diff --git a/Documentation/devicetree/bindings/ata/sata_rcar.txt b/Documentation/devicetree/bindings/ata/sata_rcar.txt index 1e6111333fa8..7dd32d321a34 100644 --- a/Documentation/devicetree/bindings/ata/sata_rcar.txt +++ b/Documentation/devicetree/bindings/ata/sata_rcar.txt @@ -3,7 +3,8 @@ Required properties: - compatible : should contain one of the following: - "renesas,sata-r8a7779" for R-Car H1 - - "renesas,sata-r8a7790" for R-Car H2 + - "renesas,sata-r8a7790-es1" for R-Car H2 ES1 + - "renesas,sata-r8a7790" for R-Car H2 other than ES1 - "renesas,sata-r8a7791" for R-Car M2 - reg : address and length of the SATA registers; - interrupts : must consist of one interrupt specifier. diff --git a/Makefile b/Makefile index 8fd06101c482..eb96e40238f7 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 3 PATCHLEVEL = 14 -SUBLEVEL = 24 +SUBLEVEL = 25 EXTRAVERSION = NAME = Remembering Coco diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 066b03480b63..8017cde13648 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -400,8 +400,7 @@ dtb_check_done: add sp, sp, r6 #endif - tst r4, #1 - bleq cache_clean_flush + bl cache_clean_flush adr r0, BSYM(restart) add r0, r0, r6 @@ -1050,6 +1049,8 @@ cache_clean_flush: b call_cache_fn __armv4_mpu_cache_flush: + tst r4, #1 + movne pc, lr mov r2, #1 mov r3, #0 mcr p15, 0, ip, c7, c6, 0 @ invalidate D cache @@ -1067,6 +1068,8 @@ __armv4_mpu_cache_flush: mov pc, lr __fa526_cache_flush: + tst r4, #1 + movne pc, lr mov r1, #0 mcr p15, 0, r1, c7, c14, 0 @ clean and invalidate D cache mcr p15, 0, r1, c7, c5, 0 @ flush I cache @@ -1075,13 +1078,16 @@ __fa526_cache_flush: __armv6_mmu_cache_flush: mov r1, #0 - mcr p15, 0, r1, c7, c14, 0 @ clean+invalidate D + tst r4, #1 + mcreq p15, 0, r1, c7, c14, 0 @ clean+invalidate D mcr p15, 0, r1, c7, c5, 0 @ invalidate I+BTB - mcr p15, 0, r1, c7, c15, 0 @ clean+invalidate unified + mcreq p15, 0, r1, c7, c15, 0 @ clean+invalidate unified mcr p15, 0, r1, c7, c10, 4 @ drain WB mov pc, lr __armv7_mmu_cache_flush: + tst r4, #1 + bne iflush mrc p15, 0, r10, c0, c1, 5 @ read ID_MMFR1 tst r10, #0xf << 16 @ hierarchical cache (ARMv7) mov r10, #0 @@ -1142,6 +1148,8 @@ iflush: mov pc, lr __armv5tej_mmu_cache_flush: + tst r4, #1 + movne pc, lr 1: mrc p15, 0, r15, c7, c14, 3 @ test,clean,invalidate D cache bne 1b mcr p15, 0, r0, c7, c5, 0 @ flush I cache @@ -1149,6 +1157,8 @@ __armv5tej_mmu_cache_flush: mov pc, lr __armv4_mmu_cache_flush: + tst r4, #1 + movne pc, lr mov r2, #64*1024 @ default: 32K dcache size (*2) mov r11, #32 @ default: 32 byte line size mrc p15, 0, r3, c0, c0, 1 @ read cache type @@ -1182,6 +1192,8 @@ no_cache_id: __armv3_mmu_cache_flush: __armv3_mpu_cache_flush: + tst r4, #1 + movne pc, lr mov r1, #0 mcr p15, 0, r1, c7, c0, 0 @ invalidate whole cache v3 mov pc, lr diff --git a/arch/arm/kernel/kprobes-common.c b/arch/arm/kernel/kprobes-common.c index 18a76282970e..380c20fb9c85 100644 --- a/arch/arm/kernel/kprobes-common.c +++ b/arch/arm/kernel/kprobes-common.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "kprobes.h" @@ -305,7 +306,8 @@ kprobe_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi) if (handler) { /* We can emulate the instruction in (possibly) modified form */ - asi->insn[0] = (insn & 0xfff00000) | (rn << 16) | reglist; + asi->insn[0] = __opcode_to_mem_arm((insn & 0xfff00000) | + (rn << 16) | reglist); asi->insn_handler = handler; return INSN_GOOD; } @@ -334,13 +336,14 @@ prepare_emulated_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi, #ifdef CONFIG_THUMB2_KERNEL if (thumb) { u16 *thumb_insn = (u16 *)asi->insn; - thumb_insn[1] = 0x4770; /* Thumb bx lr */ - thumb_insn[2] = 0x4770; /* Thumb bx lr */ + /* Thumb bx lr */ + thumb_insn[1] = __opcode_to_mem_thumb16(0x4770); + thumb_insn[2] = __opcode_to_mem_thumb16(0x4770); return insn; } - asi->insn[1] = 0xe12fff1e; /* ARM bx lr */ + asi->insn[1] = __opcode_to_mem_arm(0xe12fff1e); /* ARM bx lr */ #else - asi->insn[1] = 0xe1a0f00e; /* mov pc, lr */ + asi->insn[1] = __opcode_to_mem_arm(0xe1a0f00e); /* mov pc, lr */ #endif /* Make an ARM instruction unconditional */ if (insn < 0xe0000000) @@ -360,12 +363,12 @@ set_emulated_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi, if (thumb) { u16 *ip = (u16 *)asi->insn; if (is_wide_instruction(insn)) - *ip++ = insn >> 16; - *ip++ = insn; + *ip++ = __opcode_to_mem_thumb16(insn >> 16); + *ip++ = __opcode_to_mem_thumb16(insn); return; } #endif - asi->insn[0] = insn; + asi->insn[0] = __opcode_to_mem_arm(insn); } /* diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index 6123daf397a7..241222c66a13 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -11,6 +11,7 @@ #include #include #include +#include #include "kprobes.h" @@ -163,9 +164,9 @@ t32_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi) enum kprobe_insn ret = kprobe_decode_ldmstm(insn, asi); /* Fixup modified instruction to have halfwords in correct order...*/ - insn = asi->insn[0]; - ((u16 *)asi->insn)[0] = insn >> 16; - ((u16 *)asi->insn)[1] = insn & 0xffff; + insn = __mem_to_opcode_arm(asi->insn[0]); + ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(insn >> 16); + ((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0xffff); return ret; } @@ -1153,7 +1154,7 @@ t16_decode_hiregs(kprobe_opcode_t insn, struct arch_specific_insn *asi) { insn &= ~0x00ff; insn |= 0x001; /* Set Rdn = R1 and Rm = R0 */ - ((u16 *)asi->insn)[0] = insn; + ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(insn); asi->insn_handler = t16_emulate_hiregs; return INSN_GOOD; } @@ -1182,8 +1183,10 @@ t16_decode_push(kprobe_opcode_t insn, struct arch_specific_insn *asi) * and call it with R9=SP and LR in the register list represented * by R8. */ - ((u16 *)asi->insn)[0] = 0xe929; /* 1st half STMDB R9!,{} */ - ((u16 *)asi->insn)[1] = insn & 0x1ff; /* 2nd half (register list) */ + /* 1st half STMDB R9!,{} */ + ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(0xe929); + /* 2nd half (register list) */ + ((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0x1ff); asi->insn_handler = t16_emulate_push; return INSN_GOOD; } @@ -1232,8 +1235,10 @@ t16_decode_pop(kprobe_opcode_t insn, struct arch_specific_insn *asi) * and call it with R9=SP and PC in the register list represented * by R8. */ - ((u16 *)asi->insn)[0] = 0xe8b9; /* 1st half LDMIA R9!,{} */ - ((u16 *)asi->insn)[1] = insn & 0x1ff; /* 2nd half (register list) */ + /* 1st half LDMIA R9!,{} */ + ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(0xe8b9); + /* 2nd half (register list) */ + ((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0x1ff); asi->insn_handler = insn & 0x100 ? t16_emulate_pop_pc : t16_emulate_pop_nopc; return INSN_GOOD; diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c index a7b621ece23d..49a87b6d0bf3 100644 --- a/arch/arm/kernel/kprobes.c +++ b/arch/arm/kernel/kprobes.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include "kprobes.h" @@ -62,10 +63,10 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) #ifdef CONFIG_THUMB2_KERNEL thumb = true; addr &= ~1; /* Bit 0 would normally be set to indicate Thumb code */ - insn = ((u16 *)addr)[0]; + insn = __mem_to_opcode_thumb16(((u16 *)addr)[0]); if (is_wide_instruction(insn)) { - insn <<= 16; - insn |= ((u16 *)addr)[1]; + u16 inst2 = __mem_to_opcode_thumb16(((u16 *)addr)[1]); + insn = __opcode_thumb32_compose(insn, inst2); decode_insn = thumb32_kprobe_decode_insn; } else decode_insn = thumb16_kprobe_decode_insn; @@ -73,7 +74,7 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) thumb = false; if (addr & 0x3) return -EINVAL; - insn = *p->addr; + insn = __mem_to_opcode_arm(*p->addr); decode_insn = arm_kprobe_decode_insn; #endif diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index ca8ecdee47d8..e9c290c21744 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -798,6 +798,7 @@ config NEED_KUSER_HELPERS config KUSER_HELPERS bool "Enable kuser helpers in vector page" if !NEED_KUSER_HELPERS + depends on MMU default y help Warning: disabling this option may break user programs. diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index 92f36835486b..565e26f23f31 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -156,9 +156,10 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg) * which ends with "dsb; isb" pair guaranteeing global * visibility. */ - atomic_set(&pp->cpu_count, -1); + /* Notify other processors with an additional increment. */ + atomic_inc(&pp->cpu_count); } else { - while (atomic_read(&pp->cpu_count) != -1) + while (atomic_read(&pp->cpu_count) <= num_online_cpus()) cpu_relax(); isb(); } diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S index 6e0ed93d51fe..c17967fdf5f6 100644 --- a/arch/arm64/lib/clear_user.S +++ b/arch/arm64/lib/clear_user.S @@ -46,7 +46,7 @@ USER(9f, strh wzr, [x0], #2 ) sub x1, x1, #2 4: adds x1, x1, #1 b.mi 5f - strb wzr, [x0] +USER(9f, strb wzr, [x0] ) 5: mov x0, #0 ret ENDPROC(__clear_user) diff --git a/arch/parisc/include/uapi/asm/shmbuf.h b/arch/parisc/include/uapi/asm/shmbuf.h index 0a3eada1863b..f395cde7b593 100644 --- a/arch/parisc/include/uapi/asm/shmbuf.h +++ b/arch/parisc/include/uapi/asm/shmbuf.h @@ -36,23 +36,16 @@ struct shmid64_ds { unsigned int __unused2; }; -#ifdef CONFIG_64BIT -/* The 'unsigned int' (formerly 'unsigned long') data types below will - * ensure that a 32-bit app calling shmctl(*,IPC_INFO,*) will work on - * a wide kernel, but if some of these values are meant to contain pointers - * they may need to be 'long long' instead. -PB XXX FIXME - */ -#endif struct shminfo64 { - unsigned int shmmax; - unsigned int shmmin; - unsigned int shmmni; - unsigned int shmseg; - unsigned int shmall; - unsigned int __unused1; - unsigned int __unused2; - unsigned int __unused3; - unsigned int __unused4; + unsigned long shmmax; + unsigned long shmmin; + unsigned long shmmni; + unsigned long shmseg; + unsigned long shmall; + unsigned long __unused1; + unsigned long __unused2; + unsigned long __unused3; + unsigned long __unused4; }; #endif /* _PARISC_SHMBUF_H */ diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index 7dd8a3b22147..fc77d53e2ca5 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -286,11 +286,11 @@ ENTRY_COMP(msgsnd) ENTRY_COMP(msgrcv) ENTRY_SAME(msgget) /* 190 */ - ENTRY_SAME(msgctl) - ENTRY_SAME(shmat) + ENTRY_COMP(msgctl) + ENTRY_COMP(shmat) ENTRY_SAME(shmdt) ENTRY_SAME(shmget) - ENTRY_SAME(shmctl) /* 195 */ + ENTRY_COMP(shmctl) /* 195 */ ENTRY_SAME(ni_syscall) /* streams1 */ ENTRY_SAME(ni_syscall) /* streams2 */ ENTRY_SAME(lstat64) @@ -323,7 +323,7 @@ ENTRY_SAME(epoll_ctl) /* 225 */ ENTRY_SAME(epoll_wait) ENTRY_SAME(remap_file_pages) - ENTRY_SAME(semtimedop) + ENTRY_COMP(semtimedop) ENTRY_COMP(mq_open) ENTRY_SAME(mq_unlink) /* 230 */ ENTRY_COMP(mq_timedsend) diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h index 905832aa9e9e..a0ed182ae73c 100644 --- a/arch/sparc/include/asm/atomic_32.h +++ b/arch/sparc/include/asm/atomic_32.h @@ -21,7 +21,7 @@ extern int __atomic_add_return(int, atomic_t *); extern int atomic_cmpxchg(atomic_t *, int, int); -#define atomic_xchg(v, new) (xchg(&((v)->counter), new)) +extern int atomic_xchg(atomic_t *, int); extern int __atomic_add_unless(atomic_t *, int, int); extern void atomic_set(atomic_t *, int); diff --git a/arch/sparc/include/asm/cmpxchg_32.h b/arch/sparc/include/asm/cmpxchg_32.h index 1fae1a02e3c2..ae0f9a7a314d 100644 --- a/arch/sparc/include/asm/cmpxchg_32.h +++ b/arch/sparc/include/asm/cmpxchg_32.h @@ -11,22 +11,14 @@ #ifndef __ARCH_SPARC_CMPXCHG__ #define __ARCH_SPARC_CMPXCHG__ -static inline unsigned long xchg_u32(__volatile__ unsigned long *m, unsigned long val) -{ - __asm__ __volatile__("swap [%2], %0" - : "=&r" (val) - : "0" (val), "r" (m) - : "memory"); - return val; -} - +extern unsigned long __xchg_u32(volatile u32 *m, u32 new); extern void __xchg_called_with_bad_pointer(void); static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int size) { switch (size) { case 4: - return xchg_u32(ptr, x); + return __xchg_u32(ptr, x); } __xchg_called_with_bad_pointer(); return x; diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h index 432afa838861..55841c184e6d 100644 --- a/arch/sparc/include/asm/vio.h +++ b/arch/sparc/include/asm/vio.h @@ -118,12 +118,18 @@ struct vio_disk_attr_info { u8 vdisk_type; #define VD_DISK_TYPE_SLICE 0x01 /* Slice in block device */ #define VD_DISK_TYPE_DISK 0x02 /* Entire block device */ - u16 resv1; + u8 vdisk_mtype; /* v1.1 */ +#define VD_MEDIA_TYPE_FIXED 0x01 /* Fixed device */ +#define VD_MEDIA_TYPE_CD 0x02 /* CD Device */ +#define VD_MEDIA_TYPE_DVD 0x03 /* DVD Device */ + u8 resv1; u32 vdisk_block_size; u64 operations; - u64 vdisk_size; + u64 vdisk_size; /* v1.1 */ u64 max_xfer_size; - u64 resv2[2]; + u32 phys_block_size; /* v1.2 */ + u32 resv2; + u64 resv3[1]; }; struct vio_disk_desc { @@ -259,7 +265,7 @@ static inline u32 vio_dring_avail(struct vio_dring_state *dr, unsigned int ring_size) { return (dr->pending - - ((dr->prod - dr->cons) & (ring_size - 1))); + ((dr->prod - dr->cons) & (ring_size - 1)) - 1); } #define VIO_MAX_TYPE_LEN 32 diff --git a/arch/sparc/kernel/pci_schizo.c b/arch/sparc/kernel/pci_schizo.c index 8f76f23dac38..f9c6813c132d 100644 --- a/arch/sparc/kernel/pci_schizo.c +++ b/arch/sparc/kernel/pci_schizo.c @@ -581,7 +581,7 @@ static irqreturn_t schizo_pcierr_intr_other(struct pci_pbm_info *pbm) { unsigned long csr_reg, csr, csr_error_bits; irqreturn_t ret = IRQ_NONE; - u16 stat; + u32 stat; csr_reg = pbm->pbm_regs + SCHIZO_PCI_CTRL; csr = upa_readq(csr_reg); @@ -617,7 +617,7 @@ static irqreturn_t schizo_pcierr_intr_other(struct pci_pbm_info *pbm) pbm->name); ret = IRQ_HANDLED; } - pci_read_config_word(pbm->pci_bus->self, PCI_STATUS, &stat); + pbm->pci_ops->read(pbm->pci_bus, 0, PCI_STATUS, 2, &stat); if (stat & (PCI_STATUS_PARITY | PCI_STATUS_SIG_TARGET_ABORT | PCI_STATUS_REC_TARGET_ABORT | @@ -625,7 +625,7 @@ static irqreturn_t schizo_pcierr_intr_other(struct pci_pbm_info *pbm) PCI_STATUS_SIG_SYSTEM_ERROR)) { printk("%s: PCI bus error, PCI_STATUS[%04x]\n", pbm->name, stat); - pci_write_config_word(pbm->pci_bus->self, PCI_STATUS, 0xffff); + pbm->pci_ops->write(pbm->pci_bus, 0, PCI_STATUS, 2, 0xffff); ret = IRQ_HANDLED; } return ret; diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 50c3dd03be31..9af0a5dbb36d 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -823,13 +823,17 @@ void arch_send_call_function_single_ipi(int cpu) void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs) { clear_softint(1 << irq); + irq_enter(); generic_smp_call_function_interrupt(); + irq_exit(); } void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs) { clear_softint(1 << irq); + irq_enter(); generic_smp_call_function_single_interrupt(); + irq_exit(); } static void tsb_sync(void *info) diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c index 1d32b54089aa..8f2f94d53434 100644 --- a/arch/sparc/lib/atomic32.c +++ b/arch/sparc/lib/atomic32.c @@ -40,6 +40,19 @@ int __atomic_add_return(int i, atomic_t *v) } EXPORT_SYMBOL(__atomic_add_return); +int atomic_xchg(atomic_t *v, int new) +{ + int ret; + unsigned long flags; + + spin_lock_irqsave(ATOMIC_HASH(v), flags); + ret = v->counter; + v->counter = new; + spin_unlock_irqrestore(ATOMIC_HASH(v), flags); + return ret; +} +EXPORT_SYMBOL(atomic_xchg); + int atomic_cmpxchg(atomic_t *v, int old, int new) { int ret; @@ -132,3 +145,17 @@ unsigned long __cmpxchg_u32(volatile u32 *ptr, u32 old, u32 new) return (unsigned long)prev; } EXPORT_SYMBOL(__cmpxchg_u32); + +unsigned long __xchg_u32(volatile u32 *ptr, u32 new) +{ + unsigned long flags; + u32 prev; + + spin_lock_irqsave(ATOMIC_HASH(ptr), flags); + prev = *ptr; + *ptr = new; + spin_unlock_irqrestore(ATOMIC_HASH(ptr), flags); + + return (unsigned long)prev; +} +EXPORT_SYMBOL(__xchg_u32); diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 0fcd9133790c..14fe7cba21d1 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -75,8 +75,10 @@ suffix-$(CONFIG_KERNEL_XZ) := xz suffix-$(CONFIG_KERNEL_LZO) := lzo suffix-$(CONFIG_KERNEL_LZ4) := lz4 +RUN_SIZE = $(shell objdump -h vmlinux | \ + perl $(srctree)/arch/x86/tools/calc_run_size.pl) quiet_cmd_mkpiggy = MKPIGGY $@ - cmd_mkpiggy = $(obj)/mkpiggy $< > $@ || ( rm -f $@ ; false ) + cmd_mkpiggy = $(obj)/mkpiggy $< $(RUN_SIZE) > $@ || ( rm -f $@ ; false ) targets += piggy.S $(obj)/piggy.S: $(obj)/vmlinux.bin.$(suffix-y) $(obj)/mkpiggy FORCE diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index f45ab7a36fb6..c5b56ed10aff 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -186,7 +186,8 @@ relocated: * Do the decompression, and jump to the new kernel.. */ /* push arguments for decompress_kernel: */ - pushl $z_output_len /* decompressed length */ + pushl $z_run_size /* size of kernel with .bss and .brk */ + pushl $z_output_len /* decompressed length, end of relocs */ leal z_extract_offset_negative(%ebx), %ebp pushl %ebp /* output address */ pushl $z_input_len /* input_len */ @@ -196,7 +197,7 @@ relocated: pushl %eax /* heap area */ pushl %esi /* real mode pointer */ call decompress_kernel /* returns kernel location in %eax */ - addl $24, %esp + addl $28, %esp /* * Jump to the decompressed kernel. diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index b10fa66a2540..34bbc0911b7c 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -334,13 +334,16 @@ relocated: * Do the decompression, and jump to the new kernel.. */ pushq %rsi /* Save the real mode argument */ + movq $z_run_size, %r9 /* size of kernel with .bss and .brk */ + pushq %r9 movq %rsi, %rdi /* real mode address */ leaq boot_heap(%rip), %rsi /* malloc area for uncompression */ leaq input_data(%rip), %rdx /* input_data */ movl $z_input_len, %ecx /* input_len */ movq %rbp, %r8 /* output target address */ - movq $z_output_len, %r9 /* decompressed length */ + movq $z_output_len, %r9 /* decompressed length, end of relocs */ call decompress_kernel /* returns kernel location in %rax */ + popq %r9 popq %rsi /* diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 196eaf373a06..eb25ca1eb6da 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -393,7 +393,8 @@ asmlinkage void *decompress_kernel(void *rmode, memptr heap, unsigned char *input_data, unsigned long input_len, unsigned char *output, - unsigned long output_len) + unsigned long output_len, + unsigned long run_size) { real_mode = rmode; @@ -416,8 +417,14 @@ asmlinkage void *decompress_kernel(void *rmode, memptr heap, free_mem_ptr = heap; /* Heap */ free_mem_end_ptr = heap + BOOT_HEAP_SIZE; - output = choose_kernel_location(input_data, input_len, - output, output_len); + /* + * The memory hole needed for the kernel is the larger of either + * the entire decompressed kernel plus relocation table, or the + * entire decompressed kernel plus .bss and .brk sections. + */ + output = choose_kernel_location(input_data, input_len, output, + output_len > run_size ? output_len + : run_size); /* Validate memory location choices. */ if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1)) diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c index b669ab65bf6c..d8222f213182 100644 --- a/arch/x86/boot/compressed/mkpiggy.c +++ b/arch/x86/boot/compressed/mkpiggy.c @@ -36,11 +36,13 @@ int main(int argc, char *argv[]) uint32_t olen; long ilen; unsigned long offs; + unsigned long run_size; FILE *f = NULL; int retval = 1; - if (argc < 2) { - fprintf(stderr, "Usage: %s compressed_file\n", argv[0]); + if (argc < 3) { + fprintf(stderr, "Usage: %s compressed_file run_size\n", + argv[0]); goto bail; } @@ -74,6 +76,7 @@ int main(int argc, char *argv[]) offs += olen >> 12; /* Add 8 bytes for each 32K block */ offs += 64*1024 + 128; /* Add 64K + 128 bytes slack */ offs = (offs+4095) & ~4095; /* Round to a 4K boundary */ + run_size = atoi(argv[2]); printf(".section \".rodata..compressed\",\"a\",@progbits\n"); printf(".globl z_input_len\n"); @@ -85,6 +88,8 @@ int main(int argc, char *argv[]) /* z_extract_offset_negative allows simplification of head_32.S */ printf(".globl z_extract_offset_negative\n"); printf("z_extract_offset_negative = -0x%lx\n", offs); + printf(".globl z_run_size\n"); + printf("z_run_size = %lu\n", run_size); printf(".globl input_data, input_data_end\n"); printf("input_data:\n"); diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c index 617a9e284245..b63773ba1646 100644 --- a/arch/x86/kernel/cpu/microcode/amd_early.c +++ b/arch/x86/kernel/cpu/microcode/amd_early.c @@ -108,12 +108,13 @@ static size_t compute_container_size(u8 *data, u32 total_size) * load_microcode_amd() to save equivalent cpu table and microcode patches in * kernel heap memory. */ -static void apply_ucode_in_initrd(void *ucode, size_t size) +static void apply_ucode_in_initrd(void *ucode, size_t size, bool save_patch) { struct equiv_cpu_entry *eq; size_t *cont_sz; u32 *header; u8 *data, **cont; + u8 (*patch)[PATCH_MAX_SIZE]; u16 eq_id = 0; int offset, left; u32 rev, eax, ebx, ecx, edx; @@ -123,10 +124,12 @@ static void apply_ucode_in_initrd(void *ucode, size_t size) new_rev = (u32 *)__pa_nodebug(&ucode_new_rev); cont_sz = (size_t *)__pa_nodebug(&container_size); cont = (u8 **)__pa_nodebug(&container); + patch = (u8 (*)[PATCH_MAX_SIZE])__pa_nodebug(&amd_ucode_patch); #else new_rev = &ucode_new_rev; cont_sz = &container_size; cont = &container; + patch = &amd_ucode_patch; #endif data = ucode; @@ -213,9 +216,9 @@ static void apply_ucode_in_initrd(void *ucode, size_t size) rev = mc->hdr.patch_id; *new_rev = rev; - /* save ucode patch */ - memcpy(amd_ucode_patch, mc, - min_t(u32, header[1], PATCH_MAX_SIZE)); + if (save_patch) + memcpy(patch, mc, + min_t(u32, header[1], PATCH_MAX_SIZE)); } } @@ -246,7 +249,7 @@ void __init load_ucode_amd_bsp(void) *data = cp.data; *size = cp.size; - apply_ucode_in_initrd(cp.data, cp.size); + apply_ucode_in_initrd(cp.data, cp.size, true); } #ifdef CONFIG_X86_32 @@ -263,7 +266,7 @@ void load_ucode_amd_ap(void) size_t *usize; void **ucode; - mc = (struct microcode_amd *)__pa(amd_ucode_patch); + mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch); if (mc->hdr.patch_id && mc->hdr.processor_rev_id) { __apply_microcode_amd(mc); return; @@ -275,7 +278,7 @@ void load_ucode_amd_ap(void) if (!*ucode || !*usize) return; - apply_ucode_in_initrd(*ucode, *usize); + apply_ucode_in_initrd(*ucode, *usize, false); } static void __init collect_cpu_sig_on_bsp(void *arg) @@ -339,7 +342,7 @@ void load_ucode_amd_ap(void) * AP has a different equivalence ID than BSP, looks like * mixed-steppings silicon so go through the ucode blob anew. */ - apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size); + apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size, false); } } #endif @@ -347,7 +350,9 @@ void load_ucode_amd_ap(void) int __init save_microcode_in_initrd_amd(void) { unsigned long cont; + int retval = 0; enum ucode_state ret; + u8 *cont_va; u32 eax; if (!container) @@ -355,13 +360,15 @@ int __init save_microcode_in_initrd_amd(void) #ifdef CONFIG_X86_32 get_bsp_sig(); - cont = (unsigned long)container; + cont = (unsigned long)container; + cont_va = __va(container); #else /* * We need the physical address of the container for both bitness since * boot_params.hdr.ramdisk_image is a physical address. */ - cont = __pa(container); + cont = __pa(container); + cont_va = container; #endif /* @@ -372,6 +379,8 @@ int __init save_microcode_in_initrd_amd(void) if (relocated_ramdisk) container = (u8 *)(__va(relocated_ramdisk) + (cont - boot_params.hdr.ramdisk_image)); + else + container = cont_va; if (ucode_new_rev) pr_info("microcode: updated early to new patch_level=0x%08x\n", @@ -382,7 +391,7 @@ int __init save_microcode_in_initrd_amd(void) ret = load_microcode_amd(eax, container, container_size); if (ret != UCODE_OK) - return -EINVAL; + retval = -EINVAL; /* * This will be freed any msec now, stash patches for the current @@ -391,5 +400,5 @@ int __init save_microcode_in_initrd_amd(void) container = NULL; container_size = 0; - return 0; + return retval; } diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 1340ebfcb467..5ee8064bd1d2 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -2475,6 +2475,9 @@ __init int intel_pmu_init(void) case 62: /* IvyBridge EP */ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + /* dTLB-load-misses on IVB is different than SNB */ + hw_cache_event_ids[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = 0x8108; /* DTLB_LOAD_MISSES.DEMAND_LD_MISS_CAUSES_A_WALK */ + memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 7461f50d5bb1..0686fe313b3b 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1441,15 +1441,6 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, force_sig_info(SIGTRAP, &info, tsk); } - -#ifdef CONFIG_X86_32 -# define IS_IA32 1 -#elif defined CONFIG_IA32_EMULATION -# define IS_IA32 is_compat_task() -#else -# define IS_IA32 0 -#endif - /* * We must return the syscall number to actually look up in the table. * This can be -1L to skip running any syscall at all. @@ -1487,7 +1478,7 @@ long syscall_trace_enter(struct pt_regs *regs) if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_enter(regs, regs->orig_ax); - if (IS_IA32) + if (is_ia32_task()) audit_syscall_entry(AUDIT_ARCH_I386, regs->orig_ax, regs->bx, regs->cx, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 51c2851ca243..fab97ade0fc8 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4911,7 +4911,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu) ++vcpu->stat.insn_emulation_fail; trace_kvm_emulate_insn_failed(vcpu); - if (!is_guest_mode(vcpu)) { + if (!is_guest_mode(vcpu) && kvm_x86_ops->get_cpl(vcpu) == 0) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; vcpu->run->internal.ndata = 0; diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index c96314abd144..0004ac72dbdd 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -399,13 +399,20 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma, int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { - int young; - - young = ptep_test_and_clear_young(vma, address, ptep); - if (young) - flush_tlb_page(vma, address); - - return young; + /* + * On x86 CPUs, clearing the accessed bit without a TLB flush + * doesn't cause data corruption. [ It could cause incorrect + * page aging and the (mistaken) reclaim of hot pages, but the + * chance of that should be relatively low. ] + * + * So as a performance optimization don't flush the TLB when + * clearing the accessed bit, it will eventually be flushed by + * a context switch or a VM operation anyway. [ In the rare + * event of it not getting flushed for a long time the delay + * shouldn't really matter because there's no real memory + * pressure for swapout to react to. ] + */ + return ptep_test_and_clear_young(vma, address, ptep); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/arch/x86/tools/calc_run_size.pl b/arch/x86/tools/calc_run_size.pl new file mode 100644 index 000000000000..0b0b124d3ece --- /dev/null +++ b/arch/x86/tools/calc_run_size.pl @@ -0,0 +1,30 @@ +#!/usr/bin/perl +# +# Calculate the amount of space needed to run the kernel, including room for +# the .bss and .brk sections. +# +# Usage: +# objdump -h a.out | perl calc_run_size.pl +use strict; + +my $mem_size = 0; +my $file_offset = 0; + +my $sections=" *[0-9]+ \.(?:bss|brk) +"; +while (<>) { + if (/^$sections([0-9a-f]+) +(?:[0-9a-f]+ +){2}([0-9a-f]+)/) { + my $size = hex($1); + my $offset = hex($2); + $mem_size += $size; + if ($file_offset == 0) { + $file_offset = $offset; + } elsif ($file_offset != $offset) { + die ".bss and .brk lack common file offset\n"; + } + } +} + +if ($file_offset == 0) { + die "Never found .bss or .brk file offset\n"; +} +printf("%d\n", $mem_size + $file_offset); diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h index b9395529f02d..50084f7c01c8 100644 --- a/arch/xtensa/include/uapi/asm/unistd.h +++ b/arch/xtensa/include/uapi/asm/unistd.h @@ -384,7 +384,8 @@ __SYSCALL(174, sys_chroot, 1) #define __NR_pivot_root 175 __SYSCALL(175, sys_pivot_root, 2) #define __NR_umount 176 -__SYSCALL(176, sys_umount, 2) +__SYSCALL(176, sys_oldumount, 1) +#define __ARCH_WANT_SYS_OLDUMOUNT #define __NR_swapoff 177 __SYSCALL(177, sys_swapoff, 1) #define __NR_sync 178 diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 00663d60f6d4..e662f147d436 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -61,6 +61,7 @@ enum board_ids { /* board IDs by feature in alphabetical order */ board_ahci, board_ahci_ign_iferr, + board_ahci_nomsi, board_ahci_noncq, board_ahci_nosntf, board_ahci_yes_fbs, @@ -122,6 +123,13 @@ static const struct ata_port_info ahci_port_info[] = { .udma_mask = ATA_UDMA6, .port_ops = &ahci_ops, }, + [board_ahci_nomsi] = { + AHCI_HFLAGS (AHCI_HFLAG_NO_MSI), + .flags = AHCI_FLAG_COMMON, + .pio_mask = ATA_PIO4, + .udma_mask = ATA_UDMA6, + .port_ops = &ahci_ops, + }, [board_ahci_noncq] = { AHCI_HFLAGS (AHCI_HFLAG_NO_NCQ), .flags = AHCI_FLAG_COMMON, @@ -314,6 +322,11 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x8c87), board_ahci }, /* 9 Series RAID */ { PCI_VDEVICE(INTEL, 0x8c8e), board_ahci }, /* 9 Series RAID */ { PCI_VDEVICE(INTEL, 0x8c8f), board_ahci }, /* 9 Series RAID */ + { PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H AHCI */ + { PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H RAID */ + { PCI_VDEVICE(INTEL, 0xa105), board_ahci }, /* Sunrise Point-H RAID */ + { PCI_VDEVICE(INTEL, 0xa107), board_ahci }, /* Sunrise Point-H RAID */ + { PCI_VDEVICE(INTEL, 0xa10f), board_ahci }, /* Sunrise Point-H RAID */ /* JMicron 360/1/3/5/6, match class to avoid IDE function */ { PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, @@ -476,10 +489,10 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci }, /* ASM1062 */ /* - * Samsung SSDs found on some macbooks. NCQ times out. - * https://bugzilla.kernel.org/show_bug.cgi?id=60731 + * Samsung SSDs found on some macbooks. NCQ times out if MSI is + * enabled. https://bugzilla.kernel.org/show_bug.cgi?id=60731 */ - { PCI_VDEVICE(SAMSUNG, 0x1600), board_ahci_noncq }, + { PCI_VDEVICE(SAMSUNG, 0x1600), board_ahci_nomsi }, /* Enmotus */ { PCI_DEVICE(0x1c44, 0x8000), board_ahci }, diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c index 2b25bd83fc9d..c1ea780fca07 100644 --- a/drivers/ata/sata_rcar.c +++ b/drivers/ata/sata_rcar.c @@ -146,6 +146,7 @@ enum sata_rcar_type { RCAR_GEN1_SATA, RCAR_GEN2_SATA, + RCAR_R8A7790_ES1_SATA, }; struct sata_rcar_priv { @@ -763,6 +764,9 @@ static void sata_rcar_setup_port(struct ata_host *host) ap->udma_mask = ATA_UDMA6; ap->flags |= ATA_FLAG_SATA; + if (priv->type == RCAR_R8A7790_ES1_SATA) + ap->flags |= ATA_FLAG_NO_DIPM; + ioaddr->cmd_addr = base + SDATA_REG; ioaddr->ctl_addr = base + SSDEVCON_REG; ioaddr->scr_addr = base + SCRSSTS_REG; @@ -792,6 +796,7 @@ static void sata_rcar_init_controller(struct ata_host *host) sata_rcar_gen1_phy_init(priv); break; case RCAR_GEN2_SATA: + case RCAR_R8A7790_ES1_SATA: sata_rcar_gen2_phy_init(priv); break; default: @@ -838,6 +843,10 @@ static struct of_device_id sata_rcar_match[] = { .data = (void *)RCAR_GEN2_SATA }, { + .compatible = "renesas,sata-r8a7790-es1", + .data = (void *)RCAR_R8A7790_ES1_SATA + }, + { .compatible = "renesas,sata-r8a7791", .data = (void *)RCAR_GEN2_SATA }, @@ -849,6 +858,7 @@ static const struct platform_device_id sata_rcar_id_table[] = { { "sata_rcar", RCAR_GEN1_SATA }, /* Deprecated by "sata-r8a7779" */ { "sata-r8a7779", RCAR_GEN1_SATA }, { "sata-r8a7790", RCAR_GEN2_SATA }, + { "sata-r8a7790-es1", RCAR_R8A7790_ES1_SATA }, { "sata-r8a7791", RCAR_GEN2_SATA }, { }, }; diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index f6cff3be0ed7..2f9a3d8ecbbf 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -1557,8 +1557,10 @@ int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val, } else { void *wval; - if (!val_count) - return -EINVAL; + if (!val_count) { + ret = -EINVAL; + goto out; + } wval = kmemdup(val, val_count * val_bytes, GFP_KERNEL); if (!wval) { diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 5814deb6963d..0ebadf93b6c5 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -22,8 +23,8 @@ #define DRV_MODULE_NAME "sunvdc" #define PFX DRV_MODULE_NAME ": " -#define DRV_MODULE_VERSION "1.0" -#define DRV_MODULE_RELDATE "June 25, 2007" +#define DRV_MODULE_VERSION "1.1" +#define DRV_MODULE_RELDATE "February 13, 2013" static char version[] = DRV_MODULE_NAME ".c:v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n"; @@ -32,7 +33,7 @@ MODULE_DESCRIPTION("Sun LDOM virtual disk client driver"); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_MODULE_VERSION); -#define VDC_TX_RING_SIZE 256 +#define VDC_TX_RING_SIZE 512 #define WAITING_FOR_LINK_UP 0x01 #define WAITING_FOR_TX_SPACE 0x02 @@ -65,11 +66,9 @@ struct vdc_port { u64 operations; u32 vdisk_size; u8 vdisk_type; + u8 vdisk_mtype; char disk_name[32]; - - struct vio_disk_geom geom; - struct vio_disk_vtoc label; }; static inline struct vdc_port *to_vdc_port(struct vio_driver_state *vio) @@ -79,9 +78,16 @@ static inline struct vdc_port *to_vdc_port(struct vio_driver_state *vio) /* Ordered from largest major to lowest */ static struct vio_version vdc_versions[] = { + { .major = 1, .minor = 1 }, { .major = 1, .minor = 0 }, }; +static inline int vdc_version_supported(struct vdc_port *port, + u16 major, u16 minor) +{ + return port->vio.ver.major == major && port->vio.ver.minor >= minor; +} + #define VDCBLK_NAME "vdisk" static int vdc_major; #define PARTITION_SHIFT 3 @@ -94,18 +100,54 @@ static inline u32 vdc_tx_dring_avail(struct vio_dring_state *dr) static int vdc_getgeo(struct block_device *bdev, struct hd_geometry *geo) { struct gendisk *disk = bdev->bd_disk; - struct vdc_port *port = disk->private_data; + sector_t nsect = get_capacity(disk); + sector_t cylinders = nsect; - geo->heads = (u8) port->geom.num_hd; - geo->sectors = (u8) port->geom.num_sec; - geo->cylinders = port->geom.num_cyl; + geo->heads = 0xff; + geo->sectors = 0x3f; + sector_div(cylinders, geo->heads * geo->sectors); + geo->cylinders = cylinders; + if ((sector_t)(geo->cylinders + 1) * geo->heads * geo->sectors < nsect) + geo->cylinders = 0xffff; return 0; } +/* Add ioctl/CDROM_GET_CAPABILITY to support cdrom_id in udev + * when vdisk_mtype is VD_MEDIA_TYPE_CD or VD_MEDIA_TYPE_DVD. + * Needed to be able to install inside an ldom from an iso image. + */ +static int vdc_ioctl(struct block_device *bdev, fmode_t mode, + unsigned command, unsigned long argument) +{ + int i; + struct gendisk *disk; + + switch (command) { + case CDROMMULTISESSION: + pr_debug(PFX "Multisession CDs not supported\n"); + for (i = 0; i < sizeof(struct cdrom_multisession); i++) + if (put_user(0, (char __user *)(argument + i))) + return -EFAULT; + return 0; + + case CDROM_GET_CAPABILITY: + disk = bdev->bd_disk; + + if (bdev->bd_disk && (disk->flags & GENHD_FL_CD)) + return 0; + return -EINVAL; + + default: + pr_debug(PFX "ioctl %08x not supported\n", command); + return -EINVAL; + } +} + static const struct block_device_operations vdc_fops = { .owner = THIS_MODULE, .getgeo = vdc_getgeo, + .ioctl = vdc_ioctl, }; static void vdc_finish(struct vio_driver_state *vio, int err, int waiting_for) @@ -165,9 +207,9 @@ static int vdc_handle_attr(struct vio_driver_state *vio, void *arg) struct vio_disk_attr_info *pkt = arg; viodbg(HS, "GOT ATTR stype[0x%x] ops[%llx] disk_size[%llu] disk_type[%x] " - "xfer_mode[0x%x] blksz[%u] max_xfer[%llu]\n", + "mtype[0x%x] xfer_mode[0x%x] blksz[%u] max_xfer[%llu]\n", pkt->tag.stype, pkt->operations, - pkt->vdisk_size, pkt->vdisk_type, + pkt->vdisk_size, pkt->vdisk_type, pkt->vdisk_mtype, pkt->xfer_mode, pkt->vdisk_block_size, pkt->max_xfer_size); @@ -192,8 +234,11 @@ static int vdc_handle_attr(struct vio_driver_state *vio, void *arg) } port->operations = pkt->operations; - port->vdisk_size = pkt->vdisk_size; port->vdisk_type = pkt->vdisk_type; + if (vdc_version_supported(port, 1, 1)) { + port->vdisk_size = pkt->vdisk_size; + port->vdisk_mtype = pkt->vdisk_mtype; + } if (pkt->max_xfer_size < port->max_xfer_size) port->max_xfer_size = pkt->max_xfer_size; port->vdisk_block_size = pkt->vdisk_block_size; @@ -236,7 +281,9 @@ static void vdc_end_one(struct vdc_port *port, struct vio_dring_state *dr, __blk_end_request(req, (desc->status ? -EIO : 0), desc->size); - if (blk_queue_stopped(port->disk->queue)) + /* restart blk queue when ring is half emptied */ + if (blk_queue_stopped(port->disk->queue) && + vdc_tx_dring_avail(dr) * 100 / VDC_TX_RING_SIZE >= 50) blk_start_queue(port->disk->queue); } @@ -388,12 +435,6 @@ static int __send_request(struct request *req) for (i = 0; i < nsg; i++) len += sg[i].length; - if (unlikely(vdc_tx_dring_avail(dr) < 1)) { - blk_stop_queue(port->disk->queue); - err = -ENOMEM; - goto out; - } - desc = vio_dring_cur(dr); err = ldc_map_sg(port->vio.lp, sg, nsg, @@ -433,21 +474,32 @@ static int __send_request(struct request *req) port->req_id++; dr->prod = (dr->prod + 1) & (VDC_TX_RING_SIZE - 1); } -out: return err; } -static void do_vdc_request(struct request_queue *q) +static void do_vdc_request(struct request_queue *rq) { - while (1) { - struct request *req = blk_fetch_request(q); + struct request *req; - if (!req) - break; + while ((req = blk_peek_request(rq)) != NULL) { + struct vdc_port *port; + struct vio_dring_state *dr; - if (__send_request(req) < 0) - __blk_end_request_all(req, -EIO); + port = req->rq_disk->private_data; + dr = &port->vio.drings[VIO_DRIVER_TX_RING]; + if (unlikely(vdc_tx_dring_avail(dr) < 1)) + goto wait; + + blk_start_request(req); + + if (__send_request(req) < 0) { + blk_requeue_request(rq, req); +wait: + /* Avoid pointless unplugs. */ + blk_stop_queue(rq); + break; + } } } @@ -656,25 +708,27 @@ static int probe_disk(struct vdc_port *port) if (comp.err) return comp.err; - err = generic_request(port, VD_OP_GET_VTOC, - &port->label, sizeof(port->label)); - if (err < 0) { - printk(KERN_ERR PFX "VD_OP_GET_VTOC returns error %d\n", err); - return err; - } - - err = generic_request(port, VD_OP_GET_DISKGEOM, - &port->geom, sizeof(port->geom)); - if (err < 0) { - printk(KERN_ERR PFX "VD_OP_GET_DISKGEOM returns " - "error %d\n", err); - return err; + if (vdc_version_supported(port, 1, 1)) { + /* vdisk_size should be set during the handshake, if it wasn't + * then the underlying disk is reserved by another system + */ + if (port->vdisk_size == -1) + return -ENODEV; + } else { + struct vio_disk_geom geom; + + err = generic_request(port, VD_OP_GET_DISKGEOM, + &geom, sizeof(geom)); + if (err < 0) { + printk(KERN_ERR PFX "VD_OP_GET_DISKGEOM returns " + "error %d\n", err); + return err; + } + port->vdisk_size = ((u64)geom.num_cyl * + (u64)geom.num_hd * + (u64)geom.num_sec); } - port->vdisk_size = ((u64)port->geom.num_cyl * - (u64)port->geom.num_hd * - (u64)port->geom.num_sec); - q = blk_init_queue(do_vdc_request, &port->vio.lock); if (!q) { printk(KERN_ERR PFX "%s: Could not allocate queue.\n", @@ -691,6 +745,10 @@ static int probe_disk(struct vdc_port *port) port->disk = g; + /* Each segment in a request is up to an aligned page in size. */ + blk_queue_segment_boundary(q, PAGE_SIZE - 1); + blk_queue_max_segment_size(q, PAGE_SIZE); + blk_queue_max_segments(q, port->ring_cookies); blk_queue_max_hw_sectors(q, port->max_xfer_size); g->major = vdc_major; @@ -704,9 +762,32 @@ static int probe_disk(struct vdc_port *port) set_capacity(g, port->vdisk_size); - printk(KERN_INFO PFX "%s: %u sectors (%u MB)\n", + if (vdc_version_supported(port, 1, 1)) { + switch (port->vdisk_mtype) { + case VD_MEDIA_TYPE_CD: + pr_info(PFX "Virtual CDROM %s\n", port->disk_name); + g->flags |= GENHD_FL_CD; + g->flags |= GENHD_FL_REMOVABLE; + set_disk_ro(g, 1); + break; + + case VD_MEDIA_TYPE_DVD: + pr_info(PFX "Virtual DVD %s\n", port->disk_name); + g->flags |= GENHD_FL_CD; + g->flags |= GENHD_FL_REMOVABLE; + set_disk_ro(g, 1); + break; + + case VD_MEDIA_TYPE_FIXED: + pr_info(PFX "Virtual Hard disk %s\n", port->disk_name); + break; + } + } + + pr_info(PFX "%s: %u sectors (%u MB) protocol %d.%d\n", g->disk_name, - port->vdisk_size, (port->vdisk_size >> (20 - 9))); + port->vdisk_size, (port->vdisk_size >> (20 - 9)), + port->vio.ver.major, port->vio.ver.minor); add_disk(g); @@ -765,6 +846,7 @@ static int vdc_port_probe(struct vio_dev *vdev, const struct vio_device_id *id) else snprintf(port->disk_name, sizeof(port->disk_name), VDCBLK_NAME "%c", 'a' + ((int)vdev->dev_no % 26)); + port->vdisk_size = -1; err = vio_driver_init(&port->vio, vdev, VDEV_DISK, vdc_versions, ARRAY_SIZE(vdc_versions), diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 51c557cfd92b..d8ddb8e2adc1 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -447,7 +447,8 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, } if (page_zero_filled(uncmem)) { - kunmap_atomic(user_mem); + if (user_mem) + kunmap_atomic(user_mem); /* Free memory associated with this sector now. */ write_lock(&zram->meta->tb_lock); zram_free_page(zram, index); diff --git a/drivers/char/hw_random/pseries-rng.c b/drivers/char/hw_random/pseries-rng.c index ab7ffdec0ec3..f38f2c13e79c 100644 --- a/drivers/char/hw_random/pseries-rng.c +++ b/drivers/char/hw_random/pseries-rng.c @@ -25,18 +25,21 @@ #include -static int pseries_rng_data_read(struct hwrng *rng, u32 *data) +static int pseries_rng_read(struct hwrng *rng, void *data, size_t max, bool wait) { + u64 buffer[PLPAR_HCALL_BUFSIZE]; + size_t size = max < 8 ? max : 8; int rc; - rc = plpar_hcall(H_RANDOM, (unsigned long *)data); + rc = plpar_hcall(H_RANDOM, (unsigned long *)buffer); if (rc != H_SUCCESS) { pr_err_ratelimited("H_RANDOM call failed %d\n", rc); return -EIO; } + memcpy(data, buffer, size); /* The hypervisor interface returns 64 bits */ - return 8; + return size; } /** @@ -55,7 +58,7 @@ static unsigned long pseries_rng_get_desired_dma(struct vio_dev *vdev) static struct hwrng pseries_rng = { .name = KBUILD_MODNAME, - .data_read = pseries_rng_data_read, + .read = pseries_rng_read, }; static int __init pseries_rng_probe(struct vio_dev *dev, diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c index a4127453baae..d97a03dbf42c 100644 --- a/drivers/crypto/caam/caamhash.c +++ b/drivers/crypto/caam/caamhash.c @@ -835,8 +835,9 @@ static int ahash_update_ctx(struct ahash_request *req) edesc->sec4_sg + sec4_sg_src_index, chained); if (*next_buflen) { - sg_copy_part(next_buf, req->src, to_hash - - *buflen, req->nbytes); + scatterwalk_map_and_copy(next_buf, req->src, + to_hash - *buflen, + *next_buflen, 0); state->current_buf = !state->current_buf; } } else { @@ -869,7 +870,8 @@ static int ahash_update_ctx(struct ahash_request *req) kfree(edesc); } } else if (*next_buflen) { - sg_copy(buf + *buflen, req->src, req->nbytes); + scatterwalk_map_and_copy(buf + *buflen, req->src, 0, + req->nbytes, 0); *buflen = *next_buflen; *next_buflen = last_buflen; } @@ -1216,8 +1218,9 @@ static int ahash_update_no_ctx(struct ahash_request *req) src_map_to_sec4_sg(jrdev, req->src, src_nents, edesc->sec4_sg + 1, chained); if (*next_buflen) { - sg_copy_part(next_buf, req->src, to_hash - *buflen, - req->nbytes); + scatterwalk_map_and_copy(next_buf, req->src, + to_hash - *buflen, + *next_buflen, 0); state->current_buf = !state->current_buf; } @@ -1248,7 +1251,8 @@ static int ahash_update_no_ctx(struct ahash_request *req) kfree(edesc); } } else if (*next_buflen) { - sg_copy(buf + *buflen, req->src, req->nbytes); + scatterwalk_map_and_copy(buf + *buflen, req->src, 0, + req->nbytes, 0); *buflen = *next_buflen; *next_buflen = 0; } @@ -1405,7 +1409,8 @@ static int ahash_update_first(struct ahash_request *req) } if (*next_buflen) - sg_copy_part(next_buf, req->src, to_hash, req->nbytes); + scatterwalk_map_and_copy(next_buf, req->src, to_hash, + *next_buflen, 0); sh_len = desc_len(sh_desc); desc = edesc->hw_desc; @@ -1438,7 +1443,8 @@ static int ahash_update_first(struct ahash_request *req) state->update = ahash_update_no_ctx; state->finup = ahash_finup_no_ctx; state->final = ahash_final_no_ctx; - sg_copy(next_buf, req->src, req->nbytes); + scatterwalk_map_and_copy(next_buf, req->src, 0, + req->nbytes, 0); } #ifdef DEBUG print_hex_dump(KERN_ERR, "next buf@"__stringify(__LINE__)": ", diff --git a/drivers/crypto/caam/key_gen.c b/drivers/crypto/caam/key_gen.c index ea2e406610eb..b872eed2957b 100644 --- a/drivers/crypto/caam/key_gen.c +++ b/drivers/crypto/caam/key_gen.c @@ -51,23 +51,29 @@ int gen_split_key(struct device *jrdev, u8 *key_out, int split_key_len, u32 *desc; struct split_key_result result; dma_addr_t dma_addr_in, dma_addr_out; - int ret = 0; + int ret = -ENOMEM; desc = kmalloc(CAAM_CMD_SZ * 6 + CAAM_PTR_SZ * 2, GFP_KERNEL | GFP_DMA); if (!desc) { dev_err(jrdev, "unable to allocate key input memory\n"); - return -ENOMEM; + return ret; } - init_job_desc(desc, 0); - dma_addr_in = dma_map_single(jrdev, (void *)key_in, keylen, DMA_TO_DEVICE); if (dma_mapping_error(jrdev, dma_addr_in)) { dev_err(jrdev, "unable to map key input memory\n"); - kfree(desc); - return -ENOMEM; + goto out_free; } + + dma_addr_out = dma_map_single(jrdev, key_out, split_key_pad_len, + DMA_FROM_DEVICE); + if (dma_mapping_error(jrdev, dma_addr_out)) { + dev_err(jrdev, "unable to map key output memory\n"); + goto out_unmap_in; + } + + init_job_desc(desc, 0); append_key(desc, dma_addr_in, keylen, CLASS_2 | KEY_DEST_CLASS_REG); /* Sets MDHA up into an HMAC-INIT */ @@ -84,13 +90,6 @@ int gen_split_key(struct device *jrdev, u8 *key_out, int split_key_len, * FIFO_STORE with the explicit split-key content store * (0x26 output type) */ - dma_addr_out = dma_map_single(jrdev, key_out, split_key_pad_len, - DMA_FROM_DEVICE); - if (dma_mapping_error(jrdev, dma_addr_out)) { - dev_err(jrdev, "unable to map key output memory\n"); - kfree(desc); - return -ENOMEM; - } append_fifo_store(desc, dma_addr_out, split_key_len, LDST_CLASS_2_CCB | FIFOST_TYPE_SPLIT_KEK); @@ -118,10 +117,10 @@ int gen_split_key(struct device *jrdev, u8 *key_out, int split_key_len, dma_unmap_single(jrdev, dma_addr_out, split_key_pad_len, DMA_FROM_DEVICE); +out_unmap_in: dma_unmap_single(jrdev, dma_addr_in, keylen, DMA_TO_DEVICE); - +out_free: kfree(desc); - return ret; } EXPORT_SYMBOL(gen_split_key); diff --git a/drivers/crypto/caam/sg_sw_sec4.h b/drivers/crypto/caam/sg_sw_sec4.h index b12ff85f4241..ce28a563effc 100644 --- a/drivers/crypto/caam/sg_sw_sec4.h +++ b/drivers/crypto/caam/sg_sw_sec4.h @@ -116,57 +116,3 @@ static int dma_unmap_sg_chained(struct device *dev, struct scatterlist *sg, } return nents; } - -/* Map SG page in kernel virtual address space and copy */ -static inline void sg_map_copy(u8 *dest, struct scatterlist *sg, - int len, int offset) -{ - u8 *mapped_addr; - - /* - * Page here can be user-space pinned using get_user_pages - * Same must be kmapped before use and kunmapped subsequently - */ - mapped_addr = kmap_atomic(sg_page(sg)); - memcpy(dest, mapped_addr + offset, len); - kunmap_atomic(mapped_addr); -} - -/* Copy from len bytes of sg to dest, starting from beginning */ -static inline void sg_copy(u8 *dest, struct scatterlist *sg, unsigned int len) -{ - struct scatterlist *current_sg = sg; - int cpy_index = 0, next_cpy_index = current_sg->length; - - while (next_cpy_index < len) { - sg_map_copy(dest + cpy_index, current_sg, current_sg->length, - current_sg->offset); - current_sg = scatterwalk_sg_next(current_sg); - cpy_index = next_cpy_index; - next_cpy_index += current_sg->length; - } - if (cpy_index < len) - sg_map_copy(dest + cpy_index, current_sg, len-cpy_index, - current_sg->offset); -} - -/* Copy sg data, from to_skip to end, to dest */ -static inline void sg_copy_part(u8 *dest, struct scatterlist *sg, - int to_skip, unsigned int end) -{ - struct scatterlist *current_sg = sg; - int sg_index, cpy_index, offset; - - sg_index = current_sg->length; - while (sg_index <= to_skip) { - current_sg = scatterwalk_sg_next(current_sg); - sg_index += current_sg->length; - } - cpy_index = sg_index - to_skip; - offset = current_sg->offset + current_sg->length - cpy_index; - sg_map_copy(dest, current_sg, cpy_index, offset); - if (end - sg_index) { - current_sg = scatterwalk_sg_next(current_sg); - sg_copy(dest + cpy_index, current_sg, end - sg_index); - } -} diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index d7d5c8af92b9..6d4456898007 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -1637,8 +1637,7 @@ static int dispatch_ioctl(struct client *client, _IOC_SIZE(cmd) > sizeof(buffer)) return -ENOTTY; - if (_IOC_DIR(cmd) == _IOC_READ) - memset(&buffer, 0, _IOC_SIZE(cmd)); + memset(&buffer, 0, sizeof(buffer)); if (_IOC_DIR(cmd) & _IOC_WRITE) if (copy_from_user(&buffer, arg, _IOC_SIZE(cmd))) diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c index ab5c26575622..ddf70d6c0270 100644 --- a/drivers/gpu/drm/radeon/cik.c +++ b/drivers/gpu/drm/radeon/cik.c @@ -3936,8 +3936,8 @@ static int cik_cp_gfx_start(struct radeon_device *rdev) /* init the CE partitions. CE only used for gfx on CIK */ radeon_ring_write(ring, PACKET3(PACKET3_SET_BASE, 2)); radeon_ring_write(ring, PACKET3_BASE_INDEX(CE_PARTITION_BASE)); - radeon_ring_write(ring, 0xc000); - radeon_ring_write(ring, 0xc000); + radeon_ring_write(ring, 0x8000); + radeon_ring_write(ring, 0x8000); /* setup clear context state */ radeon_ring_write(ring, PACKET3(PACKET3_PREAMBLE_CNTL, 0)); @@ -8893,6 +8893,9 @@ void dce8_bandwidth_update(struct radeon_device *rdev) u32 num_heads = 0, lb_size; int i; + if (!rdev->mode_info.mode_config_initialized) + return; + radeon_update_display_priority(rdev); for (i = 0; i < rdev->num_crtc; i++) { diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 4b3c5f7ae63b..7138f3e31b7c 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -2362,6 +2362,9 @@ void evergreen_bandwidth_update(struct radeon_device *rdev) u32 num_heads = 0, lb_size; int i; + if (!rdev->mode_info.mode_config_initialized) + return; + radeon_update_display_priority(rdev); for (i = 0; i < rdev->num_crtc; i++) { @@ -2570,6 +2573,7 @@ void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *sav WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1); tmp |= EVERGREEN_CRTC_BLANK_DATA_EN; WREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i], tmp); + WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0); } } else { tmp = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]); diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c index 3cc78bb66042..07620e198a6d 100644 --- a/drivers/gpu/drm/radeon/r100.c +++ b/drivers/gpu/drm/radeon/r100.c @@ -3219,6 +3219,9 @@ void r100_bandwidth_update(struct radeon_device *rdev) uint32_t pixel_bytes1 = 0; uint32_t pixel_bytes2 = 0; + if (!rdev->mode_info.mode_config_initialized) + return; + radeon_update_display_priority(rdev); if (rdev->mode_info.crtcs[0]->base.enabled) { diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c index 95b693c11640..e5619d5e2a30 100644 --- a/drivers/gpu/drm/radeon/rs600.c +++ b/drivers/gpu/drm/radeon/rs600.c @@ -890,6 +890,9 @@ void rs600_bandwidth_update(struct radeon_device *rdev) u32 d1mode_priority_a_cnt, d2mode_priority_a_cnt; /* FIXME: implement full support */ + if (!rdev->mode_info.mode_config_initialized) + return; + radeon_update_display_priority(rdev); if (rdev->mode_info.crtcs[0]->base.enabled) diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c index 3462b64369bf..0a2d36e81108 100644 --- a/drivers/gpu/drm/radeon/rs690.c +++ b/drivers/gpu/drm/radeon/rs690.c @@ -579,6 +579,9 @@ void rs690_bandwidth_update(struct radeon_device *rdev) u32 d1mode_priority_a_cnt, d1mode_priority_b_cnt; u32 d2mode_priority_a_cnt, d2mode_priority_b_cnt; + if (!rdev->mode_info.mode_config_initialized) + return; + radeon_update_display_priority(rdev); if (rdev->mode_info.crtcs[0]->base.enabled) diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c index 237dd29d9f1c..b49965a21a2d 100644 --- a/drivers/gpu/drm/radeon/rv515.c +++ b/drivers/gpu/drm/radeon/rv515.c @@ -1276,6 +1276,9 @@ void rv515_bandwidth_update(struct radeon_device *rdev) struct drm_display_mode *mode0 = NULL; struct drm_display_mode *mode1 = NULL; + if (!rdev->mode_info.mode_config_initialized) + return; + radeon_update_display_priority(rdev); if (rdev->mode_info.crtcs[0]->base.enabled) diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index 559564c1dc97..52b64ad285d6 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -2227,6 +2227,9 @@ void dce6_bandwidth_update(struct radeon_device *rdev) u32 num_heads = 0, lb_size; int i; + if (!rdev->mode_info.mode_config_initialized) + return; + radeon_update_display_priority(rdev); for (i = 0; i < rdev->num_crtc; i++) { diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index ea6203ee7bcc..23467a2abd62 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -2425,6 +2425,8 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file, attr.grh.sgid_index = cmd.attr.grh.sgid_index; attr.grh.hop_limit = cmd.attr.grh.hop_limit; attr.grh.traffic_class = cmd.attr.grh.traffic_class; + attr.vlan_id = 0; + memset(&attr.dmac, 0, sizeof(attr.dmac)); memcpy(attr.grh.dgid.raw, cmd.attr.grh.dgid, 16); ah = ib_create_ah(pd, &attr); diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c index fb15c64ffb95..4979b00fbf04 100644 --- a/drivers/input/mouse/alps.c +++ b/drivers/input/mouse/alps.c @@ -1047,7 +1047,13 @@ static psmouse_ret_t alps_process_byte(struct psmouse *psmouse) { struct alps_data *priv = psmouse->private; - if ((psmouse->packet[0] & 0xc8) == 0x08) { /* PS/2 packet */ + /* + * Check if we are dealing with a bare PS/2 packet, presumably from + * a device connected to the external PS/2 port. Because bare PS/2 + * protocol does not have enough constant bits to self-synchronize + * properly we only do this if the device is fully synchronized. + */ + if (!psmouse->out_of_sync_cnt && (psmouse->packet[0] & 0xc8) == 0x08) { if (psmouse->pktcnt == 3) { alps_report_bare_ps2_packet(psmouse, psmouse->packet, true); @@ -1071,12 +1077,27 @@ static psmouse_ret_t alps_process_byte(struct psmouse *psmouse) } /* Bytes 2 - pktsize should have 0 in the highest bit */ - if ((priv->proto_version < ALPS_PROTO_V5) && + if (priv->proto_version < ALPS_PROTO_V5 && psmouse->pktcnt >= 2 && psmouse->pktcnt <= psmouse->pktsize && (psmouse->packet[psmouse->pktcnt - 1] & 0x80)) { psmouse_dbg(psmouse, "refusing packet[%i] = %x\n", psmouse->pktcnt - 1, psmouse->packet[psmouse->pktcnt - 1]); + + if (priv->proto_version == ALPS_PROTO_V3 && + psmouse->pktcnt == psmouse->pktsize) { + /* + * Some Dell boxes, such as Latitude E6440 or E7440 + * with closed lid, quite often smash last byte of + * otherwise valid packet with 0xff. Given that the + * next packet is very likely to be valid let's + * report PSMOUSE_FULL_PACKET but not process data, + * rather than reporting PSMOUSE_BAD_DATA and + * filling the logs. + */ + return PSMOUSE_FULL_PACKET; + } + return PSMOUSE_BAD_DATA; } @@ -2148,6 +2169,9 @@ int alps_init(struct psmouse *psmouse) /* We are having trouble resyncing ALPS touchpads so disable it for now */ psmouse->resync_time = 0; + /* Allow 2 invalid packets without resetting device */ + psmouse->resetafter = psmouse->pktsize * 2; + return 0; init_fail: diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index a50a2a7a43f7..1e76eb8f06c7 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -132,8 +132,8 @@ static const struct min_max_quirk min_max_pnpid_table[] = { 1232, 5710, 1156, 4696 }, { - (const char * const []){"LEN0034", "LEN0036", "LEN2002", - "LEN2004", NULL}, + (const char * const []){"LEN0034", "LEN0036", "LEN0039", + "LEN2002", "LEN2004", NULL}, 1024, 5112, 2024, 4832 }, { @@ -160,6 +160,7 @@ static const char * const topbuttonpad_pnp_ids[] = { "LEN0036", /* T440 */ "LEN0037", "LEN0038", + "LEN0039", /* T440s */ "LEN0041", "LEN0042", /* Yoga */ "LEN0045", diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index ca1621b49453..a1cebf745b22 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1448,9 +1448,9 @@ static void drop_buffers(struct dm_bufio_client *c) /* * Test if the buffer is unused and too old, and commit it. - * At if noio is set, we must not do any I/O because we hold - * dm_bufio_clients_lock and we would risk deadlock if the I/O gets rerouted to - * different bufio client. + * And if GFP_NOFS is used, we must not do any I/O because we hold + * dm_bufio_clients_lock and we would risk deadlock if the I/O gets + * rerouted to different bufio client. */ static int __cleanup_old_buffer(struct dm_buffer *b, gfp_t gfp, unsigned long max_jiffies) @@ -1458,7 +1458,7 @@ static int __cleanup_old_buffer(struct dm_buffer *b, gfp_t gfp, if (jiffies - b->last_accessed < max_jiffies) return 0; - if (!(gfp & __GFP_IO)) { + if (!(gfp & __GFP_FS)) { if (test_bit(B_READING, &b->state) || test_bit(B_WRITING, &b->state) || test_bit(B_DIRTY, &b->state)) @@ -1500,7 +1500,7 @@ 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_IO) + if (sc->gfp_mask & __GFP_FS) dm_bufio_lock(c); else if (!dm_bufio_trylock(c)) return SHRINK_STOP; @@ -1517,7 +1517,7 @@ dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc) unsigned long count; c = container_of(shrink, struct dm_bufio_client, shrinker); - if (sc->gfp_mask & __GFP_IO) + if (sc->gfp_mask & __GFP_FS) dm_bufio_lock(c); else if (!dm_bufio_trylock(c)) return 0; diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 4880b69e2e9e..59715389b3cf 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -785,8 +785,7 @@ struct dm_raid_superblock { __le32 layout; __le32 stripe_sectors; - __u8 pad[452]; /* Round struct to 512 bytes. */ - /* Always set to 0 when writing. */ + /* Remainder of a logical block is zero-filled when writing (see super_sync()). */ } __packed; static int read_disk_sb(struct md_rdev *rdev, int size) @@ -823,7 +822,7 @@ static void super_sync(struct mddev *mddev, struct md_rdev *rdev) test_bit(Faulty, &(rs->dev[i].rdev.flags))) failed_devices |= (1ULL << i); - memset(sb, 0, sizeof(*sb)); + memset(sb + 1, 0, rdev->sb_size - sizeof(*sb)); sb->magic = cpu_to_le32(DM_RAID_MAGIC); sb->features = cpu_to_le32(0); /* No features yet */ @@ -858,7 +857,11 @@ static int super_load(struct md_rdev *rdev, struct md_rdev *refdev) uint64_t events_sb, events_refsb; rdev->sb_start = 0; - rdev->sb_size = sizeof(*sb); + rdev->sb_size = bdev_logical_block_size(rdev->meta_bdev); + if (rdev->sb_size < sizeof(*sb) || rdev->sb_size > PAGE_SIZE) { + DMERR("superblock size of a logical block is no longer valid"); + return -EINVAL; + } ret = read_disk_sb(rdev, rdev->sb_size); if (ret) diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 359af3a519b5..37f2648c112b 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -1704,6 +1704,14 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_SUBMITTED; } + /* + * We must hold the virtual cell before doing the lookup, otherwise + * there's a race with discard. + */ + build_virtual_key(tc->td, block, &key); + if (dm_bio_detain(tc->pool->prison, &key, bio, &cell1, &cell_result)) + return DM_MAPIO_SUBMITTED; + r = dm_thin_find_block(td, block, 0, &result); /* @@ -1727,13 +1735,10 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) * shared flag will be set in their case. */ thin_defer_bio(tc, bio); + cell_defer_no_holder_no_free(tc, &cell1); return DM_MAPIO_SUBMITTED; } - build_virtual_key(tc->td, block, &key); - if (dm_bio_detain(tc->pool->prison, &key, bio, &cell1, &cell_result)) - return DM_MAPIO_SUBMITTED; - build_data_key(tc->td, result.block, &key); if (dm_bio_detain(tc->pool->prison, &key, bio, &cell2, &cell_result)) { cell_defer_no_holder_no_free(tc, &cell1); @@ -1754,6 +1759,7 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) * of doing so. */ handle_unserviceable_bio(tc->pool, bio); + cell_defer_no_holder_no_free(tc, &cell1); return DM_MAPIO_SUBMITTED; } /* fall through */ @@ -1764,6 +1770,7 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) * provide the hint to load the metadata into cache. */ thin_defer_bio(tc, bio); + cell_defer_no_holder_no_free(tc, &cell1); return DM_MAPIO_SUBMITTED; default: @@ -1773,6 +1780,7 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) * pool is switched to fail-io mode. */ bio_io_error(bio); + cell_defer_no_holder_no_free(tc, &cell1); return DM_MAPIO_SUBMITTED; } } diff --git a/drivers/md/md.c b/drivers/md/md.c index 73aedcb639c0..40959ee73583 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5333,6 +5333,7 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev) printk("md: %s still in use.\n",mdname(mddev)); if (did_freeze) { clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); } err = -EBUSY; @@ -5347,6 +5348,8 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev) mddev->ro = 1; set_disk_ro(mddev->gendisk, 1); clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + md_wakeup_thread(mddev->thread); sysfs_notify_dirent_safe(mddev->sysfs_state); err = 0; } @@ -5390,6 +5393,7 @@ static int do_md_stop(struct mddev * mddev, int mode, mutex_unlock(&mddev->open_mutex); if (did_freeze) { clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); } return -EBUSY; diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h index 37d367bb9aa8..bf2b80d5c470 100644 --- a/drivers/md/persistent-data/dm-btree-internal.h +++ b/drivers/md/persistent-data/dm-btree-internal.h @@ -42,6 +42,12 @@ struct btree_node { } __packed; +/* + * Locks a block using the btree node validator. + */ +int bn_read_lock(struct dm_btree_info *info, dm_block_t b, + struct dm_block **result); + void inc_children(struct dm_transaction_manager *tm, struct btree_node *n, struct dm_btree_value_type *vt); diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c index cf9fd676ae44..1b5e13ec7f96 100644 --- a/drivers/md/persistent-data/dm-btree-spine.c +++ b/drivers/md/persistent-data/dm-btree-spine.c @@ -92,7 +92,7 @@ struct dm_block_validator btree_node_validator = { /*----------------------------------------------------------------*/ -static int bn_read_lock(struct dm_btree_info *info, dm_block_t b, +int bn_read_lock(struct dm_btree_info *info, dm_block_t b, struct dm_block **result) { return dm_tm_read_lock(info->tm, b, &btree_node_validator, result); diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c index 416060c25709..200ac12a1d40 100644 --- a/drivers/md/persistent-data/dm-btree.c +++ b/drivers/md/persistent-data/dm-btree.c @@ -847,22 +847,26 @@ EXPORT_SYMBOL_GPL(dm_btree_find_lowest_key); * FIXME: We shouldn't use a recursive algorithm when we have limited stack * space. Also this only works for single level trees. */ -static int walk_node(struct ro_spine *s, dm_block_t block, +static int walk_node(struct dm_btree_info *info, dm_block_t block, int (*fn)(void *context, uint64_t *keys, void *leaf), void *context) { int r; unsigned i, nr; + struct dm_block *node; struct btree_node *n; uint64_t keys; - r = ro_step(s, block); - n = ro_node(s); + r = bn_read_lock(info, block, &node); + if (r) + return r; + + n = dm_block_data(node); nr = le32_to_cpu(n->header.nr_entries); for (i = 0; i < nr; i++) { if (le32_to_cpu(n->header.flags) & INTERNAL_NODE) { - r = walk_node(s, value64(n, i), fn, context); + r = walk_node(info, value64(n, i), fn, context); if (r) goto out; } else { @@ -874,7 +878,7 @@ static int walk_node(struct ro_spine *s, dm_block_t block, } out: - ro_pop(s); + dm_tm_unlock(info->tm, node); return r; } @@ -882,15 +886,7 @@ int dm_btree_walk(struct dm_btree_info *info, dm_block_t root, int (*fn)(void *context, uint64_t *keys, void *leaf), void *context) { - int r; - struct ro_spine spine; - BUG_ON(info->levels > 1); - - init_ro_spine(&spine, info); - r = walk_node(&spine, root, fn, context); - exit_ro_spine(&spine); - - return r; + return walk_node(info, root, fn, context); } EXPORT_SYMBOL_GPL(dm_btree_walk); diff --git a/drivers/media/usb/ttusb-dec/ttusbdecfe.c b/drivers/media/usb/ttusb-dec/ttusbdecfe.c index 5c45c9d0712d..9c29552aedec 100644 --- a/drivers/media/usb/ttusb-dec/ttusbdecfe.c +++ b/drivers/media/usb/ttusb-dec/ttusbdecfe.c @@ -156,6 +156,9 @@ static int ttusbdecfe_dvbs_diseqc_send_master_cmd(struct dvb_frontend* fe, struc 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }; + if (cmd->msg_len > sizeof(b) - 4) + return -EINVAL; + memcpy(&b[4], cmd->msg, cmd->msg_len); state->config->send_command(fe, 0x72, diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c index 6382b7c416f4..e10f5ed26181 100644 --- a/drivers/net/ethernet/smsc/smsc911x.c +++ b/drivers/net/ethernet/smsc/smsc911x.c @@ -1341,6 +1341,42 @@ static void smsc911x_rx_multicast_update_workaround(struct smsc911x_data *pdata) spin_unlock(&pdata->mac_lock); } +static int smsc911x_phy_general_power_up(struct smsc911x_data *pdata) +{ + int rc = 0; + + if (!pdata->phy_dev) + return rc; + + /* If the internal PHY is in General Power-Down mode, all, except the + * management interface, is powered-down and stays in that condition as + * long as Phy register bit 0.11 is HIGH. + * + * In that case, clear the bit 0.11, so the PHY powers up and we can + * access to the phy registers. + */ + rc = phy_read(pdata->phy_dev, MII_BMCR); + if (rc < 0) { + SMSC_WARN(pdata, drv, "Failed reading PHY control reg"); + return rc; + } + + /* If the PHY general power-down bit is not set is not necessary to + * disable the general power down-mode. + */ + if (rc & BMCR_PDOWN) { + rc = phy_write(pdata->phy_dev, MII_BMCR, rc & ~BMCR_PDOWN); + if (rc < 0) { + SMSC_WARN(pdata, drv, "Failed writing PHY control reg"); + return rc; + } + + usleep_range(1000, 1500); + } + + return 0; +} + static int smsc911x_phy_disable_energy_detect(struct smsc911x_data *pdata) { int rc = 0; @@ -1414,6 +1450,16 @@ static int smsc911x_soft_reset(struct smsc911x_data *pdata) int ret; /* + * Make sure to power-up the PHY chip before doing a reset, otherwise + * the reset fails. + */ + ret = smsc911x_phy_general_power_up(pdata); + if (ret) { + SMSC_WARN(pdata, drv, "Failed to power-up the PHY chip"); + return ret; + } + + /* * LAN9210/LAN9211/LAN9220/LAN9221 chips have an internal PHY that * are initialized in a Energy Detect Power-Down mode that prevents * the MAC chip to be software reseted. So we have to wakeup the PHY diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index fd411d6e19a2..03ae9def0e0c 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -656,7 +656,7 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev) spin_lock_irqsave(&port->vio.lock, flags); dr = &port->vio.drings[VIO_DRIVER_TX_RING]; - if (unlikely(vnet_tx_dring_avail(dr) < 2)) { + if (unlikely(vnet_tx_dring_avail(dr) < 1)) { if (!netif_queue_stopped(dev)) { netif_stop_queue(dev); @@ -704,7 +704,7 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev) dev->stats.tx_bytes += skb->len; dr->prod = (dr->prod + 1) & (VNET_TX_RING_SIZE - 1); - if (unlikely(vnet_tx_dring_avail(dr) < 2)) { + if (unlikely(vnet_tx_dring_avail(dr) < 1)) { netif_stop_queue(dev); if (vnet_tx_dring_avail(dr) > VNET_TX_WAKEUP_THRESH(dr)) netif_wake_queue(dev); diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index f30ceb17d5fc..07c942b6ae01 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -66,7 +66,7 @@ static struct cdev macvtap_cdev; static const struct proto_ops macvtap_socket_ops; #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \ - NETIF_F_TSO6) + NETIF_F_TSO6 | NETIF_F_UFO) #define RX_OFFLOADS (NETIF_F_GRO | NETIF_F_LRO) #define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG) @@ -570,8 +570,6 @@ static int macvtap_skb_from_vnet_hdr(struct sk_buff *skb, gso_type = SKB_GSO_TCPV6; break; case VIRTIO_NET_HDR_GSO_UDP: - pr_warn_once("macvtap: %s: using disabled UFO feature; please fix this program\n", - current->comm); gso_type = SKB_GSO_UDP; if (skb->protocol == htons(ETH_P_IPV6)) ipv6_proxy_select_ident(skb); @@ -619,6 +617,8 @@ static void macvtap_skb_to_vnet_hdr(const struct sk_buff *skb, vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (sinfo->gso_type & SKB_GSO_TCPV6) vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6; + else if (sinfo->gso_type & SKB_GSO_UDP) + vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP; else BUG(); if (sinfo->gso_type & SKB_GSO_TCP_ECN) @@ -629,6 +629,8 @@ static void macvtap_skb_to_vnet_hdr(const struct sk_buff *skb, if (skb->ip_summed == CHECKSUM_PARTIAL) { vnet_hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; vnet_hdr->csum_start = skb_checksum_start_offset(skb); + if (vlan_tx_tag_present(skb)) + vnet_hdr->csum_start += VLAN_HLEN; vnet_hdr->csum_offset = skb->csum_offset; } else if (skb->ip_summed == CHECKSUM_UNNECESSARY) { vnet_hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID; @@ -953,6 +955,9 @@ static int set_offload(struct macvtap_queue *q, unsigned long arg) if (arg & TUN_F_TSO6) feature_mask |= NETIF_F_TSO6; } + + if (arg & TUN_F_UFO) + feature_mask |= NETIF_F_UFO; } /* tun/tap driver inverts the usage for TSO offloads, where @@ -963,7 +968,7 @@ static int set_offload(struct macvtap_queue *q, unsigned long arg) * When user space turns off TSO, we turn off GSO/LRO so that * user-space will not receive TSO frames. */ - if (feature_mask & (NETIF_F_TSO | NETIF_F_TSO6)) + if (feature_mask & (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_UFO)) features |= RX_OFFLOADS; else features &= ~RX_OFFLOADS; @@ -1064,7 +1069,7 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd, case TUNSETOFFLOAD: /* let the user check for future flags */ if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 | - TUN_F_TSO_ECN)) + TUN_F_TSO_ECN | TUN_F_UFO)) return -EINVAL; rtnl_lock(); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 2c8b1c21c452..ec63314d6480 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -175,7 +175,7 @@ struct tun_struct { struct net_device *dev; netdev_features_t set_features; #define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \ - NETIF_F_TSO6) + NETIF_F_TSO6|NETIF_F_UFO) int vnet_hdr_sz; int sndbuf; @@ -1153,20 +1153,10 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; break; case VIRTIO_NET_HDR_GSO_UDP: - { - static bool warned; - - if (!warned) { - warned = true; - netdev_warn(tun->dev, - "%s: using disabled UFO feature; please fix this program\n", - current->comm); - } skb_shinfo(skb)->gso_type = SKB_GSO_UDP; if (skb->protocol == htons(ETH_P_IPV6)) ipv6_proxy_select_ident(skb); break; - } default: tun->dev->stats.rx_frame_errors++; kfree_skb(skb); @@ -1236,6 +1226,10 @@ static ssize_t tun_put_user(struct tun_struct *tun, struct tun_pi pi = { 0, skb->protocol }; ssize_t total = 0; int vlan_offset = 0, copied; + int vlan_hlen = 0; + + if (vlan_tx_tag_present(skb)) + vlan_hlen = VLAN_HLEN; if (!(tun->flags & TUN_NO_PI)) { if ((len -= sizeof(pi)) < 0) @@ -1266,6 +1260,8 @@ static ssize_t tun_put_user(struct tun_struct *tun, gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (sinfo->gso_type & SKB_GSO_TCPV6) gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV6; + else if (sinfo->gso_type & SKB_GSO_UDP) + gso.gso_type = VIRTIO_NET_HDR_GSO_UDP; else { pr_err("unexpected GSO type: " "0x%x, gso_size %d, hdr_len %d\n", @@ -1285,7 +1281,8 @@ static ssize_t tun_put_user(struct tun_struct *tun, if (skb->ip_summed == CHECKSUM_PARTIAL) { gso.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; - gso.csum_start = skb_checksum_start_offset(skb); + gso.csum_start = skb_checksum_start_offset(skb) + + vlan_hlen; gso.csum_offset = skb->csum_offset; } else if (skb->ip_summed == CHECKSUM_UNNECESSARY) { gso.flags = VIRTIO_NET_HDR_F_DATA_VALID; @@ -1298,10 +1295,9 @@ static ssize_t tun_put_user(struct tun_struct *tun, } copied = total; - total += skb->len; - if (!vlan_tx_tag_present(skb)) { - len = min_t(int, skb->len, len); - } else { + len = min_t(int, skb->len + vlan_hlen, len); + total += skb->len + vlan_hlen; + if (vlan_hlen) { int copy, ret; struct { __be16 h_vlan_proto; @@ -1312,8 +1308,6 @@ static ssize_t tun_put_user(struct tun_struct *tun, veth.h_vlan_TCI = htons(vlan_tx_tag_get(skb)); vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto); - len = min_t(int, skb->len + VLAN_HLEN, len); - total += VLAN_HLEN; copy = min_t(int, vlan_offset, len); ret = skb_copy_datagram_const_iovec(skb, 0, iv, copied, copy); @@ -1795,6 +1789,11 @@ static int set_offload(struct tun_struct *tun, unsigned long arg) features |= NETIF_F_TSO6; arg &= ~(TUN_F_TSO4|TUN_F_TSO6); } + + if (arg & TUN_F_UFO) { + features |= NETIF_F_UFO; + arg &= ~TUN_F_UFO; + } } /* This gives the user a way to test for new features in future by diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 07a3255fd3cc..841b60831df1 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -496,17 +496,8 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len) skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; break; case VIRTIO_NET_HDR_GSO_UDP: - { - static bool warned; - - if (!warned) { - warned = true; - netdev_warn(dev, - "host using disabled UFO feature; please fix it\n"); - } skb_shinfo(skb)->gso_type = SKB_GSO_UDP; break; - } case VIRTIO_NET_HDR_GSO_TCPV6: skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; break; @@ -845,6 +836,8 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb) hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV6; + else if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP) + hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_UDP; else BUG(); if (skb_shinfo(skb)->gso_type & SKB_GSO_TCP_ECN) @@ -1664,7 +1657,7 @@ static int virtnet_probe(struct virtio_device *vdev) dev->features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST; if (virtio_has_feature(vdev, VIRTIO_NET_F_GSO)) { - dev->hw_features |= NETIF_F_TSO + dev->hw_features |= NETIF_F_TSO | NETIF_F_UFO | NETIF_F_TSO_ECN | NETIF_F_TSO6; } /* Individual feature bits: what can host handle? */ @@ -1674,9 +1667,11 @@ static int virtnet_probe(struct virtio_device *vdev) dev->hw_features |= NETIF_F_TSO6; if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_ECN)) dev->hw_features |= NETIF_F_TSO_ECN; + if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_UFO)) + dev->hw_features |= NETIF_F_UFO; if (gso) - dev->features |= dev->hw_features & NETIF_F_ALL_TSO; + dev->features |= dev->hw_features & (NETIF_F_ALL_TSO|NETIF_F_UFO); /* (!csum && gso) case will be fixed by register_netdev() */ } if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_CSUM)) @@ -1716,7 +1711,8 @@ static int virtnet_probe(struct virtio_device *vdev) /* If we can receive ANY GSO packets, we must allocate large ones. */ if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) || virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6) || - virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN)) + virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN) || + virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_UFO)) vi->big_packets = true; if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) @@ -1907,9 +1903,9 @@ static struct virtio_device_id id_table[] = { static unsigned int features[] = { VIRTIO_NET_F_CSUM, VIRTIO_NET_F_GUEST_CSUM, VIRTIO_NET_F_GSO, VIRTIO_NET_F_MAC, - VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_TSO6, + VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_UFO, VIRTIO_NET_F_HOST_TSO6, VIRTIO_NET_F_HOST_ECN, VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6, - VIRTIO_NET_F_GUEST_ECN, + VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO, VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ, VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN, VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 0704a0402897..5441b49ef89d 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -279,13 +279,15 @@ static inline struct vxlan_rdst *first_remote_rtnl(struct vxlan_fdb *fdb) return list_first_entry(&fdb->remotes, struct vxlan_rdst, list); } -/* Find VXLAN socket based on network namespace and UDP port */ -static struct vxlan_sock *vxlan_find_sock(struct net *net, __be16 port) +/* Find VXLAN socket based on network namespace, address family and UDP port */ +static struct vxlan_sock *vxlan_find_sock(struct net *net, + sa_family_t family, __be16 port) { struct vxlan_sock *vs; hlist_for_each_entry_rcu(vs, vs_head(net, port), hlist) { - if (inet_sk(vs->sock->sk)->inet_sport == port) + if (inet_sk(vs->sock->sk)->inet_sport == port && + inet_sk(vs->sock->sk)->sk.sk_family == family) return vs; } return NULL; @@ -304,11 +306,12 @@ static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, u32 id) } /* Look up VNI in a per net namespace table */ -static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id, __be16 port) +static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id, + sa_family_t family, __be16 port) { struct vxlan_sock *vs; - vs = vxlan_find_sock(net, port); + vs = vxlan_find_sock(net, family, port); if (!vs) return NULL; @@ -1872,7 +1875,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, struct vxlan_dev *dst_vxlan; ip_rt_put(rt); - dst_vxlan = vxlan_find_vni(dev_net(dev), vni, dst_port); + dst_vxlan = vxlan_find_vni(dev_net(dev), vni, + dst->sa.sa_family, dst_port); if (!dst_vxlan) goto tx_error; vxlan_encap_bypass(skb, vxlan, dst_vxlan); @@ -1925,7 +1929,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, struct vxlan_dev *dst_vxlan; dst_release(ndst); - dst_vxlan = vxlan_find_vni(dev_net(dev), vni, dst_port); + dst_vxlan = vxlan_find_vni(dev_net(dev), vni, + dst->sa.sa_family, dst_port); if (!dst_vxlan) goto tx_error; vxlan_encap_bypass(skb, vxlan, dst_vxlan); @@ -2083,6 +2088,7 @@ static int vxlan_init(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id); + bool ipv6 = vxlan->flags & VXLAN_F_IPV6; struct vxlan_sock *vs; int i; @@ -2098,7 +2104,8 @@ static int vxlan_init(struct net_device *dev) spin_lock(&vn->sock_lock); - vs = vxlan_find_sock(dev_net(dev), vxlan->dst_port); + vs = vxlan_find_sock(dev_net(dev), ipv6 ? AF_INET6 : AF_INET, + vxlan->dst_port); if (vs) { /* If we have a socket with same port already, reuse it */ atomic_inc(&vs->refcnt); @@ -2566,7 +2573,7 @@ struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port, return vs; spin_lock(&vn->sock_lock); - vs = vxlan_find_sock(net, port); + vs = vxlan_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port); if (vs) { if (vs->rcv == rcv) atomic_inc(&vs->refcnt); @@ -2712,7 +2719,8 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, if (data[IFLA_VXLAN_PORT]) vxlan->dst_port = nla_get_be16(data[IFLA_VXLAN_PORT]); - if (vxlan_find_vni(net, vni, vxlan->dst_port)) { + if (vxlan_find_vni(net, vni, use_ipv6 ? AF_INET6 : AF_INET, + vxlan->dst_port)) { pr_info("duplicate VNI %u\n", vni); return -EEXIST; } diff --git a/drivers/net/wireless/iwlwifi/iwl-trans.h b/drivers/net/wireless/iwlwifi/iwl-trans.h index 1f065cf4a4ba..d090ed79ada0 100644 --- a/drivers/net/wireless/iwlwifi/iwl-trans.h +++ b/drivers/net/wireless/iwlwifi/iwl-trans.h @@ -514,6 +514,7 @@ enum iwl_trans_state { * Set during transport allocation. * @hw_id_str: a string with info about HW ID. Set during transport allocation. * @pm_support: set to true in start_hw if link pm is supported + * @ltr_enabled: set to true if the LTR is enabled * @dev_cmd_pool: pool for Tx cmd allocation - for internal use only. * The user should use iwl_trans_{alloc,free}_tx_cmd. * @dev_cmd_headroom: room needed for the transport's private use before the @@ -539,6 +540,7 @@ struct iwl_trans { u8 rx_mpdu_cmd, rx_mpdu_cmd_hdr_size; bool pm_support; + bool ltr_enabled; /* The following fields are internal only */ struct kmem_cache *dev_cmd_pool; diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h b/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h index 884c08725308..fa66471283d9 100644 --- a/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h +++ b/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h @@ -66,13 +66,46 @@ /* Power Management Commands, Responses, Notifications */ +/** + * enum iwl_ltr_config_flags - masks for LTR config command flags + * @LTR_CFG_FLAG_FEATURE_ENABLE: Feature operational status + * @LTR_CFG_FLAG_HW_DIS_ON_SHADOW_REG_ACCESS: allow LTR change on shadow + * memory access + * @LTR_CFG_FLAG_HW_EN_SHRT_WR_THROUGH: allow LTR msg send on ANY LTR + * reg change + * @LTR_CFG_FLAG_HW_DIS_ON_D0_2_D3: allow LTR msg send on transition from + * D0 to D3 + * @LTR_CFG_FLAG_SW_SET_SHORT: fixed static short LTR register + * @LTR_CFG_FLAG_SW_SET_LONG: fixed static short LONG register + * @LTR_CFG_FLAG_DENIE_C10_ON_PD: allow going into C10 on PD + */ +enum iwl_ltr_config_flags { + LTR_CFG_FLAG_FEATURE_ENABLE = BIT(0), + LTR_CFG_FLAG_HW_DIS_ON_SHADOW_REG_ACCESS = BIT(1), + LTR_CFG_FLAG_HW_EN_SHRT_WR_THROUGH = BIT(2), + LTR_CFG_FLAG_HW_DIS_ON_D0_2_D3 = BIT(3), + LTR_CFG_FLAG_SW_SET_SHORT = BIT(4), + LTR_CFG_FLAG_SW_SET_LONG = BIT(5), + LTR_CFG_FLAG_DENIE_C10_ON_PD = BIT(6), +}; + +/** + * struct iwl_ltr_config_cmd - configures the LTR + * @flags: See %enum iwl_ltr_config_flags + */ +struct iwl_ltr_config_cmd { + __le32 flags; + __le32 static_long; + __le32 static_short; +} __packed; + /* Radio LP RX Energy Threshold measured in dBm */ #define POWER_LPRX_RSSI_THRESHOLD 75 #define POWER_LPRX_RSSI_THRESHOLD_MAX 94 #define POWER_LPRX_RSSI_THRESHOLD_MIN 30 /** - * enum iwl_scan_flags - masks for power table command flags + * enum iwl_power_flags - masks for power table command flags * @POWER_FLAGS_POWER_SAVE_ENA_MSK: '1' Allow to save power by turning off * receiver and transmitter. '0' - does not allow. * @POWER_FLAGS_POWER_MANAGEMENT_ENA_MSK: '0' Driver disables power management, diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api.h b/drivers/net/wireless/iwlwifi/mvm/fw-api.h index d0a04779d734..d8948aa9c2d2 100644 --- a/drivers/net/wireless/iwlwifi/mvm/fw-api.h +++ b/drivers/net/wireless/iwlwifi/mvm/fw-api.h @@ -142,6 +142,7 @@ enum { /* Power - legacy power table command */ POWER_TABLE_CMD = 0x77, PSM_UAPSD_AP_MISBEHAVING_NOTIFICATION = 0x78, + LTR_CONFIG = 0xee, /* Thermal Throttling*/ REPLY_THERMAL_MNG_BACKOFF = 0x7e, diff --git a/drivers/net/wireless/iwlwifi/mvm/fw.c b/drivers/net/wireless/iwlwifi/mvm/fw.c index c03d39541f9e..2ef344fc0acb 100644 --- a/drivers/net/wireless/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/iwlwifi/mvm/fw.c @@ -439,6 +439,15 @@ int iwl_mvm_up(struct iwl_mvm *mvm) goto error; } + if (mvm->trans->ltr_enabled) { + struct iwl_ltr_config_cmd cmd = { + .flags = cpu_to_le32(LTR_CFG_FLAG_FEATURE_ENABLE), + }; + + WARN_ON(iwl_mvm_send_cmd_pdu(mvm, LTR_CONFIG, 0, + sizeof(cmd), &cmd)); + } + ret = iwl_mvm_power_update_device_mode(mvm); if (ret) goto error; diff --git a/drivers/net/wireless/iwlwifi/mvm/ops.c b/drivers/net/wireless/iwlwifi/mvm/ops.c index a3d43de342d7..dbff7f0bc6a8 100644 --- a/drivers/net/wireless/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/iwlwifi/mvm/ops.c @@ -313,6 +313,7 @@ static const char *iwl_mvm_cmd_strings[REPLY_MAX] = { CMD(REPLY_BEACON_FILTERING_CMD), CMD(REPLY_THERMAL_MNG_BACKOFF), CMD(MAC_PM_POWER_TABLE), + CMD(LTR_CONFIG), CMD(BT_COEX_CI), CMD(PSM_UAPSD_AP_MISBEHAVING_NOTIFICATION), }; diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c index 16be0c07c64a..fb62927ca44d 100644 --- a/drivers/net/wireless/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/iwlwifi/pcie/trans.c @@ -94,6 +94,7 @@ static void iwl_pcie_apm_config(struct iwl_trans *trans) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); u16 lctl; + u16 cap; /* * HW bug W/A for instability in PCIe bus L0S->L1 transition. @@ -104,16 +105,17 @@ static void iwl_pcie_apm_config(struct iwl_trans *trans) * power savings, even without L1. */ pcie_capability_read_word(trans_pcie->pci_dev, PCI_EXP_LNKCTL, &lctl); - if (lctl & PCI_EXP_LNKCTL_ASPM_L1) { - /* L1-ASPM enabled; disable(!) L0S */ + if (lctl & PCI_EXP_LNKCTL_ASPM_L1) iwl_set_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_ENABLED); - dev_info(trans->dev, "L1 Enabled; Disabling L0S\n"); - } else { - /* L1-ASPM disabled; enable(!) L0S */ + else iwl_clear_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_ENABLED); - dev_info(trans->dev, "L1 Disabled; Enabling L0S\n"); - } trans->pm_support = !(lctl & PCI_EXP_LNKCTL_ASPM_L0S); + + pcie_capability_read_word(trans_pcie->pci_dev, PCI_EXP_DEVCTL2, &cap); + trans->ltr_enabled = cap & PCI_EXP_DEVCTL2_LTR_EN; + dev_info(trans->dev, "L1 %sabled - LTR %sabled\n", + (lctl & PCI_EXP_LNKCTL_ASPM_L1) ? "En" : "Dis", + trans->ltr_enabled ? "En" : "Dis"); } /* diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 69d4c3179d04..505ff601d9f4 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -1974,7 +1974,7 @@ static int mac80211_hwsim_create_radio(int channels, const char *reg_alpha2, if (err != 0) { printk(KERN_DEBUG "mac80211_hwsim: device_bind_driver failed (%d)\n", err); - goto failed_hw; + goto failed_bind; } skb_queue_head_init(&data->pending); @@ -2157,6 +2157,8 @@ static int mac80211_hwsim_create_radio(int channels, const char *reg_alpha2, return idx; failed_hw: + device_release_driver(data->dev); +failed_bind: device_unregister(data->dev); failed_drvdata: ieee80211_free_hw(hw); diff --git a/drivers/platform/x86/dell-wmi.c b/drivers/platform/x86/dell-wmi.c index 390e8e33d5e3..25721bf20092 100644 --- a/drivers/platform/x86/dell-wmi.c +++ b/drivers/platform/x86/dell-wmi.c @@ -163,18 +163,24 @@ static void dell_wmi_notify(u32 value, void *context) const struct key_entry *key; int reported_key; u16 *buffer_entry = (u16 *)obj->buffer.pointer; + int buffer_size = obj->buffer.length/2; - if (dell_new_hk_type && (buffer_entry[1] != 0x10)) { + if (buffer_size >= 2 && dell_new_hk_type && buffer_entry[1] != 0x10) { pr_info("Received unknown WMI event (0x%x)\n", buffer_entry[1]); kfree(obj); return; } - if (dell_new_hk_type || buffer_entry[1] == 0x0) + if (buffer_size >= 3 && (dell_new_hk_type || buffer_entry[1] == 0x0)) reported_key = (int)buffer_entry[2]; - else + else if (buffer_size >= 2) reported_key = (int)buffer_entry[1] & 0xffff; + else { + pr_info("Received unknown WMI event\n"); + kfree(obj); + return; + } key = sparse_keymap_entry_from_scancode(dell_wmi_input_dev, reported_key); diff --git a/drivers/power/bq2415x_charger.c b/drivers/power/bq2415x_charger.c index e384844a1ae1..1f49986fc605 100644 --- a/drivers/power/bq2415x_charger.c +++ b/drivers/power/bq2415x_charger.c @@ -1579,8 +1579,15 @@ static int bq2415x_probe(struct i2c_client *client, if (np) { bq->notify_psy = power_supply_get_by_phandle(np, "ti,usb-charger-detection"); - if (!bq->notify_psy) - return -EPROBE_DEFER; + if (IS_ERR(bq->notify_psy)) { + dev_info(&client->dev, + "no 'ti,usb-charger-detection' property (err=%ld)\n", + PTR_ERR(bq->notify_psy)); + bq->notify_psy = NULL; + } else if (!bq->notify_psy) { + ret = -EPROBE_DEFER; + goto error_2; + } } else if (pdata->notify_device) bq->notify_psy = power_supply_get_by_name(pdata->notify_device); @@ -1602,27 +1609,27 @@ static int bq2415x_probe(struct i2c_client *client, ret = of_property_read_u32(np, "ti,current-limit", &bq->init_data.current_limit); if (ret) - return ret; + goto error_2; ret = of_property_read_u32(np, "ti,weak-battery-voltage", &bq->init_data.weak_battery_voltage); if (ret) - return ret; + goto error_2; ret = of_property_read_u32(np, "ti,battery-regulation-voltage", &bq->init_data.battery_regulation_voltage); if (ret) - return ret; + goto error_2; ret = of_property_read_u32(np, "ti,charge-current", &bq->init_data.charge_current); if (ret) - return ret; + goto error_2; ret = of_property_read_u32(np, "ti,termination-current", &bq->init_data.termination_current); if (ret) - return ret; + goto error_2; ret = of_property_read_u32(np, "ti,resistor-sense", &bq->init_data.resistor_sense); if (ret) - return ret; + goto error_2; } else { memcpy(&bq->init_data, pdata, sizeof(bq->init_data)); } diff --git a/drivers/power/charger-manager.c b/drivers/power/charger-manager.c index ef1f4c928431..03bfac3655ef 100644 --- a/drivers/power/charger-manager.c +++ b/drivers/power/charger-manager.c @@ -97,6 +97,7 @@ static struct charger_global_desc *g_desc; /* init with setup_charger_manager */ static bool is_batt_present(struct charger_manager *cm) { union power_supply_propval val; + struct power_supply *psy; bool present = false; int i, ret; @@ -107,16 +108,27 @@ static bool is_batt_present(struct charger_manager *cm) case CM_NO_BATTERY: break; case CM_FUEL_GAUGE: - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + psy = power_supply_get_by_name(cm->desc->psy_fuel_gauge); + if (!psy) + break; + + ret = psy->get_property(psy, POWER_SUPPLY_PROP_PRESENT, &val); if (ret == 0 && val.intval) present = true; break; case CM_CHARGER_STAT: - for (i = 0; cm->charger_stat[i]; i++) { - ret = cm->charger_stat[i]->get_property( - cm->charger_stat[i], - POWER_SUPPLY_PROP_PRESENT, &val); + for (i = 0; cm->desc->psy_charger_stat[i]; i++) { + psy = power_supply_get_by_name( + cm->desc->psy_charger_stat[i]); + if (!psy) { + dev_err(cm->dev, "Cannot find power supply \"%s\"\n", + cm->desc->psy_charger_stat[i]); + continue; + } + + ret = psy->get_property(psy, POWER_SUPPLY_PROP_PRESENT, + &val); if (ret == 0 && val.intval) { present = true; break; @@ -139,14 +151,20 @@ static bool is_batt_present(struct charger_manager *cm) static bool is_ext_pwr_online(struct charger_manager *cm) { union power_supply_propval val; + struct power_supply *psy; bool online = false; int i, ret; /* If at least one of them has one, it's yes. */ - for (i = 0; cm->charger_stat[i]; i++) { - ret = cm->charger_stat[i]->get_property( - cm->charger_stat[i], - POWER_SUPPLY_PROP_ONLINE, &val); + for (i = 0; cm->desc->psy_charger_stat[i]; i++) { + psy = power_supply_get_by_name(cm->desc->psy_charger_stat[i]); + if (!psy) { + dev_err(cm->dev, "Cannot find power supply \"%s\"\n", + cm->desc->psy_charger_stat[i]); + continue; + } + + ret = psy->get_property(psy, POWER_SUPPLY_PROP_ONLINE, &val); if (ret == 0 && val.intval) { online = true; break; @@ -167,12 +185,14 @@ static bool is_ext_pwr_online(struct charger_manager *cm) static int get_batt_uV(struct charger_manager *cm, int *uV) { union power_supply_propval val; + struct power_supply *fuel_gauge; int ret; - if (!cm->fuel_gauge) + fuel_gauge = power_supply_get_by_name(cm->desc->psy_fuel_gauge); + if (!fuel_gauge) return -ENODEV; - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + ret = fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_VOLTAGE_NOW, &val); if (ret) return ret; @@ -189,6 +209,7 @@ static bool is_charging(struct charger_manager *cm) { int i, ret; bool charging = false; + struct power_supply *psy; union power_supply_propval val; /* If there is no battery, it cannot be charged */ @@ -196,17 +217,22 @@ static bool is_charging(struct charger_manager *cm) return false; /* If at least one of the charger is charging, return yes */ - for (i = 0; cm->charger_stat[i]; i++) { + for (i = 0; cm->desc->psy_charger_stat[i]; i++) { /* 1. The charger sholuld not be DISABLED */ if (cm->emergency_stop) continue; if (!cm->charger_enabled) continue; + psy = power_supply_get_by_name(cm->desc->psy_charger_stat[i]); + if (!psy) { + dev_err(cm->dev, "Cannot find power supply \"%s\"\n", + cm->desc->psy_charger_stat[i]); + continue; + } + /* 2. The charger should be online (ext-power) */ - ret = cm->charger_stat[i]->get_property( - cm->charger_stat[i], - POWER_SUPPLY_PROP_ONLINE, &val); + ret = psy->get_property(psy, POWER_SUPPLY_PROP_ONLINE, &val); if (ret) { dev_warn(cm->dev, "Cannot read ONLINE value from %s\n", cm->desc->psy_charger_stat[i]); @@ -219,9 +245,7 @@ static bool is_charging(struct charger_manager *cm) * 3. The charger should not be FULL, DISCHARGING, * or NOT_CHARGING. */ - ret = cm->charger_stat[i]->get_property( - cm->charger_stat[i], - POWER_SUPPLY_PROP_STATUS, &val); + ret = psy->get_property(psy, POWER_SUPPLY_PROP_STATUS, &val); if (ret) { dev_warn(cm->dev, "Cannot read STATUS value from %s\n", cm->desc->psy_charger_stat[i]); @@ -248,6 +272,7 @@ static bool is_full_charged(struct charger_manager *cm) { struct charger_desc *desc = cm->desc; union power_supply_propval val; + struct power_supply *fuel_gauge; int ret = 0; int uV; @@ -255,11 +280,15 @@ static bool is_full_charged(struct charger_manager *cm) if (!is_batt_present(cm)) return false; - if (cm->fuel_gauge && desc->fullbatt_full_capacity > 0) { + fuel_gauge = power_supply_get_by_name(cm->desc->psy_fuel_gauge); + if (!fuel_gauge) + return false; + + if (desc->fullbatt_full_capacity > 0) { val.intval = 0; /* Not full if capacity of fuel gauge isn't full */ - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + ret = fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_CHARGE_FULL, &val); if (!ret && val.intval > desc->fullbatt_full_capacity) return true; @@ -273,10 +302,10 @@ static bool is_full_charged(struct charger_manager *cm) } /* Full, if the capacity is more than fullbatt_soc */ - if (cm->fuel_gauge && desc->fullbatt_soc > 0) { + if (desc->fullbatt_soc > 0) { val.intval = 0; - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + ret = fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_CAPACITY, &val); if (!ret && val.intval >= desc->fullbatt_soc) return true; @@ -551,6 +580,20 @@ static int check_charging_duration(struct charger_manager *cm) return ret; } +static int cm_get_battery_temperature_by_psy(struct charger_manager *cm, + int *temp) +{ + struct power_supply *fuel_gauge; + + fuel_gauge = power_supply_get_by_name(cm->desc->psy_fuel_gauge); + if (!fuel_gauge) + return -ENODEV; + + return fuel_gauge->get_property(fuel_gauge, + POWER_SUPPLY_PROP_TEMP, + (union power_supply_propval *)temp); +} + static int cm_get_battery_temperature(struct charger_manager *cm, int *temp) { @@ -560,15 +603,18 @@ static int cm_get_battery_temperature(struct charger_manager *cm, return -ENODEV; #ifdef CONFIG_THERMAL - ret = thermal_zone_get_temp(cm->tzd_batt, (unsigned long *)temp); - if (!ret) - /* Calibrate temperature unit */ - *temp /= 100; -#else - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, - POWER_SUPPLY_PROP_TEMP, - (union power_supply_propval *)temp); + if (cm->tzd_batt) { + ret = thermal_zone_get_temp(cm->tzd_batt, (unsigned long *)temp); + if (!ret) + /* Calibrate temperature unit */ + *temp /= 100; + } else #endif + { + /* if-else continued from CONFIG_THERMAL */ + ret = cm_get_battery_temperature_by_psy(cm, temp); + } + return ret; } @@ -827,6 +873,7 @@ static int charger_get_property(struct power_supply *psy, struct charger_manager *cm = container_of(psy, struct charger_manager, charger_psy); struct charger_desc *desc = cm->desc; + struct power_supply *fuel_gauge; int ret = 0; int uV; @@ -857,14 +904,20 @@ static int charger_get_property(struct power_supply *psy, ret = get_batt_uV(cm, &val->intval); break; case POWER_SUPPLY_PROP_CURRENT_NOW: - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + fuel_gauge = power_supply_get_by_name(cm->desc->psy_fuel_gauge); + if (!fuel_gauge) { + ret = -ENODEV; + break; + } + ret = fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_CURRENT_NOW, val); break; case POWER_SUPPLY_PROP_TEMP: case POWER_SUPPLY_PROP_TEMP_AMBIENT: return cm_get_battery_temperature(cm, &val->intval); case POWER_SUPPLY_PROP_CAPACITY: - if (!cm->fuel_gauge) { + fuel_gauge = power_supply_get_by_name(cm->desc->psy_fuel_gauge); + if (!fuel_gauge) { ret = -ENODEV; break; } @@ -875,7 +928,7 @@ static int charger_get_property(struct power_supply *psy, break; } - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + ret = fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_CAPACITY, val); if (ret) break; @@ -924,7 +977,14 @@ static int charger_get_property(struct power_supply *psy, break; case POWER_SUPPLY_PROP_CHARGE_NOW: if (is_charging(cm)) { - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + fuel_gauge = power_supply_get_by_name( + cm->desc->psy_fuel_gauge); + if (!fuel_gauge) { + ret = -ENODEV; + break; + } + + ret = fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_CHARGE_NOW, val); if (ret) { @@ -1485,14 +1545,15 @@ err: return ret; } -static int cm_init_thermal_data(struct charger_manager *cm) +static int cm_init_thermal_data(struct charger_manager *cm, + struct power_supply *fuel_gauge) { struct charger_desc *desc = cm->desc; union power_supply_propval val; int ret; /* Verify whether fuel gauge provides battery temperature */ - ret = cm->fuel_gauge->get_property(cm->fuel_gauge, + ret = fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_TEMP, &val); if (!ret) { @@ -1502,8 +1563,6 @@ static int cm_init_thermal_data(struct charger_manager *cm) cm->desc->measure_battery_temp = true; } #ifdef CONFIG_THERMAL - cm->tzd_batt = cm->fuel_gauge->tzd; - if (ret && desc->thermal_zone) { cm->tzd_batt = thermal_zone_get_zone_by_name(desc->thermal_zone); @@ -1666,6 +1725,7 @@ static int charger_manager_probe(struct platform_device *pdev) int ret = 0, i = 0; int j = 0; union power_supply_propval val; + struct power_supply *fuel_gauge; if (g_desc && !rtc_dev && g_desc->rtc_name) { rtc_dev = rtc_class_open(g_desc->rtc_name); @@ -1729,23 +1789,20 @@ static int charger_manager_probe(struct platform_device *pdev) while (desc->psy_charger_stat[i]) i++; - cm->charger_stat = devm_kzalloc(&pdev->dev, - sizeof(struct power_supply *) * i, GFP_KERNEL); - if (!cm->charger_stat) - return -ENOMEM; - + /* Check if charger's supplies are present at probe */ for (i = 0; desc->psy_charger_stat[i]; i++) { - cm->charger_stat[i] = power_supply_get_by_name( - desc->psy_charger_stat[i]); - if (!cm->charger_stat[i]) { + struct power_supply *psy; + + psy = power_supply_get_by_name(desc->psy_charger_stat[i]); + if (!psy) { dev_err(&pdev->dev, "Cannot find power supply \"%s\"\n", desc->psy_charger_stat[i]); return -ENODEV; } } - cm->fuel_gauge = power_supply_get_by_name(desc->psy_fuel_gauge); - if (!cm->fuel_gauge) { + fuel_gauge = power_supply_get_by_name(desc->psy_fuel_gauge); + if (!fuel_gauge) { dev_err(&pdev->dev, "Cannot find power supply \"%s\"\n", desc->psy_fuel_gauge); return -ENODEV; @@ -1788,13 +1845,13 @@ static int charger_manager_probe(struct platform_device *pdev) cm->charger_psy.num_properties = psy_default.num_properties; /* Find which optional psy-properties are available */ - if (!cm->fuel_gauge->get_property(cm->fuel_gauge, + if (!fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_CHARGE_NOW, &val)) { cm->charger_psy.properties[cm->charger_psy.num_properties] = POWER_SUPPLY_PROP_CHARGE_NOW; cm->charger_psy.num_properties++; } - if (!cm->fuel_gauge->get_property(cm->fuel_gauge, + if (!fuel_gauge->get_property(fuel_gauge, POWER_SUPPLY_PROP_CURRENT_NOW, &val)) { cm->charger_psy.properties[cm->charger_psy.num_properties] = @@ -1802,7 +1859,7 @@ static int charger_manager_probe(struct platform_device *pdev) cm->charger_psy.num_properties++; } - ret = cm_init_thermal_data(cm); + ret = cm_init_thermal_data(cm, fuel_gauge); if (ret) { dev_err(&pdev->dev, "Failed to initialize thermal data\n"); cm->desc->measure_battery_temp = false; @@ -2059,8 +2116,8 @@ static bool find_power_supply(struct charger_manager *cm, int i; bool found = false; - for (i = 0; cm->charger_stat[i]; i++) { - if (psy == cm->charger_stat[i]) { + for (i = 0; cm->desc->psy_charger_stat[i]; i++) { + if (!strcmp(psy->name, cm->desc->psy_charger_stat[i])) { found = true; break; } diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index edb4d46fa874..96b6664bb1cf 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -1984,8 +1984,10 @@ static void scsi_restart_operations(struct Scsi_Host *shost) * is no point trying to lock the door of an off-line device. */ shost_for_each_device(sdev, shost) { - if (scsi_device_online(sdev) && sdev->locked) + if (scsi_device_online(sdev) && sdev->was_reset && sdev->locked) { scsi_eh_lock_door(sdev); + sdev->was_reset = 0; + } } /* diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index b01fb6c527e3..d43c544d3b68 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -472,7 +472,7 @@ static noinline int add_ra_bio_pages(struct inode *inode, rcu_read_lock(); page = radix_tree_lookup(&mapping->page_tree, pg_index); rcu_read_unlock(); - if (page) { + if (page && !radix_tree_exceptional_entry(page)) { misses++; if (misses > 4) break; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index a9a881ed8cbe..f6d00df99a8c 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -425,13 +425,8 @@ static noinline int btrfs_copy_from_user(loff_t pos, int num_pages, struct page *page = prepared_pages[pg]; /* * Copy data from userspace to the current page - * - * Disable pagefault to avoid recursive lock since - * the pages are already locked */ - pagefault_disable(); copied = iov_iter_copy_from_user_atomic(page, i, offset, count); - pagefault_enable(); /* Flush processor's dcache for this page */ flush_dcache_page(page); diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 06610cf94d57..a1f801c14fbc 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -195,8 +195,7 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i struct page *page = NULL; if (blocknr + i < devsize) { - page = read_mapping_page_async(mapping, blocknr + i, - NULL); + page = read_mapping_page(mapping, blocknr + i, NULL); /* synchronous error? */ if (IS_ERR(page)) page = NULL; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 77bcc303c3ae..a91d3b4d32f3 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1003,9 +1003,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req, if (mapping_writably_mapped(mapping)) flush_dcache_page(page); - pagefault_disable(); tmp = iov_iter_copy_from_user_atomic(page, ii, offset, bytes); - pagefault_enable(); flush_dcache_page(page); mark_page_accessed(page); diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index c7f24690ed05..b82a9c99e18b 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -97,6 +97,11 @@ const struct address_space_operations gfs2_meta_aops = { .releasepage = gfs2_releasepage, }; +const struct address_space_operations gfs2_rgrp_aops = { + .writepage = gfs2_aspace_writepage, + .releasepage = gfs2_releasepage, +}; + /** * gfs2_getbuf - Get a buffer with a given address space * @gl: the glock diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h index 4823b934208a..ac5d8027d335 100644 --- a/fs/gfs2/meta_io.h +++ b/fs/gfs2/meta_io.h @@ -38,12 +38,15 @@ static inline void gfs2_buffer_copy_tail(struct buffer_head *to_bh, } extern const struct address_space_operations gfs2_meta_aops; +extern const struct address_space_operations gfs2_rgrp_aops; static inline struct gfs2_sbd *gfs2_mapping2sbd(struct address_space *mapping) { struct inode *inode = mapping->host; if (mapping->a_ops == &gfs2_meta_aops) return (((struct gfs2_glock *)mapping) - 1)->gl_sbd; + else if (mapping->a_ops == &gfs2_rgrp_aops) + return container_of(mapping, struct gfs2_sbd, sd_aspace); else return inode->i_sb->s_fs_info; } diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index c6872d09561a..f6c9d83aa39b 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -104,7 +104,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) mapping = &sdp->sd_aspace; address_space_init_once(mapping); - mapping->a_ops = &gfs2_meta_aops; + mapping->a_ops = &gfs2_rgrp_aops; mapping->host = sb->s_bdev->bd_inode; mapping->flags = 0; mapping_set_gfp_mask(mapping, GFP_NOFS); diff --git a/fs/ioprio.c b/fs/ioprio.c index e50170ca7c33..31666c92b46a 100644 --- a/fs/ioprio.c +++ b/fs/ioprio.c @@ -157,14 +157,16 @@ out: int ioprio_best(unsigned short aprio, unsigned short bprio) { - unsigned short aclass = IOPRIO_PRIO_CLASS(aprio); - unsigned short bclass = IOPRIO_PRIO_CLASS(bprio); + unsigned short aclass; + unsigned short bclass; - if (aclass == IOPRIO_CLASS_NONE) - aclass = IOPRIO_CLASS_BE; - if (bclass == IOPRIO_CLASS_NONE) - bclass = IOPRIO_CLASS_BE; + if (!ioprio_valid(aprio)) + aprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM); + if (!ioprio_valid(bprio)) + bprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM); + aclass = IOPRIO_PRIO_CLASS(aprio); + bclass = IOPRIO_PRIO_CLASS(bprio); if (aclass == bclass) return min(aprio, bprio); if (aclass > bclass) diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index a69e426435dd..5b234db85854 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -687,7 +687,7 @@ unsigned char *jffs2_gc_fetch_page(struct jffs2_sb_info *c, struct inode *inode = OFNI_EDONI_2SFFJ(f); struct page *pg; - pg = read_cache_page_async(inode->i_mapping, offset >> PAGE_CACHE_SHIFT, + pg = read_cache_page(inode->i_mapping, offset >> PAGE_CACHE_SHIFT, (void *)jffs2_do_readpage_unlock, inode); if (IS_ERR(pg)) return (void *)pg; diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 56ff823ca82e..65d849bdf77a 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -1213,7 +1213,7 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx) end = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE); if (end != NFS_I(inode)->npages) { rcu_read_lock(); - end = radix_tree_next_hole(&mapping->page_tree, idx + 1, ULONG_MAX); + end = page_cache_next_hole(mapping, idx + 1, ULONG_MAX); rcu_read_unlock(); } diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 5d8ccecf5f5c..3ed1be9aade3 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -109,6 +109,8 @@ again: continue; if (!test_bit(NFS_DELEGATED_STATE, &state->flags)) continue; + if (!nfs4_valid_open_stateid(state)) + continue; if (!nfs4_stateid_match(&state->stateid, stateid)) continue; get_nfs_open_context(ctx); @@ -177,7 +179,11 @@ static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation * { int res = 0; - res = nfs4_proc_delegreturn(inode, delegation->cred, &delegation->stateid, issync); + if (!test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) + res = nfs4_proc_delegreturn(inode, + delegation->cred, + &delegation->stateid, + issync); nfs_free_delegation(delegation); return res; } @@ -364,11 +370,13 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation { struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; struct nfs_inode *nfsi = NFS_I(inode); - int err; + int err = 0; if (delegation == NULL) return 0; do { + if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) + break; err = nfs_delegation_claim_opens(inode, &delegation->stateid); if (!issync || err != -EAGAIN) break; @@ -589,10 +597,23 @@ static void nfs_client_mark_return_unused_delegation_types(struct nfs_client *cl rcu_read_unlock(); } +static void nfs_revoke_delegation(struct inode *inode) +{ + struct nfs_delegation *delegation; + rcu_read_lock(); + delegation = rcu_dereference(NFS_I(inode)->delegation); + if (delegation != NULL) { + set_bit(NFS_DELEGATION_REVOKED, &delegation->flags); + nfs_mark_return_delegation(NFS_SERVER(inode), delegation); + } + rcu_read_unlock(); +} + void nfs_remove_bad_delegation(struct inode *inode) { struct nfs_delegation *delegation; + nfs_revoke_delegation(inode); delegation = nfs_inode_detach_delegation(inode); if (delegation) { nfs_inode_find_state_and_recover(inode, &delegation->stateid); diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index 9a79c7a99d6d..e02b090ab9da 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -31,6 +31,7 @@ enum { NFS_DELEGATION_RETURN_IF_CLOSED, NFS_DELEGATION_REFERENCED, NFS_DELEGATION_RETURNING, + NFS_DELEGATION_REVOKED, }; int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index b8797ae6831f..de2543d3c283 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -178,6 +178,7 @@ static void nfs_direct_req_free(struct kref *kref) { struct nfs_direct_req *dreq = container_of(kref, struct nfs_direct_req, kref); + nfs_free_pnfs_ds_cinfo(&dreq->ds_cinfo); if (dreq->l_ctx != NULL) nfs_put_lock_context(dreq->l_ctx); if (dreq->ctx != NULL) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 15f9d98627a4..6659ce545f15 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -592,7 +592,7 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) { struct inode *inode = dentry->d_inode; int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME; - int err; + int err = 0; trace_nfs_getattr_enter(inode); /* Flush out writes to the server in order to update c/mtime. */ diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index da657b7804a5..bd01803d0656 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1587,7 +1587,7 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct nfs_inode_find_state_and_recover(state->inode, stateid); nfs4_schedule_stateid_recovery(server, state); - return 0; + return -EAGAIN; case -NFS4ERR_DELAY: case -NFS4ERR_GRACE: set_bit(NFS_DELEGATED_STATE, &state->flags); @@ -2034,46 +2034,60 @@ static int nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *sta return ret; } +static void nfs_finish_clear_delegation_stateid(struct nfs4_state *state) +{ + nfs_remove_bad_delegation(state->inode); + write_seqlock(&state->seqlock); + nfs4_stateid_copy(&state->stateid, &state->open_stateid); + write_sequnlock(&state->seqlock); + clear_bit(NFS_DELEGATED_STATE, &state->flags); +} + +static void nfs40_clear_delegation_stateid(struct nfs4_state *state) +{ + if (rcu_access_pointer(NFS_I(state->inode)->delegation) != NULL) + nfs_finish_clear_delegation_stateid(state); +} + +static int nfs40_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state) +{ + /* NFSv4.0 doesn't allow for delegation recovery on open expire */ + nfs40_clear_delegation_stateid(state); + return nfs4_open_expired(sp, state); +} + #if defined(CONFIG_NFS_V4_1) -static void nfs41_clear_delegation_stateid(struct nfs4_state *state) +static void nfs41_check_delegation_stateid(struct nfs4_state *state) { struct nfs_server *server = NFS_SERVER(state->inode); - nfs4_stateid *stateid = &state->stateid; + nfs4_stateid stateid; struct nfs_delegation *delegation; - struct rpc_cred *cred = NULL; - int status = -NFS4ERR_BAD_STATEID; - - /* If a state reset has been done, test_stateid is unneeded */ - if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0) - return; + struct rpc_cred *cred; + int status; /* Get the delegation credential for use by test/free_stateid */ rcu_read_lock(); delegation = rcu_dereference(NFS_I(state->inode)->delegation); - if (delegation != NULL && - nfs4_stateid_match(&delegation->stateid, stateid)) { - cred = get_rpccred(delegation->cred); - rcu_read_unlock(); - status = nfs41_test_stateid(server, stateid, cred); - trace_nfs4_test_delegation_stateid(state, NULL, status); - } else + if (delegation == NULL) { rcu_read_unlock(); + return; + } + + nfs4_stateid_copy(&stateid, &delegation->stateid); + cred = get_rpccred(delegation->cred); + rcu_read_unlock(); + status = nfs41_test_stateid(server, &stateid, cred); + trace_nfs4_test_delegation_stateid(state, NULL, status); if (status != NFS_OK) { /* Free the stateid unless the server explicitly * informs us the stateid is unrecognized. */ if (status != -NFS4ERR_BAD_STATEID) - nfs41_free_stateid(server, stateid, cred); - nfs_remove_bad_delegation(state->inode); - - write_seqlock(&state->seqlock); - nfs4_stateid_copy(&state->stateid, &state->open_stateid); - write_sequnlock(&state->seqlock); - clear_bit(NFS_DELEGATED_STATE, &state->flags); + nfs41_free_stateid(server, &stateid, cred); + nfs_finish_clear_delegation_stateid(state); } - if (cred != NULL) - put_rpccred(cred); + put_rpccred(cred); } /** @@ -2117,7 +2131,7 @@ static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *st { int status; - nfs41_clear_delegation_stateid(state); + nfs41_check_delegation_stateid(state); status = nfs41_check_open_stateid(state); if (status != NFS_OK) status = nfs4_open_expired(sp, state); @@ -8255,7 +8269,7 @@ static const struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = { static const struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = { .owner_flag_bit = NFS_OWNER_RECLAIM_NOGRACE, .state_flag_bit = NFS_STATE_RECLAIM_NOGRACE, - .recover_open = nfs4_open_expired, + .recover_open = nfs40_open_expired, .recover_lock = nfs4_lock_expired, .establish_clid = nfs4_init_clientid, }; diff --git a/fs/super.c b/fs/super.c index 88a6bc6e3cc9..440ef51cd696 100644 --- a/fs/super.c +++ b/fs/super.c @@ -114,9 +114,14 @@ static unsigned long super_cache_count(struct shrinker *shrink, sb = container_of(shrink, struct super_block, s_shrink); - if (!grab_super_passive(sb)) - return 0; - + /* + * Don't call grab_super_passive as it is a potential + * scalability bottleneck. The counts could get updated + * between super_cache_count and super_cache_scan anyway. + * Call to super_cache_count with shrinker_rwsem held + * ensures the safety of call to list_lru_count_node() and + * s_op->nr_cached_objects(). + */ if (sb->s_op && sb->s_op->nr_cached_objects) total_objects = sb->s_op->nr_cached_objects(sb, sc->nid); @@ -127,7 +132,6 @@ static unsigned long super_cache_count(struct shrinker *shrink, sc->nid); total_objects = vfs_pressure_ratio(total_objects); - drop_super(sb); return total_objects; } @@ -278,10 +282,8 @@ void deactivate_locked_super(struct super_block *s) struct file_system_type *fs = s->s_type; if (atomic_dec_and_test(&s->s_active)) { cleancache_invalidate_fs(s); - fs->kill_sb(s); - - /* caches are now gone, we can safely kill the shrinker now */ unregister_shrinker(&s->s_shrink); + fs->kill_sb(s); put_filesystem(fs); put_super(s); diff --git a/include/dt-bindings/pinctrl/dra.h b/include/dt-bindings/pinctrl/dra.h index 3d33794e4f3e..7448edff4723 100644 --- a/include/dt-bindings/pinctrl/dra.h +++ b/include/dt-bindings/pinctrl/dra.h @@ -40,8 +40,8 @@ /* Active pin states */ #define PIN_OUTPUT (0 | PULL_DIS) -#define PIN_OUTPUT_PULLUP (PIN_OUTPUT | PULL_ENA | PULL_UP) -#define PIN_OUTPUT_PULLDOWN (PIN_OUTPUT | PULL_ENA) +#define PIN_OUTPUT_PULLUP (PULL_UP) +#define PIN_OUTPUT_PULLDOWN (0) #define PIN_INPUT (INPUT_EN | PULL_DIS) #define PIN_INPUT_SLEW (INPUT_EN | SLEWCONTROL) #define PIN_INPUT_PULLUP (PULL_ENA | INPUT_EN | PULL_UP) diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 67301a405712..879065d8d208 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -289,7 +289,7 @@ extern struct clocksource* clocksource_get_next(void); extern void clocksource_change_rating(struct clocksource *cs, int rating); extern void clocksource_suspend(void); extern void clocksource_resume(void); -extern struct clocksource * __init __weak clocksource_default_clock(void); +extern struct clocksource * __init clocksource_default_clock(void); extern void clocksource_mark_unstable(struct clocksource *cs); extern u64 diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 7e1c76e3cd68..01e3132820da 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -22,7 +22,7 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write, extern int fragmentation_index(struct zone *zone, unsigned int order); extern unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask, - bool sync, bool *contended); + enum migrate_mode mode, bool *contended); extern void compact_pgdat(pg_data_t *pgdat, int order); extern void reset_isolation_suitable(pg_data_t *pgdat); extern unsigned long compaction_suitable(struct zone *zone, int order); @@ -91,7 +91,7 @@ static inline bool compaction_restarting(struct zone *zone, int order) #else static inline unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask, - bool sync, bool *contended) + enum migrate_mode mode, bool *contended) { return COMPACT_CONTINUE; } diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 7032518f8542..60023e5d3169 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -14,14 +14,13 @@ extern unsigned long long elfcorehdr_addr; extern unsigned long long elfcorehdr_size; -extern int __weak elfcorehdr_alloc(unsigned long long *addr, - unsigned long long *size); -extern void __weak elfcorehdr_free(unsigned long long addr); -extern ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos); -extern ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos); -extern int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma, - unsigned long from, unsigned long pfn, - unsigned long size, pgprot_t prot); +extern int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size); +extern void elfcorehdr_free(unsigned long long addr); +extern ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos); +extern ssize_t elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos); +extern int remap_oldmem_pfn_range(struct vm_area_struct *vma, + unsigned long from, unsigned long pfn, + unsigned long size, pgprot_t prot); extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, unsigned long, int); diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 6b06d378f3df..e465bb15912d 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -283,7 +283,7 @@ struct kgdb_io { extern struct kgdb_arch arch_kgdb_ops; -extern unsigned long __weak kgdb_arch_pc(int exception, struct pt_regs *regs); +extern unsigned long kgdb_arch_pc(int exception, struct pt_regs *regs); #ifdef CONFIG_SERIAL_KGDB_NMI extern int kgdb_register_nmi_console(void); diff --git a/include/linux/memory.h b/include/linux/memory.h index bb7384e3c3d8..8b8d8d12348e 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -35,7 +35,7 @@ struct memory_block { }; int arch_get_memory_phys_device(unsigned long start_pfn); -unsigned long __weak memory_block_size_bytes(void); +unsigned long memory_block_size_bytes(void); /* These states are exposed to userspace as text strings in sysfs */ #define MEM_ONLINE (1<<0) /* exposed to userspace */ diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 84a31ad0b791..a2901c414664 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -5,7 +5,9 @@ #include #include -typedef struct page *new_page_t(struct page *, unsigned long private, int **); +typedef struct page *new_page_t(struct page *page, unsigned long private, + int **reason); +typedef void free_page_t(struct page *page, unsigned long private); /* * Return values from addresss_space_operations.migratepage(): @@ -38,7 +40,7 @@ enum migrate_reason { extern void putback_movable_pages(struct list_head *l); extern int migrate_page(struct address_space *, struct page *, struct page *, enum migrate_mode); -extern int migrate_pages(struct list_head *l, new_page_t x, +extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, unsigned long private, enum migrate_mode mode, int reason); extern int migrate_prep(void); @@ -56,8 +58,9 @@ extern int migrate_page_move_mapping(struct address_space *mapping, #else static inline void putback_movable_pages(struct list_head *l) {} -static inline int migrate_pages(struct list_head *l, new_page_t x, - unsigned long private, enum migrate_mode mode, int reason) +static inline int migrate_pages(struct list_head *l, new_page_t new, + free_page_t free, unsigned long private, enum migrate_mode mode, + int reason) { return -ENOSYS; } static inline int migrate_prep(void) { return -ENOSYS; } diff --git a/include/linux/mm.h b/include/linux/mm.h index 0a0b024ec7e8..d5039daf1e1c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1041,6 +1041,14 @@ extern void show_free_areas(unsigned int flags); extern bool skip_free_areas_node(unsigned int flags, int nid); int shmem_zero_setup(struct vm_area_struct *); +#ifdef CONFIG_SHMEM +bool shmem_mapping(struct address_space *mapping); +#else +static inline bool shmem_mapping(struct address_space *mapping) +{ + return false; +} +#endif extern int can_do_mlock(void); extern int user_shm_lock(size_t, struct user_struct *); @@ -1848,9 +1856,6 @@ void page_cache_async_readahead(struct address_space *mapping, unsigned long size); unsigned long max_sane_readahead(unsigned long nr); -unsigned long ra_submit(struct file_ra_state *ra, - struct address_space *mapping, - struct file *filp); /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index e6800f0c0d7b..18843532a0c9 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -361,9 +361,10 @@ struct zone { /* Set to true when the PG_migrate_skip bits should be cleared */ bool compact_blockskip_flush; - /* pfns where compaction scanners should start */ + /* pfn where compaction free scanner should start */ unsigned long compact_cached_free_pfn; - unsigned long compact_cached_migrate_pfn; + /* pfn where async and sync compaction migration scanner should start */ + unsigned long compact_cached_migrate_pfn[2]; #endif #ifdef CONFIG_MEMORY_HOTPLUG /* see spanned/present_pages for more description */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 5624e4e2763c..53988cb3c05a 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1247,11 +1247,22 @@ struct nfs41_free_stateid_res { unsigned int status; }; +static inline void +nfs_free_pnfs_ds_cinfo(struct pnfs_ds_commit_info *cinfo) +{ + kfree(cinfo->buckets); +} + #else struct pnfs_ds_commit_info { }; +static inline void +nfs_free_pnfs_ds_cinfo(struct pnfs_ds_commit_info *cinfo) +{ +} + #endif /* CONFIG_NFS_V4_1 */ struct nfs_page; diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 1710d1b060ba..09c1b03867d9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -243,12 +243,20 @@ static inline struct page *page_cache_alloc_readahead(struct address_space *x) typedef int filler_t(void *, struct page *); -extern struct page * find_get_page(struct address_space *mapping, - pgoff_t index); -extern struct page * find_lock_page(struct address_space *mapping, - pgoff_t index); -extern struct page * find_or_create_page(struct address_space *mapping, - pgoff_t index, gfp_t gfp_mask); +pgoff_t page_cache_next_hole(struct address_space *mapping, + pgoff_t index, unsigned long max_scan); +pgoff_t page_cache_prev_hole(struct address_space *mapping, + pgoff_t index, unsigned long max_scan); + +struct page *find_get_entry(struct address_space *mapping, pgoff_t offset); +struct page *find_get_page(struct address_space *mapping, pgoff_t offset); +struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset); +struct page *find_lock_page(struct address_space *mapping, pgoff_t offset); +struct page *find_or_create_page(struct address_space *mapping, pgoff_t index, + gfp_t gfp_mask); +unsigned find_get_entries(struct address_space *mapping, pgoff_t start, + unsigned int nr_entries, struct page **entries, + pgoff_t *indices); unsigned find_get_pages(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages); unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, @@ -270,8 +278,6 @@ static inline struct page *grab_cache_page(struct address_space *mapping, extern struct page * grab_cache_page_nowait(struct address_space *mapping, pgoff_t index); -extern struct page * read_cache_page_async(struct address_space *mapping, - pgoff_t index, filler_t *filler, void *data); extern struct page * read_cache_page(struct address_space *mapping, pgoff_t index, filler_t *filler, void *data); extern struct page * read_cache_page_gfp(struct address_space *mapping, @@ -279,14 +285,6 @@ extern struct page * read_cache_page_gfp(struct address_space *mapping, extern int read_cache_pages(struct address_space *mapping, struct list_head *pages, filler_t *filler, void *data); -static inline struct page *read_mapping_page_async( - struct address_space *mapping, - pgoff_t index, void *data) -{ - filler_t *filler = (filler_t *)mapping->a_ops->readpage; - return read_cache_page_async(mapping, index, filler, data); -} - static inline struct page *read_mapping_page(struct address_space *mapping, pgoff_t index, void *data) { diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index e4dbfab37729..b45d391b4540 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -22,6 +22,11 @@ struct pagevec { void __pagevec_release(struct pagevec *pvec); void __pagevec_lru_add(struct pagevec *pvec); +unsigned pagevec_lookup_entries(struct pagevec *pvec, + struct address_space *mapping, + pgoff_t start, unsigned nr_entries, + pgoff_t *indices); +void pagevec_remove_exceptionals(struct pagevec *pvec); unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping, pgoff_t start, unsigned nr_pages); unsigned pagevec_lookup_tag(struct pagevec *pvec, diff --git a/include/linux/power/charger-manager.h b/include/linux/power/charger-manager.h index 07e7945a1ff2..e97fc656a058 100644 --- a/include/linux/power/charger-manager.h +++ b/include/linux/power/charger-manager.h @@ -253,9 +253,6 @@ struct charger_manager { struct device *dev; struct charger_desc *desc; - struct power_supply *fuel_gauge; - struct power_supply **charger_stat; - #ifdef CONFIG_THERMAL struct thermal_zone_device *tzd_batt; #endif diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 403940787be1..e8be53ecfc45 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -219,6 +219,7 @@ static inline void radix_tree_replace_slot(void **pslot, void *item) int radix_tree_insert(struct radix_tree_root *, unsigned long, void *); void *radix_tree_lookup(struct radix_tree_root *, unsigned long); void **radix_tree_lookup_slot(struct radix_tree_root *, unsigned long); +void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *); void *radix_tree_delete(struct radix_tree_root *, unsigned long); unsigned int radix_tree_gang_lookup(struct radix_tree_root *root, void **results, @@ -226,10 +227,6 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results, unsigned int radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results, unsigned long *indices, unsigned long first_index, unsigned int max_items); -unsigned long radix_tree_next_hole(struct radix_tree_root *root, - unsigned long index, unsigned long max_scan); -unsigned long radix_tree_prev_hole(struct radix_tree_root *root, - unsigned long index, unsigned long max_scan); int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); void radix_tree_init(void); diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 9d55438bc4ad..4d1771c2d29f 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -51,6 +51,7 @@ extern struct file *shmem_kernel_file_setup(const char *name, loff_t size, unsigned long flags); extern int shmem_zero_setup(struct vm_area_struct *); extern int shmem_lock(struct file *file, int lock, struct user_struct *user); +extern bool shmem_mapping(struct address_space *mapping); extern void shmem_unlock_mapping(struct address_space *mapping); extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index a3353f45ef94..ba41e01ebc54 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -433,6 +433,11 @@ static inline void sctp_assoc_pending_pmtu(struct sock *sk, struct sctp_associat asoc->pmtu_pending = 0; } +static inline bool sctp_chunk_pending(const struct sctp_chunk *chunk) +{ + return !list_empty(&chunk->list); +} + /* Walk through a list of TLV parameters. Don't trust the * individual parameter lengths and instead depend on * the chunk length to indicate when to stop. Make sure diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 7f4eeb340a54..72a31db47ded 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -248,9 +248,9 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *, int, __be16); struct sctp_chunk *sctp_make_asconf_set_prim(struct sctp_association *asoc, union sctp_addr *addr); -int sctp_verify_asconf(const struct sctp_association *asoc, - struct sctp_paramhdr *param_hdr, void *chunk_end, - struct sctp_paramhdr **errp); +bool sctp_verify_asconf(const struct sctp_association *asoc, + struct sctp_chunk *chunk, bool addr_param_needed, + struct sctp_paramhdr **errp); struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, struct sctp_chunk *asconf); int sctp_process_asconf_ack(struct sctp_association *asoc, diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h index 06f544ef2f6f..c6814b917bdf 100644 --- a/include/trace/events/compaction.h +++ b/include/trace/events/compaction.h @@ -5,6 +5,7 @@ #define _TRACE_COMPACTION_H #include +#include #include #include @@ -47,10 +48,11 @@ DEFINE_EVENT(mm_compaction_isolate_template, mm_compaction_isolate_freepages, TRACE_EVENT(mm_compaction_migratepages, - TP_PROTO(unsigned long nr_migrated, - unsigned long nr_failed), + TP_PROTO(unsigned long nr_all, + int migrate_rc, + struct list_head *migratepages), - TP_ARGS(nr_migrated, nr_failed), + TP_ARGS(nr_all, migrate_rc, migratepages), TP_STRUCT__entry( __field(unsigned long, nr_migrated) @@ -58,7 +60,22 @@ TRACE_EVENT(mm_compaction_migratepages, ), TP_fast_assign( - __entry->nr_migrated = nr_migrated; + unsigned long nr_failed = 0; + struct list_head *page_lru; + + /* + * migrate_pages() returns either a non-negative number + * with the number of pages that failed migration, or an + * error code, in which case we need to count the remaining + * pages manually + */ + if (migrate_rc >= 0) + nr_failed = migrate_rc; + else + list_for_each(page_lru, migratepages) + nr_failed++; + + __entry->nr_migrated = nr_all - nr_failed; __entry->nr_failed = nr_failed; ), diff --git a/include/uapi/linux/netfilter/xt_bpf.h b/include/uapi/linux/netfilter/xt_bpf.h index 5dda450eb55b..2ec9fbcd06f9 100644 --- a/include/uapi/linux/netfilter/xt_bpf.h +++ b/include/uapi/linux/netfilter/xt_bpf.h @@ -6,6 +6,8 @@ #define XT_BPF_MAX_NUM_INSTR 64 +struct sk_filter; + struct xt_bpf_info { __u16 bpf_program_num_elem; struct sock_filter bpf_program[XT_BPF_MAX_NUM_INSTR]; diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c index 17028648cfeb..cadddc8388f3 100644 --- a/ipc/ipc_sysctl.c +++ b/ipc/ipc_sysctl.c @@ -123,7 +123,6 @@ static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table ipc_table; - size_t lenp_bef = *lenp; int oldval; int rc; @@ -133,7 +132,7 @@ static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write, rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos); - if (write && !rc && lenp_bef == *lenp) { + if (write && !rc) { int newval = *((int *)(ipc_table.data)); /* * The file "auto_msgmni" has correctly been set. diff --git a/kernel/audit.c b/kernel/audit.c index 2c0ecd1753de..b45b2daa9f92 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -687,7 +687,7 @@ static int audit_get_feature(struct sk_buff *skb) seq = nlmsg_hdr(skb)->nlmsg_seq; - audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &af, sizeof(af)); + audit_send_reply(skb, seq, AUDIT_GET_FEATURE, 0, 0, &af, sizeof(af)); return 0; } @@ -702,7 +702,7 @@ static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_FEATURE_CHANGE); audit_log_task_info(ab, current); - audit_log_format(ab, "feature=%s old=%u new=%u old_lock=%u new_lock=%u res=%d", + audit_log_format(ab, " feature=%s old=%u new=%u old_lock=%u new_lock=%u res=%d", audit_feature_names[which], !!old_feature, !!new_feature, !!old_lock, !!new_lock, res); audit_log_end(ab); diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 135944a7b28a..a79db03990db 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -154,6 +154,7 @@ static struct audit_chunk *alloc_chunk(int count) chunk->owners[i].index = i; } fsnotify_init_mark(&chunk->mark, audit_tree_destroy_watch); + chunk->mark.mask = FS_IN_IGNORED; return chunk; } diff --git a/kernel/events/core.c b/kernel/events/core.c index 4ced342f1ba9..4bbb27adf23d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -39,6 +39,7 @@ #include #include #include +#include #include "internal.h" @@ -3693,6 +3694,26 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return 0; } +#ifdef CONFIG_COMPAT +static long perf_compat_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + switch (_IOC_NR(cmd)) { + case _IOC_NR(PERF_EVENT_IOC_SET_FILTER): + case _IOC_NR(PERF_EVENT_IOC_ID): + /* Fix up pointer size (usually 4 -> 8 in 32-on-64-bit case */ + if (_IOC_SIZE(cmd) == sizeof(compat_uptr_t)) { + cmd &= ~IOCSIZE_MASK; + cmd |= sizeof(void *) << IOCSIZE_SHIFT; + } + break; + } + return perf_ioctl(file, cmd, arg); +} +#else +# define perf_compat_ioctl NULL +#endif + int perf_event_task_enable(void) { struct perf_event *event; @@ -4185,7 +4206,7 @@ static const struct file_operations perf_fops = { .read = perf_read, .poll = perf_poll, .unlocked_ioctl = perf_ioctl, - .compat_ioctl = perf_ioctl, + .compat_ioctl = perf_compat_ioctl, .mmap = perf_mmap, .fasync = perf_fasync, }; diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index b3d116cd072d..6705d947ef14 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1228,6 +1228,22 @@ static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) } /* + * Awaken the grace-period kthread for the specified flavor of RCU. + * Don't do a self-awaken, and don't bother awakening when there is + * nothing for the grace-period kthread to do (as in several CPUs + * raced to awaken, and we lost), and finally don't try to awaken + * a kthread that has not yet been created. + */ +static void rcu_gp_kthread_wake(struct rcu_state *rsp) +{ + if (current == rsp->gp_kthread || + !ACCESS_ONCE(rsp->gp_flags) || + !rsp->gp_kthread) + return; + wake_up(&rsp->gp_wq); +} + +/* * If there is room, assign a ->completed number to any callbacks on * this CPU that have not already been assigned. Also accelerate any * callbacks that were previously assigned a ->completed number that has @@ -1670,7 +1686,7 @@ static void rsp_wakeup(struct irq_work *work) struct rcu_state *rsp = container_of(work, struct rcu_state, wakeup_work); /* Wake up rcu_gp_kthread() to start the grace period. */ - wake_up(&rsp->gp_wq); + rcu_gp_kthread_wake(rsp); } /* @@ -1746,7 +1762,7 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) { WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags); - wake_up(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */ + rcu_gp_kthread_wake(rsp); } /* @@ -2322,7 +2338,7 @@ static void force_quiescent_state(struct rcu_state *rsp) } rsp->gp_flags |= RCU_GP_FLAG_FQS; raw_spin_unlock_irqrestore(&rnp_old->lock, flags); - wake_up(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */ + rcu_gp_kthread_wake(rsp); } /* diff --git a/lib/radix-tree.c b/lib/radix-tree.c index bd4a8dfdf0b8..7e30d2a7f346 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -946,81 +946,6 @@ next: } EXPORT_SYMBOL(radix_tree_range_tag_if_tagged); - -/** - * radix_tree_next_hole - find the next hole (not-present entry) - * @root: tree root - * @index: index key - * @max_scan: maximum range to search - * - * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the lowest - * indexed hole. - * - * Returns: the index of the hole if found, otherwise returns an index - * outside of the set specified (in which case 'return - index >= max_scan' - * will be true). In rare cases of index wrap-around, 0 will be returned. - * - * radix_tree_next_hole may be called under rcu_read_lock. However, like - * radix_tree_gang_lookup, this will not atomically search a snapshot of - * the tree at a single point in time. For example, if a hole is created - * at index 5, then subsequently a hole is created at index 10, - * radix_tree_next_hole covering both indexes may return 10 if called - * under rcu_read_lock. - */ -unsigned long radix_tree_next_hole(struct radix_tree_root *root, - unsigned long index, unsigned long max_scan) -{ - unsigned long i; - - for (i = 0; i < max_scan; i++) { - if (!radix_tree_lookup(root, index)) - break; - index++; - if (index == 0) - break; - } - - return index; -} -EXPORT_SYMBOL(radix_tree_next_hole); - -/** - * radix_tree_prev_hole - find the prev hole (not-present entry) - * @root: tree root - * @index: index key - * @max_scan: maximum range to search - * - * Search backwards in the range [max(index-max_scan+1, 0), index] - * for the first hole. - * - * Returns: the index of the hole if found, otherwise returns an index - * outside of the set specified (in which case 'index - return >= max_scan' - * will be true). In rare cases of wrap-around, ULONG_MAX will be returned. - * - * radix_tree_next_hole may be called under rcu_read_lock. However, like - * radix_tree_gang_lookup, this will not atomically search a snapshot of - * the tree at a single point in time. For example, if a hole is created - * at index 10, then subsequently a hole is created at index 5, - * radix_tree_prev_hole covering both indexes may return 5 if called under - * rcu_read_lock. - */ -unsigned long radix_tree_prev_hole(struct radix_tree_root *root, - unsigned long index, unsigned long max_scan) -{ - unsigned long i; - - for (i = 0; i < max_scan; i++) { - if (!radix_tree_lookup(root, index)) - break; - index--; - if (index == ULONG_MAX) - break; - } - - return index; -} -EXPORT_SYMBOL(radix_tree_prev_hole); - /** * radix_tree_gang_lookup - perform multiple lookup on a radix tree * @root: radix tree root @@ -1337,15 +1262,18 @@ static inline void radix_tree_shrink(struct radix_tree_root *root) } /** - * radix_tree_delete - delete an item from a radix tree + * radix_tree_delete_item - delete an item from a radix tree * @root: radix tree root * @index: index key + * @item: expected item * - * Remove the item at @index from the radix tree rooted at @root. + * Remove @item at @index from the radix tree rooted at @root. * - * Returns the address of the deleted item, or NULL if it was not present. + * Returns the address of the deleted item, or NULL if it was not present + * or the entry at the given @index was not @item. */ -void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) +void *radix_tree_delete_item(struct radix_tree_root *root, + unsigned long index, void *item) { struct radix_tree_node *node = NULL; struct radix_tree_node *slot = NULL; @@ -1380,6 +1308,11 @@ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) if (slot == NULL) goto out; + if (item && slot != item) { + slot = NULL; + goto out; + } + /* * Clear all tags associated with the item to be deleted. * This way of doing it would be inefficient, but seldom is any set. @@ -1424,6 +1357,21 @@ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) out: return slot; } +EXPORT_SYMBOL(radix_tree_delete_item); + +/** + * radix_tree_delete - delete an item from a radix tree + * @root: radix tree root + * @index: index key + * + * Remove the item at @index from the radix tree rooted at @root. + * + * Returns the address of the deleted item, or NULL if it was not present. + */ +void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) +{ + return radix_tree_delete_item(root, index, NULL); +} EXPORT_SYMBOL(radix_tree_delete); /** diff --git a/mm/compaction.c b/mm/compaction.c index 5e38e5706f62..4229fc22a477 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -89,7 +89,8 @@ static void __reset_isolation_suitable(struct zone *zone) unsigned long end_pfn = zone_end_pfn(zone); unsigned long pfn; - zone->compact_cached_migrate_pfn = start_pfn; + zone->compact_cached_migrate_pfn[0] = start_pfn; + zone->compact_cached_migrate_pfn[1] = start_pfn; zone->compact_cached_free_pfn = end_pfn; zone->compact_blockskip_flush = false; @@ -131,9 +132,10 @@ void reset_isolation_suitable(pg_data_t *pgdat) */ static void update_pageblock_skip(struct compact_control *cc, struct page *page, unsigned long nr_isolated, - bool migrate_scanner) + bool set_unsuitable, bool migrate_scanner) { struct zone *zone = cc->zone; + unsigned long pfn; if (cc->ignore_skip_hint) return; @@ -141,20 +143,32 @@ static void update_pageblock_skip(struct compact_control *cc, if (!page) return; - if (!nr_isolated) { - unsigned long pfn = page_to_pfn(page); + if (nr_isolated) + return; + + /* + * Only skip pageblocks when all forms of compaction will be known to + * fail in the near future. + */ + if (set_unsuitable) set_pageblock_skip(page); - /* Update where compaction should restart */ - if (migrate_scanner) { - if (!cc->finished_update_migrate && - pfn > zone->compact_cached_migrate_pfn) - zone->compact_cached_migrate_pfn = pfn; - } else { - if (!cc->finished_update_free && - pfn < zone->compact_cached_free_pfn) - zone->compact_cached_free_pfn = pfn; - } + pfn = page_to_pfn(page); + + /* Update where async and sync compaction should restart */ + if (migrate_scanner) { + if (cc->finished_update_migrate) + return; + if (pfn > zone->compact_cached_migrate_pfn[0]) + zone->compact_cached_migrate_pfn[0] = pfn; + if (cc->mode != MIGRATE_ASYNC && + pfn > zone->compact_cached_migrate_pfn[1]) + zone->compact_cached_migrate_pfn[1] = pfn; + } else { + if (cc->finished_update_free) + return; + if (pfn < zone->compact_cached_free_pfn) + zone->compact_cached_free_pfn = pfn; } } #else @@ -166,7 +180,7 @@ static inline bool isolation_suitable(struct compact_control *cc, static void update_pageblock_skip(struct compact_control *cc, struct page *page, unsigned long nr_isolated, - bool migrate_scanner) + bool set_unsuitable, bool migrate_scanner) { } #endif /* CONFIG_COMPACTION */ @@ -195,7 +209,7 @@ static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags, } /* async aborts if taking too long or contended */ - if (!cc->sync) { + if (cc->mode == MIGRATE_ASYNC) { cc->contended = true; return false; } @@ -208,10 +222,28 @@ static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags, return true; } -static inline bool compact_trylock_irqsave(spinlock_t *lock, - unsigned long *flags, struct compact_control *cc) +/* + * Aside from avoiding lock contention, compaction also periodically checks + * need_resched() and either schedules in sync compaction or aborts async + * compaction. This is similar to what compact_checklock_irqsave() does, but + * is used where no lock is concerned. + * + * Returns false when no scheduling was needed, or sync compaction scheduled. + * Returns true when async compaction should abort. + */ +static inline bool compact_should_abort(struct compact_control *cc) { - return compact_checklock_irqsave(lock, flags, false, cc); + /* async compaction aborts if contended */ + if (need_resched()) { + if (cc->mode == MIGRATE_ASYNC) { + cc->contended = true; + return true; + } + + cond_resched(); + } + + return false; } /* Returns true if the page is within a block suitable for migration to */ @@ -329,7 +361,8 @@ isolate_fail: /* Update the pageblock-skip if the whole pageblock was scanned */ if (blockpfn == end_pfn) - update_pageblock_skip(cc, valid_page, total_isolated, false); + update_pageblock_skip(cc, valid_page, total_isolated, true, + false); count_compact_events(COMPACTFREE_SCANNED, nr_scanned); if (total_isolated) @@ -464,8 +497,9 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, unsigned long flags; bool locked = false; struct page *page = NULL, *valid_page = NULL; - bool skipped_async_unsuitable = false; - const isolate_mode_t mode = (!cc->sync ? ISOLATE_ASYNC_MIGRATE : 0) | + bool set_unsuitable = true; + const isolate_mode_t mode = (cc->mode == MIGRATE_ASYNC ? + ISOLATE_ASYNC_MIGRATE : 0) | (unevictable ? ISOLATE_UNEVICTABLE : 0); /* @@ -475,7 +509,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, */ while (unlikely(too_many_isolated(zone))) { /* async migration should just abort */ - if (!cc->sync) + if (cc->mode == MIGRATE_ASYNC) return 0; congestion_wait(BLK_RW_ASYNC, HZ/10); @@ -484,8 +518,10 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, return 0; } + if (compact_should_abort(cc)) + return 0; + /* Time to isolate some pages for migration */ - cond_resched(); for (; low_pfn < end_pfn; low_pfn++) { /* give a chance to irqs before checking need_resched() */ if (locked && !(low_pfn % SWAP_CLUSTER_MAX)) { @@ -540,9 +576,9 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, * the minimum amount of work satisfies the allocation */ mt = get_pageblock_migratetype(page); - if (!cc->sync && !migrate_async_suitable(mt)) { - cc->finished_update_migrate = true; - skipped_async_unsuitable = true; + if (cc->mode == MIGRATE_ASYNC && + !migrate_async_suitable(mt)) { + set_unsuitable = false; goto next_pageblock; } } @@ -646,11 +682,10 @@ next_pageblock: /* * Update the pageblock-skip information and cached scanner pfn, * if the whole pageblock was scanned without isolating any page. - * This is not done when pageblock was skipped due to being unsuitable - * for async compaction, so that eventual sync compaction can try. */ - if (low_pfn == end_pfn && !skipped_async_unsuitable) - update_pageblock_skip(cc, valid_page, nr_isolated, true); + if (low_pfn == end_pfn) + update_pageblock_skip(cc, valid_page, nr_isolated, + set_unsuitable, true); trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated); @@ -671,7 +706,9 @@ static void isolate_freepages(struct zone *zone, struct compact_control *cc) { struct page *page; - unsigned long high_pfn, low_pfn, pfn, z_end_pfn; + unsigned long block_start_pfn; /* start of current pageblock */ + unsigned long block_end_pfn; /* end of current pageblock */ + unsigned long low_pfn; /* lowest pfn scanner is able to scan */ int nr_freepages = cc->nr_freepages; struct list_head *freelist = &cc->freepages; @@ -679,41 +716,38 @@ static void isolate_freepages(struct zone *zone, * Initialise the free scanner. The starting point is where we last * successfully isolated from, zone-cached value, or the end of the * zone when isolating for the first time. We need this aligned to - * the pageblock boundary, because we do pfn -= pageblock_nr_pages - * in the for loop. + * the pageblock boundary, because we do + * block_start_pfn -= pageblock_nr_pages in the for loop. + * For ending point, take care when isolating in last pageblock of a + * a zone which ends in the middle of a pageblock. * The low boundary is the end of the pageblock the migration scanner * is using. */ - pfn = cc->free_pfn & ~(pageblock_nr_pages-1); + block_start_pfn = cc->free_pfn & ~(pageblock_nr_pages-1); + block_end_pfn = min(block_start_pfn + pageblock_nr_pages, + zone_end_pfn(zone)); low_pfn = ALIGN(cc->migrate_pfn + 1, pageblock_nr_pages); /* - * Take care that if the migration scanner is at the end of the zone - * that the free scanner does not accidentally move to the next zone - * in the next isolation cycle. - */ - high_pfn = min(low_pfn, pfn); - - z_end_pfn = zone_end_pfn(zone); - - /* * Isolate free pages until enough are available to migrate the * pages on cc->migratepages. We stop searching if the migrate * and free page scanners meet or enough free pages are isolated. */ - for (; pfn >= low_pfn && cc->nr_migratepages > nr_freepages; - pfn -= pageblock_nr_pages) { + for (; block_start_pfn >= low_pfn && cc->nr_migratepages > nr_freepages; + block_end_pfn = block_start_pfn, + block_start_pfn -= pageblock_nr_pages) { unsigned long isolated; - unsigned long end_pfn; /* * This can iterate a massively long zone without finding any * suitable migration targets, so periodically check if we need - * to schedule. + * to schedule, or even abort async compaction. */ - cond_resched(); + if (!(block_start_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages)) + && compact_should_abort(cc)) + break; - if (!pfn_valid(pfn)) + if (!pfn_valid(block_start_pfn)) continue; /* @@ -723,7 +757,7 @@ static void isolate_freepages(struct zone *zone, * i.e. it's possible that all pages within a zones range of * pages do not belong to a single zone. */ - page = pfn_to_page(pfn); + page = pfn_to_page(block_start_pfn); if (page_zone(page) != zone) continue; @@ -736,26 +770,26 @@ static void isolate_freepages(struct zone *zone, continue; /* Found a block suitable for isolating free pages from */ - isolated = 0; + cc->free_pfn = block_start_pfn; + isolated = isolate_freepages_block(cc, block_start_pfn, + block_end_pfn, freelist, false); + nr_freepages += isolated; /* - * Take care when isolating in last pageblock of a zone which - * ends in the middle of a pageblock. + * Set a flag that we successfully isolated in this pageblock. + * In the next loop iteration, zone->compact_cached_free_pfn + * will not be updated and thus it will effectively contain the + * highest pageblock we isolated pages from. */ - end_pfn = min(pfn + pageblock_nr_pages, z_end_pfn); - isolated = isolate_freepages_block(cc, pfn, end_pfn, - freelist, false); - nr_freepages += isolated; + if (isolated) + cc->finished_update_free = true; /* - * Record the highest PFN we isolated pages from. When next - * looking for free pages, the search will restart here as - * page migration may have returned some pages to the allocator + * isolate_freepages_block() might have aborted due to async + * compaction being contended */ - if (isolated) { - cc->finished_update_free = true; - high_pfn = max(high_pfn, pfn); - } + if (cc->contended) + break; } /* split_free_page does not map the pages */ @@ -765,10 +799,9 @@ static void isolate_freepages(struct zone *zone, * If we crossed the migrate scanner, we want to keep it that way * so that compact_finished() may detect this */ - if (pfn < low_pfn) - cc->free_pfn = max(pfn, zone->zone_start_pfn); - else - cc->free_pfn = high_pfn; + if (block_start_pfn < low_pfn) + cc->free_pfn = cc->migrate_pfn; + cc->nr_freepages = nr_freepages; } @@ -783,9 +816,13 @@ static struct page *compaction_alloc(struct page *migratepage, struct compact_control *cc = (struct compact_control *)data; struct page *freepage; - /* Isolate free pages if necessary */ + /* + * Isolate free pages if necessary, and if we are not aborting due to + * contention. + */ if (list_empty(&cc->freepages)) { - isolate_freepages(cc->zone, cc); + if (!cc->contended) + isolate_freepages(cc->zone, cc); if (list_empty(&cc->freepages)) return NULL; @@ -799,23 +836,16 @@ static struct page *compaction_alloc(struct page *migratepage, } /* - * We cannot control nr_migratepages and nr_freepages fully when migration is - * running as migrate_pages() has no knowledge of compact_control. When - * migration is complete, we count the number of pages on the lists by hand. + * This is a migrate-callback that "frees" freepages back to the isolated + * freelist. All pages on the freelist are from the same zone, so there is no + * special handling needed for NUMA. */ -static void update_nr_listpages(struct compact_control *cc) +static void compaction_free(struct page *page, unsigned long data) { - int nr_migratepages = 0; - int nr_freepages = 0; - struct page *page; - - list_for_each_entry(page, &cc->migratepages, lru) - nr_migratepages++; - list_for_each_entry(page, &cc->freepages, lru) - nr_freepages++; + struct compact_control *cc = (struct compact_control *)data; - cc->nr_migratepages = nr_migratepages; - cc->nr_freepages = nr_freepages; + list_add(&page->lru, &cc->freepages); + cc->nr_freepages++; } /* possible outcome of isolate_migratepages */ @@ -862,13 +892,14 @@ static int compact_finished(struct zone *zone, unsigned int order; unsigned long watermark; - if (fatal_signal_pending(current)) + if (cc->contended || fatal_signal_pending(current)) return COMPACT_PARTIAL; /* Compaction run completes if the migrate and free scanner meet */ if (cc->free_pfn <= cc->migrate_pfn) { /* Let the next compaction start anew. */ - zone->compact_cached_migrate_pfn = zone->zone_start_pfn; + zone->compact_cached_migrate_pfn[0] = zone->zone_start_pfn; + zone->compact_cached_migrate_pfn[1] = zone->zone_start_pfn; zone->compact_cached_free_pfn = zone_end_pfn(zone); /* @@ -968,6 +999,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) int ret; unsigned long start_pfn = zone->zone_start_pfn; unsigned long end_pfn = zone_end_pfn(zone); + const bool sync = cc->mode != MIGRATE_ASYNC; ret = compaction_suitable(zone, cc->order); switch (ret) { @@ -993,7 +1025,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) * information on where the scanners should start but check that it * is initialised by ensuring the values are within zone boundaries. */ - cc->migrate_pfn = zone->compact_cached_migrate_pfn; + cc->migrate_pfn = zone->compact_cached_migrate_pfn[sync]; cc->free_pfn = zone->compact_cached_free_pfn; if (cc->free_pfn < start_pfn || cc->free_pfn > end_pfn) { cc->free_pfn = end_pfn & ~(pageblock_nr_pages-1); @@ -1001,7 +1033,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) } if (cc->migrate_pfn < start_pfn || cc->migrate_pfn > end_pfn) { cc->migrate_pfn = start_pfn; - zone->compact_cached_migrate_pfn = cc->migrate_pfn; + zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn; + zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn; } trace_mm_compaction_begin(start_pfn, cc->migrate_pfn, cc->free_pfn, end_pfn); @@ -1009,7 +1042,6 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) migrate_prep_local(); while ((ret = compact_finished(zone, cc)) == COMPACT_CONTINUE) { - unsigned long nr_migrate, nr_remaining; int err; switch (isolate_migratepages(zone, cc)) { @@ -1024,21 +1056,20 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) ; } - nr_migrate = cc->nr_migratepages; + if (!cc->nr_migratepages) + continue; + err = migrate_pages(&cc->migratepages, compaction_alloc, - (unsigned long)cc, - cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC, + compaction_free, (unsigned long)cc, cc->mode, MR_COMPACTION); - update_nr_listpages(cc); - nr_remaining = cc->nr_migratepages; - trace_mm_compaction_migratepages(nr_migrate - nr_remaining, - nr_remaining); + trace_mm_compaction_migratepages(cc->nr_migratepages, err, + &cc->migratepages); - /* Release isolated pages not migrated */ + /* All pages were either migrated or will be released */ + cc->nr_migratepages = 0; if (err) { putback_movable_pages(&cc->migratepages); - cc->nr_migratepages = 0; /* * migrate_pages() may return -ENOMEM when scanners meet * and we want compact_finished() to detect it @@ -1060,9 +1091,8 @@ out: return ret; } -static unsigned long compact_zone_order(struct zone *zone, - int order, gfp_t gfp_mask, - bool sync, bool *contended) +static unsigned long compact_zone_order(struct zone *zone, int order, + gfp_t gfp_mask, enum migrate_mode mode, bool *contended) { unsigned long ret; struct compact_control cc = { @@ -1071,7 +1101,7 @@ static unsigned long compact_zone_order(struct zone *zone, .order = order, .migratetype = allocflags_to_migratetype(gfp_mask), .zone = zone, - .sync = sync, + .mode = mode, }; INIT_LIST_HEAD(&cc.freepages); INIT_LIST_HEAD(&cc.migratepages); @@ -1093,7 +1123,7 @@ int sysctl_extfrag_threshold = 500; * @order: The order of the current allocation * @gfp_mask: The GFP mask of the current allocation * @nodemask: The allowed nodes to allocate from - * @sync: Whether migration is synchronous or not + * @mode: The migration mode for async, sync light, or sync migration * @contended: Return value that is true if compaction was aborted due to lock contention * @page: Optionally capture a free page of the requested order during compaction * @@ -1101,7 +1131,7 @@ int sysctl_extfrag_threshold = 500; */ unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask, - bool sync, bool *contended) + enum migrate_mode mode, bool *contended) { enum zone_type high_zoneidx = gfp_zone(gfp_mask); int may_enter_fs = gfp_mask & __GFP_FS; @@ -1126,7 +1156,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, nodemask) { int status; - status = compact_zone_order(zone, order, gfp_mask, sync, + status = compact_zone_order(zone, order, gfp_mask, mode, contended); rc = max(status, rc); @@ -1165,9 +1195,6 @@ static void __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc) if (zone_watermark_ok(zone, cc->order, low_wmark_pages(zone), 0, 0)) compaction_defer_reset(zone, cc->order, false); - /* Currently async compaction is never deferred. */ - else if (cc->sync) - defer_compaction(zone, cc->order); } VM_BUG_ON(!list_empty(&cc->freepages)); @@ -1179,7 +1206,7 @@ void compact_pgdat(pg_data_t *pgdat, int order) { struct compact_control cc = { .order = order, - .sync = false, + .mode = MIGRATE_ASYNC, }; if (!order) @@ -1192,7 +1219,7 @@ static void compact_node(int nid) { struct compact_control cc = { .order = -1, - .sync = true, + .mode = MIGRATE_SYNC, .ignore_skip_hint = true, }; diff --git a/mm/filemap.c b/mm/filemap.c index c2cc7c95eff1..bdaa21555abe 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -448,6 +448,29 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) } EXPORT_SYMBOL_GPL(replace_page_cache_page); +static int page_cache_tree_insert(struct address_space *mapping, + struct page *page) +{ + void **slot; + int error; + + slot = radix_tree_lookup_slot(&mapping->page_tree, page->index); + if (slot) { + void *p; + + p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock); + if (!radix_tree_exceptional_entry(p)) + return -EEXIST; + radix_tree_replace_slot(slot, page); + mapping->nrpages++; + return 0; + } + error = radix_tree_insert(&mapping->page_tree, page->index, page); + if (!error) + mapping->nrpages++; + return error; +} + /** * add_to_page_cache_locked - add a locked page to the pagecache * @page: page to add @@ -482,11 +505,10 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, page->index = offset; spin_lock_irq(&mapping->tree_lock); - error = radix_tree_insert(&mapping->page_tree, offset, page); + error = page_cache_tree_insert(mapping, page); radix_tree_preload_end(); if (unlikely(error)) goto err_insert; - mapping->nrpages++; __inc_zone_page_state(page, NR_FILE_PAGES); spin_unlock_irq(&mapping->tree_lock); trace_mm_filemap_add_to_page_cache(page); @@ -688,14 +710,101 @@ int __lock_page_or_retry(struct page *page, struct mm_struct *mm, } /** - * find_get_page - find and get a page reference + * page_cache_next_hole - find the next hole (not-present entry) + * @mapping: mapping + * @index: index + * @max_scan: maximum range to search + * + * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the + * lowest indexed hole. + * + * Returns: the index of the hole if found, otherwise returns an index + * outside of the set specified (in which case 'return - index >= + * max_scan' will be true). In rare cases of index wrap-around, 0 will + * be returned. + * + * page_cache_next_hole may be called under rcu_read_lock. However, + * like radix_tree_gang_lookup, this will not atomically search a + * snapshot of the tree at a single point in time. For example, if a + * hole is created at index 5, then subsequently a hole is created at + * index 10, page_cache_next_hole covering both indexes may return 10 + * if called under rcu_read_lock. + */ +pgoff_t page_cache_next_hole(struct address_space *mapping, + pgoff_t index, unsigned long max_scan) +{ + unsigned long i; + + for (i = 0; i < max_scan; i++) { + struct page *page; + + page = radix_tree_lookup(&mapping->page_tree, index); + if (!page || radix_tree_exceptional_entry(page)) + break; + index++; + if (index == 0) + break; + } + + return index; +} +EXPORT_SYMBOL(page_cache_next_hole); + +/** + * page_cache_prev_hole - find the prev hole (not-present entry) + * @mapping: mapping + * @index: index + * @max_scan: maximum range to search + * + * Search backwards in the range [max(index-max_scan+1, 0), index] for + * the first hole. + * + * Returns: the index of the hole if found, otherwise returns an index + * outside of the set specified (in which case 'index - return >= + * max_scan' will be true). In rare cases of wrap-around, ULONG_MAX + * will be returned. + * + * page_cache_prev_hole may be called under rcu_read_lock. However, + * like radix_tree_gang_lookup, this will not atomically search a + * snapshot of the tree at a single point in time. For example, if a + * hole is created at index 10, then subsequently a hole is created at + * index 5, page_cache_prev_hole covering both indexes may return 5 if + * called under rcu_read_lock. + */ +pgoff_t page_cache_prev_hole(struct address_space *mapping, + pgoff_t index, unsigned long max_scan) +{ + unsigned long i; + + for (i = 0; i < max_scan; i++) { + struct page *page; + + page = radix_tree_lookup(&mapping->page_tree, index); + if (!page || radix_tree_exceptional_entry(page)) + break; + index--; + if (index == ULONG_MAX) + break; + } + + return index; +} +EXPORT_SYMBOL(page_cache_prev_hole); + +/** + * find_get_entry - find and get a page cache entry * @mapping: the address_space to search - * @offset: the page index + * @offset: the page cache index * - * Is there a pagecache struct page at the given (mapping, offset) tuple? - * If yes, increment its refcount and return it; if no, return NULL. + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned with an increased refcount. + * + * If the slot holds a shadow entry of a previously evicted page, it + * is returned. + * + * Otherwise, %NULL is returned. */ -struct page *find_get_page(struct address_space *mapping, pgoff_t offset) +struct page *find_get_entry(struct address_space *mapping, pgoff_t offset) { void **pagep; struct page *page; @@ -736,24 +845,50 @@ out: return page; } -EXPORT_SYMBOL(find_get_page); +EXPORT_SYMBOL(find_get_entry); /** - * find_lock_page - locate, pin and lock a pagecache page + * find_get_page - find and get a page reference * @mapping: the address_space to search * @offset: the page index * - * Locates the desired pagecache page, locks it, increments its reference - * count and returns its address. + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned with an increased refcount. * - * Returns zero if the page was not present. find_lock_page() may sleep. + * Otherwise, %NULL is returned. */ -struct page *find_lock_page(struct address_space *mapping, pgoff_t offset) +struct page *find_get_page(struct address_space *mapping, pgoff_t offset) +{ + struct page *page = find_get_entry(mapping, offset); + + if (radix_tree_exceptional_entry(page)) + page = NULL; + return page; +} +EXPORT_SYMBOL(find_get_page); + +/** + * find_lock_entry - locate, pin and lock a page cache entry + * @mapping: the address_space to search + * @offset: the page cache index + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. + * + * If the slot holds a shadow entry of a previously evicted page, it + * is returned. + * + * Otherwise, %NULL is returned. + * + * find_lock_entry() may sleep. + */ +struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset) { struct page *page; repeat: - page = find_get_page(mapping, offset); + page = find_get_entry(mapping, offset); if (page && !radix_tree_exception(page)) { lock_page(page); /* Has the page been truncated? */ @@ -766,6 +901,29 @@ repeat: } return page; } +EXPORT_SYMBOL(find_lock_entry); + +/** + * find_lock_page - locate, pin and lock a pagecache page + * @mapping: the address_space to search + * @offset: the page index + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. + * + * Otherwise, %NULL is returned. + * + * find_lock_page() may sleep. + */ +struct page *find_lock_page(struct address_space *mapping, pgoff_t offset) +{ + struct page *page = find_lock_entry(mapping, offset); + + if (radix_tree_exceptional_entry(page)) + page = NULL; + return page; +} EXPORT_SYMBOL(find_lock_page); /** @@ -774,16 +932,18 @@ EXPORT_SYMBOL(find_lock_page); * @index: the page's index into the mapping * @gfp_mask: page allocation mode * - * Locates a page in the pagecache. If the page is not present, a new page - * is allocated using @gfp_mask and is added to the pagecache and to the VM's - * LRU list. The returned page is locked and has its reference count - * incremented. + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. + * + * If the page is not present, a new page is allocated using @gfp_mask + * and added to the page cache and the VM's LRU list. The page is + * returned locked and with an increased refcount. * - * find_or_create_page() may sleep, even if @gfp_flags specifies an atomic - * allocation! + * On memory exhaustion, %NULL is returned. * - * find_or_create_page() returns the desired page's address, or zero on - * memory exhaustion. + * find_or_create_page() may sleep, even if @gfp_flags specifies an + * atomic allocation! */ struct page *find_or_create_page(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask) @@ -816,6 +976,76 @@ repeat: EXPORT_SYMBOL(find_or_create_page); /** + * find_get_entries - gang pagecache lookup + * @mapping: The address_space to search + * @start: The starting page cache index + * @nr_entries: The maximum number of entries + * @entries: Where the resulting entries are placed + * @indices: The cache indices corresponding to the entries in @entries + * + * find_get_entries() will search for and return a group of up to + * @nr_entries entries in the mapping. The entries are placed at + * @entries. find_get_entries() takes a reference against any actual + * pages it returns. + * + * The search returns a group of mapping-contiguous page cache entries + * with ascending indexes. There may be holes in the indices due to + * not-present pages. + * + * Any shadow entries of evicted pages are included in the returned + * array. + * + * find_get_entries() returns the number of pages and shadow entries + * which were found. + */ +unsigned find_get_entries(struct address_space *mapping, + pgoff_t start, unsigned int nr_entries, + struct page **entries, pgoff_t *indices) +{ + void **slot; + unsigned int ret = 0; + struct radix_tree_iter iter; + + if (!nr_entries) + return 0; + + rcu_read_lock(); +restart: + radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { + struct page *page; +repeat: + page = radix_tree_deref_slot(slot); + if (unlikely(!page)) + continue; + if (radix_tree_exception(page)) { + if (radix_tree_deref_retry(page)) + goto restart; + /* + * Otherwise, we must be storing a swap entry + * here as an exceptional entry: so return it + * without attempting to raise page count. + */ + goto export; + } + if (!page_cache_get_speculative(page)) + goto repeat; + + /* Has the page moved? */ + if (unlikely(page != *slot)) { + page_cache_release(page); + goto repeat; + } +export: + indices[ret] = iter.index; + entries[ret] = page; + if (++ret == nr_entries) + break; + } + rcu_read_unlock(); + return ret; +} + +/** * find_get_pages - gang pagecache lookup * @mapping: The address_space to search * @start: The starting page index @@ -1797,6 +2027,18 @@ int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma) EXPORT_SYMBOL(generic_file_mmap); EXPORT_SYMBOL(generic_file_readonly_mmap); +static struct page *wait_on_page_read(struct page *page) +{ + if (!IS_ERR(page)) { + wait_on_page_locked(page); + if (!PageUptodate(page)) { + page_cache_release(page); + page = ERR_PTR(-EIO); + } + } + return page; +} + static struct page *__read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *, struct page *), @@ -1823,6 +2065,8 @@ repeat: if (err < 0) { page_cache_release(page); page = ERR_PTR(err); + } else { + page = wait_on_page_read(page); } } return page; @@ -1859,6 +2103,10 @@ retry: if (err < 0) { page_cache_release(page); return ERR_PTR(err); + } else { + page = wait_on_page_read(page); + if (IS_ERR(page)) + return page; } out: mark_page_accessed(page); @@ -1866,40 +2114,25 @@ out: } /** - * read_cache_page_async - read into page cache, fill it if needed + * read_cache_page - read into page cache, fill it if needed * @mapping: the page's address_space * @index: the page index * @filler: function to perform the read * @data: first arg to filler(data, page) function, often left as NULL * - * Same as read_cache_page, but don't wait for page to become unlocked - * after submitting it to the filler. - * * Read into the page cache. If a page already exists, and PageUptodate() is - * not set, try to fill the page but don't wait for it to become unlocked. + * not set, try to fill the page and wait for it to become unlocked. * * If the page does not get brought uptodate, return -EIO. */ -struct page *read_cache_page_async(struct address_space *mapping, +struct page *read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *, struct page *), void *data) { return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping)); } -EXPORT_SYMBOL(read_cache_page_async); - -static struct page *wait_on_page_read(struct page *page) -{ - if (!IS_ERR(page)) { - wait_on_page_locked(page); - if (!PageUptodate(page)) { - page_cache_release(page); - page = ERR_PTR(-EIO); - } - } - return page; -} +EXPORT_SYMBOL(read_cache_page); /** * read_cache_page_gfp - read into page cache, using specified page allocation flags. @@ -1918,31 +2151,10 @@ struct page *read_cache_page_gfp(struct address_space *mapping, { filler_t *filler = (filler_t *)mapping->a_ops->readpage; - return wait_on_page_read(do_read_cache_page(mapping, index, filler, NULL, gfp)); + return do_read_cache_page(mapping, index, filler, NULL, gfp); } EXPORT_SYMBOL(read_cache_page_gfp); -/** - * read_cache_page - read into page cache, fill it if needed - * @mapping: the page's address_space - * @index: the page index - * @filler: function to perform the read - * @data: first arg to filler(data, page) function, often left as NULL - * - * Read into the page cache. If a page already exists, and PageUptodate() is - * not set, try to fill the page then wait for it to become unlocked. - * - * If the page does not get brought uptodate, return -EIO. - */ -struct page *read_cache_page(struct address_space *mapping, - pgoff_t index, - int (*filler)(void *, struct page *), - void *data) -{ - return wait_on_page_read(read_cache_page_async(mapping, index, filler, data)); -} -EXPORT_SYMBOL(read_cache_page); - static size_t __iovec_copy_from_user_inatomic(char *vaddr, const struct iovec *iov, size_t base, size_t bytes) { @@ -1976,7 +2188,6 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, char *kaddr; size_t copied; - BUG_ON(!in_atomic()); kaddr = kmap_atomic(page); if (likely(i->nr_segs == 1)) { int left; @@ -2350,9 +2561,7 @@ again: if (mapping_writably_mapped(mapping)) flush_dcache_page(page); - pagefault_disable(); copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); - pagefault_enable(); flush_dcache_page(page); mark_page_accessed(page); diff --git a/mm/internal.h b/mm/internal.h index 3e910000fda4..1a8a0d4b687a 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -11,6 +11,7 @@ #ifndef __MM_INTERNAL_H #define __MM_INTERNAL_H +#include #include void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, @@ -21,6 +22,20 @@ static inline void set_page_count(struct page *page, int v) atomic_set(&page->_count, v); } +extern int __do_page_cache_readahead(struct address_space *mapping, + struct file *filp, pgoff_t offset, unsigned long nr_to_read, + unsigned long lookahead_size); + +/* + * Submit IO for the read-ahead request in file_ra_state. + */ +static inline unsigned long ra_submit(struct file_ra_state *ra, + struct address_space *mapping, struct file *filp) +{ + return __do_page_cache_readahead(mapping, filp, + ra->start, ra->size, ra->async_size); +} + /* * Turn a non-refcounted page (->_count == 0) into refcounted with * a count of one. @@ -119,7 +134,7 @@ struct compact_control { unsigned long nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ unsigned long migrate_pfn; /* isolate_migratepages search base */ - bool sync; /* Synchronous migration */ + enum migrate_mode mode; /* Async or sync migration mode */ bool ignore_skip_hint; /* Scan blocks even if marked skip */ bool finished_update_free; /* True when the zone cached pfns are * no longer being updated @@ -129,7 +144,10 @@ struct compact_control { int order; /* order a direct compactor needs */ int migratetype; /* MOVABLE, RECLAIMABLE etc */ struct zone *zone; - bool contended; /* True if a lock was contended */ + bool contended; /* True if a lock was contended, or + * need_resched() true during async + * compaction + */ }; unsigned long diff --git a/mm/madvise.c b/mm/madvise.c index 539eeb96b323..a402f8fdc68e 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -195,7 +195,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma, for (; start < end; start += PAGE_SIZE) { index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; - page = find_get_page(mapping, index); + page = find_get_entry(mapping, index); if (!radix_tree_exceptional_entry(page)) { if (page) page_cache_release(page); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 33365e9ce6a7..a98c7fce470a 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1540,7 +1540,7 @@ static int soft_offline_huge_page(struct page *page, int flags) /* Keep page count to indicate a given hugepage is isolated. */ list_move(&hpage->lru, &pagelist); - ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, + ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { pr_info("soft offline: %#lx: migration failed %d, type %lx\n", @@ -1621,7 +1621,7 @@ static int __soft_offline_page(struct page *page, int flags) inc_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); list_add(&page->lru, &pagelist); - ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, + ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { if (!list_empty(&pagelist)) { diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index a650db29606f..f6f23833de44 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1332,7 +1332,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) * alloc_migrate_target should be improooooved!! * migrate_pages returns # of failed pages. */ - ret = migrate_pages(&source, alloc_migrate_target, 0, + ret = migrate_pages(&source, alloc_migrate_target, NULL, 0, MIGRATE_SYNC, MR_MEMORY_HOTPLUG); if (ret) putback_movable_pages(&source); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 796c7e6cf93b..e8fff0fa1202 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1060,7 +1060,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, flags | MPOL_MF_DISCONTIG_OK, &pagelist); if (!list_empty(&pagelist)) { - err = migrate_pages(&pagelist, new_node_page, dest, + err = migrate_pages(&pagelist, new_node_page, NULL, dest, MIGRATE_SYNC, MR_SYSCALL); if (err) putback_movable_pages(&pagelist); @@ -1306,7 +1306,7 @@ static long do_mbind(unsigned long start, unsigned long len, if (!list_empty(&pagelist)) { WARN_ON_ONCE(flags & MPOL_MF_LAZY); - nr_failed = migrate_pages(&pagelist, new_page, + nr_failed = migrate_pages(&pagelist, new_page, NULL, start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND); if (nr_failed) putback_movable_pages(&pagelist); diff --git a/mm/migrate.c b/mm/migrate.c index 13f47fbe3550..3acac4a62c4b 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -941,8 +941,9 @@ out: * Obtain the lock on page, remove all ptes and migrate the page * to the newly allocated page in newpage. */ -static int unmap_and_move(new_page_t get_new_page, unsigned long private, - struct page *page, int force, enum migrate_mode mode) +static int unmap_and_move(new_page_t get_new_page, free_page_t put_new_page, + unsigned long private, struct page *page, int force, + enum migrate_mode mode) { int rc = 0; int *result = NULL; @@ -986,11 +987,18 @@ out: page_is_file_cache(page)); putback_lru_page(page); } + /* - * Move the new page to the LRU. If migration was not successful - * then this will free the page. + * If migration was not successful and there's a freeing callback, use + * it. Otherwise, putback_lru_page() will drop the reference grabbed + * during isolation. */ - putback_lru_page(newpage); + if (rc != MIGRATEPAGE_SUCCESS && put_new_page) { + ClearPageSwapBacked(newpage); + put_new_page(newpage, private); + } else + putback_lru_page(newpage); + if (result) { if (rc) *result = rc; @@ -1019,8 +1027,9 @@ out: * will wait in the page fault for migration to complete. */ static int unmap_and_move_huge_page(new_page_t get_new_page, - unsigned long private, struct page *hpage, - int force, enum migrate_mode mode) + free_page_t put_new_page, unsigned long private, + struct page *hpage, int force, + enum migrate_mode mode) { int rc = 0; int *result = NULL; @@ -1059,20 +1068,30 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, if (!page_mapped(hpage)) rc = move_to_new_page(new_hpage, hpage, 1, mode); - if (rc) + if (rc != MIGRATEPAGE_SUCCESS) remove_migration_ptes(hpage, hpage); if (anon_vma) put_anon_vma(anon_vma); - if (!rc) + if (rc == MIGRATEPAGE_SUCCESS) hugetlb_cgroup_migrate(hpage, new_hpage); unlock_page(hpage); out: if (rc != -EAGAIN) putback_active_hugepage(hpage); - put_page(new_hpage); + + /* + * If migration was not successful and there's a freeing callback, use + * it. Otherwise, put_page() will drop the reference grabbed during + * isolation. + */ + if (rc != MIGRATEPAGE_SUCCESS && put_new_page) + put_new_page(new_hpage, private); + else + put_page(new_hpage); + if (result) { if (rc) *result = rc; @@ -1089,6 +1108,8 @@ out: * @from: The list of pages to be migrated. * @get_new_page: The function used to allocate free pages to be used * as the target of the page migration. + * @put_new_page: The function used to free target pages if migration + * fails, or NULL if no special handling is necessary. * @private: Private data to be passed on to get_new_page() * @mode: The migration mode that specifies the constraints for * page migration, if any. @@ -1102,7 +1123,8 @@ out: * Returns the number of pages that were not migrated, or an error code. */ int migrate_pages(struct list_head *from, new_page_t get_new_page, - unsigned long private, enum migrate_mode mode, int reason) + free_page_t put_new_page, unsigned long private, + enum migrate_mode mode, int reason) { int retry = 1; int nr_failed = 0; @@ -1124,10 +1146,11 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page, if (PageHuge(page)) rc = unmap_and_move_huge_page(get_new_page, - private, page, pass > 2, mode); + put_new_page, private, page, + pass > 2, mode); else - rc = unmap_and_move(get_new_page, private, - page, pass > 2, mode); + rc = unmap_and_move(get_new_page, put_new_page, + private, page, pass > 2, mode); switch(rc) { case -ENOMEM: @@ -1276,7 +1299,7 @@ set_status: err = 0; if (!list_empty(&pagelist)) { - err = migrate_pages(&pagelist, new_page_node, + err = migrate_pages(&pagelist, new_page_node, NULL, (unsigned long)pm, MIGRATE_SYNC, MR_SYSCALL); if (err) putback_movable_pages(&pagelist); @@ -1732,7 +1755,8 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, list_add(&page->lru, &migratepages); nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page, - node, MIGRATE_ASYNC, MR_NUMA_MISPLACED); + NULL, node, MIGRATE_ASYNC, + MR_NUMA_MISPLACED); if (nr_remaining) { if (!list_empty(&migratepages)) { list_del(&page->lru); diff --git a/mm/mincore.c b/mm/mincore.c index 101623378fbf..725c80961048 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -70,13 +70,21 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff) * any other file mapping (ie. marked !present and faulted in with * tmpfs's .fault). So swapped out tmpfs mappings are tested here. */ - page = find_get_page(mapping, pgoff); #ifdef CONFIG_SWAP - /* shmem/tmpfs may return swap: account for swapcache page too. */ - if (radix_tree_exceptional_entry(page)) { - swp_entry_t swap = radix_to_swp_entry(page); - page = find_get_page(swap_address_space(swap), swap.val); - } + if (shmem_mapping(mapping)) { + page = find_get_entry(mapping, pgoff); + /* + * shmem/tmpfs may return swap: account for swapcache + * page too. + */ + if (radix_tree_exceptional_entry(page)) { + swp_entry_t swp = radix_to_swp_entry(page); + page = find_get_page(swap_address_space(swp), swp.val); + } + } else + page = find_get_page(mapping, pgoff); +#else + page = find_get_page(mapping, pgoff); #endif if (page) { present = PageUptodate(page); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7b2611a055a7..4b258297cc7c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -943,6 +943,7 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, rmv_page_order(page); area->nr_free--; expand(zone, page, order, current_order, area, migratetype); + set_freepage_migratetype(page, migratetype); return page; } @@ -1069,7 +1070,9 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page, /* * When borrowing from MIGRATE_CMA, we need to release the excess - * buddy pages to CMA itself. + * buddy pages to CMA itself. We also ensure the freepage_migratetype + * is set to CMA so it is returned to the correct freelist in case + * the page ends up being not actually allocated from the pcp lists. */ if (is_migrate_cma(fallback_type)) return fallback_type; @@ -1137,6 +1140,12 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype) expand(zone, page, order, current_order, area, new_type); + /* The freepage_migratetype may differ from pageblock's + * migratetype depending on the decisions in + * try_to_steal_freepages. This is OK as long as it does + * not differ for MIGRATE_CMA type. + */ + set_freepage_migratetype(page, new_type); trace_mm_page_alloc_extfrag(page, order, current_order, start_migratetype, migratetype, new_type); @@ -1187,7 +1196,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, unsigned long count, struct list_head *list, int migratetype, int cold) { - int mt = migratetype, i; + int i; spin_lock(&zone->lock); for (i = 0; i < count; ++i) { @@ -1208,14 +1217,8 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, list_add(&page->lru, list); else list_add_tail(&page->lru, list); - if (IS_ENABLED(CONFIG_CMA)) { - mt = get_pageblock_migratetype(page); - if (!is_migrate_cma(mt) && !is_migrate_isolate(mt)) - mt = migratetype; - } - set_freepage_migratetype(page, mt); list = &page->lru; - if (is_migrate_cma(mt)) + if (is_migrate_cma(get_freepage_migratetype(page))) __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, -(1 << order)); } @@ -1584,7 +1587,7 @@ again: if (!page) goto failed; __mod_zone_freepage_state(zone, -(1 << order), - get_pageblock_migratetype(page)); + get_freepage_migratetype(page)); } __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order)); @@ -2246,7 +2249,7 @@ static struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, bool sync_migration, + int migratetype, enum migrate_mode mode, bool *contended_compaction, bool *deferred_compaction, unsigned long *did_some_progress) { @@ -2260,7 +2263,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, current->flags |= PF_MEMALLOC; *did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask, - nodemask, sync_migration, + nodemask, mode, contended_compaction); current->flags &= ~PF_MEMALLOC; @@ -2293,7 +2296,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, * As async compaction considers a subset of pageblocks, only * defer if the failure was a sync compaction failure. */ - if (sync_migration) + if (mode != MIGRATE_ASYNC) defer_compaction(preferred_zone, order); cond_resched(); @@ -2306,9 +2309,8 @@ static inline struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, bool sync_migration, - bool *contended_compaction, bool *deferred_compaction, - unsigned long *did_some_progress) + int migratetype, enum migrate_mode mode, bool *contended_compaction, + bool *deferred_compaction, unsigned long *did_some_progress) { return NULL; } @@ -2503,7 +2505,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, int alloc_flags; unsigned long pages_reclaimed = 0; unsigned long did_some_progress; - bool sync_migration = false; + enum migrate_mode migration_mode = MIGRATE_ASYNC; bool deferred_compaction = false; bool contended_compaction = false; @@ -2597,17 +2599,15 @@ rebalance: * Try direct compaction. The first pass is asynchronous. Subsequent * attempts after direct reclaim are synchronous */ - page = __alloc_pages_direct_compact(gfp_mask, order, - zonelist, high_zoneidx, - nodemask, - alloc_flags, preferred_zone, - migratetype, sync_migration, - &contended_compaction, + page = __alloc_pages_direct_compact(gfp_mask, order, zonelist, + high_zoneidx, nodemask, alloc_flags, + preferred_zone, migratetype, + migration_mode, &contended_compaction, &deferred_compaction, &did_some_progress); if (page) goto got_pg; - sync_migration = true; + migration_mode = MIGRATE_SYNC_LIGHT; /* * If compaction is deferred for high-order allocations, it is because @@ -2682,12 +2682,10 @@ rebalance: * direct reclaim and reclaim/compaction depends on compaction * being called after reclaim so call directly if necessary */ - page = __alloc_pages_direct_compact(gfp_mask, order, - zonelist, high_zoneidx, - nodemask, - alloc_flags, preferred_zone, - migratetype, sync_migration, - &contended_compaction, + page = __alloc_pages_direct_compact(gfp_mask, order, zonelist, + high_zoneidx, nodemask, alloc_flags, + preferred_zone, migratetype, + migration_mode, &contended_compaction, &deferred_compaction, &did_some_progress); if (page) @@ -6261,7 +6259,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, cc->nr_migratepages -= nr_reclaimed; ret = migrate_pages(&cc->migratepages, alloc_migrate_target, - 0, MIGRATE_SYNC, MR_CMA); + NULL, 0, cc->mode, MR_CMA); } if (ret < 0) { putback_movable_pages(&cc->migratepages); @@ -6300,7 +6298,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, .nr_migratepages = 0, .order = -1, .zone = page_zone(pfn_to_page(start)), - .sync = true, + .mode = MIGRATE_SYNC, .ignore_skip_hint = true, }; INIT_LIST_HEAD(&cc.migratepages); diff --git a/mm/readahead.c b/mm/readahead.c index 1fa0d6fca556..0ca36a7770b1 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -8,9 +8,7 @@ */ #include -#include #include -#include #include #include #include @@ -20,6 +18,8 @@ #include #include +#include "internal.h" + /* * Initialise a struct file's readahead state. Assumes that the caller has * memset *ra to zero. @@ -149,8 +149,7 @@ out: * * Returns the number of pages requested, or the maximum amount of I/O allowed. */ -static int -__do_page_cache_readahead(struct address_space *mapping, struct file *filp, +int __do_page_cache_readahead(struct address_space *mapping, struct file *filp, pgoff_t offset, unsigned long nr_to_read, unsigned long lookahead_size) { @@ -179,7 +178,7 @@ __do_page_cache_readahead(struct address_space *mapping, struct file *filp, rcu_read_lock(); page = radix_tree_lookup(&mapping->page_tree, page_offset); rcu_read_unlock(); - if (page) + if (page && !radix_tree_exceptional_entry(page)) continue; page = page_cache_alloc_readahead(mapping); @@ -244,20 +243,6 @@ unsigned long max_sane_readahead(unsigned long nr) } /* - * Submit IO for the read-ahead request in file_ra_state. - */ -unsigned long ra_submit(struct file_ra_state *ra, - struct address_space *mapping, struct file *filp) -{ - int actual; - - actual = __do_page_cache_readahead(mapping, filp, - ra->start, ra->size, ra->async_size); - - return actual; -} - -/* * Set the initial window size, round to next power of 2 and square * for small size, x 4 for medium, and x 2 for large * for 128k (32 page) max ra @@ -347,7 +332,7 @@ static pgoff_t count_history_pages(struct address_space *mapping, pgoff_t head; rcu_read_lock(); - head = radix_tree_prev_hole(&mapping->page_tree, offset - 1, max); + head = page_cache_prev_hole(mapping, offset - 1, max); rcu_read_unlock(); return offset - 1 - head; @@ -427,7 +412,7 @@ ondemand_readahead(struct address_space *mapping, pgoff_t start; rcu_read_lock(); - start = radix_tree_next_hole(&mapping->page_tree, offset+1,max); + start = page_cache_next_hole(mapping, offset + 1, max); rcu_read_unlock(); if (!start || start - offset > max) diff --git a/mm/shmem.c b/mm/shmem.c index f0d698ba7d0f..0f1447563f17 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -243,19 +243,17 @@ static int shmem_radix_tree_replace(struct address_space *mapping, pgoff_t index, void *expected, void *replacement) { void **pslot; - void *item = NULL; + void *item; VM_BUG_ON(!expected); + VM_BUG_ON(!replacement); pslot = radix_tree_lookup_slot(&mapping->page_tree, index); - if (pslot) - item = radix_tree_deref_slot_protected(pslot, - &mapping->tree_lock); + if (!pslot) + return -ENOENT; + item = radix_tree_deref_slot_protected(pslot, &mapping->tree_lock); if (item != expected) return -ENOENT; - if (replacement) - radix_tree_replace_slot(pslot, replacement); - else - radix_tree_delete(&mapping->page_tree, index); + radix_tree_replace_slot(pslot, replacement); return 0; } @@ -332,84 +330,20 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap) } /* - * Like find_get_pages, but collecting swap entries as well as pages. - */ -static unsigned shmem_find_get_pages_and_swap(struct address_space *mapping, - pgoff_t start, unsigned int nr_pages, - struct page **pages, pgoff_t *indices) -{ - void **slot; - unsigned int ret = 0; - struct radix_tree_iter iter; - - if (!nr_pages) - return 0; - - rcu_read_lock(); -restart: - radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { - struct page *page; -repeat: - page = radix_tree_deref_slot(slot); - if (unlikely(!page)) - continue; - if (radix_tree_exception(page)) { - if (radix_tree_deref_retry(page)) - goto restart; - /* - * Otherwise, we must be storing a swap entry - * here as an exceptional entry: so return it - * without attempting to raise page count. - */ - goto export; - } - if (!page_cache_get_speculative(page)) - goto repeat; - - /* Has the page moved? */ - if (unlikely(page != *slot)) { - page_cache_release(page); - goto repeat; - } -export: - indices[ret] = iter.index; - pages[ret] = page; - if (++ret == nr_pages) - break; - } - rcu_read_unlock(); - return ret; -} - -/* * Remove swap entry from radix tree, free the swap and its page cache. */ static int shmem_free_swap(struct address_space *mapping, pgoff_t index, void *radswap) { - int error; + void *old; spin_lock_irq(&mapping->tree_lock); - error = shmem_radix_tree_replace(mapping, index, radswap, NULL); + old = radix_tree_delete_item(&mapping->page_tree, index, radswap); spin_unlock_irq(&mapping->tree_lock); - if (!error) - free_swap_and_cache(radix_to_swp_entry(radswap)); - return error; -} - -/* - * Pagevec may contain swap entries, so shuffle up pages before releasing. - */ -static void shmem_deswap_pagevec(struct pagevec *pvec) -{ - int i, j; - - for (i = 0, j = 0; i < pagevec_count(pvec); i++) { - struct page *page = pvec->pages[i]; - if (!radix_tree_exceptional_entry(page)) - pvec->pages[j++] = page; - } - pvec->nr = j; + if (old != radswap) + return -ENOENT; + free_swap_and_cache(radix_to_swp_entry(radswap)); + return 0; } /* @@ -430,12 +364,12 @@ void shmem_unlock_mapping(struct address_space *mapping) * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it * has finished, if it hits a row of PAGEVEC_SIZE swap entries. */ - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, - PAGEVEC_SIZE, pvec.pages, indices); + pvec.nr = find_get_entries(mapping, index, + PAGEVEC_SIZE, pvec.pages, indices); if (!pvec.nr) break; index = indices[pvec.nr - 1] + 1; - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); check_move_unevictable_pages(pvec.pages, pvec.nr); pagevec_release(&pvec); cond_resched(); @@ -467,9 +401,9 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, pagevec_init(&pvec, 0); index = start; while (index < end) { - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE), - pvec.pages, indices); + pvec.nr = find_get_entries(mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + pvec.pages, indices); if (!pvec.nr) break; mem_cgroup_uncharge_start(); @@ -498,7 +432,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, } unlock_page(page); } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); @@ -536,9 +470,10 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, index = start; while (index < end) { cond_resched(); - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, + + pvec.nr = find_get_entries(mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE), - pvec.pages, indices); + pvec.pages, indices); if (!pvec.nr) { /* If all gone or hole-punch or unfalloc, we're done */ if (index == start || end != -1) @@ -581,7 +516,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, } unlock_page(page); } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); index++; @@ -1088,7 +1023,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, return -EFBIG; repeat: swap.val = 0; - page = find_lock_page(mapping, index); + page = find_lock_entry(mapping, index); if (radix_tree_exceptional_entry(page)) { swap = radix_to_swp_entry(page); page = NULL; @@ -1483,6 +1418,11 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode return inode; } +bool shmem_mapping(struct address_space *mapping) +{ + return mapping->backing_dev_info == &shmem_backing_dev_info; +} + #ifdef CONFIG_TMPFS static const struct inode_operations shmem_symlink_inode_operations; static const struct inode_operations shmem_short_symlink_operations; @@ -1795,7 +1735,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping, pagevec_init(&pvec, 0); pvec.nr = 1; /* start small: we may be there already */ while (!done) { - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, + pvec.nr = find_get_entries(mapping, index, pvec.nr, pvec.pages, indices); if (!pvec.nr) { if (whence == SEEK_DATA) @@ -1822,7 +1762,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping, break; } } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); pvec.nr = PAGEVEC_SIZE; cond_resched(); diff --git a/mm/swap.c b/mm/swap.c index 0092097b3f4c..c8048d71c642 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -948,6 +948,57 @@ void __pagevec_lru_add(struct pagevec *pvec) EXPORT_SYMBOL(__pagevec_lru_add); /** + * pagevec_lookup_entries - gang pagecache lookup + * @pvec: Where the resulting entries are placed + * @mapping: The address_space to search + * @start: The starting entry index + * @nr_entries: The maximum number of entries + * @indices: The cache indices corresponding to the entries in @pvec + * + * pagevec_lookup_entries() will search for and return a group of up + * to @nr_entries pages and shadow entries in the mapping. All + * entries are placed in @pvec. pagevec_lookup_entries() takes a + * reference against actual pages in @pvec. + * + * The search returns a group of mapping-contiguous entries with + * ascending indexes. There may be holes in the indices due to + * not-present entries. + * + * pagevec_lookup_entries() returns the number of entries which were + * found. + */ +unsigned pagevec_lookup_entries(struct pagevec *pvec, + struct address_space *mapping, + pgoff_t start, unsigned nr_pages, + pgoff_t *indices) +{ + pvec->nr = find_get_entries(mapping, start, nr_pages, + pvec->pages, indices); + return pagevec_count(pvec); +} + +/** + * pagevec_remove_exceptionals - pagevec exceptionals pruning + * @pvec: The pagevec to prune + * + * pagevec_lookup_entries() fills both pages and exceptional radix + * tree entries into the pagevec. This function prunes all + * exceptionals from @pvec without leaving holes, so that it can be + * passed on to page-only pagevec operations. + */ +void pagevec_remove_exceptionals(struct pagevec *pvec) +{ + int i, j; + + for (i = 0, j = 0; i < pagevec_count(pvec); i++) { + struct page *page = pvec->pages[i]; + if (!radix_tree_exceptional_entry(page)) + pvec->pages[j++] = page; + } + pvec->nr = j; +} + +/** * pagevec_lookup - gang pagecache lookup * @pvec: Where the resulting pages are placed * @mapping: The address_space to search diff --git a/mm/truncate.c b/mm/truncate.c index ac18edc30649..827ad8d2b5cd 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -23,6 +23,22 @@ #include #include "internal.h" +static void clear_exceptional_entry(struct address_space *mapping, + pgoff_t index, void *entry) +{ + /* Handled by shmem itself */ + if (shmem_mapping(mapping)) + return; + + spin_lock_irq(&mapping->tree_lock); + /* + * Regular page slots are stabilized by the page lock even + * without the tree itself locked. These unlocked entries + * need verification under the tree lock. + */ + radix_tree_delete_item(&mapping->page_tree, index, entry); + spin_unlock_irq(&mapping->tree_lock); +} /** * do_invalidatepage - invalidate part or all of a page @@ -209,6 +225,7 @@ void truncate_inode_pages_range(struct address_space *mapping, unsigned int partial_start; /* inclusive */ unsigned int partial_end; /* exclusive */ struct pagevec pvec; + pgoff_t indices[PAGEVEC_SIZE]; pgoff_t index; int i; @@ -239,17 +256,23 @@ void truncate_inode_pages_range(struct address_space *mapping, pagevec_init(&pvec, 0); index = start; - while (index < end && pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE))) { + while (index < end && pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + indices)) { mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; + index = indices[i]; if (index >= end) break; + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } + if (!trylock_page(page)) continue; WARN_ON(page->index != index); @@ -260,6 +283,7 @@ void truncate_inode_pages_range(struct address_space *mapping, truncate_inode_page(mapping, page); unlock_page(page); } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); @@ -308,14 +332,16 @@ void truncate_inode_pages_range(struct address_space *mapping, index = start; for ( ; ; ) { cond_resched(); - if (!pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE))) { + if (!pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + indices)) { if (index == start) break; index = start; continue; } - if (index == start && pvec.pages[0]->index >= end) { + if (index == start && indices[0] >= end) { + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); break; } @@ -324,16 +350,22 @@ void truncate_inode_pages_range(struct address_space *mapping, struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; + index = indices[i]; if (index >= end) break; + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } + lock_page(page); WARN_ON(page->index != index); wait_on_page_writeback(page); truncate_inode_page(mapping, page); unlock_page(page); } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); index++; @@ -376,6 +408,7 @@ EXPORT_SYMBOL(truncate_inode_pages); unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end) { + pgoff_t indices[PAGEVEC_SIZE]; struct pagevec pvec; pgoff_t index = start; unsigned long ret; @@ -391,17 +424,23 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, */ pagevec_init(&pvec, 0); - while (index <= end && pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { + while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, + indices)) { mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; + index = indices[i]; if (index > end) break; + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } + if (!trylock_page(page)) continue; WARN_ON(page->index != index); @@ -415,6 +454,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, deactivate_page(page); count += ret; } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); @@ -482,6 +522,7 @@ static int do_launder_page(struct address_space *mapping, struct page *page) int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end) { + pgoff_t indices[PAGEVEC_SIZE]; struct pagevec pvec; pgoff_t index; int i; @@ -492,17 +533,23 @@ int invalidate_inode_pages2_range(struct address_space *mapping, cleancache_invalidate_inode(mapping); pagevec_init(&pvec, 0); index = start; - while (index <= end && pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { + while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, + indices)) { mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; + index = indices[i]; if (index > end) break; + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } + lock_page(page); WARN_ON(page->index != index); if (page->mapping != mapping) { @@ -540,6 +587,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, ret = ret2; unlock_page(page); } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); diff --git a/mm/vmscan.c b/mm/vmscan.c index 0c0b36e5b4f8..deb139e6b8ed 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2018,13 +2018,27 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) unsigned long nr_reclaimed = 0; unsigned long nr_to_reclaim = sc->nr_to_reclaim; struct blk_plug plug; - bool scan_adjusted = false; + bool scan_adjusted; get_scan_count(lruvec, sc, nr); /* Record the original scan target for proportional adjustments later */ memcpy(targets, nr, sizeof(nr)); + /* + * Global reclaiming within direct reclaim at DEF_PRIORITY is a normal + * event that can occur when there is little memory pressure e.g. + * multiple streaming readers/writers. Hence, we do not abort scanning + * when the requested number of pages are reclaimed when scanning at + * DEF_PRIORITY on the assumption that the fact we are direct + * reclaiming implies that kswapd is not keeping up and it is best to + * do a batch of work at once. For memcg reclaim one check is made to + * abort proportional reclaim if either the file or anon lru has already + * dropped to zero at the first pass. + */ + scan_adjusted = (global_reclaim(sc) && !current_is_kswapd() && + sc->priority == DEF_PRIORITY); + blk_start_plug(&plug); while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || nr[LRU_INACTIVE_FILE]) { @@ -2045,17 +2059,8 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) continue; /* - * For global direct reclaim, reclaim only the number of pages - * requested. Less care is taken to scan proportionally as it - * is more important to minimise direct reclaim stall latency - * than it is to properly age the LRU lists. - */ - if (global_reclaim(sc) && !current_is_kswapd()) - break; - - /* * For kswapd and memcg, reclaim at least the number of pages - * requested. Ensure that the anon and file LRUs shrink + * requested. Ensure that the anon and file LRUs are scanned * proportionally what was requested by get_scan_count(). We * stop reclaiming one LRU and reduce the amount scanning * proportional to the original scan target. @@ -2063,6 +2068,15 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE]; nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON]; + /* + * It's just vindictive to attack the larger once the smaller + * has gone to zero. And given the way we stop scanning the + * smaller below, this makes sure that we only make one nudge + * towards proportionality once we've got nr_to_reclaim. + */ + if (!nr_file || !nr_anon) + break; + if (nr_file > nr_anon) { unsigned long scan_target = targets[LRU_INACTIVE_ANON] + targets[LRU_ACTIVE_ANON] + 1; diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c index 6e7a236525b6..06f19b9e159a 100644 --- a/net/ceph/crypto.c +++ b/net/ceph/crypto.c @@ -89,11 +89,82 @@ static struct crypto_blkcipher *ceph_crypto_alloc_cipher(void) static const u8 *aes_iv = (u8 *)CEPH_AES_IV; +/* + * Should be used for buffers allocated with ceph_kvmalloc(). + * Currently these are encrypt out-buffer (ceph_buffer) and decrypt + * in-buffer (msg front). + * + * Dispose of @sgt with teardown_sgtable(). + * + * @prealloc_sg is to avoid memory allocation inside sg_alloc_table() + * in cases where a single sg is sufficient. No attempt to reduce the + * number of sgs by squeezing physically contiguous pages together is + * made though, for simplicity. + */ +static int setup_sgtable(struct sg_table *sgt, struct scatterlist *prealloc_sg, + const void *buf, unsigned int buf_len) +{ + struct scatterlist *sg; + const bool is_vmalloc = is_vmalloc_addr(buf); + unsigned int off = offset_in_page(buf); + unsigned int chunk_cnt = 1; + unsigned int chunk_len = PAGE_ALIGN(off + buf_len); + int i; + int ret; + + if (buf_len == 0) { + memset(sgt, 0, sizeof(*sgt)); + return -EINVAL; + } + + if (is_vmalloc) { + chunk_cnt = chunk_len >> PAGE_SHIFT; + chunk_len = PAGE_SIZE; + } + + if (chunk_cnt > 1) { + ret = sg_alloc_table(sgt, chunk_cnt, GFP_NOFS); + if (ret) + return ret; + } else { + WARN_ON(chunk_cnt != 1); + sg_init_table(prealloc_sg, 1); + sgt->sgl = prealloc_sg; + sgt->nents = sgt->orig_nents = 1; + } + + for_each_sg(sgt->sgl, sg, sgt->orig_nents, i) { + struct page *page; + unsigned int len = min(chunk_len - off, buf_len); + + if (is_vmalloc) + page = vmalloc_to_page(buf); + else + page = virt_to_page(buf); + + sg_set_page(sg, page, len, off); + + off = 0; + buf += len; + buf_len -= len; + } + WARN_ON(buf_len != 0); + + return 0; +} + +static void teardown_sgtable(struct sg_table *sgt) +{ + if (sgt->orig_nents > 1) + sg_free_table(sgt); +} + static int ceph_aes_encrypt(const void *key, int key_len, void *dst, size_t *dst_len, const void *src, size_t src_len) { - struct scatterlist sg_in[2], sg_out[1]; + struct scatterlist sg_in[2], prealloc_sg; + struct sg_table sg_out; struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 }; int ret; @@ -109,16 +180,18 @@ static int ceph_aes_encrypt(const void *key, int key_len, *dst_len = src_len + zero_padding; - crypto_blkcipher_setkey((void *)tfm, key, key_len); sg_init_table(sg_in, 2); sg_set_buf(&sg_in[0], src, src_len); sg_set_buf(&sg_in[1], pad, zero_padding); - sg_init_table(sg_out, 1); - sg_set_buf(sg_out, dst, *dst_len); + ret = setup_sgtable(&sg_out, &prealloc_sg, dst, *dst_len); + if (ret) + goto out_tfm; + + crypto_blkcipher_setkey((void *)tfm, key, key_len); iv = crypto_blkcipher_crt(tfm)->iv; ivsize = crypto_blkcipher_ivsize(tfm); - memcpy(iv, aes_iv, ivsize); + /* print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1, key, key_len, 1); @@ -127,16 +200,22 @@ static int ceph_aes_encrypt(const void *key, int key_len, print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1, pad, zero_padding, 1); */ - ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in, + ret = crypto_blkcipher_encrypt(&desc, sg_out.sgl, sg_in, src_len + zero_padding); - crypto_free_blkcipher(tfm); - if (ret < 0) + if (ret < 0) { pr_err("ceph_aes_crypt failed %d\n", ret); + goto out_sg; + } /* print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1, dst, *dst_len, 1); */ - return 0; + +out_sg: + teardown_sgtable(&sg_out); +out_tfm: + crypto_free_blkcipher(tfm); + return ret; } static int ceph_aes_encrypt2(const void *key, int key_len, void *dst, @@ -144,7 +223,8 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst, const void *src1, size_t src1_len, const void *src2, size_t src2_len) { - struct scatterlist sg_in[3], sg_out[1]; + struct scatterlist sg_in[3], prealloc_sg; + struct sg_table sg_out; struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 }; int ret; @@ -160,17 +240,19 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst, *dst_len = src1_len + src2_len + zero_padding; - crypto_blkcipher_setkey((void *)tfm, key, key_len); sg_init_table(sg_in, 3); sg_set_buf(&sg_in[0], src1, src1_len); sg_set_buf(&sg_in[1], src2, src2_len); sg_set_buf(&sg_in[2], pad, zero_padding); - sg_init_table(sg_out, 1); - sg_set_buf(sg_out, dst, *dst_len); + ret = setup_sgtable(&sg_out, &prealloc_sg, dst, *dst_len); + if (ret) + goto out_tfm; + + crypto_blkcipher_setkey((void *)tfm, key, key_len); iv = crypto_blkcipher_crt(tfm)->iv; ivsize = crypto_blkcipher_ivsize(tfm); - memcpy(iv, aes_iv, ivsize); + /* print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1, key, key_len, 1); @@ -181,23 +263,30 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst, print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1, pad, zero_padding, 1); */ - ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in, + ret = crypto_blkcipher_encrypt(&desc, sg_out.sgl, sg_in, src1_len + src2_len + zero_padding); - crypto_free_blkcipher(tfm); - if (ret < 0) + if (ret < 0) { pr_err("ceph_aes_crypt2 failed %d\n", ret); + goto out_sg; + } /* print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1, dst, *dst_len, 1); */ - return 0; + +out_sg: + teardown_sgtable(&sg_out); +out_tfm: + crypto_free_blkcipher(tfm); + return ret; } static int ceph_aes_decrypt(const void *key, int key_len, void *dst, size_t *dst_len, const void *src, size_t src_len) { - struct scatterlist sg_in[1], sg_out[2]; + struct sg_table sg_in; + struct scatterlist sg_out[2], prealloc_sg; struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); struct blkcipher_desc desc = { .tfm = tfm }; char pad[16]; @@ -209,16 +298,16 @@ static int ceph_aes_decrypt(const void *key, int key_len, if (IS_ERR(tfm)) return PTR_ERR(tfm); - crypto_blkcipher_setkey((void *)tfm, key, key_len); - sg_init_table(sg_in, 1); sg_init_table(sg_out, 2); - sg_set_buf(sg_in, src, src_len); sg_set_buf(&sg_out[0], dst, *dst_len); sg_set_buf(&sg_out[1], pad, sizeof(pad)); + ret = setup_sgtable(&sg_in, &prealloc_sg, src, src_len); + if (ret) + goto out_tfm; + crypto_blkcipher_setkey((void *)tfm, key, key_len); iv = crypto_blkcipher_crt(tfm)->iv; ivsize = crypto_blkcipher_ivsize(tfm); - memcpy(iv, aes_iv, ivsize); /* @@ -227,12 +316,10 @@ static int ceph_aes_decrypt(const void *key, int key_len, print_hex_dump(KERN_ERR, "dec in: ", DUMP_PREFIX_NONE, 16, 1, src, src_len, 1); */ - - ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len); - crypto_free_blkcipher(tfm); + ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in.sgl, src_len); if (ret < 0) { pr_err("ceph_aes_decrypt failed %d\n", ret); - return ret; + goto out_sg; } if (src_len <= *dst_len) @@ -250,7 +337,12 @@ static int ceph_aes_decrypt(const void *key, int key_len, print_hex_dump(KERN_ERR, "dec out: ", DUMP_PREFIX_NONE, 16, 1, dst, *dst_len, 1); */ - return 0; + +out_sg: + teardown_sgtable(&sg_in); +out_tfm: + crypto_free_blkcipher(tfm); + return ret; } static int ceph_aes_decrypt2(const void *key, int key_len, @@ -258,7 +350,8 @@ static int ceph_aes_decrypt2(const void *key, int key_len, void *dst2, size_t *dst2_len, const void *src, size_t src_len) { - struct scatterlist sg_in[1], sg_out[3]; + struct sg_table sg_in; + struct scatterlist sg_out[3], prealloc_sg; struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); struct blkcipher_desc desc = { .tfm = tfm }; char pad[16]; @@ -270,17 +363,17 @@ static int ceph_aes_decrypt2(const void *key, int key_len, if (IS_ERR(tfm)) return PTR_ERR(tfm); - sg_init_table(sg_in, 1); - sg_set_buf(sg_in, src, src_len); sg_init_table(sg_out, 3); sg_set_buf(&sg_out[0], dst1, *dst1_len); sg_set_buf(&sg_out[1], dst2, *dst2_len); sg_set_buf(&sg_out[2], pad, sizeof(pad)); + ret = setup_sgtable(&sg_in, &prealloc_sg, src, src_len); + if (ret) + goto out_tfm; crypto_blkcipher_setkey((void *)tfm, key, key_len); iv = crypto_blkcipher_crt(tfm)->iv; ivsize = crypto_blkcipher_ivsize(tfm); - memcpy(iv, aes_iv, ivsize); /* @@ -289,12 +382,10 @@ static int ceph_aes_decrypt2(const void *key, int key_len, print_hex_dump(KERN_ERR, "dec in: ", DUMP_PREFIX_NONE, 16, 1, src, src_len, 1); */ - - ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len); - crypto_free_blkcipher(tfm); + ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in.sgl, src_len); if (ret < 0) { pr_err("ceph_aes_decrypt failed %d\n", ret); - return ret; + goto out_sg; } if (src_len <= *dst1_len) @@ -324,7 +415,11 @@ static int ceph_aes_decrypt2(const void *key, int key_len, dst2, *dst2_len, 1); */ - return 0; +out_sg: + teardown_sgtable(&sg_in); +out_tfm: + crypto_free_blkcipher(tfm); + return ret; } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index cb57aa862177..b27f6d34762b 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -962,8 +962,6 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) else dev->flags &= ~IFF_POINTOPOINT; - dev->iflink = p->link; - /* Precalculate GRE options length */ if (t->parms.o_flags&(GRE_CSUM|GRE_KEY|GRE_SEQ)) { if (t->parms.o_flags&GRE_CSUM) @@ -1273,6 +1271,7 @@ static int ip6gre_tunnel_init(struct net_device *dev) u64_stats_init(&ip6gre_tunnel_stats->syncp); } + dev->iflink = tunnel->parms.link; return 0; } @@ -1474,6 +1473,8 @@ static int ip6gre_tap_init(struct net_device *dev) u64_stats_init(&ip6gre_tap_stats->syncp); } + dev->iflink = tunnel->parms.link; + return 0; } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 912033957ad3..657639d39f70 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -272,9 +272,6 @@ static int ip6_tnl_create2(struct net_device *dev) int err; t = netdev_priv(dev); - err = ip6_tnl_dev_init(dev); - if (err < 0) - goto out; err = register_netdevice(dev); if (err < 0) @@ -1456,6 +1453,7 @@ ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) static const struct net_device_ops ip6_tnl_netdev_ops = { + .ndo_init = ip6_tnl_dev_init, .ndo_uninit = ip6_tnl_dev_uninit, .ndo_start_xmit = ip6_tnl_xmit, .ndo_do_ioctl = ip6_tnl_ioctl, @@ -1547,16 +1545,10 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - int err = ip6_tnl_dev_init_gen(dev); - - if (err) - return err; t->parms.proto = IPPROTO_IPV6; dev_hold(dev); - ip6_tnl_link_config(t); - rcu_assign_pointer(ip6n->tnls_wc[0], t); return 0; } diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 2d19272b8cee..9a5339fcb450 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -172,10 +172,6 @@ static int vti6_tnl_create2(struct net_device *dev) struct vti6_net *ip6n = net_generic(net, vti6_net_id); int err; - err = vti6_dev_init(dev); - if (err < 0) - goto out; - err = register_netdevice(dev); if (err < 0) goto out; @@ -693,6 +689,7 @@ static int vti6_change_mtu(struct net_device *dev, int new_mtu) } static const struct net_device_ops vti6_netdev_ops = { + .ndo_init = vti6_dev_init, .ndo_uninit = vti6_dev_uninit, .ndo_start_xmit = vti6_tnl_xmit, .ndo_do_ioctl = vti6_ioctl, @@ -772,16 +769,10 @@ static int __net_init vti6_fb_tnl_dev_init(struct net_device *dev) struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); - int err = vti6_dev_init_gen(dev); - - if (err) - return err; t->parms.proto = IPPROTO_IPV6; dev_hold(dev); - vti6_link_config(t); - rcu_assign_pointer(ip6n->tnls_wc[0], t); return 0; } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index b12b11b123ff..317b6dbf3190 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -195,10 +195,8 @@ static int ipip6_tunnel_create(struct net_device *dev) struct sit_net *sitn = net_generic(net, sit_net_id); int err; - err = ipip6_tunnel_init(dev); - if (err < 0) - goto out; - ipip6_tunnel_clone_6rd(dev, sitn); + memcpy(dev->dev_addr, &t->parms.iph.saddr, 4); + memcpy(dev->broadcast, &t->parms.iph.daddr, 4); if ((__force u16)t->parms.i_flags & SIT_ISATAP) dev->priv_flags |= IFF_ISATAP; @@ -207,7 +205,8 @@ static int ipip6_tunnel_create(struct net_device *dev) if (err < 0) goto out; - strcpy(t->parms.name, dev->name); + ipip6_tunnel_clone_6rd(dev, sitn); + dev->rtnl_link_ops = &sit_link_ops; dev_hold(dev); @@ -1321,6 +1320,7 @@ static int ipip6_tunnel_change_mtu(struct net_device *dev, int new_mtu) } static const struct net_device_ops ipip6_netdev_ops = { + .ndo_init = ipip6_tunnel_init, .ndo_uninit = ipip6_tunnel_uninit, .ndo_start_xmit = sit_tunnel_xmit, .ndo_do_ioctl = ipip6_tunnel_ioctl, @@ -1367,9 +1367,7 @@ static int ipip6_tunnel_init(struct net_device *dev) tunnel->dev = dev; tunnel->net = dev_net(dev); - - memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4); - memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); + strcpy(tunnel->parms.name, dev->name); ipip6_tunnel_bind_dev(dev); dev->tstats = alloc_percpu(struct pcpu_sw_netstats); @@ -1401,7 +1399,6 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) tunnel->dev = dev; tunnel->net = dev_net(dev); - strcpy(tunnel->parms.name, dev->name); iph->version = 4; iph->protocol = IPPROTO_IPV6; diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index ea7013cb7e52..3f076b9c9308 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -815,7 +815,7 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata, memset(¶ms, 0, sizeof(params)); memset(&csa_ie, 0, sizeof(csa_ie)); - err = ieee80211_parse_ch_switch_ie(sdata, elems, beacon, + err = ieee80211_parse_ch_switch_ie(sdata, elems, ifibss->chandef.chan->band, sta_flags, ifibss->bssid, &csa_ie); /* can't switch to destination channel, fail */ diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index b127902361f4..bf7a1bbb975f 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1569,7 +1569,6 @@ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, * ieee80211_parse_ch_switch_ie - parses channel switch IEs * @sdata: the sdata of the interface which has received the frame * @elems: parsed 802.11 elements received with the frame - * @beacon: indicates if the frame was a beacon or probe response * @current_band: indicates the current band * @sta_flags: contains information about own capabilities and restrictions * to decide which channel switch announcements can be accepted. Only the @@ -1583,7 +1582,7 @@ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, * Return: 0 on success, <0 on error and >0 if there is nothing to parse. */ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, - struct ieee802_11_elems *elems, bool beacon, + struct ieee802_11_elems *elems, enum ieee80211_band current_band, u32 sta_flags, u8 *bssid, struct ieee80211_csa_ie *csa_ie); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 8f7fabc46c97..06f5de4e4fbb 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -760,10 +760,12 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, int i, flushed; struct ps_data *ps; struct cfg80211_chan_def chandef; + bool cancel_scan; clear_bit(SDATA_STATE_RUNNING, &sdata->state); - if (rcu_access_pointer(local->scan_sdata) == sdata) + cancel_scan = rcu_access_pointer(local->scan_sdata) == sdata; + if (cancel_scan) ieee80211_scan_cancel(local); /* @@ -973,6 +975,9 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, ieee80211_recalc_ps(local, -1); + if (cancel_scan) + flush_delayed_work(&local->scan_work); + if (local->open_count == 0) { ieee80211_stop_device(local); diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 5b919cab1de0..3d52d1d68431 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -885,7 +885,7 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata, memset(¶ms, 0, sizeof(params)); memset(&csa_ie, 0, sizeof(csa_ie)); - err = ieee80211_parse_ch_switch_ie(sdata, elems, beacon, band, + err = ieee80211_parse_ch_switch_ie(sdata, elems, band, sta_flags, sdata->vif.addr, &csa_ie); if (err < 0) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 189eef014c4f..c9535a976b56 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1001,7 +1001,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, current_band = cbss->channel->band; memset(&csa_ie, 0, sizeof(csa_ie)); - res = ieee80211_parse_ch_switch_ie(sdata, elems, beacon, current_band, + res = ieee80211_parse_ch_switch_ie(sdata, elems, current_band, ifmgd->flags, ifmgd->associated->bssid, &csa_ie); if (res < 0) @@ -1086,7 +1086,8 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, ieee80211_queue_work(&local->hw, &ifmgd->chswitch_work); else mod_timer(&ifmgd->chswitch_timer, - TU_TO_EXP_TIME(csa_ie.count * cbss->beacon_interval)); + TU_TO_EXP_TIME((csa_ie.count - 1) * + cbss->beacon_interval)); } static u32 ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 3e57f96c9666..095c16037bc5 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1679,11 +1679,14 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) sc = le16_to_cpu(hdr->seq_ctrl); frag = sc & IEEE80211_SCTL_FRAG; - if (likely((!ieee80211_has_morefrags(fc) && frag == 0) || - is_multicast_ether_addr(hdr->addr1))) { - /* not fragmented */ + if (likely(!ieee80211_has_morefrags(fc) && frag == 0)) + goto out; + + if (is_multicast_ether_addr(hdr->addr1)) { + rx->local->dot11MulticastReceivedFrameCount++; goto out; } + I802_DEBUG_INC(rx->local->rx_handlers_fragments); if (skb_linearize(rx->skb)) @@ -1776,10 +1779,7 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) out: if (rx->sta) rx->sta->rx_packets++; - if (is_multicast_ether_addr(hdr->addr1)) - rx->local->dot11MulticastReceivedFrameCount++; - else - ieee80211_led_rx(rx->local); + ieee80211_led_rx(rx->local); return RX_CONTINUE; } diff --git a/net/mac80211/spectmgmt.c b/net/mac80211/spectmgmt.c index 6ab009070084..efeba56c913b 100644 --- a/net/mac80211/spectmgmt.c +++ b/net/mac80211/spectmgmt.c @@ -22,7 +22,7 @@ #include "wme.h" int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, - struct ieee802_11_elems *elems, bool beacon, + struct ieee802_11_elems *elems, enum ieee80211_band current_band, u32 sta_flags, u8 *bssid, struct ieee80211_csa_ie *csa_ie) @@ -91,19 +91,13 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, return -EINVAL; } - if (!beacon && sec_chan_offs) { + if (sec_chan_offs) { secondary_channel_offset = sec_chan_offs->sec_chan_offs; - } else if (beacon && ht_oper) { - secondary_channel_offset = - ht_oper->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET; } else if (!(sta_flags & IEEE80211_STA_DISABLE_HT)) { - /* If it's not a beacon, HT is enabled and the IE not present, - * it's 20 MHz, 802.11-2012 8.5.2.6: - * This element [the Secondary Channel Offset Element] is - * present when switching to a 40 MHz channel. It may be - * present when switching to a 20 MHz channel (in which - * case the secondary channel offset is set to SCN). - */ + /* If the secondary channel offset IE is not present, + * we can't know what's the post-CSA offset, so the + * best we can do is use 20MHz. + */ secondary_channel_offset = IEEE80211_HT_PARAM_CHA_SEC_NONE; } diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index de770ec39e51..cf9937743abb 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -636,7 +636,7 @@ ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index) struct ip_set *set; struct ip_set_net *inst = ip_set_pernet(net); - if (index > inst->ip_set_max) + if (index >= inst->ip_set_max) return IPSET_INVALID_ID; nfnl_lock(NFNL_SUBSYS_IPSET); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index a155d19a225e..6ff12a191400 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -45,7 +45,8 @@ #define NFULNL_NLBUFSIZ_DEFAULT NLMSG_GOODSIZE #define NFULNL_TIMEOUT_DEFAULT 100 /* every second */ #define NFULNL_QTHRESH_DEFAULT 100 /* 100 packets */ -#define NFULNL_COPY_RANGE_MAX 0xFFFF /* max packet size is limited by 16-bit struct nfattr nfa_len field */ +/* max packet size is limited by 16-bit struct nfattr nfa_len field */ +#define NFULNL_COPY_RANGE_MAX (0xFFFF - NLA_HDRLEN) #define PRINTR(x, args...) do { if (net_ratelimit()) \ printk(x, ## args); } while (0); @@ -255,6 +256,8 @@ nfulnl_set_mode(struct nfulnl_instance *inst, u_int8_t mode, case NFULNL_COPY_PACKET: inst->copy_mode = mode; + if (range == 0) + range = NFULNL_COPY_RANGE_MAX; inst->copy_range = min_t(unsigned int, range, NFULNL_COPY_RANGE_MAX); break; @@ -346,26 +349,25 @@ nfulnl_alloc_skb(struct net *net, u32 peer_portid, unsigned int inst_size, return skb; } -static int +static void __nfulnl_send(struct nfulnl_instance *inst) { - int status = -1; - if (inst->qlen > 1) { struct nlmsghdr *nlh = nlmsg_put(inst->skb, 0, 0, NLMSG_DONE, sizeof(struct nfgenmsg), 0); - if (!nlh) + if (WARN_ONCE(!nlh, "bad nlskb size: %u, tailroom %d\n", + inst->skb->len, skb_tailroom(inst->skb))) { + kfree_skb(inst->skb); goto out; + } } - status = nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid, - MSG_DONTWAIT); - + nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid, + MSG_DONTWAIT); +out: inst->qlen = 0; inst->skb = NULL; -out: - return status; } static void @@ -652,7 +654,8 @@ nfulnl_log_packet(struct net *net, + nla_total_size(sizeof(u_int32_t)) /* gid */ + nla_total_size(plen) /* prefix */ + nla_total_size(sizeof(struct nfulnl_msg_packet_hw)) - + nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp)); + + nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp)) + + nla_total_size(sizeof(struct nfgenmsg)); /* NLMSG_DONE */ if (in && skb_mac_header_was_set(skb)) { size += nla_total_size(skb->dev->hard_header_len) @@ -681,8 +684,7 @@ nfulnl_log_packet(struct net *net, break; case NFULNL_COPY_PACKET: - if (inst->copy_range == 0 - || inst->copy_range > skb->len) + if (inst->copy_range > skb->len) data_len = skb->len; else data_len = inst->copy_range; @@ -695,8 +697,7 @@ nfulnl_log_packet(struct net *net, goto unlock_and_release; } - if (inst->skb && - size > skb_tailroom(inst->skb) - sizeof(struct nfgenmsg)) { + if (inst->skb && size > skb_tailroom(inst->skb)) { /* either the queue len is too high or we don't have * enough room in the skb left. flush to userspace. */ __nfulnl_flush(inst); diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 82cb8236f8a1..ad979612238a 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -678,7 +678,7 @@ nft_target_select_ops(const struct nft_ctx *ctx, family = ctx->afi->family; /* Re-use the existing target if it's already loaded. */ - list_for_each_entry(nft_target, &nft_match_list, head) { + list_for_each_entry(nft_target, &nft_target_list, head) { struct xt_target *target = nft_target->ops.data; if (strcmp(target->name, tg_name) == 0 && diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 5d97d8fe4be7..d477d476714d 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1627,6 +1627,8 @@ struct sctp_chunk *sctp_assoc_lookup_asconf_ack( * ack chunk whose serial number matches that of the request. */ list_for_each_entry(ack, &asoc->asconf_ack_list, transmitted_list) { + if (sctp_chunk_pending(ack)) + continue; if (ack->subh.addip_hdr->serial == serial) { sctp_chunk_hold(ack); return ack; diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 0e8529113dc5..fb7976aee61c 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -862,8 +862,6 @@ int sctp_auth_set_key(struct sctp_endpoint *ep, list_add(&cur_key->key_list, sh_keys); cur_key->key = key; - sctp_auth_key_hold(key); - return 0; nomem: if (!replace) diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 4de12afa13d4..7e8a16c77039 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -140,18 +140,9 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) } else { /* Nothing to do. Next chunk in the packet, please. */ ch = (sctp_chunkhdr_t *) chunk->chunk_end; - /* Force chunk->skb->data to chunk->chunk_end. */ - skb_pull(chunk->skb, - chunk->chunk_end - chunk->skb->data); - - /* Verify that we have at least chunk headers - * worth of buffer left. - */ - if (skb_headlen(chunk->skb) < sizeof(sctp_chunkhdr_t)) { - sctp_chunk_free(chunk); - chunk = queue->in_progress = NULL; - } + skb_pull(chunk->skb, chunk->chunk_end - chunk->skb->data); + /* We are guaranteed to pull a SCTP header. */ } } @@ -187,24 +178,14 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) skb_pull(chunk->skb, sizeof(sctp_chunkhdr_t)); chunk->subh.v = NULL; /* Subheader is no longer valid. */ - if (chunk->chunk_end < skb_tail_pointer(chunk->skb)) { + if (chunk->chunk_end + sizeof(sctp_chunkhdr_t) < + skb_tail_pointer(chunk->skb)) { /* This is not a singleton */ chunk->singleton = 0; } else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) { - /* RFC 2960, Section 6.10 Bundling - * - * Partial chunks MUST NOT be placed in an SCTP packet. - * If the receiver detects a partial chunk, it MUST drop - * the chunk. - * - * Since the end of the chunk is past the end of our buffer - * (which contains the whole packet, we can freely discard - * the whole packet. - */ - sctp_chunk_free(chunk); - chunk = queue->in_progress = NULL; - - return NULL; + /* Discard inside state machine. */ + chunk->pdiscard = 1; + chunk->chunk_end = skb_tail_pointer(chunk->skb); } else { /* We are at the end of the packet, so mark the chunk * in case we need to send a SACK. diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index fee5552ddf92..43abb643f3a1 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2609,6 +2609,9 @@ do_addr_param: addr_param = param.v + sizeof(sctp_addip_param_t); af = sctp_get_af_specific(param_type2af(param.p->type)); + if (af == NULL) + break; + af->from_addr_param(&addr, addr_param, htons(asoc->peer.port), 0); @@ -3110,50 +3113,63 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, return SCTP_ERROR_NO_ERROR; } -/* Verify the ASCONF packet before we process it. */ -int sctp_verify_asconf(const struct sctp_association *asoc, - struct sctp_paramhdr *param_hdr, void *chunk_end, - struct sctp_paramhdr **errp) { - sctp_addip_param_t *asconf_param; +/* Verify the ASCONF packet before we process it. */ +bool sctp_verify_asconf(const struct sctp_association *asoc, + struct sctp_chunk *chunk, bool addr_param_needed, + struct sctp_paramhdr **errp) +{ + sctp_addip_chunk_t *addip = (sctp_addip_chunk_t *) chunk->chunk_hdr; union sctp_params param; - int length, plen; + bool addr_param_seen = false; - param.v = (sctp_paramhdr_t *) param_hdr; - while (param.v <= chunk_end - sizeof(sctp_paramhdr_t)) { - length = ntohs(param.p->length); - *errp = param.p; - - if (param.v > chunk_end - length || - length < sizeof(sctp_paramhdr_t)) - return 0; + sctp_walk_params(param, addip, addip_hdr.params) { + size_t length = ntohs(param.p->length); + *errp = param.p; switch (param.p->type) { + case SCTP_PARAM_ERR_CAUSE: + break; + case SCTP_PARAM_IPV4_ADDRESS: + if (length != sizeof(sctp_ipv4addr_param_t)) + return false; + addr_param_seen = true; + break; + case SCTP_PARAM_IPV6_ADDRESS: + if (length != sizeof(sctp_ipv6addr_param_t)) + return false; + addr_param_seen = true; + break; case SCTP_PARAM_ADD_IP: case SCTP_PARAM_DEL_IP: case SCTP_PARAM_SET_PRIMARY: - asconf_param = (sctp_addip_param_t *)param.v; - plen = ntohs(asconf_param->param_hdr.length); - if (plen < sizeof(sctp_addip_param_t) + - sizeof(sctp_paramhdr_t)) - return 0; + /* In ASCONF chunks, these need to be first. */ + if (addr_param_needed && !addr_param_seen) + return false; + length = ntohs(param.addip->param_hdr.length); + if (length < sizeof(sctp_addip_param_t) + + sizeof(sctp_paramhdr_t)) + return false; break; case SCTP_PARAM_SUCCESS_REPORT: case SCTP_PARAM_ADAPTATION_LAYER_IND: if (length != sizeof(sctp_addip_param_t)) - return 0; - + return false; break; default: - break; + /* This is unkown to us, reject! */ + return false; } - - param.v += WORD_ROUND(length); } - if (param.v != chunk_end) - return 0; + /* Remaining sanity checks. */ + if (addr_param_needed && !addr_param_seen) + return false; + if (!addr_param_needed && addr_param_seen) + return false; + if (param.v != chunk->chunk_end) + return false; - return 1; + return true; } /* Process an incoming ASCONF chunk with the next expected serial no. and @@ -3162,16 +3178,17 @@ int sctp_verify_asconf(const struct sctp_association *asoc, struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, struct sctp_chunk *asconf) { + sctp_addip_chunk_t *addip = (sctp_addip_chunk_t *) asconf->chunk_hdr; + bool all_param_pass = true; + union sctp_params param; sctp_addiphdr_t *hdr; union sctp_addr_param *addr_param; sctp_addip_param_t *asconf_param; struct sctp_chunk *asconf_ack; - __be16 err_code; int length = 0; int chunk_len; __u32 serial; - int all_param_pass = 1; chunk_len = ntohs(asconf->chunk_hdr->length) - sizeof(sctp_chunkhdr_t); hdr = (sctp_addiphdr_t *)asconf->skb->data; @@ -3199,9 +3216,14 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, goto done; /* Process the TLVs contained within the ASCONF chunk. */ - while (chunk_len > 0) { + sctp_walk_params(param, addip, addip_hdr.params) { + /* Skip preceeding address parameters. */ + if (param.p->type == SCTP_PARAM_IPV4_ADDRESS || + param.p->type == SCTP_PARAM_IPV6_ADDRESS) + continue; + err_code = sctp_process_asconf_param(asoc, asconf, - asconf_param); + param.addip); /* ADDIP 4.1 A7) * If an error response is received for a TLV parameter, * all TLVs with no response before the failed TLV are @@ -3209,28 +3231,20 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, * the failed response are considered unsuccessful unless * a specific success indication is present for the parameter. */ - if (SCTP_ERROR_NO_ERROR != err_code) - all_param_pass = 0; - + if (err_code != SCTP_ERROR_NO_ERROR) + all_param_pass = false; if (!all_param_pass) - sctp_add_asconf_response(asconf_ack, - asconf_param->crr_id, err_code, - asconf_param); + sctp_add_asconf_response(asconf_ack, param.addip->crr_id, + err_code, param.addip); /* ADDIP 4.3 D11) When an endpoint receiving an ASCONF to add * an IP address sends an 'Out of Resource' in its response, it * MUST also fail any subsequent add or delete requests bundled * in the ASCONF. */ - if (SCTP_ERROR_RSRC_LOW == err_code) + if (err_code == SCTP_ERROR_RSRC_LOW) goto done; - - /* Move to the next ASCONF param. */ - length = ntohs(asconf_param->param_hdr.length); - asconf_param = (void *)asconf_param + length; - chunk_len -= length; } - done: asoc->peer.addip_serial++; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 7194fe8589b0..3e287a3fa03b 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -170,6 +170,9 @@ sctp_chunk_length_valid(struct sctp_chunk *chunk, { __u16 chunk_length = ntohs(chunk->chunk_hdr->length); + /* Previously already marked? */ + if (unlikely(chunk->pdiscard)) + return 0; if (unlikely(chunk_length < required_length)) return 0; @@ -3591,9 +3594,7 @@ sctp_disposition_t sctp_sf_do_asconf(struct net *net, struct sctp_chunk *asconf_ack = NULL; struct sctp_paramhdr *err_param = NULL; sctp_addiphdr_t *hdr; - union sctp_addr_param *addr_param; __u32 serial; - int length; if (!sctp_vtag_verify(chunk, asoc)) { sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_BAD_TAG, @@ -3618,17 +3619,8 @@ sctp_disposition_t sctp_sf_do_asconf(struct net *net, hdr = (sctp_addiphdr_t *)chunk->skb->data; serial = ntohl(hdr->serial); - addr_param = (union sctp_addr_param *)hdr->params; - length = ntohs(addr_param->p.length); - if (length < sizeof(sctp_paramhdr_t)) - return sctp_sf_violation_paramlen(net, ep, asoc, type, arg, - (void *)addr_param, commands); - /* Verify the ASCONF chunk before processing it. */ - if (!sctp_verify_asconf(asoc, - (sctp_paramhdr_t *)((void *)addr_param + length), - (void *)chunk->chunk_end, - &err_param)) + if (!sctp_verify_asconf(asoc, chunk, true, &err_param)) return sctp_sf_violation_paramlen(net, ep, asoc, type, arg, (void *)err_param, commands); @@ -3745,10 +3737,7 @@ sctp_disposition_t sctp_sf_do_asconf_ack(struct net *net, rcvd_serial = ntohl(addip_hdr->serial); /* Verify the ASCONF-ACK chunk before processing it. */ - if (!sctp_verify_asconf(asoc, - (sctp_paramhdr_t *)addip_hdr->params, - (void *)asconf_ack->chunk_end, - &err_param)) + if (!sctp_verify_asconf(asoc, asconf_ack, false, &err_param)) return sctp_sf_violation_paramlen(net, ep, asoc, type, arg, (void *)err_param, commands); diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index f4b12c216f1c..5a723df670b4 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -885,6 +885,11 @@ static int snd_ftu_eff_switch_put(struct snd_kcontrol *kctl, return changed; } +static void kctl_private_value_free(struct snd_kcontrol *kctl) +{ + kfree((void *)kctl->private_value); +} + static int snd_ftu_create_effect_switch(struct usb_mixer_interface *mixer, int validx, int bUnitID) { @@ -919,6 +924,7 @@ static int snd_ftu_create_effect_switch(struct usb_mixer_interface *mixer, return -ENOMEM; } + kctl->private_free = kctl_private_value_free; err = snd_ctl_add(mixer->chip->card, kctl); if (err < 0) return err;