block_count + + (long long)segs * sbi->blocks_per_seg); +} + +int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count) +{ + __u64 old_block_count, shrunk_blocks; + unsigned int secs; + int gc_mode, gc_type; + int err = 0; + __u32 rem; + + old_block_count = le64_to_cpu(F2FS_RAW_SUPER(sbi)->block_count); + if (block_count > old_block_count) + return -EINVAL; + + /* new fs size should align to section size */ + div_u64_rem(block_count, BLKS_PER_SEC(sbi), &rem); + if (rem) + return -EINVAL; + + if (block_count == old_block_count) + return 0; + + if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) { + f2fs_err(sbi, "Should run fsck to repair first."); + return -EFSCORRUPTED; + } + + if (test_opt(sbi, DISABLE_CHECKPOINT)) { + f2fs_err(sbi, "Checkpoint should be enabled."); + return -EINVAL; + } + + freeze_bdev(sbi->sb->s_bdev); + + shrunk_blocks = old_block_count - block_count; + secs = div_u64(shrunk_blocks, BLKS_PER_SEC(sbi)); + spin_lock(&sbi->stat_lock); + if (shrunk_blocks + valid_user_blocks(sbi) + + sbi->current_reserved_blocks + sbi->unusable_block_count + + F2FS_OPTION(sbi).root_reserved_blocks > sbi->user_block_count) + err = -ENOSPC; + else + sbi->user_block_count -= shrunk_blocks; + spin_unlock(&sbi->stat_lock); + if (err) { + thaw_bdev(sbi->sb->s_bdev, sbi->sb); + return err; + } + + mutex_lock(&sbi->resize_mutex); + set_sbi_flag(sbi, SBI_IS_RESIZEFS); + + mutex_lock(&DIRTY_I(sbi)->seglist_lock); + + MAIN_SECS(sbi) -= secs; + + for (gc_mode = 0; gc_mode < MAX_GC_POLICY; gc_mode++) + if (SIT_I(sbi)->last_victim[gc_mode] >= + MAIN_SECS(sbi) * sbi->segs_per_sec) + SIT_I(sbi)->last_victim[gc_mode] = 0; + + for (gc_type = BG_GC; gc_type <= FG_GC; gc_type++) + if (sbi->next_victim_seg[gc_type] >= + MAIN_SECS(sbi) * sbi->segs_per_sec) + sbi->next_victim_seg[gc_type] = NULL_SEGNO; + + mutex_unlock(&DIRTY_I(sbi)->seglist_lock); + + err = free_segment_range(sbi, MAIN_SECS(sbi) * sbi->segs_per_sec, + MAIN_SEGS(sbi) - 1); + if (err) + goto out; + + update_sb_metadata(sbi, -secs); + + err = f2fs_commit_super(sbi, false); + if (err) { + update_sb_metadata(sbi, secs); + goto out; + } + + update_fs_metadata(sbi, -secs); + clear_sbi_flag(sbi, SBI_IS_RESIZEFS); + err = f2fs_sync_fs(sbi->sb, 1); + if (err) { + update_fs_metadata(sbi, secs); + update_sb_metadata(sbi, secs); + f2fs_commit_super(sbi, false); + } +out: + if (err) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_err(sbi, "resize_fs failed, should run fsck to repair!"); + + MAIN_SECS(sbi) += secs; + spin_lock(&sbi->stat_lock); + sbi->user_block_count += shrunk_blocks; + spin_unlock(&sbi->stat_lock); + } + clear_sbi_flag(sbi, SBI_IS_RESIZEFS); + mutex_unlock(&sbi->resize_mutex); + thaw_bdev(sbi->sb->s_bdev, sbi->sb); + return err; +} diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 7ad88aa2aa9f..aef822b1fa9d 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -158,11 +158,9 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page) if (unlikely(dn->data_blkaddr != NEW_ADDR)) { f2fs_put_dnode(dn); set_sbi_flag(fio.sbi, SBI_NEED_FSCK); - f2fs_msg(fio.sbi->sb, KERN_WARNING, - "%s: corrupted inline inode ino=%lx, i_addr[0]:0x%x, " - "run fsck to fix.", - __func__, dn->inode->i_ino, dn->data_blkaddr); - return -EINVAL; + f2fs_warn(fio.sbi, "%s: corrupted inline inode ino=%lx, i_addr[0]:0x%x, run fsck to fix.", + __func__, dn->inode->i_ino, dn->data_blkaddr); + return -EFSCORRUPTED; } f2fs_bug_on(F2FS_P_SB(page), PageWriteback(page)); @@ -401,11 +399,9 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage, if (unlikely(dn.data_blkaddr != NEW_ADDR)) { f2fs_put_dnode(&dn); set_sbi_flag(F2FS_P_SB(page), SBI_NEED_FSCK); - f2fs_msg(F2FS_P_SB(page)->sb, KERN_WARNING, - "%s: corrupted inline inode ino=%lx, i_addr[0]:0x%x, " - "run fsck to fix.", - __func__, dir->i_ino, dn.data_blkaddr); - err = -EINVAL; + f2fs_warn(F2FS_P_SB(page), "%s: corrupted inline inode ino=%lx, i_addr[0]:0x%x, run fsck to fix.", + __func__, dir->i_ino, dn.data_blkaddr); + err = -EFSCORRUPTED; goto out; } diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 63a0fcd84492..2f02199047a9 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -74,7 +74,7 @@ static int __written_first_block(struct f2fs_sb_info *sbi, if (!__is_valid_data_blkaddr(addr)) return 1; if (!f2fs_is_valid_blkaddr(sbi, addr, DATA_GENERIC_ENHANCE)) - return -EFAULT; + return -EFSCORRUPTED; return 0; } @@ -176,9 +176,8 @@ bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page) calculated = f2fs_inode_chksum(sbi, page); if (provided != calculated) - f2fs_msg(sbi->sb, KERN_WARNING, - "checksum invalid, nid = %lu, ino_of_node = %x, %x vs. %x", - page->index, ino_of_node(page), provided, calculated); + f2fs_warn(sbi, "checksum invalid, nid = %lu, ino_of_node = %x, %x vs. %x", + page->index, ino_of_node(page), provided, calculated); return provided == calculated; } @@ -202,50 +201,41 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page) iblocks = le64_to_cpu(F2FS_INODE(node_page)->i_blocks); if (!iblocks) { set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_msg(sbi->sb, KERN_WARNING, - "%s: corrupted inode i_blocks i_ino=%lx iblocks=%llu, " - "run fsck to fix.", - __func__, inode->i_ino, iblocks); + f2fs_warn(sbi, "%s: corrupted inode i_blocks i_ino=%lx iblocks=%llu, run fsck to fix.", + __func__, inode->i_ino, iblocks); return false; } if (ino_of_node(node_page) != nid_of_node(node_page)) { set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_msg(sbi->sb, KERN_WARNING, - "%s: corrupted inode footer i_ino=%lx, ino,nid: " - "[%u, %u] run fsck to fix.", - __func__, inode->i_ino, - ino_of_node(node_page), nid_of_node(node_page)); + f2fs_warn(sbi, "%s: corrupted inode footer i_ino=%lx, ino,nid: [%u, %u] run fsck to fix.", + __func__, inode->i_ino, + ino_of_node(node_page), nid_of_node(node_page)); return false; } if (f2fs_sb_has_flexible_inline_xattr(sbi) && !f2fs_has_extra_attr(inode)) { set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_msg(sbi->sb, KERN_WARNING, - "%s: corrupted inode ino=%lx, run fsck to fix.", - __func__, inode->i_ino); + f2fs_warn(sbi, "%s: corrupted inode ino=%lx, run fsck to fix.", + __func__, inode->i_ino); return false; } if (f2fs_has_extra_attr(inode) && !f2fs_sb_has_extra_attr(sbi)) { set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_msg(sbi->sb, KERN_WARNING, - "%s: inode (ino=%lx) is with extra_attr, " - "but extra_attr feature is off", - __func__, inode->i_ino); + f2fs_warn(sbi, "%s: inode (ino=%lx) is with extra_attr, but extra_attr feature is off", + __func__, inode->i_ino); return false; } if (fi->i_extra_isize > F2FS_TOTAL_EXTRA_ATTR_SIZE || fi->i_extra_isize % sizeof(__le32)) { set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_msg(sbi->sb, KERN_WARNING, - "%s: inode (ino=%lx) has corrupted i_extra_isize: %d, " - "max: %zu", - __func__, inode->i_ino, fi->i_extra_isize, - F2FS_TOTAL_EXTRA_ATTR_SIZE); + f2fs_warn(sbi, "%s: inode (ino=%lx) has corrupted i_extra_isize: %d, max: %zu", + __func__, inode->i_ino, fi->i_extra_isize, + F2FS_TOTAL_EXTRA_ATTR_SIZE); return false; } @@ -255,11 +245,9 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page) (!fi->i_inline_xattr_size || fi->i_inline_xattr_size > MAX_INLINE_XATTR_SIZE)) { set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_msg(sbi->sb, KERN_WARNING, - "%s: inode (ino=%lx) has corrupted " - "i_inline_xattr_size: %d, max: %zu", - __func__, inode->i_ino, fi->i_inline_xattr_size, - MAX_INLINE_XATTR_SIZE); + f2fs_warn(sbi, "%s: inode (ino=%lx) has corrupted i_inline_xattr_size: %d, max: %zu", + __func__, inode->i_ino, fi->i_inline_xattr_size, + MAX_INLINE_XATTR_SIZE); return false; } @@ -272,11 +260,9 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page) !f2fs_is_valid_blkaddr(sbi, ei->blk + ei->len - 1, DATA_GENERIC_ENHANCE))) { set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_msg(sbi->sb, KERN_WARNING, - "%s: inode (ino=%lx) extent info [%u, %u, %u] " - "is incorrect, run fsck to fix", - __func__, inode->i_ino, - ei->blk, ei->fofs, ei->len); + f2fs_warn(sbi, "%s: inode (ino=%lx) extent info [%u, %u, %u] is incorrect, run fsck to fix", + __func__, inode->i_ino, + ei->blk, ei->fofs, ei->len); return false; } } @@ -284,19 +270,15 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page) if (f2fs_has_inline_data(inode) && (!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode))) { set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_msg(sbi->sb, KERN_WARNING, - "%s: inode (ino=%lx, mode=%u) should not have " - "inline_data, run fsck to fix", - __func__, inode->i_ino, inode->i_mode); + f2fs_warn(sbi, "%s: inode (ino=%lx, mode=%u) should not have inline_data, run fsck to fix", + __func__, inode->i_ino, inode->i_mode); return false; } if (f2fs_has_inline_dentry(inode) && !S_ISDIR(inode->i_mode)) { set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_msg(sbi->sb, KERN_WARNING, - "%s: inode (ino=%lx, mode=%u) should not have " - "inline_dentry, run fsck to fix", - __func__, inode->i_ino, inode->i_mode); + f2fs_warn(sbi, "%s: inode (ino=%lx, mode=%u) should not have inline_dentry, run fsck to fix", + __func__, inode->i_ino, inode->i_mode); return false; } @@ -343,6 +325,8 @@ static int do_read_inode(struct inode *inode) le16_to_cpu(ri->i_gc_failures); fi->i_xattr_nid = le32_to_cpu(ri->i_xattr_nid); fi->i_flags = le32_to_cpu(ri->i_flags); + if (S_ISREG(inode->i_mode)) + fi->i_flags &= ~F2FS_PROJINHERIT_FL; fi->flags = 0; fi->i_advise = ri->i_advise; fi->i_pino = le32_to_cpu(ri->i_pino); @@ -374,7 +358,7 @@ static int do_read_inode(struct inode *inode) if (!sanity_check_inode(inode, node_page)) { f2fs_put_page(node_page, 1); - return -EINVAL; + return -EFSCORRUPTED; } /* check data exist */ @@ -783,8 +767,7 @@ void f2fs_handle_failed_inode(struct inode *inode) err = f2fs_get_node_info(sbi, inode->i_ino, &ni); if (err) { set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_msg(sbi->sb, KERN_WARNING, - "May loss orphan inode, run fsck to fix."); + f2fs_warn(sbi, "May loss orphan inode, run fsck to fix."); goto out; } @@ -792,8 +775,7 @@ void f2fs_handle_failed_inode(struct inode *inode) err = f2fs_acquire_orphan_inode(sbi); if (err) { set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_msg(sbi->sb, KERN_WARNING, - "Too many orphan inodes, run fsck to fix."); + f2fs_warn(sbi, "Too many orphan inodes, run fsck to fix."); } else { f2fs_add_orphan_inode(inode); } diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index aa82a5d25b66..94902b82d4ec 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -386,9 +386,8 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino) int err = 0; if (f2fs_readonly(sbi->sb)) { - f2fs_msg(sbi->sb, KERN_INFO, - "skip recovering inline_dots inode (ino:%lu, pino:%u) " - "in readonly mountpoint", dir->i_ino, pino); + f2fs_info(sbi, "skip recovering inline_dots inode (ino:%lu, pino:%u) in readonly mountpoint", + dir->i_ino, pino); return 0; } @@ -481,9 +480,8 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, if (f2fs_encrypted_inode(dir) && (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) && !fscrypt_has_permitted_context(dir, inode)) { - f2fs_msg(inode->i_sb, KERN_WARNING, - "Inconsistent encryption contexts: %lu/%lu", - dir->i_ino, inode->i_ino); + f2fs_warn(F2FS_I_SB(inode), "Inconsistent encryption contexts: %lu/%lu", + dir->i_ino, inode->i_ino); err = -EPERM; goto out_iput; } diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index a39aa8856d17..508e684c8dbd 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -34,10 +34,9 @@ int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid) { if (unlikely(nid < F2FS_ROOT_INO(sbi) || nid >= NM_I(sbi)->max_nid)) { set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_msg(sbi->sb, KERN_WARNING, - "%s: out-of-range nid=%x, run fsck to fix.", - __func__, nid); - return -EINVAL; + f2fs_warn(sbi, "%s: out-of-range nid=%x, run fsck to fix.", + __func__, nid); + return -EFSCORRUPTED; } return 0; } @@ -1187,10 +1186,8 @@ int f2fs_remove_inode_page(struct inode *inode) } if (unlikely(inode->i_blocks != 0 && inode->i_blocks != 8)) { - f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING, - "Inconsistent i_blocks, ino:%lu, iblocks:%llu", - inode->i_ino, - (unsigned long long)inode->i_blocks); + f2fs_warn(F2FS_I_SB(inode), "Inconsistent i_blocks, ino:%lu, iblocks:%llu", + inode->i_ino, (unsigned long long)inode->i_blocks); set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK); } @@ -1289,7 +1286,7 @@ static int read_node_page(struct page *page, int op_flags) if (PageUptodate(page)) { if (!f2fs_inode_chksum_verify(sbi, page)) { ClearPageUptodate(page); - return -EBADMSG; + return -EFSBADCRC; } return LOCKED_PAGE; } @@ -1375,16 +1372,15 @@ repeat: } if (!f2fs_inode_chksum_verify(sbi, page)) { - err = -EBADMSG; + err = -EFSBADCRC; goto out_err; } page_hit: if(unlikely(nid != nid_of_node(page))) { - f2fs_msg(sbi->sb, KERN_WARNING, "inconsistent node block, " - "nid:%lu, node_footer[nid:%u,ino:%u,ofs:%u,cpver:%llu,blkaddr:%u]", - nid, nid_of_node(page), ino_of_node(page), - ofs_of_node(page), cpver_of_node(page), - next_blkaddr_of_node(page)); + f2fs_warn(sbi, "inconsistent node block, nid:%lu, node_footer[nid:%u,ino:%u,ofs:%u,cpver:%llu,blkaddr:%u]", + nid, nid_of_node(page), ino_of_node(page), + ofs_of_node(page), cpver_of_node(page), + next_blkaddr_of_node(page)); err = -EINVAL; out_err: ClearPageUptodate(page); @@ -1752,9 +1748,8 @@ continue_unlock: break; } if (!ret && atomic && !marked) { - f2fs_msg(sbi->sb, KERN_DEBUG, - "Retry to write fsync mark: ino=%u, idx=%lx", - ino, last_page->index); + f2fs_debug(sbi, "Retry to write fsync mark: ino=%u, idx=%lx", + ino, last_page->index); lock_page(last_page); f2fs_wait_on_page_writeback(last_page, NODE, true, true); set_page_dirty(last_page); @@ -2307,8 +2302,7 @@ static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi, if (ret) { up_read(&nm_i->nat_tree_lock); f2fs_bug_on(sbi, !mount); - f2fs_msg(sbi->sb, KERN_ERR, - "NAT is corrupt, run fsck to fix it"); + f2fs_err(sbi, "NAT is corrupt, run fsck to fix it"); return ret; } } @@ -2728,7 +2722,7 @@ static void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid, i = 1; } for (; i < NAT_ENTRY_PER_BLOCK; i++) { - if (nat_blk->entries[i].block_addr != NULL_ADDR) + if (le32_to_cpu(nat_blk->entries[i].block_addr) != NULL_ADDR) valid++; } if (valid == 0) { @@ -2918,7 +2912,7 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi) nm_i->full_nat_bits = nm_i->nat_bits + 8; nm_i->empty_nat_bits = nm_i->full_nat_bits + nat_bits_bytes; - f2fs_msg(sbi->sb, KERN_NOTICE, "Found nat_bits in checkpoint"); + f2fs_notice(sbi, "Found nat_bits in checkpoint"); return 0; } diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 67206eff5cca..5d0c77054252 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -188,10 +188,9 @@ out: name = "<encrypted>"; else name = raw_inode->i_name; - f2fs_msg(inode->i_sb, KERN_NOTICE, - "%s: ino = %x, name = %s, dir = %lx, err = %d", - __func__, ino_of_node(ipage), name, - IS_ERR(dir) ? 0 : dir->i_ino, err); + f2fs_notice(F2FS_I_SB(inode), "%s: ino = %x, name = %s, dir = %lx, err = %d", + __func__, ino_of_node(ipage), name, + IS_ERR(dir) ? 0 : dir->i_ino, err); return err; } @@ -284,9 +283,8 @@ static int recover_inode(struct inode *inode, struct page *page) else name = F2FS_INODE(page)->i_name; - f2fs_msg(inode->i_sb, KERN_NOTICE, - "recover_inode: ino = %x, name = %s, inline = %x", - ino_of_node(page), name, raw->i_inline); + f2fs_notice(F2FS_I_SB(inode), "recover_inode: ino = %x, name = %s, inline = %x", + ino_of_node(page), name, raw->i_inline); return 0; } @@ -363,10 +361,9 @@ next: /* sanity check in order to detect looped node chain */ if (++loop_cnt >= free_blocks || blkaddr == next_blkaddr_of_node(page)) { - f2fs_msg(sbi->sb, KERN_NOTICE, - "%s: detect looped node chain, " - "blkaddr:%u, next:%u", - __func__, blkaddr, next_blkaddr_of_node(page)); + f2fs_notice(sbi, "%s: detect looped node chain, blkaddr:%u, next:%u", + __func__, blkaddr, + next_blkaddr_of_node(page)); f2fs_put_page(page, 1); err = -EINVAL; break; @@ -545,11 +542,10 @@ retry_dn: f2fs_bug_on(sbi, ni.ino != ino_of_node(page)); if (ofs_of_node(dn.node_page) != ofs_of_node(page)) { - f2fs_msg(sbi->sb, KERN_WARNING, - "Inconsistent ofs_of_node, ino:%lu, ofs:%u, %u", - inode->i_ino, ofs_of_node(dn.node_page), - ofs_of_node(page)); - err = -EFAULT; + f2fs_warn(sbi, "Inconsistent ofs_of_node, ino:%lu, ofs:%u, %u", + inode->i_ino, ofs_of_node(dn.node_page), + ofs_of_node(page)); + err = -EFSCORRUPTED; goto err; } @@ -561,13 +557,13 @@ retry_dn: if (__is_valid_data_blkaddr(src) && !f2fs_is_valid_blkaddr(sbi, src, META_POR)) { - err = -EFAULT; + err = -EFSCORRUPTED; goto err; } if (__is_valid_data_blkaddr(dest) && !f2fs_is_valid_blkaddr(sbi, dest, META_POR)) { - err = -EFAULT; + err = -EFSCORRUPTED; goto err; } @@ -634,11 +630,9 @@ retry_prev: err: f2fs_put_dnode(&dn); out: - f2fs_msg(sbi->sb, KERN_NOTICE, - "recover_data: ino = %lx (i_size: %s) recovered = %d, err = %d", - inode->i_ino, - file_keep_isize(inode) ? "keep" : "recover", - recovered, err); + f2fs_notice(sbi, "recover_data: ino = %lx (i_size: %s) recovered = %d, err = %d", + inode->i_ino, file_keep_isize(inode) ? "keep" : "recover", + recovered, err); return err; } @@ -726,8 +720,7 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) #endif if (s_flags & MS_RDONLY) { - f2fs_msg(sbi->sb, KERN_INFO, - "recover fsync data on readonly fs"); + f2fs_info(sbi, "recover fsync data on readonly fs"); sbi->sb->s_flags &= ~MS_RDONLY; } diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index af4770f0672a..553a16e985aa 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -546,9 +546,13 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi) if (test_opt(sbi, DATA_FLUSH)) { struct blk_plug plug; + mutex_lock(&sbi->flush_lock); + blk_start_plug(&plug); f2fs_sync_dirty_inodes(sbi, FILE_INODE); blk_finish_plug(&plug); + + mutex_unlock(&sbi->flush_lock); } f2fs_sync_fs(sbi->sb, true); stat_inc_bg_cp_count(sbi->stat_info); @@ -869,11 +873,14 @@ void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi) mutex_unlock(&dirty_i->seglist_lock); } -int f2fs_disable_cp_again(struct f2fs_sb_info *sbi) +block_t f2fs_get_unusable_blocks(struct f2fs_sb_info *sbi) { + int ovp_hole_segs = + (overprovision_segments(sbi) - reserved_segments(sbi)); + block_t ovp_holes = ovp_hole_segs << sbi->log_blocks_per_seg; struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); - block_t ovp = overprovision_segments(sbi) << sbi->log_blocks_per_seg; block_t holes[2] = {0, 0}; /* DATA and NODE */ + block_t unusable; struct seg_entry *se; unsigned int segno; @@ -887,10 +894,20 @@ int f2fs_disable_cp_again(struct f2fs_sb_info *sbi) } mutex_unlock(&dirty_i->seglist_lock); - if (holes[DATA] > ovp || holes[NODE] > ovp) + unusable = holes[DATA] > holes[NODE] ? holes[DATA] : holes[NODE]; + if (unusable > ovp_holes) + return unusable - ovp_holes; + return 0; +} + +int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable) +{ + int ovp_hole_segs = + (overprovision_segments(sbi) - reserved_segments(sbi)); + if (unusable > F2FS_OPTION(sbi).unusable_cap) return -EAGAIN; if (is_sbi_flag_set(sbi, SBI_CP_DISABLED_QUICK) && - dirty_segments(sbi) > overprovision_segments(sbi)) + dirty_segments(sbi) > ovp_hole_segs) return -EAGAIN; return 0; } @@ -1556,6 +1573,10 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi, list_for_each_entry_safe(dc, tmp, pend_list, list) { f2fs_bug_on(sbi, dc->state != D_PREP); + if (dpolicy->timeout != 0 && + f2fs_time_over(sbi, dpolicy->timeout)) + break; + if (dpolicy->io_aware && i < dpolicy->io_aware_gran && !is_idle(sbi, DISCARD_TIME)) { io_interrupted = true; @@ -1816,8 +1837,7 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi, devi = f2fs_target_device_index(sbi, blkstart); if (blkstart < FDEV(devi).start_blk || blkstart > FDEV(devi).end_blk) { - f2fs_msg(sbi->sb, KERN_ERR, "Invalid block %x", - blkstart); + f2fs_err(sbi, "Invalid block %x", blkstart); return -EIO; } blkstart -= FDEV(devi).start_blk; @@ -1830,10 +1850,9 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi, if (sector & (bdev_zone_sectors(bdev) - 1) || nr_sects != bdev_zone_sectors(bdev)) { - f2fs_msg(sbi->sb, KERN_ERR, - "(%d) %s: Unaligned zone reset attempted (block %x + %x)", - devi, sbi->s_ndevs ? FDEV(devi).path: "", - blkstart, blklen); + f2fs_err(sbi, "(%d) %s: Unaligned zone reset attempted (block %x + %x)", + devi, sbi->s_ndevs ? FDEV(devi).path : "", + blkstart, blklen); return -EIO; } trace_f2fs_issue_reset_zone(bdev, blkstart); @@ -2197,15 +2216,14 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) mir_exist = f2fs_test_and_set_bit(offset, se->cur_valid_map_mir); if (unlikely(exist != mir_exist)) { - f2fs_msg(sbi->sb, KERN_ERR, "Inconsistent error " - "when setting bitmap, blk:%u, old bit:%d", - blkaddr, exist); + f2fs_err(sbi, "Inconsistent error when setting bitmap, blk:%u, old bit:%d", + blkaddr, exist); f2fs_bug_on(sbi, 1); } #endif if (unlikely(exist)) { - f2fs_msg(sbi->sb, KERN_ERR, - "Bitmap was wrongly set, blk:%u", blkaddr); + f2fs_err(sbi, "Bitmap was wrongly set, blk:%u", + blkaddr); f2fs_bug_on(sbi, 1); se->valid_blocks--; del = 0; @@ -2226,15 +2244,14 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) mir_exist = f2fs_test_and_clear_bit(offset, se->cur_valid_map_mir); if (unlikely(exist != mir_exist)) { - f2fs_msg(sbi->sb, KERN_ERR, "Inconsistent error " - "when clearing bitmap, blk:%u, old bit:%d", - blkaddr, exist); + f2fs_err(sbi, "Inconsistent error when clearing bitmap, blk:%u, old bit:%d", + blkaddr, exist); f2fs_bug_on(sbi, 1); } #endif if (unlikely(!exist)) { - f2fs_msg(sbi->sb, KERN_ERR, - "Bitmap was wrongly cleared, blk:%u", blkaddr); + f2fs_err(sbi, "Bitmap was wrongly cleared, blk:%u", + blkaddr); f2fs_bug_on(sbi, 1); se->valid_blocks++; del = 0; @@ -2716,6 +2733,39 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi, stat_inc_seg_type(sbi, curseg); } +void allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type, + unsigned int start, unsigned int end) +{ + struct curseg_info *curseg = CURSEG_I(sbi, type); + unsigned int segno; + + down_read(&SM_I(sbi)->curseg_lock); + mutex_lock(&curseg->curseg_mutex); + down_write(&SIT_I(sbi)->sentry_lock); + + segno = CURSEG_I(sbi, type)->segno; + if (segno < start || segno > end) + goto unlock; + + if (f2fs_need_SSR(sbi) && get_ssr_segment(sbi, type)) + change_curseg(sbi, type); + else + new_curseg(sbi, type, true); + + stat_inc_seg_type(sbi, curseg); + + locate_dirty_segment(sbi, segno); +unlock: + up_write(&SIT_I(sbi)->sentry_lock); + + if (segno != curseg->segno) + f2fs_notice(sbi, "For resize: curseg of type %d: %u ==> %u", + type, segno, curseg->segno); + + mutex_unlock(&curseg->curseg_mutex); + up_read(&SM_I(sbi)->curseg_lock); +} + void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi) { struct curseg_info *curseg; @@ -2848,9 +2898,8 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) goto out; if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) { - f2fs_msg(sbi->sb, KERN_WARNING, - "Found FS corruption, run fsck to fix."); - return -EIO; + f2fs_warn(sbi, "Found FS corruption, run fsck to fix."); + return -EFSCORRUPTED; } /* start/end segment number in main_area */ @@ -3274,12 +3323,17 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio) if (!IS_DATASEG(get_seg_entry(sbi, segno)->type)) { set_sbi_flag(sbi, SBI_NEED_FSCK); - return -EFAULT; + f2fs_warn(sbi, "%s: incorrect segment(%u) type, run fsck to fix.", + __func__, segno); + return -EFSCORRUPTED; } stat_inc_inplace_blocks(fio->sbi); - err = f2fs_submit_page_bio(fio); + if (fio->bio) + err = f2fs_merge_page_bio(fio); + else + err = f2fs_submit_page_bio(fio); if (!err) { update_device_state(fio); f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE); @@ -3470,6 +3524,11 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi) seg_i = CURSEG_I(sbi, i); segno = le32_to_cpu(ckpt->cur_data_segno[i]); blk_off = le16_to_cpu(ckpt->cur_data_blkoff[i]); + if (blk_off > ENTRIES_IN_SUM) { + f2fs_bug_on(sbi, 1); + f2fs_put_page(page, 1); + return -EFAULT; + } seg_i->next_segno = segno; reset_curseg(sbi, i, 0); seg_i->alloc_type = ckpt->alloc_type[i]; @@ -3607,8 +3666,11 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi) /* sanity check for summary blocks */ if (nats_in_cursum(nat_j) > NAT_JOURNAL_ENTRIES || - sits_in_cursum(sit_j) > SIT_JOURNAL_ENTRIES) + sits_in_cursum(sit_j) > SIT_JOURNAL_ENTRIES) { + f2fs_err(sbi, "invalid journal entries nats %u sits %u\n", + nats_in_cursum(nat_j), sits_in_cursum(sit_j)); return -EINVAL; + } return 0; } @@ -3839,7 +3901,7 @@ void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) struct f2fs_journal *journal = curseg->journal; struct sit_entry_set *ses, *tmp; struct list_head *head = &SM_I(sbi)->sit_entry_set; - bool to_journal = true; + bool to_journal = !is_sbi_flag_set(sbi, SBI_IS_RESIZEFS); struct seg_entry *se; down_write(&sit_i->sentry_lock); @@ -3858,7 +3920,8 @@ void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) * entries, remove all entries from journal and add and account * them in sit entry set. */ - if (!__has_cursum_space(journal, sit_i->dirty_sentries, SIT_JOURNAL)) + if (!__has_cursum_space(journal, sit_i->dirty_sentries, SIT_JOURNAL) || + !to_journal) remove_sits_in_journal(sbi); /* @@ -4173,11 +4236,10 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) start = le32_to_cpu(segno_in_journal(journal, i)); if (start >= MAIN_SEGS(sbi)) { - f2fs_msg(sbi->sb, KERN_ERR, - "Wrong journal entry on segno %u", - start); + f2fs_err(sbi, "Wrong journal entry on segno %u", + start); set_sbi_flag(sbi, SBI_NEED_FSCK); - err = -EINVAL; + err = -EFSCORRUPTED; break; } @@ -4214,11 +4276,10 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) up_read(&curseg->journal_rwsem); if (!err && total_node_blocks != valid_node_count(sbi)) { - f2fs_msg(sbi->sb, KERN_ERR, - "SIT is corrupted node# %u vs %u", - total_node_blocks, valid_node_count(sbi)); + f2fs_err(sbi, "SIT is corrupted node# %u vs %u", + total_node_blocks, valid_node_count(sbi)); set_sbi_flag(sbi, SBI_NEED_FSCK); - err = -EINVAL; + err = -EFSCORRUPTED; } return err; @@ -4309,6 +4370,39 @@ static int build_dirty_segmap(struct f2fs_sb_info *sbi) return init_victim_secmap(sbi); } +static int sanity_check_curseg(struct f2fs_sb_info *sbi) +{ + int i; + + /* + * In LFS/SSR curseg, .next_blkoff should point to an unused blkaddr; + * In LFS curseg, all blkaddr after .next_blkoff should be unused. + */ + for (i = 0; i < NO_CHECK_TYPE; i++) { + struct curseg_info *curseg = CURSEG_I(sbi, i); + struct seg_entry *se = get_seg_entry(sbi, curseg->segno); + unsigned int blkofs = curseg->next_blkoff; + + if (f2fs_test_bit(blkofs, se->cur_valid_map)) + goto out; + + if (curseg->alloc_type == SSR) + continue; + + for (blkofs += 1; blkofs < sbi->blocks_per_seg; blkofs++) { + if (!f2fs_test_bit(blkofs, se->cur_valid_map)) + continue; +out: + f2fs_err(sbi, + "Current segment's next free block offset is inconsistent with bitmap, logtype:%u, segno:%u, type:%u, next_blkoff:%u, blkofs:%u", + i, curseg->segno, curseg->alloc_type, + curseg->next_blkoff, blkofs); + return -EFSCORRUPTED; + } + } + return 0; +} + /* * Update min, max modified time for cost-benefit GC algorithm */ @@ -4404,6 +4498,10 @@ int f2fs_build_segment_manager(struct f2fs_sb_info *sbi) if (err) return err; + err = sanity_check_curseg(sbi); + if (err) + return err; + init_min_max_mtime(sbi); return 0; } diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 429007b8036e..b74602813a05 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -109,7 +109,7 @@ #define START_SEGNO(segno) \ (SIT_BLOCK_OFFSET(segno) * SIT_ENTRY_PER_BLOCK) #define SIT_BLK_CNT(sbi) \ - ((MAIN_SEGS(sbi) + SIT_ENTRY_PER_BLOCK - 1) / SIT_ENTRY_PER_BLOCK) + DIV_ROUND_UP(MAIN_SEGS(sbi), SIT_ENTRY_PER_BLOCK) #define f2fs_bitmap_size(nr) \ (BITS_TO_LONGS(nr) * sizeof(unsigned long)) @@ -693,21 +693,19 @@ static inline int check_block_count(struct f2fs_sb_info *sbi, } while (cur_pos < sbi->blocks_per_seg); if (unlikely(GET_SIT_VBLOCKS(raw_sit) != valid_blocks)) { - f2fs_msg(sbi->sb, KERN_ERR, - "Mismatch valid blocks %d vs. %d", - GET_SIT_VBLOCKS(raw_sit), valid_blocks); + f2fs_err(sbi, "Mismatch valid blocks %d vs. %d", + GET_SIT_VBLOCKS(raw_sit), valid_blocks); set_sbi_flag(sbi, SBI_NEED_FSCK); - return -EINVAL; + return -EFSCORRUPTED; } /* check segment usage, and check boundary of a given segment number */ if (unlikely(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg || segno > TOTAL_SEGS(sbi) - 1)) { - f2fs_msg(sbi->sb, KERN_ERR, - "Wrong valid blocks %d or segno %u", - GET_SIT_VBLOCKS(raw_sit), segno); + f2fs_err(sbi, "Wrong valid blocks %d or segno %u", + GET_SIT_VBLOCKS(raw_sit), segno); set_sbi_flag(sbi, SBI_NEED_FSCK); - return -EINVAL; + return -EFSCORRUPTED; } return 0; } diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index ff908f108eca..cda6651bfecf 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -136,7 +136,10 @@ enum { Opt_alloc, Opt_fsync, Opt_test_dummy_encryption, - Opt_checkpoint, + Opt_checkpoint_disable, + Opt_checkpoint_disable_cap, + Opt_checkpoint_disable_cap_perc, + Opt_checkpoint_enable, Opt_err, }; @@ -195,45 +198,52 @@ static match_table_t f2fs_tokens = { {Opt_alloc, "alloc_mode=%s"}, {Opt_fsync, "fsync_mode=%s"}, {Opt_test_dummy_encryption, "test_dummy_encryption"}, - {Opt_checkpoint, "checkpoint=%s"}, + {Opt_checkpoint_disable, "checkpoint=disable"}, + {Opt_checkpoint_disable_cap, "checkpoint=disable:%u"}, + {Opt_checkpoint_disable_cap_perc, "checkpoint=disable:%u%%"}, + {Opt_checkpoint_enable, "checkpoint=enable"}, {Opt_err, NULL}, }; -void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...) +void f2fs_printk(struct f2fs_sb_info *sbi, const char *fmt, ...) { struct va_format vaf; va_list args; + int level; va_start(args, fmt); - vaf.fmt = fmt; + + level = printk_get_level(fmt); + vaf.fmt = printk_skip_level(fmt); vaf.va = &args; - printk("%sF2FS-fs (%s): %pV\n", level, sb->s_id, &vaf); + printk("%c%cF2FS-fs (%s): %pV\n", + KERN_SOH_ASCII, level, sbi->sb->s_id, &vaf); + va_end(args); } static inline void limit_reserve_root(struct f2fs_sb_info *sbi) { - block_t limit = (sbi->user_block_count << 1) / 1000; + block_t limit = min((sbi->user_block_count << 1) / 1000, + sbi->user_block_count - sbi->reserved_blocks); /* limit is 0.2% */ if (test_opt(sbi, RESERVE_ROOT) && F2FS_OPTION(sbi).root_reserved_blocks > limit) { F2FS_OPTION(sbi).root_reserved_blocks = limit; - f2fs_msg(sbi->sb, KERN_INFO, - "Reduce reserved blocks for root = %u", - F2FS_OPTION(sbi).root_reserved_blocks); + f2fs_info(sbi, "Reduce reserved blocks for root = %u", + F2FS_OPTION(sbi).root_reserved_blocks); } if (!test_opt(sbi, RESERVE_ROOT) && (!uid_eq(F2FS_OPTION(sbi).s_resuid, make_kuid(&init_user_ns, F2FS_DEF_RESUID)) || !gid_eq(F2FS_OPTION(sbi).s_resgid, make_kgid(&init_user_ns, F2FS_DEF_RESGID)))) - f2fs_msg(sbi->sb, KERN_INFO, - "Ignore s_resuid=%u, s_resgid=%u w/o reserve_root", - from_kuid_munged(&init_user_ns, - F2FS_OPTION(sbi).s_resuid), - from_kgid_munged(&init_user_ns, - F2FS_OPTION(sbi).s_resgid)); + f2fs_info(sbi, "Ignore s_resuid=%u, s_resgid=%u w/o reserve_root", + from_kuid_munged(&init_user_ns, + F2FS_OPTION(sbi).s_resuid), + from_kgid_munged(&init_user_ns, + F2FS_OPTION(sbi).s_resgid)); } static void init_once(void *foo) @@ -254,35 +264,29 @@ static int f2fs_set_qf_name(struct super_block *sb, int qtype, int ret = -EINVAL; if (sb_any_quota_loaded(sb) && !F2FS_OPTION(sbi).s_qf_names[qtype]) { - f2fs_msg(sb, KERN_ERR, - "Cannot change journaled " - "quota options when quota turned on"); + f2fs_err(sbi, "Cannot change journaled quota options when quota turned on"); return -EINVAL; } if (f2fs_sb_has_quota_ino(sbi)) { - f2fs_msg(sb, KERN_INFO, - "QUOTA feature is enabled, so ignore qf_name"); + f2fs_info(sbi, "QUOTA feature is enabled, so ignore qf_name"); return 0; } qname = match_strdup(args); if (!qname) { - f2fs_msg(sb, KERN_ERR, - "Not enough memory for storing quotafile name"); + f2fs_err(sbi, "Not enough memory for storing quotafile name"); return -ENOMEM; } if (F2FS_OPTION(sbi).s_qf_names[qtype]) { if (strcmp(F2FS_OPTION(sbi).s_qf_names[qtype], qname) == 0) ret = 0; else - f2fs_msg(sb, KERN_ERR, - "%s quota file already specified", + f2fs_err(sbi, "%s quota file already specified", QTYPE2NAME(qtype)); goto errout; } if (strchr(qname, '/')) { - f2fs_msg(sb, KERN_ERR, - "quotafile must be on filesystem root"); + f2fs_err(sbi, "quotafile must be on filesystem root"); goto errout; } F2FS_OPTION(sbi).s_qf_names[qtype] = qname; @@ -298,8 +302,7 @@ static int f2fs_clear_qf_name(struct super_block *sb, int qtype) struct f2fs_sb_info *sbi = F2FS_SB(sb); if (sb_any_quota_loaded(sb) && F2FS_OPTION(sbi).s_qf_names[qtype]) { - f2fs_msg(sb, KERN_ERR, "Cannot change journaled quota options" - " when quota turned on"); + f2fs_err(sbi, "Cannot change journaled quota options when quota turned on"); return -EINVAL; } kvfree(F2FS_OPTION(sbi).s_qf_names[qtype]); @@ -315,8 +318,7 @@ static int f2fs_check_quota_options(struct f2fs_sb_info *sbi) * to support legacy quotas in quota files. */ if (test_opt(sbi, PRJQUOTA) && !f2fs_sb_has_project_quota(sbi)) { - f2fs_msg(sbi->sb, KERN_ERR, "Project quota feature not enabled. " - "Cannot enable project quota enforcement."); + f2fs_err(sbi, "Project quota feature not enabled. Cannot enable project quota enforcement."); return -1; } if (F2FS_OPTION(sbi).s_qf_names[USRQUOTA] || @@ -336,21 +338,18 @@ static int f2fs_check_quota_options(struct f2fs_sb_info *sbi) if (test_opt(sbi, GRPQUOTA) || test_opt(sbi, USRQUOTA) || test_opt(sbi, PRJQUOTA)) { - f2fs_msg(sbi->sb, KERN_ERR, "old and new quota " - "format mixing"); + f2fs_err(sbi, "old and new quota format mixing"); return -1; } if (!F2FS_OPTION(sbi).s_jquota_fmt) { - f2fs_msg(sbi->sb, KERN_ERR, "journaled quota format " - "not specified"); + f2fs_err(sbi, "journaled quota format not specified"); return -1; } } if (f2fs_sb_has_quota_ino(sbi) && F2FS_OPTION(sbi).s_jquota_fmt) { - f2fs_msg(sbi->sb, KERN_INFO, - "QUOTA feature is enabled, so ignore jquota_fmt"); + f2fs_info(sbi, "QUOTA feature is enabled, so ignore jquota_fmt"); F2FS_OPTION(sbi).s_jquota_fmt = 0; } return 0; @@ -418,8 +417,7 @@ static int parse_options(struct super_block *sb, char *options) break; case Opt_nodiscard: if (f2fs_sb_has_blkzoned(sbi)) { - f2fs_msg(sb, KERN_WARNING, - "discard is required for zoned block devices"); + f2fs_warn(sbi, "discard is required for zoned block devices"); return -EINVAL; } clear_opt(sbi, DISCARD); @@ -451,20 +449,16 @@ static int parse_options(struct super_block *sb, char *options) break; #else case Opt_user_xattr: - f2fs_msg(sb, KERN_INFO, - "user_xattr options not supported"); + f2fs_info(sbi, "user_xattr options not supported"); break; case Opt_nouser_xattr: - f2fs_msg(sb, KERN_INFO, - "nouser_xattr options not supported"); + f2fs_info(sbi, "nouser_xattr options not supported"); break; case Opt_inline_xattr: - f2fs_msg(sb, KERN_INFO, - "inline_xattr options not supported"); + f2fs_info(sbi, "inline_xattr options not supported"); break; case Opt_noinline_xattr: - f2fs_msg(sb, KERN_INFO, - "noinline_xattr options not supported"); + f2fs_info(sbi, "noinline_xattr options not supported"); break; #endif #ifdef CONFIG_F2FS_FS_POSIX_ACL @@ -476,10 +470,10 @@ static int parse_options(struct super_block *sb, char *options) break; #else case Opt_acl: - f2fs_msg(sb, KERN_INFO, "acl options not supported"); + f2fs_info(sbi, "acl options not supported"); break; case Opt_noacl: - f2fs_msg(sb, KERN_INFO, "noacl options not supported"); + f2fs_info(sbi, "noacl options not supported"); break; #endif case Opt_active_logs: @@ -529,9 +523,8 @@ static int parse_options(struct super_block *sb, char *options) if (args->from && match_int(args, &arg)) return -EINVAL; if (test_opt(sbi, RESERVE_ROOT)) { - f2fs_msg(sb, KERN_INFO, - "Preserve previous reserve_root=%u", - F2FS_OPTION(sbi).root_reserved_blocks); + f2fs_info(sbi, "Preserve previous reserve_root=%u", + F2FS_OPTION(sbi).root_reserved_blocks); } else { F2FS_OPTION(sbi).root_reserved_blocks = arg; set_opt(sbi, RESERVE_ROOT); @@ -542,8 +535,7 @@ static int parse_options(struct super_block *sb, char *options) return -EINVAL; uid = make_kuid(current_user_ns(), arg); if (!uid_valid(uid)) { - f2fs_msg(sb, KERN_ERR, - "Invalid uid value %d", arg); + f2fs_err(sbi, "Invalid uid value %d", arg); return -EINVAL; } F2FS_OPTION(sbi).s_resuid = uid; @@ -553,8 +545,7 @@ static int parse_options(struct super_block *sb, char *options) return -EINVAL; gid = make_kgid(current_user_ns(), arg); if (!gid_valid(gid)) { - f2fs_msg(sb, KERN_ERR, - "Invalid gid value %d", arg); + f2fs_err(sbi, "Invalid gid value %d", arg); return -EINVAL; } F2FS_OPTION(sbi).s_resgid = gid; @@ -567,9 +558,7 @@ static int parse_options(struct super_block *sb, char *options) if (strlen(name) == 8 && !strncmp(name, "adaptive", 8)) { if (f2fs_sb_has_blkzoned(sbi)) { - f2fs_msg(sb, KERN_WARNING, - "adaptive mode is not allowed with " - "zoned block device feature"); + f2fs_warn(sbi, "adaptive mode is not allowed with zoned block device feature"); kvfree(name); return -EINVAL; } @@ -587,9 +576,8 @@ static int parse_options(struct super_block *sb, char *options) if (args->from && match_int(args, &arg)) return -EINVAL; if (arg <= 0 || arg > __ilog2_u32(BIO_MAX_PAGES)) { - f2fs_msg(sb, KERN_WARNING, - "Not support %d, larger than %d", - 1 << arg, BIO_MAX_PAGES); + f2fs_warn(sbi, "Not support %d, larger than %d", + 1 << arg, BIO_MAX_PAGES); return -EINVAL; } F2FS_OPTION(sbi).write_io_size_bits = arg; @@ -610,13 +598,11 @@ static int parse_options(struct super_block *sb, char *options) break; #else case Opt_fault_injection: - f2fs_msg(sb, KERN_INFO, - "fault_injection options not supported"); + f2fs_info(sbi, "fault_injection options not supported"); break; case Opt_fault_type: - f2fs_msg(sb, KERN_INFO, - "fault_type options not supported"); + f2fs_info(sbi, "fault_type options not supported"); break; #endif case Opt_lazytime: @@ -696,8 +682,7 @@ static int parse_options(struct super_block *sb, char *options) case Opt_jqfmt_vfsv0: case Opt_jqfmt_vfsv1: case Opt_noquota: - f2fs_msg(sb, KERN_INFO, - "quota operations not supported"); + f2fs_info(sbi, "quota operations not supported"); break; #endif case Opt_whint: @@ -759,39 +744,44 @@ static int parse_options(struct super_block *sb, char *options) case Opt_test_dummy_encryption: #ifdef CONFIG_F2FS_FS_ENCRYPTION if (!f2fs_sb_has_encrypt(sbi)) { - f2fs_msg(sb, KERN_ERR, "Encrypt feature is off"); + f2fs_err(sbi, "Encrypt feature is off"); return -EINVAL; } F2FS_OPTION(sbi).test_dummy_encryption = true; - f2fs_msg(sb, KERN_INFO, - "Test dummy encryption mode enabled"); + f2fs_info(sbi, "Test dummy encryption mode enabled"); #else - f2fs_msg(sb, KERN_INFO, - "Test dummy encryption mount option ignored"); + f2fs_info(sbi, "Test dummy encryption mount option ignored"); #endif break; - case Opt_checkpoint: - name = match_strdup(&args[0]); - if (!name) - return -ENOMEM; - - if (strlen(name) == 6 && - !strncmp(name, "enable", 6)) { - clear_opt(sbi, DISABLE_CHECKPOINT); - } else if (strlen(name) == 7 && - !strncmp(name, "disable", 7)) { - set_opt(sbi, DISABLE_CHECKPOINT); - } else { - kvfree(name); + case Opt_checkpoint_disable_cap_perc: + if (args->from && match_int(args, &arg)) return -EINVAL; - } - kvfree(name); + if (arg < 0 || arg > 100) + return -EINVAL; + if (arg == 100) + F2FS_OPTION(sbi).unusable_cap = + sbi->user_block_count; + else + F2FS_OPTION(sbi).unusable_cap = + (sbi->user_block_count / 100) * arg; + set_opt(sbi, DISABLE_CHECKPOINT); + break; + case Opt_checkpoint_disable_cap: + if (args->from && match_int(args, &arg)) + return -EINVAL; + F2FS_OPTION(sbi).unusable_cap = arg; + set_opt(sbi, DISABLE_CHECKPOINT); + break; + case Opt_checkpoint_disable: + set_opt(sbi, DISABLE_CHECKPOINT); + break; + case Opt_checkpoint_enable: + clear_opt(sbi, DISABLE_CHECKPOINT); break; default: - f2fs_msg(sb, KERN_ERR, - "Unrecognized mount option \"%s\" or missing value", - p); + f2fs_err(sbi, "Unrecognized mount option \"%s\" or missing value", + p); return -EINVAL; } } @@ -800,23 +790,18 @@ static int parse_options(struct super_block *sb, char *options) return -EINVAL; #else if (f2fs_sb_has_quota_ino(sbi) && !f2fs_readonly(sbi->sb)) { - f2fs_msg(sbi->sb, KERN_INFO, - "Filesystem with quota feature cannot be mounted RDWR " - "without CONFIG_QUOTA"); + f2fs_info(sbi, "Filesystem with quota feature cannot be mounted RDWR without CONFIG_QUOTA"); return -EINVAL; } if (f2fs_sb_has_project_quota(sbi) && !f2fs_readonly(sbi->sb)) { - f2fs_msg(sb, KERN_ERR, - "Filesystem with project quota feature cannot be " - "mounted RDWR without CONFIG_QUOTA"); + f2fs_err(sbi, "Filesystem with project quota feature cannot be mounted RDWR without CONFIG_QUOTA"); return -EINVAL; } #endif if (F2FS_IO_SIZE_BITS(sbi) && !test_opt(sbi, LFS)) { - f2fs_msg(sb, KERN_ERR, - "Should set mode=lfs with %uKB-sized IO", - F2FS_IO_SIZE_KB(sbi)); + f2fs_err(sbi, "Should set mode=lfs with %uKB-sized IO", + F2FS_IO_SIZE_KB(sbi)); return -EINVAL; } @@ -825,15 +810,11 @@ static int parse_options(struct super_block *sb, char *options) if (!f2fs_sb_has_extra_attr(sbi) || !f2fs_sb_has_flexible_inline_xattr(sbi)) { - f2fs_msg(sb, KERN_ERR, - "extra_attr or flexible_inline_xattr " - "feature is off"); + f2fs_err(sbi, "extra_attr or flexible_inline_xattr feature is off"); return -EINVAL; } if (!test_opt(sbi, INLINE_XATTR)) { - f2fs_msg(sb, KERN_ERR, - "inline_xattr_size option should be " - "set with inline_xattr option"); + f2fs_err(sbi, "inline_xattr_size option should be set with inline_xattr option"); return -EINVAL; } @@ -842,16 +823,14 @@ static int parse_options(struct super_block *sb, char *options) if (F2FS_OPTION(sbi).inline_xattr_size < min_size || F2FS_OPTION(sbi).inline_xattr_size > max_size) { - f2fs_msg(sb, KERN_ERR, - "inline xattr size is out of range: %d ~ %d", - min_size, max_size); + f2fs_err(sbi, "inline xattr size is out of range: %d ~ %d", + min_size, max_size); return -EINVAL; } } if (test_opt(sbi, DISABLE_CHECKPOINT) && test_opt(sbi, LFS)) { - f2fs_msg(sb, KERN_ERR, - "LFS not compatible with checkpoint=disable\n"); + f2fs_err(sbi, "LFS not compatible with checkpoint=disable\n"); return -EINVAL; } @@ -1319,6 +1298,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",disable_roll_forward"); if (test_opt(sbi, DISCARD)) seq_puts(seq, ",discard"); + else + seq_puts(seq, ",nodiscard"); if (test_opt(sbi, NOHEAP)) seq_puts(seq, ",no_heap"); else @@ -1415,8 +1396,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_printf(seq, ",alloc_mode=%s", "reuse"); if (test_opt(sbi, DISABLE_CHECKPOINT)) - seq_puts(seq, ",checkpoint=disable"); - + seq_printf(seq, ",checkpoint=disable:%u", + F2FS_OPTION(sbi).unusable_cap); if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_POSIX) seq_printf(seq, ",fsync_mode=%s", "posix"); else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) @@ -1446,6 +1427,7 @@ static void default_options(struct f2fs_sb_info *sbi) set_opt(sbi, NOHEAP); sbi->sb->s_flags |= MS_LAZYTIME; clear_opt(sbi, DISABLE_CHECKPOINT); + F2FS_OPTION(sbi).unusable_cap = 0; set_opt(sbi, FLUSH_MERGE); set_opt(sbi, DISCARD); if (f2fs_sb_has_blkzoned(sbi)) @@ -1473,10 +1455,10 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) struct cp_control cpc; int err = 0; int ret; + block_t unusable; if (s_flags & MS_RDONLY) { - f2fs_msg(sbi->sb, KERN_ERR, - "checkpoint=disable on readonly fs"); + f2fs_err(sbi, "checkpoint=disable on readonly fs"); return -EINVAL; } sbi->sb->s_flags |= MS_ACTIVE; @@ -1500,7 +1482,8 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) goto restore_flag; } - if (f2fs_disable_cp_again(sbi)) { + unusable = f2fs_get_unusable_blocks(sbi); + if (f2fs_disable_cp_again(sbi, unusable)) { err = -EAGAIN; goto restore_flag; } @@ -1513,7 +1496,7 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) goto out_unlock; spin_lock(&sbi->stat_lock); - sbi->unusable_block_count = 0; + sbi->unusable_block_count = unusable; spin_unlock(&sbi->stat_lock); out_unlock: @@ -1578,8 +1561,8 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) /* recover superblocks we couldn't write due to previous RO mount */ if (!(*flags & MS_RDONLY) && is_sbi_flag_set(sbi, SBI_NEED_SB_WRITE)) { err = f2fs_commit_super(sbi, false); - f2fs_msg(sb, KERN_INFO, - "Try to recover all the superblocks, ret: %d", err); + f2fs_info(sbi, "Try to recover all the superblocks, ret: %d", + err); if (!err) clear_sbi_flag(sbi, SBI_NEED_SB_WRITE); } @@ -1620,15 +1603,13 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) /* disallow enable/disable extent_cache dynamically */ if (no_extent_cache == !!test_opt(sbi, EXTENT_CACHE)) { err = -EINVAL; - f2fs_msg(sbi->sb, KERN_WARNING, - "switch extent_cache option is not allowed"); + f2fs_warn(sbi, "switch extent_cache option is not allowed"); goto restore_opts; } if ((*flags & MS_RDONLY) && test_opt(sbi, DISABLE_CHECKPOINT)) { err = -EINVAL; - f2fs_msg(sbi->sb, KERN_WARNING, - "disabling checkpoint not compatible with read-only"); + f2fs_warn(sbi, "disabling checkpoint not compatible with read-only"); goto restore_opts; } @@ -1698,8 +1679,7 @@ skip: restore_gc: if (need_restart_gc) { if (f2fs_start_gc_thread(sbi)) - f2fs_msg(sbi->sb, KERN_WARNING, - "background gc thread has stopped"); + f2fs_warn(sbi, "background gc thread has stopped"); } else if (need_stop_gc) { f2fs_stop_gc_thread(sbi); } @@ -1838,8 +1818,7 @@ static qsize_t *f2fs_get_reserved_space(struct inode *inode) static int f2fs_quota_on_mount(struct f2fs_sb_info *sbi, int type) { if (is_set_ckpt_flags(sbi, CP_QUOTA_NEED_FSCK_FLAG)) { - f2fs_msg(sbi->sb, KERN_ERR, - "quota sysfile may be corrupted, skip loading it"); + f2fs_err(sbi, "quota sysfile may be corrupted, skip loading it"); return 0; } @@ -1855,8 +1834,7 @@ int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly) if (f2fs_sb_has_quota_ino(sbi) && rdonly) { err = f2fs_enable_quotas(sbi->sb); if (err) { - f2fs_msg(sbi->sb, KERN_ERR, - "Cannot turn on quota_ino: %d", err); + f2fs_err(sbi, "Cannot turn on quota_ino: %d", err); return 0; } return 1; @@ -1869,8 +1847,8 @@ int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly) enabled = 1; continue; } - f2fs_msg(sbi->sb, KERN_ERR, - "Cannot turn on quotas: %d on %d", err, i); + f2fs_err(sbi, "Cannot turn on quotas: %d on %d", + err, i); } } return enabled; @@ -1891,8 +1869,7 @@ static int f2fs_quota_enable(struct super_block *sb, int type, int format_id, qf_inode = f2fs_iget(sb, qf_inum); if (IS_ERR(qf_inode)) { - f2fs_msg(sb, KERN_ERR, - "Bad quota inode %u:%lu", type, qf_inum); + f2fs_err(F2FS_SB(sb), "Bad quota inode %u:%lu", type, qf_inum); return PTR_ERR(qf_inode); } @@ -1905,17 +1882,17 @@ static int f2fs_quota_enable(struct super_block *sb, int type, int format_id, static int f2fs_enable_quotas(struct super_block *sb) { + struct f2fs_sb_info *sbi = F2FS_SB(sb); int type, err = 0; unsigned long qf_inum; bool quota_mopt[MAXQUOTAS] = { - test_opt(F2FS_SB(sb), USRQUOTA), - test_opt(F2FS_SB(sb), GRPQUOTA), - test_opt(F2FS_SB(sb), PRJQUOTA), + test_opt(sbi, USRQUOTA), + test_opt(sbi, GRPQUOTA), + test_opt(sbi, PRJQUOTA), }; if (is_set_ckpt_flags(F2FS_SB(sb), CP_QUOTA_NEED_FSCK_FLAG)) { - f2fs_msg(sb, KERN_ERR, - "quota file may be corrupted, skip loading it"); + f2fs_err(sbi, "quota file may be corrupted, skip loading it"); return 0; } @@ -1928,10 +1905,8 @@ static int f2fs_enable_quotas(struct super_block *sb) DQUOT_USAGE_ENABLED | (quota_mopt[type] ? DQUOT_LIMITS_ENABLED : 0)); if (err) { - f2fs_msg(sb, KERN_ERR, - "Failed to enable quota tracking " - "(type=%d, err=%d). Please run " - "fsck to fix.", type, err); + f2fs_err(sbi, "Failed to enable quota tracking (type=%d, err=%d). Please run fsck to fix.", + type, err); for (type--; type >= 0; type--) dquot_quota_off(sb, type); set_sbi_flag(F2FS_SB(sb), @@ -1950,6 +1925,18 @@ int f2fs_quota_sync(struct super_block *sb, int type) int cnt; int ret; + /* + * do_quotactl + * f2fs_quota_sync + * down_read(quota_sem) + * dquot_writeback_dquots() + * f2fs_dquot_commit + * block_operation + * down_read(quota_sem) + */ + f2fs_lock_op(sbi); + + down_read(&sbi->quota_sem); ret = dquot_writeback_dquots(sb, type); if (ret) goto out; @@ -1987,6 +1974,8 @@ int f2fs_quota_sync(struct super_block *sb, int type) out: if (ret) set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); + up_read(&sbi->quota_sem); + f2fs_unlock_op(sbi); return ret; } @@ -2051,10 +2040,8 @@ void f2fs_quota_off_umount(struct super_block *sb) if (err) { int ret = dquot_quota_off(sb, type); - f2fs_msg(sb, KERN_ERR, - "Fail to turn off disk quota " - "(type: %d, err: %d, ret:%d), Please " - "run fsck to fix it.", type, err, ret); + f2fs_err(F2FS_SB(sb), "Fail to turn off disk quota (type: %d, err: %d, ret:%d), Please run fsck to fix it.", + type, err, ret); set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); } } @@ -2080,32 +2067,40 @@ static void f2fs_truncate_quota_inode_pages(struct super_block *sb) static int f2fs_dquot_commit(struct dquot *dquot) { + struct f2fs_sb_info *sbi = F2FS_SB(dquot->dq_sb); int ret; + down_read(&sbi->quota_sem); ret = dquot_commit(dquot); if (ret < 0) - set_sbi_flag(F2FS_SB(dquot->dq_sb), SBI_QUOTA_NEED_REPAIR); + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + up_read(&sbi->quota_sem); return ret; } static int f2fs_dquot_acquire(struct dquot *dquot) { + struct f2fs_sb_info *sbi = F2FS_SB(dquot->dq_sb); int ret; + down_read(&sbi->quota_sem); ret = dquot_acquire(dquot); if (ret < 0) - set_sbi_flag(F2FS_SB(dquot->dq_sb), SBI_QUOTA_NEED_REPAIR); - + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + up_read(&sbi->quota_sem); return ret; } static int f2fs_dquot_release(struct dquot *dquot) { + struct f2fs_sb_info *sbi = F2FS_SB(dquot->dq_sb); int ret; + down_read(&sbi->quota_sem); ret = dquot_release(dquot); if (ret < 0) - set_sbi_flag(F2FS_SB(dquot->dq_sb), SBI_QUOTA_NEED_REPAIR); + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + up_read(&sbi->quota_sem); return ret; } @@ -2115,22 +2110,27 @@ static int f2fs_dquot_mark_dquot_dirty(struct dquot *dquot) struct f2fs_sb_info *sbi = F2FS_SB(sb); int ret; + down_read(&sbi->quota_sem); ret = dquot_mark_dquot_dirty(dquot); /* if we are using journalled quota */ if (is_journalled_quota(sbi)) set_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH); + up_read(&sbi->quota_sem); return ret; } static int f2fs_dquot_commit_info(struct super_block *sb, int type) { + struct f2fs_sb_info *sbi = F2FS_SB(sb); int ret; + down_read(&sbi->quota_sem); ret = dquot_commit_info(sb, type); if (ret < 0) - set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + up_read(&sbi->quota_sem); return ret; } @@ -2350,55 +2350,49 @@ static inline bool sanity_check_area_boundary(struct f2fs_sb_info *sbi, (segment_count << log_blocks_per_seg); if (segment0_blkaddr != cp_blkaddr) { - f2fs_msg(sb, KERN_INFO, - "Mismatch start address, segment0(%u) cp_blkaddr(%u)", - segment0_blkaddr, cp_blkaddr); + f2fs_info(sbi, "Mismatch start address, segment0(%u) cp_blkaddr(%u)", + segment0_blkaddr, cp_blkaddr); return true; } if (cp_blkaddr + (segment_count_ckpt << log_blocks_per_seg) != sit_blkaddr) { - f2fs_msg(sb, KERN_INFO, - "Wrong CP boundary, start(%u) end(%u) blocks(%u)", - cp_blkaddr, sit_blkaddr, - segment_count_ckpt << log_blocks_per_seg); + f2fs_info(sbi, "Wrong CP boundary, start(%u) end(%u) blocks(%u)", + cp_blkaddr, sit_blkaddr, + segment_count_ckpt << log_blocks_per_seg); return true; } if (sit_blkaddr + (segment_count_sit << log_blocks_per_seg) != nat_blkaddr) { - f2fs_msg(sb, KERN_INFO, - "Wrong SIT boundary, start(%u) end(%u) blocks(%u)", - sit_blkaddr, nat_blkaddr, - segment_count_sit << log_blocks_per_seg); + f2fs_info(sbi, "Wrong SIT boundary, start(%u) end(%u) blocks(%u)", + sit_blkaddr, nat_blkaddr, + segment_count_sit << log_blocks_per_seg); return true; } if (nat_blkaddr + (segment_count_nat << log_blocks_per_seg) != ssa_blkaddr) { - f2fs_msg(sb, KERN_INFO, - "Wrong NAT boundary, start(%u) end(%u) blocks(%u)", - nat_blkaddr, ssa_blkaddr, - segment_count_nat << log_blocks_per_seg); + f2fs_info(sbi, "Wrong NAT boundary, start(%u) end(%u) blocks(%u)", + nat_blkaddr, ssa_blkaddr, + segment_count_nat << log_blocks_per_seg); return true; } if (ssa_blkaddr + (segment_count_ssa << log_blocks_per_seg) != main_blkaddr) { - f2fs_msg(sb, KERN_INFO, - "Wrong SSA boundary, start(%u) end(%u) blocks(%u)", - ssa_blkaddr, main_blkaddr, - segment_count_ssa << log_blocks_per_seg); + f2fs_info(sbi, "Wrong SSA boundary, start(%u) end(%u) blocks(%u)", + ssa_blkaddr, main_blkaddr, + segment_count_ssa << log_blocks_per_seg); return true; } if (main_end_blkaddr > seg_end_blkaddr) { - f2fs_msg(sb, KERN_INFO, - "Wrong MAIN_AREA boundary, start(%u) end(%u) block(%u)", - main_blkaddr, - segment0_blkaddr + - (segment_count << log_blocks_per_seg), - segment_count_main << log_blocks_per_seg); + f2fs_info(sbi, "Wrong MAIN_AREA boundary, start(%u) end(%u) block(%u)", + main_blkaddr, + segment0_blkaddr + + (segment_count << log_blocks_per_seg), + segment_count_main << log_blocks_per_seg); return true; } else if (main_end_blkaddr < seg_end_blkaddr) { int err = 0; @@ -2415,12 +2409,11 @@ static inline bool sanity_check_area_boundary(struct f2fs_sb_info *sbi, err = __f2fs_commit_super(bh, NULL); res = err ? "failed" : "done"; } - f2fs_msg(sb, KERN_INFO, - "Fix alignment : %s, start(%u) end(%u) block(%u)", - res, main_blkaddr, - segment0_blkaddr + - (segment_count << log_blocks_per_seg), - segment_count_main << log_blocks_per_seg); + f2fs_info(sbi, "Fix alignment : %s, start(%u) end(%u) block(%u)", + res, main_blkaddr, + segment0_blkaddr + + (segment_count << log_blocks_per_seg), + segment_count_main << log_blocks_per_seg); if (err) return true; } @@ -2434,59 +2427,52 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, block_t total_sections, blocks_per_seg; struct f2fs_super_block *raw_super = (struct f2fs_super_block *) (bh->b_data + F2FS_SUPER_OFFSET); - struct super_block *sb = sbi->sb; unsigned int blocksize; size_t crc_offset = 0; __u32 crc = 0; + if (le32_to_cpu(raw_super->magic) != F2FS_SUPER_MAGIC) { + f2fs_info(sbi, "Magic Mismatch, valid(0x%x) - read(0x%x)", + F2FS_SUPER_MAGIC, le32_to_cpu(raw_super->magic)); + return -EINVAL; + } + /* Check checksum_offset and crc in superblock */ if (__F2FS_HAS_FEATURE(raw_super, F2FS_FEATURE_SB_CHKSUM)) { crc_offset = le32_to_cpu(raw_super->checksum_offset); if (crc_offset != offsetof(struct f2fs_super_block, crc)) { - f2fs_msg(sb, KERN_INFO, - "Invalid SB checksum offset: %zu", - crc_offset); - return 1; + f2fs_info(sbi, "Invalid SB checksum offset: %zu", + crc_offset); + return -EFSCORRUPTED; } crc = le32_to_cpu(raw_super->crc); if (!f2fs_crc_valid(sbi, crc, raw_super, crc_offset)) { - f2fs_msg(sb, KERN_INFO, - "Invalid SB checksum value: %u", crc); - return 1; + f2fs_info(sbi, "Invalid SB checksum value: %u", crc); + return -EFSCORRUPTED; } } - if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) { - f2fs_msg(sb, KERN_INFO, - "Magic Mismatch, valid(0x%x) - read(0x%x)", - F2FS_SUPER_MAGIC, le32_to_cpu(raw_super->magic)); - return 1; - } - /* Currently, support only 4KB page cache size */ if (F2FS_BLKSIZE != PAGE_SIZE) { - f2fs_msg(sb, KERN_INFO, - "Invalid page_cache_size (%lu), supports only 4KB", - PAGE_SIZE); - return 1; + f2fs_info(sbi, "Invalid page_cache_size (%lu), supports only 4KB", + PAGE_SIZE); + return -EFSCORRUPTED; } /* Currently, support only 4KB block size */ blocksize = 1 << le32_to_cpu(raw_super->log_blocksize); if (blocksize != F2FS_BLKSIZE) { - f2fs_msg(sb, KERN_INFO, - "Invalid blocksize (%u), supports only 4KB", - blocksize); - return 1; + f2fs_info(sbi, "Invalid blocksize (%u), supports only 4KB", + blocksize); + return -EFSCORRUPTED; } /* check log blocks per segment */ if (le32_to_cpu(raw_super->log_blocks_per_seg) != 9) { - f2fs_msg(sb, KERN_INFO, - "Invalid log blocks per segment (%u)", - le32_to_cpu(raw_super->log_blocks_per_seg)); - return 1; + f2fs_info(sbi, "Invalid log blocks per segment (%u)", + le32_to_cpu(raw_super->log_blocks_per_seg)); + return -EFSCORRUPTED; } /* Currently, support 512/1024/2048/4096 bytes sector size */ @@ -2494,18 +2480,17 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, F2FS_MAX_LOG_SECTOR_SIZE || le32_to_cpu(raw_super->log_sectorsize) < F2FS_MIN_LOG_SECTOR_SIZE) { - f2fs_msg(sb, KERN_INFO, "Invalid log sectorsize (%u)", - le32_to_cpu(raw_super->log_sectorsize)); - return 1; + f2fs_info(sbi, "Invalid log sectorsize (%u)", + le32_to_cpu(raw_super->log_sectorsize)); + return -EFSCORRUPTED; } if (le32_to_cpu(raw_super->log_sectors_per_block) + le32_to_cpu(raw_super->log_sectorsize) != F2FS_MAX_LOG_SECTOR_SIZE) { - f2fs_msg(sb, KERN_INFO, - "Invalid log sectors per block(%u) log sectorsize(%u)", - le32_to_cpu(raw_super->log_sectors_per_block), - le32_to_cpu(raw_super->log_sectorsize)); - return 1; + f2fs_info(sbi, "Invalid log sectors per block(%u) log sectorsize(%u)", + le32_to_cpu(raw_super->log_sectors_per_block), + le32_to_cpu(raw_super->log_sectorsize)); + return -EFSCORRUPTED; } segment_count = le32_to_cpu(raw_super->segment_count); @@ -2518,77 +2503,68 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, if (segment_count > F2FS_MAX_SEGMENT || segment_count < F2FS_MIN_SEGMENTS) { - f2fs_msg(sb, KERN_INFO, - "Invalid segment count (%u)", - segment_count); - return 1; + f2fs_info(sbi, "Invalid segment count (%u)", segment_count); + return -EFSCORRUPTED; } if (total_sections > segment_count || total_sections < F2FS_MIN_SEGMENTS || segs_per_sec > segment_count || !segs_per_sec) { - f2fs_msg(sb, KERN_INFO, - "Invalid segment/section count (%u, %u x %u)", - segment_count, total_sections, segs_per_sec); - return 1; + f2fs_info(sbi, "Invalid segment/section count (%u, %u x %u)", + segment_count, total_sections, segs_per_sec); + return -EFSCORRUPTED; } if ((segment_count / segs_per_sec) < total_sections) { - f2fs_msg(sb, KERN_INFO, - "Small segment_count (%u < %u * %u)", - segment_count, segs_per_sec, total_sections); - return 1; + f2fs_info(sbi, "Small segment_count (%u < %u * %u)", + segment_count, segs_per_sec, total_sections); + return -EFSCORRUPTED; } if (segment_count > (le64_to_cpu(raw_super->block_count) >> 9)) { - f2fs_msg(sb, KERN_INFO, - "Wrong segment_count / block_count (%u > %llu)", - segment_count, le64_to_cpu(raw_super->block_count)); - return 1; + f2fs_info(sbi, "Wrong segment_count / block_count (%u > %llu)", + segment_count, le64_to_cpu(raw_super->block_count)); + return -EFSCORRUPTED; } if (secs_per_zone > total_sections || !secs_per_zone) { - f2fs_msg(sb, KERN_INFO, - "Wrong secs_per_zone / total_sections (%u, %u)", - secs_per_zone, total_sections); - return 1; + f2fs_info(sbi, "Wrong secs_per_zone / total_sections (%u, %u)", + secs_per_zone, total_sections); + return -EFSCORRUPTED; } if (le32_to_cpu(raw_super->extension_count) > F2FS_MAX_EXTENSION || raw_super->hot_ext_count > F2FS_MAX_EXTENSION || (le32_to_cpu(raw_super->extension_count) + raw_super->hot_ext_count) > F2FS_MAX_EXTENSION) { - f2fs_msg(sb, KERN_INFO, - "Corrupted extension count (%u + %u > %u)", - le32_to_cpu(raw_super->extension_count), - raw_super->hot_ext_count, - F2FS_MAX_EXTENSION); - return 1; + f2fs_info(sbi, "Corrupted extension count (%u + %u > %u)", + le32_to_cpu(raw_super->extension_count), + raw_super->hot_ext_count, + F2FS_MAX_EXTENSION); + return -EFSCORRUPTED; } if (le32_to_cpu(raw_super->cp_payload) > (blocks_per_seg - F2FS_CP_PACKS)) { - f2fs_msg(sb, KERN_INFO, - "Insane cp_payload (%u > %u)", - le32_to_cpu(raw_super->cp_payload), - blocks_per_seg - F2FS_CP_PACKS); - return 1; + f2fs_info(sbi, "Insane cp_payload (%u > %u)", + le32_to_cpu(raw_super->cp_payload), + blocks_per_seg - F2FS_CP_PACKS); + return -EFSCORRUPTED; } /* check reserved ino info */ if (le32_to_cpu(raw_super->node_ino) != 1 || le32_to_cpu(raw_super->meta_ino) != 2 || le32_to_cpu(raw_super->root_ino) != 3) { - f2fs_msg(sb, KERN_INFO, - "Invalid Fs Meta Ino: node(%u) meta(%u) root(%u)", - le32_to_cpu(raw_super->node_ino), - le32_to_cpu(raw_super->meta_ino), - le32_to_cpu(raw_super->root_ino)); - return 1; + f2fs_info(sbi, "Invalid Fs Meta Ino: node(%u) meta(%u) root(%u)", + le32_to_cpu(raw_super->node_ino), + le32_to_cpu(raw_super->meta_ino), + le32_to_cpu(raw_super->root_ino)); + return -EFSCORRUPTED; } /* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */ if (sanity_check_area_boundary(sbi, bh)) - return 1; + return -EFSCORRUPTED; return 0; } @@ -2626,8 +2602,7 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) if (unlikely(fsmeta < F2FS_MIN_SEGMENTS || ovp_segments == 0 || reserved_segments == 0)) { - f2fs_msg(sbi->sb, KERN_ERR, - "Wrong layout: check mkfs.f2fs version"); + f2fs_err(sbi, "Wrong layout: check mkfs.f2fs version"); return 1; } @@ -2636,16 +2611,15 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg); if (!user_block_count || user_block_count >= segment_count_main << log_blocks_per_seg) { - f2fs_msg(sbi->sb, KERN_ERR, - "Wrong user_block_count: %u", user_block_count); + f2fs_err(sbi, "Wrong user_block_count: %u", + user_block_count); return 1; } valid_user_blocks = le64_to_cpu(ckpt->valid_block_count); if (valid_user_blocks > user_block_count) { - f2fs_msg(sbi->sb, KERN_ERR, - "Wrong valid_user_blocks: %u, user_block_count: %u", - valid_user_blocks, user_block_count); + f2fs_err(sbi, "Wrong valid_user_blocks: %u, user_block_count: %u", + valid_user_blocks, user_block_count); return 1; } @@ -2653,9 +2627,8 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) avail_node_count = sbi->total_node_count - sbi->nquota_files - F2FS_RESERVED_NODE_NUM; if (valid_node_count > avail_node_count) { - f2fs_msg(sbi->sb, KERN_ERR, - "Wrong valid_node_count: %u, avail_node_count: %u", - valid_node_count, avail_node_count); + f2fs_err(sbi, "Wrong valid_node_count: %u, avail_node_count: %u", + valid_node_count, avail_node_count); return 1; } @@ -2669,10 +2642,9 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) for (j = i + 1; j < NR_CURSEG_NODE_TYPE; j++) { if (le32_to_cpu(ckpt->cur_node_segno[i]) == le32_to_cpu(ckpt->cur_node_segno[j])) { - f2fs_msg(sbi->sb, KERN_ERR, - "Node segment (%u, %u) has the same " - "segno: %u", i, j, - le32_to_cpu(ckpt->cur_node_segno[i])); + f2fs_err(sbi, "Node segment (%u, %u) has the same segno: %u", + i, j, + le32_to_cpu(ckpt->cur_node_segno[i])); return 1; } } @@ -2684,10 +2656,9 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) for (j = i + 1; j < NR_CURSEG_DATA_TYPE; j++) { if (le32_to_cpu(ckpt->cur_data_segno[i]) == le32_to_cpu(ckpt->cur_data_segno[j])) { - f2fs_msg(sbi->sb, KERN_ERR, - "Data segment (%u, %u) has the same " - "segno: %u", i, j, - le32_to_cpu(ckpt->cur_data_segno[i])); + f2fs_err(sbi, "Data segment (%u, %u) has the same segno: %u", + i, j, + le32_to_cpu(ckpt->cur_data_segno[i])); return 1; } } @@ -2696,10 +2667,9 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) for (j = i; j < NR_CURSEG_DATA_TYPE; j++) { if (le32_to_cpu(ckpt->cur_node_segno[i]) == le32_to_cpu(ckpt->cur_data_segno[j])) { - f2fs_msg(sbi->sb, KERN_ERR, - "Data segment (%u) and Data segment (%u)" - " has the same segno: %u", i, j, - le32_to_cpu(ckpt->cur_node_segno[i])); + f2fs_err(sbi, "Data segment (%u) and Data segment (%u) has the same segno: %u", + i, j, + le32_to_cpu(ckpt->cur_node_segno[i])); return 1; } } @@ -2710,9 +2680,8 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) if (sit_bitmap_size != ((sit_segs / 2) << log_blocks_per_seg) / 8 || nat_bitmap_size != ((nat_segs / 2) << log_blocks_per_seg) / 8) { - f2fs_msg(sbi->sb, KERN_ERR, - "Wrong bitmap size: sit: %u, nat:%u", - sit_bitmap_size, nat_bitmap_size); + f2fs_err(sbi, "Wrong bitmap size: sit: %u, nat:%u", + sit_bitmap_size, nat_bitmap_size); return 1; } @@ -2721,14 +2690,22 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) if (cp_pack_start_sum < cp_payload + 1 || cp_pack_start_sum > blocks_per_seg - 1 - NR_CURSEG_TYPE) { - f2fs_msg(sbi->sb, KERN_ERR, - "Wrong cp_pack_start_sum: %u", - cp_pack_start_sum); + f2fs_err(sbi, "Wrong cp_pack_start_sum: %u", + cp_pack_start_sum); + return 1; + } + + if (__is_set_ckpt_flags(ckpt, CP_LARGE_NAT_BITMAP_FLAG) && + le32_to_cpu(ckpt->checksum_offset) != CP_MIN_CHKSUM_OFFSET) { + f2fs_warn(sbi, "using deprecated layout of large_nat_bitmap, " + "please run fsck v1.13.0 or higher to repair, chksum_offset: %u, " + "fixed with patch: \"f2fs-tools: relocate chksum_offset for large_nat_bitmap feature\"", + le32_to_cpu(ckpt->checksum_offset)); return 1; } if (unlikely(f2fs_cp_error(sbi))) { - f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck"); + f2fs_err(sbi, "A bug case: need to run fsck"); return 1; } return 0; @@ -2897,18 +2874,17 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi, for (block = 0; block < 2; block++) { bh = sb_bread(sb, block); if (!bh) { - f2fs_msg(sb, KERN_ERR, "Unable to read %dth superblock", - block + 1); + f2fs_err(sbi, "Unable to read %dth superblock", + block + 1); err = -EIO; continue; } /* sanity checking of raw super */ - if (sanity_check_raw_super(sbi, bh)) { - f2fs_msg(sb, KERN_ERR, - "Can't find valid F2FS filesystem in %dth superblock", - block + 1); - err = -EINVAL; + err = sanity_check_raw_super(sbi, bh); + if (err) { + f2fs_err(sbi, "Can't find valid F2FS filesystem in %dth superblock", + block + 1); brelse(bh); continue; } @@ -3041,36 +3017,32 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) #ifdef CONFIG_BLK_DEV_ZONED if (bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HM && !f2fs_sb_has_blkzoned(sbi)) { - f2fs_msg(sbi->sb, KERN_ERR, - "Zoned block device feature not enabled\n"); + f2fs_err(sbi, "Zoned block device feature not enabled\n"); return -EINVAL; } if (bdev_zoned_model(FDEV(i).bdev) != BLK_ZONED_NONE) { if (init_blkz_info(sbi, i)) { - f2fs_msg(sbi->sb, KERN_ERR, - "Failed to initialize F2FS blkzone information"); + f2fs_err(sbi, "Failed to initialize F2FS blkzone information"); return -EINVAL; } if (max_devices == 1) break; - f2fs_msg(sbi->sb, KERN_INFO, - "Mount Device [%2d]: %20s, %8u, %8x - %8x (zone: %s)", - i, FDEV(i).path, - FDEV(i).total_segments, - FDEV(i).start_blk, FDEV(i).end_blk, - bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HA ? - "Host-aware" : "Host-managed"); + f2fs_info(sbi, "Mount Device [%2d]: %20s, %8u, %8x - %8x (zone: %s)", + i, FDEV(i).path, + FDEV(i).total_segments, + FDEV(i).start_blk, FDEV(i).end_blk, + bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HA ? + "Host-aware" : "Host-managed"); continue; } #endif - f2fs_msg(sbi->sb, KERN_INFO, - "Mount Device [%2d]: %20s, %8u, %8x - %8x", - i, FDEV(i).path, - FDEV(i).total_segments, - FDEV(i).start_blk, FDEV(i).end_blk); - } - f2fs_msg(sbi->sb, KERN_INFO, - "IO Block Size: %8d KB", F2FS_IO_SIZE_KB(sbi)); + f2fs_info(sbi, "Mount Device [%2d]: %20s, %8u, %8x - %8x", + i, FDEV(i).path, + FDEV(i).total_segments, + FDEV(i).start_blk, FDEV(i).end_blk); + } + f2fs_info(sbi, + "IO Block Size: %8d KB", F2FS_IO_SIZE_KB(sbi)); return 0; } @@ -3116,7 +3088,7 @@ try_onemore: /* Load the checksum driver */ sbi->s_chksum_driver = crypto_alloc_shash("crc32", 0, 0); if (IS_ERR(sbi->s_chksum_driver)) { - f2fs_msg(sb, KERN_ERR, "Cannot load crc32 driver."); + f2fs_err(sbi, "Cannot load crc32 driver."); err = PTR_ERR(sbi->s_chksum_driver); sbi->s_chksum_driver = NULL; goto free_sbi; @@ -3124,7 +3096,7 @@ try_onemore: /* set a block size */ if (unlikely(!sb_set_blocksize(sb, F2FS_BLKSIZE))) { - f2fs_msg(sb, KERN_ERR, "unable to set blocksize"); + f2fs_err(sbi, "unable to set blocksize"); goto free_sbi; } @@ -3148,8 +3120,7 @@ try_onemore: */ #ifndef CONFIG_BLK_DEV_ZONED if (f2fs_sb_has_blkzoned(sbi)) { - f2fs_msg(sb, KERN_ERR, - "Zoned block device support is not enabled"); + f2fs_err(sbi, "Zoned block device support is not enabled"); err = -EOPNOTSUPP; goto free_sb_buf; } @@ -3202,6 +3173,7 @@ try_onemore: mutex_init(&sbi->gc_mutex); mutex_init(&sbi->writepages); mutex_init(&sbi->cp_mutex); + mutex_init(&sbi->resize_mutex); init_rwsem(&sbi->node_write); init_rwsem(&sbi->node_change); @@ -3237,6 +3209,7 @@ try_onemore: } init_rwsem(&sbi->cp_rwsem); + init_rwsem(&sbi->quota_sem); init_waitqueue_head(&sbi->cp_wait); init_sb_info(sbi); @@ -3256,14 +3229,14 @@ try_onemore: /* get an inode for meta space */ sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi)); if (IS_ERR(sbi->meta_inode)) { - f2fs_msg(sb, KERN_ERR, "Failed to read F2FS meta data inode"); + f2fs_err(sbi, "Failed to read F2FS meta data inode"); err = PTR_ERR(sbi->meta_inode); goto free_io_dummy; } err = f2fs_get_valid_checkpoint(sbi); if (err) { - f2fs_msg(sb, KERN_ERR, "Failed to get valid F2FS checkpoint"); + f2fs_err(sbi, "Failed to get valid F2FS checkpoint"); goto free_meta_inode; } @@ -3274,10 +3247,13 @@ try_onemore: sbi->interval_time[DISABLE_TIME] = DEF_DISABLE_QUICK_INTERVAL; } + if (__is_set_ckpt_flags(F2FS_CKPT(sbi), CP_FSCK_FLAG)) + set_sbi_flag(sbi, SBI_NEED_FSCK); + /* Initialize device list */ err = f2fs_scan_devices(sbi); if (err) { - f2fs_msg(sb, KERN_ERR, "Failed to find devices"); + f2fs_err(sbi, "Failed to find devices"); goto free_devices; } @@ -3297,6 +3273,7 @@ try_onemore: INIT_LIST_HEAD(&sbi->inode_list[i]); spin_lock_init(&sbi->inode_lock[i]); } + mutex_init(&sbi->flush_lock); f2fs_init_extent_cache_info(sbi); @@ -3307,14 +3284,14 @@ try_onemore: /* setup f2fs internal modules */ err = f2fs_build_segment_manager(sbi); if (err) { - f2fs_msg(sb, KERN_ERR, - "Failed to initialize F2FS segment manager"); + f2fs_err(sbi, "Failed to initialize F2FS segment manager (%d)", + err); goto free_sm; } err = f2fs_build_node_manager(sbi); if (err) { - f2fs_msg(sb, KERN_ERR, - "Failed to initialize F2FS node manager"); + f2fs_err(sbi, "Failed to initialize F2FS node manager (%d)", + err); goto free_nm; } @@ -3338,7 +3315,7 @@ try_onemore: /* get an inode for node space */ sbi->node_inode = f2fs_iget(sb, F2FS_NODE_INO(sbi)); if (IS_ERR(sbi->node_inode)) { - f2fs_msg(sb, KERN_ERR, "Failed to read node inode"); + f2fs_err(sbi, "Failed to read node inode"); err = PTR_ERR(sbi->node_inode); goto free_stats; } @@ -3346,7 +3323,7 @@ try_onemore: /* read root inode and dentry */ root = f2fs_iget(sb, F2FS_ROOT_INO(sbi)); if (IS_ERR(root)) { - f2fs_msg(sb, KERN_ERR, "Failed to read root inode"); + f2fs_err(sbi, "Failed to read root inode"); err = PTR_ERR(root); goto free_node_inode; } @@ -3372,8 +3349,7 @@ try_onemore: if (f2fs_sb_has_quota_ino(sbi) && !f2fs_readonly(sb)) { err = f2fs_enable_quotas(sb); if (err) - f2fs_msg(sb, KERN_ERR, - "Cannot turn on quotas: error %d", err); + f2fs_err(sbi, "Cannot turn on quotas: error %d", err); } #endif /* if there are nt orphan nodes free them */ @@ -3393,13 +3369,10 @@ try_onemore: if (f2fs_hw_is_readonly(sbi)) { if (!is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) { err = -EROFS; - f2fs_msg(sb, KERN_ERR, - "Need to recover fsync data, but " - "write access unavailable"); + f2fs_err(sbi, "Need to recover fsync data, but write access unavailable"); goto free_meta; } - f2fs_msg(sbi->sb, KERN_INFO, "write access " - "unavailable, skipping recovery"); + f2fs_info(sbi, "write access unavailable, skipping recovery"); goto reset_checkpoint; } @@ -3414,8 +3387,8 @@ try_onemore: if (err != -ENOMEM) skip_recovery = true; need_fsck = true; - f2fs_msg(sb, KERN_ERR, - "Cannot recover all fsync data errno=%d", err); + f2fs_err(sbi, "Cannot recover all fsync data errno=%d", + err); goto free_meta; } } else { @@ -3423,8 +3396,7 @@ try_onemore: if (!f2fs_readonly(sb) && err > 0) { err = -EINVAL; - f2fs_msg(sb, KERN_ERR, - "Need to recover fsync data"); + f2fs_err(sbi, "Need to recover fsync data"); goto free_meta; } } @@ -3455,17 +3427,16 @@ reset_checkpoint: /* recover broken superblock */ if (recovery) { err = f2fs_commit_super(sbi, true); - f2fs_msg(sb, KERN_INFO, - "Try to recover %dth superblock, ret: %d", - sbi->valid_super_block ? 1 : 2, err); + f2fs_info(sbi, "Try to recover %dth superblock, ret: %d", + sbi->valid_super_block ? 1 : 2, err); } f2fs_join_shrinker(sbi); f2fs_tuning_parameters(sbi); - f2fs_msg(sbi->sb, KERN_NOTICE, "Mounted with checkpoint version = %llx", - cur_cp_version(F2FS_CKPT(sbi))); + f2fs_notice(sbi, "Mounted with checkpoint version = %llx", + cur_cp_version(F2FS_CKPT(sbi))); f2fs_update_time(sbi, CP_TIME); f2fs_update_time(sbi, REQ_TIME); clear_sbi_flag(sbi, SBI_CP_DISABLED_QUICK); diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index d7b47662a0aa..9e910b15bb4b 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -68,6 +68,20 @@ static ssize_t dirty_segments_show(struct f2fs_attr *a, (unsigned long long)(dirty_segments(sbi))); } +static ssize_t unusable_show(struct f2fs_attr *a, + struct f2fs_sb_info *sbi, char *buf) +{ + block_t unusable; + + if (test_opt(sbi, DISABLE_CHECKPOINT)) + unusable = sbi->unusable_block_count; + else + unusable = f2fs_get_unusable_blocks(sbi); + return snprintf(buf, PAGE_SIZE, "%llu\n", + (unsigned long long)unusable); +} + + static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { @@ -440,6 +454,7 @@ F2FS_GENERAL_RO_ATTR(dirty_segments); F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes); F2FS_GENERAL_RO_ATTR(features); F2FS_GENERAL_RO_ATTR(current_reserved_blocks); +F2FS_GENERAL_RO_ATTR(unusable); #ifdef CONFIG_F2FS_FS_ENCRYPTION F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO); @@ -495,6 +510,7 @@ static struct attribute *f2fs_attrs[] = { ATTR_LIST(inject_type), #endif ATTR_LIST(dirty_segments), + ATTR_LIST(unusable), ATTR_LIST(lifetime_write_kbytes), ATTR_LIST(features), ATTR_LIST(reserved_blocks), @@ -566,8 +582,7 @@ static int __maybe_unused segment_info_seq_show(struct seq_file *seq, if ((i % 10) == 0) seq_printf(seq, "%-10d", i); - seq_printf(seq, "%d|%-3u", se->type, - get_valid_blocks(sbi, i, false)); + seq_printf(seq, "%d|%-3u", se->type, se->valid_blocks); if ((i % 10) == 9 || i == (total_segs - 1)) seq_putc(seq, '\n'); else @@ -593,8 +608,7 @@ static int __maybe_unused segment_bits_seq_show(struct seq_file *seq, struct seg_entry *se = get_seg_entry(sbi, i); seq_printf(seq, "%-10d", i); - seq_printf(seq, "%d|%-3u|", se->type, - get_valid_blocks(sbi, i, false)); + seq_printf(seq, "%d|%-3u|", se->type, se->valid_blocks); for (j = 0; j < SIT_VBLOCK_MAP_SIZE; j++) seq_printf(seq, " %.2x", se->cur_valid_map[j]); seq_putc(seq, '\n'); diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 376db951b7c4..d48af3b5857b 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -392,7 +392,10 @@ static int lookup_all_xattrs(struct inode *inode, struct page *ipage, *xe = __find_xattr(cur_addr, last_txattr_addr, index, len, name); if (!*xe) { - err = -EFAULT; + f2fs_err(F2FS_I_SB(inode), "inode (%lu) has corrupted xattr", + inode->i_ino); + set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK); + err = -EFSCORRUPTED; goto out; } check: @@ -661,7 +664,10 @@ static int __f2fs_setxattr(struct inode *inode, int index, /* find entry with wanted name. */ here = __find_xattr(base_addr, last_base_addr, index, len, name); if (!here) { - error = -EFAULT; + f2fs_err(F2FS_I_SB(inode), "inode (%lu) has corrupted xattr", + inode->i_ino); + set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK); + error = -EFSCORRUPTED; goto exit; } diff --git a/fs/inode.c b/fs/inode.c index 10015f17b8ea..8e811a0e6be1 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2052,3 +2052,27 @@ void inode_nohighmem(struct inode *inode) mapping_set_gfp_mask(inode->i_mapping, GFP_USER); } EXPORT_SYMBOL(inode_nohighmem); + +/* + * Generic function to check FS_IOC_SETFLAGS values and reject any invalid + * configurations. + * + * Note: the caller should be holding i_mutex, or else be sure that they have + * exclusive access to the inode structure. + */ +int vfs_ioc_setflags_prepare(struct inode *inode, unsigned int oldflags, + unsigned int flags) +{ + /* + * The IMMUTABLE and APPEND_ONLY flags can only be changed by + * the relevant capability. + * + * This test looks nicer. Thanks to Pauline Middelink + */ + if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL) && + !capable(CAP_LINUX_IMMUTABLE)) + return -EPERM; + + return 0; +} +EXPORT_SYMBOL(vfs_ioc_setflags_prepare); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 668ac19af58f..d25b55ceb9d5 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -935,6 +935,7 @@ int nfs_open(struct inode *inode, struct file *filp) nfs_fscache_open_file(inode, filp); return 0; } +EXPORT_SYMBOL_GPL(nfs_open); /* * This function is called whenever some part of NFS notices that diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 679e003818b1..d3e3761eacfa 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -49,7 +49,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) return err; if ((openflags & O_ACCMODE) == 3) - openflags--; + return nfs_open(inode, filp); /* We can't create new files here */ openflags &= ~(O_CREAT|O_EXCL); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 41c8ddbc80dc..d1816ee0c11b 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -997,6 +997,12 @@ struct nfs4_opendata { int cancelled; }; +struct nfs4_open_createattrs { + struct nfs4_label *label; + struct iattr *sattr; + const __u32 verf[2]; +}; + static bool nfs4_clear_cap_atomic_open_v1(struct nfs_server *server, int err, struct nfs4_exception *exception) { @@ -1066,8 +1072,7 @@ static void nfs4_init_opendata_res(struct nfs4_opendata *p) static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, struct nfs4_state_owner *sp, fmode_t fmode, int flags, - const struct iattr *attrs, - struct nfs4_label *label, + const struct nfs4_open_createattrs *c, enum open_claim_type4 claim, gfp_t gfp_mask) { @@ -1075,6 +1080,7 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, struct inode *dir = d_inode(parent); struct nfs_server *server = NFS_SERVER(dir); struct nfs_seqid *(*alloc_seqid)(struct nfs_seqid_counter *, gfp_t); + struct nfs4_label *label = (c != NULL) ? c->label : NULL; struct nfs4_opendata *p; p = kzalloc(sizeof(*p), gfp_mask); @@ -1131,15 +1137,11 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, case NFS4_OPEN_CLAIM_DELEG_PREV_FH: p->o_arg.fh = NFS_FH(d_inode(dentry)); } - if (attrs != NULL && attrs->ia_valid != 0) { - __u32 verf[2]; - + if (c != NULL && c->sattr != NULL && c->sattr->ia_valid != 0) { p->o_arg.u.attrs = &p->attrs; - memcpy(&p->attrs, attrs, sizeof(p->attrs)); + memcpy(&p->attrs, c->sattr, sizeof(p->attrs)); - verf[0] = jiffies; - verf[1] = current->pid; - memcpy(p->o_arg.u.verifier.data, verf, + memcpy(p->o_arg.u.verifier.data, c->verf, sizeof(p->o_arg.u.verifier.data)); } p->c_arg.fh = &p->o_res.fh; @@ -1653,7 +1655,7 @@ static struct nfs4_opendata *nfs4_open_recoverdata_alloc(struct nfs_open_context struct nfs4_opendata *opendata; opendata = nfs4_opendata_alloc(ctx->dentry, state->owner, 0, 0, - NULL, NULL, claim, GFP_NOFS); + NULL, claim, GFP_NOFS); if (opendata == NULL) return ERR_PTR(-ENOMEM); opendata->state = state; @@ -2488,8 +2490,7 @@ out: static int _nfs4_do_open(struct inode *dir, struct nfs_open_context *ctx, int flags, - struct iattr *sattr, - struct nfs4_label *label, + const struct nfs4_open_createattrs *c, int *opened) { struct nfs4_state_owner *sp; @@ -2501,6 +2502,8 @@ static int _nfs4_do_open(struct inode *dir, struct nfs4_threshold **ctx_th = &ctx->mdsthreshold; fmode_t fmode = ctx->mode & (FMODE_READ|FMODE_WRITE|FMODE_EXEC); enum open_claim_type4 claim = NFS4_OPEN_CLAIM_NULL; + struct iattr *sattr = c->sattr; + struct nfs4_label *label = c->label; struct nfs4_label *olabel = NULL; int status; @@ -2519,8 +2522,8 @@ static int _nfs4_do_open(struct inode *dir, status = -ENOMEM; if (d_really_is_positive(dentry)) claim = NFS4_OPEN_CLAIM_FH; - opendata = nfs4_opendata_alloc(dentry, sp, fmode, flags, sattr, - label, claim, GFP_KERNEL); + opendata = nfs4_opendata_alloc(dentry, sp, fmode, flags, + c, claim, GFP_KERNEL); if (opendata == NULL) goto err_put_state_owner; @@ -2596,10 +2599,18 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir, struct nfs_server *server = NFS_SERVER(dir); struct nfs4_exception exception = { }; struct nfs4_state *res; + struct nfs4_open_createattrs c = { + .label = label, + .sattr = sattr, + .verf = { + [0] = (__u32)jiffies, + [1] = (__u32)current->pid, + }, + }; int status; do { - status = _nfs4_do_open(dir, ctx, flags, sattr, label, opened); + status = _nfs4_do_open(dir, ctx, flags, &c, opened); res = ctx->state; trace_nfs4_open_file(ctx, flags, status); if (status == 0) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index ba27a5ff8677..ea5cb1ba282f 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1391,11 +1391,16 @@ static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca) { u32 slotsize = slot_bytes(ca); u32 num = ca->maxreqs; - int avail; + unsigned long avail, total_avail; spin_lock(&nfsd_drc_lock); - avail = min((unsigned long)NFSD_MAX_MEM_PER_SESSION, - nfsd_drc_max_mem - nfsd_drc_mem_used); + total_avail = nfsd_drc_max_mem - nfsd_drc_mem_used; + avail = min((unsigned long)NFSD_MAX_MEM_PER_SESSION, total_avail); + /* + * Never use more than a third of the remaining memory, + * unless it's the only way to give this client a slot: + */ + avail = clamp_t(unsigned long, avail, slotsize, total_avail/3); num = min_t(int, num, avail / slotsize); nfsd_drc_mem_used += num * slotsize; spin_unlock(&nfsd_drc_lock); diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index b6eb56d18568..0fa990f08daf 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -360,7 +360,7 @@ void nfsd_reset_versions(void) */ static void set_max_drc(void) { - #define NFSD_DRC_SIZE_SHIFT 10 + #define NFSD_DRC_SIZE_SHIFT 7 nfsd_drc_max_mem = (nr_free_buffer_pages() >> NFSD_DRC_SIZE_SHIFT) * PAGE_SIZE; nfsd_drc_mem_used = 0; diff --git a/fs/open.c b/fs/open.c index e6a55dd45cba..b7e2889a710c 100644 --- a/fs/open.c +++ b/fs/open.c @@ -373,6 +373,25 @@ SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode) override_cred->cap_permitted; } + /* + * The new set of credentials can *only* be used in + * task-synchronous circumstances, and does not need + * RCU freeing, unless somebody then takes a separate + * reference to it. + * + * NOTE! This is _only_ true because this credential + * is used purely for override_creds() that installs + * it as the subjective cred. Other threads will be + * accessing ->real_cred, not the subjective cred. + * + * If somebody _does_ make a copy of this (using the + * 'get_current_cred()' function), that will clear the + * non_rcu field, because now that other user may be + * expecting RCU freeing. But normal thread-synchronous + * cred accesses will keep things non-RCY. + */ + override_cred->non_rcu = 1; + old_cred = override_creds(override_cred); retry: res = user_path_at(dfd, filename, lookup_flags, &path); diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 9aff8178aa8c..85507909823d 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -155,7 +155,7 @@ int ovl_permission(struct inode *inode, int mask) old_cred = ovl_override_creds(inode->i_sb); err = __inode_permission(realinode, mask); - revert_creds(old_cred); + ovl_revert_creds(old_cred); out_dput: dput(alias); diff --git a/include/linux/cred.h b/include/linux/cred.h index 9e120c92551b..d2db1da3036c 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -153,7 +153,11 @@ struct cred { struct user_struct *user; /* real user ID subscription */ struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */ struct group_info *group_info; /* supplementary groups for euid/fsgid */ - struct rcu_head rcu; /* RCU deletion hook */ + /* RCU deletion */ + union { + int non_rcu; /* Can we skip RCU deletion? */ + struct rcu_head rcu; /* RCU deletion hook */ + }; }; extern void __put_cred(struct cred *); @@ -251,6 +255,7 @@ static inline const struct cred *get_cred(const struct cred *cred) { struct cred *nonconst_cred = (struct cred *) cred; validate_creds(cred); + nonconst_cred->non_rcu = 0; return get_new_cred(nonconst_cred); } diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 638b324f0291..92ad08a29884 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -97,7 +97,7 @@ struct elevator_type struct module *elevator_owner; /* managed by elevator core */ - char icq_cache_name[ELV_NAME_MAX + 5]; /* elvname + "_io_cq" */ + char icq_cache_name[ELV_NAME_MAX + 6]; /* elvname + "_io_cq" */ struct list_head list; }; diff --git a/include/linux/fs.h b/include/linux/fs.h index 7493e807f073..66360a2f97bc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3141,4 +3141,7 @@ static inline bool dir_relax(struct inode *inode) extern bool path_noexec(const struct path *path); extern void inode_nohighmem(struct inode *inode); +int vfs_ioc_setflags_prepare(struct inode *inode, unsigned int oldflags, + unsigned int flags); + #endif /* _LINUX_FS_H */ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index addd03641e1a..0a93e9d1708e 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -852,7 +852,7 @@ static inline void rcu_preempt_sleep_check(void) * read-side critical sections may be preempted and they may also block, but * only when acquiring spinlocks that are subject to priority inheritance. */ -static inline void rcu_read_lock(void) +static __always_inline void rcu_read_lock(void) { __rcu_read_lock(); __acquire(RCU); diff --git a/include/linux/sched.h b/include/linux/sched.h index 2378cbf2612d..a05e1e82ecf3 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2149,7 +2149,7 @@ extern int arch_task_struct_size __read_mostly; extern void task_numa_fault(int last_node, int node, int pages, int flags); extern pid_t task_numa_group_id(struct task_struct *p); extern void set_numabalancing_state(bool enabled); -extern void task_numa_free(struct task_struct *p); +extern void task_numa_free(struct task_struct *p, bool final); extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page, int src_nid, int dst_cpu); #else @@ -2164,7 +2164,7 @@ static inline pid_t task_numa_group_id(struct task_struct *p) static inline void set_numabalancing_state(bool enabled) { } -static inline void task_numa_free(struct task_struct *p) +static inline void task_numa_free(struct task_struct *p, bool final) { } static inline bool should_numa_migrate_memory(struct task_struct *p, diff --git a/include/net/tcp.h b/include/net/tcp.h index b9b5bc27b844..bafb7e8737dc 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1461,6 +1461,11 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, void tcp_fastopen_init_key_once(bool publish); #define TCP_FASTOPEN_KEY_LENGTH 16 +static inline void tcp_init_send_head(struct sock *sk) +{ + sk->sk_send_head = NULL; +} + /* Fastopen key context */ struct tcp_fastopen_context { struct crypto_cipher *tfm; @@ -1477,6 +1482,7 @@ static inline void tcp_write_queue_purge(struct sock *sk) sk_wmem_free_skb(sk, skb); sk_mem_reclaim(sk); tcp_clear_all_retrans_hints(tcp_sk(sk)); + tcp_init_send_head(sk); inet_csk(sk)->icsk_backoff = 0; } @@ -1538,11 +1544,6 @@ static inline void tcp_check_send_head(struct sock *sk, struct sk_buff *skb_unli tcp_sk(sk)->highest_sack = NULL; } -static inline void tcp_init_send_head(struct sock *sk) -{ - sk->sk_send_head = NULL; -} - static inline void __tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb) { __skb_queue_tail(&sk->sk_write_queue, skb); diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index e84cbb11fe7f..b6850fe5465f 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -1016,8 +1016,8 @@ DECLARE_EVENT_CLASS(f2fs__submit_page_bio, ), TP_fast_assign( - __entry->dev = page->mapping->host->i_sb->s_dev; - __entry->ino = page->mapping->host->i_ino; + __entry->dev = page_file_mapping(page)->host->i_sb->s_dev; + __entry->ino = page_file_mapping(page)->host->i_ino; __entry->index = page->index; __entry->old_blkaddr = fio->old_blkaddr; __entry->new_blkaddr = fio->new_blkaddr; @@ -1204,10 +1204,11 @@ DECLARE_EVENT_CLASS(f2fs__page, ), TP_fast_assign( - __entry->dev = page->mapping->host->i_sb->s_dev; - __entry->ino = page->mapping->host->i_ino; + __entry->dev = page_file_mapping(page)->host->i_sb->s_dev; + __entry->ino = page_file_mapping(page)->host->i_ino; __entry->type = type; - __entry->dir = S_ISDIR(page->mapping->host->i_mode); + __entry->dir = + S_ISDIR(page_file_mapping(page)->host->i_mode); __entry->index = page->index; __entry->dirty = PageDirty(page); __entry->uptodate = PageUptodate(page); diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index d122ea5338d1..c66b52303114 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -239,6 +239,7 @@ struct fscrypt_key { #define FS_NOCOMP_FL 0x00000400 /* Don't compress */ #define FS_ECOMPR_FL 0x00000800 /* Compression error */ /* End compression flags --- maybe not all used */ +#define FS_ENCRYPT_FL 0x00000800 /* Encrypted file */ #define FS_BTREE_FL 0x00001000 /* btree format dir */ #define FS_INDEX_FL 0x00001000 /* hash-indexed directory */ #define FS_IMAGIC_FL 0x00002000 /* AFS directory */ @@ -249,6 +250,7 @@ struct fscrypt_key { #define FS_EXTENT_FL 0x00080000 /* Extents */ #define FS_DIRECTIO_FL 0x00100000 /* Use direct i/o */ #define FS_NOCOW_FL 0x00800000 /* Do not cow file */ +#define FS_INLINE_DATA_FL 0x10000000 /* Reserved for ext4 */ #define FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ #define FS_RESERVED_FL 0x80000000 /* reserved for ext2 lib */ diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 13272582eee0..677991f29d66 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -1,4 +1,5 @@ obj-y := core.o +CFLAGS_core.o += $(call cc-disable-warning, override-init) obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o diff --git a/kernel/cred.c b/kernel/cred.c index 098af0bc0b7e..a2e06b05a90c 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -146,7 +146,10 @@ void __put_cred(struct cred *cred) BUG_ON(cred == current->cred); BUG_ON(cred == current->real_cred); - call_rcu(&cred->rcu, put_cred_rcu); + if (cred->non_rcu) + put_cred_rcu(&cred->rcu); + else + call_rcu(&cred->rcu, put_cred_rcu); } EXPORT_SYMBOL(__put_cred); @@ -257,6 +260,7 @@ struct cred *prepare_creds(void) old = task->cred; memcpy(new, old, sizeof(struct cred)); + new->non_rcu = 0; atomic_set(&new->usage, 1); set_cred_subscribers(new, 0); get_group_info(new->group_info); @@ -536,7 +540,19 @@ const struct cred *override_creds(const struct cred *new) validate_creds(old); validate_creds(new); - get_cred(new); + + /* + * NOTE! This uses 'get_new_cred()' rather than 'get_cred()'. + * + * That means that we do not clear the 'non_rcu' flag, since + * we are only installing the cred into the thread-synchronous + * '->cred' pointer, not the '->real_cred' pointer that is + * visible to other threads under RCU. + * + * Also note that we did validate_creds() manually, not depending + * on the validation in 'get_cred()'. + */ + get_new_cred((struct cred *)new); alter_cred_subscribers(new, 1); rcu_assign_pointer(current->cred, new); alter_cred_subscribers(old, -1); @@ -619,6 +635,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) validate_creds(old); *new = *old; + new->non_rcu = 0; atomic_set(&new->usage, 1); set_cred_subscribers(new, 0); get_uid(new->user); diff --git a/kernel/fork.c b/kernel/fork.c index e8bc7ed77b59..b3899603f88e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -261,7 +261,7 @@ void __put_task_struct(struct task_struct *tsk) WARN_ON(tsk == current); cgroup_free(tsk); - task_numa_free(tsk); + task_numa_free(tsk, true); security_task_free(tsk); exit_creds(tsk); delayacct_tsk_free(tsk); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 774ab79d3ec7..f2df5f86af28 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -3128,17 +3128,17 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, if (depth) { hlock = curr->held_locks + depth - 1; if (hlock->class_idx == class_idx && nest_lock) { - if (hlock->references) { - /* - * Check: unsigned int references:12, overflow. - */ - if (DEBUG_LOCKS_WARN_ON(hlock->references == (1 << 12)-1)) - return 0; + if (!references) + references++; + if (!hlock->references) hlock->references++; - } else { - hlock->references = 2; - } + + hlock->references += references; + + /* Overflow */ + if (DEBUG_LOCKS_WARN_ON(hlock->references < references)) + return 0; return 1; } diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index dbb61a302548..35b34eccdd10 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -217,7 +217,6 @@ static void lockdep_stats_debug_show(struct seq_file *m) static int lockdep_stats_show(struct seq_file *m, void *v) { - struct lock_class *class; unsigned long nr_unused = 0, nr_uncategorized = 0, nr_irq_safe = 0, nr_irq_unsafe = 0, nr_softirq_safe = 0, nr_softirq_unsafe = 0, @@ -227,6 +226,9 @@ static int lockdep_stats_show(struct seq_file *m, void *v) nr_hardirq_read_safe = 0, nr_hardirq_read_unsafe = 0, sum_forward_deps = 0; +#ifdef CONFIG_PROVE_LOCKING + struct lock_class *class; + list_for_each_entry(class, &all_lock_classes, lock_entry) { if (class->usage_mask == 0) @@ -258,13 +260,13 @@ static int lockdep_stats_show(struct seq_file *m, void *v) if (class->usage_mask & LOCKF_ENABLED_HARDIRQ_READ) nr_hardirq_read_unsafe++; -#ifdef CONFIG_PROVE_LOCKING sum_forward_deps += lockdep_count_forward_deps(class); -#endif } #ifdef CONFIG_DEBUG_LOCKDEP DEBUG_LOCKS_WARN_ON(debug_atomic_read(nr_unused_locks) != nr_unused); #endif + +#endif seq_printf(m, " lock-classes: %11lu [max: %lu]\n", nr_lock_classes, MAX_LOCKDEP_KEYS); seq_printf(m, " direct dependencies: %11lu [max: %lu]\n", diff --git a/kernel/padata.c b/kernel/padata.c index ecc7b3f452c7..282b489a286d 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -273,7 +273,12 @@ static void padata_reorder(struct parallel_data *pd) * The next object that needs serialization might have arrived to * the reorder queues in the meantime, we will be called again * from the timer function if no one else cares for it. + * + * Ensure reorder_objects is read after pd->lock is dropped so we see + * an increment from another task in padata_do_serial. Pairs with + * smp_mb__after_atomic in padata_do_serial. */ + smp_mb(); if (atomic_read(&pd->reorder_objects) && !(pinst->flags & PADATA_RESET)) mod_timer(&pd->timer, jiffies + HZ); @@ -342,6 +347,13 @@ void padata_do_serial(struct padata_priv *padata) list_add_tail(&padata->list, &pqueue->reorder.list); spin_unlock(&pqueue->reorder.lock); + /* + * Ensure the atomic_inc of reorder_objects above is ordered correctly + * with the trylock of pd->lock in padata_reorder. Pairs with smp_mb + * in padata_reorder. + */ + smp_mb__after_atomic(); + put_cpu(); padata_reorder(pd); diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 567ecc826bc8..6353372801f2 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -325,7 +325,7 @@ int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd) } read_lock(&tasklist_lock); - force_sig(SIGKILL, pid_ns->child_reaper); + send_sig(SIGKILL, pid_ns->child_reaper, 1); read_unlock(&tasklist_lock); do_exit(0); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 1eac0642fa86..e497ef064ab0 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2233,13 +2233,23 @@ no_join: return; } -void task_numa_free(struct task_struct *p) +/* + * Get rid of NUMA staticstics associated with a task (either current or dead). + * If @final is set, the task is dead and has reached refcount zero, so we can + * safely free all relevant data structures. Otherwise, there might be + * concurrent reads from places like load balancing and procfs, and we should + * reset the data back to default state without freeing ->numa_faults. + */ +void task_numa_free(struct task_struct *p, bool final) { struct numa_group *grp = p->numa_group; - void *numa_faults = p->numa_faults; + unsigned long *numa_faults = p->numa_faults; unsigned long flags; int i; + if (!numa_faults) + return; + if (grp) { spin_lock_irqsave(&grp->lock, flags); for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) @@ -2252,8 +2262,14 @@ void task_numa_free(struct task_struct *p) put_numa_group(grp); } - p->numa_faults = NULL; - kfree(numa_faults); + if (final) { + p->numa_faults = NULL; + kfree(numa_faults); + } else { + p->total_numa_faults = 0; + for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) + numa_faults[i] = 0; + } } /* diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 0e0dc5d89911..bbe767b1f454 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -39,6 +39,7 @@ static u64 tick_length_base; #define MAX_TICKADJ 500LL /* usecs */ #define MAX_TICKADJ_SCALED \ (((MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ) +#define MAX_TAI_OFFSET 100000 /* * phase-lock loop variables @@ -633,7 +634,8 @@ static inline void process_adjtimex_modes(struct timex *txc, time_constant = max(time_constant, 0l); } - if (txc->modes & ADJ_TAI && txc->constant >= 0) + if (txc->modes & ADJ_TAI && + txc->constant >= 0 && txc->constant <= MAX_TAI_OFFSET) *time_tai = txc->constant; if (txc->modes & ADJ_OFFSET) diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index d38f8dde3c75..7b67a9fb3788 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -289,23 +289,6 @@ static inline void timer_list_header(struct seq_file *m, u64 now) SEQ_printf(m, "\n"); } -static int timer_list_show(struct seq_file *m, void *v) -{ - struct timer_list_iter *iter = v; - - if (iter->cpu == -1 && !iter->second_pass) - timer_list_header(m, iter->now); - else if (!iter->second_pass) - print_cpu(m, iter->cpu, iter->now); -#ifdef CONFIG_GENERIC_CLOCKEVENTS - else if (iter->cpu == -1 && iter->second_pass) - timer_list_show_tickdevices_header(m); - else - print_tickdevice(m, tick_get_device(iter->cpu), iter->cpu); -#endif - return 0; -} - void sysrq_timer_list_show(void) { u64 now = ktime_to_ns(ktime_get()); @@ -324,6 +307,24 @@ void sysrq_timer_list_show(void) return; } +#ifdef CONFIG_PROC_FS +static int timer_list_show(struct seq_file *m, void *v) +{ + struct timer_list_iter *iter = v; + + if (iter->cpu == -1 && !iter->second_pass) + timer_list_header(m, iter->now); + else if (!iter->second_pass) + print_cpu(m, iter->cpu, iter->now); +#ifdef CONFIG_GENERIC_CLOCKEVENTS + else if (iter->cpu == -1 && iter->second_pass) + timer_list_show_tickdevices_header(m); + else + print_tickdevice(m, tick_get_device(iter->cpu), iter->cpu); +#endif + return 0; +} + static void *move_iter(struct timer_list_iter *iter, loff_t offset) { for (; offset; offset--) { @@ -395,3 +396,4 @@ static int __init init_timer_list_procfs(void) return 0; } __initcall(init_timer_list_procfs); +#endif diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 6368792ab807..12f8bf9bf85d 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5567,11 +5567,15 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, break; } #endif - if (!tr->allocated_snapshot) { + if (!tr->allocated_snapshot) + ret = resize_buffer_duplicate_size(&tr->max_buffer, + &tr->trace_buffer, iter->cpu_file); + else ret = alloc_snapshot(tr); - if (ret < 0) - break; - } + + if (ret < 0) + break; + local_irq_disable(); /* Now, we're going to swap */ if (iter->cpu_file == RING_BUFFER_ALL_CPUS) diff --git a/lib/reed_solomon/decode_rs.c b/lib/reed_solomon/decode_rs.c index 0ec3f257ffdf..a5d313381539 100644 --- a/lib/reed_solomon/decode_rs.c +++ b/lib/reed_solomon/decode_rs.c @@ -42,8 +42,18 @@ BUG_ON(pad < 0 || pad >= nn); /* Does the caller provide the syndrome ? */ - if (s != NULL) - goto decode; + if (s != NULL) { + for (i = 0; i < nroots; i++) { + /* The syndrome is in index form, + * so nn represents zero + */ + if (s[i] != nn) + goto decode; + } + + /* syndrome is zero, no errors to correct */ + return 0; + } /* form the syndromes; i.e., evaluate data(x) at roots of * g(x) */ @@ -99,9 +109,9 @@ if (no_eras > 0) { /* Init lambda to be the erasure locator polynomial */ lambda[1] = alpha_to[rs_modnn(rs, - prim * (nn - 1 - eras_pos[0]))]; + prim * (nn - 1 - (eras_pos[0] + pad)))]; for (i = 1; i < no_eras; i++) { - u = rs_modnn(rs, prim * (nn - 1 - eras_pos[i])); + u = rs_modnn(rs, prim * (nn - 1 - (eras_pos[i] + pad))); for (j = i + 1; j > 0; j--) { tmp = index_of[lambda[j - 1]]; if (tmp != nn) { diff --git a/lib/scatterlist.c b/lib/scatterlist.c index bafa9933fa76..0b86b7992f93 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -496,17 +496,18 @@ static bool sg_miter_get_next_page(struct sg_mapping_iter *miter) { if (!miter->__remaining) { struct scatterlist *sg; - unsigned long pgoffset; if (!__sg_page_iter_next(&miter->piter)) return false; sg = miter->piter.sg; - pgoffset = miter->piter.sg_pgoffset; - miter->__offset = pgoffset ? 0 : sg->offset; + miter->__offset = miter->piter.sg_pgoffset ? 0 : sg->offset; + miter->piter.sg_pgoffset += miter->__offset >> PAGE_SHIFT; + miter->__offset &= PAGE_SIZE - 1; miter->__remaining = sg->offset + sg->length - - (pgoffset << PAGE_SHIFT) - miter->__offset; + (miter->piter.sg_pgoffset << PAGE_SHIFT) - + miter->__offset; miter->__remaining = min_t(unsigned long, miter->__remaining, PAGE_SIZE - miter->__offset); } diff --git a/mm/kmemleak.c b/mm/kmemleak.c index de479ce41690..ff0390823e04 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -576,7 +576,7 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size, if (in_irq()) { object->pid = 0; strncpy(object->comm, "hardirq", sizeof(object->comm)); - } else if (in_softirq()) { + } else if (in_serving_softirq()) { object->pid = 0; strncpy(object->comm, "softirq", sizeof(object->comm)); } else { diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 5fbdd367bbed..ad90b8f85223 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -286,7 +286,7 @@ static int do_mmu_notifier_register(struct mmu_notifier *mn, * thanks to mm_take_all_locks(). */ spin_lock(&mm->mmu_notifier_mm->lock); - hlist_add_head(&mn->hlist, &mm->mmu_notifier_mm->list); + hlist_add_head_rcu(&mn->hlist, &mm->mmu_notifier_mm->list); spin_unlock(&mm->mmu_notifier_mm->lock); mm_drop_all_locks(mm); diff --git a/mm/vmstat.c b/mm/vmstat.c index ce1f13a90967..e297ed47aa58 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1393,10 +1393,15 @@ static void vmstat_update(struct work_struct *w) * Counters were updated so we expect more updates * to occur in the future. Keep on running the * update worker thread. + * If we were marked on cpu_stat_off clear the flag + * so that vmstat_shepherd doesn't schedule us again. */ - queue_delayed_work_on(smp_processor_id(), vmstat_wq, - this_cpu_ptr(&vmstat_work), - round_jiffies_relative(sysctl_stat_interval)); + if (!cpumask_test_and_clear_cpu(smp_processor_id(), + cpu_stat_off)) { + queue_delayed_work_on(smp_processor_id(), vmstat_wq, + this_cpu_ptr(&vmstat_work), + round_jiffies_relative(sysctl_stat_interval)); + } } else { /* * We did not update any counters so the app may be in @@ -1415,18 +1420,6 @@ static void vmstat_update(struct work_struct *w) * until the diffs stay at zero. The function is used by NOHZ and can only be * invoked when tick processing is not active. */ -void quiet_vmstat(void) -{ - if (system_state != SYSTEM_RUNNING) - return; - - do { - if (!cpumask_test_and_set_cpu(smp_processor_id(), cpu_stat_off)) - cancel_delayed_work(this_cpu_ptr(&vmstat_work)); - - } while (refresh_cpu_vm_stats(false)); -} - /* * Check if the diffs for a certain cpu indicate that * an update is needed. @@ -1450,6 +1443,30 @@ static bool need_update(int cpu) return false; } +void quiet_vmstat(void) +{ + if (system_state != SYSTEM_RUNNING) + return; + + /* + * If we are already in hands of the shepherd then there + * is nothing for us to do here. + */ + if (cpumask_test_and_set_cpu(smp_processor_id(), cpu_stat_off)) + return; + + if (!need_update(smp_processor_id())) + return; + + /* + * Just refresh counters and do not care about the pending delayed + * vmstat_update. It doesn't fire that often to matter and canceling + * it would be too expensive from this path. + * vmstat_shepherd will take care about that for us. + */ + refresh_cpu_vm_stats(false); +} + /* * Shepherd worker thread that checks the @@ -1467,18 +1484,25 @@ static void vmstat_shepherd(struct work_struct *w) get_online_cpus(); /* Check processors whose vmstat worker threads have been disabled */ - for_each_cpu(cpu, cpu_stat_off) - if (!cpu_isolated(cpu) && need_update(cpu) && - cpumask_test_and_clear_cpu(cpu, cpu_stat_off)) - - queue_delayed_work_on(cpu, vmstat_wq, - &per_cpu(vmstat_work, cpu), 0); + for_each_cpu(cpu, cpu_stat_off) { + struct delayed_work *dw = &per_cpu(vmstat_work, cpu); + if (!cpu_isolated(cpu) && need_update(cpu)) { + if (cpumask_test_and_clear_cpu(cpu, cpu_stat_off)) + queue_delayed_work_on(cpu, vmstat_wq, dw, 0); + } else { + /* + * Cancel the work if quiet_vmstat has put this + * cpu on cpu_stat_off because the work item might + * be still scheduled + */ + cancel_delayed_work(dw); + } + } put_online_cpus(); schedule_delayed_work(&shepherd, round_jiffies_relative(sysctl_stat_interval)); - } static void __init start_shepherd_timer(void) diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 2a15b6aa9cdd..5892bd1457d4 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -767,10 +767,16 @@ static struct p9_trans_module p9_virtio_trans = { /* The standard init function */ static int __init p9_virtio_init(void) { + int rc; + INIT_LIST_HEAD(&virtio_chan_list); v9fs_register_trans(&p9_virtio_trans); - return register_virtio_driver(&p9_virtio_drv); + rc = register_virtio_driver(&p9_virtio_drv); + if (rc) + v9fs_unregister_trans(&p9_virtio_trans); + + return rc; } static void __exit p9_virtio_cleanup(void) diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index f2079acb555d..ffd49b40e76a 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -3158,6 +3158,8 @@ static void batadv_tt_purge(struct work_struct *work) void batadv_tt_free(struct batadv_priv *bat_priv) { + batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_ROAM, 1); + batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_TT, 1); batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_TT, 1); diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 795ddd8b2f77..4cd6b8d811ff 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -184,10 +184,16 @@ static inline struct lowpan_peer *peer_lookup_dst(struct lowpan_dev *dev, } if (!rt) { - nexthop = &lowpan_cb(skb)->gw; - - if (ipv6_addr_any(nexthop)) - return NULL; + if (ipv6_addr_any(&lowpan_cb(skb)->gw)) { + /* There is neither route nor gateway, + * probably the destination is a direct peer. + */ + nexthop = daddr; + } else { + /* There is a known gateway + */ + nexthop = &lowpan_cb(skb)->gw; + } } else { nexthop = rt6_nexthop(rt, daddr); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index cc1b7488861b..8d65bea9d93b 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -5062,6 +5062,11 @@ static void hci_le_remote_conn_param_req_evt(struct hci_dev *hdev, return send_conn_param_neg_reply(hdev, handle, HCI_ERROR_UNKNOWN_CONN_ID); + if (min < hcon->le_conn_min_interval || + max > hcon->le_conn_max_interval) + return send_conn_param_neg_reply(hdev, handle, + HCI_ERROR_INVALID_LL_PARAMS); + if (hci_check_conn_params(min, max, latency, timeout)) return send_conn_param_neg_reply(hdev, handle, HCI_ERROR_INVALID_LL_PARAMS); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index ad00753adef7..6233951af203 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4363,6 +4363,12 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, l2cap_chan_lock(chan); + if (chan->state != BT_DISCONN) { + l2cap_chan_unlock(chan); + mutex_unlock(&conn->chan_lock); + return 0; + } + l2cap_chan_hold(chan); l2cap_chan_del(chan, 0); @@ -5261,7 +5267,14 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn, memset(&rsp, 0, sizeof(rsp)); - err = hci_check_conn_params(min, max, latency, to_multiplier); + if (min < hcon->le_conn_min_interval || + max > hcon->le_conn_max_interval) { + BT_DBG("requested connection interval exceeds current bounds."); + err = -EINVAL; + } else { + err = hci_check_conn_params(min, max, latency, to_multiplier); + } + if (err) rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_REJECTED); else diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 68ffdf0d3876..d3114dfd8adf 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -2532,6 +2532,19 @@ static int smp_cmd_ident_addr_info(struct l2cap_conn *conn, goto distribute; } + /* Drop IRK if peer is using identity address during pairing but is + * providing different address as identity information. + * + * Microsoft Surface Precision Mouse is known to have this bug. + */ + if (hci_is_identity_address(&hcon->dst, hcon->dst_type) && + (bacmp(&info->bdaddr, &hcon->dst) || + info->addr_type != hcon->dst_type)) { + bt_dev_err(hcon->hdev, + "ignoring IRK with invalid identity address"); + goto distribute; + } + bacpy(&smp->id_addr, &info->bdaddr); smp->id_addr_type = info->addr_type; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index a52b4ffe30f4..0298bfd9e1d7 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1011,6 +1011,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, int type; int err = 0; __be32 group; + u16 nsrcs; ih = igmpv3_report_hdr(skb); num = ntohs(ih->ngrec); @@ -1024,8 +1025,9 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, grec = (void *)(skb->data + len - sizeof(*grec)); group = grec->grec_mca; type = grec->grec_type; + nsrcs = ntohs(grec->grec_nsrcs); - len += ntohs(grec->grec_nsrcs) * 4; + len += nsrcs * 4; if (!pskb_may_pull(skb, len)) return -EINVAL; @@ -1045,7 +1047,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, if ((type == IGMPV3_CHANGE_TO_INCLUDE || type == IGMPV3_MODE_IS_INCLUDE) && - ntohs(grec->grec_nsrcs) == 0) { + nsrcs == 0) { br_ip4_multicast_leave_group(br, port, group, vid); } else { err = br_ip4_multicast_add_group(br, port, group, vid); @@ -1078,23 +1080,26 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, len = skb_transport_offset(skb) + sizeof(*icmp6h); for (i = 0; i < num; i++) { - __be16 *nsrcs, _nsrcs; - - nsrcs = skb_header_pointer(skb, - len + offsetof(struct mld2_grec, - grec_nsrcs), - sizeof(_nsrcs), &_nsrcs); - if (!nsrcs) + __be16 *_nsrcs, __nsrcs; + u16 nsrcs; + + _nsrcs = skb_header_pointer(skb, + len + offsetof(struct mld2_grec, + grec_nsrcs), + sizeof(__nsrcs), &__nsrcs); + if (!_nsrcs) return -EINVAL; + nsrcs = ntohs(*_nsrcs); + if (!pskb_may_pull(skb, len + sizeof(*grec) + - sizeof(struct in6_addr) * ntohs(*nsrcs))) + sizeof(struct in6_addr) * nsrcs)) return -EINVAL; grec = (struct mld2_grec *)(skb->data + len); len += sizeof(*grec) + - sizeof(struct in6_addr) * ntohs(*nsrcs); + sizeof(struct in6_addr) * nsrcs; /* We treat these as MLDv1 reports for now. */ switch (grec->grec_type) { @@ -1112,7 +1117,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, if ((grec->grec_type == MLD2_CHANGE_TO_INCLUDE || grec->grec_type == MLD2_MODE_IS_INCLUDE) && - ntohs(*nsrcs) == 0) { + nsrcs == 0) { br_ip6_multicast_leave_group(br, port, &grec->grec_mca, vid); } else { @@ -1348,7 +1353,6 @@ static int br_ip6_multicast_query(struct net_bridge *br, struct sk_buff *skb, u16 vid) { - const struct ipv6hdr *ip6h = ipv6_hdr(skb); struct mld_msg *mld; struct net_bridge_mdb_entry *mp; struct mld2_query *mld2q; @@ -1392,7 +1396,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, if (is_general_query) { saddr.proto = htons(ETH_P_IPV6); - saddr.u.ip6 = ip6h->saddr; + saddr.u.ip6 = ipv6_hdr(skb)->saddr; br_multicast_query_received(br, port, &br->ip6_other_query, &saddr, max_delay); diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c index 5881fbc114a9..36282eb3492d 100644 --- a/net/bridge/br_stp_bpdu.c +++ b/net/bridge/br_stp_bpdu.c @@ -147,7 +147,6 @@ void br_send_tcn_bpdu(struct net_bridge_port *p) void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb, struct net_device *dev) { - const unsigned char *dest = eth_hdr(skb)->h_dest; struct net_bridge_port *p; struct net_bridge *br; const unsigned char *buf; @@ -176,7 +175,7 @@ void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb, if (p->state == BR_STATE_DISABLED) goto out; - if (!ether_addr_equal(dest, br->group_addr)) + if (!ether_addr_equal(eth_hdr(skb)->h_dest, br->group_addr)) goto out; if (p->flags & BR_BPDU_GUARD) { diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 2572b51e86f4..bfd16b515ab9 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -982,6 +982,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) atomic_set(&neigh->probes, NEIGH_VAR(neigh->parms, UCAST_PROBES)); + neigh_del_timer(neigh); neigh->nud_state = NUD_INCOMPLETE; neigh->updated = now; next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME), @@ -998,6 +999,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) } } else if (neigh->nud_state & NUD_STALE) { neigh_dbg(2, "neigh %p is delayed\n", neigh); + neigh_del_timer(neigh); neigh->nud_state = NUD_DELAY; neigh->updated = jiffies; neigh_add_timer(neigh, jiffies + diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 1e3c47930cb2..e9df88f8579c 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -67,6 +67,11 @@ #include "fib_lookup.h" +#define IPV6ONLY_FLAGS \ + (IFA_F_NODAD | IFA_F_OPTIMISTIC | IFA_F_DADFAILED | \ + IFA_F_HOMEADDRESS | IFA_F_TENTATIVE | \ + IFA_F_MANAGETEMPADDR | IFA_F_STABLE_PRIVACY) + static struct ipv4_devconf ipv4_devconf = { .data = { [IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1, @@ -453,6 +458,9 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, ifa->ifa_flags &= ~IFA_F_SECONDARY; last_primary = &in_dev->ifa_list; + /* Don't set IPv6 only flags to IPv4 addresses */ + ifa->ifa_flags &= ~IPV6ONLY_FLAGS; + for (ifap = &in_dev->ifa_list; (ifa1 = *ifap) != NULL; ifap = &ifa1->ifa_next) { if (!(ifa1->ifa_flags & IFA_F_SECONDARY) && diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0fe1eaf0bc31..abae27d60f67 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2281,6 +2281,8 @@ int tcp_disconnect(struct sock *sk, int flags) dst_release(sk->sk_rx_dst); sk->sk_rx_dst = NULL; tcp_saved_syn_free(tp); + tp->bytes_acked = 0; + tp->bytes_received = 0; WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index e348a140e540..91f16e679f63 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1666,6 +1666,10 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns struct net *net = sock_net(sk); struct mr6_table *mrt; + if (sk->sk_type != SOCK_RAW || + inet_sk(sk)->inet_num != IPPROTO_ICMPV6) + return -EOPNOTSUPP; + mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); if (!mrt) return -ENOENT; @@ -1677,9 +1681,6 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns switch (optname) { case MRT6_INIT: - if (sk->sk_type != SOCK_RAW || - inet_sk(sk)->inet_num != IPPROTO_ICMPV6) - return -EOPNOTSUPP; if (optlen < sizeof(int)) return -EINVAL; @@ -1816,6 +1817,10 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, struct net *net = sock_net(sk); struct mr6_table *mrt; + if (sk->sk_type != SOCK_RAW || + inet_sk(sk)->inet_num != IPPROTO_ICMPV6) + return -EOPNOTSUPP; + mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); if (!mrt) return -ENOENT; diff --git a/net/key/af_key.c b/net/key/af_key.c index 58c045d027fc..0b147079b0c6 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2453,8 +2453,10 @@ static int key_pol_get_resp(struct sock *sk, struct xfrm_policy *xp, const struc goto out; } err = pfkey_xfrm_policy2msg(out_skb, xp, dir); - if (err < 0) + if (err < 0) { + kfree_skb(out_skb); goto out; + } out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = hdr->sadb_msg_version; @@ -2707,8 +2709,10 @@ static int dump_sp(struct xfrm_policy *xp, int dir, int count, void *ptr) return PTR_ERR(out_skb); err = pfkey_xfrm_policy2msg(out_skb, xp, dir); - if (err < 0) + if (err < 0) { + kfree_skb(out_skb); return err; + } out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = pfk->dump.msg_version; diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 046ae1caecea..e5888983bec4 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -870,7 +870,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) unsigned short frametype, flags, window, timeout; int ret; - skb->sk = NULL; /* Initially we don't know who it's for */ + skb_orphan(skb); /* * skb->data points to the netrom frame start @@ -968,7 +968,9 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) window = skb->data[20]; + sock_hold(make); skb->sk = make; + skb->destructor = sock_efree; make->sk_state = TCP_ESTABLISHED; /* Fill in his circuit details */ diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c index dbd24254412a..d20383779710 100644 --- a/net/nfc/nci/data.c +++ b/net/nfc/nci/data.c @@ -119,7 +119,7 @@ static int nci_queue_tx_data_frags(struct nci_dev *ndev, conn_info = nci_get_conn_info_by_conn_id(ndev, conn_id); if (!conn_info) { rc = -EPROTO; - goto free_exit; + goto exit; } __skb_queue_head_init(&frags_q); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 2e48d0b1ddd0..49ff7556b2b5 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1857,11 +1857,6 @@ int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen struct xfrm_mgr *km; struct xfrm_policy *pol = NULL; -#ifdef CONFIG_COMPAT - if (is_compat_task()) - return -EOPNOTSUPP; -#endif - if (!optval && !optlen) { xfrm_sk_policy_insert(sk, XFRM_POLICY_IN, NULL); xfrm_sk_policy_insert(sk, XFRM_POLICY_OUT, NULL); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 4804f29fd011..46366810e93e 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -151,6 +151,25 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, err = -EINVAL; switch (p->family) { case AF_INET: + break; + + case AF_INET6: +#if IS_ENABLED(CONFIG_IPV6) + break; +#else + err = -EAFNOSUPPORT; + goto out; +#endif + + default: + goto out; + } + + switch (p->sel.family) { + case AF_UNSPEC: + break; + + case AF_INET: if (p->sel.prefixlen_d > 32 || p->sel.prefixlen_s > 32) goto out; @@ -2524,11 +2543,6 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) const struct xfrm_link *link; int type, err; -#ifdef CONFIG_COMPAT - if (is_compat_task()) - return -EOPNOTSUPP; -#endif - type = nlh->nlmsg_type; if (type > XFRM_MSG_MAX) return -EINVAL; diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 8fa81e84e295..d117c68d1607 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -158,6 +158,9 @@ static int read_symbol(FILE *in, struct sym_entry *s) /* exclude debugging symbols */ else if (stype == 'N') return -1; + /* exclude s390 kasan local symbols */ + else if (!strncmp(sym, ".LASANPC", 8)) + return -1; /* include the type field in the symbol name, so that it gets * compressed together */ diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h index b9897e2be404..04151ede8043 100644 --- a/scripts/recordmcount.h +++ b/scripts/recordmcount.h @@ -326,7 +326,8 @@ static uint_t *sift_rel_mcount(uint_t *mlocp, if (!mcountsym) mcountsym = get_mcountsym(sym0, relp, str0); - if (mcountsym == Elf_r_sym(relp) && !is_fake_mcount(relp)) { + if (mcountsym && mcountsym == Elf_r_sym(relp) && + !is_fake_mcount(relp)) { uint_t const addend = _w(_w(relp->r_offset) - recval + mcount_adjust); mrelp->r_offset = _w(offbase diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 0d0e0c2651c2..7fa0219c9758 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -1014,7 +1014,7 @@ static ssize_t snd_seq_write(struct file *file, const char __user *buf, { struct snd_seq_client *client = file->private_data; int written = 0, len; - int err; + int err, handled; struct snd_seq_event event; if (!(snd_seq_file_flags(file) & SNDRV_SEQ_LFLG_OUTPUT)) @@ -1027,6 +1027,8 @@ static ssize_t snd_seq_write(struct file *file, const char __user *buf, if (!client->accept_output || client->pool == NULL) return -ENXIO; + repeat: + handled = 0; /* allocate the pool now if the pool is not allocated yet */ mutex_lock(&client->ioctl_mutex); if (client->pool->size > 0 && !snd_seq_write_pool_allocated(client)) { @@ -1086,12 +1088,19 @@ static ssize_t snd_seq_write(struct file *file, const char __user *buf, 0, 0, &client->ioctl_mutex); if (err < 0) break; + handled++; __skip_event: /* Update pointers and counts */ count -= len; buf += len; written += len; + + /* let's have a coffee break if too many events are queued */ + if (++handled >= 200) { + mutex_unlock(&client->ioctl_mutex); + goto repeat; + } } out: diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 40dd46556452..05e745e2f427 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -1008,6 +1008,7 @@ static int patch_conexant_auto(struct hda_codec *codec) */ static const struct hda_device_id snd_hda_id_conexant[] = { + HDA_CODEC_ENTRY(0x14f11f86, "CX8070", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f12008, "CX8200", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f15045, "CX20549 (Venice)", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f15047, "CX20551 (Waikiki)", patch_conexant_auto), diff --git a/sound/usb/line6/podhd.c b/sound/usb/line6/podhd.c index 63dcaef41ac3..7fa37bae1f37 100644 --- a/sound/usb/line6/podhd.c +++ b/sound/usb/line6/podhd.c @@ -155,7 +155,7 @@ static const struct line6_properties podhd_properties_table[] = { .capabilities = LINE6_CAP_CONTROL | LINE6_CAP_PCM | LINE6_CAP_HWMON, - .altsetting = 1, + .altsetting = 0, .ep_ctrl_r = 0x81, .ep_ctrl_w = 0x01, .ep_audio_r = 0x86, diff --git a/tools/iio/iio_utils.c b/tools/iio/iio_utils.c index 5eb6793f3972..2d0dcd6fc64c 100644 --- a/tools/iio/iio_utils.c +++ b/tools/iio/iio_utils.c @@ -163,9 +163,9 @@ int iioutils_get_type(unsigned *is_signed, unsigned *bytes, unsigned *bits_used, *be = (endianchar == 'b'); *bytes = padint / 8; if (*bits_used == 64) - *mask = ~0; + *mask = ~(0ULL); else - *mask = (1ULL << *bits_used) - 1; + *mask = (1ULL << *bits_used) - 1ULL; *is_signed = (signchar == 's'); if (fclose(sysfsfp)) { diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c index 145050e2e544..195ba31e2f35 100644 --- a/tools/perf/tests/mmap-thread-lookup.c +++ b/tools/perf/tests/mmap-thread-lookup.c @@ -49,7 +49,7 @@ static void *thread_fn(void *arg) { struct thread_data *td = arg; ssize_t ret; - int go; + int go = 0; if (thread_init(td)) return NULL; diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 54af2f2e2ee4..1a35ab044c11 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -12,6 +12,32 @@ #define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \ PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD) +#if defined(__s390x__) +/* Return true if kvm module is available and loaded. Test this + * and retun success when trace point kvm_s390_create_vm + * exists. Otherwise this test always fails. + */ +static bool kvm_s390_create_vm_valid(void) +{ + char *eventfile; + bool rc = false; + + eventfile = get_events_file("kvm-s390"); + + if (eventfile) { + DIR *mydir = opendir(eventfile); + + if (mydir) { + rc = true; + closedir(mydir); + } + put_events_file(eventfile); + } + + return rc; +} +#endif + static int test__checkevent_tracepoint(struct perf_evlist *evlist) { struct perf_evsel *evsel = perf_evlist__first(evlist); @@ -1561,6 +1587,7 @@ static struct evlist_test test__events[] = { { .name = "kvm-s390:kvm_s390_create_vm", .check = test__checkevent_tracepoint, + .valid = kvm_s390_create_vm_valid, .id = 100, }, #endif diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 9aa10043103a..448b43ca7234 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -492,6 +492,9 @@ const char *perf_evsel__name(struct perf_evsel *evsel) { char bf[128]; + if (!evsel) + goto out_unknown; + if (evsel->name) return evsel->name; @@ -528,7 +531,10 @@ const char *perf_evsel__name(struct perf_evsel *evsel) evsel->name = strdup(bf); - return evsel->name ?: "unknown"; + if (evsel->name) + return evsel->name; +out_unknown: + return "unknown"; } const char *perf_evsel__group_name(struct perf_evsel *evsel) diff --git a/tools/power/cpupower/utils/cpufreq-set.c b/tools/power/cpupower/utils/cpufreq-set.c index 0fbd1a22c0a9..2f86935094ca 100644 --- a/tools/power/cpupower/utils/cpufreq-set.c +++ b/tools/power/cpupower/utils/cpufreq-set.c @@ -306,6 +306,8 @@ int cmd_freq_set(int argc, char **argv) bitmask_setbit(cpus_chosen, cpus->cpu); cpus = cpus->next; } + /* Set the last cpu in related cpus list */ + bitmask_setbit(cpus_chosen, cpus->cpu); cpufreq_put_related_cpus(cpus); } } |