diff options
276 files changed, 4608 insertions, 1323 deletions
diff --git a/Documentation/fb/efifb.txt b/Documentation/fb/efifb.txt index a59916c29b33..1a85c1bdaf38 100644 --- a/Documentation/fb/efifb.txt +++ b/Documentation/fb/efifb.txt @@ -27,5 +27,11 @@ You have to add the following kernel parameters in your elilo.conf: Macbook Pro 17", iMac 20" : video=efifb:i20 +Accepted options: + +nowc Don't map the framebuffer write combined. This can be used + to workaround side-effects and slowdowns on other CPU cores + when large amounts of console data are written. + -- Edgar Hucek <gimli@dark-green.com> diff --git a/Documentation/gpio/gpio-legacy.txt b/Documentation/gpio/gpio-legacy.txt index b34fd94f7089..5eacc147ea87 100644 --- a/Documentation/gpio/gpio-legacy.txt +++ b/Documentation/gpio/gpio-legacy.txt @@ -459,7 +459,7 @@ pin controller? This is done by registering "ranges" of pins, which are essentially cross-reference tables. These are described in -Documentation/pinctrl.txt +Documentation/driver-api/pinctl.rst While the pin allocation is totally managed by the pinctrl subsystem, gpio (under gpiolib) is still maintained by gpio drivers. It may happen diff --git a/MAINTAINERS b/MAINTAINERS index 44cb004c765d..6f7721d1634c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1161,7 +1161,7 @@ M: Brendan Higgins <brendanhiggins@google.com> R: Benjamin Herrenschmidt <benh@kernel.crashing.org> R: Joel Stanley <joel@jms.id.au> L: linux-i2c@vger.kernel.org -L: openbmc@lists.ozlabs.org +L: openbmc@lists.ozlabs.org (moderated for non-subscribers) S: Maintained F: drivers/irqchip/irq-aspeed-i2c-ic.c F: drivers/i2c/busses/i2c-aspeed.c @@ -5834,7 +5834,7 @@ F: drivers/staging/greybus/spi.c F: drivers/staging/greybus/spilib.c F: drivers/staging/greybus/spilib.h -GREYBUS LOOBACK/TIME PROTOCOLS DRIVERS +GREYBUS LOOPBACK/TIME PROTOCOLS DRIVERS M: Bryan O'Donoghue <pure.logic@nexus-software.ie> S: Maintained F: drivers/staging/greybus/loopback.c @@ -10383,7 +10383,7 @@ L: linux-gpio@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl.git S: Maintained F: Documentation/devicetree/bindings/pinctrl/ -F: Documentation/pinctrl.txt +F: Documentation/driver-api/pinctl.rst F: drivers/pinctrl/ F: include/linux/pinctrl/ @@ -14004,6 +14004,7 @@ F: drivers/block/virtio_blk.c F: include/linux/virtio*.h F: include/uapi/linux/virtio_*.h F: drivers/crypto/virtio/ +F: mm/balloon_compaction.c VIRTIO CRYPTO DRIVER M: Gonglei <arei.gonglei@huawei.com> diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h index 3f2eb76243e3..d5562f9ce600 100644 --- a/arch/arm/include/asm/tlb.h +++ b/arch/arm/include/asm/tlb.h @@ -148,7 +148,8 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb) } static inline void -tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end) +arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, + unsigned long start, unsigned long end) { tlb->mm = mm; tlb->fullmm = !(start | (end+1)); @@ -166,8 +167,14 @@ tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start } static inline void -tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) +arch_tlb_finish_mmu(struct mmu_gather *tlb, + unsigned long start, unsigned long end, bool force) { + if (force) { + tlb->range_start = start; + tlb->range_end = end; + } + tlb_flush_mmu(tlb); /* keep the page table cache within bounds */ diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h index fced197b9626..cbe5ac3699bf 100644 --- a/arch/ia64/include/asm/tlb.h +++ b/arch/ia64/include/asm/tlb.h @@ -168,7 +168,8 @@ static inline void __tlb_alloc_page(struct mmu_gather *tlb) static inline void -tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end) +arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, + unsigned long start, unsigned long end) { tlb->mm = mm; tlb->max = ARRAY_SIZE(tlb->local); @@ -185,8 +186,11 @@ tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start * collected. */ static inline void -tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) +arch_tlb_finish_mmu(struct mmu_gather *tlb, + unsigned long start, unsigned long end, bool force) { + if (force) + tlb->need_flush = 1; /* * Note: tlb->nr may be 0 at this point, so we can't rely on tlb->start_addr and * tlb->end_addr. diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c new file mode 100644 index 000000000000..3f87b96da5c4 --- /dev/null +++ b/arch/mips/net/ebpf_jit.c @@ -0,0 +1,1950 @@ +/* + * Just-In-Time compiler for eBPF filters on MIPS + * + * Copyright (c) 2017 Cavium, Inc. + * + * Based on code from: + * + * Copyright (c) 2014 Imagination Technologies Ltd. + * Author: Markos Chandras <markos.chandras@imgtec.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; version 2 of the License. + */ + +#include <linux/bitops.h> +#include <linux/errno.h> +#include <linux/filter.h> +#include <linux/bpf.h> +#include <linux/slab.h> +#include <asm/bitops.h> +#include <asm/byteorder.h> +#include <asm/cacheflush.h> +#include <asm/cpu-features.h> +#include <asm/uasm.h> + +/* Registers used by JIT */ +#define MIPS_R_ZERO 0 +#define MIPS_R_AT 1 +#define MIPS_R_V0 2 /* BPF_R0 */ +#define MIPS_R_V1 3 +#define MIPS_R_A0 4 /* BPF_R1 */ +#define MIPS_R_A1 5 /* BPF_R2 */ +#define MIPS_R_A2 6 /* BPF_R3 */ +#define MIPS_R_A3 7 /* BPF_R4 */ +#define MIPS_R_A4 8 /* BPF_R5 */ +#define MIPS_R_T4 12 /* BPF_AX */ +#define MIPS_R_T5 13 +#define MIPS_R_T6 14 +#define MIPS_R_T7 15 +#define MIPS_R_S0 16 /* BPF_R6 */ +#define MIPS_R_S1 17 /* BPF_R7 */ +#define MIPS_R_S2 18 /* BPF_R8 */ +#define MIPS_R_S3 19 /* BPF_R9 */ +#define MIPS_R_S4 20 /* BPF_TCC */ +#define MIPS_R_S5 21 +#define MIPS_R_S6 22 +#define MIPS_R_S7 23 +#define MIPS_R_T8 24 +#define MIPS_R_T9 25 +#define MIPS_R_SP 29 +#define MIPS_R_RA 31 + +/* eBPF flags */ +#define EBPF_SAVE_S0 BIT(0) +#define EBPF_SAVE_S1 BIT(1) +#define EBPF_SAVE_S2 BIT(2) +#define EBPF_SAVE_S3 BIT(3) +#define EBPF_SAVE_S4 BIT(4) +#define EBPF_SAVE_RA BIT(5) +#define EBPF_SEEN_FP BIT(6) +#define EBPF_SEEN_TC BIT(7) +#define EBPF_TCC_IN_V1 BIT(8) + +/* + * For the mips64 ISA, we need to track the value range or type for + * each JIT register. The BPF machine requires zero extended 32-bit + * values, but the mips64 ISA requires sign extended 32-bit values. + * At each point in the BPF program we track the state of every + * register so that we can zero extend or sign extend as the BPF + * semantics require. + */ +enum reg_val_type { + /* uninitialized */ + REG_UNKNOWN, + /* not known to be 32-bit compatible. */ + REG_64BIT, + /* 32-bit compatible, no truncation needed for 64-bit ops. */ + REG_64BIT_32BIT, + /* 32-bit compatible, need truncation for 64-bit ops. */ + REG_32BIT, + /* 32-bit zero extended. */ + REG_32BIT_ZERO_EX, + /* 32-bit no sign/zero extension needed. */ + REG_32BIT_POS +}; + +/* + * high bit of offsets indicates if long branch conversion done at + * this insn. + */ +#define OFFSETS_B_CONV BIT(31) + +/** + * struct jit_ctx - JIT context + * @skf: The sk_filter + * @stack_size: eBPF stack size + * @tmp_offset: eBPF $sp offset to 8-byte temporary memory + * @idx: Instruction index + * @flags: JIT flags + * @offsets: Instruction offsets + * @target: Memory location for the compiled filter + * @reg_val_types Packed enum reg_val_type for each register. + */ +struct jit_ctx { + const struct bpf_prog *skf; + int stack_size; + int tmp_offset; + u32 idx; + u32 flags; + u32 *offsets; + u32 *target; + u64 *reg_val_types; + unsigned int long_b_conversion:1; + unsigned int gen_b_offsets:1; +}; + +static void set_reg_val_type(u64 *rvt, int reg, enum reg_val_type type) +{ + *rvt &= ~(7ull << (reg * 3)); + *rvt |= ((u64)type << (reg * 3)); +} + +static enum reg_val_type get_reg_val_type(const struct jit_ctx *ctx, + int index, int reg) +{ + return (ctx->reg_val_types[index] >> (reg * 3)) & 7; +} + +/* Simply emit the instruction if the JIT memory space has been allocated */ +#define emit_instr(ctx, func, ...) \ +do { \ + if ((ctx)->target != NULL) { \ + u32 *p = &(ctx)->target[ctx->idx]; \ + uasm_i_##func(&p, ##__VA_ARGS__); \ + } \ + (ctx)->idx++; \ +} while (0) + +static unsigned int j_target(struct jit_ctx *ctx, int target_idx) +{ + unsigned long target_va, base_va; + unsigned int r; + + if (!ctx->target) + return 0; + + base_va = (unsigned long)ctx->target; + target_va = base_va + (ctx->offsets[target_idx] & ~OFFSETS_B_CONV); + + if ((base_va & ~0x0ffffffful) != (target_va & ~0x0ffffffful)) + return (unsigned int)-1; + r = target_va & 0x0ffffffful; + return r; +} + +/* Compute the immediate value for PC-relative branches. */ +static u32 b_imm(unsigned int tgt, struct jit_ctx *ctx) +{ + if (!ctx->gen_b_offsets) + return 0; + + /* + * We want a pc-relative branch. tgt is the instruction offset + * we want to jump to. + + * Branch on MIPS: + * I: target_offset <- sign_extend(offset) + * I+1: PC += target_offset (delay slot) + * + * ctx->idx currently points to the branch instruction + * but the offset is added to the delay slot so we need + * to subtract 4. + */ + return (ctx->offsets[tgt] & ~OFFSETS_B_CONV) - + (ctx->idx * 4) - 4; +} + +int bpf_jit_enable __read_mostly; + +enum which_ebpf_reg { + src_reg, + src_reg_no_fp, + dst_reg, + dst_reg_fp_ok +}; + +/* + * For eBPF, the register mapping naturally falls out of the + * requirements of eBPF and the MIPS n64 ABI. We don't maintain a + * separate frame pointer, so BPF_REG_10 relative accesses are + * adjusted to be $sp relative. + */ +int ebpf_to_mips_reg(struct jit_ctx *ctx, const struct bpf_insn *insn, + enum which_ebpf_reg w) +{ + int ebpf_reg = (w == src_reg || w == src_reg_no_fp) ? + insn->src_reg : insn->dst_reg; + + switch (ebpf_reg) { + case BPF_REG_0: + return MIPS_R_V0; + case BPF_REG_1: + return MIPS_R_A0; + case BPF_REG_2: + return MIPS_R_A1; + case BPF_REG_3: + return MIPS_R_A2; + case BPF_REG_4: + return MIPS_R_A3; + case BPF_REG_5: + return MIPS_R_A4; + case BPF_REG_6: + ctx->flags |= EBPF_SAVE_S0; + return MIPS_R_S0; + case BPF_REG_7: + ctx->flags |= EBPF_SAVE_S1; + return MIPS_R_S1; + case BPF_REG_8: + ctx->flags |= EBPF_SAVE_S2; + return MIPS_R_S2; + case BPF_REG_9: + ctx->flags |= EBPF_SAVE_S3; + return MIPS_R_S3; + case BPF_REG_10: + if (w == dst_reg || w == src_reg_no_fp) + goto bad_reg; + ctx->flags |= EBPF_SEEN_FP; + /* + * Needs special handling, return something that + * cannot be clobbered just in case. + */ + return MIPS_R_ZERO; + case BPF_REG_AX: + return MIPS_R_T4; + default: +bad_reg: + WARN(1, "Illegal bpf reg: %d\n", ebpf_reg); + return -EINVAL; + } +} +/* + * eBPF stack frame will be something like: + * + * Entry $sp ------> +--------------------------------+ + * | $ra (optional) | + * +--------------------------------+ + * | $s0 (optional) | + * +--------------------------------+ + * | $s1 (optional) | + * +--------------------------------+ + * | $s2 (optional) | + * +--------------------------------+ + * | $s3 (optional) | + * +--------------------------------+ + * | $s4 (optional) | + * +--------------------------------+ + * | tmp-storage (if $ra saved) | + * $sp + tmp_offset --> +--------------------------------+ <--BPF_REG_10 + * | BPF_REG_10 relative storage | + * | MAX_BPF_STACK (optional) | + * | . | + * | . | + * | . | + * $sp --------> +--------------------------------+ + * + * If BPF_REG_10 is never referenced, then the MAX_BPF_STACK sized + * area is not allocated. + */ +static int gen_int_prologue(struct jit_ctx *ctx) +{ + int stack_adjust = 0; + int store_offset; + int locals_size; + + if (ctx->flags & EBPF_SAVE_RA) + /* + * If RA we are doing a function call and may need + * extra 8-byte tmp area. + */ + stack_adjust += 16; + if (ctx->flags & EBPF_SAVE_S0) + stack_adjust += 8; + if (ctx->flags & EBPF_SAVE_S1) + stack_adjust += 8; + if (ctx->flags & EBPF_SAVE_S2) + stack_adjust += 8; + if (ctx->flags & EBPF_SAVE_S3) + stack_adjust += 8; + if (ctx->flags & EBPF_SAVE_S4) + stack_adjust += 8; + + BUILD_BUG_ON(MAX_BPF_STACK & 7); + locals_size = (ctx->flags & EBPF_SEEN_FP) ? MAX_BPF_STACK : 0; + + stack_adjust += locals_size; + ctx->tmp_offset = locals_size; + + ctx->stack_size = stack_adjust; + + /* + * First instruction initializes the tail call count (TCC). + * On tail call we skip this instruction, and the TCC is + * passed in $v1 from the caller. + */ + emit_instr(ctx, daddiu, MIPS_R_V1, MIPS_R_ZERO, MAX_TAIL_CALL_CNT); + if (stack_adjust) + emit_instr(ctx, daddiu, MIPS_R_SP, MIPS_R_SP, -stack_adjust); + else + return 0; + + store_offset = stack_adjust - 8; + + if (ctx->flags & EBPF_SAVE_RA) { + emit_instr(ctx, sd, MIPS_R_RA, store_offset, MIPS_R_SP); + store_offset -= 8; + } + if (ctx->flags & EBPF_SAVE_S0) { + emit_instr(ctx, sd, MIPS_R_S0, store_offset, MIPS_R_SP); + store_offset -= 8; + } + if (ctx->flags & EBPF_SAVE_S1) { + emit_instr(ctx, sd, MIPS_R_S1, store_offset, MIPS_R_SP); + store_offset -= 8; + } + if (ctx->flags & EBPF_SAVE_S2) { + emit_instr(ctx, sd, MIPS_R_S2, store_offset, MIPS_R_SP); + store_offset -= 8; + } + if (ctx->flags & EBPF_SAVE_S3) { + emit_instr(ctx, sd, MIPS_R_S3, store_offset, MIPS_R_SP); + store_offset -= 8; + } + if (ctx->flags & EBPF_SAVE_S4) { + emit_instr(ctx, sd, MIPS_R_S4, store_offset, MIPS_R_SP); + store_offset -= 8; + } + + if ((ctx->flags & EBPF_SEEN_TC) && !(ctx->flags & EBPF_TCC_IN_V1)) + emit_instr(ctx, daddu, MIPS_R_S4, MIPS_R_V1, MIPS_R_ZERO); + + return 0; +} + +static int build_int_epilogue(struct jit_ctx *ctx, int dest_reg) +{ + const struct bpf_prog *prog = ctx->skf; + int stack_adjust = ctx->stack_size; + int store_offset = stack_adjust - 8; + int r0 = MIPS_R_V0; + + if (dest_reg == MIPS_R_RA && + get_reg_val_type(ctx, prog->len, BPF_REG_0) == REG_32BIT_ZERO_EX) + /* Don't let zero extended value escape. */ + emit_instr(ctx, sll, r0, r0, 0); + + if (ctx->flags & EBPF_SAVE_RA) { + emit_instr(ctx, ld, MIPS_R_RA, store_offset, MIPS_R_SP); + store_offset -= 8; + } + if (ctx->flags & EBPF_SAVE_S0) { + emit_instr(ctx, ld, MIPS_R_S0, store_offset, MIPS_R_SP); + store_offset -= 8; + } + if (ctx->flags & EBPF_SAVE_S1) { + emit_instr(ctx, ld, MIPS_R_S1, store_offset, MIPS_R_SP); + store_offset -= 8; + } + if (ctx->flags & EBPF_SAVE_S2) { + emit_instr(ctx, ld, MIPS_R_S2, store_offset, MIPS_R_SP); + store_offset -= 8; + } + if (ctx->flags & EBPF_SAVE_S3) { + emit_instr(ctx, ld, MIPS_R_S3, store_offset, MIPS_R_SP); + store_offset -= 8; + } + if (ctx->flags & EBPF_SAVE_S4) { + emit_instr(ctx, ld, MIPS_R_S4, store_offset, MIPS_R_SP); + store_offset -= 8; + } + emit_instr(ctx, jr, dest_reg); + + if (stack_adjust) + emit_instr(ctx, daddiu, MIPS_R_SP, MIPS_R_SP, stack_adjust); + else + emit_instr(ctx, nop); + + return 0; +} + +static void gen_imm_to_reg(const struct bpf_insn *insn, int reg, + struct jit_ctx *ctx) +{ + if (insn->imm >= S16_MIN && insn->imm <= S16_MAX) { + emit_instr(ctx, addiu, reg, MIPS_R_ZERO, insn->imm); + } else { + int lower = (s16)(insn->imm & 0xffff); + int upper = insn->imm - lower; + + emit_instr(ctx, lui, reg, upper >> 16); + emit_instr(ctx, addiu, reg, reg, lower); + } + +} + +static int gen_imm_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, + int idx) +{ + int upper_bound, lower_bound; + int dst = ebpf_to_mips_reg(ctx, insn, dst_reg); + + if (dst < 0) + return dst; + + switch (BPF_OP(insn->code)) { + case BPF_MOV: + case BPF_ADD: + upper_bound = S16_MAX; + lower_bound = S16_MIN; + break; + case BPF_SUB: + upper_bound = -(int)S16_MIN; + lower_bound = -(int)S16_MAX; + break; + case BPF_AND: + case BPF_OR: + case BPF_XOR: + upper_bound = 0xffff; + lower_bound = 0; + break; + case BPF_RSH: + case BPF_LSH: + case BPF_ARSH: + /* Shift amounts are truncated, no need for bounds */ + upper_bound = S32_MAX; + lower_bound = S32_MIN; + break; + default: + return -EINVAL; + } + + /* + * Immediate move clobbers the register, so no sign/zero + * extension needed. + */ + if (BPF_CLASS(insn->code) == BPF_ALU64 && + BPF_OP(insn->code) != BPF_MOV && + get_reg_val_type(ctx, idx, insn->dst_reg) == REG_32BIT) + emit_instr(ctx, dinsu, dst, MIPS_R_ZERO, 32, 32); + /* BPF_ALU | BPF_LSH doesn't need separate sign extension */ + if (BPF_CLASS(insn->code) == BPF_ALU && + BPF_OP(insn->code) != BPF_LSH && + BPF_OP(insn->code) != BPF_MOV && + get_reg_val_type(ctx, idx, insn->dst_reg) != REG_32BIT) + emit_instr(ctx, sll, dst, dst, 0); + + if (insn->imm >= lower_bound && insn->imm <= upper_bound) { + /* single insn immediate case */ + switch (BPF_OP(insn->code) | BPF_CLASS(insn->code)) { + case BPF_ALU64 | BPF_MOV: + emit_instr(ctx, daddiu, dst, MIPS_R_ZERO, insn->imm); + break; + case BPF_ALU64 | BPF_AND: + case BPF_ALU | BPF_AND: + emit_instr(ctx, andi, dst, dst, insn->imm); + break; + case BPF_ALU64 | BPF_OR: + case BPF_ALU | BPF_OR: + emit_instr(ctx, ori, dst, dst, insn->imm); + break; + case BPF_ALU64 | BPF_XOR: + case BPF_ALU | BPF_XOR: + emit_instr(ctx, xori, dst, dst, insn->imm); + break; + case BPF_ALU64 | BPF_ADD: + emit_instr(ctx, daddiu, dst, dst, insn->imm); + break; + case BPF_ALU64 | BPF_SUB: + emit_instr(ctx, daddiu, dst, dst, -insn->imm); + break; + case BPF_ALU64 | BPF_RSH: + emit_instr(ctx, dsrl_safe, dst, dst, insn->imm & 0x3f); + break; + case BPF_ALU | BPF_RSH: + emit_instr(ctx, srl, dst, dst, insn->imm & 0x1f); + break; + case BPF_ALU64 | BPF_LSH: + emit_instr(ctx, dsll_safe, dst, dst, insn->imm & 0x3f); + break; + case BPF_ALU | BPF_LSH: + emit_instr(ctx, sll, dst, dst, insn->imm & 0x1f); + break; + case BPF_ALU64 | BPF_ARSH: + emit_instr(ctx, dsra_safe, dst, dst, insn->imm & 0x3f); + break; + case BPF_ALU | BPF_ARSH: + emit_instr(ctx, sra, dst, dst, insn->imm & 0x1f); + break; + case BPF_ALU | BPF_MOV: + emit_instr(ctx, addiu, dst, MIPS_R_ZERO, insn->imm); + break; + case BPF_ALU | BPF_ADD: + emit_instr(ctx, addiu, dst, dst, insn->imm); + break; + case BPF_ALU | BPF_SUB: + emit_instr(ctx, addiu, dst, dst, -insn->imm); + break; + default: + return -EINVAL; + } + } else { + /* multi insn immediate case */ + if (BPF_OP(insn->code) == BPF_MOV) { + gen_imm_to_reg(insn, dst, ctx); + } else { + gen_imm_to_reg(insn, MIPS_R_AT, ctx); + switch (BPF_OP(insn->code) | BPF_CLASS(insn->code)) { + case BPF_ALU64 | BPF_AND: + case BPF_ALU | BPF_AND: + emit_instr(ctx, and, dst, dst, MIPS_R_AT); + break; + case BPF_ALU64 | BPF_OR: + case BPF_ALU | BPF_OR: + emit_instr(ctx, or, dst, dst, MIPS_R_AT); + break; + case BPF_ALU64 | BPF_XOR: + case BPF_ALU | BPF_XOR: + emit_instr(ctx, xor, dst, dst, MIPS_R_AT); + break; + case BPF_ALU64 | BPF_ADD: + emit_instr(ctx, daddu, dst, dst, MIPS_R_AT); + break; + case BPF_ALU64 | BPF_SUB: + emit_instr(ctx, dsubu, dst, dst, MIPS_R_AT); + break; + case BPF_ALU | BPF_ADD: + emit_instr(ctx, addu, dst, dst, MIPS_R_AT); + break; + case BPF_ALU | BPF_SUB: + emit_instr(ctx, subu, dst, dst, MIPS_R_AT); + break; + default: + return -EINVAL; + } + } + } + + return 0; +} + +static void * __must_check +ool_skb_header_pointer(const struct sk_buff *skb, int offset, + int len, void *buffer) +{ + return skb_header_pointer(skb, offset, len, buffer); +} + +static int size_to_len(const struct bpf_insn *insn) +{ + switch (BPF_SIZE(insn->code)) { + case BPF_B: + return 1; + case BPF_H: + return 2; + case BPF_W: + return 4; + case BPF_DW: + return 8; + } + return 0; +} + +static void emit_const_to_reg(struct jit_ctx *ctx, int dst, u64 value) +{ + if (value >= 0xffffffffffff8000ull || value < 0x8000ull) { + emit_instr(ctx, daddiu, dst, MIPS_R_ZERO, (int)value); + } else if (value >= 0xffffffff80000000ull || + (value < 0x80000000 && value > 0xffff)) { + emit_instr(ctx, lui, dst, (s32)(s16)(value >> 16)); + emit_instr(ctx, ori, dst, dst, (unsigned int)(value & 0xffff)); + } else { + int i; + bool seen_part = false; + int needed_shift = 0; + + for (i = 0; i < 4; i++) { + u64 part = (value >> (16 * (3 - i))) & 0xffff; + + if (seen_part && needed_shift > 0 && (part || i == 3)) { + emit_instr(ctx, dsll_safe, dst, dst, needed_shift); + needed_shift = 0; + } + if (part) { + if (i == 0 || (!seen_part && i < 3 && part < 0x8000)) { + emit_instr(ctx, lui, dst, (s32)(s16)part); + needed_shift = -16; + } else { + emit_instr(ctx, ori, dst, + seen_part ? dst : MIPS_R_ZERO, + (unsigned int)part); + } + seen_part = true; + } + if (seen_part) + needed_shift += 16; + } + } +} + +static int emit_bpf_tail_call(struct jit_ctx *ctx, int this_idx) +{ + int off, b_off; + + ctx->flags |= EBPF_SEEN_TC; + /* + * if (index >= array->map.max_entries) + * goto out; + */ + off = offsetof(struct bpf_array, map.max_entries); + emit_instr(ctx, lwu, MIPS_R_T5, off, MIPS_R_A1); + emit_instr(ctx, sltu, MIPS_R_AT, MIPS_R_T5, MIPS_R_A2); + b_off = b_imm(this_idx + 1, ctx); + emit_instr(ctx, bne, MIPS_R_AT, MIPS_R_ZERO, b_off); + /* + * if (--TCC < 0) + * goto out; + */ + /* Delay slot */ + emit_instr(ctx, daddiu, MIPS_R_T5, + (ctx->flags & EBPF_TCC_IN_V1) ? MIPS_R_V1 : MIPS_R_S4, -1); + b_off = b_imm(this_idx + 1, ctx); + emit_instr(ctx, bltz, MIPS_R_T5, b_off); + /* + * prog = array->ptrs[index]; + * if (prog == NULL) + * goto out; + */ + /* Delay slot */ + emit_instr(ctx, dsll, MIPS_R_T8, MIPS_R_A2, 3); + emit_instr(ctx, daddu, MIPS_R_T8, MIPS_R_T8, MIPS_R_A1); + off = offsetof(struct bpf_array, ptrs); + emit_instr(ctx, ld, MIPS_R_AT, off, MIPS_R_T8); + b_off = b_imm(this_idx + 1, ctx); + emit_instr(ctx, beq, MIPS_R_AT, MIPS_R_ZERO, b_off); + /* Delay slot */ + emit_instr(ctx, nop); + + /* goto *(prog->bpf_func + 4); */ + off = offsetof(struct bpf_prog, bpf_func); + emit_instr(ctx, ld, MIPS_R_T9, off, MIPS_R_AT); + /* All systems are go... propagate TCC */ + emit_instr(ctx, daddu, MIPS_R_V1, MIPS_R_T5, MIPS_R_ZERO); + /* Skip first instruction (TCC initialization) */ + emit_instr(ctx, daddiu, MIPS_R_T9, MIPS_R_T9, 4); + return build_int_epilogue(ctx, MIPS_R_T9); +} + +static bool use_bbit_insns(void) +{ + switch (current_cpu_type()) { + case CPU_CAVIUM_OCTEON: + case CPU_CAVIUM_OCTEON_PLUS: + case CPU_CAVIUM_OCTEON2: + case CPU_CAVIUM_OCTEON3: + return true; + default: + return false; + } +} + +static bool is_bad_offset(int b_off) +{ + return b_off > 0x1ffff || b_off < -0x20000; +} + +/* Returns the number of insn slots consumed. */ +static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, + int this_idx, int exit_idx) +{ + int src, dst, r, td, ts, mem_off, b_off; + bool need_swap, did_move, cmp_eq; + unsigned int target; + u64 t64; + s64 t64s; + + switch (insn->code) { + case BPF_ALU64 | BPF_ADD | BPF_K: /* ALU64_IMM */ + case BPF_ALU64 | BPF_SUB | BPF_K: /* ALU64_IMM */ + case BPF_ALU64 | BPF_OR | BPF_K: /* ALU64_IMM */ + case BPF_ALU64 | BPF_AND | BPF_K: /* ALU64_IMM */ + case BPF_ALU64 | BPF_LSH | BPF_K: /* ALU64_IMM */ + case BPF_ALU64 | BPF_RSH | BPF_K: /* ALU64_IMM */ + case BPF_ALU64 | BPF_XOR | BPF_K: /* ALU64_IMM */ + case BPF_ALU64 | BPF_ARSH | BPF_K: /* ALU64_IMM */ + case BPF_ALU64 | BPF_MOV | BPF_K: /* ALU64_IMM */ + case BPF_ALU | BPF_MOV | BPF_K: /* ALU32_IMM */ + case BPF_ALU | BPF_ADD | BPF_K: /* ALU32_IMM */ + case BPF_ALU | BPF_SUB | BPF_K: /* ALU32_IMM */ + case BPF_ALU | BPF_OR | BPF_K: /* ALU64_IMM */ + case BPF_ALU | BPF_AND | BPF_K: /* ALU64_IMM */ + case BPF_ALU | BPF_LSH | BPF_K: /* ALU64_IMM */ + case BPF_ALU | BPF_RSH | BPF_K: /* ALU64_IMM */ + case BPF_ALU | BPF_XOR | BPF_K: /* ALU64_IMM */ + case BPF_ALU | BPF_ARSH | BPF_K: /* ALU64_IMM */ + r = gen_imm_insn(insn, ctx, this_idx); + if (r < 0) + return r; + break; + case BPF_ALU64 | BPF_MUL | BPF_K: /* ALU64_IMM */ + dst = ebpf_to_mips_reg(ctx, insn, dst_reg); + if (dst < 0) + return dst; + if (get_reg_val_type(ctx, this_idx, insn->dst_reg) == REG_32BIT) + emit_instr(ctx, dinsu, dst, MIPS_R_ZERO, 32, 32); + if (insn->imm == 1) /* Mult by 1 is a nop */ + break; + gen_imm_to_reg(insn, MIPS_R_AT, ctx); + emit_instr(ctx, dmultu, MIPS_R_AT, dst); + emit_instr(ctx, mflo, dst); + break; + case BPF_ALU64 | BPF_NEG | BPF_K: /* ALU64_IMM */ + dst = ebpf_to_mips_reg(ctx, insn, dst_reg); + if (dst < 0) + return dst; + if (get_reg_val_type(ctx, this_idx, insn->dst_reg) == REG_32BIT) + emit_instr(ctx, dinsu, dst, MIPS_R_ZERO, 32, 32); + emit_instr(ctx, dsubu, dst, MIPS_R_ZERO, dst); + break; + case BPF_ALU | BPF_MUL | BPF_K: /* ALU_IMM */ + dst = ebpf_to_mips_reg(ctx, insn, dst_reg); + if (dst < 0) + return dst; + td = get_reg_val_type(ctx, this_idx, insn->dst_reg); + if (td == REG_64BIT || td == REG_32BIT_ZERO_EX) { + /* sign extend */ + emit_instr(ctx, sll, dst, dst, 0); + } + if (insn->imm == 1) /* Mult by 1 is a nop */ + break; + gen_imm_to_reg(insn, MIPS_R_AT, ctx); + emit_instr(ctx, multu, dst, MIPS_R_AT); + emit_instr(ctx, mflo, dst); + break; + case BPF_ALU | BPF_NEG | BPF_K: /* ALU_IMM */ + dst = ebpf_to_mips_reg(ctx, insn, dst_reg); + if (dst < 0) + return dst; + td = get_reg_val_type(ctx, this_idx, insn->dst_reg); + if (td == REG_64BIT || td == REG_32BIT_ZERO_EX) { + /* sign extend */ + emit_instr(ctx, sll, dst, dst, 0); + } + emit_instr(ctx, subu, dst, MIPS_R_ZERO, dst); + break; + case BPF_ALU | BPF_DIV | BPF_K: /* ALU_IMM */ + case BPF_ALU | BPF_MOD | BPF_K: /* ALU_IMM */ + dst = ebpf_to_mips_reg(ctx, insn, dst_reg); + if (dst < 0) + return dst; + if (insn->imm == 0) { /* Div by zero */ + b_off = b_imm(exit_idx, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_instr(ctx, beq, MIPS_R_ZERO, MIPS_R_ZERO, b_off); + emit_instr(ctx, addu, MIPS_R_V0, MIPS_R_ZERO, MIPS_R_ZERO); + } + td = get_reg_val_type(ctx, this_idx, insn->dst_reg); + if (td == REG_64BIT || td == REG_32BIT_ZERO_EX) + /* sign extend */ + emit_instr(ctx, sll, dst, dst, 0); + if (insn->imm == 1) { + /* div by 1 is a nop, mod by 1 is zero */ + if (BPF_OP(insn->code) == BPF_MOD) + emit_instr(ctx, addu, dst, MIPS_R_ZERO, MIPS_R_ZERO); + break; + } + gen_imm_to_reg(insn, MIPS_R_AT, ctx); + emit_instr(ctx, divu, dst, MIPS_R_AT); + if (BPF_OP(insn->code) == BPF_DIV) + emit_instr(ctx, mflo, dst); + else + emit_instr(ctx, mfhi, dst); + break; + case BPF_ALU64 | BPF_DIV | BPF_K: /* ALU_IMM */ + case BPF_ALU64 | BPF_MOD | BPF_K: /* ALU_IMM */ + dst = ebpf_to_mips_reg(ctx, insn, dst_reg); + if (dst < 0) + return dst; + if (insn->imm == 0) { /* Div by zero */ + b_off = b_imm(exit_idx, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_instr(ctx, beq, MIPS_R_ZERO, MIPS_R_ZERO, b_off); + emit_instr(ctx, addu, MIPS_R_V0, MIPS_R_ZERO, MIPS_R_ZERO); + } + if (get_reg_val_type(ctx, this_idx, insn->dst_reg) == REG_32BIT) + emit_instr(ctx, dinsu, dst, MIPS_R_ZERO, 32, 32); + + if (insn->imm == 1) { + /* div by 1 is a nop, mod by 1 is zero */ + if (BPF_OP(insn->code) == BPF_MOD) + emit_instr(ctx, addu, dst, MIPS_R_ZERO, MIPS_R_ZERO); + break; + } + gen_imm_to_reg(insn, MIPS_R_AT, ctx); + emit_instr(ctx, ddivu, dst, MIPS_R_AT); + if (BPF_OP(insn->code) == BPF_DIV) + emit_instr(ctx, mflo, dst); + else + emit_instr(ctx, mfhi, dst); + break; + case BPF_ALU64 | BPF_MOV | BPF_X: /* ALU64_REG */ + case BPF_ALU64 | BPF_ADD | BPF_X: /* ALU64_REG */ + case BPF_ALU64 | BPF_SUB | BPF_X: /* ALU64_REG */ + case BPF_ALU64 | BPF_XOR | BPF_X: /* ALU64_REG */ + case BPF_ALU64 | BPF_OR | BPF_X: /* ALU64_REG */ + case BPF_ALU64 | BPF_AND | BPF_X: /* ALU64_REG */ + case BPF_ALU64 | BPF_MUL | BPF_X: /* ALU64_REG */ + case BPF_ALU64 | BPF_DIV | BPF_X: /* ALU64_REG */ + case BPF_ALU64 | BPF_MOD | BPF_X: /* ALU64_REG */ + case BPF_ALU64 | BPF_LSH | BPF_X: /* ALU64_REG */ + case BPF_ALU64 | BPF_RSH | BPF_X: /* ALU64_REG */ + case BPF_ALU64 | BPF_ARSH | BPF_X: /* ALU64_REG */ + src = ebpf_to_mips_reg(ctx, insn, src_reg); + dst = ebpf_to_mips_reg(ctx, insn, dst_reg); + if (src < 0 || dst < 0) + return -EINVAL; + if (get_reg_val_type(ctx, this_idx, insn->dst_reg) == REG_32BIT) + emit_instr(ctx, dinsu, dst, MIPS_R_ZERO, 32, 32); + did_move = false; + if (insn->src_reg == BPF_REG_10) { + if (BPF_OP(insn->code) == BPF_MOV) { + emit_instr(ctx, daddiu, dst, MIPS_R_SP, MAX_BPF_STACK); + did_move = true; + } else { + emit_instr(ctx, daddiu, MIPS_R_AT, MIPS_R_SP, MAX_BPF_STACK); + src = MIPS_R_AT; + } + } else if (get_reg_val_type(ctx, this_idx, insn->src_reg) == REG_32BIT) { + int tmp_reg = MIPS_R_AT; + + if (BPF_OP(insn->code) == BPF_MOV) { + tmp_reg = dst; + did_move = true; + } + emit_instr(ctx, daddu, tmp_reg, src, MIPS_R_ZERO); + emit_instr(ctx, dinsu, tmp_reg, MIPS_R_ZERO, 32, 32); + src = MIPS_R_AT; + } + switch (BPF_OP(insn->code)) { + case BPF_MOV: + if (!did_move) + emit_instr(ctx, daddu, dst, src, MIPS_R_ZERO); + break; + case BPF_ADD: + emit_instr(ctx, daddu, dst, dst, src); + break; + case BPF_SUB: + emit_instr(ctx, dsubu, dst, dst, src); + break; + case BPF_XOR: + emit_instr(ctx, xor, dst, dst, src); + break; + case BPF_OR: + emit_instr(ctx, or, dst, dst, src); + break; + case BPF_AND: + emit_instr(ctx, and, dst, dst, src); + break; + case BPF_MUL: + emit_instr(ctx, dmultu, dst, src); + emit_instr(ctx, mflo, dst); + break; + case BPF_DIV: + case BPF_MOD: + b_off = b_imm(exit_idx, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_instr(ctx, beq, src, MIPS_R_ZERO, b_off); + emit_instr(ctx, movz, MIPS_R_V0, MIPS_R_ZERO, src); + emit_instr(ctx, ddivu, dst, src); + if (BPF_OP(insn->code) == BPF_DIV) + emit_instr(ctx, mflo, dst); + else + emit_instr(ctx, mfhi, dst); + break; + case BPF_LSH: + emit_instr(ctx, dsllv, dst, dst, src); + break; + case BPF_RSH: + emit_instr(ctx, dsrlv, dst, dst, src); + break; + case BPF_ARSH: + emit_instr(ctx, dsrav, dst, dst, src); + break; + default: + pr_err("ALU64_REG NOT HANDLED\n"); + return -EINVAL; + } + break; + case BPF_ALU | BPF_MOV | BPF_X: /* ALU_REG */ + case BPF_ALU | BPF_ADD | BPF_X: /* ALU_REG */ + case BPF_ALU | BPF_SUB | BPF_X: /* ALU_REG */ + case BPF_ALU | BPF_XOR | BPF_X: /* ALU_REG */ + case BPF_ALU | BPF_OR | BPF_X: /* ALU_REG */ + case BPF_ALU | BPF_AND | BPF_X: /* ALU_REG */ + case BPF_ALU | BPF_MUL | BPF_X: /* ALU_REG */ + case BPF_ALU | BPF_DIV | BPF_X: /* ALU_REG */ + case BPF_ALU | BPF_MOD | BPF_X: /* ALU_REG */ + case BPF_ALU | BPF_LSH | BPF_X: /* ALU_REG */ + case BPF_ALU | BPF_RSH | BPF_X: /* ALU_REG */ + src = ebpf_to_mips_reg(ctx, insn, src_reg_no_fp); + dst = ebpf_to_mips_reg(ctx, insn, dst_reg); + if (src < 0 || dst < 0) + return -EINVAL; + td = get_reg_val_type(ctx, this_idx, insn->dst_reg); + if (td == REG_64BIT || td == REG_32BIT_ZERO_EX) { + /* sign extend */ + emit_instr(ctx, sll, dst, dst, 0); + } + did_move = false; + ts = get_reg_val_type(ctx, this_idx, insn->src_reg); + if (ts == REG_64BIT || ts == REG_32BIT_ZERO_EX) { + int tmp_reg = MIPS_R_AT; + + if (BPF_OP(insn->code) == BPF_MOV) { + tmp_reg = dst; + did_move = true; + } + /* sign extend */ + emit_instr(ctx, sll, tmp_reg, src, 0); + src = MIPS_R_AT; + } + switch (BPF_OP(insn->code)) { + case BPF_MOV: + if (!did_move) + emit_instr(ctx, addu, dst, src, MIPS_R_ZERO); + break; + case BPF_ADD: + emit_instr(ctx, addu, dst, dst, src); + break; + case BPF_SUB: + emit_instr(ctx, subu, dst, dst, src); + break; + case BPF_XOR: + emit_instr(ctx, xor, dst, dst, src); + break; + case BPF_OR: + emit_instr(ctx, or, dst, dst, src); + break; + case BPF_AND: + emit_instr(ctx, and, dst, dst, src); + break; + case BPF_MUL: + emit_instr(ctx, mul, dst, dst, src); + break; + case BPF_DIV: + case BPF_MOD: + b_off = b_imm(exit_idx, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_instr(ctx, beq, src, MIPS_R_ZERO, b_off); + emit_instr(ctx, movz, MIPS_R_V0, MIPS_R_ZERO, src); + emit_instr(ctx, divu, dst, src); + if (BPF_OP(insn->code) == BPF_DIV) + emit_instr(ctx, mflo, dst); + else + emit_instr(ctx, mfhi, dst); + break; + case BPF_LSH: + emit_instr(ctx, sllv, dst, dst, src); + break; + case BPF_RSH: + emit_instr(ctx, srlv, dst, dst, src); + break; + default: + pr_err("ALU_REG NOT HANDLED\n"); + return -EINVAL; + } + break; + case BPF_JMP | BPF_EXIT: + if (this_idx + 1 < exit_idx) { + b_off = b_imm(exit_idx, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_instr(ctx, beq, MIPS_R_ZERO, MIPS_R_ZERO, b_off); + emit_instr(ctx, nop); + } + break; + case BPF_JMP | BPF_JEQ | BPF_K: /* JMP_IMM */ + case BPF_JMP | BPF_JNE | BPF_K: /* JMP_IMM */ + cmp_eq = (BPF_OP(insn->code) == BPF_JEQ); + dst = ebpf_to_mips_reg(ctx, insn, dst_reg_fp_ok); + if (dst < 0) + return dst; + if (insn->imm == 0) { + src = MIPS_R_ZERO; + } else { + gen_imm_to_reg(insn, MIPS_R_AT, ctx); + src = MIPS_R_AT; + } + goto jeq_common; + case BPF_JMP | BPF_JEQ | BPF_X: /* JMP_REG */ + case BPF_JMP | BPF_JNE | BPF_X: + case BPF_JMP | BPF_JSGT | BPF_X: + case BPF_JMP | BPF_JSGE | BPF_X: + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JSET | BPF_X: + src = ebpf_to_mips_reg(ctx, insn, src_reg_no_fp); + dst = ebpf_to_mips_reg(ctx, insn, dst_reg); + if (src < 0 || dst < 0) + return -EINVAL; + td = get_reg_val_type(ctx, this_idx, insn->dst_reg); + ts = get_reg_val_type(ctx, this_idx, insn->src_reg); + if (td == REG_32BIT && ts != REG_32BIT) { + emit_instr(ctx, sll, MIPS_R_AT, src, 0); + src = MIPS_R_AT; + } else if (ts == REG_32BIT && td != REG_32BIT) { + emit_instr(ctx, sll, MIPS_R_AT, dst, 0); + dst = MIPS_R_AT; + } + if (BPF_OP(insn->code) == BPF_JSET) { + emit_instr(ctx, and, MIPS_R_AT, dst, src); + cmp_eq = false; + dst = MIPS_R_AT; + src = MIPS_R_ZERO; + } else if (BPF_OP(insn->code) == BPF_JSGT) { + emit_instr(ctx, dsubu, MIPS_R_AT, dst, src); + if ((insn + 1)->code == (BPF_JMP | BPF_EXIT) && insn->off == 1) { + b_off = b_imm(exit_idx, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_instr(ctx, blez, MIPS_R_AT, b_off); + emit_instr(ctx, nop); + return 2; /* We consumed the exit. */ + } + b_off = b_imm(this_idx + insn->off + 1, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_instr(ctx, bgtz, MIPS_R_AT, b_off); + emit_instr(ctx, nop); + break; + } else if (BPF_OP(insn->code) == BPF_JSGE) { + emit_instr(ctx, slt, MIPS_R_AT, dst, src); + cmp_eq = true; + dst = MIPS_R_AT; + src = MIPS_R_ZERO; + } else if (BPF_OP(insn->code) == BPF_JGT) { + /* dst or src could be AT */ + emit_instr(ctx, dsubu, MIPS_R_T8, dst, src); + emit_instr(ctx, sltu, MIPS_R_AT, dst, src); + /* SP known to be non-zero, movz becomes boolean not */ + emit_instr(ctx, movz, MIPS_R_T9, MIPS_R_SP, MIPS_R_T8); + emit_instr(ctx, movn, MIPS_R_T9, MIPS_R_ZERO, MIPS_R_T8); + emit_instr(ctx, or, MIPS_R_AT, MIPS_R_T9, MIPS_R_AT); + cmp_eq = true; + dst = MIPS_R_AT; + src = MIPS_R_ZERO; + } else if (BPF_OP(insn->code) == BPF_JGE) { + emit_instr(ctx, sltu, MIPS_R_AT, dst, src); + cmp_eq = true; + dst = MIPS_R_AT; + src = MIPS_R_ZERO; + } else { /* JNE/JEQ case */ + cmp_eq = (BPF_OP(insn->code) == BPF_JEQ); + } +jeq_common: + /* + * If the next insn is EXIT and we are jumping arround + * only it, invert the sense of the compare and + * conditionally jump to the exit. Poor man's branch + * chaining. + */ + if ((insn + 1)->code == (BPF_JMP | BPF_EXIT) && insn->off == 1) { + b_off = b_imm(exit_idx, ctx); + if (is_bad_offset(b_off)) { + target = j_target(ctx, exit_idx); + if (target == (unsigned int)-1) + return -E2BIG; + cmp_eq = !cmp_eq; + b_off = 4 * 3; + if (!(ctx->offsets[this_idx] & OFFSETS_B_CONV)) { + ctx->offsets[this_idx] |= OFFSETS_B_CONV; + ctx->long_b_conversion = 1; + } + } + + if (cmp_eq) + emit_instr(ctx, bne, dst, src, b_off); + else + emit_instr(ctx, beq, dst, src, b_off); + emit_instr(ctx, nop); + if (ctx->offsets[this_idx] & OFFSETS_B_CONV) { + emit_instr(ctx, j, target); + emit_instr(ctx, nop); + } + return 2; /* We consumed the exit. */ + } + b_off = b_imm(this_idx + insn->off + 1, ctx); + if (is_bad_offset(b_off)) { + target = j_target(ctx, this_idx + insn->off + 1); + if (target == (unsigned int)-1) + return -E2BIG; + cmp_eq = !cmp_eq; + b_off = 4 * 3; + if (!(ctx->offsets[this_idx] & OFFSETS_B_CONV)) { + ctx->offsets[this_idx] |= OFFSETS_B_CONV; + ctx->long_b_conversion = 1; + } + } + + if (cmp_eq) + emit_instr(ctx, beq, dst, src, b_off); + else + emit_instr(ctx, bne, dst, src, b_off); + emit_instr(ctx, nop); + if (ctx->offsets[this_idx] & OFFSETS_B_CONV) { + emit_instr(ctx, j, target); + emit_instr(ctx, nop); + } + break; + case BPF_JMP | BPF_JSGT | BPF_K: /* JMP_IMM */ + case BPF_JMP | BPF_JSGE | BPF_K: /* JMP_IMM */ + cmp_eq = (BPF_OP(insn->code) == BPF_JSGE); + dst = ebpf_to_mips_reg(ctx, insn, dst_reg_fp_ok); + if (dst < 0) + return dst; + + if (insn->imm == 0) { + if ((insn + 1)->code == (BPF_JMP | BPF_EXIT) && insn->off == 1) { + b_off = b_imm(exit_idx, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + if (cmp_eq) + emit_instr(ctx, bltz, dst, b_off); + else + emit_instr(ctx, blez, dst, b_off); + emit_instr(ctx, nop); + return 2; /* We consumed the exit. */ + } + b_off = b_imm(this_idx + insn->off + 1, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + if (cmp_eq) + emit_instr(ctx, bgez, dst, b_off); + else + emit_instr(ctx, bgtz, dst, b_off); + emit_instr(ctx, nop); + break; + } + /* + * only "LT" compare available, so we must use imm + 1 + * to generate "GT" + */ + t64s = insn->imm + (cmp_eq ? 0 : 1); + if (t64s >= S16_MIN && t64s <= S16_MAX) { + emit_instr(ctx, slti, MIPS_R_AT, dst, (int)t64s); + src = MIPS_R_AT; + dst = MIPS_R_ZERO; + cmp_eq = true; + goto jeq_common; + } + emit_const_to_reg(ctx, MIPS_R_AT, (u64)t64s); + emit_instr(ctx, slt, MIPS_R_AT, dst, MIPS_R_AT); + src = MIPS_R_AT; + dst = MIPS_R_ZERO; + cmp_eq = true; + goto jeq_common; + + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JGE | BPF_K: + cmp_eq = (BPF_OP(insn->code) == BPF_JGE); + dst = ebpf_to_mips_reg(ctx, insn, dst_reg_fp_ok); + if (dst < 0) + return dst; + /* + * only "LT" compare available, so we must use imm + 1 + * to generate "GT" + */ + t64s = (u64)(u32)(insn->imm) + (cmp_eq ? 0 : 1); + if (t64s >= 0 && t64s <= S16_MAX) { + emit_instr(ctx, sltiu, MIPS_R_AT, dst, (int)t64s); + src = MIPS_R_AT; + dst = MIPS_R_ZERO; + cmp_eq = true; + goto jeq_common; + } + emit_const_to_reg(ctx, MIPS_R_AT, (u64)t64s); + emit_instr(ctx, sltu, MIPS_R_AT, dst, MIPS_R_AT); + src = MIPS_R_AT; + dst = MIPS_R_ZERO; + cmp_eq = true; + goto jeq_common; + + case BPF_JMP | BPF_JSET | BPF_K: /* JMP_IMM */ + dst = ebpf_to_mips_reg(ctx, insn, dst_reg_fp_ok); + if (dst < 0) + return dst; + + if (use_bbit_insns() && hweight32((u32)insn->imm) == 1) { + if ((insn + 1)->code == (BPF_JMP | BPF_EXIT) && insn->off == 1) { + b_off = b_imm(exit_idx, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_instr(ctx, bbit0, dst, ffs((u32)insn->imm) - 1, b_off); + emit_instr(ctx, nop); + return 2; /* We consumed the exit. */ + } + b_off = b_imm(this_idx + insn->off + 1, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_instr(ctx, bbit1, dst, ffs((u32)insn->imm) - 1, b_off); + emit_instr(ctx, nop); + break; + } + t64 = (u32)insn->imm; + emit_const_to_reg(ctx, MIPS_R_AT, t64); + emit_instr(ctx, and, MIPS_R_AT, dst, MIPS_R_AT); + src = MIPS_R_AT; + dst = MIPS_R_ZERO; + cmp_eq = false; + goto jeq_common; + + case BPF_JMP | BPF_JA: + /* + * Prefer relative branch for easier debugging, but + * fall back if needed. + */ + b_off = b_imm(this_idx + insn->off + 1, ctx); + if (is_bad_offset(b_off)) { + target = j_target(ctx, this_idx + insn->off + 1); + if (target == (unsigned int)-1) + return -E2BIG; + emit_instr(ctx, j, target); + } else { + emit_instr(ctx, b, b_off); + } + emit_instr(ctx, nop); + break; + case BPF_LD | BPF_DW | BPF_IMM: + if (insn->src_reg != 0) + return -EINVAL; + dst = ebpf_to_mips_reg(ctx, insn, dst_reg); + if (dst < 0) + return dst; + t64 = ((u64)(u32)insn->imm) | ((u64)(insn + 1)->imm << 32); + emit_const_to_reg(ctx, dst, t64); + return 2; /* Double slot insn */ + + case BPF_JMP | BPF_CALL: + ctx->flags |= EBPF_SAVE_RA; + t64s = (s64)insn->imm + (s64)__bpf_call_base; + emit_const_to_reg(ctx, MIPS_R_T9, (u64)t64s); + emit_instr(ctx, jalr, MIPS_R_RA, MIPS_R_T9); + /* delay slot */ + emit_instr(ctx, nop); + break; + + case BPF_JMP | BPF_TAIL_CALL: + if (emit_bpf_tail_call(ctx, this_idx)) + return -EINVAL; + break; + + case BPF_LD | BPF_B | BPF_ABS: + case BPF_LD | BPF_H | BPF_ABS: + case BPF_LD | BPF_W | BPF_ABS: + case BPF_LD | BPF_DW | BPF_ABS: + ctx->flags |= EBPF_SAVE_RA; + + gen_imm_to_reg(insn, MIPS_R_A1, ctx); + emit_instr(ctx, addiu, MIPS_R_A2, MIPS_R_ZERO, size_to_len(insn)); + + if (insn->imm < 0) { + emit_const_to_reg(ctx, MIPS_R_T9, (u64)bpf_internal_load_pointer_neg_helper); + } else { + emit_const_to_reg(ctx, MIPS_R_T9, (u64)ool_skb_header_pointer); + emit_instr(ctx, daddiu, MIPS_R_A3, MIPS_R_SP, ctx->tmp_offset); + } + goto ld_skb_common; + + case BPF_LD | BPF_B | BPF_IND: + case BPF_LD | BPF_H | BPF_IND: + case BPF_LD | BPF_W | BPF_IND: + case BPF_LD | BPF_DW | BPF_IND: + ctx->flags |= EBPF_SAVE_RA; + src = ebpf_to_mips_reg(ctx, insn, src_reg_no_fp); + if (src < 0) + return src; + ts = get_reg_val_type(ctx, this_idx, insn->src_reg); + if (ts == REG_32BIT_ZERO_EX) { + /* sign extend */ + emit_instr(ctx, sll, MIPS_R_A1, src, 0); + src = MIPS_R_A1; + } + if (insn->imm >= S16_MIN && insn->imm <= S16_MAX) { + emit_instr(ctx, daddiu, MIPS_R_A1, src, insn->imm); + } else { + gen_imm_to_reg(insn, MIPS_R_AT, ctx); + emit_instr(ctx, daddu, MIPS_R_A1, MIPS_R_AT, src); + } + /* truncate to 32-bit int */ + emit_instr(ctx, sll, MIPS_R_A1, MIPS_R_A1, 0); + emit_instr(ctx, daddiu, MIPS_R_A3, MIPS_R_SP, ctx->tmp_offset); + emit_instr(ctx, slt, MIPS_R_AT, MIPS_R_A1, MIPS_R_ZERO); + + emit_const_to_reg(ctx, MIPS_R_T8, (u64)bpf_internal_load_pointer_neg_helper); + emit_const_to_reg(ctx, MIPS_R_T9, (u64)ool_skb_header_pointer); + emit_instr(ctx, addiu, MIPS_R_A2, MIPS_R_ZERO, size_to_len(insn)); + emit_instr(ctx, movn, MIPS_R_T9, MIPS_R_T8, MIPS_R_AT); + +ld_skb_common: + emit_instr(ctx, jalr, MIPS_R_RA, MIPS_R_T9); + /* delay slot move */ + emit_instr(ctx, daddu, MIPS_R_A0, MIPS_R_S0, MIPS_R_ZERO); + + /* Check the error value */ + b_off = b_imm(exit_idx, ctx); + if (is_bad_offset(b_off)) { + target = j_target(ctx, exit_idx); + if (target == (unsigned int)-1) + return -E2BIG; + + if (!(ctx->offsets[this_idx] & OFFSETS_B_CONV)) { + ctx->offsets[this_idx] |= OFFSETS_B_CONV; + ctx->long_b_conversion = 1; + } + emit_instr(ctx, bne, MIPS_R_V0, MIPS_R_ZERO, 4 * 3); + emit_instr(ctx, nop); + emit_instr(ctx, j, target); + emit_instr(ctx, nop); + } else { + emit_instr(ctx, beq, MIPS_R_V0, MIPS_R_ZERO, b_off); + emit_instr(ctx, nop); + } + +#ifdef __BIG_ENDIAN + need_swap = false; +#else + need_swap = true; +#endif + dst = MIPS_R_V0; + switch (BPF_SIZE(insn->code)) { + case BPF_B: + emit_instr(ctx, lbu, dst, 0, MIPS_R_V0); + break; + case BPF_H: + emit_instr(ctx, lhu, dst, 0, MIPS_R_V0); + if (need_swap) + emit_instr(ctx, wsbh, dst, dst); + break; + case BPF_W: + emit_instr(ctx, lw, dst, 0, MIPS_R_V0); + if (need_swap) { + emit_instr(ctx, wsbh, dst, dst); + emit_instr(ctx, rotr, dst, dst, 16); + } + break; + case BPF_DW: + emit_instr(ctx, ld, dst, 0, MIPS_R_V0); + if (need_swap) { + emit_instr(ctx, dsbh, dst, dst); + emit_instr(ctx, dshd, dst, dst); + } + break; + } + + break; + case BPF_ALU | BPF_END | BPF_FROM_BE: + case BPF_ALU | BPF_END | BPF_FROM_LE: + dst = ebpf_to_mips_reg(ctx, insn, dst_reg); + if (dst < 0) + return dst; + td = get_reg_val_type(ctx, this_idx, insn->dst_reg); + if (insn->imm == 64 && td == REG_32BIT) + emit_instr(ctx, dinsu, dst, MIPS_R_ZERO, 32, 32); + + if (insn->imm != 64 && + (td == REG_64BIT || td == REG_32BIT_ZERO_EX)) { + /* sign extend */ + emit_instr(ctx, sll, dst, dst, 0); + } + +#ifdef __BIG_ENDIAN + need_swap = (BPF_SRC(insn->code) == BPF_FROM_LE); +#else + need_swap = (BPF_SRC(insn->code) == BPF_FROM_BE); +#endif + if (insn->imm == 16) { + if (need_swap) + emit_instr(ctx, wsbh, dst, dst); + emit_instr(ctx, andi, dst, dst, 0xffff); + } else if (insn->imm == 32) { + if (need_swap) { + emit_instr(ctx, wsbh, dst, dst); + emit_instr(ctx, rotr, dst, dst, 16); + } + } else { /* 64-bit*/ + if (need_swap) { + emit_instr(ctx, dsbh, dst, dst); + emit_instr(ctx, dshd, dst, dst); + } + } + break; + + case BPF_ST | BPF_B | BPF_MEM: + case BPF_ST | BPF_H | BPF_MEM: + case BPF_ST | BPF_W | BPF_MEM: + case BPF_ST | BPF_DW | BPF_MEM: + if (insn->dst_reg == BPF_REG_10) { + ctx->flags |= EBPF_SEEN_FP; + dst = MIPS_R_SP; + mem_off = insn->off + MAX_BPF_STACK; + } else { + dst = ebpf_to_mips_reg(ctx, insn, dst_reg); + if (dst < 0) + return dst; + mem_off = insn->off; + } + gen_imm_to_reg(insn, MIPS_R_AT, ctx); + switch (BPF_SIZE(insn->code)) { + case BPF_B: + emit_instr(ctx, sb, MIPS_R_AT, mem_off, dst); + break; + case BPF_H: + emit_instr(ctx, sh, MIPS_R_AT, mem_off, dst); + break; + case BPF_W: + emit_instr(ctx, sw, MIPS_R_AT, mem_off, dst); + break; + case BPF_DW: + emit_instr(ctx, sd, MIPS_R_AT, mem_off, dst); + break; + } + break; + + case BPF_LDX | BPF_B | BPF_MEM: + case BPF_LDX | BPF_H | BPF_MEM: + case BPF_LDX | BPF_W | BPF_MEM: + case BPF_LDX | BPF_DW | BPF_MEM: + if (insn->src_reg == BPF_REG_10) { + ctx->flags |= EBPF_SEEN_FP; + src = MIPS_R_SP; + mem_off = insn->off + MAX_BPF_STACK; + } else { + src = ebpf_to_mips_reg(ctx, insn, src_reg_no_fp); + if (src < 0) + return src; + mem_off = insn->off; + } + dst = ebpf_to_mips_reg(ctx, insn, dst_reg); + if (dst < 0) + return dst; + switch (BPF_SIZE(insn->code)) { + case BPF_B: + emit_instr(ctx, lbu, dst, mem_off, src); + break; + case BPF_H: + emit_instr(ctx, lhu, dst, mem_off, src); + break; + case BPF_W: + emit_instr(ctx, lw, dst, mem_off, src); + break; + case BPF_DW: + emit_instr(ctx, ld, dst, mem_off, src); + break; + } + break; + + case BPF_STX | BPF_B | BPF_MEM: + case BPF_STX | BPF_H | BPF_MEM: + case BPF_STX | BPF_W | BPF_MEM: + case BPF_STX | BPF_DW | BPF_MEM: + case BPF_STX | BPF_W | BPF_XADD: + case BPF_STX | BPF_DW | BPF_XADD: + if (insn->dst_reg == BPF_REG_10) { + ctx->flags |= EBPF_SEEN_FP; + dst = MIPS_R_SP; + mem_off = insn->off + MAX_BPF_STACK; + } else { + dst = ebpf_to_mips_reg(ctx, insn, dst_reg); + if (dst < 0) + return dst; + mem_off = insn->off; + } + src = ebpf_to_mips_reg(ctx, insn, src_reg_no_fp); + if (src < 0) + return dst; + if (BPF_MODE(insn->code) == BPF_XADD) { + switch (BPF_SIZE(insn->code)) { + case BPF_W: + if (get_reg_val_type(ctx, this_idx, insn->src_reg) == REG_32BIT) { + emit_instr(ctx, sll, MIPS_R_AT, src, 0); + src = MIPS_R_AT; + } + emit_instr(ctx, ll, MIPS_R_T8, mem_off, dst); + emit_instr(ctx, addu, MIPS_R_T8, MIPS_R_T8, src); + emit_instr(ctx, sc, MIPS_R_T8, mem_off, dst); + /* + * On failure back up to LL (-4 + * instructions of 4 bytes each + */ + emit_instr(ctx, beq, MIPS_R_T8, MIPS_R_ZERO, -4 * 4); + emit_instr(ctx, nop); + break; + case BPF_DW: + if (get_reg_val_type(ctx, this_idx, insn->src_reg) == REG_32BIT) { + emit_instr(ctx, daddu, MIPS_R_AT, src, MIPS_R_ZERO); + emit_instr(ctx, dinsu, MIPS_R_AT, MIPS_R_ZERO, 32, 32); + src = MIPS_R_AT; + } + emit_instr(ctx, lld, MIPS_R_T8, mem_off, dst); + emit_instr(ctx, daddu, MIPS_R_T8, MIPS_R_T8, src); + emit_instr(ctx, scd, MIPS_R_T8, mem_off, dst); + emit_instr(ctx, beq, MIPS_R_T8, MIPS_R_ZERO, -4 * 4); + emit_instr(ctx, nop); + break; + } + } else { /* BPF_MEM */ + switch (BPF_SIZE(insn->code)) { + case BPF_B: + emit_instr(ctx, sb, src, mem_off, dst); + break; + case BPF_H: + emit_instr(ctx, sh, src, mem_off, dst); + break; + case BPF_W: + emit_instr(ctx, sw, src, mem_off, dst); + break; + case BPF_DW: + if (get_reg_val_type(ctx, this_idx, insn->src_reg) == REG_32BIT) { + emit_instr(ctx, daddu, MIPS_R_AT, src, MIPS_R_ZERO); + emit_instr(ctx, dinsu, MIPS_R_AT, MIPS_R_ZERO, 32, 32); + src = MIPS_R_AT; + } + emit_instr(ctx, sd, src, mem_off, dst); + break; + } + } + break; + + default: + pr_err("NOT HANDLED %d - (%02x)\n", + this_idx, (unsigned int)insn->code); + return -EINVAL; + } + return 1; +} + +#define RVT_VISITED_MASK 0xc000000000000000ull +#define RVT_FALL_THROUGH 0x4000000000000000ull +#define RVT_BRANCH_TAKEN 0x8000000000000000ull +#define RVT_DONE (RVT_FALL_THROUGH | RVT_BRANCH_TAKEN) + +static int build_int_body(struct jit_ctx *ctx) +{ + const struct bpf_prog *prog = ctx->skf; + const struct bpf_insn *insn; + int i, r; + + for (i = 0; i < prog->len; ) { + insn = prog->insnsi + i; + if ((ctx->reg_val_types[i] & RVT_VISITED_MASK) == 0) { + /* dead instruction, don't emit it. */ + i++; + continue; + } + + if (ctx->target == NULL) + ctx->offsets[i] = (ctx->offsets[i] & OFFSETS_B_CONV) | (ctx->idx * 4); + + r = build_one_insn(insn, ctx, i, prog->len); + if (r < 0) + return r; + i += r; + } + /* epilogue offset */ + if (ctx->target == NULL) + ctx->offsets[i] = ctx->idx * 4; + + /* + * All exits have an offset of the epilogue, some offsets may + * not have been set due to banch-around threading, so set + * them now. + */ + if (ctx->target == NULL) + for (i = 0; i < prog->len; i++) { + insn = prog->insnsi + i; + if (insn->code == (BPF_JMP | BPF_EXIT)) + ctx->offsets[i] = ctx->idx * 4; + } + return 0; +} + +/* return the last idx processed, or negative for error */ +static int reg_val_propagate_range(struct jit_ctx *ctx, u64 initial_rvt, + int start_idx, bool follow_taken) +{ + const struct bpf_prog *prog = ctx->skf; + const struct bpf_insn *insn; + u64 exit_rvt = initial_rvt; + u64 *rvt = ctx->reg_val_types; + int idx; + int reg; + + for (idx = start_idx; idx < prog->len; idx++) { + rvt[idx] = (rvt[idx] & RVT_VISITED_MASK) | exit_rvt; + insn = prog->insnsi + idx; + switch (BPF_CLASS(insn->code)) { + case BPF_ALU: + switch (BPF_OP(insn->code)) { + case BPF_ADD: + case BPF_SUB: + case BPF_MUL: + case BPF_DIV: + case BPF_OR: + case BPF_AND: + case BPF_LSH: + case BPF_RSH: + case BPF_NEG: + case BPF_MOD: + case BPF_XOR: + set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT); + break; + case BPF_MOV: + if (BPF_SRC(insn->code)) { + set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT); + } else { + /* IMM to REG move*/ + if (insn->imm >= 0) + set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT_POS); + else + set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT); + } + break; + case BPF_END: + if (insn->imm == 64) + set_reg_val_type(&exit_rvt, insn->dst_reg, REG_64BIT); + else if (insn->imm == 32) + set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT); + else /* insn->imm == 16 */ + set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT_POS); + break; + } + rvt[idx] |= RVT_DONE; + break; + case BPF_ALU64: + switch (BPF_OP(insn->code)) { + case BPF_MOV: + if (BPF_SRC(insn->code)) { + /* REG to REG move*/ + set_reg_val_type(&exit_rvt, insn->dst_reg, REG_64BIT); + } else { + /* IMM to REG move*/ + if (insn->imm >= 0) + set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT_POS); + else + set_reg_val_type(&exit_rvt, insn->dst_reg, REG_64BIT_32BIT); + } + break; + default: + set_reg_val_type(&exit_rvt, insn->dst_reg, REG_64BIT); + } + rvt[idx] |= RVT_DONE; + break; + case BPF_LD: + switch (BPF_SIZE(insn->code)) { + case BPF_DW: + if (BPF_MODE(insn->code) == BPF_IMM) { + s64 val; + + val = (s64)((u32)insn->imm | ((u64)(insn + 1)->imm << 32)); + if (val > 0 && val <= S32_MAX) + set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT_POS); + else if (val >= S32_MIN && val <= S32_MAX) + set_reg_val_type(&exit_rvt, insn->dst_reg, REG_64BIT_32BIT); + else + set_reg_val_type(&exit_rvt, insn->dst_reg, REG_64BIT); + rvt[idx] |= RVT_DONE; + idx++; + } else { + set_reg_val_type(&exit_rvt, insn->dst_reg, REG_64BIT); + } + break; + case BPF_B: + case BPF_H: + set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT_POS); + break; + case BPF_W: + if (BPF_MODE(insn->code) == BPF_IMM) + set_reg_val_type(&exit_rvt, insn->dst_reg, + insn->imm >= 0 ? REG_32BIT_POS : REG_32BIT); + else + set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT); + break; + } + rvt[idx] |= RVT_DONE; + break; + case BPF_LDX: + switch (BPF_SIZE(insn->code)) { + case BPF_DW: + set_reg_val_type(&exit_rvt, insn->dst_reg, REG_64BIT); + break; + case BPF_B: + case BPF_H: + set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT_POS); + break; + case BPF_W: + set_reg_val_type(&exit_rvt, insn->dst_reg, REG_32BIT); + break; + } + rvt[idx] |= RVT_DONE; + break; + case BPF_JMP: + switch (BPF_OP(insn->code)) { + case BPF_EXIT: + rvt[idx] = RVT_DONE | exit_rvt; + rvt[prog->len] = exit_rvt; + return idx; + case BPF_JA: + rvt[idx] |= RVT_DONE; + idx += insn->off; + break; + case BPF_JEQ: + case BPF_JGT: + case BPF_JGE: + case BPF_JSET: + case BPF_JNE: + case BPF_JSGT: + case BPF_JSGE: + if (follow_taken) { + rvt[idx] |= RVT_BRANCH_TAKEN; + idx += insn->off; + follow_taken = false; + } else { + rvt[idx] |= RVT_FALL_THROUGH; + } + break; + case BPF_CALL: + set_reg_val_type(&exit_rvt, BPF_REG_0, REG_64BIT); + /* Upon call return, argument registers are clobbered. */ + for (reg = BPF_REG_0; reg <= BPF_REG_5; reg++) + set_reg_val_type(&exit_rvt, reg, REG_64BIT); + + rvt[idx] |= RVT_DONE; + break; + default: + WARN(1, "Unhandled BPF_JMP case.\n"); + rvt[idx] |= RVT_DONE; + break; + } + break; + default: + rvt[idx] |= RVT_DONE; + break; + } + } + return idx; +} + +/* + * Track the value range (i.e. 32-bit vs. 64-bit) of each register at + * each eBPF insn. This allows unneeded sign and zero extension + * operations to be omitted. + * + * Doesn't handle yet confluence of control paths with conflicting + * ranges, but it is good enough for most sane code. + */ +static int reg_val_propagate(struct jit_ctx *ctx) +{ + const struct bpf_prog *prog = ctx->skf; + u64 exit_rvt; + int reg; + int i; + + /* + * 11 registers * 3 bits/reg leaves top bits free for other + * uses. Bit-62..63 used to see if we have visited an insn. + */ + exit_rvt = 0; + + /* Upon entry, argument registers are 64-bit. */ + for (reg = BPF_REG_1; reg <= BPF_REG_5; reg++) + set_reg_val_type(&exit_rvt, reg, REG_64BIT); + + /* + * First follow all conditional branches on the fall-through + * edge of control flow.. + */ + reg_val_propagate_range(ctx, exit_rvt, 0, false); +restart_search: + /* + * Then repeatedly find the first conditional branch where + * both edges of control flow have not been taken, and follow + * the branch taken edge. We will end up restarting the + * search once per conditional branch insn. + */ + for (i = 0; i < prog->len; i++) { + u64 rvt = ctx->reg_val_types[i]; + + if ((rvt & RVT_VISITED_MASK) == RVT_DONE || + (rvt & RVT_VISITED_MASK) == 0) + continue; + if ((rvt & RVT_VISITED_MASK) == RVT_FALL_THROUGH) { + reg_val_propagate_range(ctx, rvt & ~RVT_VISITED_MASK, i, true); + } else { /* RVT_BRANCH_TAKEN */ + WARN(1, "Unexpected RVT_BRANCH_TAKEN case.\n"); + reg_val_propagate_range(ctx, rvt & ~RVT_VISITED_MASK, i, false); + } + goto restart_search; + } + /* + * Eventually all conditional branches have been followed on + * both branches and we are done. Any insn that has not been + * visited at this point is dead. + */ + + return 0; +} + +static void jit_fill_hole(void *area, unsigned int size) +{ + u32 *p; + + /* We are guaranteed to have aligned memory. */ + for (p = area; size >= sizeof(u32); size -= sizeof(u32)) + uasm_i_break(&p, BRK_BUG); /* Increments p */ +} + +struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) +{ + struct bpf_prog *orig_prog = prog; + bool tmp_blinded = false; + struct bpf_prog *tmp; + struct bpf_binary_header *header = NULL; + struct jit_ctx ctx; + unsigned int image_size; + u8 *image_ptr; + + if (!bpf_jit_enable || !cpu_has_mips64r2) + return prog; + + tmp = bpf_jit_blind_constants(prog); + /* If blinding was requested and we failed during blinding, + * we must fall back to the interpreter. + */ + if (IS_ERR(tmp)) + return orig_prog; + if (tmp != prog) { + tmp_blinded = true; + prog = tmp; + } + + memset(&ctx, 0, sizeof(ctx)); + + ctx.offsets = kcalloc(prog->len + 1, sizeof(*ctx.offsets), GFP_KERNEL); + if (ctx.offsets == NULL) + goto out_err; + + ctx.reg_val_types = kcalloc(prog->len + 1, sizeof(*ctx.reg_val_types), GFP_KERNEL); + if (ctx.reg_val_types == NULL) + goto out_err; + + ctx.skf = prog; + + if (reg_val_propagate(&ctx)) + goto out_err; + + /* + * First pass discovers used resources and instruction offsets + * assuming short branches are used. + */ + if (build_int_body(&ctx)) + goto out_err; + + /* + * If no calls are made (EBPF_SAVE_RA), then tail call count + * in $v1, else we must save in n$s4. + */ + if (ctx.flags & EBPF_SEEN_TC) { + if (ctx.flags & EBPF_SAVE_RA) + ctx.flags |= EBPF_SAVE_S4; + else + ctx.flags |= EBPF_TCC_IN_V1; + } + + /* + * Second pass generates offsets, if any branches are out of + * range a jump-around long sequence is generated, and we have + * to try again from the beginning to generate the new + * offsets. This is done until no additional conversions are + * necessary. + */ + do { + ctx.idx = 0; + ctx.gen_b_offsets = 1; + ctx.long_b_conversion = 0; + if (gen_int_prologue(&ctx)) + goto out_err; + if (build_int_body(&ctx)) + goto out_err; + if (build_int_epilogue(&ctx, MIPS_R_RA)) + goto out_err; + } while (ctx.long_b_conversion); + + image_size = 4 * ctx.idx; + + header = bpf_jit_binary_alloc(image_size, &image_ptr, + sizeof(u32), jit_fill_hole); + if (header == NULL) + goto out_err; + + ctx.target = (u32 *)image_ptr; + + /* Third pass generates the code */ + ctx.idx = 0; + if (gen_int_prologue(&ctx)) + goto out_err; + if (build_int_body(&ctx)) + goto out_err; + if (build_int_epilogue(&ctx, MIPS_R_RA)) + goto out_err; + + /* Update the icache */ + flush_icache_range((unsigned long)ctx.target, + (unsigned long)(ctx.target + ctx.idx * sizeof(u32))); + + if (bpf_jit_enable > 1) + /* Dump JIT code */ + bpf_jit_dump(prog->len, image_size, 2, ctx.target); + + bpf_jit_binary_lock_ro(header); + prog->bpf_func = (void *)ctx.target; + prog->jited = 1; + prog->jited_len = image_size; +out_normal: + if (tmp_blinded) + bpf_jit_prog_release_other(prog, prog == orig_prog ? + tmp : orig_prog); + kfree(ctx.offsets); + kfree(ctx.reg_val_types); + + return prog; + +out_err: + prog = orig_prog; + if (header) + bpf_jit_binary_free(header); + goto out_normal; +} diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig index 0695ce047d56..34fc9bbfca9e 100644 --- a/arch/powerpc/configs/powernv_defconfig +++ b/arch/powerpc/configs/powernv_defconfig @@ -293,7 +293,8 @@ CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_STACK_USAGE=y CONFIG_DEBUG_STACKOVERFLOW=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y +CONFIG_HARDLOCKUP_DETECTOR=y CONFIG_LATENCYTOP=y CONFIG_SCHED_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 5175028c56ce..c5246d29f385 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -324,7 +324,8 @@ CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_STACK_USAGE=y CONFIG_DEBUG_STACKOVERFLOW=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y +CONFIG_HARDLOCKUP_DETECTOR=y CONFIG_DEBUG_MUTEXES=y CONFIG_LATENCYTOP=y CONFIG_SCHED_TRACER=y diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index 1a61aa20dfba..fd5d98a0b95c 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -291,7 +291,8 @@ CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_STACK_USAGE=y CONFIG_DEBUG_STACKOVERFLOW=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y +CONFIG_HARDLOCKUP_DETECTOR=y CONFIG_LATENCYTOP=y CONFIG_SCHED_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 49d8422767b4..e925c1c99c71 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -223,17 +223,27 @@ system_call_exit: andi. r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK) bne- .Lsyscall_exit_work - /* If MSR_FP and MSR_VEC are set in user msr, then no need to restore */ - li r7,MSR_FP + andi. r0,r8,MSR_FP + beq 2f #ifdef CONFIG_ALTIVEC - oris r7,r7,MSR_VEC@h + andis. r0,r8,MSR_VEC@h + bne 3f #endif - and r0,r8,r7 - cmpd r0,r7 - bne .Lsyscall_restore_math -.Lsyscall_restore_math_cont: +2: addi r3,r1,STACK_FRAME_OVERHEAD +#ifdef CONFIG_PPC_BOOK3S + li r10,MSR_RI + mtmsrd r10,1 /* Restore RI */ +#endif + bl restore_math +#ifdef CONFIG_PPC_BOOK3S + li r11,0 + mtmsrd r11,1 +#endif + ld r8,_MSR(r1) + ld r3,RESULT(r1) + li r11,-MAX_ERRNO - cmpld r3,r11 +3: cmpld r3,r11 ld r5,_CCR(r1) bge- .Lsyscall_error .Lsyscall_error_cont: @@ -267,40 +277,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) std r5,_CCR(r1) b .Lsyscall_error_cont -.Lsyscall_restore_math: - /* - * Some initial tests from restore_math to avoid the heavyweight - * C code entry and MSR manipulations. - */ - LOAD_REG_IMMEDIATE(r0, MSR_TS_MASK) - and. r0,r0,r8 - bne 1f - - ld r7,PACACURRENT(r13) - lbz r0,THREAD+THREAD_LOAD_FP(r7) -#ifdef CONFIG_ALTIVEC - lbz r6,THREAD+THREAD_LOAD_VEC(r7) - add r0,r0,r6 -#endif - cmpdi r0,0 - beq .Lsyscall_restore_math_cont - -1: addi r3,r1,STACK_FRAME_OVERHEAD -#ifdef CONFIG_PPC_BOOK3S - li r10,MSR_RI - mtmsrd r10,1 /* Restore RI */ -#endif - bl restore_math -#ifdef CONFIG_PPC_BOOK3S - li r11,0 - mtmsrd r11,1 -#endif - /* Restore volatiles, reload MSR from updated one */ - ld r8,_MSR(r1) - ld r3,RESULT(r1) - li r11,-MAX_ERRNO - b .Lsyscall_restore_math_cont - /* Traced system call support */ .Lsyscall_dotrace: bl save_nvgprs diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 9f3e2c932dcc..ec480966f9bf 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -511,10 +511,6 @@ void restore_math(struct pt_regs *regs) { unsigned long msr; - /* - * Syscall exit makes a similar initial check before branching - * to restore_math. Keep them in synch. - */ if (!msr_tm_active(regs->msr) && !current->thread.load_fp && !loadvec(current->thread)) return; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index cf0e1245b8cc..8d3320562c70 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -351,7 +351,7 @@ static void nmi_ipi_lock_start(unsigned long *flags) hard_irq_disable(); while (atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) { raw_local_irq_restore(*flags); - cpu_relax(); + spin_until_cond(atomic_read(&__nmi_ipi_lock) == 0); raw_local_irq_save(*flags); hard_irq_disable(); } @@ -360,7 +360,7 @@ static void nmi_ipi_lock_start(unsigned long *flags) static void nmi_ipi_lock(void) { while (atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) - cpu_relax(); + spin_until_cond(atomic_read(&__nmi_ipi_lock) == 0); } static void nmi_ipi_unlock(void) @@ -475,7 +475,7 @@ int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us) nmi_ipi_lock_start(&flags); while (nmi_ipi_busy_count) { nmi_ipi_unlock_end(&flags); - cpu_relax(); + spin_until_cond(nmi_ipi_busy_count == 0); nmi_ipi_lock_start(&flags); } diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index b67f8b03a32d..34721a257a77 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -71,15 +71,20 @@ static inline void wd_smp_lock(unsigned long *flags) * This may be called from low level interrupt handlers at some * point in future. */ - local_irq_save(*flags); - while (unlikely(test_and_set_bit_lock(0, &__wd_smp_lock))) - cpu_relax(); + raw_local_irq_save(*flags); + hard_irq_disable(); /* Make it soft-NMI safe */ + while (unlikely(test_and_set_bit_lock(0, &__wd_smp_lock))) { + raw_local_irq_restore(*flags); + spin_until_cond(!test_bit(0, &__wd_smp_lock)); + raw_local_irq_save(*flags); + hard_irq_disable(); + } } static inline void wd_smp_unlock(unsigned long *flags) { clear_bit_unlock(0, &__wd_smp_lock); - local_irq_restore(*flags); + raw_local_irq_restore(*flags); } static void wd_lockup_ipi(struct pt_regs *regs) @@ -96,10 +101,10 @@ static void wd_lockup_ipi(struct pt_regs *regs) nmi_panic(regs, "Hard LOCKUP"); } -static void set_cpu_stuck(int cpu, u64 tb) +static void set_cpumask_stuck(const struct cpumask *cpumask, u64 tb) { - cpumask_set_cpu(cpu, &wd_smp_cpus_stuck); - cpumask_clear_cpu(cpu, &wd_smp_cpus_pending); + cpumask_or(&wd_smp_cpus_stuck, &wd_smp_cpus_stuck, cpumask); + cpumask_andnot(&wd_smp_cpus_pending, &wd_smp_cpus_pending, cpumask); if (cpumask_empty(&wd_smp_cpus_pending)) { wd_smp_last_reset_tb = tb; cpumask_andnot(&wd_smp_cpus_pending, @@ -107,6 +112,10 @@ static void set_cpu_stuck(int cpu, u64 tb) &wd_smp_cpus_stuck); } } +static void set_cpu_stuck(int cpu, u64 tb) +{ + set_cpumask_stuck(cpumask_of(cpu), tb); +} static void watchdog_smp_panic(int cpu, u64 tb) { @@ -135,11 +144,9 @@ static void watchdog_smp_panic(int cpu, u64 tb) } smp_flush_nmi_ipi(1000000); - /* Take the stuck CPU out of the watch group */ - for_each_cpu(c, &wd_smp_cpus_pending) - set_cpu_stuck(c, tb); + /* Take the stuck CPUs out of the watch group */ + set_cpumask_stuck(&wd_smp_cpus_pending, tb); -out: wd_smp_unlock(&flags); printk_safe_flush(); @@ -152,6 +159,11 @@ out: if (hardlockup_panic) nmi_panic(NULL, "Hard LOCKUP"); + + return; + +out: + wd_smp_unlock(&flags); } static void wd_smp_clear_cpu_pending(int cpu, u64 tb) @@ -258,9 +270,11 @@ static void wd_timer_fn(unsigned long data) void arch_touch_nmi_watchdog(void) { + unsigned long ticks = tb_ticks_per_usec * wd_timer_period_ms * 1000; int cpu = smp_processor_id(); - watchdog_timer_interrupt(cpu); + if (get_tb() - per_cpu(wd_timer_tb, cpu) >= ticks) + watchdog_timer_interrupt(cpu); } EXPORT_SYMBOL(arch_touch_nmi_watchdog); @@ -283,6 +297,8 @@ static void stop_watchdog_timer_on(unsigned int cpu) static int start_wd_on_cpu(unsigned int cpu) { + unsigned long flags; + if (cpumask_test_cpu(cpu, &wd_cpus_enabled)) { WARN_ON(1); return 0; @@ -297,12 +313,14 @@ static int start_wd_on_cpu(unsigned int cpu) if (!cpumask_test_cpu(cpu, &watchdog_cpumask)) return 0; + wd_smp_lock(&flags); cpumask_set_cpu(cpu, &wd_cpus_enabled); if (cpumask_weight(&wd_cpus_enabled) == 1) { cpumask_set_cpu(cpu, &wd_smp_cpus_pending); wd_smp_last_reset_tb = get_tb(); } - smp_wmb(); + wd_smp_unlock(&flags); + start_watchdog_timer_on(cpu); return 0; @@ -310,12 +328,17 @@ static int start_wd_on_cpu(unsigned int cpu) static int stop_wd_on_cpu(unsigned int cpu) { + unsigned long flags; + if (!cpumask_test_cpu(cpu, &wd_cpus_enabled)) return 0; /* Can happen in CPU unplug case */ stop_watchdog_timer_on(cpu); + wd_smp_lock(&flags); cpumask_clear_cpu(cpu, &wd_cpus_enabled); + wd_smp_unlock(&flags); + wd_smp_clear_cpu_pending(cpu, get_tb()); return 0; diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index 2abee070373f..a553aeea7af6 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -56,6 +56,7 @@ u64 pnv_first_deep_stop_state = MAX_STOP_STATE; */ static u64 pnv_deepest_stop_psscr_val; static u64 pnv_deepest_stop_psscr_mask; +static u64 pnv_deepest_stop_flag; static bool deepest_stop_found; static int pnv_save_sprs_for_deep_states(void) @@ -185,8 +186,40 @@ static void pnv_alloc_idle_core_states(void) update_subcore_sibling_mask(); - if (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT) - pnv_save_sprs_for_deep_states(); + if (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT) { + int rc = pnv_save_sprs_for_deep_states(); + + if (likely(!rc)) + return; + + /* + * The stop-api is unable to restore hypervisor + * resources on wakeup from platform idle states which + * lose full context. So disable such states. + */ + supported_cpuidle_states &= ~OPAL_PM_LOSE_FULL_CONTEXT; + pr_warn("cpuidle-powernv: Disabling idle states that lose full context\n"); + pr_warn("cpuidle-powernv: Idle power-savings, CPU-Hotplug affected\n"); + + if (cpu_has_feature(CPU_FTR_ARCH_300) && + (pnv_deepest_stop_flag & OPAL_PM_LOSE_FULL_CONTEXT)) { + /* + * Use the default stop state for CPU-Hotplug + * if available. + */ + if (default_stop_found) { + pnv_deepest_stop_psscr_val = + pnv_default_stop_val; + pnv_deepest_stop_psscr_mask = + pnv_default_stop_mask; + pr_warn("cpuidle-powernv: Offlined CPUs will stop with psscr = 0x%016llx\n", + pnv_deepest_stop_psscr_val); + } else { /* Fallback to snooze loop for CPU-Hotplug */ + deepest_stop_found = false; + pr_warn("cpuidle-powernv: Offlined CPUs will busy wait\n"); + } + } + } } u32 pnv_get_supported_cpuidle_states(void) @@ -375,7 +408,8 @@ unsigned long pnv_cpu_offline(unsigned int cpu) pnv_deepest_stop_psscr_val; srr1 = power9_idle_stop(psscr); - } else if (idle_states & OPAL_PM_WINKLE_ENABLED) { + } else if ((idle_states & OPAL_PM_WINKLE_ENABLED) && + (idle_states & OPAL_PM_LOSE_FULL_CONTEXT)) { srr1 = power7_idle_insn(PNV_THREAD_WINKLE); } else if ((idle_states & OPAL_PM_SLEEP_ENABLED) || (idle_states & OPAL_PM_SLEEP_ENABLED_ER1)) { @@ -553,6 +587,7 @@ static int __init pnv_power9_idle_init(struct device_node *np, u32 *flags, max_residency_ns = residency_ns[i]; pnv_deepest_stop_psscr_val = psscr_val[i]; pnv_deepest_stop_psscr_mask = psscr_mask[i]; + pnv_deepest_stop_flag = flags[i]; deepest_stop_found = true; } diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index 7317b3108a88..2eb8ff0d6fca 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -47,10 +47,9 @@ struct mmu_table_batch { extern void tlb_table_flush(struct mmu_gather *tlb); extern void tlb_remove_table(struct mmu_gather *tlb, void *table); -static inline void tlb_gather_mmu(struct mmu_gather *tlb, - struct mm_struct *mm, - unsigned long start, - unsigned long end) +static inline void +arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, + unsigned long start, unsigned long end) { tlb->mm = mm; tlb->start = start; @@ -76,9 +75,15 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb) tlb_flush_mmu_free(tlb); } -static inline void tlb_finish_mmu(struct mmu_gather *tlb, - unsigned long start, unsigned long end) +static inline void +arch_tlb_finish_mmu(struct mmu_gather *tlb, + unsigned long start, unsigned long end, bool force) { + if (force) { + tlb->start = start; + tlb->end = end; + } + tlb_flush_mmu(tlb); } diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 01c6fbc3e85b..1803797fc885 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -1253,7 +1253,8 @@ static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp) insn_count = bpf_jit_insn(jit, fp, i); if (insn_count < 0) return -1; - jit->addrs[i + 1] = jit->prg; /* Next instruction address */ + /* Next instruction address */ + jit->addrs[i + insn_count] = jit->prg; } bpf_jit_epilogue(jit); diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h index 46e0d635e36f..51a8bc967e75 100644 --- a/arch/sh/include/asm/tlb.h +++ b/arch/sh/include/asm/tlb.h @@ -36,7 +36,8 @@ static inline void init_tlb_gather(struct mmu_gather *tlb) } static inline void -tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end) +arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, + unsigned long start, unsigned long end) { tlb->mm = mm; tlb->start = start; @@ -47,9 +48,10 @@ tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start } static inline void -tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) +arch_tlb_finish_mmu(struct mmu_gather *tlb, + unsigned long start, unsigned long end, bool force) { - if (tlb->fullmm) + if (tlb->fullmm || force) flush_tlb_mm(tlb->mm); /* keep the page table cache within bounds */ diff --git a/arch/sparc/include/asm/spitfire.h b/arch/sparc/include/asm/spitfire.h index 1d8321c827a8..1b1286d05069 100644 --- a/arch/sparc/include/asm/spitfire.h +++ b/arch/sparc/include/asm/spitfire.h @@ -47,10 +47,26 @@ #define SUN4V_CHIP_NIAGARA5 0x05 #define SUN4V_CHIP_SPARC_M6 0x06 #define SUN4V_CHIP_SPARC_M7 0x07 +#define SUN4V_CHIP_SPARC_M8 0x08 #define SUN4V_CHIP_SPARC64X 0x8a #define SUN4V_CHIP_SPARC_SN 0x8b #define SUN4V_CHIP_UNKNOWN 0xff +/* + * The following CPU_ID_xxx constants are used + * to identify the CPU type in the setup phase + * (see head_64.S) + */ +#define CPU_ID_NIAGARA1 ('1') +#define CPU_ID_NIAGARA2 ('2') +#define CPU_ID_NIAGARA3 ('3') +#define CPU_ID_NIAGARA4 ('4') +#define CPU_ID_NIAGARA5 ('5') +#define CPU_ID_M6 ('6') +#define CPU_ID_M7 ('7') +#define CPU_ID_M8 ('8') +#define CPU_ID_SONOMA1 ('N') + #ifndef __ASSEMBLY__ enum ultra_tlb_layout { diff --git a/arch/sparc/kernel/cpu.c b/arch/sparc/kernel/cpu.c index 493e023a468a..ef4f18f7a674 100644 --- a/arch/sparc/kernel/cpu.c +++ b/arch/sparc/kernel/cpu.c @@ -506,6 +506,12 @@ static void __init sun4v_cpu_probe(void) sparc_pmu_type = "sparc-m7"; break; + case SUN4V_CHIP_SPARC_M8: + sparc_cpu_type = "SPARC-M8"; + sparc_fpu_type = "SPARC-M8 integrated FPU"; + sparc_pmu_type = "sparc-m8"; + break; + case SUN4V_CHIP_SPARC_SN: sparc_cpu_type = "SPARC-SN"; sparc_fpu_type = "SPARC-SN integrated FPU"; diff --git a/arch/sparc/kernel/cpumap.c b/arch/sparc/kernel/cpumap.c index 45c820e1cba5..90d550bbfeef 100644 --- a/arch/sparc/kernel/cpumap.c +++ b/arch/sparc/kernel/cpumap.c @@ -328,6 +328,7 @@ static int iterate_cpu(struct cpuinfo_tree *t, unsigned int root_index) case SUN4V_CHIP_NIAGARA5: case SUN4V_CHIP_SPARC_M6: case SUN4V_CHIP_SPARC_M7: + case SUN4V_CHIP_SPARC_M8: case SUN4V_CHIP_SPARC_SN: case SUN4V_CHIP_SPARC64X: rover_inc_table = niagara_iterate_method; diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S index 41a407328667..78e0211753d2 100644 --- a/arch/sparc/kernel/head_64.S +++ b/arch/sparc/kernel/head_64.S @@ -424,22 +424,25 @@ EXPORT_SYMBOL(sun4v_chip_type) nop 70: ldub [%g1 + 7], %g2 - cmp %g2, '3' + cmp %g2, CPU_ID_NIAGARA3 be,pt %xcc, 5f mov SUN4V_CHIP_NIAGARA3, %g4 - cmp %g2, '4' + cmp %g2, CPU_ID_NIAGARA4 be,pt %xcc, 5f mov SUN4V_CHIP_NIAGARA4, %g4 - cmp %g2, '5' + cmp %g2, CPU_ID_NIAGARA5 be,pt %xcc, 5f mov SUN4V_CHIP_NIAGARA5, %g4 - cmp %g2, '6' + cmp %g2, CPU_ID_M6 be,pt %xcc, 5f mov SUN4V_CHIP_SPARC_M6, %g4 - cmp %g2, '7' + cmp %g2, CPU_ID_M7 be,pt %xcc, 5f mov SUN4V_CHIP_SPARC_M7, %g4 - cmp %g2, 'N' + cmp %g2, CPU_ID_M8 + be,pt %xcc, 5f + mov SUN4V_CHIP_SPARC_M8, %g4 + cmp %g2, CPU_ID_SONOMA1 be,pt %xcc, 5f mov SUN4V_CHIP_SPARC_SN, %g4 ba,pt %xcc, 49f @@ -448,10 +451,10 @@ EXPORT_SYMBOL(sun4v_chip_type) 91: sethi %hi(prom_cpu_compatible), %g1 or %g1, %lo(prom_cpu_compatible), %g1 ldub [%g1 + 17], %g2 - cmp %g2, '1' + cmp %g2, CPU_ID_NIAGARA1 be,pt %xcc, 5f mov SUN4V_CHIP_NIAGARA1, %g4 - cmp %g2, '2' + cmp %g2, CPU_ID_NIAGARA2 be,pt %xcc, 5f mov SUN4V_CHIP_NIAGARA2, %g4 @@ -602,6 +605,9 @@ niagara_tlb_fixup: cmp %g1, SUN4V_CHIP_SPARC_M7 be,pt %xcc, niagara4_patch nop + cmp %g1, SUN4V_CHIP_SPARC_M8 + be,pt %xcc, niagara4_patch + nop cmp %g1, SUN4V_CHIP_SPARC_SN be,pt %xcc, niagara4_patch nop diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index 4d9c3e13c150..150ee7d4b059 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -288,10 +288,17 @@ static void __init sun4v_patch(void) sun4v_patch_2insn_range(&__sun4v_2insn_patch, &__sun4v_2insn_patch_end); - if (sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || - sun4v_chip_type == SUN4V_CHIP_SPARC_SN) + + switch (sun4v_chip_type) { + case SUN4V_CHIP_SPARC_M7: + case SUN4V_CHIP_SPARC_M8: + case SUN4V_CHIP_SPARC_SN: sun_m7_patch_2insn_range(&__sun_m7_2insn_patch, &__sun_m7_2insn_patch_end); + break; + default: + break; + } sun4v_hvapi_init(); } @@ -529,6 +536,7 @@ static void __init init_sparc64_elf_hwcap(void) sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M8 || sun4v_chip_type == SUN4V_CHIP_SPARC_SN || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= HWCAP_SPARC_BLKINIT; @@ -538,6 +546,7 @@ static void __init init_sparc64_elf_hwcap(void) sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M8 || sun4v_chip_type == SUN4V_CHIP_SPARC_SN || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= HWCAP_SPARC_N2; @@ -568,6 +577,7 @@ static void __init init_sparc64_elf_hwcap(void) sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M8 || sun4v_chip_type == SUN4V_CHIP_SPARC_SN || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= (AV_SPARC_VIS | AV_SPARC_VIS2 | @@ -578,6 +588,7 @@ static void __init init_sparc64_elf_hwcap(void) sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || + sun4v_chip_type == SUN4V_CHIP_SPARC_M8 || sun4v_chip_type == SUN4V_CHIP_SPARC_SN || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= (AV_SPARC_VIS3 | AV_SPARC_HPC | diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index fed73f14aa49..afa0099f3748 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -1944,12 +1944,22 @@ static void __init setup_page_offset(void) break; case SUN4V_CHIP_SPARC_M7: case SUN4V_CHIP_SPARC_SN: - default: /* M7 and later support 52-bit virtual addresses. */ sparc64_va_hole_top = 0xfff8000000000000UL; sparc64_va_hole_bottom = 0x0008000000000000UL; max_phys_bits = 49; break; + case SUN4V_CHIP_SPARC_M8: + default: + /* M8 and later support 54-bit virtual addresses. + * However, restricting M8 and above VA bits to 53 + * as 4-level page table cannot support more than + * 53 VA bits. + */ + sparc64_va_hole_top = 0xfff0000000000000UL; + sparc64_va_hole_bottom = 0x0010000000000000UL; + max_phys_bits = 51; + break; } } @@ -2161,6 +2171,7 @@ static void __init sun4v_linear_pte_xor_finalize(void) */ switch (sun4v_chip_type) { case SUN4V_CHIP_SPARC_M7: + case SUN4V_CHIP_SPARC_M8: case SUN4V_CHIP_SPARC_SN: pagecv_flag = 0x00; break; @@ -2313,6 +2324,7 @@ void __init paging_init(void) */ switch (sun4v_chip_type) { case SUN4V_CHIP_SPARC_M7: + case SUN4V_CHIP_SPARC_M8: case SUN4V_CHIP_SPARC_SN: page_cache4v_flag = _PAGE_CP_4V; break; diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h index 600a2e9bfee2..344d95619d03 100644 --- a/arch/um/include/asm/tlb.h +++ b/arch/um/include/asm/tlb.h @@ -45,7 +45,8 @@ static inline void init_tlb_gather(struct mmu_gather *tlb) } static inline void -tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end) +arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, + unsigned long start, unsigned long end) { tlb->mm = mm; tlb->start = start; @@ -80,13 +81,19 @@ tlb_flush_mmu(struct mmu_gather *tlb) tlb_flush_mmu_free(tlb); } -/* tlb_finish_mmu +/* arch_tlb_finish_mmu * Called at the end of the shootdown operation to free up any resources * that were required. */ static inline void -tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) +arch_tlb_finish_mmu(struct mmu_gather *tlb, + unsigned long start, unsigned long end, bool force) { + if (force) { + tlb->start = start; + tlb->end = end; + tlb->need_flush = 1; + } tlb_flush_mmu(tlb); /* keep the page table cache within bounds */ diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h index 21126155a739..0ead9dbb9130 100644 --- a/arch/x86/include/asm/hypervisor.h +++ b/arch/x86/include/asm/hypervisor.h @@ -43,6 +43,9 @@ struct hypervisor_x86 { /* pin current vcpu to specified physical cpu (run rarely) */ void (*pin_vcpu)(int); + + /* called during init_mem_mapping() to setup early mappings. */ + void (*init_mem_mapping)(void); }; extern const struct hypervisor_x86 *x86_hyper; @@ -57,8 +60,15 @@ extern const struct hypervisor_x86 x86_hyper_kvm; extern void init_hypervisor_platform(void); extern bool hypervisor_x2apic_available(void); extern void hypervisor_pin_vcpu(int cpu); + +static inline void hypervisor_init_mem_mapping(void) +{ + if (x86_hyper && x86_hyper->init_mem_mapping) + x86_hyper->init_mem_mapping(); +} #else static inline void init_hypervisor_platform(void) { } static inline bool hypervisor_x2apic_available(void) { return false; } +static inline void hypervisor_init_mem_mapping(void) { } #endif /* CONFIG_HYPERVISOR_GUEST */ #endif /* _ASM_X86_HYPERVISOR_H */ diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 673541eb3b3f..bf3f1065d6ad 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -18,6 +18,7 @@ #include <asm/dma.h> /* for MAX_DMA_PFN */ #include <asm/microcode.h> #include <asm/kaslr.h> +#include <asm/hypervisor.h> /* * We need to define the tracepoints somewhere, and tlb.c @@ -636,6 +637,8 @@ void __init init_mem_mapping(void) load_cr3(swapper_pg_dir); __flush_tlb_all(); + hypervisor_init_mem_mapping(); + early_memtest(0, max_pfn_mapped << PAGE_SHIFT); } diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 87d791356ea9..de503c225ae1 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -12,6 +12,7 @@ #include <asm/setup.h> #include <asm/hypervisor.h> #include <asm/e820/api.h> +#include <asm/early_ioremap.h> #include <asm/xen/cpuid.h> #include <asm/xen/hypervisor.h> @@ -21,38 +22,50 @@ #include "mmu.h" #include "smp.h" -void __ref xen_hvm_init_shared_info(void) +static unsigned long shared_info_pfn; + +void xen_hvm_init_shared_info(void) { struct xen_add_to_physmap xatp; - u64 pa; - - if (HYPERVISOR_shared_info == &xen_dummy_shared_info) { - /* - * Search for a free page starting at 4kB physical address. - * Low memory is preferred to avoid an EPT large page split up - * by the mapping. - * Starting below X86_RESERVE_LOW (usually 64kB) is fine as - * the BIOS used for HVM guests is well behaved and won't - * clobber memory other than the first 4kB. - */ - for (pa = PAGE_SIZE; - !e820__mapped_all(pa, pa + PAGE_SIZE, E820_TYPE_RAM) || - memblock_is_reserved(pa); - pa += PAGE_SIZE) - ; - - memblock_reserve(pa, PAGE_SIZE); - HYPERVISOR_shared_info = __va(pa); - } xatp.domid = DOMID_SELF; xatp.idx = 0; xatp.space = XENMAPSPACE_shared_info; - xatp.gpfn = virt_to_pfn(HYPERVISOR_shared_info); + xatp.gpfn = shared_info_pfn; if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp)) BUG(); } +static void __init reserve_shared_info(void) +{ + u64 pa; + + /* + * Search for a free page starting at 4kB physical address. + * Low memory is preferred to avoid an EPT large page split up + * by the mapping. + * Starting below X86_RESERVE_LOW (usually 64kB) is fine as + * the BIOS used for HVM guests is well behaved and won't + * clobber memory other than the first 4kB. + */ + for (pa = PAGE_SIZE; + !e820__mapped_all(pa, pa + PAGE_SIZE, E820_TYPE_RAM) || + memblock_is_reserved(pa); + pa += PAGE_SIZE) + ; + + shared_info_pfn = PHYS_PFN(pa); + + memblock_reserve(pa, PAGE_SIZE); + HYPERVISOR_shared_info = early_memremap(pa, PAGE_SIZE); +} + +static void __init xen_hvm_init_mem_mapping(void) +{ + early_memunmap(HYPERVISOR_shared_info, PAGE_SIZE); + HYPERVISOR_shared_info = __va(PFN_PHYS(shared_info_pfn)); +} + static void __init init_hvm_pv_info(void) { int major, minor; @@ -153,6 +166,7 @@ static void __init xen_hvm_guest_init(void) init_hvm_pv_info(); + reserve_shared_info(); xen_hvm_init_shared_info(); /* @@ -218,5 +232,6 @@ const struct hypervisor_x86 x86_hyper_xen_hvm = { .init_platform = xen_hvm_guest_init, .pin_vcpu = xen_pin_vcpu, .x2apic_available = xen_x2apic_para_available, + .init_mem_mapping = xen_hvm_init_mem_mapping, }; EXPORT_SYMBOL(x86_hyper_xen_hvm); diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild index 2d716ebc5a5e..dff7cc39437c 100644 --- a/arch/xtensa/include/asm/Kbuild +++ b/arch/xtensa/include/asm/Kbuild @@ -1,5 +1,6 @@ generic-y += bug.h generic-y += clkdev.h +generic-y += device.h generic-y += div64.h generic-y += dma-contiguous.h generic-y += emergency-restart.h @@ -17,6 +18,7 @@ generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h +generic-y += param.h generic-y += percpu.h generic-y += preempt.h generic-y += rwsem.h diff --git a/arch/xtensa/include/asm/device.h b/arch/xtensa/include/asm/device.h deleted file mode 100644 index 1deeb8ebbb1b..000000000000 --- a/arch/xtensa/include/asm/device.h +++ /dev/null @@ -1,15 +0,0 @@ -/* - * Arch specific extensions to struct device - * - * This file is released under the GPLv2 - */ -#ifndef _ASM_XTENSA_DEVICE_H -#define _ASM_XTENSA_DEVICE_H - -struct dev_archdata { -}; - -struct pdev_archdata { -}; - -#endif /* _ASM_XTENSA_DEVICE_H */ diff --git a/arch/xtensa/include/asm/param.h b/arch/xtensa/include/asm/param.h deleted file mode 100644 index 0a70e780ef2a..000000000000 --- a/arch/xtensa/include/asm/param.h +++ /dev/null @@ -1,18 +0,0 @@ -/* - * include/asm-xtensa/param.h - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2001 - 2005 Tensilica Inc. - */ -#ifndef _XTENSA_PARAM_H -#define _XTENSA_PARAM_H - -#include <uapi/asm/param.h> - -# define HZ CONFIG_HZ /* internal timer frequency */ -# define USER_HZ 100 /* for user interfaces in "ticks" */ -# define CLOCKS_PER_SEC (USER_HZ) /* frequnzy at which times() counts */ -#endif /* _XTENSA_PARAM_H */ diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c index d159e9b9c018..672391003e40 100644 --- a/arch/xtensa/kernel/xtensa_ksyms.c +++ b/arch/xtensa/kernel/xtensa_ksyms.c @@ -94,13 +94,11 @@ unsigned long __sync_fetch_and_or_4(unsigned long *p, unsigned long v) } EXPORT_SYMBOL(__sync_fetch_and_or_4); -#ifdef CONFIG_NET /* * Networking support */ EXPORT_SYMBOL(csum_partial); EXPORT_SYMBOL(csum_partial_copy_generic); -#endif /* CONFIG_NET */ /* * Architecture-specific symbols diff --git a/arch/xtensa/mm/cache.c b/arch/xtensa/mm/cache.c index 1a804a2f9a5b..3c75c4e597da 100644 --- a/arch/xtensa/mm/cache.c +++ b/arch/xtensa/mm/cache.c @@ -103,6 +103,7 @@ void clear_user_highpage(struct page *page, unsigned long vaddr) clear_page_alias(kvaddr, paddr); preempt_enable(); } +EXPORT_SYMBOL(clear_user_highpage); void copy_user_highpage(struct page *dst, struct page *src, unsigned long vaddr, struct vm_area_struct *vma) @@ -119,10 +120,7 @@ void copy_user_highpage(struct page *dst, struct page *src, copy_page_alias(dst_vaddr, src_vaddr, dst_paddr, src_paddr); preempt_enable(); } - -#endif /* DCACHE_WAY_SIZE > PAGE_SIZE */ - -#if (DCACHE_WAY_SIZE > PAGE_SIZE) && XCHAL_DCACHE_IS_WRITEBACK +EXPORT_SYMBOL(copy_user_highpage); /* * Any time the kernel writes to a user page cache page, or it is about to @@ -176,7 +174,7 @@ void flush_dcache_page(struct page *page) /* There shouldn't be an entry in the cache for this page anymore. */ } - +EXPORT_SYMBOL(flush_dcache_page); /* * For now, flush the whole cache. FIXME?? @@ -188,6 +186,7 @@ void local_flush_cache_range(struct vm_area_struct *vma, __flush_invalidate_dcache_all(); __invalidate_icache_all(); } +EXPORT_SYMBOL(local_flush_cache_range); /* * Remove any entry in the cache for this page. @@ -207,8 +206,9 @@ void local_flush_cache_page(struct vm_area_struct *vma, unsigned long address, __flush_invalidate_dcache_page_alias(virt, phys); __invalidate_icache_page_alias(virt, phys); } +EXPORT_SYMBOL(local_flush_cache_page); -#endif +#endif /* DCACHE_WAY_SIZE > PAGE_SIZE */ void update_mmu_cache(struct vm_area_struct * vma, unsigned long addr, pte_t *ptep) @@ -225,7 +225,7 @@ update_mmu_cache(struct vm_area_struct * vma, unsigned long addr, pte_t *ptep) flush_tlb_page(vma, addr); -#if (DCACHE_WAY_SIZE > PAGE_SIZE) && XCHAL_DCACHE_IS_WRITEBACK +#if (DCACHE_WAY_SIZE > PAGE_SIZE) if (!PageReserved(page) && test_bit(PG_arch_1, &page->flags)) { unsigned long phys = page_to_phys(page); @@ -256,7 +256,7 @@ update_mmu_cache(struct vm_area_struct * vma, unsigned long addr, pte_t *ptep) * flush_dcache_page() on the page. */ -#if (DCACHE_WAY_SIZE > PAGE_SIZE) && XCHAL_DCACHE_IS_WRITEBACK +#if (DCACHE_WAY_SIZE > PAGE_SIZE) void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long vaddr, void *dst, const void *src, diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index 63e771ab56d8..859f0a8c97c8 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -71,17 +71,29 @@ struct bfq_service_tree { * * bfq_sched_data is the basic scheduler queue. It supports three * ioprio_classes, and can be used either as a toplevel queue or as an - * intermediate queue on a hierarchical setup. @next_in_service - * points to the active entity of the sched_data service trees that - * will be scheduled next. It is used to reduce the number of steps - * needed for each hierarchical-schedule update. + * intermediate queue in a hierarchical setup. * * The supported ioprio_classes are the same as in CFQ, in descending * priority order, IOPRIO_CLASS_RT, IOPRIO_CLASS_BE, IOPRIO_CLASS_IDLE. * Requests from higher priority queues are served before all the * requests from lower priority queues; among requests of the same * queue requests are served according to B-WF2Q+. - * All the fields are protected by the queue lock of the containing bfqd. + * + * The schedule is implemented by the service trees, plus the field + * @next_in_service, which points to the entity on the active trees + * that will be served next, if 1) no changes in the schedule occurs + * before the current in-service entity is expired, 2) the in-service + * queue becomes idle when it expires, and 3) if the entity pointed by + * in_service_entity is not a queue, then the in-service child entity + * of the entity pointed by in_service_entity becomes idle on + * expiration. This peculiar definition allows for the following + * optimization, not yet exploited: while a given entity is still in + * service, we already know which is the best candidate for next + * service among the other active entitities in the same parent + * entity. We can then quickly compare the timestamps of the + * in-service entity with those of such best candidate. + * + * All fields are protected by the lock of the containing bfqd. */ struct bfq_sched_data { /* entity in service */ diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c index 979f8f21b7e2..911aa7431dbe 100644 --- a/block/bfq-wf2q.c +++ b/block/bfq-wf2q.c @@ -188,21 +188,23 @@ static bool bfq_update_parent_budget(struct bfq_entity *next_in_service) /* * This function tells whether entity stops being a candidate for next - * service, according to the following logic. + * service, according to the restrictive definition of the field + * next_in_service. In particular, this function is invoked for an + * entity that is about to be set in service. * - * This function is invoked for an entity that is about to be set in - * service. If such an entity is a queue, then the entity is no longer - * a candidate for next service (i.e, a candidate entity to serve - * after the in-service entity is expired). The function then returns - * true. + * If entity is a queue, then the entity is no longer a candidate for + * next service according to the that definition, because entity is + * about to become the in-service queue. This function then returns + * true if entity is a queue. * - * In contrast, the entity could stil be a candidate for next service - * if it is not a queue, and has more than one child. In fact, even if - * one of its children is about to be set in service, other children - * may still be the next to serve. As a consequence, a non-queue - * entity is not a candidate for next-service only if it has only one - * child. And only if this condition holds, then the function returns - * true for a non-queue entity. + * In contrast, entity could still be a candidate for next service if + * it is not a queue, and has more than one active child. In fact, + * even if one of its children is about to be set in service, other + * active children may still be the next to serve, for the parent + * entity, even according to the above definition. As a consequence, a + * non-queue entity is not a candidate for next-service only if it has + * only one active child. And only if this condition holds, then this + * function returns true for a non-queue entity. */ static bool bfq_no_longer_next_in_service(struct bfq_entity *entity) { @@ -213,6 +215,18 @@ static bool bfq_no_longer_next_in_service(struct bfq_entity *entity) bfqg = container_of(entity, struct bfq_group, entity); + /* + * The field active_entities does not always contain the + * actual number of active children entities: it happens to + * not account for the in-service entity in case the latter is + * removed from its active tree (which may get done after + * invoking the function bfq_no_longer_next_in_service in + * bfq_get_next_queue). Fortunately, here, i.e., while + * bfq_no_longer_next_in_service is not yet completed in + * bfq_get_next_queue, bfq_active_extract has not yet been + * invoked, and thus active_entities still coincides with the + * actual number of active entities. + */ if (bfqg->active_entities == 1) return true; @@ -954,7 +968,7 @@ static void bfq_update_fin_time_enqueue(struct bfq_entity *entity, * one of its children receives a new request. * * Basically, this function updates the timestamps of entity and - * inserts entity into its active tree, ater possible extracting it + * inserts entity into its active tree, ater possibly extracting it * from its idle tree. */ static void __bfq_activate_entity(struct bfq_entity *entity, @@ -1048,7 +1062,7 @@ static void __bfq_requeue_entity(struct bfq_entity *entity) entity->start = entity->finish; /* * In addition, if the entity had more than one child - * when set in service, then was not extracted from + * when set in service, then it was not extracted from * the active tree. This implies that the position of * the entity in the active tree may need to be * changed now, because we have just updated the start @@ -1056,9 +1070,8 @@ static void __bfq_requeue_entity(struct bfq_entity *entity) * time in a moment (the requeueing is then, more * precisely, a repositioning in this case). To * implement this repositioning, we: 1) dequeue the - * entity here, 2) update the finish time and - * requeue the entity according to the new - * timestamps below. + * entity here, 2) update the finish time and requeue + * the entity according to the new timestamps below. */ if (entity->tree) bfq_active_extract(st, entity); @@ -1105,9 +1118,10 @@ static void __bfq_activate_requeue_entity(struct bfq_entity *entity, /** - * bfq_activate_entity - activate or requeue an entity representing a bfq_queue, - * and activate, requeue or reposition all ancestors - * for which such an update becomes necessary. + * bfq_activate_requeue_entity - activate or requeue an entity representing a + * bfq_queue, and activate, requeue or reposition + * all ancestors for which such an update becomes + * necessary. * @entity: the entity to activate. * @non_blocking_wait_rq: true if this entity was waiting for a request * @requeue: true if this is a requeue, which implies that bfqq is @@ -1135,9 +1149,9 @@ static void bfq_activate_requeue_entity(struct bfq_entity *entity, * @ins_into_idle_tree: if false, the entity will not be put into the * idle tree. * - * Deactivates an entity, independently from its previous state. Must + * Deactivates an entity, independently of its previous state. Must * be invoked only if entity is on a service tree. Extracts the entity - * from that tree, and if necessary and allowed, puts it on the idle + * from that tree, and if necessary and allowed, puts it into the idle * tree. */ bool __bfq_deactivate_entity(struct bfq_entity *entity, bool ins_into_idle_tree) @@ -1158,8 +1172,10 @@ bool __bfq_deactivate_entity(struct bfq_entity *entity, bool ins_into_idle_tree) st = bfq_entity_service_tree(entity); is_in_service = entity == sd->in_service_entity; - if (is_in_service) + if (is_in_service) { bfq_calc_finish(entity, entity->service); + sd->in_service_entity = NULL; + } if (entity->tree == &st->active) bfq_active_extract(st, entity); @@ -1177,7 +1193,7 @@ bool __bfq_deactivate_entity(struct bfq_entity *entity, bool ins_into_idle_tree) /** * bfq_deactivate_entity - deactivate an entity representing a bfq_queue. * @entity: the entity to deactivate. - * @ins_into_idle_tree: true if the entity can be put on the idle tree + * @ins_into_idle_tree: true if the entity can be put into the idle tree */ static void bfq_deactivate_entity(struct bfq_entity *entity, bool ins_into_idle_tree, @@ -1208,16 +1224,29 @@ static void bfq_deactivate_entity(struct bfq_entity *entity, */ bfq_update_next_in_service(sd, NULL); - if (sd->next_in_service) + if (sd->next_in_service || sd->in_service_entity) { /* - * The parent entity is still backlogged, - * because next_in_service is not NULL. So, no - * further upwards deactivation must be - * performed. Yet, next_in_service has - * changed. Then the schedule does need to be - * updated upwards. + * The parent entity is still active, because + * either next_in_service or in_service_entity + * is not NULL. So, no further upwards + * deactivation must be performed. Yet, + * next_in_service has changed. Then the + * schedule does need to be updated upwards. + * + * NOTE If in_service_entity is not NULL, then + * next_in_service may happen to be NULL, + * although the parent entity is evidently + * active. This happens if 1) the entity + * pointed by in_service_entity is the only + * active entity in the parent entity, and 2) + * according to the definition of + * next_in_service, the in_service_entity + * cannot be considered as + * next_in_service. See the comments on the + * definition of next_in_service for details. */ break; + } /* * If we get here, then the parent is no more @@ -1494,47 +1523,34 @@ struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd) /* * If entity is no longer a candidate for next - * service, then we extract it from its active tree, - * for the following reason. To further boost the - * throughput in some special case, BFQ needs to know - * which is the next candidate entity to serve, while - * there is already an entity in service. In this - * respect, to make it easy to compute/update the next - * candidate entity to serve after the current - * candidate has been set in service, there is a case - * where it is necessary to extract the current - * candidate from its service tree. Such a case is - * when the entity just set in service cannot be also - * a candidate for next service. Details about when - * this conditions holds are reported in the comments - * on the function bfq_no_longer_next_in_service() - * invoked below. + * service, then it must be extracted from its active + * tree, so as to make sure that it won't be + * considered when computing next_in_service. See the + * comments on the function + * bfq_no_longer_next_in_service() for details. */ if (bfq_no_longer_next_in_service(entity)) bfq_active_extract(bfq_entity_service_tree(entity), entity); /* - * For the same reason why we may have just extracted - * entity from its active tree, we may need to update - * next_in_service for the sched_data of entity too, - * regardless of whether entity has been extracted. - * In fact, even if entity has not been extracted, a - * descendant entity may get extracted. Such an event - * would cause a change in next_in_service for the - * level of the descendant entity, and thus possibly - * back to upper levels. + * Even if entity is not to be extracted according to + * the above check, a descendant entity may get + * extracted in one of the next iterations of this + * loop. Such an event could cause a change in + * next_in_service for the level of the descendant + * entity, and thus possibly back to this level. * - * We cannot perform the resulting needed update - * before the end of this loop, because, to know which - * is the correct next-to-serve candidate entity for - * each level, we need first to find the leaf entity - * to set in service. In fact, only after we know - * which is the next-to-serve leaf entity, we can - * discover whether the parent entity of the leaf - * entity becomes the next-to-serve, and so on. + * However, we cannot perform the resulting needed + * update of next_in_service for this level before the + * end of the whole loop, because, to know which is + * the correct next-to-serve candidate entity for each + * level, we need first to find the leaf entity to set + * in service. In fact, only after we know which is + * the next-to-serve leaf entity, we can discover + * whether the parent entity of the leaf entity + * becomes the next-to-serve, and so on. */ - } bfqq = bfq_entity_to_bfqq(entity); diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 83e92beb3c9f..9b1ea478577b 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -387,9 +387,11 @@ static void bio_integrity_verify_fn(struct work_struct *work) */ bool __bio_integrity_endio(struct bio *bio) { - if (bio_op(bio) == REQ_OP_READ && !bio->bi_status) { - struct bio_integrity_payload *bip = bio_integrity(bio); + struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev); + struct bio_integrity_payload *bip = bio_integrity(bio); + if (bio_op(bio) == REQ_OP_READ && !bio->bi_status && + (bip->bip_flags & BIP_BLOCK_INTEGRITY) && bi->profile->verify_fn) { INIT_WORK(&bip->bip_work, bio_integrity_verify_fn); queue_work(kintegrityd_wq, &bip->bip_work); return false; diff --git a/block/blk-mq.c b/block/blk-mq.c index 041f7b7fa0d6..535cbdf32aab 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -301,11 +301,12 @@ static struct request *blk_mq_get_request(struct request_queue *q, struct elevator_queue *e = q->elevator; struct request *rq; unsigned int tag; + struct blk_mq_ctx *local_ctx = NULL; blk_queue_enter_live(q); data->q = q; if (likely(!data->ctx)) - data->ctx = blk_mq_get_ctx(q); + data->ctx = local_ctx = blk_mq_get_ctx(q); if (likely(!data->hctx)) data->hctx = blk_mq_map_queue(q, data->ctx->cpu); if (op & REQ_NOWAIT) @@ -324,6 +325,10 @@ static struct request *blk_mq_get_request(struct request_queue *q, tag = blk_mq_get_tag(data); if (tag == BLK_MQ_TAG_FAIL) { + if (local_ctx) { + blk_mq_put_ctx(local_ctx); + data->ctx = NULL; + } blk_queue_exit(q); return NULL; } @@ -356,12 +361,12 @@ struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op, rq = blk_mq_get_request(q, NULL, op, &alloc_data); - blk_mq_put_ctx(alloc_data.ctx); - blk_queue_exit(q); - if (!rq) return ERR_PTR(-EWOULDBLOCK); + blk_mq_put_ctx(alloc_data.ctx); + blk_queue_exit(q); + rq->__data_len = 0; rq->__sector = (sector_t) -1; rq->bio = rq->biotail = NULL; @@ -407,11 +412,11 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, rq = blk_mq_get_request(q, NULL, op, &alloc_data); - blk_queue_exit(q); - if (!rq) return ERR_PTR(-EWOULDBLOCK); + blk_queue_exit(q); + return rq; } EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx); @@ -679,8 +684,8 @@ EXPORT_SYMBOL(blk_mq_kick_requeue_list); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs) { - kblockd_schedule_delayed_work(&q->requeue_work, - msecs_to_jiffies(msecs)); + kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work, + msecs_to_jiffies(msecs)); } EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list); diff --git a/drivers/acpi/spcr.c b/drivers/acpi/spcr.c index 4ac3e06b41d8..98aa8c808a33 100644 --- a/drivers/acpi/spcr.c +++ b/drivers/acpi/spcr.c @@ -17,6 +17,16 @@ #include <linux/serial_core.h> /* + * Erratum 44 for QDF2432v1 and QDF2400v1 SoCs describes the BUSY bit as + * occasionally getting stuck as 1. To avoid the potential for a hang, check + * TXFE == 0 instead of BUSY == 1. This may not be suitable for all UART + * implementations, so only do so if an affected platform is detected in + * parse_spcr(). + */ +bool qdf2400_e44_present; +EXPORT_SYMBOL(qdf2400_e44_present); + +/* * Some Qualcomm Datacenter Technologies SoCs have a defective UART BUSY bit. * Detect them by examining the OEM fields in the SPCR header, similiar to PCI * quirk detection in pci_mcfg.c. @@ -147,8 +157,30 @@ int __init parse_spcr(bool earlycon) goto done; } - if (qdf2400_erratum_44_present(&table->header)) - uart = "qdf2400_e44"; + /* + * If the E44 erratum is required, then we need to tell the pl011 + * driver to implement the work-around. + * + * The global variable is used by the probe function when it + * creates the UARTs, whether or not they're used as a console. + * + * If the user specifies "traditional" earlycon, the qdf2400_e44 + * console name matches the EARLYCON_DECLARE() statement, and + * SPCR is not used. Parameter "earlycon" is false. + * + * If the user specifies "SPCR" earlycon, then we need to update + * the console name so that it also says "qdf2400_e44". Parameter + * "earlycon" is true. + * + * For consistency, if we change the console name, then we do it + * for everyone, not just earlycon. + */ + if (qdf2400_erratum_44_present(&table->header)) { + qdf2400_e44_present = true; + if (earlycon) + uart = "qdf2400_e44"; + } + if (xgene_8250_erratum_present(table)) iotype = "mmio32"; diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c index b9f907eedbf7..bfbe1e154128 100644 --- a/drivers/base/firmware_class.c +++ b/drivers/base/firmware_class.c @@ -30,7 +30,6 @@ #include <linux/syscore_ops.h> #include <linux/reboot.h> #include <linux/security.h> -#include <linux/swait.h> #include <generated/utsrelease.h> @@ -112,13 +111,13 @@ static inline long firmware_loading_timeout(void) * state of the firmware loading. */ struct fw_state { - struct swait_queue_head wq; + struct completion completion; enum fw_status status; }; static void fw_state_init(struct fw_state *fw_st) { - init_swait_queue_head(&fw_st->wq); + init_completion(&fw_st->completion); fw_st->status = FW_STATUS_UNKNOWN; } @@ -131,9 +130,7 @@ static int __fw_state_wait_common(struct fw_state *fw_st, long timeout) { long ret; - ret = swait_event_interruptible_timeout(fw_st->wq, - __fw_state_is_done(READ_ONCE(fw_st->status)), - timeout); + ret = wait_for_completion_killable_timeout(&fw_st->completion, timeout); if (ret != 0 && fw_st->status == FW_STATUS_ABORTED) return -ENOENT; if (!ret) @@ -148,35 +145,34 @@ static void __fw_state_set(struct fw_state *fw_st, WRITE_ONCE(fw_st->status, status); if (status == FW_STATUS_DONE || status == FW_STATUS_ABORTED) - swake_up(&fw_st->wq); + complete_all(&fw_st->completion); } #define fw_state_start(fw_st) \ __fw_state_set(fw_st, FW_STATUS_LOADING) #define fw_state_done(fw_st) \ __fw_state_set(fw_st, FW_STATUS_DONE) +#define fw_state_aborted(fw_st) \ + __fw_state_set(fw_st, FW_STATUS_ABORTED) #define fw_state_wait(fw_st) \ __fw_state_wait_common(fw_st, MAX_SCHEDULE_TIMEOUT) -#ifndef CONFIG_FW_LOADER_USER_HELPER - -#define fw_state_is_aborted(fw_st) false - -#else /* CONFIG_FW_LOADER_USER_HELPER */ - static int __fw_state_check(struct fw_state *fw_st, enum fw_status status) { return fw_st->status == status; } +#define fw_state_is_aborted(fw_st) \ + __fw_state_check(fw_st, FW_STATUS_ABORTED) + +#ifdef CONFIG_FW_LOADER_USER_HELPER + #define fw_state_aborted(fw_st) \ __fw_state_set(fw_st, FW_STATUS_ABORTED) #define fw_state_is_done(fw_st) \ __fw_state_check(fw_st, FW_STATUS_DONE) #define fw_state_is_loading(fw_st) \ __fw_state_check(fw_st, FW_STATUS_LOADING) -#define fw_state_is_aborted(fw_st) \ - __fw_state_check(fw_st, FW_STATUS_ABORTED) #define fw_state_wait_timeout(fw_st, timeout) \ __fw_state_wait_common(fw_st, timeout) @@ -1200,6 +1196,28 @@ _request_firmware_prepare(struct firmware **firmware_p, const char *name, return 1; /* need to load */ } +/* + * Batched requests need only one wake, we need to do this step last due to the + * fallback mechanism. The buf is protected with kref_get(), and it won't be + * released until the last user calls release_firmware(). + * + * Failed batched requests are possible as well, in such cases we just share + * the struct firmware_buf and won't release it until all requests are woken + * and have gone through this same path. + */ +static void fw_abort_batch_reqs(struct firmware *fw) +{ + struct firmware_buf *buf; + + /* Loaded directly? */ + if (!fw || !fw->priv) + return; + + buf = fw->priv; + if (!fw_state_is_aborted(&buf->fw_st)) + fw_state_aborted(&buf->fw_st); +} + /* called from request_firmware() and request_firmware_work_func() */ static int _request_firmware(const struct firmware **firmware_p, const char *name, @@ -1243,6 +1261,7 @@ _request_firmware(const struct firmware **firmware_p, const char *name, out: if (ret < 0) { + fw_abort_batch_reqs(fw); release_firmware(fw); fw = NULL; } diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 6b16ead1da58..ad9749463d4f 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -875,6 +875,56 @@ static void print_version(void) printk(KERN_INFO "%s", version); } +struct vdc_check_port_data { + int dev_no; + char *type; +}; + +static int vdc_device_probed(struct device *dev, void *arg) +{ + struct vio_dev *vdev = to_vio_dev(dev); + struct vdc_check_port_data *port_data; + + port_data = (struct vdc_check_port_data *)arg; + + if ((vdev->dev_no == port_data->dev_no) && + (!(strcmp((char *)&vdev->type, port_data->type))) && + dev_get_drvdata(dev)) { + /* This device has already been configured + * by vdc_port_probe() + */ + return 1; + } else { + return 0; + } +} + +/* Determine whether the VIO device is part of an mpgroup + * by locating all the virtual-device-port nodes associated + * with the parent virtual-device node for the VIO device + * and checking whether any of these nodes are vdc-ports + * which have already been configured. + * + * Returns true if this device is part of an mpgroup and has + * already been probed. + */ +static bool vdc_port_mpgroup_check(struct vio_dev *vdev) +{ + struct vdc_check_port_data port_data; + struct device *dev; + + port_data.dev_no = vdev->dev_no; + port_data.type = (char *)&vdev->type; + + dev = device_find_child(vdev->dev.parent, &port_data, + vdc_device_probed); + + if (dev) + return true; + + return false; +} + static int vdc_port_probe(struct vio_dev *vdev, const struct vio_device_id *id) { struct mdesc_handle *hp; @@ -893,6 +943,14 @@ static int vdc_port_probe(struct vio_dev *vdev, const struct vio_device_id *id) goto err_out_release_mdesc; } + /* Check if this device is part of an mpgroup */ + if (vdc_port_mpgroup_check(vdev)) { + printk(KERN_WARNING + "VIO: Ignoring extra vdisk port %s", + dev_name(&vdev->dev)); + goto err_out_release_mdesc; + } + port = kzalloc(sizeof(*port), GFP_KERNEL); err = -ENOMEM; if (!port) { @@ -943,6 +1001,9 @@ static int vdc_port_probe(struct vio_dev *vdev, const struct vio_device_id *id) if (err) goto err_out_free_tx_ring; + /* Note that the device driver_data is used to determine + * whether the port has been probed. + */ dev_set_drvdata(&vdev->dev, port); mdesc_release(hp); diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 856d5dc02451..3b1b6340ba13 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -308,7 +308,7 @@ static ssize_t comp_algorithm_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct zram *zram = dev_to_zram(dev); - char compressor[CRYPTO_MAX_ALG_NAME]; + char compressor[ARRAY_SIZE(zram->compressor)]; size_t sz; strlcpy(compressor, buf, sizeof(compressor)); @@ -327,7 +327,7 @@ static ssize_t comp_algorithm_store(struct device *dev, return -EBUSY; } - strlcpy(zram->compressor, compressor, sizeof(compressor)); + strcpy(zram->compressor, compressor); up_write(&zram->init_lock); return len; } diff --git a/drivers/char/random.c b/drivers/char/random.c index afa3ce7d3e72..8ad92707e45f 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1492,7 +1492,7 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller, #ifndef CONFIG_WARN_ALL_UNSEEDED_RANDOM print_once = true; #endif - pr_notice("random: %s called from %pF with crng_init=%d\n", + pr_notice("random: %s called from %pS with crng_init=%d\n", func_name, caller, crng_init); } diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c index 37b0698b7193..42896a67aeae 100644 --- a/drivers/cpuidle/cpuidle-powernv.c +++ b/drivers/cpuidle/cpuidle-powernv.c @@ -235,6 +235,7 @@ static inline int validate_dt_prop_sizes(const char *prop1, int prop1_len, return -1; } +extern u32 pnv_get_supported_cpuidle_states(void); static int powernv_add_idle_states(void) { struct device_node *power_mgt; @@ -248,6 +249,8 @@ static int powernv_add_idle_states(void) const char *names[CPUIDLE_STATE_MAX]; u32 has_stop_states = 0; int i, rc; + u32 supported_flags = pnv_get_supported_cpuidle_states(); + /* Currently we have snooze statically defined */ @@ -362,6 +365,13 @@ static int powernv_add_idle_states(void) for (i = 0; i < dt_idle_states; i++) { unsigned int exit_latency, target_residency; bool stops_timebase = false; + + /* + * Skip the platform idle state whose flag isn't in + * the supported_cpuidle_states flag mask. + */ + if ((flags[i] & supported_flags) != flags[i]) + continue; /* * If an idle state has exit latency beyond * POWERNV_THRESHOLD_LATENCY_NS then don't use it diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c index 8527a5899a2f..3f819399cd95 100644 --- a/drivers/crypto/inside-secure/safexcel_hash.c +++ b/drivers/crypto/inside-secure/safexcel_hash.c @@ -883,10 +883,7 @@ static int safexcel_hmac_sha1_setkey(struct crypto_ahash *tfm, const u8 *key, if (ret) return ret; - memcpy(ctx->ipad, &istate.state, SHA1_DIGEST_SIZE); - memcpy(ctx->opad, &ostate.state, SHA1_DIGEST_SIZE); - - for (i = 0; i < ARRAY_SIZE(istate.state); i++) { + for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(u32); i++) { if (ctx->ipad[i] != le32_to_cpu(istate.state[i]) || ctx->opad[i] != le32_to_cpu(ostate.state[i])) { ctx->base.needs_inv = true; @@ -894,6 +891,9 @@ static int safexcel_hmac_sha1_setkey(struct crypto_ahash *tfm, const u8 *key, } } + memcpy(ctx->ipad, &istate.state, SHA1_DIGEST_SIZE); + memcpy(ctx->opad, &ostate.state, SHA1_DIGEST_SIZE); + return 0; } diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c index d7e219d2669d..66fb40d0ebdb 100644 --- a/drivers/dma-buf/sync_file.c +++ b/drivers/dma-buf/sync_file.c @@ -304,7 +304,7 @@ static int sync_file_release(struct inode *inode, struct file *file) { struct sync_file *sync_file = file->private_data; - if (test_bit(POLL_ENABLED, &sync_file->fence->flags)) + if (test_bit(POLL_ENABLED, &sync_file->flags)) dma_fence_remove_callback(sync_file->fence, &sync_file->cb); dma_fence_put(sync_file->fence); kfree(sync_file); @@ -318,7 +318,8 @@ static unsigned int sync_file_poll(struct file *file, poll_table *wait) poll_wait(file, &sync_file->wq, wait); - if (!test_and_set_bit(POLL_ENABLED, &sync_file->fence->flags)) { + if (list_empty(&sync_file->cb.node) && + !test_and_set_bit(POLL_ENABLED, &sync_file->flags)) { if (dma_fence_add_callback(sync_file->fence, &sync_file->cb, fence_check_cb_func) < 0) wake_up_all(&sync_file->wq); diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c index 5c26488e7a2d..0529e500c534 100644 --- a/drivers/gpu/drm/bridge/tc358767.c +++ b/drivers/gpu/drm/bridge/tc358767.c @@ -1255,7 +1255,7 @@ static int tc_probe(struct i2c_client *client, const struct i2c_device_id *id) /* port@2 is the output port */ ret = drm_of_find_panel_or_bridge(dev->of_node, 2, 0, &tc->panel, NULL); - if (ret) + if (ret && ret != -ENODEV) return ret; /* Shut down GPIO is optional */ diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c index 5bd93169dac2..6463fc2c736f 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c @@ -270,8 +270,8 @@ static int submit_reloc(struct etnaviv_gem_submit *submit, void *stream, if (ret) return ret; - if (r->reloc_offset >= bo->obj->base.size - sizeof(*ptr)) { - DRM_ERROR("relocation %u outside object", i); + if (r->reloc_offset > bo->obj->base.size - sizeof(*ptr)) { + DRM_ERROR("relocation %u outside object\n", i); return -EINVAL; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_fb.c b/drivers/gpu/drm/exynos/exynos_drm_fb.c index d48fd7c918f8..73217c281c9a 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fb.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fb.c @@ -145,13 +145,19 @@ static struct drm_framebuffer * exynos_user_fb_create(struct drm_device *dev, struct drm_file *file_priv, const struct drm_mode_fb_cmd2 *mode_cmd) { + const struct drm_format_info *info = drm_get_format_info(dev, mode_cmd); struct exynos_drm_gem *exynos_gem[MAX_FB_BUFFER]; struct drm_gem_object *obj; struct drm_framebuffer *fb; int i; int ret; - for (i = 0; i < drm_format_num_planes(mode_cmd->pixel_format); i++) { + for (i = 0; i < info->num_planes; i++) { + unsigned int height = (i == 0) ? mode_cmd->height : + DIV_ROUND_UP(mode_cmd->height, info->vsub); + unsigned long size = height * mode_cmd->pitches[i] + + mode_cmd->offsets[i]; + obj = drm_gem_object_lookup(file_priv, mode_cmd->handles[i]); if (!obj) { DRM_ERROR("failed to lookup gem object\n"); @@ -160,6 +166,12 @@ exynos_user_fb_create(struct drm_device *dev, struct drm_file *file_priv, } exynos_gem[i] = to_exynos_gem(obj); + + if (size > exynos_gem[i]->size) { + i++; + ret = -EINVAL; + goto err; + } } fb = exynos_drm_framebuffer_init(dev, mode_cmd, exynos_gem, i); diff --git a/drivers/gpu/drm/i915/gvt/execlist.c b/drivers/gpu/drm/i915/gvt/execlist.c index 700050556242..1648887d3f55 100644 --- a/drivers/gpu/drm/i915/gvt/execlist.c +++ b/drivers/gpu/drm/i915/gvt/execlist.c @@ -46,6 +46,8 @@ #define same_context(a, b) (((a)->context_id == (b)->context_id) && \ ((a)->lrca == (b)->lrca)) +static void clean_workloads(struct intel_vgpu *vgpu, unsigned long engine_mask); + static int context_switch_events[] = { [RCS] = RCS_AS_CONTEXT_SWITCH, [BCS] = BCS_AS_CONTEXT_SWITCH, @@ -499,10 +501,10 @@ static void release_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx) static int complete_execlist_workload(struct intel_vgpu_workload *workload) { struct intel_vgpu *vgpu = workload->vgpu; - struct intel_vgpu_execlist *execlist = - &vgpu->execlist[workload->ring_id]; + int ring_id = workload->ring_id; + struct intel_vgpu_execlist *execlist = &vgpu->execlist[ring_id]; struct intel_vgpu_workload *next_workload; - struct list_head *next = workload_q_head(vgpu, workload->ring_id)->next; + struct list_head *next = workload_q_head(vgpu, ring_id)->next; bool lite_restore = false; int ret; @@ -512,10 +514,25 @@ static int complete_execlist_workload(struct intel_vgpu_workload *workload) release_shadow_batch_buffer(workload); release_shadow_wa_ctx(&workload->wa_ctx); - if (workload->status || vgpu->resetting) + if (workload->status || (vgpu->resetting_eng & ENGINE_MASK(ring_id))) { + /* if workload->status is not successful means HW GPU + * has occurred GPU hang or something wrong with i915/GVT, + * and GVT won't inject context switch interrupt to guest. + * So this error is a vGPU hang actually to the guest. + * According to this we should emunlate a vGPU hang. If + * there are pending workloads which are already submitted + * from guest, we should clean them up like HW GPU does. + * + * if it is in middle of engine resetting, the pending + * workloads won't be submitted to HW GPU and will be + * cleaned up during the resetting process later, so doing + * the workload clean up here doesn't have any impact. + **/ + clean_workloads(vgpu, ENGINE_MASK(ring_id)); goto out; + } - if (!list_empty(workload_q_head(vgpu, workload->ring_id))) { + if (!list_empty(workload_q_head(vgpu, ring_id))) { struct execlist_ctx_descriptor_format *this_desc, *next_desc; next_workload = container_of(next, diff --git a/drivers/gpu/drm/i915/gvt/firmware.c b/drivers/gpu/drm/i915/gvt/firmware.c index 5dad9298b2d5..a26c1705430e 100644 --- a/drivers/gpu/drm/i915/gvt/firmware.c +++ b/drivers/gpu/drm/i915/gvt/firmware.c @@ -72,11 +72,13 @@ static int expose_firmware_sysfs(struct intel_gvt *gvt) struct intel_gvt_device_info *info = &gvt->device_info; struct pci_dev *pdev = gvt->dev_priv->drm.pdev; struct intel_gvt_mmio_info *e; + struct gvt_mmio_block *block = gvt->mmio.mmio_block; + int num = gvt->mmio.num_mmio_block; struct gvt_firmware_header *h; void *firmware; void *p; unsigned long size, crc32_start; - int i; + int i, j; int ret; size = sizeof(*h) + info->mmio_size + info->cfg_space_size; @@ -105,6 +107,13 @@ static int expose_firmware_sysfs(struct intel_gvt *gvt) hash_for_each(gvt->mmio.mmio_info_table, i, e, node) *(u32 *)(p + e->offset) = I915_READ_NOTRACE(_MMIO(e->offset)); + for (i = 0; i < num; i++, block++) { + for (j = 0; j < block->size; j += 4) + *(u32 *)(p + INTEL_GVT_MMIO_OFFSET(block->offset) + j) = + I915_READ_NOTRACE(_MMIO(INTEL_GVT_MMIO_OFFSET( + block->offset) + j)); + } + memcpy(gvt->firmware.mmio, p, info->mmio_size); crc32_start = offsetof(struct gvt_firmware_header, crc32) + 4; diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index 3a74e79eac2f..2964a4d01a66 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -149,7 +149,7 @@ struct intel_vgpu { bool active; bool pv_notified; bool failsafe; - bool resetting; + unsigned int resetting_eng; void *sched_data; struct vgpu_sched_ctl sched_ctl; @@ -195,6 +195,15 @@ struct intel_gvt_fence { unsigned long vgpu_allocated_fence_num; }; +/* Special MMIO blocks. */ +struct gvt_mmio_block { + unsigned int device; + i915_reg_t offset; + unsigned int size; + gvt_mmio_func read; + gvt_mmio_func write; +}; + #define INTEL_GVT_MMIO_HASH_BITS 11 struct intel_gvt_mmio { @@ -214,6 +223,9 @@ struct intel_gvt_mmio { /* This reg could be accessed by unaligned address */ #define F_UNALIGN (1 << 6) + struct gvt_mmio_block *mmio_block; + unsigned int num_mmio_block; + DECLARE_HASHTABLE(mmio_info_table, INTEL_GVT_MMIO_HASH_BITS); unsigned int num_tracked_mmio; }; diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 17febe830ff6..feed9921b3b3 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -2857,31 +2857,15 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) return 0; } -/* Special MMIO blocks. */ -static struct gvt_mmio_block { - unsigned int device; - i915_reg_t offset; - unsigned int size; - gvt_mmio_func read; - gvt_mmio_func write; -} gvt_mmio_blocks[] = { - {D_SKL_PLUS, _MMIO(CSR_MMIO_START_RANGE), 0x3000, NULL, NULL}, - {D_ALL, _MMIO(MCHBAR_MIRROR_BASE_SNB), 0x40000, NULL, NULL}, - {D_ALL, _MMIO(VGT_PVINFO_PAGE), VGT_PVINFO_SIZE, - pvinfo_mmio_read, pvinfo_mmio_write}, - {D_ALL, LGC_PALETTE(PIPE_A, 0), 1024, NULL, NULL}, - {D_ALL, LGC_PALETTE(PIPE_B, 0), 1024, NULL, NULL}, - {D_ALL, LGC_PALETTE(PIPE_C, 0), 1024, NULL, NULL}, -}; - static struct gvt_mmio_block *find_mmio_block(struct intel_gvt *gvt, unsigned int offset) { unsigned long device = intel_gvt_get_device_type(gvt); - struct gvt_mmio_block *block = gvt_mmio_blocks; + struct gvt_mmio_block *block = gvt->mmio.mmio_block; + int num = gvt->mmio.num_mmio_block; int i; - for (i = 0; i < ARRAY_SIZE(gvt_mmio_blocks); i++, block++) { + for (i = 0; i < num; i++, block++) { if (!(device & block->device)) continue; if (offset >= INTEL_GVT_MMIO_OFFSET(block->offset) && @@ -2912,6 +2896,17 @@ void intel_gvt_clean_mmio_info(struct intel_gvt *gvt) gvt->mmio.mmio_attribute = NULL; } +/* Special MMIO blocks. */ +static struct gvt_mmio_block mmio_blocks[] = { + {D_SKL_PLUS, _MMIO(CSR_MMIO_START_RANGE), 0x3000, NULL, NULL}, + {D_ALL, _MMIO(MCHBAR_MIRROR_BASE_SNB), 0x40000, NULL, NULL}, + {D_ALL, _MMIO(VGT_PVINFO_PAGE), VGT_PVINFO_SIZE, + pvinfo_mmio_read, pvinfo_mmio_write}, + {D_ALL, LGC_PALETTE(PIPE_A, 0), 1024, NULL, NULL}, + {D_ALL, LGC_PALETTE(PIPE_B, 0), 1024, NULL, NULL}, + {D_ALL, LGC_PALETTE(PIPE_C, 0), 1024, NULL, NULL}, +}; + /** * intel_gvt_setup_mmio_info - setup MMIO information table for GVT device * @gvt: GVT device @@ -2951,6 +2946,9 @@ int intel_gvt_setup_mmio_info(struct intel_gvt *gvt) goto err; } + gvt->mmio.mmio_block = mmio_blocks; + gvt->mmio.num_mmio_block = ARRAY_SIZE(mmio_blocks); + gvt_dbg_mmio("traced %u virtual mmio registers\n", gvt->mmio.num_tracked_mmio); return 0; @@ -3030,7 +3028,7 @@ int intel_vgpu_mmio_reg_rw(struct intel_vgpu *vgpu, unsigned int offset, gvt_mmio_func func; int ret; - if (WARN_ON(bytes > 4)) + if (WARN_ON(bytes > 8)) return -EINVAL; /* diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 4f7057d62d88..22e08eb2d0b7 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -432,7 +432,8 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id) i915_gem_request_put(fetch_and_zero(&workload->req)); - if (!workload->status && !vgpu->resetting) { + if (!workload->status && !(vgpu->resetting_eng & + ENGINE_MASK(ring_id))) { update_guest_context(workload); for_each_set_bit(event, workload->pending_events, diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 90c14e6e3ea0..3deadcbd5a24 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -480,11 +480,13 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr, { struct intel_gvt *gvt = vgpu->gvt; struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler; + unsigned int resetting_eng = dmlr ? ALL_ENGINES : engine_mask; gvt_dbg_core("------------------------------------------\n"); gvt_dbg_core("resseting vgpu%d, dmlr %d, engine_mask %08x\n", vgpu->id, dmlr, engine_mask); - vgpu->resetting = true; + + vgpu->resetting_eng = resetting_eng; intel_vgpu_stop_schedule(vgpu); /* @@ -497,7 +499,7 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr, mutex_lock(&gvt->lock); } - intel_vgpu_reset_execlist(vgpu, dmlr ? ALL_ENGINES : engine_mask); + intel_vgpu_reset_execlist(vgpu, resetting_eng); /* full GPU reset or device model level reset */ if (engine_mask == ALL_ENGINES || dmlr) { @@ -520,7 +522,7 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr, } } - vgpu->resetting = false; + vgpu->resetting_eng = 0; gvt_dbg_core("reset vgpu%d done\n", vgpu->id); gvt_dbg_core("------------------------------------------\n"); } diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c index 1032f98add11..77fb39808131 100644 --- a/drivers/gpu/drm/i915/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c @@ -43,16 +43,21 @@ static bool shrinker_lock(struct drm_i915_private *dev_priv, bool *unlock) return true; case MUTEX_TRYLOCK_FAILED: + *unlock = false; + preempt_disable(); do { cpu_relax(); if (mutex_trylock(&dev_priv->drm.struct_mutex)) { - case MUTEX_TRYLOCK_SUCCESS: *unlock = true; - return true; + break; } } while (!need_resched()); + preempt_enable(); + return *unlock; - return false; + case MUTEX_TRYLOCK_SUCCESS: + *unlock = true; + return true; } BUG(); diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 9cd22f83b0cf..f33d90226704 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -1601,11 +1601,11 @@ static int gen8_emit_oa_config(struct drm_i915_gem_request *req) u32 *cs; int i; - cs = intel_ring_begin(req, n_flex_regs * 2 + 4); + cs = intel_ring_begin(req, ARRAY_SIZE(flex_mmio) * 2 + 4); if (IS_ERR(cs)) return PTR_ERR(cs); - *cs++ = MI_LOAD_REGISTER_IMM(n_flex_regs + 1); + *cs++ = MI_LOAD_REGISTER_IMM(ARRAY_SIZE(flex_mmio) + 1); *cs++ = i915_mmio_reg_offset(GEN8_OACTXCONTROL); *cs++ = (dev_priv->perf.oa.period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) | diff --git a/drivers/gpu/drm/i915/intel_color.c b/drivers/gpu/drm/i915/intel_color.c index 306c6b06b330..17c4ae7e4e7c 100644 --- a/drivers/gpu/drm/i915/intel_color.c +++ b/drivers/gpu/drm/i915/intel_color.c @@ -398,6 +398,7 @@ static void bdw_load_gamma_lut(struct drm_crtc_state *state, u32 offset) } /* Program the max register to clamp values > 1.0. */ + i = lut_size - 1; I915_WRITE(PREC_PAL_GC_MAX(pipe, 0), drm_color_lut_extract(lut[i].red, 16)); I915_WRITE(PREC_PAL_GC_MAX(pipe, 1), diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index 96c2cbd81869..593349be8b9d 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -469,7 +469,7 @@ static u32 intel_panel_compute_brightness(struct intel_connector *connector, if (i915.invert_brightness > 0 || dev_priv->quirks & QUIRK_INVERT_BRIGHTNESS) { - return panel->backlight.max - val; + return panel->backlight.max - val + panel->backlight.min; } return val; diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig index b638d192ce5e..99d39b2aefa6 100644 --- a/drivers/gpu/drm/msm/Kconfig +++ b/drivers/gpu/drm/msm/Kconfig @@ -5,7 +5,7 @@ config DRM_MSM depends on ARCH_QCOM || (ARM && COMPILE_TEST) depends on OF && COMMON_CLK depends on MMU - select QCOM_MDT_LOADER + select QCOM_MDT_LOADER if ARCH_QCOM select REGULATOR select DRM_KMS_HELPER select DRM_PANEL diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index b4b54f1c24bc..f9eae03aa1dc 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -15,7 +15,7 @@ #include <linux/cpumask.h> #include <linux/qcom_scm.h> #include <linux/dma-mapping.h> -#include <linux/of_reserved_mem.h> +#include <linux/of_address.h> #include <linux/soc/qcom/mdt_loader.h> #include "msm_gem.h" #include "msm_mmu.h" @@ -26,16 +26,34 @@ static void a5xx_dump(struct msm_gpu *gpu); #define GPU_PAS_ID 13 -#if IS_ENABLED(CONFIG_QCOM_MDT_LOADER) - static int zap_shader_load_mdt(struct device *dev, const char *fwname) { const struct firmware *fw; + struct device_node *np; + struct resource r; phys_addr_t mem_phys; ssize_t mem_size; void *mem_region = NULL; int ret; + if (!IS_ENABLED(CONFIG_ARCH_QCOM)) + return -EINVAL; + + np = of_get_child_by_name(dev->of_node, "zap-shader"); + if (!np) + return -ENODEV; + + np = of_parse_phandle(np, "memory-region", 0); + if (!np) + return -EINVAL; + + ret = of_address_to_resource(np, 0, &r); + if (ret) + return ret; + + mem_phys = r.start; + mem_size = resource_size(&r); + /* Request the MDT file for the firmware */ ret = request_firmware(&fw, fwname, dev); if (ret) { @@ -51,7 +69,7 @@ static int zap_shader_load_mdt(struct device *dev, const char *fwname) } /* Allocate memory for the firmware image */ - mem_region = dmam_alloc_coherent(dev, mem_size, &mem_phys, GFP_KERNEL); + mem_region = memremap(mem_phys, mem_size, MEMREMAP_WC); if (!mem_region) { ret = -ENOMEM; goto out; @@ -69,16 +87,13 @@ static int zap_shader_load_mdt(struct device *dev, const char *fwname) DRM_DEV_ERROR(dev, "Unable to authorize the image\n"); out: + if (mem_region) + memunmap(mem_region); + release_firmware(fw); return ret; } -#else -static int zap_shader_load_mdt(struct device *dev, const char *fwname) -{ - return -ENODEV; -} -#endif static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, struct msm_file_private *ctx) @@ -117,12 +132,10 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, gpu->funcs->flush(gpu); } -struct a5xx_hwcg { +static const struct { u32 offset; u32 value; -}; - -static const struct a5xx_hwcg a530_hwcg[] = { +} a5xx_hwcg[] = { {REG_A5XX_RBBM_CLOCK_CNTL_SP0, 0x02222222}, {REG_A5XX_RBBM_CLOCK_CNTL_SP1, 0x02222222}, {REG_A5XX_RBBM_CLOCK_CNTL_SP2, 0x02222222}, @@ -217,38 +230,16 @@ static const struct a5xx_hwcg a530_hwcg[] = { {REG_A5XX_RBBM_CLOCK_DELAY_VFD, 0x00002222} }; -static const struct { - int (*test)(struct adreno_gpu *gpu); - const struct a5xx_hwcg *regs; - unsigned int count; -} a5xx_hwcg_regs[] = { - { adreno_is_a530, a530_hwcg, ARRAY_SIZE(a530_hwcg), }, -}; - -static void _a5xx_enable_hwcg(struct msm_gpu *gpu, - const struct a5xx_hwcg *regs, unsigned int count) +void a5xx_set_hwcg(struct msm_gpu *gpu, bool state) { unsigned int i; - for (i = 0; i < count; i++) - gpu_write(gpu, regs[i].offset, regs[i].value); + for (i = 0; i < ARRAY_SIZE(a5xx_hwcg); i++) + gpu_write(gpu, a5xx_hwcg[i].offset, + state ? a5xx_hwcg[i].value : 0); - gpu_write(gpu, REG_A5XX_RBBM_CLOCK_CNTL, 0xAAA8AA00); - gpu_write(gpu, REG_A5XX_RBBM_ISDB_CNT, 0x182); -} - -static void a5xx_enable_hwcg(struct msm_gpu *gpu) -{ - struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); - unsigned int i; - - for (i = 0; i < ARRAY_SIZE(a5xx_hwcg_regs); i++) { - if (a5xx_hwcg_regs[i].test(adreno_gpu)) { - _a5xx_enable_hwcg(gpu, a5xx_hwcg_regs[i].regs, - a5xx_hwcg_regs[i].count); - return; - } - } + gpu_write(gpu, REG_A5XX_RBBM_CLOCK_CNTL, state ? 0xAAA8AA00 : 0); + gpu_write(gpu, REG_A5XX_RBBM_ISDB_CNT, state ? 0x182 : 0x180); } static int a5xx_me_init(struct msm_gpu *gpu) @@ -377,45 +368,6 @@ static int a5xx_zap_shader_resume(struct msm_gpu *gpu) return ret; } -/* Set up a child device to "own" the zap shader */ -static int a5xx_zap_shader_dev_init(struct device *parent, struct device *dev) -{ - struct device_node *node; - int ret; - - if (dev->parent) - return 0; - - /* Find the sub-node for the zap shader */ - node = of_get_child_by_name(parent->of_node, "zap-shader"); - if (!node) { - DRM_DEV_ERROR(parent, "zap-shader not found in device tree\n"); - return -ENODEV; - } - - dev->parent = parent; - dev->of_node = node; - dev_set_name(dev, "adreno_zap_shader"); - - ret = device_register(dev); - if (ret) { - DRM_DEV_ERROR(parent, "Couldn't register zap shader device\n"); - goto out; - } - - ret = of_reserved_mem_device_init(dev); - if (ret) { - DRM_DEV_ERROR(parent, "Unable to set up the reserved memory\n"); - device_unregister(dev); - } - -out: - if (ret) - dev->parent = NULL; - - return ret; -} - static int a5xx_zap_shader_init(struct msm_gpu *gpu) { static bool loaded; @@ -444,11 +396,7 @@ static int a5xx_zap_shader_init(struct msm_gpu *gpu) return -ENODEV; } - ret = a5xx_zap_shader_dev_init(&pdev->dev, &a5xx_gpu->zap_dev); - - if (!ret) - ret = zap_shader_load_mdt(&a5xx_gpu->zap_dev, - adreno_gpu->info->zapfw); + ret = zap_shader_load_mdt(&pdev->dev, adreno_gpu->info->zapfw); loaded = !ret; @@ -545,7 +493,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu) gpu_write(gpu, REG_A5XX_RBBM_AHB_CNTL1, 0xA6FFFFFF); /* Enable HWCG */ - a5xx_enable_hwcg(gpu); + a5xx_set_hwcg(gpu, true); gpu_write(gpu, REG_A5XX_RBBM_AHB_CNTL2, 0x0000003F); @@ -691,9 +639,6 @@ static void a5xx_destroy(struct msm_gpu *gpu) DBG("%s", gpu->name); - if (a5xx_gpu->zap_dev.parent) - device_unregister(&a5xx_gpu->zap_dev); - if (a5xx_gpu->pm4_bo) { if (a5xx_gpu->pm4_iova) msm_gem_put_iova(a5xx_gpu->pm4_bo, gpu->aspace); @@ -920,31 +865,30 @@ static const u32 a5xx_registers[] = { 0x0000, 0x0002, 0x0004, 0x0020, 0x0022, 0x0026, 0x0029, 0x002B, 0x002E, 0x0035, 0x0038, 0x0042, 0x0044, 0x0044, 0x0047, 0x0095, 0x0097, 0x00BB, 0x03A0, 0x0464, 0x0469, 0x046F, 0x04D2, 0x04D3, - 0x04E0, 0x0533, 0x0540, 0x0555, 0xF400, 0xF400, 0xF800, 0xF807, - 0x0800, 0x081A, 0x081F, 0x0841, 0x0860, 0x0860, 0x0880, 0x08A0, - 0x0B00, 0x0B12, 0x0B15, 0x0B28, 0x0B78, 0x0B7F, 0x0BB0, 0x0BBD, - 0x0BC0, 0x0BC6, 0x0BD0, 0x0C53, 0x0C60, 0x0C61, 0x0C80, 0x0C82, - 0x0C84, 0x0C85, 0x0C90, 0x0C98, 0x0CA0, 0x0CA0, 0x0CB0, 0x0CB2, - 0x2180, 0x2185, 0x2580, 0x2585, 0x0CC1, 0x0CC1, 0x0CC4, 0x0CC7, - 0x0CCC, 0x0CCC, 0x0CD0, 0x0CD8, 0x0CE0, 0x0CE5, 0x0CE8, 0x0CE8, - 0x0CEC, 0x0CF1, 0x0CFB, 0x0D0E, 0x2100, 0x211E, 0x2140, 0x2145, - 0x2500, 0x251E, 0x2540, 0x2545, 0x0D10, 0x0D17, 0x0D20, 0x0D23, - 0x0D30, 0x0D30, 0x20C0, 0x20C0, 0x24C0, 0x24C0, 0x0E40, 0x0E43, - 0x0E4A, 0x0E4A, 0x0E50, 0x0E57, 0x0E60, 0x0E7C, 0x0E80, 0x0E8E, - 0x0E90, 0x0E96, 0x0EA0, 0x0EA8, 0x0EB0, 0x0EB2, 0xE140, 0xE147, - 0xE150, 0xE187, 0xE1A0, 0xE1A9, 0xE1B0, 0xE1B6, 0xE1C0, 0xE1C7, - 0xE1D0, 0xE1D1, 0xE200, 0xE201, 0xE210, 0xE21C, 0xE240, 0xE268, - 0xE000, 0xE006, 0xE010, 0xE09A, 0xE0A0, 0xE0A4, 0xE0AA, 0xE0EB, - 0xE100, 0xE105, 0xE380, 0xE38F, 0xE3B0, 0xE3B0, 0xE400, 0xE405, - 0xE408, 0xE4E9, 0xE4F0, 0xE4F0, 0xE280, 0xE280, 0xE282, 0xE2A3, - 0xE2A5, 0xE2C2, 0xE940, 0xE947, 0xE950, 0xE987, 0xE9A0, 0xE9A9, - 0xE9B0, 0xE9B6, 0xE9C0, 0xE9C7, 0xE9D0, 0xE9D1, 0xEA00, 0xEA01, - 0xEA10, 0xEA1C, 0xEA40, 0xEA68, 0xE800, 0xE806, 0xE810, 0xE89A, - 0xE8A0, 0xE8A4, 0xE8AA, 0xE8EB, 0xE900, 0xE905, 0xEB80, 0xEB8F, - 0xEBB0, 0xEBB0, 0xEC00, 0xEC05, 0xEC08, 0xECE9, 0xECF0, 0xECF0, - 0xEA80, 0xEA80, 0xEA82, 0xEAA3, 0xEAA5, 0xEAC2, 0xA800, 0xA8FF, - 0xAC60, 0xAC60, 0xB000, 0xB97F, 0xB9A0, 0xB9BF, - ~0 + 0x04E0, 0x0533, 0x0540, 0x0555, 0x0800, 0x081A, 0x081F, 0x0841, + 0x0860, 0x0860, 0x0880, 0x08A0, 0x0B00, 0x0B12, 0x0B15, 0x0B28, + 0x0B78, 0x0B7F, 0x0BB0, 0x0BBD, 0x0BC0, 0x0BC6, 0x0BD0, 0x0C53, + 0x0C60, 0x0C61, 0x0C80, 0x0C82, 0x0C84, 0x0C85, 0x0C90, 0x0C98, + 0x0CA0, 0x0CA0, 0x0CB0, 0x0CB2, 0x2180, 0x2185, 0x2580, 0x2585, + 0x0CC1, 0x0CC1, 0x0CC4, 0x0CC7, 0x0CCC, 0x0CCC, 0x0CD0, 0x0CD8, + 0x0CE0, 0x0CE5, 0x0CE8, 0x0CE8, 0x0CEC, 0x0CF1, 0x0CFB, 0x0D0E, + 0x2100, 0x211E, 0x2140, 0x2145, 0x2500, 0x251E, 0x2540, 0x2545, + 0x0D10, 0x0D17, 0x0D20, 0x0D23, 0x0D30, 0x0D30, 0x20C0, 0x20C0, + 0x24C0, 0x24C0, 0x0E40, 0x0E43, 0x0E4A, 0x0E4A, 0x0E50, 0x0E57, + 0x0E60, 0x0E7C, 0x0E80, 0x0E8E, 0x0E90, 0x0E96, 0x0EA0, 0x0EA8, + 0x0EB0, 0x0EB2, 0xE140, 0xE147, 0xE150, 0xE187, 0xE1A0, 0xE1A9, + 0xE1B0, 0xE1B6, 0xE1C0, 0xE1C7, 0xE1D0, 0xE1D1, 0xE200, 0xE201, + 0xE210, 0xE21C, 0xE240, 0xE268, 0xE000, 0xE006, 0xE010, 0xE09A, + 0xE0A0, 0xE0A4, 0xE0AA, 0xE0EB, 0xE100, 0xE105, 0xE380, 0xE38F, + 0xE3B0, 0xE3B0, 0xE400, 0xE405, 0xE408, 0xE4E9, 0xE4F0, 0xE4F0, + 0xE280, 0xE280, 0xE282, 0xE2A3, 0xE2A5, 0xE2C2, 0xE940, 0xE947, + 0xE950, 0xE987, 0xE9A0, 0xE9A9, 0xE9B0, 0xE9B6, 0xE9C0, 0xE9C7, + 0xE9D0, 0xE9D1, 0xEA00, 0xEA01, 0xEA10, 0xEA1C, 0xEA40, 0xEA68, + 0xE800, 0xE806, 0xE810, 0xE89A, 0xE8A0, 0xE8A4, 0xE8AA, 0xE8EB, + 0xE900, 0xE905, 0xEB80, 0xEB8F, 0xEBB0, 0xEBB0, 0xEC00, 0xEC05, + 0xEC08, 0xECE9, 0xECF0, 0xECF0, 0xEA80, 0xEA80, 0xEA82, 0xEAA3, + 0xEAA5, 0xEAC2, 0xA800, 0xA8FF, 0xAC60, 0xAC60, 0xB000, 0xB97F, + 0xB9A0, 0xB9BF, ~0 }; static void a5xx_dump(struct msm_gpu *gpu) @@ -1020,7 +964,14 @@ static void a5xx_show(struct msm_gpu *gpu, struct seq_file *m) { seq_printf(m, "status: %08x\n", gpu_read(gpu, REG_A5XX_RBBM_STATUS)); + + /* + * Temporarily disable hardware clock gating before going into + * adreno_show to avoid issues while reading the registers + */ + a5xx_set_hwcg(gpu, false); adreno_show(gpu, m); + a5xx_set_hwcg(gpu, true); } #endif diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h index 6638bc85645d..1137092241d5 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h @@ -36,8 +36,6 @@ struct a5xx_gpu { uint32_t gpmu_dwords; uint32_t lm_leakage; - - struct device zap_dev; }; #define to_a5xx_gpu(x) container_of(x, struct a5xx_gpu, base) @@ -59,5 +57,6 @@ static inline int spin_usecs(struct msm_gpu *gpu, uint32_t usecs, } bool a5xx_idle(struct msm_gpu *gpu); +void a5xx_set_hwcg(struct msm_gpu *gpu, bool state); #endif /* __A5XX_GPU_H__ */ diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index f1ab2703674a..7414c6bbd582 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -48,8 +48,15 @@ int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value) *value = adreno_gpu->base.fast_rate; return 0; case MSM_PARAM_TIMESTAMP: - if (adreno_gpu->funcs->get_timestamp) - return adreno_gpu->funcs->get_timestamp(gpu, value); + if (adreno_gpu->funcs->get_timestamp) { + int ret; + + pm_runtime_get_sync(&gpu->pdev->dev); + ret = adreno_gpu->funcs->get_timestamp(gpu, value); + pm_runtime_put_autosuspend(&gpu->pdev->dev); + + return ret; + } return -EINVAL; default: DBG("%s: invalid param: %u", gpu->name, param); diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 9e9c5696bc03..c7b612c3d771 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -2137,6 +2137,13 @@ void msm_dsi_host_get_phy_clk_req(struct mipi_dsi_host *host, struct msm_dsi_phy_clk_request *clk_req) { struct msm_dsi_host *msm_host = to_msm_dsi_host(host); + int ret; + + ret = dsi_calc_clk_rate(msm_host); + if (ret) { + pr_err("%s: unable to calc clk rate, %d\n", __func__, ret); + return; + } clk_req->bitclk_rate = msm_host->byte_clk_rate * 8; clk_req->escclk_rate = msm_host->esc_clk_rate; @@ -2280,7 +2287,6 @@ int msm_dsi_host_set_display_mode(struct mipi_dsi_host *host, struct drm_display_mode *mode) { struct msm_dsi_host *msm_host = to_msm_dsi_host(host); - int ret; if (msm_host->mode) { drm_mode_destroy(msm_host->dev, msm_host->mode); @@ -2293,12 +2299,6 @@ int msm_dsi_host_set_display_mode(struct mipi_dsi_host *host, return -ENOMEM; } - ret = dsi_calc_clk_rate(msm_host); - if (ret) { - pr_err("%s: unable to calc clk rate, %d\n", __func__, ret); - return ret; - } - return 0; } diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c index cb5415d6c04b..735a87a699fa 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c @@ -221,8 +221,8 @@ static void blend_setup(struct drm_crtc *crtc) struct mdp5_ctl *ctl = mdp5_cstate->ctl; uint32_t blend_op, fg_alpha, bg_alpha, ctl_blend_flags = 0; unsigned long flags; - enum mdp5_pipe stage[STAGE_MAX + 1][MAX_PIPE_STAGE] = { SSPP_NONE }; - enum mdp5_pipe r_stage[STAGE_MAX + 1][MAX_PIPE_STAGE] = { SSPP_NONE }; + enum mdp5_pipe stage[STAGE_MAX + 1][MAX_PIPE_STAGE] = { { SSPP_NONE } }; + enum mdp5_pipe r_stage[STAGE_MAX + 1][MAX_PIPE_STAGE] = { { SSPP_NONE } }; int i, plane_cnt = 0; bool bg_alpha_enabled = false; u32 mixer_op_mode = 0; @@ -753,6 +753,7 @@ static int mdp5_crtc_cursor_set(struct drm_crtc *crtc, if (!handle) { DBG("Cursor off"); cursor_enable = false; + mdp5_enable(mdp5_kms); goto set_cursor; } @@ -776,6 +777,8 @@ static int mdp5_crtc_cursor_set(struct drm_crtc *crtc, get_roi(crtc, &roi_w, &roi_h); + mdp5_enable(mdp5_kms); + mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_STRIDE(lm), stride); mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_FORMAT(lm), MDP5_LM_CURSOR_FORMAT_FORMAT(CURSOR_FMT_ARGB8888)); @@ -804,6 +807,7 @@ set_cursor: crtc_flush(crtc, flush_mask); end: + mdp5_disable(mdp5_kms); if (old_bo) { drm_flip_work_queue(&mdp5_crtc->unref_cursor_work, old_bo); /* enable vblank to complete cursor work: */ @@ -836,6 +840,8 @@ static int mdp5_crtc_cursor_move(struct drm_crtc *crtc, int x, int y) get_roi(crtc, &roi_w, &roi_h); + mdp5_enable(mdp5_kms); + spin_lock_irqsave(&mdp5_crtc->cursor.lock, flags); mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_SIZE(lm), MDP5_LM_CURSOR_SIZE_ROI_H(roi_h) | @@ -847,6 +853,8 @@ static int mdp5_crtc_cursor_move(struct drm_crtc *crtc, int x, int y) crtc_flush(crtc, flush_mask); + mdp5_disable(mdp5_kms); + return 0; } diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_encoder.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_encoder.c index 97f3294fbfc6..70bef51245af 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_encoder.c +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_encoder.c @@ -299,7 +299,7 @@ static void mdp5_encoder_enable(struct drm_encoder *encoder) struct mdp5_interface *intf = mdp5_encoder->intf; if (intf->mode == MDP5_INTF_DSI_MODE_COMMAND) - mdp5_cmd_encoder_disable(encoder); + mdp5_cmd_encoder_enable(encoder); else mdp5_vid_encoder_enable(encoder); } diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c index 5d13fa5381ee..1c603aef3c59 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c @@ -502,7 +502,7 @@ static int get_clk(struct platform_device *pdev, struct clk **clkp, const char *name, bool mandatory) { struct device *dev = &pdev->dev; - struct clk *clk = devm_clk_get(dev, name); + struct clk *clk = msm_clk_get(pdev, name); if (IS_ERR(clk) && mandatory) { dev_err(dev, "failed to get %s (%ld)\n", name, PTR_ERR(clk)); return PTR_ERR(clk); @@ -887,21 +887,21 @@ static int mdp5_init(struct platform_device *pdev, struct drm_device *dev) } /* mandatory clocks: */ - ret = get_clk(pdev, &mdp5_kms->axi_clk, "bus_clk", true); + ret = get_clk(pdev, &mdp5_kms->axi_clk, "bus", true); if (ret) goto fail; - ret = get_clk(pdev, &mdp5_kms->ahb_clk, "iface_clk", true); + ret = get_clk(pdev, &mdp5_kms->ahb_clk, "iface", true); if (ret) goto fail; - ret = get_clk(pdev, &mdp5_kms->core_clk, "core_clk", true); + ret = get_clk(pdev, &mdp5_kms->core_clk, "core", true); if (ret) goto fail; - ret = get_clk(pdev, &mdp5_kms->vsync_clk, "vsync_clk", true); + ret = get_clk(pdev, &mdp5_kms->vsync_clk, "vsync", true); if (ret) goto fail; /* optional clocks: */ - get_clk(pdev, &mdp5_kms->lut_clk, "lut_clk", false); + get_clk(pdev, &mdp5_kms->lut_clk, "lut", false); /* we need to set a default rate before enabling. Set a safe * rate first, then figure out hw revision, and then set a diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c index fe3a4de1a433..61f39c86dd09 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c @@ -890,8 +890,8 @@ static int mdp5_plane_mode_set(struct drm_plane *plane, struct mdp5_hw_pipe *right_hwpipe; const struct mdp_format *format; uint32_t nplanes, config = 0; - struct phase_step step = { 0 }; - struct pixel_ext pe = { 0 }; + struct phase_step step = { { 0 } }; + struct pixel_ext pe = { { 0 } }; uint32_t hdecm = 0, vdecm = 0; uint32_t pix_format; unsigned int rotation; diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 65f35544c1ec..a0c60e738db8 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -383,8 +383,10 @@ int msm_gem_get_iova(struct drm_gem_object *obj, struct page **pages; vma = add_vma(obj, aspace); - if (IS_ERR(vma)) - return PTR_ERR(vma); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto unlock; + } pages = get_pages(obj); if (IS_ERR(pages)) { @@ -405,7 +407,7 @@ int msm_gem_get_iova(struct drm_gem_object *obj, fail: del_vma(vma); - +unlock: mutex_unlock(&msm_obj->lock); return ret; } @@ -928,8 +930,12 @@ static struct drm_gem_object *_msm_gem_new(struct drm_device *dev, if (use_vram) { struct msm_gem_vma *vma; struct page **pages; + struct msm_gem_object *msm_obj = to_msm_bo(obj); + + mutex_lock(&msm_obj->lock); vma = add_vma(obj, NULL); + mutex_unlock(&msm_obj->lock); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto fail; diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 6bfca7470141..8a75c0bd8a78 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -34,8 +34,8 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev, struct msm_gpu *gpu, uint32_t nr_bos, uint32_t nr_cmds) { struct msm_gem_submit *submit; - uint64_t sz = sizeof(*submit) + (nr_bos * sizeof(submit->bos[0])) + - (nr_cmds * sizeof(submit->cmd[0])); + uint64_t sz = sizeof(*submit) + ((u64)nr_bos * sizeof(submit->bos[0])) + + ((u64)nr_cmds * sizeof(submit->cmd[0])); if (sz > SIZE_MAX) return NULL; @@ -451,7 +451,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, if (ret) goto out; - if (!(args->fence & MSM_SUBMIT_NO_IMPLICIT)) { + if (!(args->flags & MSM_SUBMIT_NO_IMPLICIT)) { ret = submit_fence_sync(submit); if (ret) goto out; diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c index c36321bc8714..d34e331554f3 100644 --- a/drivers/gpu/drm/msm/msm_gem_vma.c +++ b/drivers/gpu/drm/msm/msm_gem_vma.c @@ -42,7 +42,7 @@ void msm_gem_unmap_vma(struct msm_gem_address_space *aspace, struct msm_gem_vma *vma, struct sg_table *sgt) { - if (!vma->iova) + if (!aspace || !vma->iova) return; if (aspace->mmu) { diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c index c7c84d34d97e..88582af8bd89 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c @@ -267,6 +267,8 @@ nvkm_disp_oneinit(struct nvkm_engine *engine) /* Create output path objects for each VBIOS display path. */ i = -1; while ((data = dcb_outp_parse(bios, ++i, &ver, &hdr, &dcbE))) { + if (ver < 0x40) /* No support for chipsets prior to NV50. */ + break; if (dcbE.type == DCB_OUTPUT_UNUSED) continue; if (dcbE.type == DCB_OUTPUT_EOL) diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index 5d450332c2fd..2900f1410d95 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -500,7 +500,7 @@ static void vop_line_flag_irq_disable(struct vop *vop) static int vop_enable(struct drm_crtc *crtc) { struct vop *vop = to_vop(crtc); - int ret; + int ret, i; ret = pm_runtime_get_sync(vop->dev); if (ret < 0) { @@ -533,6 +533,20 @@ static int vop_enable(struct drm_crtc *crtc) } memcpy(vop->regs, vop->regsbak, vop->len); + /* + * We need to make sure that all windows are disabled before we + * enable the crtc. Otherwise we might try to scan from a destroyed + * buffer later. + */ + for (i = 0; i < vop->data->win_size; i++) { + struct vop_win *vop_win = &vop->win[i]; + const struct vop_win_data *win = vop_win->data; + + spin_lock(&vop->reg_lock); + VOP_WIN_SET(vop, win, enable, 0); + spin_unlock(&vop->reg_lock); + } + vop_cfg_done(vop); /* @@ -566,28 +580,11 @@ err_put_pm_runtime: static void vop_crtc_disable(struct drm_crtc *crtc) { struct vop *vop = to_vop(crtc); - int i; WARN_ON(vop->event); rockchip_drm_psr_deactivate(&vop->crtc); - /* - * We need to make sure that all windows are disabled before we - * disable that crtc. Otherwise we might try to scan from a destroyed - * buffer later. - */ - for (i = 0; i < vop->data->win_size; i++) { - struct vop_win *vop_win = &vop->win[i]; - const struct vop_win_data *win = vop_win->data; - - spin_lock(&vop->reg_lock); - VOP_WIN_SET(vop, win, enable, 0); - spin_unlock(&vop->reg_lock); - } - - vop_cfg_done(vop); - drm_crtc_vblank_off(crtc); /* @@ -682,8 +679,10 @@ static int vop_plane_atomic_check(struct drm_plane *plane, * Src.x1 can be odd when do clip, but yuv plane start point * need align with 2 pixel. */ - if (is_yuv_support(fb->format->format) && ((state->src.x1 >> 16) % 2)) + if (is_yuv_support(fb->format->format) && ((state->src.x1 >> 16) % 2)) { + DRM_ERROR("Invalid Source: Yuv format not support odd xpos\n"); return -EINVAL; + } return 0; } @@ -764,7 +763,7 @@ static void vop_plane_atomic_update(struct drm_plane *plane, spin_lock(&vop->reg_lock); VOP_WIN_SET(vop, win, format, format); - VOP_WIN_SET(vop, win, yrgb_vir, fb->pitches[0] >> 2); + VOP_WIN_SET(vop, win, yrgb_vir, DIV_ROUND_UP(fb->pitches[0], 4)); VOP_WIN_SET(vop, win, yrgb_mst, dma_addr); if (is_yuv_support(fb->format->format)) { int hsub = drm_format_horz_chroma_subsampling(fb->format->format); @@ -778,7 +777,7 @@ static void vop_plane_atomic_update(struct drm_plane *plane, offset += (src->y1 >> 16) * fb->pitches[1] / vsub; dma_addr = rk_uv_obj->dma_addr + offset + fb->offsets[1]; - VOP_WIN_SET(vop, win, uv_vir, fb->pitches[1] >> 2); + VOP_WIN_SET(vop, win, uv_vir, DIV_ROUND_UP(fb->pitches[1], 4)); VOP_WIN_SET(vop, win, uv_mst, dma_addr); } diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h index 9979fd0c2282..27eefbfcf3d0 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h @@ -282,6 +282,9 @@ static inline uint16_t scl_get_bili_dn_vskip(int src_h, int dst_h, act_height = (src_h + vskiplines - 1) / vskiplines; + if (act_height == dst_h) + return GET_SCL_FT_BILI_DN(src_h, dst_h) / vskiplines; + return GET_SCL_FT_BILI_DN(act_height, dst_h); } diff --git a/drivers/gpu/drm/stm/Kconfig b/drivers/gpu/drm/stm/Kconfig index 2c4817fb0890..8fe5b184b4e8 100644 --- a/drivers/gpu/drm/stm/Kconfig +++ b/drivers/gpu/drm/stm/Kconfig @@ -7,7 +7,6 @@ config DRM_STM select DRM_PANEL select VIDEOMODE_HELPERS select FB_PROVIDE_GET_FB_UNMAPPED_AREA - default y help Enable support for the on-chip display controller on diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index 1006b230b236..65fa29591d21 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -983,7 +983,7 @@ config I2C_UNIPHIER_F config I2C_VERSATILE tristate "ARM Versatile/Realview I2C bus support" - depends on ARCH_VERSATILE || ARCH_REALVIEW || ARCH_VEXPRESS || COMPILE_TEST + depends on ARCH_MPS2 || ARCH_VERSATILE || ARCH_REALVIEW || ARCH_VEXPRESS || COMPILE_TEST select I2C_ALGOBIT help Say yes if you want to support the I2C serial bus on ARMs Versatile diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c index 2ea6d0d25a01..143a8fd582b4 100644 --- a/drivers/i2c/busses/i2c-designware-platdrv.c +++ b/drivers/i2c/busses/i2c-designware-platdrv.c @@ -298,6 +298,9 @@ static int dw_i2c_plat_probe(struct platform_device *pdev) } acpi_speed = i2c_acpi_find_bus_speed(&pdev->dev); + /* Some broken DSTDs use 1MiHz instead of 1MHz */ + if (acpi_speed == 1048576) + acpi_speed = 1000000; /* * Find bus speed from the "clock-frequency" device property, ACPI * or by using fast mode if neither is set. @@ -319,7 +322,8 @@ static int dw_i2c_plat_probe(struct platform_device *pdev) if (dev->clk_freq != 100000 && dev->clk_freq != 400000 && dev->clk_freq != 1000000 && dev->clk_freq != 3400000) { dev_err(&pdev->dev, - "Only 100kHz, 400kHz, 1MHz and 3.4MHz supported"); + "%d Hz is unsupported, only 100kHz, 400kHz, 1MHz and 3.4MHz are supported\n", + dev->clk_freq); ret = -EINVAL; goto exit_reset; } diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c index 4842ec3a5451..a9126b3cda61 100644 --- a/drivers/i2c/i2c-core-acpi.c +++ b/drivers/i2c/i2c-core-acpi.c @@ -230,6 +230,16 @@ void i2c_acpi_register_devices(struct i2c_adapter *adap) dev_warn(&adap->dev, "failed to enumerate I2C slaves\n"); } +const struct acpi_device_id * +i2c_acpi_match_device(const struct acpi_device_id *matches, + struct i2c_client *client) +{ + if (!(client && matches)) + return NULL; + + return acpi_match_device(matches, &client->dev); +} + static acpi_status i2c_acpi_lookup_speed(acpi_handle handle, u32 level, void *data, void **return_value) { @@ -289,7 +299,7 @@ u32 i2c_acpi_find_bus_speed(struct device *dev) } EXPORT_SYMBOL_GPL(i2c_acpi_find_bus_speed); -static int i2c_acpi_match_adapter(struct device *dev, void *data) +static int i2c_acpi_find_match_adapter(struct device *dev, void *data) { struct i2c_adapter *adapter = i2c_verify_adapter(dev); @@ -299,7 +309,7 @@ static int i2c_acpi_match_adapter(struct device *dev, void *data) return ACPI_HANDLE(dev) == (acpi_handle)data; } -static int i2c_acpi_match_device(struct device *dev, void *data) +static int i2c_acpi_find_match_device(struct device *dev, void *data) { return ACPI_COMPANION(dev) == data; } @@ -309,7 +319,7 @@ static struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle handle) struct device *dev; dev = bus_find_device(&i2c_bus_type, NULL, handle, - i2c_acpi_match_adapter); + i2c_acpi_find_match_adapter); return dev ? i2c_verify_adapter(dev) : NULL; } @@ -317,7 +327,8 @@ static struct i2c_client *i2c_acpi_find_client_by_adev(struct acpi_device *adev) { struct device *dev; - dev = bus_find_device(&i2c_bus_type, NULL, adev, i2c_acpi_match_device); + dev = bus_find_device(&i2c_bus_type, NULL, adev, + i2c_acpi_find_match_device); return dev ? i2c_verify_client(dev) : NULL; } diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index c89dac7fd2e7..12822a4b8f8f 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -357,6 +357,7 @@ static int i2c_device_probe(struct device *dev) * Tree match table entry is supplied for the probing device. */ if (!driver->id_table && + !i2c_acpi_match_device(dev->driver->acpi_match_table, client) && !i2c_of_match_device(dev->driver->of_match_table, client)) return -ENODEV; diff --git a/drivers/i2c/i2c-core.h b/drivers/i2c/i2c-core.h index 3b63f5e5b89c..3d3d9bf02101 100644 --- a/drivers/i2c/i2c-core.h +++ b/drivers/i2c/i2c-core.h @@ -31,9 +31,18 @@ int i2c_check_addr_validity(unsigned addr, unsigned short flags); int i2c_check_7bit_addr_validity_strict(unsigned short addr); #ifdef CONFIG_ACPI +const struct acpi_device_id * +i2c_acpi_match_device(const struct acpi_device_id *matches, + struct i2c_client *client); void i2c_acpi_register_devices(struct i2c_adapter *adap); #else /* CONFIG_ACPI */ static inline void i2c_acpi_register_devices(struct i2c_adapter *adap) { } +static inline const struct acpi_device_id * +i2c_acpi_match_device(const struct acpi_device_id *matches, + struct i2c_client *client) +{ + return NULL; +} #endif /* CONFIG_ACPI */ extern struct notifier_block i2c_acpi_notifier; diff --git a/drivers/i2c/muxes/Kconfig b/drivers/i2c/muxes/Kconfig index 2c64d0e0740f..17121329bb79 100644 --- a/drivers/i2c/muxes/Kconfig +++ b/drivers/i2c/muxes/Kconfig @@ -83,7 +83,7 @@ config I2C_MUX_PINCTRL different sets of pins at run-time. This driver can also be built as a module. If so, the module will be - called pinctrl-i2cmux. + called i2c-mux-pinctrl. config I2C_MUX_REG tristate "Register-based I2C multiplexer" diff --git a/drivers/iio/accel/bmc150-accel-core.c b/drivers/iio/accel/bmc150-accel-core.c index 6b5d3be283c4..807299dd45eb 100644 --- a/drivers/iio/accel/bmc150-accel-core.c +++ b/drivers/iio/accel/bmc150-accel-core.c @@ -193,7 +193,6 @@ struct bmc150_accel_data { struct regmap *regmap; int irq; struct bmc150_accel_interrupt interrupts[BMC150_ACCEL_INTERRUPTS]; - atomic_t active_intr; struct bmc150_accel_trigger triggers[BMC150_ACCEL_TRIGGERS]; struct mutex mutex; u8 fifo_mode, watermark; @@ -493,11 +492,6 @@ static int bmc150_accel_set_interrupt(struct bmc150_accel_data *data, int i, goto out_fix_power_state; } - if (state) - atomic_inc(&data->active_intr); - else - atomic_dec(&data->active_intr); - return 0; out_fix_power_state: @@ -1710,8 +1704,7 @@ static int bmc150_accel_resume(struct device *dev) struct bmc150_accel_data *data = iio_priv(indio_dev); mutex_lock(&data->mutex); - if (atomic_read(&data->active_intr)) - bmc150_accel_set_mode(data, BMC150_ACCEL_SLEEP_MODE_NORMAL, 0); + bmc150_accel_set_mode(data, BMC150_ACCEL_SLEEP_MODE_NORMAL, 0); bmc150_accel_fifo_set_mode(data); mutex_unlock(&data->mutex); diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c index 07d1489cd457..e44f62bf9caa 100644 --- a/drivers/iio/accel/st_accel_core.c +++ b/drivers/iio/accel/st_accel_core.c @@ -166,6 +166,10 @@ static const struct st_sensor_settings st_accel_sensors_settings[] = { .mask_ihl = 0x02, .addr_stat_drdy = ST_SENSORS_DEFAULT_STAT_ADDR, }, + .sim = { + .addr = 0x23, + .value = BIT(0), + }, .multi_read_bit = true, .bootime = 2, }, @@ -234,6 +238,10 @@ static const struct st_sensor_settings st_accel_sensors_settings[] = { .mask_od = 0x40, .addr_stat_drdy = ST_SENSORS_DEFAULT_STAT_ADDR, }, + .sim = { + .addr = 0x23, + .value = BIT(0), + }, .multi_read_bit = true, .bootime = 2, }, @@ -316,6 +324,10 @@ static const struct st_sensor_settings st_accel_sensors_settings[] = { .en_mask = 0x08, }, }, + .sim = { + .addr = 0x24, + .value = BIT(0), + }, .multi_read_bit = false, .bootime = 2, }, @@ -379,6 +391,10 @@ static const struct st_sensor_settings st_accel_sensors_settings[] = { .mask_int1 = 0x04, .addr_stat_drdy = ST_SENSORS_DEFAULT_STAT_ADDR, }, + .sim = { + .addr = 0x21, + .value = BIT(1), + }, .multi_read_bit = true, .bootime = 2, /* guess */ }, @@ -437,6 +453,10 @@ static const struct st_sensor_settings st_accel_sensors_settings[] = { .mask_od = 0x40, .addr_stat_drdy = ST_SENSORS_DEFAULT_STAT_ADDR, }, + .sim = { + .addr = 0x21, + .value = BIT(7), + }, .multi_read_bit = false, .bootime = 2, /* guess */ }, @@ -499,6 +519,10 @@ static const struct st_sensor_settings st_accel_sensors_settings[] = { .addr_ihl = 0x22, .mask_ihl = 0x80, }, + .sim = { + .addr = 0x23, + .value = BIT(0), + }, .multi_read_bit = true, .bootime = 2, }, @@ -547,6 +571,10 @@ static const struct st_sensor_settings st_accel_sensors_settings[] = { .mask_int1 = 0x04, .addr_stat_drdy = ST_SENSORS_DEFAULT_STAT_ADDR, }, + .sim = { + .addr = 0x21, + .value = BIT(1), + }, .multi_read_bit = false, .bootime = 2, }, @@ -614,6 +642,10 @@ static const struct st_sensor_settings st_accel_sensors_settings[] = { .mask_ihl = 0x02, .addr_stat_drdy = ST_SENSORS_DEFAULT_STAT_ADDR, }, + .sim = { + .addr = 0x23, + .value = BIT(0), + }, .multi_read_bit = true, .bootime = 2, }, diff --git a/drivers/iio/adc/aspeed_adc.c b/drivers/iio/adc/aspeed_adc.c index e0ea411a0b2d..c02b23d675cb 100644 --- a/drivers/iio/adc/aspeed_adc.c +++ b/drivers/iio/adc/aspeed_adc.c @@ -22,6 +22,7 @@ #include <linux/iio/iio.h> #include <linux/iio/driver.h> +#include <linux/iopoll.h> #define ASPEED_RESOLUTION_BITS 10 #define ASPEED_CLOCKS_PER_SAMPLE 12 @@ -38,11 +39,17 @@ #define ASPEED_ENGINE_ENABLE BIT(0) +#define ASPEED_ADC_CTRL_INIT_RDY BIT(8) + +#define ASPEED_ADC_INIT_POLLING_TIME 500 +#define ASPEED_ADC_INIT_TIMEOUT 500000 + struct aspeed_adc_model_data { const char *model_name; unsigned int min_sampling_rate; // Hz unsigned int max_sampling_rate; // Hz unsigned int vref_voltage; // mV + bool wait_init_sequence; }; struct aspeed_adc_data { @@ -211,6 +218,24 @@ static int aspeed_adc_probe(struct platform_device *pdev) goto scaler_error; } + model_data = of_device_get_match_data(&pdev->dev); + + if (model_data->wait_init_sequence) { + /* Enable engine in normal mode. */ + writel(ASPEED_OPERATION_MODE_NORMAL | ASPEED_ENGINE_ENABLE, + data->base + ASPEED_REG_ENGINE_CONTROL); + + /* Wait for initial sequence complete. */ + ret = readl_poll_timeout(data->base + ASPEED_REG_ENGINE_CONTROL, + adc_engine_control_reg_val, + adc_engine_control_reg_val & + ASPEED_ADC_CTRL_INIT_RDY, + ASPEED_ADC_INIT_POLLING_TIME, + ASPEED_ADC_INIT_TIMEOUT); + if (ret) + goto scaler_error; + } + /* Start all channels in normal mode. */ ret = clk_prepare_enable(data->clk_scaler->clk); if (ret) @@ -274,6 +299,7 @@ static const struct aspeed_adc_model_data ast2500_model_data = { .vref_voltage = 1800, // mV .min_sampling_rate = 1, .max_sampling_rate = 1000000, + .wait_init_sequence = true, }; static const struct of_device_id aspeed_adc_matches[] = { diff --git a/drivers/iio/adc/axp288_adc.c b/drivers/iio/adc/axp288_adc.c index 64799ad7ebad..462a99c13e7a 100644 --- a/drivers/iio/adc/axp288_adc.c +++ b/drivers/iio/adc/axp288_adc.c @@ -28,6 +28,8 @@ #include <linux/iio/driver.h> #define AXP288_ADC_EN_MASK 0xF1 +#define AXP288_ADC_TS_PIN_GPADC 0xF2 +#define AXP288_ADC_TS_PIN_ON 0xF3 enum axp288_adc_id { AXP288_ADC_TS, @@ -121,6 +123,26 @@ static int axp288_adc_read_channel(int *val, unsigned long address, return IIO_VAL_INT; } +static int axp288_adc_set_ts(struct regmap *regmap, unsigned int mode, + unsigned long address) +{ + int ret; + + /* channels other than GPADC do not need to switch TS pin */ + if (address != AXP288_GP_ADC_H) + return 0; + + ret = regmap_write(regmap, AXP288_ADC_TS_PIN_CTRL, mode); + if (ret) + return ret; + + /* When switching to the GPADC pin give things some time to settle */ + if (mode == AXP288_ADC_TS_PIN_GPADC) + usleep_range(6000, 10000); + + return 0; +} + static int axp288_adc_read_raw(struct iio_dev *indio_dev, struct iio_chan_spec const *chan, int *val, int *val2, long mask) @@ -131,7 +153,16 @@ static int axp288_adc_read_raw(struct iio_dev *indio_dev, mutex_lock(&indio_dev->mlock); switch (mask) { case IIO_CHAN_INFO_RAW: + if (axp288_adc_set_ts(info->regmap, AXP288_ADC_TS_PIN_GPADC, + chan->address)) { + dev_err(&indio_dev->dev, "GPADC mode\n"); + ret = -EINVAL; + break; + } ret = axp288_adc_read_channel(val, chan->address, info->regmap); + if (axp288_adc_set_ts(info->regmap, AXP288_ADC_TS_PIN_ON, + chan->address)) + dev_err(&indio_dev->dev, "TS pin restore\n"); break; default: ret = -EINVAL; @@ -141,6 +172,15 @@ static int axp288_adc_read_raw(struct iio_dev *indio_dev, return ret; } +static int axp288_adc_set_state(struct regmap *regmap) +{ + /* ADC should be always enabled for internal FG to function */ + if (regmap_write(regmap, AXP288_ADC_TS_PIN_CTRL, AXP288_ADC_TS_PIN_ON)) + return -EIO; + + return regmap_write(regmap, AXP20X_ADC_EN1, AXP288_ADC_EN_MASK); +} + static const struct iio_info axp288_adc_iio_info = { .read_raw = &axp288_adc_read_raw, .driver_module = THIS_MODULE, @@ -169,7 +209,7 @@ static int axp288_adc_probe(struct platform_device *pdev) * Set ADC to enabled state at all time, including system suspend. * otherwise internal fuel gauge functionality may be affected. */ - ret = regmap_write(info->regmap, AXP20X_ADC_EN1, AXP288_ADC_EN_MASK); + ret = axp288_adc_set_state(axp20x->regmap); if (ret) { dev_err(&pdev->dev, "unable to enable ADC device\n"); return ret; diff --git a/drivers/iio/adc/sun4i-gpadc-iio.c b/drivers/iio/adc/sun4i-gpadc-iio.c index 81d4c39e414a..137f577d9432 100644 --- a/drivers/iio/adc/sun4i-gpadc-iio.c +++ b/drivers/iio/adc/sun4i-gpadc-iio.c @@ -256,6 +256,7 @@ static int sun4i_gpadc_read(struct iio_dev *indio_dev, int channel, int *val, err: pm_runtime_put_autosuspend(indio_dev->dev.parent); + disable_irq(irq); mutex_unlock(&info->mutex); return ret; @@ -365,7 +366,6 @@ static irqreturn_t sun4i_gpadc_temp_data_irq_handler(int irq, void *dev_id) complete(&info->completion); out: - disable_irq_nosync(info->temp_data_irq); return IRQ_HANDLED; } @@ -380,7 +380,6 @@ static irqreturn_t sun4i_gpadc_fifo_data_irq_handler(int irq, void *dev_id) complete(&info->completion); out: - disable_irq_nosync(info->fifo_data_irq); return IRQ_HANDLED; } diff --git a/drivers/iio/adc/vf610_adc.c b/drivers/iio/adc/vf610_adc.c index 01fc76f7d660..c168e0db329a 100644 --- a/drivers/iio/adc/vf610_adc.c +++ b/drivers/iio/adc/vf610_adc.c @@ -77,7 +77,7 @@ #define VF610_ADC_ADSTS_MASK 0x300 #define VF610_ADC_ADLPC_EN 0x80 #define VF610_ADC_ADHSC_EN 0x400 -#define VF610_ADC_REFSEL_VALT 0x100 +#define VF610_ADC_REFSEL_VALT 0x800 #define VF610_ADC_REFSEL_VBG 0x1000 #define VF610_ADC_ADTRG_HARD 0x2000 #define VF610_ADC_AVGS_8 0x4000 diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c index 79c8c7cd70d5..6e6a1ecc99dd 100644 --- a/drivers/iio/common/st_sensors/st_sensors_core.c +++ b/drivers/iio/common/st_sensors/st_sensors_core.c @@ -550,6 +550,31 @@ out: } EXPORT_SYMBOL(st_sensors_read_info_raw); +static int st_sensors_init_interface_mode(struct iio_dev *indio_dev, + const struct st_sensor_settings *sensor_settings) +{ + struct st_sensor_data *sdata = iio_priv(indio_dev); + struct device_node *np = sdata->dev->of_node; + struct st_sensors_platform_data *pdata; + + pdata = (struct st_sensors_platform_data *)sdata->dev->platform_data; + if (((np && of_property_read_bool(np, "spi-3wire")) || + (pdata && pdata->spi_3wire)) && sensor_settings->sim.addr) { + int err; + + err = sdata->tf->write_byte(&sdata->tb, sdata->dev, + sensor_settings->sim.addr, + sensor_settings->sim.value); + if (err < 0) { + dev_err(&indio_dev->dev, + "failed to init interface mode\n"); + return err; + } + } + + return 0; +} + int st_sensors_check_device_support(struct iio_dev *indio_dev, int num_sensors_list, const struct st_sensor_settings *sensor_settings) @@ -574,6 +599,10 @@ int st_sensors_check_device_support(struct iio_dev *indio_dev, return -ENODEV; } + err = st_sensors_init_interface_mode(indio_dev, &sensor_settings[i]); + if (err < 0) + return err; + if (sensor_settings[i].wai_addr) { err = sdata->tf->read_byte(&sdata->tb, sdata->dev, sensor_settings[i].wai_addr, &wai); diff --git a/drivers/iio/light/tsl2563.c b/drivers/iio/light/tsl2563.c index e7d4ea75e007..7599693f7fe9 100644 --- a/drivers/iio/light/tsl2563.c +++ b/drivers/iio/light/tsl2563.c @@ -626,7 +626,7 @@ static irqreturn_t tsl2563_event_handler(int irq, void *private) struct tsl2563_chip *chip = iio_priv(dev_info); iio_push_event(dev_info, - IIO_UNMOD_EVENT_CODE(IIO_LIGHT, + IIO_UNMOD_EVENT_CODE(IIO_INTENSITY, 0, IIO_EV_TYPE_THRESH, IIO_EV_DIR_EITHER), diff --git a/drivers/iio/pressure/st_pressure_core.c b/drivers/iio/pressure/st_pressure_core.c index aa61ec15c139..f1bce05ffa13 100644 --- a/drivers/iio/pressure/st_pressure_core.c +++ b/drivers/iio/pressure/st_pressure_core.c @@ -456,7 +456,7 @@ static const struct st_sensor_settings st_press_sensors_settings[] = { .mask_od = 0x40, .addr_stat_drdy = ST_SENSORS_DEFAULT_STAT_ADDR, }, - .multi_read_bit = true, + .multi_read_bit = false, .bootime = 2, }, }; diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index 01236cef7bfb..437522ca97b4 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -61,6 +61,7 @@ struct addr_req { void (*callback)(int status, struct sockaddr *src_addr, struct rdma_dev_addr *addr, void *context); unsigned long timeout; + struct delayed_work work; int status; u32 seq; }; @@ -295,7 +296,7 @@ int rdma_translate_ip(const struct sockaddr *addr, } EXPORT_SYMBOL(rdma_translate_ip); -static void set_timeout(unsigned long time) +static void set_timeout(struct delayed_work *delayed_work, unsigned long time) { unsigned long delay; @@ -303,7 +304,7 @@ static void set_timeout(unsigned long time) if ((long)delay < 0) delay = 0; - mod_delayed_work(addr_wq, &work, delay); + mod_delayed_work(addr_wq, delayed_work, delay); } static void queue_req(struct addr_req *req) @@ -318,8 +319,7 @@ static void queue_req(struct addr_req *req) list_add(&req->list, &temp_req->list); - if (req_list.next == &req->list) - set_timeout(req->timeout); + set_timeout(&req->work, req->timeout); mutex_unlock(&lock); } @@ -574,6 +574,37 @@ static int addr_resolve(struct sockaddr *src_in, return ret; } +static void process_one_req(struct work_struct *_work) +{ + struct addr_req *req; + struct sockaddr *src_in, *dst_in; + + mutex_lock(&lock); + req = container_of(_work, struct addr_req, work.work); + + if (req->status == -ENODATA) { + src_in = (struct sockaddr *)&req->src_addr; + dst_in = (struct sockaddr *)&req->dst_addr; + req->status = addr_resolve(src_in, dst_in, req->addr, + true, req->seq); + if (req->status && time_after_eq(jiffies, req->timeout)) { + req->status = -ETIMEDOUT; + } else if (req->status == -ENODATA) { + /* requeue the work for retrying again */ + set_timeout(&req->work, req->timeout); + mutex_unlock(&lock); + return; + } + } + list_del(&req->list); + mutex_unlock(&lock); + + req->callback(req->status, (struct sockaddr *)&req->src_addr, + req->addr, req->context); + put_client(req->client); + kfree(req); +} + static void process_req(struct work_struct *work) { struct addr_req *req, *temp_req; @@ -591,20 +622,23 @@ static void process_req(struct work_struct *work) true, req->seq); if (req->status && time_after_eq(jiffies, req->timeout)) req->status = -ETIMEDOUT; - else if (req->status == -ENODATA) + else if (req->status == -ENODATA) { + set_timeout(&req->work, req->timeout); continue; + } } list_move_tail(&req->list, &done_list); } - if (!list_empty(&req_list)) { - req = list_entry(req_list.next, struct addr_req, list); - set_timeout(req->timeout); - } mutex_unlock(&lock); list_for_each_entry_safe(req, temp_req, &done_list, list) { list_del(&req->list); + /* It is safe to cancel other work items from this work item + * because at a time there can be only one work item running + * with this single threaded work queue. + */ + cancel_delayed_work(&req->work); req->callback(req->status, (struct sockaddr *) &req->src_addr, req->addr, req->context); put_client(req->client); @@ -647,6 +681,7 @@ int rdma_resolve_ip(struct rdma_addr_client *client, req->context = context; req->client = client; atomic_inc(&client->refcount); + INIT_DELAYED_WORK(&req->work, process_one_req); req->seq = (u32)atomic_inc_return(&ib_nl_addr_request_seq); req->status = addr_resolve(src_in, dst_in, addr, true, req->seq); @@ -701,7 +736,7 @@ void rdma_addr_cancel(struct rdma_dev_addr *addr) req->status = -ECANCELED; req->timeout = jiffies; list_move(&req->list, &req_list); - set_timeout(req->timeout); + set_timeout(&req->work, req->timeout); break; } } @@ -807,9 +842,8 @@ static int netevent_callback(struct notifier_block *self, unsigned long event, if (event == NETEVENT_NEIGH_UPDATE) { struct neighbour *neigh = ctx; - if (neigh->nud_state & NUD_VALID) { - set_timeout(jiffies); - } + if (neigh->nud_state & NUD_VALID) + set_timeout(&work, jiffies); } return 0; } @@ -820,7 +854,7 @@ static struct notifier_block nb = { int addr_init(void) { - addr_wq = alloc_workqueue("ib_addr", WQ_MEM_RECLAIM, 0); + addr_wq = alloc_ordered_workqueue("ib_addr", WQ_MEM_RECLAIM); if (!addr_wq) return -ENOMEM; diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 2c98533a0203..c551d2b275fd 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -1153,7 +1153,7 @@ ssize_t ib_uverbs_resize_cq(struct ib_uverbs_file *file, int out_len) { struct ib_uverbs_resize_cq cmd; - struct ib_uverbs_resize_cq_resp resp; + struct ib_uverbs_resize_cq_resp resp = {}; struct ib_udata udata; struct ib_cq *cq; int ret = -EINVAL; diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 3d2609608f58..c023e2c81b8f 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -250,6 +250,7 @@ void ib_uverbs_release_file(struct kref *ref) if (atomic_dec_and_test(&file->device->refcount)) ib_uverbs_comp_dev(file->device); + kobject_put(&file->device->kobj); kfree(file); } @@ -917,7 +918,6 @@ err: static int ib_uverbs_close(struct inode *inode, struct file *filp) { struct ib_uverbs_file *file = filp->private_data; - struct ib_uverbs_device *dev = file->device; mutex_lock(&file->cleanup_mutex); if (file->ucontext) { @@ -939,7 +939,6 @@ static int ib_uverbs_close(struct inode *inode, struct file *filp) ib_uverbs_release_async_event_file); kref_put(&file->ref, ib_uverbs_release_file); - kobject_put(&dev->kobj); return 0; } diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index fb98ed67d5bc..7f8fe443df46 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -895,7 +895,6 @@ static const struct { } qp_state_table[IB_QPS_ERR + 1][IB_QPS_ERR + 1] = { [IB_QPS_RESET] = { [IB_QPS_RESET] = { .valid = 1 }, - [IB_QPS_ERR] = { .valid = 1 }, [IB_QPS_INIT] = { .valid = 1, .req_param = { diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c index 23fad6d96944..2540b65e242c 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c @@ -733,7 +733,7 @@ static int hns_roce_v1_rsv_lp_qp(struct hns_roce_dev *hr_dev) continue; free_mr->mr_free_qp[i] = hns_roce_v1_create_lp_qp(hr_dev, pd); - if (IS_ERR(free_mr->mr_free_qp[i])) { + if (!free_mr->mr_free_qp[i]) { dev_err(dev, "Create loop qp failed!\n"); goto create_lp_qp_failed; } diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index ae0746754008..3d701c7a4c91 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -939,7 +939,7 @@ static int mlx5_ib_mr_initiator_pfault_handler( if (qp->ibqp.qp_type != IB_QPT_RC) { av = *wqe; - if (av->dqp_dct & be32_to_cpu(MLX5_WQE_AV_EXT)) + if (av->dqp_dct & cpu_to_be32(MLX5_EXTENDED_UD_AV)) *wqe += sizeof(struct mlx5_av); else *wqe += sizeof(struct mlx5_base_av); diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index ff50a7bd66d8..7ac25059c40f 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -336,6 +336,7 @@ struct ipoib_dev_priv { unsigned long flags; struct rw_semaphore vlan_rwsem; + struct mutex mcast_mutex; struct rb_root path_tree; struct list_head path_list; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index f87d104837dc..d69410c2ed97 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -511,7 +511,6 @@ static int ipoib_cm_rx_handler(struct ib_cm_id *cm_id, case IB_CM_REQ_RECEIVED: return ipoib_cm_req_handler(cm_id, event); case IB_CM_DREQ_RECEIVED: - p = cm_id->context; ib_send_cm_drep(cm_id, NULL, 0); /* Fall through */ case IB_CM_REJ_RECEIVED: diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c b/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c index 7871379342f4..184a22f48027 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c @@ -52,7 +52,8 @@ static const struct ipoib_stats ipoib_gstrings_stats[] = { IPOIB_NETDEV_STAT(tx_bytes), IPOIB_NETDEV_STAT(tx_errors), IPOIB_NETDEV_STAT(rx_dropped), - IPOIB_NETDEV_STAT(tx_dropped) + IPOIB_NETDEV_STAT(tx_dropped), + IPOIB_NETDEV_STAT(multicast), }; #define IPOIB_GLOBAL_STATS_LEN ARRAY_SIZE(ipoib_gstrings_stats) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 57a9655e844d..2e075377242e 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -256,6 +256,8 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) ++dev->stats.rx_packets; dev->stats.rx_bytes += skb->len; + if (skb->pkt_type == PACKET_MULTICAST) + dev->stats.multicast++; skb->dev = dev; if ((dev->features & NETIF_F_RXCSUM) && @@ -709,6 +711,27 @@ static int recvs_pending(struct net_device *dev) return pending; } +static void check_qp_movement_and_print(struct ipoib_dev_priv *priv, + struct ib_qp *qp, + enum ib_qp_state new_state) +{ + struct ib_qp_attr qp_attr; + struct ib_qp_init_attr query_init_attr; + int ret; + + ret = ib_query_qp(qp, &qp_attr, IB_QP_STATE, &query_init_attr); + if (ret) { + ipoib_warn(priv, "%s: Failed to query QP\n", __func__); + return; + } + /* print according to the new-state and the previous state.*/ + if (new_state == IB_QPS_ERR && qp_attr.qp_state == IB_QPS_RESET) + ipoib_dbg(priv, "Failed modify QP, IB_QPS_RESET to IB_QPS_ERR, acceptable\n"); + else + ipoib_warn(priv, "Failed to modify QP to state: %d from state: %d\n", + new_state, qp_attr.qp_state); +} + int ipoib_ib_dev_stop_default(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); @@ -728,7 +751,7 @@ int ipoib_ib_dev_stop_default(struct net_device *dev) */ qp_attr.qp_state = IB_QPS_ERR; if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE)) - ipoib_warn(priv, "Failed to modify QP to ERROR state\n"); + check_qp_movement_and_print(priv, priv->qp, IB_QPS_ERR); /* Wait for all sends and receives to complete */ begin = jiffies; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 4ce315c92b48..6c77df34869d 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -1560,6 +1560,7 @@ static void ipoib_flush_neighs(struct ipoib_dev_priv *priv) int i, wait_flushed = 0; init_completion(&priv->ntbl.flushed); + set_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags); spin_lock_irqsave(&priv->lock, flags); @@ -1604,7 +1605,6 @@ static void ipoib_neigh_hash_uninit(struct net_device *dev) ipoib_dbg(priv, "ipoib_neigh_hash_uninit\n"); init_completion(&priv->ntbl.deleted); - set_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags); /* Stop GC if called at init fail need to cancel work */ stopped = test_and_set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags); @@ -1847,6 +1847,7 @@ static const struct net_device_ops ipoib_netdev_ops_vf = { .ndo_tx_timeout = ipoib_timeout, .ndo_set_rx_mode = ipoib_set_mcast_list, .ndo_get_iflink = ipoib_get_iflink, + .ndo_get_stats64 = ipoib_get_stats, }; void ipoib_setup_common(struct net_device *dev) @@ -1877,6 +1878,7 @@ static void ipoib_build_priv(struct net_device *dev) priv->dev = dev; spin_lock_init(&priv->lock); init_rwsem(&priv->vlan_rwsem); + mutex_init(&priv->mcast_mutex); INIT_LIST_HEAD(&priv->path_list); INIT_LIST_HEAD(&priv->child_intfs); @@ -2173,14 +2175,14 @@ static struct net_device *ipoib_add_port(const char *format, priv->dev->dev_id = port - 1; result = ib_query_port(hca, port, &attr); - if (!result) - priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu); - else { + if (result) { printk(KERN_WARNING "%s: ib_query_port %d failed\n", hca->name, port); goto device_init_failed; } + priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu); + /* MTU will be reset when mcast join happens */ priv->dev->mtu = IPOIB_UD_MTU(priv->max_ib_mtu); priv->mcast_mtu = priv->admin_mtu = priv->dev->mtu; @@ -2211,12 +2213,14 @@ static struct net_device *ipoib_add_port(const char *format, printk(KERN_WARNING "%s: ib_query_gid port %d failed (ret = %d)\n", hca->name, port, result); goto device_init_failed; - } else - memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw, sizeof (union ib_gid)); + } + + memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw, + sizeof(union ib_gid)); set_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags); result = ipoib_dev_init(priv->dev, hca, port); - if (result < 0) { + if (result) { printk(KERN_WARNING "%s: failed to initialize port %d (ret = %d)\n", hca->name, port, result); goto device_init_failed; @@ -2365,6 +2369,7 @@ static int __init ipoib_init_module(void) ipoib_sendq_size = max3(ipoib_sendq_size, 2 * MAX_SEND_CQE, IPOIB_MIN_QUEUE_SIZE); #ifdef CONFIG_INFINIBAND_IPOIB_CM ipoib_max_conn_qp = min(ipoib_max_conn_qp, IPOIB_CM_MAX_CONN_QP); + ipoib_max_conn_qp = max(ipoib_max_conn_qp, 0); #endif /* diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 057f58e6afca..93e149efc1f5 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -684,15 +684,10 @@ void ipoib_mcast_start_thread(struct net_device *dev) int ipoib_mcast_stop_thread(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); - unsigned long flags; ipoib_dbg_mcast(priv, "stopping multicast thread\n"); - spin_lock_irqsave(&priv->lock, flags); - cancel_delayed_work(&priv->mcast_task); - spin_unlock_irqrestore(&priv->lock, flags); - - flush_workqueue(priv->wq); + cancel_delayed_work_sync(&priv->mcast_task); return 0; } @@ -748,6 +743,14 @@ void ipoib_mcast_remove_list(struct list_head *remove_list) { struct ipoib_mcast *mcast, *tmcast; + /* + * make sure the in-flight joins have finished before we attempt + * to leave + */ + list_for_each_entry_safe(mcast, tmcast, remove_list, list) + if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) + wait_for_completion(&mcast->done); + list_for_each_entry_safe(mcast, tmcast, remove_list, list) { ipoib_mcast_leave(mcast->dev, mcast); ipoib_mcast_free(mcast); @@ -838,6 +841,7 @@ void ipoib_mcast_dev_flush(struct net_device *dev) struct ipoib_mcast *mcast, *tmcast; unsigned long flags; + mutex_lock(&priv->mcast_mutex); ipoib_dbg_mcast(priv, "flushing multicast list\n"); spin_lock_irqsave(&priv->lock, flags); @@ -856,15 +860,8 @@ void ipoib_mcast_dev_flush(struct net_device *dev) spin_unlock_irqrestore(&priv->lock, flags); - /* - * make sure the in-flight joins have finished before we attempt - * to leave - */ - list_for_each_entry_safe(mcast, tmcast, &remove_list, list) - if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) - wait_for_completion(&mcast->done); - ipoib_mcast_remove_list(&remove_list); + mutex_unlock(&priv->mcast_mutex); } static int ipoib_mcast_addr_is_valid(const u8 *addr, const u8 *broadcast) @@ -982,14 +979,6 @@ void ipoib_mcast_restart_task(struct work_struct *work) netif_addr_unlock(dev); local_irq_restore(flags); - /* - * make sure the in-flight joins have finished before we attempt - * to leave - */ - list_for_each_entry_safe(mcast, tmcast, &remove_list, list) - if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) - wait_for_completion(&mcast->done); - ipoib_mcast_remove_list(&remove_list); /* diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index b97188acc4f1..2d80fa8a0634 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -1519,6 +1519,13 @@ static int arm_smmu_add_device(struct device *dev) if (using_legacy_binding) { ret = arm_smmu_register_legacy_master(dev, &smmu); + + /* + * If dev->iommu_fwspec is initally NULL, arm_smmu_register_legacy_master() + * will allocate/initialise a new one. Thus we need to update fwspec for + * later use. + */ + fwspec = dev->iommu_fwspec; if (ret) goto out_free; } else if (fwspec && fwspec->ops == &arm_smmu_ops) { diff --git a/drivers/isdn/hysdn/hysdn_proclog.c b/drivers/isdn/hysdn/hysdn_proclog.c index 7b5fd8fb1761..aaca0b3d662e 100644 --- a/drivers/isdn/hysdn/hysdn_proclog.c +++ b/drivers/isdn/hysdn/hysdn_proclog.c @@ -44,7 +44,6 @@ struct procdata { char log_name[15]; /* log filename */ struct log_data *log_head, *log_tail; /* head and tail for queue */ int if_used; /* open count for interface */ - int volatile del_lock; /* lock for delete operations */ unsigned char logtmp[LOG_MAX_LINELEN]; wait_queue_head_t rd_queue; }; @@ -102,7 +101,6 @@ put_log_buffer(hysdn_card *card, char *cp) { struct log_data *ib; struct procdata *pd = card->proclog; - int i; unsigned long flags; if (!pd) @@ -126,21 +124,21 @@ put_log_buffer(hysdn_card *card, char *cp) else pd->log_tail->next = ib; /* follows existing messages */ pd->log_tail = ib; /* new tail */ - i = pd->del_lock++; /* get lock state */ - spin_unlock_irqrestore(&card->hysdn_lock, flags); /* delete old entrys */ - if (!i) - while (pd->log_head->next) { - if ((pd->log_head->usage_cnt <= 0) && - (pd->log_head->next->usage_cnt <= 0)) { - ib = pd->log_head; - pd->log_head = pd->log_head->next; - kfree(ib); - } else - break; - } /* pd->log_head->next */ - pd->del_lock--; /* release lock level */ + while (pd->log_head->next) { + if ((pd->log_head->usage_cnt <= 0) && + (pd->log_head->next->usage_cnt <= 0)) { + ib = pd->log_head; + pd->log_head = pd->log_head->next; + kfree(ib); + } else { + break; + } + } /* pd->log_head->next */ + + spin_unlock_irqrestore(&card->hysdn_lock, flags); + wake_up_interruptible(&(pd->rd_queue)); /* announce new entry */ } /* put_log_buffer */ diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 8621a198a2ce..bac33311f55a 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -216,6 +216,12 @@ static int mei_me_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_drvdata(pdev, dev); /* + * MEI requires to resume from runtime suspend mode + * in order to perform link reset flow upon system suspend. + */ + pdev->dev_flags |= PCI_DEV_FLAGS_NEEDS_RESUME; + + /* * For not wake-able HW runtime pm framework * can't be used on pci device level. * Use domain runtime pm callbacks instead. diff --git a/drivers/misc/mei/pci-txe.c b/drivers/misc/mei/pci-txe.c index f811cd524468..e38a5f144373 100644 --- a/drivers/misc/mei/pci-txe.c +++ b/drivers/misc/mei/pci-txe.c @@ -138,6 +138,12 @@ static int mei_txe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_drvdata(pdev, dev); /* + * MEI requires to resume from runtime suspend mode + * in order to perform link reset flow upon system suspend. + */ + pdev->dev_flags |= PCI_DEV_FLAGS_NEEDS_RESUME; + + /* * For not wake-able HW runtime pm framework * can't be used on pci device level. * Use domain runtime pm callbacks instead. diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index e5938c791330..f1bbfd389367 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -2170,7 +2170,9 @@ static void mmc_blk_remove_req(struct mmc_blk_data *md) * from being accepted. */ card = md->queue.card; + spin_lock_irq(md->queue.queue->queue_lock); queue_flag_set(QUEUE_FLAG_BYPASS, md->queue.queue); + spin_unlock_irq(md->queue.queue->queue_lock); blk_set_queue_dying(md->queue.queue); mmc_cleanup_queue(&md->queue); if (md->disk->flags & GENHD_FL_UP) { diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index 4ffea14b7eb6..2bae69e39544 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -1289,7 +1289,7 @@ out_err: static int mmc_select_hs400es(struct mmc_card *card) { struct mmc_host *host = card->host; - int err = 0; + int err = -EINVAL; u8 val; if (!(host->caps & MMC_CAP_8_BIT_DATA)) { diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index 04ff3c97a535..2ab4788d021f 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -2086,7 +2086,7 @@ static int omap_hsmmc_probe(struct platform_device *pdev) mmc->max_seg_size = mmc->max_req_size; mmc->caps |= MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED | - MMC_CAP_WAIT_WHILE_BUSY | MMC_CAP_ERASE; + MMC_CAP_WAIT_WHILE_BUSY | MMC_CAP_ERASE | MMC_CAP_CMD23; mmc->caps |= mmc_pdata(host)->caps; if (mmc->caps & MMC_CAP_8_BIT_DATA) diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index f336a9b85576..9ec8f033ac5f 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -113,6 +113,7 @@ static blk_status_t do_blktrans_request(struct mtd_blktrans_ops *tr, for (; nsect > 0; nsect--, block++, buf += tr->blksize) if (tr->writesect(dev, block, buf)) return BLK_STS_IOERR; + return BLK_STS_OK; default: return BLK_STS_IOERR; } diff --git a/drivers/mtd/nand/atmel/nand-controller.c b/drivers/mtd/nand/atmel/nand-controller.c index d922a88e407f..2c8baa0c2c4e 100644 --- a/drivers/mtd/nand/atmel/nand-controller.c +++ b/drivers/mtd/nand/atmel/nand-controller.c @@ -1201,7 +1201,7 @@ static int atmel_smc_nand_prepare_smcconf(struct atmel_nand *nand, * tRC < 30ns implies EDO mode. This controller does not support this * mode. */ - if (conf->timings.sdr.tRC_min < 30) + if (conf->timings.sdr.tRC_min < 30000) return -ENOTSUPP; atmel_smc_cs_conf_init(smcconf); diff --git a/drivers/mtd/nand/atmel/pmecc.c b/drivers/mtd/nand/atmel/pmecc.c index 55a8ee5306ea..8c210a5776bc 100644 --- a/drivers/mtd/nand/atmel/pmecc.c +++ b/drivers/mtd/nand/atmel/pmecc.c @@ -945,6 +945,7 @@ struct atmel_pmecc *devm_atmel_pmecc_get(struct device *userdev) */ struct platform_device *pdev = to_platform_device(userdev); const struct atmel_pmecc_caps *caps; + const struct of_device_id *match; /* No PMECC engine available. */ if (!of_property_read_bool(userdev->of_node, @@ -953,21 +954,11 @@ struct atmel_pmecc *devm_atmel_pmecc_get(struct device *userdev) caps = &at91sam9g45_caps; - /* - * Try to find the NFC subnode and extract the associated caps - * from there. - */ - np = of_find_compatible_node(userdev->of_node, NULL, - "atmel,sama5d3-nfc"); - if (np) { - const struct of_device_id *match; - - match = of_match_node(atmel_pmecc_legacy_match, np); - if (match && match->data) - caps = match->data; - - of_node_put(np); - } + /* Find the caps associated to the NAND dev node. */ + match = of_match_node(atmel_pmecc_legacy_match, + userdev->of_node); + if (match && match->data) + caps = match->data; pmecc = atmel_pmecc_create(pdev, caps, 1, 2); } diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index 5fa5ddc94834..c6c18b82f8f4 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -65,8 +65,14 @@ static int nand_ooblayout_ecc_sp(struct mtd_info *mtd, int section, if (!section) { oobregion->offset = 0; - oobregion->length = 4; + if (mtd->oobsize == 16) + oobregion->length = 4; + else + oobregion->length = 3; } else { + if (mtd->oobsize == 8) + return -ERANGE; + oobregion->offset = 6; oobregion->length = ecc->total - 4; } @@ -1125,7 +1131,9 @@ static int nand_setup_data_interface(struct nand_chip *chip, int chipnr) * Ensure the timing mode has been changed on the chip side * before changing timings on the controller side. */ - if (chip->onfi_version) { + if (chip->onfi_version && + (le16_to_cpu(chip->onfi_params.opt_cmd) & + ONFI_OPT_CMD_SET_GET_FEATURES)) { u8 tmode_param[ONFI_SUBFEATURE_PARAM_LEN] = { chip->onfi_timing_mode_default, }; @@ -2741,7 +2749,6 @@ static int nand_write_page_syndrome(struct mtd_info *mtd, * @buf: the data to write * @oob_required: must write chip->oob_poi to OOB * @page: page number to write - * @cached: cached programming * @raw: use _raw version of write_page */ static int nand_write_page(struct mtd_info *mtd, struct nand_chip *chip, diff --git a/drivers/mtd/nand/nand_timings.c b/drivers/mtd/nand/nand_timings.c index f06312df3669..7e36d7d13c26 100644 --- a/drivers/mtd/nand/nand_timings.c +++ b/drivers/mtd/nand/nand_timings.c @@ -311,9 +311,9 @@ int onfi_init_data_interface(struct nand_chip *chip, struct nand_sdr_timings *timings = &iface->timings.sdr; /* microseconds -> picoseconds */ - timings->tPROG_max = 1000000UL * le16_to_cpu(params->t_prog); - timings->tBERS_max = 1000000UL * le16_to_cpu(params->t_bers); - timings->tR_max = 1000000UL * le16_to_cpu(params->t_r); + timings->tPROG_max = 1000000ULL * le16_to_cpu(params->t_prog); + timings->tBERS_max = 1000000ULL * le16_to_cpu(params->t_bers); + timings->tR_max = 1000000ULL * le16_to_cpu(params->t_r); /* nanoseconds -> picoseconds */ timings->tCCS_min = 1000UL * le16_to_cpu(params->t_ccs); diff --git a/drivers/mtd/nand/sunxi_nand.c b/drivers/mtd/nand/sunxi_nand.c index d0b6f8f9f297..6abd142b1324 100644 --- a/drivers/mtd/nand/sunxi_nand.c +++ b/drivers/mtd/nand/sunxi_nand.c @@ -1728,6 +1728,10 @@ static int sunxi_nfc_setup_data_interface(struct mtd_info *mtd, int csline, */ chip->clk_rate = NSEC_PER_SEC / min_clk_period; real_clk_rate = clk_round_rate(nfc->mod_clk, chip->clk_rate); + if (real_clk_rate <= 0) { + dev_err(nfc->dev, "Unable to round clk %lu\n", chip->clk_rate); + return -EINVAL; + } /* * ONFI specification 3.1, paragraph 4.15.2 dictates that EDO data diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 1e46418a3b74..264b281eb86b 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -625,6 +625,44 @@ static void mt7530_adjust_link(struct dsa_switch *ds, int port, * all finished. */ mt7623_pad_clk_setup(ds); + } else { + u16 lcl_adv = 0, rmt_adv = 0; + u8 flowctrl; + u32 mcr = PMCR_USERP_LINK | PMCR_FORCE_MODE; + + switch (phydev->speed) { + case SPEED_1000: + mcr |= PMCR_FORCE_SPEED_1000; + break; + case SPEED_100: + mcr |= PMCR_FORCE_SPEED_100; + break; + }; + + if (phydev->link) + mcr |= PMCR_FORCE_LNK; + + if (phydev->duplex) { + mcr |= PMCR_FORCE_FDX; + + if (phydev->pause) + rmt_adv = LPA_PAUSE_CAP; + if (phydev->asym_pause) + rmt_adv |= LPA_PAUSE_ASYM; + + if (phydev->advertising & ADVERTISED_Pause) + lcl_adv |= ADVERTISE_PAUSE_CAP; + if (phydev->advertising & ADVERTISED_Asym_Pause) + lcl_adv |= ADVERTISE_PAUSE_ASYM; + + flowctrl = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv); + + if (flowctrl & FLOW_CTRL_TX) + mcr |= PMCR_TX_FC_EN; + if (flowctrl & FLOW_CTRL_RX) + mcr |= PMCR_RX_FC_EN; + } + mt7530_write(priv, MT7530_PMCR_P(port), mcr); } } diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index b83d76b99802..74db9822eb40 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -151,6 +151,7 @@ enum mt7530_stp_state { #define PMCR_TX_FC_EN BIT(5) #define PMCR_RX_FC_EN BIT(4) #define PMCR_FORCE_SPEED_1000 BIT(3) +#define PMCR_FORCE_SPEED_100 BIT(2) #define PMCR_FORCE_FDX BIT(1) #define PMCR_FORCE_LNK BIT(0) #define PMCR_COMMON_LINK (PMCR_IFG_XMIT(1) | PMCR_MAC_MODE | \ diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index 86058a9f3417..1d307f2def2d 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -1785,9 +1785,9 @@ static int xgene_enet_get_resources(struct xgene_enet_pdata *pdata) xgene_enet_gpiod_get(pdata); - if (pdata->phy_mode != PHY_INTERFACE_MODE_SGMII) { - pdata->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(pdata->clk)) { + pdata->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(pdata->clk)) { + if (pdata->phy_mode != PHY_INTERFACE_MODE_SGMII) { /* Abort if the clock is defined but couldn't be * retrived. Always abort if the clock is missing on * DT system as the driver can't cope with this case. diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index f411936b744c..a1125d10c825 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -2368,6 +2368,7 @@ static int b44_init_one(struct ssb_device *sdev, bp->msg_enable = netif_msg_init(b44_debug, B44_DEF_MSG_ENABLE); spin_lock_init(&bp->lock); + u64_stats_init(&bp->hw_stats.syncp); bp->rx_pending = B44_DEF_RX_RING_PENDING; bp->tx_pending = B44_DEF_TX_RING_PENDING; diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 5333601f855f..dc3052751bc1 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -449,6 +449,10 @@ static void bcm_sysport_get_stats(struct net_device *dev, p = (char *)&dev->stats; else p = (char *)priv; + + if (priv->is_lite && !bcm_sysport_lite_stat_valid(s->type)) + continue; + p += s->stat_offset; data[j] = *(unsigned long *)p; j++; diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index a3e694679635..c45e8e3b82d3 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -111,6 +111,7 @@ static void send_request_map(struct ibmvnic_adapter *, dma_addr_t, __be32, u8); static void send_request_unmap(struct ibmvnic_adapter *, u8); static void send_login(struct ibmvnic_adapter *adapter); static void send_cap_queries(struct ibmvnic_adapter *adapter); +static int init_sub_crqs(struct ibmvnic_adapter *); static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter); static int ibmvnic_init(struct ibmvnic_adapter *); static void release_crq_queue(struct ibmvnic_adapter *); @@ -651,6 +652,7 @@ static int ibmvnic_login(struct net_device *netdev) struct ibmvnic_adapter *adapter = netdev_priv(netdev); unsigned long timeout = msecs_to_jiffies(30000); struct device *dev = &adapter->vdev->dev; + int rc; do { if (adapter->renegotiate) { @@ -664,6 +666,18 @@ static int ibmvnic_login(struct net_device *netdev) dev_err(dev, "Capabilities query timeout\n"); return -1; } + rc = init_sub_crqs(adapter); + if (rc) { + dev_err(dev, + "Initialization of SCRQ's failed\n"); + return -1; + } + rc = init_sub_crq_irqs(adapter); + if (rc) { + dev_err(dev, + "Initialization of SCRQ's irqs failed\n"); + return -1; + } } reinit_completion(&adapter->init_done); @@ -3004,7 +3018,6 @@ static void handle_request_cap_rsp(union ibmvnic_crq *crq, *req_value, (long int)be64_to_cpu(crq->request_capability_rsp. number), name); - release_sub_crqs(adapter); *req_value = be64_to_cpu(crq->request_capability_rsp.number); ibmvnic_send_req_caps(adapter, 1); return; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index b936febc315a..2194960d5855 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1113,6 +1113,8 @@ int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring) if (!tx_ring->tx_bi) goto err; + u64_stats_init(&tx_ring->syncp); + /* round up to nearest 4K */ tx_ring->size = tx_ring->count * sizeof(struct i40e_tx_desc); /* add u32 for head writeback, align after this takes care of diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 084c53582793..032f8ac06357 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -2988,6 +2988,8 @@ int ixgbevf_setup_tx_resources(struct ixgbevf_ring *tx_ring) if (!tx_ring->tx_buffer_info) goto err; + u64_stats_init(&tx_ring->syncp); + /* round up to nearest 4K */ tx_ring->size = tx_ring->count * sizeof(union ixgbe_adv_tx_desc); tx_ring->size = ALIGN(tx_ring->size, 4096); @@ -3046,6 +3048,8 @@ int ixgbevf_setup_rx_resources(struct ixgbevf_ring *rx_ring) if (!rx_ring->rx_buffer_info) goto err; + u64_stats_init(&rx_ring->syncp); + /* Round up to nearest 4K */ rx_ring->size = rx_ring->count * sizeof(union ixgbe_adv_rx_desc); rx_ring->size = ALIGN(rx_ring->size, 4096); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index c751a1d434ad..3d4e4a5d00d1 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -223,6 +223,7 @@ static void mlx4_en_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) { struct mlx4_en_priv *priv = netdev_priv(netdev); + struct mlx4_caps *caps = &priv->mdev->dev->caps; int err = 0; u64 config = 0; u64 mask; @@ -235,24 +236,24 @@ static void mlx4_en_get_wol(struct net_device *netdev, mask = (priv->port == 1) ? MLX4_DEV_CAP_FLAG_WOL_PORT1 : MLX4_DEV_CAP_FLAG_WOL_PORT2; - if (!(priv->mdev->dev->caps.flags & mask)) { + if (!(caps->flags & mask)) { wol->supported = 0; wol->wolopts = 0; return; } + if (caps->wol_port[priv->port]) + wol->supported = WAKE_MAGIC; + else + wol->supported = 0; + err = mlx4_wol_read(priv->mdev->dev, &config, priv->port); if (err) { en_err(priv, "Failed to get WoL information\n"); return; } - if (config & MLX4_EN_WOL_MAGIC) - wol->supported = WAKE_MAGIC; - else - wol->supported = 0; - - if (config & MLX4_EN_WOL_ENABLED) + if ((config & MLX4_EN_WOL_ENABLED) && (config & MLX4_EN_WOL_MAGIC)) wol->wolopts = WAKE_MAGIC; else wol->wolopts = 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 436f7689a032..bf1638044a7a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -574,16 +574,21 @@ static inline __wsum get_fixed_vlan_csum(__wsum hw_checksum, * header, the HW adds it. To address that, we are subtracting the pseudo * header checksum from the checksum value provided by the HW. */ -static void get_fixed_ipv4_csum(__wsum hw_checksum, struct sk_buff *skb, - struct iphdr *iph) +static int get_fixed_ipv4_csum(__wsum hw_checksum, struct sk_buff *skb, + struct iphdr *iph) { __u16 length_for_csum = 0; __wsum csum_pseudo_header = 0; + __u8 ipproto = iph->protocol; + + if (unlikely(ipproto == IPPROTO_SCTP)) + return -1; length_for_csum = (be16_to_cpu(iph->tot_len) - (iph->ihl << 2)); csum_pseudo_header = csum_tcpudp_nofold(iph->saddr, iph->daddr, - length_for_csum, iph->protocol, 0); + length_for_csum, ipproto, 0); skb->csum = csum_sub(hw_checksum, csum_pseudo_header); + return 0; } #if IS_ENABLED(CONFIG_IPV6) @@ -594,17 +599,20 @@ static void get_fixed_ipv4_csum(__wsum hw_checksum, struct sk_buff *skb, static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb, struct ipv6hdr *ipv6h) { + __u8 nexthdr = ipv6h->nexthdr; __wsum csum_pseudo_hdr = 0; - if (unlikely(ipv6h->nexthdr == IPPROTO_FRAGMENT || - ipv6h->nexthdr == IPPROTO_HOPOPTS)) + if (unlikely(nexthdr == IPPROTO_FRAGMENT || + nexthdr == IPPROTO_HOPOPTS || + nexthdr == IPPROTO_SCTP)) return -1; - hw_checksum = csum_add(hw_checksum, (__force __wsum)htons(ipv6h->nexthdr)); + hw_checksum = csum_add(hw_checksum, (__force __wsum)htons(nexthdr)); csum_pseudo_hdr = csum_partial(&ipv6h->saddr, sizeof(ipv6h->saddr) + sizeof(ipv6h->daddr), 0); csum_pseudo_hdr = csum_add(csum_pseudo_hdr, (__force __wsum)ipv6h->payload_len); - csum_pseudo_hdr = csum_add(csum_pseudo_hdr, (__force __wsum)ntohs(ipv6h->nexthdr)); + csum_pseudo_hdr = csum_add(csum_pseudo_hdr, + (__force __wsum)htons(nexthdr)); skb->csum = csum_sub(hw_checksum, csum_pseudo_hdr); skb->csum = csum_add(skb->csum, csum_partial(ipv6h, sizeof(struct ipv6hdr), 0)); @@ -627,11 +635,10 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va, } if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV4)) - get_fixed_ipv4_csum(hw_checksum, skb, hdr); + return get_fixed_ipv4_csum(hw_checksum, skb, hdr); #if IS_ENABLED(CONFIG_IPV6) - else if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV6)) - if (unlikely(get_fixed_ipv6_csum(hw_checksum, skb, hdr))) - return -1; + if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV6)) + return get_fixed_ipv6_csum(hw_checksum, skb, hdr); #endif return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index 37e84a59e751..041c0ed65929 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -159,8 +159,9 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags) [32] = "Loopback source checks support", [33] = "RoCEv2 support", [34] = "DMFS Sniffer support (UC & MC)", - [35] = "QinQ VST mode support", - [36] = "sl to vl mapping table change event support" + [35] = "Diag counters per port", + [36] = "QinQ VST mode support", + [37] = "sl to vl mapping table change event support", }; int i; @@ -764,6 +765,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) #define QUERY_DEV_CAP_CQ_TS_SUPPORT_OFFSET 0x3e #define QUERY_DEV_CAP_MAX_PKEY_OFFSET 0x3f #define QUERY_DEV_CAP_EXT_FLAGS_OFFSET 0x40 +#define QUERY_DEV_CAP_WOL_OFFSET 0x43 #define QUERY_DEV_CAP_FLAGS_OFFSET 0x44 #define QUERY_DEV_CAP_RSVD_UAR_OFFSET 0x48 #define QUERY_DEV_CAP_UAR_SZ_OFFSET 0x49 @@ -920,6 +922,9 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) MLX4_GET(ext_flags, outbox, QUERY_DEV_CAP_EXT_FLAGS_OFFSET); MLX4_GET(flags, outbox, QUERY_DEV_CAP_FLAGS_OFFSET); dev_cap->flags = flags | (u64)ext_flags << 32; + MLX4_GET(field, outbox, QUERY_DEV_CAP_WOL_OFFSET); + dev_cap->wol_port[1] = !!(field & 0x20); + dev_cap->wol_port[2] = !!(field & 0x40); MLX4_GET(field, outbox, QUERY_DEV_CAP_RSVD_UAR_OFFSET); dev_cap->reserved_uars = field >> 4; MLX4_GET(field, outbox, QUERY_DEV_CAP_UAR_SZ_OFFSET); diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h index 5343a0599253..b52ba01aa486 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.h +++ b/drivers/net/ethernet/mellanox/mlx4/fw.h @@ -129,6 +129,7 @@ struct mlx4_dev_cap { u32 dmfs_high_rate_qpn_range; struct mlx4_rate_limit_caps rl_caps; struct mlx4_port_cap port_cap[MLX4_MAX_PORTS + 1]; + bool wol_port[MLX4_MAX_PORTS + 1]; }; struct mlx4_func_cap { diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index a27c9c13a36e..09b9bc17bce9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -424,6 +424,8 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev->caps.stat_rate_support = dev_cap->stat_rate_support; dev->caps.max_gso_sz = dev_cap->max_gso_sz; dev->caps.max_rss_tbl_sz = dev_cap->max_rss_tbl_sz; + dev->caps.wol_port[1] = dev_cap->wol_port[1]; + dev->caps.wol_port[2] = dev_cap->wol_port[2]; /* Save uar page shift */ if (!mlx4_is_slave(dev)) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 656b2d3f1bee..5eb1606765c5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -626,8 +626,8 @@ static int mlxsw_sp_port_attr_br_flags_set(struct mlxsw_sp_port *mlxsw_sp_port, bridge_port = mlxsw_sp_bridge_port_find(mlxsw_sp_port->mlxsw_sp->bridge, orig_dev); - if (WARN_ON(!bridge_port)) - return -EINVAL; + if (!bridge_port) + return 0; err = mlxsw_sp_bridge_port_flood_table_set(mlxsw_sp_port, bridge_port, MLXSW_SP_FLOOD_TYPE_UC, @@ -711,8 +711,8 @@ static int mlxsw_sp_port_attr_mc_router_set(struct mlxsw_sp_port *mlxsw_sp_port, bridge_port = mlxsw_sp_bridge_port_find(mlxsw_sp_port->mlxsw_sp->bridge, orig_dev); - if (WARN_ON(!bridge_port)) - return -EINVAL; + if (!bridge_port) + return 0; if (!bridge_port->bridge_device->multicast_enabled) return 0; @@ -1283,15 +1283,15 @@ static int mlxsw_sp_port_mdb_add(struct mlxsw_sp_port *mlxsw_sp_port, return 0; bridge_port = mlxsw_sp_bridge_port_find(mlxsw_sp->bridge, orig_dev); - if (WARN_ON(!bridge_port)) - return -EINVAL; + if (!bridge_port) + return 0; bridge_device = bridge_port->bridge_device; mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_bridge(mlxsw_sp_port, bridge_device, mdb->vid); - if (WARN_ON(!mlxsw_sp_port_vlan)) - return -EINVAL; + if (!mlxsw_sp_port_vlan) + return 0; fid_index = mlxsw_sp_fid_index(mlxsw_sp_port_vlan->fid); @@ -1407,15 +1407,15 @@ static int mlxsw_sp_port_mdb_del(struct mlxsw_sp_port *mlxsw_sp_port, int err = 0; bridge_port = mlxsw_sp_bridge_port_find(mlxsw_sp->bridge, orig_dev); - if (WARN_ON(!bridge_port)) - return -EINVAL; + if (!bridge_port) + return 0; bridge_device = bridge_port->bridge_device; mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_bridge(mlxsw_sp_port, bridge_device, mdb->vid); - if (WARN_ON(!mlxsw_sp_port_vlan)) - return -EINVAL; + if (!mlxsw_sp_port_vlan) + return 0; fid_index = mlxsw_sp_fid_index(mlxsw_sp_port_vlan->fid); @@ -1974,6 +1974,17 @@ static void mlxsw_sp_fdb_fini(struct mlxsw_sp *mlxsw_sp) } +static void mlxsw_sp_mids_fini(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_mid *mid, *tmp; + + list_for_each_entry_safe(mid, tmp, &mlxsw_sp->bridge->mids_list, list) { + list_del(&mid->list); + clear_bit(mid->mid, mlxsw_sp->bridge->mids_bitmap); + kfree(mid); + } +} + int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp) { struct mlxsw_sp_bridge *bridge; @@ -1996,7 +2007,7 @@ int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp) void mlxsw_sp_switchdev_fini(struct mlxsw_sp *mlxsw_sp) { mlxsw_sp_fdb_fini(mlxsw_sp); - WARN_ON(!list_empty(&mlxsw_sp->bridge->mids_list)); + mlxsw_sp_mids_fini(mlxsw_sp); WARN_ON(!list_empty(&mlxsw_sp->bridge->bridges_list)); kfree(mlxsw_sp->bridge); } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 18750ff0ede6..4631ca8b8eb2 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -513,6 +513,7 @@ nfp_net_tx_ring_init(struct nfp_net_tx_ring *tx_ring, tx_ring->idx = idx; tx_ring->r_vec = r_vec; tx_ring->is_xdp = is_xdp; + u64_stats_init(&tx_ring->r_vec->tx_sync); tx_ring->qcidx = tx_ring->idx * nn->stride_tx; tx_ring->qcp_q = nn->tx_bar + NFP_QCP_QUEUE_OFF(tx_ring->qcidx); @@ -532,6 +533,7 @@ nfp_net_rx_ring_init(struct nfp_net_rx_ring *rx_ring, rx_ring->idx = idx; rx_ring->r_vec = r_vec; + u64_stats_init(&rx_ring->r_vec->rx_sync); rx_ring->fl_qcidx = rx_ring->idx * nn->stride_rx; rx_ring->qcp_fl = nn->rx_bar + NFP_QCP_QUEUE_OFF(rx_ring->fl_qcidx); diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 9da91045d167..3eb241657368 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -253,7 +253,7 @@ int qed_mcp_cmd_init(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) size = MFW_DRV_MSG_MAX_DWORDS(p_info->mfw_mb_length) * sizeof(u32); p_info->mfw_mb_cur = kzalloc(size, GFP_KERNEL); p_info->mfw_mb_shadow = kzalloc(size, GFP_KERNEL); - if (!p_info->mfw_mb_shadow || !p_info->mfw_mb_addr) + if (!p_info->mfw_mb_cur || !p_info->mfw_mb_shadow) goto err; return 0; diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c index 32279d21c836..c2121d214f08 100644 --- a/drivers/net/ethernet/ti/cpts.c +++ b/drivers/net/ethernet/ti/cpts.c @@ -31,9 +31,18 @@ #include "cpts.h" +#define CPTS_SKB_TX_WORK_TIMEOUT 1 /* jiffies */ + +struct cpts_skb_cb_data { + unsigned long tmo; +}; + #define cpts_read32(c, r) readl_relaxed(&c->reg->r) #define cpts_write32(c, v, r) writel_relaxed(v, &c->reg->r) +static int cpts_match(struct sk_buff *skb, unsigned int ptp_class, + u16 ts_seqid, u8 ts_msgtype); + static int event_expired(struct cpts_event *event) { return time_after(jiffies, event->tmo); @@ -77,6 +86,47 @@ static int cpts_purge_events(struct cpts *cpts) return removed ? 0 : -1; } +static bool cpts_match_tx_ts(struct cpts *cpts, struct cpts_event *event) +{ + struct sk_buff *skb, *tmp; + u16 seqid; + u8 mtype; + bool found = false; + + mtype = (event->high >> MESSAGE_TYPE_SHIFT) & MESSAGE_TYPE_MASK; + seqid = (event->high >> SEQUENCE_ID_SHIFT) & SEQUENCE_ID_MASK; + + /* no need to grab txq.lock as access is always done under cpts->lock */ + skb_queue_walk_safe(&cpts->txq, skb, tmp) { + struct skb_shared_hwtstamps ssh; + unsigned int class = ptp_classify_raw(skb); + struct cpts_skb_cb_data *skb_cb = + (struct cpts_skb_cb_data *)skb->cb; + + if (cpts_match(skb, class, seqid, mtype)) { + u64 ns = timecounter_cyc2time(&cpts->tc, event->low); + + memset(&ssh, 0, sizeof(ssh)); + ssh.hwtstamp = ns_to_ktime(ns); + skb_tstamp_tx(skb, &ssh); + found = true; + __skb_unlink(skb, &cpts->txq); + dev_consume_skb_any(skb); + dev_dbg(cpts->dev, "match tx timestamp mtype %u seqid %04x\n", + mtype, seqid); + } else if (time_after(jiffies, skb_cb->tmo)) { + /* timeout any expired skbs over 1s */ + dev_dbg(cpts->dev, + "expiring tx timestamp mtype %u seqid %04x\n", + mtype, seqid); + __skb_unlink(skb, &cpts->txq); + dev_consume_skb_any(skb); + } + } + + return found; +} + /* * Returns zero if matching event type was found. */ @@ -101,9 +151,15 @@ static int cpts_fifo_read(struct cpts *cpts, int match) event->low = lo; type = event_type(event); switch (type) { + case CPTS_EV_TX: + if (cpts_match_tx_ts(cpts, event)) { + /* if the new event matches an existing skb, + * then don't queue it + */ + break; + } case CPTS_EV_PUSH: case CPTS_EV_RX: - case CPTS_EV_TX: list_del_init(&event->list); list_add_tail(&event->list, &cpts->events); break; @@ -224,6 +280,24 @@ static int cpts_ptp_enable(struct ptp_clock_info *ptp, return -EOPNOTSUPP; } +static long cpts_overflow_check(struct ptp_clock_info *ptp) +{ + struct cpts *cpts = container_of(ptp, struct cpts, info); + unsigned long delay = cpts->ov_check_period; + struct timespec64 ts; + unsigned long flags; + + spin_lock_irqsave(&cpts->lock, flags); + ts = ns_to_timespec64(timecounter_read(&cpts->tc)); + + if (!skb_queue_empty(&cpts->txq)) + delay = CPTS_SKB_TX_WORK_TIMEOUT; + spin_unlock_irqrestore(&cpts->lock, flags); + + pr_debug("cpts overflow check at %lld.%09lu\n", ts.tv_sec, ts.tv_nsec); + return (long)delay; +} + static struct ptp_clock_info cpts_info = { .owner = THIS_MODULE, .name = "CTPS timer", @@ -236,18 +310,9 @@ static struct ptp_clock_info cpts_info = { .gettime64 = cpts_ptp_gettime, .settime64 = cpts_ptp_settime, .enable = cpts_ptp_enable, + .do_aux_work = cpts_overflow_check, }; -static void cpts_overflow_check(struct work_struct *work) -{ - struct timespec64 ts; - struct cpts *cpts = container_of(work, struct cpts, overflow_work.work); - - cpts_ptp_gettime(&cpts->info, &ts); - pr_debug("cpts overflow check at %lld.%09lu\n", ts.tv_sec, ts.tv_nsec); - schedule_delayed_work(&cpts->overflow_work, cpts->ov_check_period); -} - static int cpts_match(struct sk_buff *skb, unsigned int ptp_class, u16 ts_seqid, u8 ts_msgtype) { @@ -299,7 +364,7 @@ static u64 cpts_find_ts(struct cpts *cpts, struct sk_buff *skb, int ev_type) return 0; spin_lock_irqsave(&cpts->lock, flags); - cpts_fifo_read(cpts, CPTS_EV_PUSH); + cpts_fifo_read(cpts, -1); list_for_each_safe(this, next, &cpts->events) { event = list_entry(this, struct cpts_event, list); if (event_expired(event)) { @@ -317,6 +382,19 @@ static u64 cpts_find_ts(struct cpts *cpts, struct sk_buff *skb, int ev_type) break; } } + + if (ev_type == CPTS_EV_TX && !ns) { + struct cpts_skb_cb_data *skb_cb = + (struct cpts_skb_cb_data *)skb->cb; + /* Not found, add frame to queue for processing later. + * The periodic FIFO check will handle this. + */ + skb_get(skb); + /* get the timestamp for timeouts */ + skb_cb->tmo = jiffies + msecs_to_jiffies(100); + __skb_queue_tail(&cpts->txq, skb); + ptp_schedule_worker(cpts->clock, 0); + } spin_unlock_irqrestore(&cpts->lock, flags); return ns; @@ -358,6 +436,7 @@ int cpts_register(struct cpts *cpts) { int err, i; + skb_queue_head_init(&cpts->txq); INIT_LIST_HEAD(&cpts->events); INIT_LIST_HEAD(&cpts->pool); for (i = 0; i < CPTS_MAX_EVENTS; i++) @@ -378,7 +457,7 @@ int cpts_register(struct cpts *cpts) } cpts->phc_index = ptp_clock_index(cpts->clock); - schedule_delayed_work(&cpts->overflow_work, cpts->ov_check_period); + ptp_schedule_worker(cpts->clock, cpts->ov_check_period); return 0; err_ptp: @@ -392,14 +471,15 @@ void cpts_unregister(struct cpts *cpts) if (WARN_ON(!cpts->clock)) return; - cancel_delayed_work_sync(&cpts->overflow_work); - ptp_clock_unregister(cpts->clock); cpts->clock = NULL; cpts_write32(cpts, 0, int_enable); cpts_write32(cpts, 0, control); + /* Drop all packet */ + skb_queue_purge(&cpts->txq); + clk_disable(cpts->refclk); } EXPORT_SYMBOL_GPL(cpts_unregister); @@ -476,7 +556,6 @@ struct cpts *cpts_create(struct device *dev, void __iomem *regs, cpts->dev = dev; cpts->reg = (struct cpsw_cpts __iomem *)regs; spin_lock_init(&cpts->lock); - INIT_DELAYED_WORK(&cpts->overflow_work, cpts_overflow_check); ret = cpts_of_parse(cpts, node); if (ret) diff --git a/drivers/net/ethernet/ti/cpts.h b/drivers/net/ethernet/ti/cpts.h index 01ea82ba9cdc..73d73faf0f38 100644 --- a/drivers/net/ethernet/ti/cpts.h +++ b/drivers/net/ethernet/ti/cpts.h @@ -119,13 +119,13 @@ struct cpts { u32 cc_mult; /* for the nominal frequency */ struct cyclecounter cc; struct timecounter tc; - struct delayed_work overflow_work; int phc_index; struct clk *refclk; struct list_head events; struct list_head pool; struct cpts_event pool_data[CPTS_MAX_EVENTS]; unsigned long ov_check_period; + struct sk_buff_head txq; }; void cpts_rx_timestamp(struct cpts *cpts, struct sk_buff *skb); diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index de8156c6b292..2bbda71818ad 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1091,7 +1091,7 @@ static int geneve_validate(struct nlattr *tb[], struct nlattr *data[], if (data[IFLA_GENEVE_ID]) { __u32 vni = nla_get_u32(data[IFLA_GENEVE_ID]); - if (vni >= GENEVE_VID_MASK) + if (vni >= GENEVE_N_VID) return -ERANGE; } diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 1542e837fdfa..f38e32a7ec9c 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -364,7 +364,7 @@ static int gtp_dev_init(struct net_device *dev) gtp->dev = dev; - dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index d6c25580f8dd..12cc64bfcff8 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -765,7 +765,8 @@ struct netvsc_device { u32 max_chn; u32 num_chn; - refcount_t sc_offered; + atomic_t open_chn; + wait_queue_head_t subchan_open; struct rndis_device *extension; diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 0a9167dd72fb..d18c3326a1f7 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -78,6 +78,7 @@ static struct netvsc_device *alloc_net_device(void) net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT; net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT; init_completion(&net_device->channel_init_wait); + init_waitqueue_head(&net_device->subchan_open); return net_device; } @@ -1302,6 +1303,8 @@ int netvsc_device_add(struct hv_device *device, struct netvsc_channel *nvchan = &net_device->chan_table[i]; nvchan->channel = device->channel; + u64_stats_init(&nvchan->tx_stats.syncp); + u64_stats_init(&nvchan->rx_stats.syncp); } /* Enable NAPI handler before init callbacks */ diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 85c00e1c52b6..d6308ffda53e 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -1048,8 +1048,8 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc) else netif_napi_del(&nvchan->napi); - if (refcount_dec_and_test(&nvscdev->sc_offered)) - complete(&nvscdev->channel_init_wait); + atomic_inc(&nvscdev->open_chn); + wake_up(&nvscdev->subchan_open); } int rndis_filter_device_add(struct hv_device *dev, @@ -1090,8 +1090,6 @@ int rndis_filter_device_add(struct hv_device *dev, net_device->max_chn = 1; net_device->num_chn = 1; - refcount_set(&net_device->sc_offered, 0); - net_device->extension = rndis_device; rndis_device->ndev = net; @@ -1221,11 +1219,11 @@ int rndis_filter_device_add(struct hv_device *dev, rndis_device->ind_table[i] = ethtool_rxfh_indir_default(i, net_device->num_chn); + atomic_set(&net_device->open_chn, 1); num_rss_qs = net_device->num_chn - 1; if (num_rss_qs == 0) return 0; - refcount_set(&net_device->sc_offered, num_rss_qs); vmbus_set_sc_create_callback(dev->channel, netvsc_sc_open); init_packet = &net_device->channel_init_pkt; @@ -1242,15 +1240,19 @@ int rndis_filter_device_add(struct hv_device *dev, if (ret) goto out; + wait_for_completion(&net_device->channel_init_wait); if (init_packet->msg.v5_msg.subchn_comp.status != NVSP_STAT_SUCCESS) { ret = -ENODEV; goto out; } - wait_for_completion(&net_device->channel_init_wait); net_device->num_chn = 1 + init_packet->msg.v5_msg.subchn_comp.num_subchannels; + /* wait for all sub channels to open */ + wait_event(net_device->subchan_open, + atomic_read(&net_device->open_chn) == net_device->num_chn); + /* ignore failues from setting rss parameters, still have channels */ rndis_filter_set_rss_param(rndis_device, netvsc_hash_key, net_device->num_chn); diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index f37e3c1fd4e7..8dab74a81303 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -192,7 +192,7 @@ static int ipvlan_init(struct net_device *dev) netdev_lockdep_set_classes(dev); - ipvlan->pcpu_stats = alloc_percpu(struct ipvl_pcpu_stats); + ipvlan->pcpu_stats = netdev_alloc_pcpu_stats(struct ipvl_pcpu_stats); if (!ipvlan->pcpu_stats) return -ENOMEM; diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index bd4303944e44..a404552555d4 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1915,21 +1915,23 @@ static void __ppp_channel_push(struct channel *pch) spin_unlock(&pch->downl); /* see if there is anything from the attached unit to be sent */ if (skb_queue_empty(&pch->file.xq)) { - read_lock(&pch->upl); ppp = pch->ppp; if (ppp) - ppp_xmit_process(ppp); - read_unlock(&pch->upl); + __ppp_xmit_process(ppp); } } static void ppp_channel_push(struct channel *pch) { - local_bh_disable(); - - __ppp_channel_push(pch); - - local_bh_enable(); + read_lock_bh(&pch->upl); + if (pch->ppp) { + (*this_cpu_ptr(pch->ppp->xmit_recursion))++; + __ppp_channel_push(pch); + (*this_cpu_ptr(pch->ppp->xmit_recursion))--; + } else { + __ppp_channel_push(pch); + } + read_unlock_bh(&pch->upl); } /* diff --git a/drivers/net/usb/asix.h b/drivers/net/usb/asix.h index d1092421aaa7..9a4171b90947 100644 --- a/drivers/net/usb/asix.h +++ b/drivers/net/usb/asix.h @@ -209,6 +209,7 @@ void asix_write_cmd_async(struct usbnet *dev, u8 cmd, u16 value, int asix_rx_fixup_internal(struct usbnet *dev, struct sk_buff *skb, struct asix_rx_fixup_info *rx); int asix_rx_fixup_common(struct usbnet *dev, struct sk_buff *skb); +void asix_rx_fixup_common_free(struct asix_common_private *dp); struct sk_buff *asix_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags); diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c index 7847436c441e..522d2900cd1d 100644 --- a/drivers/net/usb/asix_common.c +++ b/drivers/net/usb/asix_common.c @@ -75,6 +75,27 @@ void asix_write_cmd_async(struct usbnet *dev, u8 cmd, u16 value, u16 index, value, index, data, size); } +static void reset_asix_rx_fixup_info(struct asix_rx_fixup_info *rx) +{ + /* Reset the variables that have a lifetime outside of + * asix_rx_fixup_internal() so that future processing starts from a + * known set of initial conditions. + */ + + if (rx->ax_skb) { + /* Discard any incomplete Ethernet frame in the netdev buffer */ + kfree_skb(rx->ax_skb); + rx->ax_skb = NULL; + } + + /* Assume the Data header 32-bit word is at the start of the current + * or next URB socket buffer so reset all the state variables. + */ + rx->remaining = 0; + rx->split_head = false; + rx->header = 0; +} + int asix_rx_fixup_internal(struct usbnet *dev, struct sk_buff *skb, struct asix_rx_fixup_info *rx) { @@ -99,15 +120,7 @@ int asix_rx_fixup_internal(struct usbnet *dev, struct sk_buff *skb, if (size != ((~rx->header >> 16) & 0x7ff)) { netdev_err(dev->net, "asix_rx_fixup() Data Header synchronisation was lost, remaining %d\n", rx->remaining); - if (rx->ax_skb) { - kfree_skb(rx->ax_skb); - rx->ax_skb = NULL; - /* Discard the incomplete netdev Ethernet frame - * and assume the Data header is at the start of - * the current URB socket buffer. - */ - } - rx->remaining = 0; + reset_asix_rx_fixup_info(rx); } } @@ -139,11 +152,13 @@ int asix_rx_fixup_internal(struct usbnet *dev, struct sk_buff *skb, if (size != ((~rx->header >> 16) & 0x7ff)) { netdev_err(dev->net, "asix_rx_fixup() Bad Header Length 0x%x, offset %d\n", rx->header, offset); + reset_asix_rx_fixup_info(rx); return 0; } if (size > dev->net->mtu + ETH_HLEN + VLAN_HLEN) { netdev_dbg(dev->net, "asix_rx_fixup() Bad RX Length %d\n", size); + reset_asix_rx_fixup_info(rx); return 0; } @@ -168,8 +183,10 @@ int asix_rx_fixup_internal(struct usbnet *dev, struct sk_buff *skb, if (rx->ax_skb) { skb_put_data(rx->ax_skb, skb->data + offset, copy_length); - if (!rx->remaining) + if (!rx->remaining) { usbnet_skb_return(dev, rx->ax_skb); + rx->ax_skb = NULL; + } } offset += (copy_length + 1) & 0xfffe; @@ -178,6 +195,7 @@ int asix_rx_fixup_internal(struct usbnet *dev, struct sk_buff *skb, if (skb->len != offset) { netdev_err(dev->net, "asix_rx_fixup() Bad SKB Length %d, %d\n", skb->len, offset); + reset_asix_rx_fixup_info(rx); return 0; } @@ -192,6 +210,21 @@ int asix_rx_fixup_common(struct usbnet *dev, struct sk_buff *skb) return asix_rx_fixup_internal(dev, skb, rx); } +void asix_rx_fixup_common_free(struct asix_common_private *dp) +{ + struct asix_rx_fixup_info *rx; + + if (!dp) + return; + + rx = &dp->rx_fixup_info; + + if (rx->ax_skb) { + kfree_skb(rx->ax_skb); + rx->ax_skb = NULL; + } +} + struct sk_buff *asix_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags) { diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index a3aa0a27dfe5..b2ff88e69a81 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -764,6 +764,7 @@ static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf) static void ax88772_unbind(struct usbnet *dev, struct usb_interface *intf) { + asix_rx_fixup_common_free(dev->driver_priv); kfree(dev->driver_priv); } diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 5833f7e2a127..b99a7fb09f8e 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -2367,9 +2367,6 @@ static int lan78xx_reset(struct lan78xx_net *dev) /* Init LTM */ lan78xx_init_ltm(dev); - dev->net->hard_header_len += TX_OVERHEAD; - dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len; - if (dev->udev->speed == USB_SPEED_SUPER) { buf = DEFAULT_BURST_CAP_SIZE / SS_USB_PKT_SIZE; dev->rx_urb_size = DEFAULT_BURST_CAP_SIZE; @@ -2855,16 +2852,19 @@ static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf) return ret; } + dev->net->hard_header_len += TX_OVERHEAD; + dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len; + /* Init all registers */ ret = lan78xx_reset(dev); - lan78xx_mdio_init(dev); + ret = lan78xx_mdio_init(dev); dev->net->flags |= IFF_MULTICAST; pdata->wol = WAKE_MAGIC; - return 0; + return ret; } static void lan78xx_unbind(struct lan78xx_net *dev, struct usb_interface *intf) @@ -3525,11 +3525,11 @@ static int lan78xx_probe(struct usb_interface *intf, udev = interface_to_usbdev(intf); udev = usb_get_dev(udev); - ret = -ENOMEM; netdev = alloc_etherdev(sizeof(struct lan78xx_net)); if (!netdev) { - dev_err(&intf->dev, "Error: OOM\n"); - goto out1; + dev_err(&intf->dev, "Error: OOM\n"); + ret = -ENOMEM; + goto out1; } /* netdev_printk() needs this */ @@ -3610,7 +3610,7 @@ static int lan78xx_probe(struct usb_interface *intf, ret = register_netdev(netdev); if (ret != 0) { netif_err(dev, probe, netdev, "couldn't register the device\n"); - goto out2; + goto out3; } usb_set_intfdata(intf, dev); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 5894e3c9468f..8c3733608271 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1175,6 +1175,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x19d2, 0x1428, 2)}, /* Telewell TW-LTE 4G v2 */ {QMI_FIXED_INTF(0x19d2, 0x2002, 4)}, /* ZTE (Vodafone) K3765-Z */ {QMI_FIXED_INTF(0x2001, 0x7e19, 4)}, /* D-Link DWM-221 B1 */ + {QMI_FIXED_INTF(0x2001, 0x7e35, 4)}, /* D-Link DWM-222 */ {QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)}, /* Sierra Wireless MC7700 */ {QMI_FIXED_INTF(0x114f, 0x68a2, 8)}, /* Sierra Wireless MC7750 */ {QMI_FIXED_INTF(0x1199, 0x68a2, 8)}, /* Sierra Wireless MC7710 in QMI mode */ @@ -1340,10 +1341,14 @@ static int qmi_wwan_probe(struct usb_interface *intf, static void qmi_wwan_disconnect(struct usb_interface *intf) { struct usbnet *dev = usb_get_intfdata(intf); - struct qmi_wwan_state *info = (void *)&dev->data; + struct qmi_wwan_state *info; struct list_head *iter; struct net_device *ldev; + /* called twice if separate control and data intf */ + if (!dev) + return; + info = (void *)&dev->data; if (info->flags & QMI_WWAN_FLAG_MUX) { if (!rtnl_trylock()) { restart_syscall(); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 96aa7e6cf214..e17baac70f43 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -623,6 +623,7 @@ static struct sk_buff **vxlan_gro_receive(struct sock *sk, out: skb_gro_remcsum_cleanup(skb, &grc); + skb->remcsum_offload = 0; NAPI_GRO_CB(skb)->flush |= flush; return pp; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index c49f1f8b2e57..37046ac2c441 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -336,7 +336,7 @@ static int nvme_get_stream_params(struct nvme_ctrl *ctrl, c.directive.opcode = nvme_admin_directive_recv; c.directive.nsid = cpu_to_le32(nsid); - c.directive.numd = cpu_to_le32(sizeof(*s)); + c.directive.numd = cpu_to_le32((sizeof(*s) >> 2) - 1); c.directive.doper = NVME_DIR_RCV_ST_OP_PARAM; c.directive.dtype = NVME_DIR_STREAMS; @@ -1509,7 +1509,7 @@ static void nvme_set_queue_limits(struct nvme_ctrl *ctrl, blk_queue_write_cache(q, vwc, vwc); } -static void nvme_configure_apst(struct nvme_ctrl *ctrl) +static int nvme_configure_apst(struct nvme_ctrl *ctrl) { /* * APST (Autonomous Power State Transition) lets us program a @@ -1538,16 +1538,16 @@ static void nvme_configure_apst(struct nvme_ctrl *ctrl) * then don't do anything. */ if (!ctrl->apsta) - return; + return 0; if (ctrl->npss > 31) { dev_warn(ctrl->device, "NPSS is invalid; not using APST\n"); - return; + return 0; } table = kzalloc(sizeof(*table), GFP_KERNEL); if (!table) - return; + return 0; if (!ctrl->apst_enabled || ctrl->ps_max_latency_us == 0) { /* Turn off APST. */ @@ -1629,6 +1629,7 @@ static void nvme_configure_apst(struct nvme_ctrl *ctrl) dev_err(ctrl->device, "failed to set APST feature (%d)\n", ret); kfree(table); + return ret; } static void nvme_set_latency_tolerance(struct device *dev, s32 val) @@ -1835,13 +1836,16 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) * In fabrics we need to verify the cntlid matches the * admin connect */ - if (ctrl->cntlid != le16_to_cpu(id->cntlid)) + if (ctrl->cntlid != le16_to_cpu(id->cntlid)) { ret = -EINVAL; + goto out_free; + } if (!ctrl->opts->discovery_nqn && !ctrl->kas) { dev_err(ctrl->device, "keep-alive support is mandatory for fabrics\n"); ret = -EINVAL; + goto out_free; } } else { ctrl->cntlid = le16_to_cpu(id->cntlid); @@ -1856,11 +1860,20 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) else if (!ctrl->apst_enabled && prev_apst_enabled) dev_pm_qos_hide_latency_tolerance(ctrl->device); - nvme_configure_apst(ctrl); - nvme_configure_directives(ctrl); + ret = nvme_configure_apst(ctrl); + if (ret < 0) + return ret; + + ret = nvme_configure_directives(ctrl); + if (ret < 0) + return ret; ctrl->identified = true; + return 0; + +out_free: + kfree(id); return ret; } EXPORT_SYMBOL_GPL(nvme_init_identify); @@ -2004,9 +2017,11 @@ static ssize_t wwid_show(struct device *dev, struct device_attribute *attr, if (memchr_inv(ns->eui, 0, sizeof(ns->eui))) return sprintf(buf, "eui.%8phN\n", ns->eui); - while (ctrl->serial[serial_len - 1] == ' ') + while (serial_len > 0 && (ctrl->serial[serial_len - 1] == ' ' || + ctrl->serial[serial_len - 1] == '\0')) serial_len--; - while (ctrl->model[model_len - 1] == ' ') + while (model_len > 0 && (ctrl->model[model_len - 1] == ' ' || + ctrl->model[model_len - 1] == '\0')) model_len--; return sprintf(buf, "nvme.%04x-%*phN-%*phN-%08x\n", ctrl->vid, diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index cd888a47d0fc..74a124a06264 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1558,11 +1558,9 @@ static inline void nvme_release_cmb(struct nvme_dev *dev) if (dev->cmb) { iounmap(dev->cmb); dev->cmb = NULL; - if (dev->cmbsz) { - sysfs_remove_file_from_group(&dev->ctrl.device->kobj, - &dev_attr_cmb.attr, NULL); - dev->cmbsz = 0; - } + sysfs_remove_file_from_group(&dev->ctrl.device->kobj, + &dev_attr_cmb.attr, NULL); + dev->cmbsz = 0; } } @@ -1953,16 +1951,14 @@ static int nvme_pci_enable(struct nvme_dev *dev) /* * CMBs can currently only exist on >=1.2 PCIe devices. We only - * populate sysfs if a CMB is implemented. Note that we add the - * CMB attribute to the nvme_ctrl kobj which removes the need to remove - * it on exit. Since nvme_dev_attrs_group has no name we can pass - * NULL as final argument to sysfs_add_file_to_group. + * populate sysfs if a CMB is implemented. Since nvme_dev_attrs_group + * has no name we can pass NULL as final argument to + * sysfs_add_file_to_group. */ if (readl(dev->bar + NVME_REG_VS) >= NVME_VS(1, 2, 0)) { dev->cmb = nvme_map_cmb(dev); - - if (dev->cmbsz) { + if (dev->cmb) { if (sysfs_add_file_to_group(&dev->ctrl.device->kobj, &dev_attr_cmb.attr, NULL)) dev_warn(dev->ctrl.device, diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 31ca55dfcb1d..1b7f2520a20d 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -114,6 +114,11 @@ struct nvmet_fc_tgtport { struct kref ref; }; +struct nvmet_fc_defer_fcp_req { + struct list_head req_list; + struct nvmefc_tgt_fcp_req *fcp_req; +}; + struct nvmet_fc_tgt_queue { bool ninetypercent; u16 qid; @@ -132,6 +137,8 @@ struct nvmet_fc_tgt_queue { struct nvmet_fc_tgt_assoc *assoc; struct nvmet_fc_fcp_iod *fod; /* array of fcp_iods */ struct list_head fod_list; + struct list_head pending_cmd_list; + struct list_head avail_defer_list; struct workqueue_struct *work_q; struct kref ref; } __aligned(sizeof(unsigned long long)); @@ -223,6 +230,8 @@ static void nvmet_fc_tgt_q_put(struct nvmet_fc_tgt_queue *queue); static int nvmet_fc_tgt_q_get(struct nvmet_fc_tgt_queue *queue); static void nvmet_fc_tgtport_put(struct nvmet_fc_tgtport *tgtport); static int nvmet_fc_tgtport_get(struct nvmet_fc_tgtport *tgtport); +static void nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport, + struct nvmet_fc_fcp_iod *fod); /* *********************** FC-NVME DMA Handling **************************** */ @@ -463,9 +472,9 @@ static struct nvmet_fc_fcp_iod * nvmet_fc_alloc_fcp_iod(struct nvmet_fc_tgt_queue *queue) { static struct nvmet_fc_fcp_iod *fod; - unsigned long flags; - spin_lock_irqsave(&queue->qlock, flags); + lockdep_assert_held(&queue->qlock); + fod = list_first_entry_or_null(&queue->fod_list, struct nvmet_fc_fcp_iod, fcp_list); if (fod) { @@ -477,17 +486,37 @@ nvmet_fc_alloc_fcp_iod(struct nvmet_fc_tgt_queue *queue) * will "inherit" that reference. */ } - spin_unlock_irqrestore(&queue->qlock, flags); return fod; } static void +nvmet_fc_queue_fcp_req(struct nvmet_fc_tgtport *tgtport, + struct nvmet_fc_tgt_queue *queue, + struct nvmefc_tgt_fcp_req *fcpreq) +{ + struct nvmet_fc_fcp_iod *fod = fcpreq->nvmet_fc_private; + + /* + * put all admin cmds on hw queue id 0. All io commands go to + * the respective hw queue based on a modulo basis + */ + fcpreq->hwqid = queue->qid ? + ((queue->qid - 1) % tgtport->ops->max_hw_queues) : 0; + + if (tgtport->ops->target_features & NVMET_FCTGTFEAT_CMD_IN_ISR) + queue_work_on(queue->cpu, queue->work_q, &fod->work); + else + nvmet_fc_handle_fcp_rqst(tgtport, fod); +} + +static void nvmet_fc_free_fcp_iod(struct nvmet_fc_tgt_queue *queue, struct nvmet_fc_fcp_iod *fod) { struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq; struct nvmet_fc_tgtport *tgtport = fod->tgtport; + struct nvmet_fc_defer_fcp_req *deferfcp; unsigned long flags; fc_dma_sync_single_for_cpu(tgtport->dev, fod->rspdma, @@ -495,21 +524,56 @@ nvmet_fc_free_fcp_iod(struct nvmet_fc_tgt_queue *queue, fcpreq->nvmet_fc_private = NULL; - spin_lock_irqsave(&queue->qlock, flags); - list_add_tail(&fod->fcp_list, &fod->queue->fod_list); fod->active = false; fod->abort = false; fod->aborted = false; fod->writedataactive = false; fod->fcpreq = NULL; + + tgtport->ops->fcp_req_release(&tgtport->fc_target_port, fcpreq); + + spin_lock_irqsave(&queue->qlock, flags); + deferfcp = list_first_entry_or_null(&queue->pending_cmd_list, + struct nvmet_fc_defer_fcp_req, req_list); + if (!deferfcp) { + list_add_tail(&fod->fcp_list, &fod->queue->fod_list); + spin_unlock_irqrestore(&queue->qlock, flags); + + /* Release reference taken at queue lookup and fod allocation */ + nvmet_fc_tgt_q_put(queue); + return; + } + + /* Re-use the fod for the next pending cmd that was deferred */ + list_del(&deferfcp->req_list); + + fcpreq = deferfcp->fcp_req; + + /* deferfcp can be reused for another IO at a later date */ + list_add_tail(&deferfcp->req_list, &queue->avail_defer_list); + spin_unlock_irqrestore(&queue->qlock, flags); + /* Save NVME CMD IO in fod */ + memcpy(&fod->cmdiubuf, fcpreq->rspaddr, fcpreq->rsplen); + + /* Setup new fcpreq to be processed */ + fcpreq->rspaddr = NULL; + fcpreq->rsplen = 0; + fcpreq->nvmet_fc_private = fod; + fod->fcpreq = fcpreq; + fod->active = true; + + /* inform LLDD IO is now being processed */ + tgtport->ops->defer_rcv(&tgtport->fc_target_port, fcpreq); + + /* Submit deferred IO for processing */ + nvmet_fc_queue_fcp_req(tgtport, queue, fcpreq); + /* - * release the reference taken at queue lookup and fod allocation + * Leave the queue lookup get reference taken when + * fod was originally allocated. */ - nvmet_fc_tgt_q_put(queue); - - tgtport->ops->fcp_req_release(&tgtport->fc_target_port, fcpreq); } static int @@ -569,6 +633,8 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc, queue->port = assoc->tgtport->port; queue->cpu = nvmet_fc_queue_to_cpu(assoc->tgtport, qid); INIT_LIST_HEAD(&queue->fod_list); + INIT_LIST_HEAD(&queue->avail_defer_list); + INIT_LIST_HEAD(&queue->pending_cmd_list); atomic_set(&queue->connected, 0); atomic_set(&queue->sqtail, 0); atomic_set(&queue->rsn, 1); @@ -638,6 +704,7 @@ nvmet_fc_delete_target_queue(struct nvmet_fc_tgt_queue *queue) { struct nvmet_fc_tgtport *tgtport = queue->assoc->tgtport; struct nvmet_fc_fcp_iod *fod = queue->fod; + struct nvmet_fc_defer_fcp_req *deferfcp; unsigned long flags; int i, writedataactive; bool disconnect; @@ -666,6 +733,35 @@ nvmet_fc_delete_target_queue(struct nvmet_fc_tgt_queue *queue) } } } + + /* Cleanup defer'ed IOs in queue */ + list_for_each_entry(deferfcp, &queue->avail_defer_list, req_list) { + list_del(&deferfcp->req_list); + kfree(deferfcp); + } + + for (;;) { + deferfcp = list_first_entry_or_null(&queue->pending_cmd_list, + struct nvmet_fc_defer_fcp_req, req_list); + if (!deferfcp) + break; + + list_del(&deferfcp->req_list); + spin_unlock_irqrestore(&queue->qlock, flags); + + tgtport->ops->defer_rcv(&tgtport->fc_target_port, + deferfcp->fcp_req); + + tgtport->ops->fcp_abort(&tgtport->fc_target_port, + deferfcp->fcp_req); + + tgtport->ops->fcp_req_release(&tgtport->fc_target_port, + deferfcp->fcp_req); + + kfree(deferfcp); + + spin_lock_irqsave(&queue->qlock, flags); + } spin_unlock_irqrestore(&queue->qlock, flags); flush_workqueue(queue->work_q); @@ -2172,11 +2268,38 @@ nvmet_fc_handle_fcp_rqst_work(struct work_struct *work) * Pass a FC-NVME FCP CMD IU received from the FC link to the nvmet-fc * layer for processing. * - * The nvmet-fc layer will copy cmd payload to an internal structure for - * processing. As such, upon completion of the routine, the LLDD may - * immediately free/reuse the CMD IU buffer passed in the call. + * The nvmet_fc layer allocates a local job structure (struct + * nvmet_fc_fcp_iod) from the queue for the io and copies the + * CMD IU buffer to the job structure. As such, on a successful + * completion (returns 0), the LLDD may immediately free/reuse + * the CMD IU buffer passed in the call. + * + * However, in some circumstances, due to the packetized nature of FC + * and the api of the FC LLDD which may issue a hw command to send the + * response, but the LLDD may not get the hw completion for that command + * and upcall the nvmet_fc layer before a new command may be + * asynchronously received - its possible for a command to be received + * before the LLDD and nvmet_fc have recycled the job structure. It gives + * the appearance of more commands received than fits in the sq. + * To alleviate this scenario, a temporary queue is maintained in the + * transport for pending LLDD requests waiting for a queue job structure. + * In these "overrun" cases, a temporary queue element is allocated + * the LLDD request and CMD iu buffer information remembered, and the + * routine returns a -EOVERFLOW status. Subsequently, when a queue job + * structure is freed, it is immediately reallocated for anything on the + * pending request list. The LLDDs defer_rcv() callback is called, + * informing the LLDD that it may reuse the CMD IU buffer, and the io + * is then started normally with the transport. * - * If this routine returns error, the lldd should abort the exchange. + * The LLDD, when receiving an -EOVERFLOW completion status, is to treat + * the completion as successful but must not reuse the CMD IU buffer + * until the LLDD's defer_rcv() callback has been called for the + * corresponding struct nvmefc_tgt_fcp_req pointer. + * + * If there is any other condition in which an error occurs, the + * transport will return a non-zero status indicating the error. + * In all cases other than -EOVERFLOW, the transport has not accepted the + * request and the LLDD should abort the exchange. * * @target_port: pointer to the (registered) target port the FCP CMD IU * was received on. @@ -2194,6 +2317,8 @@ nvmet_fc_rcv_fcp_req(struct nvmet_fc_target_port *target_port, struct nvme_fc_cmd_iu *cmdiu = cmdiubuf; struct nvmet_fc_tgt_queue *queue; struct nvmet_fc_fcp_iod *fod; + struct nvmet_fc_defer_fcp_req *deferfcp; + unsigned long flags; /* validate iu, so the connection id can be used to find the queue */ if ((cmdiubuf_len != sizeof(*cmdiu)) || @@ -2214,29 +2339,60 @@ nvmet_fc_rcv_fcp_req(struct nvmet_fc_target_port *target_port, * when the fod is freed. */ + spin_lock_irqsave(&queue->qlock, flags); + fod = nvmet_fc_alloc_fcp_iod(queue); - if (!fod) { + if (fod) { + spin_unlock_irqrestore(&queue->qlock, flags); + + fcpreq->nvmet_fc_private = fod; + fod->fcpreq = fcpreq; + + memcpy(&fod->cmdiubuf, cmdiubuf, cmdiubuf_len); + + nvmet_fc_queue_fcp_req(tgtport, queue, fcpreq); + + return 0; + } + + if (!tgtport->ops->defer_rcv) { + spin_unlock_irqrestore(&queue->qlock, flags); /* release the queue lookup reference */ nvmet_fc_tgt_q_put(queue); return -ENOENT; } - fcpreq->nvmet_fc_private = fod; - fod->fcpreq = fcpreq; - /* - * put all admin cmds on hw queue id 0. All io commands go to - * the respective hw queue based on a modulo basis - */ - fcpreq->hwqid = queue->qid ? - ((queue->qid - 1) % tgtport->ops->max_hw_queues) : 0; - memcpy(&fod->cmdiubuf, cmdiubuf, cmdiubuf_len); + deferfcp = list_first_entry_or_null(&queue->avail_defer_list, + struct nvmet_fc_defer_fcp_req, req_list); + if (deferfcp) { + /* Just re-use one that was previously allocated */ + list_del(&deferfcp->req_list); + } else { + spin_unlock_irqrestore(&queue->qlock, flags); - if (tgtport->ops->target_features & NVMET_FCTGTFEAT_CMD_IN_ISR) - queue_work_on(queue->cpu, queue->work_q, &fod->work); - else - nvmet_fc_handle_fcp_rqst(tgtport, fod); + /* Now we need to dynamically allocate one */ + deferfcp = kmalloc(sizeof(*deferfcp), GFP_KERNEL); + if (!deferfcp) { + /* release the queue lookup reference */ + nvmet_fc_tgt_q_put(queue); + return -ENOMEM; + } + spin_lock_irqsave(&queue->qlock, flags); + } - return 0; + /* For now, use rspaddr / rsplen to save payload information */ + fcpreq->rspaddr = cmdiubuf; + fcpreq->rsplen = cmdiubuf_len; + deferfcp->fcp_req = fcpreq; + + /* defer processing till a fod becomes available */ + list_add_tail(&deferfcp->req_list, &queue->pending_cmd_list); + + /* NOTE: the queue lookup reference is still valid */ + + spin_unlock_irqrestore(&queue->qlock, flags); + + return -EOVERFLOW; } EXPORT_SYMBOL_GPL(nvmet_fc_rcv_fcp_req); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index af0cc3456dc1..b4b7eab29400 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4260,6 +4260,41 @@ int pci_reset_function(struct pci_dev *dev) EXPORT_SYMBOL_GPL(pci_reset_function); /** + * pci_reset_function_locked - quiesce and reset a PCI device function + * @dev: PCI device to reset + * + * Some devices allow an individual function to be reset without affecting + * other functions in the same device. The PCI device must be responsive + * to PCI config space in order to use this function. + * + * This function does not just reset the PCI portion of a device, but + * clears all the state associated with the device. This function differs + * from __pci_reset_function() in that it saves and restores device state + * over the reset. It also differs from pci_reset_function() in that it + * requires the PCI device lock to be held. + * + * Returns 0 if the device function was successfully reset or negative if the + * device doesn't support resetting a single function. + */ +int pci_reset_function_locked(struct pci_dev *dev) +{ + int rc; + + rc = pci_probe_reset_function(dev); + if (rc) + return rc; + + pci_dev_save_and_disable(dev); + + rc = __pci_reset_function_locked(dev); + + pci_dev_restore(dev); + + return rc; +} +EXPORT_SYMBOL_GPL(pci_reset_function_locked); + +/** * pci_try_reset_function - quiesce and reset a PCI device function * @dev: PCI device to reset * diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index 20f1b4493994..04e929fd0ffe 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -1548,6 +1548,13 @@ static const struct dmi_system_id chv_no_valid_mask[] = { }, }, { + .ident = "HP Chromebook 11 G5 (Setzer)", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HP"), + DMI_MATCH(DMI_PRODUCT_NAME, "Setzer"), + }, + }, + { .ident = "Acer Chromebook R11 (Cyan)", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"), diff --git a/drivers/pinctrl/intel/pinctrl-merrifield.c b/drivers/pinctrl/intel/pinctrl-merrifield.c index 4d4ef42a39b5..86c4b3fab7b0 100644 --- a/drivers/pinctrl/intel/pinctrl-merrifield.c +++ b/drivers/pinctrl/intel/pinctrl-merrifield.c @@ -343,9 +343,9 @@ static const struct pinctrl_pin_desc mrfld_pins[] = { static const unsigned int mrfld_sdio_pins[] = { 50, 51, 52, 53, 54, 55, 56 }; static const unsigned int mrfld_spi5_pins[] = { 90, 91, 92, 93, 94, 95, 96 }; -static const unsigned int mrfld_uart0_pins[] = { 124, 125, 126, 127 }; -static const unsigned int mrfld_uart1_pins[] = { 128, 129, 130, 131 }; -static const unsigned int mrfld_uart2_pins[] = { 132, 133, 134, 135 }; +static const unsigned int mrfld_uart0_pins[] = { 115, 116, 117, 118 }; +static const unsigned int mrfld_uart1_pins[] = { 119, 120, 121, 122 }; +static const unsigned int mrfld_uart2_pins[] = { 123, 124, 125, 126 }; static const unsigned int mrfld_pwm0_pins[] = { 144 }; static const unsigned int mrfld_pwm1_pins[] = { 145 }; static const unsigned int mrfld_pwm2_pins[] = { 132 }; diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c index f024e25787fc..0c6d7812d6fd 100644 --- a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c +++ b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c @@ -37,7 +37,7 @@ #define IRQ_STATUS 0x10 #define IRQ_WKUP 0x18 -#define NB_FUNCS 2 +#define NB_FUNCS 3 #define GPIO_PER_REG 32 /** @@ -126,6 +126,16 @@ struct armada_37xx_pinctrl { .funcs = {_func1, "gpio"} \ } +#define PIN_GRP_GPIO_3(_name, _start, _nr, _mask, _v1, _v2, _v3, _f1, _f2) \ + { \ + .name = _name, \ + .start_pin = _start, \ + .npins = _nr, \ + .reg_mask = _mask, \ + .val = {_v1, _v2, _v3}, \ + .funcs = {_f1, _f2, "gpio"} \ + } + #define PIN_GRP_EXTRA(_name, _start, _nr, _mask, _v1, _v2, _start2, _nr2, \ _f1, _f2) \ { \ @@ -171,12 +181,13 @@ static struct armada_37xx_pin_group armada_37xx_sb_groups[] = { PIN_GRP_GPIO("usb32_drvvbus0", 0, 1, BIT(0), "drvbus"), PIN_GRP_GPIO("usb2_drvvbus1", 1, 1, BIT(1), "drvbus"), PIN_GRP_GPIO("sdio_sb", 24, 6, BIT(2), "sdio"), - PIN_GRP_EXTRA("rgmii", 6, 12, BIT(3), 0, BIT(3), 23, 1, "mii", "gpio"), + PIN_GRP_GPIO("rgmii", 6, 12, BIT(3), "mii"), PIN_GRP_GPIO("pcie1", 3, 2, BIT(4), "pcie"), PIN_GRP_GPIO("ptp", 20, 3, BIT(5), "ptp"), PIN_GRP("ptp_clk", 21, 1, BIT(6), "ptp", "mii"), PIN_GRP("ptp_trig", 22, 1, BIT(7), "ptp", "mii"), - PIN_GRP("mii_col", 23, 1, BIT(8), "mii", "mii_err"), + PIN_GRP_GPIO_3("mii_col", 23, 1, BIT(8) | BIT(14), 0, BIT(8), BIT(14), + "mii", "mii_err"), }; const struct armada_37xx_pin_data armada_37xx_pin_nb = { @@ -187,7 +198,7 @@ const struct armada_37xx_pin_data armada_37xx_pin_nb = { }; const struct armada_37xx_pin_data armada_37xx_pin_sb = { - .nr_pins = 29, + .nr_pins = 30, .name = "GPIO2", .groups = armada_37xx_sb_groups, .ngroups = ARRAY_SIZE(armada_37xx_sb_groups), @@ -208,7 +219,7 @@ static int armada_37xx_get_func_reg(struct armada_37xx_pin_group *grp, { int f; - for (f = 0; f < NB_FUNCS; f++) + for (f = 0; (f < NB_FUNCS) && grp->funcs[f]; f++) if (!strcmp(grp->funcs[f], func)) return f; @@ -795,7 +806,7 @@ static int armada_37xx_fill_group(struct armada_37xx_pinctrl *info) for (j = 0; j < grp->extra_npins; j++) grp->pins[i+j] = grp->extra_pin + j; - for (f = 0; f < NB_FUNCS; f++) { + for (f = 0; (f < NB_FUNCS) && grp->funcs[f]; f++) { int ret; /* check for unique functions and count groups */ ret = armada_37xx_add_function(info->funcs, &funcsize, @@ -847,7 +858,7 @@ static int armada_37xx_fill_func(struct armada_37xx_pinctrl *info) struct armada_37xx_pin_group *gp = &info->groups[g]; int f; - for (f = 0; f < NB_FUNCS; f++) { + for (f = 0; (f < NB_FUNCS) && gp->funcs[f]; f++) { if (strcmp(gp->funcs[f], name) == 0) { *groups = gp->name; groups++; diff --git a/drivers/pinctrl/sunxi/pinctrl-sun4i-a10.c b/drivers/pinctrl/sunxi/pinctrl-sun4i-a10.c index 159580c04b14..47a392bc73c8 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sun4i-a10.c +++ b/drivers/pinctrl/sunxi/pinctrl-sun4i-a10.c @@ -918,6 +918,7 @@ static const struct sunxi_desc_pin sun4i_a10_pins[] = { SUNXI_FUNCTION_VARIANT(0x3, "emac", /* ETXD1 */ PINCTRL_SUN7I_A20), SUNXI_FUNCTION(0x4, "keypad"), /* IN6 */ + SUNXI_FUNCTION(0x5, "sim"), /* DET */ SUNXI_FUNCTION_IRQ(0x6, 16), /* EINT16 */ SUNXI_FUNCTION(0x7, "csi1")), /* D16 */ SUNXI_PIN(SUNXI_PINCTRL_PIN(H, 17), diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-pro4.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-pro4.c index a433a306a2d0..c75e094b2d90 100644 --- a/drivers/pinctrl/uniphier/pinctrl-uniphier-pro4.c +++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-pro4.c @@ -1084,7 +1084,7 @@ static const unsigned usb1_pins[] = {182, 183}; static const int usb1_muxvals[] = {0, 0}; static const unsigned usb2_pins[] = {184, 185}; static const int usb2_muxvals[] = {0, 0}; -static const unsigned usb3_pins[] = {186, 187}; +static const unsigned usb3_pins[] = {187, 188}; static const int usb3_muxvals[] = {0, 0}; static const unsigned port_range0_pins[] = { 300, 301, 302, 303, 304, 305, 306, 307, /* PORT0x */ diff --git a/drivers/pinctrl/zte/pinctrl-zx.c b/drivers/pinctrl/zte/pinctrl-zx.c index 787e3967bd5c..f828ee340a98 100644 --- a/drivers/pinctrl/zte/pinctrl-zx.c +++ b/drivers/pinctrl/zte/pinctrl-zx.c @@ -64,10 +64,8 @@ static int zx_set_mux(struct pinctrl_dev *pctldev, unsigned int func_selector, struct zx_pinctrl_soc_info *info = zpctl->info; const struct pinctrl_pin_desc *pindesc = info->pins + group_selector; struct zx_pin_data *data = pindesc->drv_data; - struct zx_mux_desc *mux = data->muxes; - u32 mask = (1 << data->width) - 1; - u32 offset = data->offset; - u32 bitpos = data->bitpos; + struct zx_mux_desc *mux; + u32 mask, offset, bitpos; struct function_desc *func; unsigned long flags; u32 val, mval; @@ -76,6 +74,11 @@ static int zx_set_mux(struct pinctrl_dev *pctldev, unsigned int func_selector, if (!data) return -EINVAL; + mux = data->muxes; + mask = (1 << data->width) - 1; + offset = data->offset; + bitpos = data->bitpos; + func = pinmux_generic_get_function(pctldev, func_selector); if (!func) return -EINVAL; diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index b77435783ef3..7eacc1c4b3b1 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -28,6 +28,7 @@ #include <linux/slab.h> #include <linux/syscalls.h> #include <linux/uaccess.h> +#include <uapi/linux/sched/types.h> #include "ptp_private.h" @@ -184,6 +185,19 @@ static void delete_ptp_clock(struct posix_clock *pc) kfree(ptp); } +static void ptp_aux_kworker(struct kthread_work *work) +{ + struct ptp_clock *ptp = container_of(work, struct ptp_clock, + aux_work.work); + struct ptp_clock_info *info = ptp->info; + long delay; + + delay = info->do_aux_work(info); + + if (delay >= 0) + kthread_queue_delayed_work(ptp->kworker, &ptp->aux_work, delay); +} + /* public interface */ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, @@ -217,6 +231,20 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, mutex_init(&ptp->pincfg_mux); init_waitqueue_head(&ptp->tsev_wq); + if (ptp->info->do_aux_work) { + char *worker_name = kasprintf(GFP_KERNEL, "ptp%d", ptp->index); + + kthread_init_delayed_work(&ptp->aux_work, ptp_aux_kworker); + ptp->kworker = kthread_create_worker(0, worker_name ? + worker_name : info->name); + kfree(worker_name); + if (IS_ERR(ptp->kworker)) { + err = PTR_ERR(ptp->kworker); + pr_err("failed to create ptp aux_worker %d\n", err); + goto kworker_err; + } + } + err = ptp_populate_pin_groups(ptp); if (err) goto no_pin_groups; @@ -259,6 +287,9 @@ no_pps: no_device: ptp_cleanup_pin_groups(ptp); no_pin_groups: + if (ptp->kworker) + kthread_destroy_worker(ptp->kworker); +kworker_err: mutex_destroy(&ptp->tsevq_mux); mutex_destroy(&ptp->pincfg_mux); ida_simple_remove(&ptp_clocks_map, index); @@ -274,6 +305,11 @@ int ptp_clock_unregister(struct ptp_clock *ptp) ptp->defunct = 1; wake_up_interruptible(&ptp->tsev_wq); + if (ptp->kworker) { + kthread_cancel_delayed_work_sync(&ptp->aux_work); + kthread_destroy_worker(ptp->kworker); + } + /* Release the clock's resources. */ if (ptp->pps_source) pps_unregister_source(ptp->pps_source); @@ -339,6 +375,12 @@ int ptp_find_pin(struct ptp_clock *ptp, } EXPORT_SYMBOL(ptp_find_pin); +int ptp_schedule_worker(struct ptp_clock *ptp, unsigned long delay) +{ + return kthread_mod_delayed_work(ptp->kworker, &ptp->aux_work, delay); +} +EXPORT_SYMBOL(ptp_schedule_worker); + /* module operations */ static void __exit ptp_exit(void) diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h index d95888974d0c..b86f1bfecd6f 100644 --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -22,6 +22,7 @@ #include <linux/cdev.h> #include <linux/device.h> +#include <linux/kthread.h> #include <linux/mutex.h> #include <linux/posix-clock.h> #include <linux/ptp_clock.h> @@ -56,6 +57,8 @@ struct ptp_clock { struct attribute_group pin_attr_group; /* 1st entry is a pointer to the real group, 2nd is NULL terminator */ const struct attribute_group *pin_attr_groups[2]; + struct kthread_worker *kworker; + struct kthread_delayed_work aux_work; }; /* diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 8975cd321390..d42e758518ed 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -2512,7 +2512,7 @@ static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr, struct rtable *rt = (struct rtable *) dst; __be32 *pkey = &ip_hdr(skb)->daddr; - if (rt->rt_gateway) + if (rt && rt->rt_gateway) pkey = &rt->rt_gateway; /* IPv4 */ @@ -2523,7 +2523,7 @@ static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr, struct rt6_info *rt = (struct rt6_info *) dst; struct in6_addr *pkey = &ipv6_hdr(skb)->daddr; - if (!ipv6_addr_any(&rt->rt6i_gateway)) + if (rt && !ipv6_addr_any(&rt->rt6i_gateway)) pkey = &rt->rt6i_gateway; /* IPv6 */ diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c index 707ee2f5954d..4591113c49de 100644 --- a/drivers/scsi/aacraid/aachba.c +++ b/drivers/scsi/aacraid/aachba.c @@ -3198,10 +3198,11 @@ static int query_disk(struct aac_dev *dev, void __user *arg) return -EBUSY; if (copy_from_user(&qd, arg, sizeof (struct aac_query_disk))) return -EFAULT; - if (qd.cnum == -1) + if (qd.cnum == -1) { + if (qd.id < 0 || qd.id >= dev->maximum_num_containers) + return -EINVAL; qd.cnum = qd.id; - else if ((qd.bus == -1) && (qd.id == -1) && (qd.lun == -1)) - { + } else if ((qd.bus == -1) && (qd.id == -1) && (qd.lun == -1)) { if (qd.cnum < 0 || qd.cnum >= dev->maximum_num_containers) return -EINVAL; qd.instance = dev->scsi_host_ptr->host_no; diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c index 7dfe709a7138..6844ba361616 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c +++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c @@ -2624,12 +2624,11 @@ static struct fcoe_transport bnx2fc_transport = { }; /** - * bnx2fc_percpu_thread_create - Create a receive thread for an - * online CPU + * bnx2fc_cpu_online - Create a receive thread for an online CPU * * @cpu: cpu index for the online cpu */ -static void bnx2fc_percpu_thread_create(unsigned int cpu) +static int bnx2fc_cpu_online(unsigned int cpu) { struct bnx2fc_percpu_s *p; struct task_struct *thread; @@ -2639,15 +2638,17 @@ static void bnx2fc_percpu_thread_create(unsigned int cpu) thread = kthread_create_on_node(bnx2fc_percpu_io_thread, (void *)p, cpu_to_node(cpu), "bnx2fc_thread/%d", cpu); + if (IS_ERR(thread)) + return PTR_ERR(thread); + /* bind thread to the cpu */ - if (likely(!IS_ERR(thread))) { - kthread_bind(thread, cpu); - p->iothread = thread; - wake_up_process(thread); - } + kthread_bind(thread, cpu); + p->iothread = thread; + wake_up_process(thread); + return 0; } -static void bnx2fc_percpu_thread_destroy(unsigned int cpu) +static int bnx2fc_cpu_offline(unsigned int cpu) { struct bnx2fc_percpu_s *p; struct task_struct *thread; @@ -2661,7 +2662,6 @@ static void bnx2fc_percpu_thread_destroy(unsigned int cpu) thread = p->iothread; p->iothread = NULL; - /* Free all work in the list */ list_for_each_entry_safe(work, tmp, &p->work_list, list) { list_del_init(&work->list); @@ -2673,20 +2673,6 @@ static void bnx2fc_percpu_thread_destroy(unsigned int cpu) if (thread) kthread_stop(thread); -} - - -static int bnx2fc_cpu_online(unsigned int cpu) -{ - printk(PFX "CPU %x online: Create Rx thread\n", cpu); - bnx2fc_percpu_thread_create(cpu); - return 0; -} - -static int bnx2fc_cpu_dead(unsigned int cpu) -{ - printk(PFX "CPU %x offline: Remove Rx thread\n", cpu); - bnx2fc_percpu_thread_destroy(cpu); return 0; } @@ -2761,30 +2747,16 @@ static int __init bnx2fc_mod_init(void) spin_lock_init(&p->fp_work_lock); } - get_online_cpus(); - - for_each_online_cpu(cpu) - bnx2fc_percpu_thread_create(cpu); - - rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, - "scsi/bnx2fc:online", - bnx2fc_cpu_online, NULL); + rc = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "scsi/bnx2fc:online", + bnx2fc_cpu_online, bnx2fc_cpu_offline); if (rc < 0) - goto stop_threads; + goto stop_thread; bnx2fc_online_state = rc; - cpuhp_setup_state_nocalls(CPUHP_SCSI_BNX2FC_DEAD, "scsi/bnx2fc:dead", - NULL, bnx2fc_cpu_dead); - put_online_cpus(); - cnic_register_driver(CNIC_ULP_FCOE, &bnx2fc_cnic_cb); - return 0; -stop_threads: - for_each_online_cpu(cpu) - bnx2fc_percpu_thread_destroy(cpu); - put_online_cpus(); +stop_thread: kthread_stop(l2_thread); free_wq: destroy_workqueue(bnx2fc_wq); @@ -2803,7 +2775,6 @@ static void __exit bnx2fc_mod_exit(void) struct fcoe_percpu_s *bg; struct task_struct *l2_thread; struct sk_buff *skb; - unsigned int cpu = 0; /* * NOTE: Since cnic calls register_driver routine rtnl_lock, @@ -2844,16 +2815,7 @@ static void __exit bnx2fc_mod_exit(void) if (l2_thread) kthread_stop(l2_thread); - get_online_cpus(); - /* Destroy per cpu threads */ - for_each_online_cpu(cpu) { - bnx2fc_percpu_thread_destroy(cpu); - } - - cpuhp_remove_state_nocalls(bnx2fc_online_state); - cpuhp_remove_state_nocalls(CPUHP_SCSI_BNX2FC_DEAD); - - put_online_cpus(); + cpuhp_remove_state(bnx2fc_online_state); destroy_workqueue(bnx2fc_wq); /* diff --git a/drivers/scsi/bnx2fc/bnx2fc_hwi.c b/drivers/scsi/bnx2fc/bnx2fc_hwi.c index 913c750205ce..26de61d65a4d 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_hwi.c +++ b/drivers/scsi/bnx2fc/bnx2fc_hwi.c @@ -1008,6 +1008,28 @@ static struct bnx2fc_work *bnx2fc_alloc_work(struct bnx2fc_rport *tgt, u16 wqe) return work; } +/* Pending work request completion */ +static void bnx2fc_pending_work(struct bnx2fc_rport *tgt, unsigned int wqe) +{ + unsigned int cpu = wqe % num_possible_cpus(); + struct bnx2fc_percpu_s *fps; + struct bnx2fc_work *work; + + fps = &per_cpu(bnx2fc_percpu, cpu); + spin_lock_bh(&fps->fp_work_lock); + if (fps->iothread) { + work = bnx2fc_alloc_work(tgt, wqe); + if (work) { + list_add_tail(&work->list, &fps->work_list); + wake_up_process(fps->iothread); + spin_unlock_bh(&fps->fp_work_lock); + return; + } + } + spin_unlock_bh(&fps->fp_work_lock); + bnx2fc_process_cq_compl(tgt, wqe); +} + int bnx2fc_process_new_cqes(struct bnx2fc_rport *tgt) { struct fcoe_cqe *cq; @@ -1042,28 +1064,7 @@ int bnx2fc_process_new_cqes(struct bnx2fc_rport *tgt) /* Unsolicited event notification */ bnx2fc_process_unsol_compl(tgt, wqe); } else { - /* Pending work request completion */ - struct bnx2fc_work *work = NULL; - struct bnx2fc_percpu_s *fps = NULL; - unsigned int cpu = wqe % num_possible_cpus(); - - fps = &per_cpu(bnx2fc_percpu, cpu); - spin_lock_bh(&fps->fp_work_lock); - if (unlikely(!fps->iothread)) - goto unlock; - - work = bnx2fc_alloc_work(tgt, wqe); - if (work) - list_add_tail(&work->list, - &fps->work_list); -unlock: - spin_unlock_bh(&fps->fp_work_lock); - - /* Pending work request completion */ - if (fps->iothread && work) - wake_up_process(fps->iothread); - else - bnx2fc_process_cq_compl(tgt, wqe); + bnx2fc_pending_work(tgt, wqe); num_free_sqes++; } cqe++; diff --git a/drivers/scsi/bnx2i/bnx2i_init.c b/drivers/scsi/bnx2i/bnx2i_init.c index 86afc002814c..4ebcda8d9500 100644 --- a/drivers/scsi/bnx2i/bnx2i_init.c +++ b/drivers/scsi/bnx2i/bnx2i_init.c @@ -404,12 +404,11 @@ int bnx2i_get_stats(void *handle) /** - * bnx2i_percpu_thread_create - Create a receive thread for an - * online CPU + * bnx2i_cpu_online - Create a receive thread for an online CPU * * @cpu: cpu index for the online cpu */ -static void bnx2i_percpu_thread_create(unsigned int cpu) +static int bnx2i_cpu_online(unsigned int cpu) { struct bnx2i_percpu_s *p; struct task_struct *thread; @@ -419,16 +418,17 @@ static void bnx2i_percpu_thread_create(unsigned int cpu) thread = kthread_create_on_node(bnx2i_percpu_io_thread, (void *)p, cpu_to_node(cpu), "bnx2i_thread/%d", cpu); + if (IS_ERR(thread)) + return PTR_ERR(thread); + /* bind thread to the cpu */ - if (likely(!IS_ERR(thread))) { - kthread_bind(thread, cpu); - p->iothread = thread; - wake_up_process(thread); - } + kthread_bind(thread, cpu); + p->iothread = thread; + wake_up_process(thread); + return 0; } - -static void bnx2i_percpu_thread_destroy(unsigned int cpu) +static int bnx2i_cpu_offline(unsigned int cpu) { struct bnx2i_percpu_s *p; struct task_struct *thread; @@ -451,19 +451,6 @@ static void bnx2i_percpu_thread_destroy(unsigned int cpu) spin_unlock_bh(&p->p_work_lock); if (thread) kthread_stop(thread); -} - -static int bnx2i_cpu_online(unsigned int cpu) -{ - pr_info("bnx2i: CPU %x online: Create Rx thread\n", cpu); - bnx2i_percpu_thread_create(cpu); - return 0; -} - -static int bnx2i_cpu_dead(unsigned int cpu) -{ - pr_info("CPU %x offline: Remove Rx thread\n", cpu); - bnx2i_percpu_thread_destroy(cpu); return 0; } @@ -511,27 +498,14 @@ static int __init bnx2i_mod_init(void) p->iothread = NULL; } - get_online_cpus(); - - for_each_online_cpu(cpu) - bnx2i_percpu_thread_create(cpu); - - err = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, - "scsi/bnx2i:online", - bnx2i_cpu_online, NULL); + err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "scsi/bnx2i:online", + bnx2i_cpu_online, bnx2i_cpu_offline); if (err < 0) - goto remove_threads; + goto unreg_driver; bnx2i_online_state = err; - - cpuhp_setup_state_nocalls(CPUHP_SCSI_BNX2I_DEAD, "scsi/bnx2i:dead", - NULL, bnx2i_cpu_dead); - put_online_cpus(); return 0; -remove_threads: - for_each_online_cpu(cpu) - bnx2i_percpu_thread_destroy(cpu); - put_online_cpus(); +unreg_driver: cnic_unregister_driver(CNIC_ULP_ISCSI); unreg_xport: iscsi_unregister_transport(&bnx2i_iscsi_transport); @@ -551,7 +525,6 @@ out: static void __exit bnx2i_mod_exit(void) { struct bnx2i_hba *hba; - unsigned cpu = 0; mutex_lock(&bnx2i_dev_lock); while (!list_empty(&adapter_list)) { @@ -569,14 +542,7 @@ static void __exit bnx2i_mod_exit(void) } mutex_unlock(&bnx2i_dev_lock); - get_online_cpus(); - - for_each_online_cpu(cpu) - bnx2i_percpu_thread_destroy(cpu); - - cpuhp_remove_state_nocalls(bnx2i_online_state); - cpuhp_remove_state_nocalls(CPUHP_SCSI_BNX2I_DEAD); - put_online_cpus(); + cpuhp_remove_state(bnx2i_online_state); iscsi_unregister_transport(&bnx2i_iscsi_transport); cnic_unregister_driver(CNIC_ULP_ISCSI); diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c index 4ed48ed38e79..7ee1a94c0b33 100644 --- a/drivers/scsi/lpfc/lpfc_attr.c +++ b/drivers/scsi/lpfc/lpfc_attr.c @@ -205,8 +205,10 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr, atomic_read(&tgtp->xmt_ls_rsp_error)); len += snprintf(buf+len, PAGE_SIZE-len, - "FCP: Rcv %08x Release %08x Drop %08x\n", + "FCP: Rcv %08x Defer %08x Release %08x " + "Drop %08x\n", atomic_read(&tgtp->rcv_fcp_cmd_in), + atomic_read(&tgtp->rcv_fcp_cmd_defer), atomic_read(&tgtp->xmt_fcp_release), atomic_read(&tgtp->rcv_fcp_cmd_drop)); diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c index 5cc8b0f7d885..744f3f395b64 100644 --- a/drivers/scsi/lpfc/lpfc_debugfs.c +++ b/drivers/scsi/lpfc/lpfc_debugfs.c @@ -782,8 +782,11 @@ lpfc_debugfs_nvmestat_data(struct lpfc_vport *vport, char *buf, int size) atomic_read(&tgtp->xmt_ls_rsp_error)); len += snprintf(buf + len, size - len, - "FCP: Rcv %08x Drop %08x\n", + "FCP: Rcv %08x Defer %08x Release %08x " + "Drop %08x\n", atomic_read(&tgtp->rcv_fcp_cmd_in), + atomic_read(&tgtp->rcv_fcp_cmd_defer), + atomic_read(&tgtp->xmt_fcp_release), atomic_read(&tgtp->rcv_fcp_cmd_drop)); if (atomic_read(&tgtp->rcv_fcp_cmd_in) != diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c index fbeec344c6cc..bbbd0f84160d 100644 --- a/drivers/scsi/lpfc/lpfc_nvmet.c +++ b/drivers/scsi/lpfc/lpfc_nvmet.c @@ -841,12 +841,31 @@ lpfc_nvmet_xmt_fcp_release(struct nvmet_fc_target_port *tgtport, lpfc_nvmet_ctxbuf_post(phba, ctxp->ctxbuf); } +static void +lpfc_nvmet_defer_rcv(struct nvmet_fc_target_port *tgtport, + struct nvmefc_tgt_fcp_req *rsp) +{ + struct lpfc_nvmet_tgtport *tgtp; + struct lpfc_nvmet_rcv_ctx *ctxp = + container_of(rsp, struct lpfc_nvmet_rcv_ctx, ctx.fcp_req); + struct rqb_dmabuf *nvmebuf = ctxp->rqb_buffer; + struct lpfc_hba *phba = ctxp->phba; + + lpfc_nvmeio_data(phba, "NVMET DEFERRCV: xri x%x sz %d CPU %02x\n", + ctxp->oxid, ctxp->size, smp_processor_id()); + + tgtp = phba->targetport->private; + atomic_inc(&tgtp->rcv_fcp_cmd_defer); + lpfc_rq_buf_free(phba, &nvmebuf->hbuf); /* repost */ +} + static struct nvmet_fc_target_template lpfc_tgttemplate = { .targetport_delete = lpfc_nvmet_targetport_delete, .xmt_ls_rsp = lpfc_nvmet_xmt_ls_rsp, .fcp_op = lpfc_nvmet_xmt_fcp_op, .fcp_abort = lpfc_nvmet_xmt_fcp_abort, .fcp_req_release = lpfc_nvmet_xmt_fcp_release, + .defer_rcv = lpfc_nvmet_defer_rcv, .max_hw_queues = 1, .max_sgl_segments = LPFC_NVMET_DEFAULT_SEGS, @@ -1504,6 +1523,17 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba, return; } + /* Processing of FCP command is deferred */ + if (rc == -EOVERFLOW) { + lpfc_nvmeio_data(phba, + "NVMET RCV BUSY: xri x%x sz %d from %06x\n", + oxid, size, sid); + /* defer reposting rcv buffer till .defer_rcv callback */ + ctxp->rqb_buffer = nvmebuf; + atomic_inc(&tgtp->rcv_fcp_cmd_out); + return; + } + atomic_inc(&tgtp->rcv_fcp_cmd_drop); lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR, "6159 FCP Drop IO x%x: err x%x: x%x x%x x%x\n", diff --git a/drivers/scsi/lpfc/lpfc_nvmet.h b/drivers/scsi/lpfc/lpfc_nvmet.h index e675ef17be08..48a76788b003 100644 --- a/drivers/scsi/lpfc/lpfc_nvmet.h +++ b/drivers/scsi/lpfc/lpfc_nvmet.h @@ -49,6 +49,7 @@ struct lpfc_nvmet_tgtport { atomic_t rcv_fcp_cmd_in; atomic_t rcv_fcp_cmd_out; atomic_t rcv_fcp_cmd_drop; + atomic_t rcv_fcp_cmd_defer; atomic_t xmt_fcp_release; /* Stats counters - lpfc_nvmet_xmt_fcp_op */ diff --git a/drivers/scsi/qedf/qedf.h b/drivers/scsi/qedf/qedf.h index 4d038926a455..351f06dfc5a0 100644 --- a/drivers/scsi/qedf/qedf.h +++ b/drivers/scsi/qedf/qedf.h @@ -528,7 +528,8 @@ struct fip_vlan { #define QEDF_WRITE (1 << 0) #define MAX_FIBRE_LUNS 0xffffffff -#define QEDF_MAX_NUM_CQS 8 +#define MIN_NUM_CPUS_MSIX(x) min_t(u32, x->dev_info.num_cqs, \ + num_online_cpus()) /* * PCI function probe defines diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index 7786c97e033f..1d13c9ca517d 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -2760,11 +2760,9 @@ static int qedf_set_fcoe_pf_param(struct qedf_ctx *qedf) * we allocation is the minimum off: * * Number of CPUs - * Number of MSI-X vectors - * Max number allocated in hardware (QEDF_MAX_NUM_CQS) + * Number allocated by qed for our PCI function */ - qedf->num_queues = min((unsigned int)QEDF_MAX_NUM_CQS, - num_online_cpus()); + qedf->num_queues = MIN_NUM_CPUS_MSIX(qedf); QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "Number of CQs is %d.\n", qedf->num_queues); @@ -2962,6 +2960,13 @@ static int __qedf_probe(struct pci_dev *pdev, int mode) goto err1; } + /* Learn information crucial for qedf to progress */ + rc = qed_ops->fill_dev_info(qedf->cdev, &qedf->dev_info); + if (rc) { + QEDF_ERR(&(qedf->dbg_ctx), "Failed to dev info.\n"); + goto err1; + } + /* queue allocation code should come here * order should be * slowpath_start @@ -2977,13 +2982,6 @@ static int __qedf_probe(struct pci_dev *pdev, int mode) } qed_ops->common->update_pf_params(qedf->cdev, &qedf->pf_params); - /* Learn information crucial for qedf to progress */ - rc = qed_ops->fill_dev_info(qedf->cdev, &qedf->dev_info); - if (rc) { - QEDF_ERR(&(qedf->dbg_ctx), "Failed to dev info.\n"); - goto err1; - } - /* Record BDQ producer doorbell addresses */ qedf->bdq_primary_prod = qedf->dev_info.primary_dbq_rq_addr; qedf->bdq_secondary_prod = qedf->dev_info.secondary_bdq_rq_addr; diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index b20da0d27ad7..3f82ea1b72dc 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -500,7 +500,6 @@ static int tcm_qla2xxx_handle_cmd(scsi_qla_host_t *vha, struct qla_tgt_cmd *cmd, static void tcm_qla2xxx_handle_data_work(struct work_struct *work) { struct qla_tgt_cmd *cmd = container_of(work, struct qla_tgt_cmd, work); - unsigned long flags; /* * Ensure that the complete FCP WRITE payload has been received. @@ -508,17 +507,6 @@ static void tcm_qla2xxx_handle_data_work(struct work_struct *work) */ cmd->cmd_in_wq = 0; - spin_lock_irqsave(&cmd->cmd_lock, flags); - cmd->data_work = 1; - if (cmd->aborted) { - cmd->data_work_free = 1; - spin_unlock_irqrestore(&cmd->cmd_lock, flags); - - tcm_qla2xxx_free_cmd(cmd); - return; - } - spin_unlock_irqrestore(&cmd->cmd_lock, flags); - cmd->qpair->tgt_counters.qla_core_ret_ctio++; if (!cmd->write_data_transferred) { /* @@ -765,31 +753,13 @@ static void tcm_qla2xxx_queue_tm_rsp(struct se_cmd *se_cmd) qlt_xmit_tm_rsp(mcmd); } -#define DATA_WORK_NOT_FREE(_cmd) (_cmd->data_work && !_cmd->data_work_free) static void tcm_qla2xxx_aborted_task(struct se_cmd *se_cmd) { struct qla_tgt_cmd *cmd = container_of(se_cmd, struct qla_tgt_cmd, se_cmd); - unsigned long flags; if (qlt_abort_cmd(cmd)) return; - - spin_lock_irqsave(&cmd->cmd_lock, flags); - if ((cmd->state == QLA_TGT_STATE_NEW)|| - ((cmd->state == QLA_TGT_STATE_DATA_IN) && - DATA_WORK_NOT_FREE(cmd))) { - cmd->data_work_free = 1; - spin_unlock_irqrestore(&cmd->cmd_lock, flags); - /* - * cmd has not reached fw, Use this trigger to free it. - */ - tcm_qla2xxx_free_cmd(cmd); - return; - } - spin_unlock_irqrestore(&cmd->cmd_lock, flags); - return; - } static void tcm_qla2xxx_clear_sess_lookup(struct tcm_qla2xxx_lport *, diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 4fe606b000b4..d7ff71e0c85c 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -751,35 +751,6 @@ sg_new_write(Sg_fd *sfp, struct file *file, const char __user *buf, return count; } -static bool sg_is_valid_dxfer(sg_io_hdr_t *hp) -{ - switch (hp->dxfer_direction) { - case SG_DXFER_NONE: - if (hp->dxferp || hp->dxfer_len > 0) - return false; - return true; - case SG_DXFER_FROM_DEV: - /* - * for SG_DXFER_FROM_DEV we always set dxfer_len to > 0. dxferp - * can either be NULL or != NULL so there's no point in checking - * it either. So just return true. - */ - return true; - case SG_DXFER_TO_DEV: - case SG_DXFER_TO_FROM_DEV: - if (!hp->dxferp || hp->dxfer_len == 0) - return false; - return true; - case SG_DXFER_UNKNOWN: - if ((!hp->dxferp && hp->dxfer_len) || - (hp->dxferp && hp->dxfer_len == 0)) - return false; - return true; - default: - return false; - } -} - static int sg_common_write(Sg_fd * sfp, Sg_request * srp, unsigned char *cmnd, int timeout, int blocking) @@ -800,7 +771,7 @@ sg_common_write(Sg_fd * sfp, Sg_request * srp, "sg_common_write: scsi opcode=0x%02x, cmd_size=%d\n", (int) cmnd[0], (int) hp->cmd_len)); - if (!sg_is_valid_dxfer(hp)) + if (hp->dxfer_len >= SZ_256M) return -EINVAL; k = sg_start_req(srp, cmnd); diff --git a/drivers/staging/comedi/comedi_fops.c b/drivers/staging/comedi/comedi_fops.c index ca11be21f64b..34ca7823255d 100644 --- a/drivers/staging/comedi/comedi_fops.c +++ b/drivers/staging/comedi/comedi_fops.c @@ -2396,6 +2396,7 @@ static ssize_t comedi_write(struct file *file, const char __user *buf, continue; } + set_current_state(TASK_RUNNING); wp = async->buf_write_ptr; n1 = min(n, async->prealloc_bufsz - wp); n2 = n - n1; @@ -2528,6 +2529,8 @@ static ssize_t comedi_read(struct file *file, char __user *buf, size_t nbytes, } continue; } + + set_current_state(TASK_RUNNING); rp = async->buf_read_ptr; n1 = min(n, async->prealloc_bufsz - rp); n2 = n - n1; diff --git a/drivers/staging/iio/resolver/ad2s1210.c b/drivers/staging/iio/resolver/ad2s1210.c index a6a8393d6664..3e00df74b18c 100644 --- a/drivers/staging/iio/resolver/ad2s1210.c +++ b/drivers/staging/iio/resolver/ad2s1210.c @@ -472,7 +472,7 @@ static int ad2s1210_read_raw(struct iio_dev *indio_dev, long m) { struct ad2s1210_state *st = iio_priv(indio_dev); - bool negative; + u16 negative; int ret = 0; u16 pos; s16 vel; diff --git a/drivers/target/iscsi/cxgbit/cxgbit_cm.c b/drivers/target/iscsi/cxgbit/cxgbit_cm.c index e583dd8a418b..d4fa41be80f9 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_cm.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_cm.c @@ -1510,11 +1510,13 @@ cxgbit_pass_open_rpl(struct cxgbit_device *cdev, struct sk_buff *skb) if (!cnp) { pr_info("%s stid %d lookup failure\n", __func__, stid); - return; + goto rel_skb; } cxgbit_wake_up(&cnp->com.wr_wait, __func__, rpl->status); cxgbit_put_cnp(cnp); +rel_skb: + __kfree_skb(skb); } static void @@ -1530,11 +1532,13 @@ cxgbit_close_listsrv_rpl(struct cxgbit_device *cdev, struct sk_buff *skb) if (!cnp) { pr_info("%s stid %d lookup failure\n", __func__, stid); - return; + goto rel_skb; } cxgbit_wake_up(&cnp->com.wr_wait, __func__, rpl->status); cxgbit_put_cnp(cnp); +rel_skb: + __kfree_skb(skb); } static void @@ -1819,12 +1823,16 @@ static void cxgbit_set_tcb_rpl(struct cxgbit_device *cdev, struct sk_buff *skb) struct tid_info *t = lldi->tids; csk = lookup_tid(t, tid); - if (unlikely(!csk)) + if (unlikely(!csk)) { pr_err("can't find connection for tid %u.\n", tid); - else + goto rel_skb; + } else { cxgbit_wake_up(&csk->com.wr_wait, __func__, rpl->status); + } cxgbit_put_csk(csk); +rel_skb: + __kfree_skb(skb); } static void cxgbit_rx_data(struct cxgbit_device *cdev, struct sk_buff *skb) diff --git a/drivers/target/iscsi/cxgbit/cxgbit_target.c b/drivers/target/iscsi/cxgbit/cxgbit_target.c index dda13f1af38e..514986b57c2d 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_target.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_target.c @@ -827,7 +827,7 @@ cxgbit_put_login_tx(struct iscsi_conn *conn, struct iscsi_login *login, static void cxgbit_skb_copy_to_sg(struct sk_buff *skb, struct scatterlist *sg, - unsigned int nents) + unsigned int nents, u32 skip) { struct skb_seq_state st; const u8 *buf; @@ -846,7 +846,7 @@ cxgbit_skb_copy_to_sg(struct sk_buff *skb, struct scatterlist *sg, } consumed += sg_pcopy_from_buffer(sg, nents, (void *)buf, - buf_len, consumed); + buf_len, skip + consumed); } } @@ -912,7 +912,7 @@ cxgbit_handle_immediate_data(struct iscsi_cmd *cmd, struct iscsi_scsi_req *hdr, struct scatterlist *sg = &cmd->se_cmd.t_data_sg[0]; u32 sg_nents = max(1UL, DIV_ROUND_UP(pdu_cb->dlen, PAGE_SIZE)); - cxgbit_skb_copy_to_sg(csk->skb, sg, sg_nents); + cxgbit_skb_copy_to_sg(csk->skb, sg, sg_nents, 0); } cmd->write_data_done += pdu_cb->dlen; @@ -1069,11 +1069,13 @@ static int cxgbit_handle_iscsi_dataout(struct cxgbit_sock *csk) cmd->se_cmd.data_length); if (!(pdu_cb->flags & PDUCBF_RX_DATA_DDPD)) { + u32 skip = data_offset % PAGE_SIZE; + sg_off = data_offset / PAGE_SIZE; sg_start = &cmd->se_cmd.t_data_sg[sg_off]; - sg_nents = max(1UL, DIV_ROUND_UP(data_len, PAGE_SIZE)); + sg_nents = max(1UL, DIV_ROUND_UP(skip + data_len, PAGE_SIZE)); - cxgbit_skb_copy_to_sg(csk->skb, sg_start, sg_nents); + cxgbit_skb_copy_to_sg(csk->skb, sg_start, sg_nents, skip); } check_payload: diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 74e4975dd1b1..5001261f5d69 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -418,6 +418,7 @@ int iscsit_reset_np_thread( return 0; } np->np_thread_state = ISCSI_NP_THREAD_RESET; + atomic_inc(&np->np_reset_count); if (np->np_thread) { spin_unlock_bh(&np->np_thread_lock); @@ -2167,6 +2168,7 @@ iscsit_setup_text_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, cmd->cmd_sn = be32_to_cpu(hdr->cmdsn); cmd->exp_stat_sn = be32_to_cpu(hdr->exp_statsn); cmd->data_direction = DMA_NONE; + kfree(cmd->text_in_ptr); cmd->text_in_ptr = NULL; return 0; @@ -3487,9 +3489,9 @@ iscsit_build_text_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn, return text_length; if (completed) { - hdr->flags |= ISCSI_FLAG_CMD_FINAL; + hdr->flags = ISCSI_FLAG_CMD_FINAL; } else { - hdr->flags |= ISCSI_FLAG_TEXT_CONTINUE; + hdr->flags = ISCSI_FLAG_TEXT_CONTINUE; cmd->read_data_done += text_length; if (cmd->targ_xfer_tag == 0xFFFFFFFF) cmd->targ_xfer_tag = session_get_next_ttt(conn->sess); diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index e9bdc8b86e7d..dc13afbd4c88 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -1243,9 +1243,11 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) flush_signals(current); spin_lock_bh(&np->np_thread_lock); - if (np->np_thread_state == ISCSI_NP_THREAD_RESET) { + if (atomic_dec_if_positive(&np->np_reset_count) >= 0) { np->np_thread_state = ISCSI_NP_THREAD_ACTIVE; + spin_unlock_bh(&np->np_thread_lock); complete(&np->np_restart_comp); + return 1; } else if (np->np_thread_state == ISCSI_NP_THREAD_SHUTDOWN) { spin_unlock_bh(&np->np_thread_lock); goto exit; @@ -1278,7 +1280,8 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) goto exit; } else if (rc < 0) { spin_lock_bh(&np->np_thread_lock); - if (np->np_thread_state == ISCSI_NP_THREAD_RESET) { + if (atomic_dec_if_positive(&np->np_reset_count) >= 0) { + np->np_thread_state = ISCSI_NP_THREAD_ACTIVE; spin_unlock_bh(&np->np_thread_lock); complete(&np->np_restart_comp); iscsit_put_transport(conn->conn_transport); diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c index 36913734c6bc..02e8a5d86658 100644 --- a/drivers/target/target_core_tpg.c +++ b/drivers/target/target_core_tpg.c @@ -364,7 +364,7 @@ void core_tpg_del_initiator_node_acl(struct se_node_acl *acl) mutex_lock(&tpg->acl_node_mutex); if (acl->dynamic_node_acl) acl->dynamic_node_acl = 0; - list_del(&acl->acl_list); + list_del_init(&acl->acl_list); mutex_unlock(&tpg->acl_node_mutex); target_shutdown_sessions(acl); @@ -548,7 +548,7 @@ int core_tpg_deregister(struct se_portal_group *se_tpg) * in transport_deregister_session(). */ list_for_each_entry_safe(nacl, nacl_tmp, &node_list, acl_list) { - list_del(&nacl->acl_list); + list_del_init(&nacl->acl_list); core_tpg_wait_for_nacl_pr_ref(nacl); core_free_device_list_for_node(nacl, se_tpg); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 97fed9a298bd..836d552b0385 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -466,7 +466,7 @@ static void target_complete_nacl(struct kref *kref) } mutex_lock(&se_tpg->acl_node_mutex); - list_del(&nacl->acl_list); + list_del_init(&nacl->acl_list); mutex_unlock(&se_tpg->acl_node_mutex); core_tpg_wait_for_nacl_pr_ref(nacl); @@ -538,7 +538,7 @@ void transport_free_session(struct se_session *se_sess) spin_unlock_irqrestore(&se_nacl->nacl_sess_lock, flags); if (se_nacl->dynamic_stop) - list_del(&se_nacl->acl_list); + list_del_init(&se_nacl->acl_list); } mutex_unlock(&se_tpg->acl_node_mutex); diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 80ee130f8253..942d094269fb 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -563,8 +563,6 @@ static int scatter_data_area(struct tcmu_dev *udev, block_remaining); to_offset = get_block_offset_user(udev, dbi, block_remaining); - offset = DATA_BLOCK_SIZE - block_remaining; - to += offset; if (*iov_cnt != 0 && to_offset == iov_tail(*iov)) { @@ -575,8 +573,10 @@ static int scatter_data_area(struct tcmu_dev *udev, (*iov)->iov_len = copy_bytes; } if (copy_data) { - memcpy(to, from + sg->length - sg_remaining, - copy_bytes); + offset = DATA_BLOCK_SIZE - block_remaining; + memcpy(to + offset, + from + sg->length - sg_remaining, + copy_bytes); tcmu_flush_dcache_range(to, copy_bytes); } sg_remaining -= copy_bytes; @@ -637,9 +637,8 @@ static void gather_data_area(struct tcmu_dev *udev, struct tcmu_cmd *cmd, copy_bytes = min_t(size_t, sg_remaining, block_remaining); offset = DATA_BLOCK_SIZE - block_remaining; - from += offset; tcmu_flush_dcache_range(from, copy_bytes); - memcpy(to + sg->length - sg_remaining, from, + memcpy(to + sg->length - sg_remaining, from + offset, copy_bytes); sg_remaining -= copy_bytes; @@ -1433,6 +1432,8 @@ static int tcmu_update_uio_info(struct tcmu_dev *udev) if (udev->dev_config[0]) snprintf(str + used, size - used, "/%s", udev->dev_config); + /* If the old string exists, free it */ + kfree(info->name); info->name = str; return 0; diff --git a/drivers/thunderbolt/eeprom.c b/drivers/thunderbolt/eeprom.c index 308b6e17c88a..fe2f00ceafc5 100644 --- a/drivers/thunderbolt/eeprom.c +++ b/drivers/thunderbolt/eeprom.c @@ -333,6 +333,15 @@ static int tb_drom_parse_entry_port(struct tb_switch *sw, int res; enum tb_port_type type; + /* + * Some DROMs list more ports than the controller actually has + * so we skip those but allow the parser to continue. + */ + if (header->index > sw->config.max_port_number) { + dev_info_once(&sw->dev, "ignoring unnecessary extra entries in DROM\n"); + return 0; + } + port = &sw->ports[header->index]; port->disabled = header->port_disabled; if (port->disabled) diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index b5def356af63..1aab3010fbfa 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -1043,13 +1043,24 @@ int serial8250_register_8250_port(struct uart_8250_port *up) if (up->dl_write) uart->dl_write = up->dl_write; - if (serial8250_isa_config != NULL) - serial8250_isa_config(0, &uart->port, - &uart->capabilities); + if (uart->port.type != PORT_8250_CIR) { + if (serial8250_isa_config != NULL) + serial8250_isa_config(0, &uart->port, + &uart->capabilities); + + ret = uart_add_one_port(&serial8250_reg, + &uart->port); + if (ret == 0) + ret = uart->port.line; + } else { + dev_info(uart->port.dev, + "skipping CIR port at 0x%lx / 0x%llx, IRQ %d\n", + uart->port.iobase, + (unsigned long long)uart->port.mapbase, + uart->port.irq); - ret = uart_add_one_port(&serial8250_reg, &uart->port); - if (ret == 0) - ret = uart->port.line; + ret = 0; + } } mutex_unlock(&serial_mutex); diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index 8a857bb34fbb..1888d168a41c 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -142,15 +142,7 @@ static struct vendor_data vendor_sbsa = { .fixed_options = true, }; -/* - * Erratum 44 for QDF2432v1 and QDF2400v1 SoCs describes the BUSY bit as - * occasionally getting stuck as 1. To avoid the potential for a hang, check - * TXFE == 0 instead of BUSY == 1. This may not be suitable for all UART - * implementations, so only do so if an affected platform is detected in - * parse_spcr(). - */ -static bool qdf2400_e44_present = false; - +#ifdef CONFIG_ACPI_SPCR_TABLE static struct vendor_data vendor_qdt_qdf2400_e44 = { .reg_offset = pl011_std_offsets, .fr_busy = UART011_FR_TXFE, @@ -165,6 +157,7 @@ static struct vendor_data vendor_qdt_qdf2400_e44 = { .always_enabled = true, .fixed_options = true, }; +#endif static u16 pl011_st_offsets[REG_ARRAY_SIZE] = { [REG_DR] = UART01x_DR, @@ -2375,12 +2368,14 @@ static int __init pl011_console_match(struct console *co, char *name, int idx, resource_size_t addr; int i; - if (strcmp(name, "qdf2400_e44") == 0) { - pr_info_once("UART: Working around QDF2400 SoC erratum 44"); - qdf2400_e44_present = true; - } else if (strcmp(name, "pl011") != 0) { + /* + * Systems affected by the Qualcomm Technologies QDF2400 E44 erratum + * have a distinct console name, so make sure we check for that. + * The actual implementation of the erratum occurs in the probe + * function. + */ + if ((strcmp(name, "qdf2400_e44") != 0) && (strcmp(name, "pl011") != 0)) return -ENODEV; - } if (uart_parse_earlycon(options, &iotype, &addr, &options)) return -ENODEV; @@ -2734,11 +2729,17 @@ static int sbsa_uart_probe(struct platform_device *pdev) } uap->port.irq = ret; - uap->reg_offset = vendor_sbsa.reg_offset; - uap->vendor = qdf2400_e44_present ? - &vendor_qdt_qdf2400_e44 : &vendor_sbsa; +#ifdef CONFIG_ACPI_SPCR_TABLE + if (qdf2400_e44_present) { + dev_info(&pdev->dev, "working around QDF2400 SoC erratum 44\n"); + uap->vendor = &vendor_qdt_qdf2400_e44; + } else +#endif + uap->vendor = &vendor_sbsa; + + uap->reg_offset = uap->vendor->reg_offset; uap->fifosize = 32; - uap->port.iotype = vendor_sbsa.access_32b ? UPIO_MEM32 : UPIO_MEM; + uap->port.iotype = uap->vendor->access_32b ? UPIO_MEM32 : UPIO_MEM; uap->port.ops = &sbsa_uart_pops; uap->fixed_baud = baudrate; diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index ab1bb3b538ac..7f277b092b5b 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -1888,7 +1888,7 @@ void usb_hcd_flush_endpoint(struct usb_device *udev, /* No more submits can occur */ spin_lock_irq(&hcd_urb_list_lock); rescan: - list_for_each_entry (urb, &ep->urb_list, urb_list) { + list_for_each_entry_reverse(urb, &ep->urb_list, urb_list) { int is_in; if (urb->unlinked) @@ -2485,6 +2485,8 @@ void usb_hc_died (struct usb_hcd *hcd) } if (usb_hcd_is_primary_hcd(hcd) && hcd->shared_hcd) { hcd = hcd->shared_hcd; + clear_bit(HCD_FLAG_RH_RUNNING, &hcd->flags); + set_bit(HCD_FLAG_DEAD, &hcd->flags); if (hcd->rh_registered) { clear_bit(HCD_FLAG_POLL_RH, &hcd->flags); diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 6e6797d145dd..822f8c50e423 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -4725,7 +4725,8 @@ hub_power_remaining(struct usb_hub *hub) static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, u16 portchange) { - int status, i; + int status = -ENODEV; + int i; unsigned unit_load; struct usb_device *hdev = hub->hdev; struct usb_hcd *hcd = bus_to_hcd(hdev->bus); @@ -4929,9 +4930,10 @@ loop: done: hub_port_disable(hub, port1, 1); - if (hcd->driver->relinquish_port && !hub->hdev->parent) - hcd->driver->relinquish_port(hcd, port1); - + if (hcd->driver->relinquish_port && !hub->hdev->parent) { + if (status != -ENOTCONN && status != -ENODEV) + hcd->driver->relinquish_port(hcd, port1); + } } /* Handle physical or logical connection change events. diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 3116edfcdc18..574da2b4529c 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -150,6 +150,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* appletouch */ { USB_DEVICE(0x05ac, 0x021a), .driver_info = USB_QUIRK_RESET_RESUME }, + /* Genesys Logic hub, internally used by Moshi USB to Ethernet Adapter */ + { USB_DEVICE(0x05e3, 0x0616), .driver_info = USB_QUIRK_NO_LPM }, + /* Avision AV600U */ { USB_DEVICE(0x0638, 0x0a13), .driver_info = USB_QUIRK_STRING_FETCH_255 }, @@ -249,6 +252,7 @@ static const struct usb_device_id usb_amd_resume_quirk_list[] = { { USB_DEVICE(0x093a, 0x2500), .driver_info = USB_QUIRK_RESET_RESUME }, { USB_DEVICE(0x093a, 0x2510), .driver_info = USB_QUIRK_RESET_RESUME }, { USB_DEVICE(0x093a, 0x2521), .driver_info = USB_QUIRK_RESET_RESUME }, + { USB_DEVICE(0x03f0, 0x2b4a), .driver_info = USB_QUIRK_RESET_RESUME }, /* Logitech Optical Mouse M90/M100 */ { USB_DEVICE(0x046d, 0xc05a), .driver_info = USB_QUIRK_RESET_RESUME }, diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 6b299c7b7656..f064f1549333 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -896,9 +896,40 @@ static void __dwc3_prepare_one_trb(struct dwc3_ep *dep, struct dwc3_trb *trb, if (!node) { trb->ctrl = DWC3_TRBCTL_ISOCHRONOUS_FIRST; + /* + * USB Specification 2.0 Section 5.9.2 states that: "If + * there is only a single transaction in the microframe, + * only a DATA0 data packet PID is used. If there are + * two transactions per microframe, DATA1 is used for + * the first transaction data packet and DATA0 is used + * for the second transaction data packet. If there are + * three transactions per microframe, DATA2 is used for + * the first transaction data packet, DATA1 is used for + * the second, and DATA0 is used for the third." + * + * IOW, we should satisfy the following cases: + * + * 1) length <= maxpacket + * - DATA0 + * + * 2) maxpacket < length <= (2 * maxpacket) + * - DATA1, DATA0 + * + * 3) (2 * maxpacket) < length <= (3 * maxpacket) + * - DATA2, DATA1, DATA0 + */ if (speed == USB_SPEED_HIGH) { struct usb_ep *ep = &dep->endpoint; - trb->size |= DWC3_TRB_SIZE_PCM1(ep->mult - 1); + unsigned int mult = ep->mult - 1; + unsigned int maxp = usb_endpoint_maxp(ep->desc); + + if (length <= (2 * maxp)) + mult--; + + if (length <= maxp) + mult--; + + trb->size |= DWC3_TRB_SIZE_PCM1(mult); } } else { trb->ctrl = DWC3_TRBCTL_ISOCHRONOUS; diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index 62dc9c7798e7..e1de8fe599a3 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -838,21 +838,32 @@ static struct renesas_usb3_request *usb3_get_request(struct renesas_usb3_ep return usb3_req; } -static void usb3_request_done(struct renesas_usb3_ep *usb3_ep, - struct renesas_usb3_request *usb3_req, int status) +static void __usb3_request_done(struct renesas_usb3_ep *usb3_ep, + struct renesas_usb3_request *usb3_req, + int status) { struct renesas_usb3 *usb3 = usb3_ep_to_usb3(usb3_ep); - unsigned long flags; dev_dbg(usb3_to_dev(usb3), "giveback: ep%2d, %u, %u, %d\n", usb3_ep->num, usb3_req->req.length, usb3_req->req.actual, status); usb3_req->req.status = status; - spin_lock_irqsave(&usb3->lock, flags); usb3_ep->started = false; list_del_init(&usb3_req->queue); - spin_unlock_irqrestore(&usb3->lock, flags); + spin_unlock(&usb3->lock); usb_gadget_giveback_request(&usb3_ep->ep, &usb3_req->req); + spin_lock(&usb3->lock); +} + +static void usb3_request_done(struct renesas_usb3_ep *usb3_ep, + struct renesas_usb3_request *usb3_req, int status) +{ + struct renesas_usb3 *usb3 = usb3_ep_to_usb3(usb3_ep); + unsigned long flags; + + spin_lock_irqsave(&usb3->lock, flags); + __usb3_request_done(usb3_ep, usb3_req, status); + spin_unlock_irqrestore(&usb3->lock, flags); } static void usb3_irq_epc_pipe0_status_end(struct renesas_usb3 *usb3) diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index c8989c62a262..c8f38649f749 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -98,6 +98,7 @@ enum amd_chipset_gen { AMD_CHIPSET_HUDSON2, AMD_CHIPSET_BOLTON, AMD_CHIPSET_YANGTZE, + AMD_CHIPSET_TAISHAN, AMD_CHIPSET_UNKNOWN, }; @@ -141,6 +142,11 @@ static int amd_chipset_sb_type_init(struct amd_chipset_info *pinfo) pinfo->sb_type.gen = AMD_CHIPSET_SB700; else if (rev >= 0x40 && rev <= 0x4f) pinfo->sb_type.gen = AMD_CHIPSET_SB800; + } + pinfo->smbus_dev = pci_get_device(PCI_VENDOR_ID_AMD, + 0x145c, NULL); + if (pinfo->smbus_dev) { + pinfo->sb_type.gen = AMD_CHIPSET_TAISHAN; } else { pinfo->smbus_dev = pci_get_device(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_HUDSON2_SMBUS, NULL); @@ -260,11 +266,12 @@ int usb_hcd_amd_remote_wakeup_quirk(struct pci_dev *pdev) { /* Make sure amd chipset type has already been initialized */ usb_amd_find_chipset_info(); - if (amd_chipset.sb_type.gen != AMD_CHIPSET_YANGTZE) - return 0; - - dev_dbg(&pdev->dev, "QUIRK: Enable AMD remote wakeup fix\n"); - return 1; + if (amd_chipset.sb_type.gen == AMD_CHIPSET_YANGTZE || + amd_chipset.sb_type.gen == AMD_CHIPSET_TAISHAN) { + dev_dbg(&pdev->dev, "QUIRK: Enable AMD remote wakeup fix\n"); + return 1; + } + return 0; } EXPORT_SYMBOL_GPL(usb_hcd_amd_remote_wakeup_quirk); @@ -1150,3 +1157,23 @@ static void quirk_usb_early_handoff(struct pci_dev *pdev) } DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_ANY_ID, PCI_ANY_ID, PCI_CLASS_SERIAL_USB, 8, quirk_usb_early_handoff); + +bool usb_xhci_needs_pci_reset(struct pci_dev *pdev) +{ + /* + * Our dear uPD72020{1,2} friend only partially resets when + * asked to via the XHCI interface, and may end up doing DMA + * at the wrong addresses, as it keeps the top 32bit of some + * addresses from its previous programming under obscure + * circumstances. + * Give it a good wack at probe time. Unfortunately, this + * needs to happen before we've had a chance to discover any + * quirk, or the system will be in a rather bad state. + */ + if (pdev->vendor == PCI_VENDOR_ID_RENESAS && + (pdev->device == 0x0014 || pdev->device == 0x0015)) + return true; + + return false; +} +EXPORT_SYMBOL_GPL(usb_xhci_needs_pci_reset); diff --git a/drivers/usb/host/pci-quirks.h b/drivers/usb/host/pci-quirks.h index 655994480198..5582cbafecd4 100644 --- a/drivers/usb/host/pci-quirks.h +++ b/drivers/usb/host/pci-quirks.h @@ -15,6 +15,7 @@ void usb_asmedia_modifyflowcontrol(struct pci_dev *pdev); void usb_enable_intel_xhci_ports(struct pci_dev *xhci_pdev); void usb_disable_xhci_ports(struct pci_dev *xhci_pdev); void sb800_prefetch(struct device *dev, int on); +bool usb_xhci_needs_pci_reset(struct pci_dev *pdev); #else struct pci_dev; static inline void usb_amd_quirk_pll_disable(void) {} diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 5b0fa553c8bc..8071c8fdd15e 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -284,6 +284,13 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) driver = (struct hc_driver *)id->driver_data; + /* For some HW implementation, a XHCI reset is just not enough... */ + if (usb_xhci_needs_pci_reset(dev)) { + dev_info(&dev->dev, "Resetting\n"); + if (pci_reset_function_locked(dev)) + dev_warn(&dev->dev, "Reset failed"); + } + /* Prevent runtime suspending between USB-2 and USB-3 initialization */ pm_runtime_get_noresume(&dev->dev); diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index 76decb8011eb..3344ffd5bb13 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -139,6 +139,7 @@ static void musb_h_tx_flush_fifo(struct musb_hw_ep *ep) "Could not flush host TX%d fifo: csr: %04x\n", ep->epnum, csr)) return; + mdelay(1); } } diff --git a/drivers/usb/phy/phy-msm-usb.c b/drivers/usb/phy/phy-msm-usb.c index 8fb86a5f458e..3d0dd2f97415 100644 --- a/drivers/usb/phy/phy-msm-usb.c +++ b/drivers/usb/phy/phy-msm-usb.c @@ -197,6 +197,7 @@ struct msm_otg { struct regulator *v3p3; struct regulator *v1p8; struct regulator *vddcx; + struct regulator_bulk_data supplies[3]; struct reset_control *phy_rst; struct reset_control *link_rst; @@ -1731,7 +1732,6 @@ static int msm_otg_reboot_notify(struct notifier_block *this, static int msm_otg_probe(struct platform_device *pdev) { - struct regulator_bulk_data regs[3]; int ret = 0; struct device_node *np = pdev->dev.of_node; struct msm_otg_platform_data *pdata; @@ -1817,17 +1817,18 @@ static int msm_otg_probe(struct platform_device *pdev) return motg->irq; } - regs[0].supply = "vddcx"; - regs[1].supply = "v3p3"; - regs[2].supply = "v1p8"; + motg->supplies[0].supply = "vddcx"; + motg->supplies[1].supply = "v3p3"; + motg->supplies[2].supply = "v1p8"; - ret = devm_regulator_bulk_get(motg->phy.dev, ARRAY_SIZE(regs), regs); + ret = devm_regulator_bulk_get(motg->phy.dev, ARRAY_SIZE(motg->supplies), + motg->supplies); if (ret) return ret; - motg->vddcx = regs[0].consumer; - motg->v3p3 = regs[1].consumer; - motg->v1p8 = regs[2].consumer; + motg->vddcx = motg->supplies[0].consumer; + motg->v3p3 = motg->supplies[1].consumer; + motg->v1p8 = motg->supplies[2].consumer; clk_set_rate(motg->clk, 60000000); diff --git a/drivers/usb/renesas_usbhs/mod_gadget.c b/drivers/usb/renesas_usbhs/mod_gadget.c index 93fba9033b00..2c8161bcf5b5 100644 --- a/drivers/usb/renesas_usbhs/mod_gadget.c +++ b/drivers/usb/renesas_usbhs/mod_gadget.c @@ -639,14 +639,11 @@ static int usbhsg_ep_disable(struct usb_ep *ep) struct usbhsg_uep *uep = usbhsg_ep_to_uep(ep); struct usbhs_pipe *pipe; unsigned long flags; - int ret = 0; spin_lock_irqsave(&uep->lock, flags); pipe = usbhsg_uep_to_pipe(uep); - if (!pipe) { - ret = -EINVAL; + if (!pipe) goto out; - } usbhsg_pipe_disable(uep); usbhs_pipe_free(pipe); diff --git a/drivers/usb/renesas_usbhs/rcar3.c b/drivers/usb/renesas_usbhs/rcar3.c index d544b331c9f2..02b67abfc2a1 100644 --- a/drivers/usb/renesas_usbhs/rcar3.c +++ b/drivers/usb/renesas_usbhs/rcar3.c @@ -20,9 +20,13 @@ /* Low Power Status register (LPSTS) */ #define LPSTS_SUSPM 0x4000 -/* USB General control register 2 (UGCTRL2), bit[31:6] should be 0 */ +/* + * USB General control register 2 (UGCTRL2) + * Remarks: bit[31:11] and bit[9:6] should be 0 + */ #define UGCTRL2_RESERVED_3 0x00000001 /* bit[3:0] should be B'0001 */ #define UGCTRL2_USB0SEL_OTG 0x00000030 +#define UGCTRL2_VBUSSEL 0x00000400 static void usbhs_write32(struct usbhs_priv *priv, u32 reg, u32 data) { @@ -34,7 +38,8 @@ static int usbhs_rcar3_power_ctrl(struct platform_device *pdev, { struct usbhs_priv *priv = usbhs_pdev_to_priv(pdev); - usbhs_write32(priv, UGCTRL2, UGCTRL2_RESERVED_3 | UGCTRL2_USB0SEL_OTG); + usbhs_write32(priv, UGCTRL2, UGCTRL2_RESERVED_3 | UGCTRL2_USB0SEL_OTG | + UGCTRL2_VBUSSEL); if (enable) { usbhs_bset(priv, LPSTS, LPSTS_SUSPM, LPSTS_SUSPM); diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index f64e914a8985..2d945c9f975c 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -142,6 +142,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x8998) }, /* KCF Technologies PRN */ { USB_DEVICE(0x10C4, 0x8A2A) }, /* HubZ dual ZigBee and Z-Wave dongle */ { USB_DEVICE(0x10C4, 0x8A5E) }, /* CEL EM3588 ZigBee USB Stick Long Range */ + { USB_DEVICE(0x10C4, 0x8B34) }, /* Qivicon ZigBee USB Radio Stick */ { USB_DEVICE(0x10C4, 0xEA60) }, /* Silicon Labs factory default */ { USB_DEVICE(0x10C4, 0xEA61) }, /* Silicon Labs factory default */ { USB_DEVICE(0x10C4, 0xEA70) }, /* Silicon Labs factory default */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index ebe51f11105d..fe123153b1a5 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -2025,6 +2025,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7d04, 0xff) }, /* D-Link DWM-158 */ { USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7e19, 0xff), /* D-Link DWM-221 B1 */ .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, + { USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7e35, 0xff), /* D-Link DWM-222 */ + .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */ { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */ { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x7e11, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/A3 */ diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c index c9ebefd8f35f..a585b477415d 100644 --- a/drivers/usb/serial/pl2303.c +++ b/drivers/usb/serial/pl2303.c @@ -52,6 +52,8 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID_RSAQ5) }, { USB_DEVICE(ATEN_VENDOR_ID, ATEN_PRODUCT_ID), .driver_info = PL2303_QUIRK_ENDPOINT_HACK }, + { USB_DEVICE(ATEN_VENDOR_ID, ATEN_PRODUCT_UC485), + .driver_info = PL2303_QUIRK_ENDPOINT_HACK }, { USB_DEVICE(ATEN_VENDOR_ID, ATEN_PRODUCT_ID2) }, { USB_DEVICE(ATEN_VENDOR_ID2, ATEN_PRODUCT_ID) }, { USB_DEVICE(ELCOM_VENDOR_ID, ELCOM_PRODUCT_ID) }, diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h index 09d9be88209e..3b5a15d1dc0d 100644 --- a/drivers/usb/serial/pl2303.h +++ b/drivers/usb/serial/pl2303.h @@ -27,6 +27,7 @@ #define ATEN_VENDOR_ID 0x0557 #define ATEN_VENDOR_ID2 0x0547 #define ATEN_PRODUCT_ID 0x2008 +#define ATEN_PRODUCT_UC485 0x2021 #define ATEN_PRODUCT_ID2 0x2118 #define IODATA_VENDOR_ID 0x04bb diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h index cbea9f329e71..cde115359793 100644 --- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -124,9 +124,9 @@ UNUSUAL_DEV(0x0bc2, 0xab2a, 0x0000, 0x9999, /* Reported-by: Benjamin Tissoires <benjamin.tissoires@redhat.com> */ UNUSUAL_DEV(0x13fd, 0x3940, 0x0000, 0x9999, "Initio Corporation", - "", + "INIC-3069", USB_SC_DEVICE, USB_PR_DEVICE, NULL, - US_FL_NO_ATA_1X), + US_FL_NO_ATA_1X | US_FL_IGNORE_RESIDUE), /* Reported-by: Tom Arild Naess <tanaess@gmail.com> */ UNUSUAL_DEV(0x152d, 0x0539, 0x0000, 0x9999, diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c index 06615934fed1..0dceb9fa3a06 100644 --- a/drivers/usb/storage/usb.c +++ b/drivers/usb/storage/usb.c @@ -315,6 +315,7 @@ static int usb_stor_control_thread(void * __us) { struct us_data *us = (struct us_data *)__us; struct Scsi_Host *host = us_to_host(us); + struct scsi_cmnd *srb; for (;;) { usb_stor_dbg(us, "*** thread sleeping\n"); @@ -330,6 +331,7 @@ static int usb_stor_control_thread(void * __us) scsi_lock(host); /* When we are called with no command pending, we're done */ + srb = us->srb; if (us->srb == NULL) { scsi_unlock(host); mutex_unlock(&us->dev_mutex); @@ -398,14 +400,11 @@ static int usb_stor_control_thread(void * __us) /* lock access to the state */ scsi_lock(host); - /* indicate that the command is done */ - if (us->srb->result != DID_ABORT << 16) { - usb_stor_dbg(us, "scsi cmd done, result=0x%x\n", - us->srb->result); - us->srb->scsi_done(us->srb); - } else { + /* was the command aborted? */ + if (us->srb->result == DID_ABORT << 16) { SkipForAbort: usb_stor_dbg(us, "scsi command aborted\n"); + srb = NULL; /* Don't call srb->scsi_done() */ } /* @@ -429,6 +428,13 @@ SkipForAbort: /* unlock the device pointers */ mutex_unlock(&us->dev_mutex); + + /* now that the locks are released, notify the SCSI core */ + if (srb) { + usb_stor_dbg(us, "scsi cmd done, result=0x%x\n", + srb->result); + srb->scsi_done(srb); + } } /* for (;;) */ /* Wait until we are told to stop */ diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c index ff01bed7112f..1e784adb89b1 100644 --- a/drivers/video/fbdev/efifb.c +++ b/drivers/video/fbdev/efifb.c @@ -17,6 +17,7 @@ #include <asm/efi.h> static bool request_mem_succeeded = false; +static bool nowc = false; static struct fb_var_screeninfo efifb_defined = { .activate = FB_ACTIVATE_NOW, @@ -99,6 +100,8 @@ static int efifb_setup(char *options) screen_info.lfb_height = simple_strtoul(this_opt+7, NULL, 0); else if (!strncmp(this_opt, "width:", 6)) screen_info.lfb_width = simple_strtoul(this_opt+6, NULL, 0); + else if (!strcmp(this_opt, "nowc")) + nowc = true; } } @@ -255,7 +258,10 @@ static int efifb_probe(struct platform_device *dev) info->apertures->ranges[0].base = efifb_fix.smem_start; info->apertures->ranges[0].size = size_remap; - info->screen_base = ioremap_wc(efifb_fix.smem_start, efifb_fix.smem_len); + if (nowc) + info->screen_base = ioremap(efifb_fix.smem_start, efifb_fix.smem_len); + else + info->screen_base = ioremap_wc(efifb_fix.smem_start, efifb_fix.smem_len); if (!info->screen_base) { pr_err("efifb: abort, cannot ioremap video memory 0x%x @ 0x%lx\n", efifb_fix.smem_len, efifb_fix.smem_start); diff --git a/drivers/video/fbdev/imxfb.c b/drivers/video/fbdev/imxfb.c index c166e0725be5..ba82f97fb42b 100644 --- a/drivers/video/fbdev/imxfb.c +++ b/drivers/video/fbdev/imxfb.c @@ -1073,20 +1073,16 @@ static int imxfb_remove(struct platform_device *pdev) imxfb_disable_controller(fbi); unregister_framebuffer(info); - + fb_dealloc_cmap(&info->cmap); pdata = dev_get_platdata(&pdev->dev); if (pdata && pdata->exit) pdata->exit(fbi->pdev); - - fb_dealloc_cmap(&info->cmap); - kfree(info->pseudo_palette); - framebuffer_release(info); - dma_free_wc(&pdev->dev, fbi->map_size, info->screen_base, fbi->map_dma); - iounmap(fbi->regs); release_mem_region(res->start, resource_size(res)); + kfree(info->pseudo_palette); + framebuffer_release(info); return 0; } diff --git a/drivers/video/fbdev/omap2/omapfb/dss/core.c b/drivers/video/fbdev/omap2/omapfb/dss/core.c index eecf695c16f4..09e5bb013d28 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/core.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/core.c @@ -193,7 +193,6 @@ static struct notifier_block omap_dss_pm_notif_block = { static int __init omap_dss_probe(struct platform_device *pdev) { - struct omap_dss_board_info *pdata = pdev->dev.platform_data; int r; core.pdev = pdev; diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index bae1f5d36c26..2d43118077e4 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -574,7 +574,7 @@ static void shutdown_pirq(struct irq_data *data) static void enable_pirq(struct irq_data *data) { - startup_pirq(data); + enable_dynirq(data); } static void disable_pirq(struct irq_data *data) diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index e46080214955..3e59590c7254 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -857,6 +857,8 @@ static int xenwatch_thread(void *unused) struct list_head *ent; struct xs_watch_event *event; + xenwatch_pid = current->pid; + for (;;) { wait_event_interruptible(watch_events_waitq, !list_empty(&watch_events)); @@ -925,7 +927,6 @@ int xs_init(void) task = kthread_run(xenwatch_thread, NULL, "xenwatch"); if (IS_ERR(task)) return PTR_ERR(task); - xenwatch_pid = task->pid; /* shutdown watches for kexec boot */ xs_reset_watches(); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 3ee4fdc3da9e..ab60051be6e5 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -46,7 +46,7 @@ struct fuse_file *fuse_file_alloc(struct fuse_conn *fc) { struct fuse_file *ff; - ff = kmalloc(sizeof(struct fuse_file), GFP_KERNEL); + ff = kzalloc(sizeof(struct fuse_file), GFP_KERNEL); if (unlikely(!ff)) return NULL; @@ -609,7 +609,7 @@ static void fuse_aio_complete_req(struct fuse_conn *fc, struct fuse_req *req) struct fuse_io_priv *io = req->io; ssize_t pos = -1; - fuse_release_user_pages(req, !io->write); + fuse_release_user_pages(req, io->should_dirty); if (io->write) { if (req->misc.write.in.size != req->misc.write.out.size) @@ -1316,7 +1316,6 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, loff_t *ppos, int flags) { int write = flags & FUSE_DIO_WRITE; - bool should_dirty = !write && iter_is_iovec(iter); int cuse = flags & FUSE_DIO_CUSE; struct file *file = io->file; struct inode *inode = file->f_mapping->host; @@ -1346,6 +1345,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, inode_unlock(inode); } + io->should_dirty = !write && iter_is_iovec(iter); while (count) { size_t nres; fl_owner_t owner = current->files; @@ -1360,7 +1360,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, nres = fuse_send_read(req, io, pos, nbytes, owner); if (!io->async) - fuse_release_user_pages(req, should_dirty); + fuse_release_user_pages(req, io->should_dirty); if (req->out.h.error) { err = req->out.h.error; break; @@ -1669,6 +1669,7 @@ err_nofile: err_free: fuse_request_free(req); err: + mapping_set_error(page->mapping, error); end_page_writeback(page); return error; } diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 1bd7ffdad593..bd4d2a3e1ec1 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -249,6 +249,7 @@ struct fuse_io_priv { size_t size; __u64 offset; bool write; + bool should_dirty; int err; struct kiocb *iocb; struct file *file; diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 69d02cf8cf37..5f93cfacb3d1 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -121,6 +121,7 @@ config PNFS_FILE_LAYOUT config PNFS_BLOCK tristate depends on NFS_V4_1 && BLK_DEV_DM + depends on 64BIT || LBDAF default NFS_V4 config PNFS_FLEXFILE_LAYOUT diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index 6df7a0cf5660..f32c58bbe556 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -32,6 +32,7 @@ void nfs4_ff_layout_free_deviceid(struct nfs4_ff_layout_ds *mirror_ds) { nfs4_print_deviceid(&mirror_ds->id_node.deviceid); nfs4_pnfs_ds_put(mirror_ds->ds); + kfree(mirror_ds->ds_versions); kfree_rcu(mirror_ds, id_node.rcu); } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ffd2e712595d..d90132642340 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2553,9 +2553,8 @@ static int nfs41_check_open_stateid(struct nfs4_state *state) clear_bit(NFS_O_RDWR_STATE, &state->flags); clear_bit(NFS_OPEN_STATE, &state->flags); stateid->type = NFS4_INVALID_STATEID_TYPE; - } - if (status != NFS_OK) return status; + } if (nfs_open_stateid_recover_openmode(state)) return -NFS4ERR_OPENMODE; return NFS_OK; diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 8a428498d6b2..509a61668d90 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -106,13 +106,13 @@ static int meminfo_proc_show(struct seq_file *m, void *v) global_node_page_state(NR_FILE_MAPPED)); show_val_kb(m, "Shmem: ", i.sharedram); show_val_kb(m, "Slab: ", - global_page_state(NR_SLAB_RECLAIMABLE) + - global_page_state(NR_SLAB_UNRECLAIMABLE)); + global_node_page_state(NR_SLAB_RECLAIMABLE) + + global_node_page_state(NR_SLAB_UNRECLAIMABLE)); show_val_kb(m, "SReclaimable: ", - global_page_state(NR_SLAB_RECLAIMABLE)); + global_node_page_state(NR_SLAB_RECLAIMABLE)); show_val_kb(m, "SUnreclaim: ", - global_page_state(NR_SLAB_UNRECLAIMABLE)); + global_node_page_state(NR_SLAB_UNRECLAIMABLE)); seq_printf(m, "KernelStack: %8lu kB\n", global_page_state(NR_KERNEL_STACK_KB)); show_val_kb(m, "PageTables: ", diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index b836fd61ed87..fe8f3265e877 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -16,9 +16,10 @@ #include <linux/mmu_notifier.h> #include <linux/page_idle.h> #include <linux/shmem_fs.h> +#include <linux/uaccess.h> #include <asm/elf.h> -#include <linux/uaccess.h> +#include <asm/tlb.h> #include <asm/tlbflush.h> #include "internal.h" @@ -1008,6 +1009,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, struct mm_struct *mm; struct vm_area_struct *vma; enum clear_refs_types type; + struct mmu_gather tlb; int itype; int rv; @@ -1054,6 +1056,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, } down_read(&mm->mmap_sem); + tlb_gather_mmu(&tlb, mm, 0, -1); if (type == CLEAR_REFS_SOFT_DIRTY) { for (vma = mm->mmap; vma; vma = vma->vm_next) { if (!(vma->vm_flags & VM_SOFTDIRTY)) @@ -1075,7 +1078,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, walk_page_range(0, mm->highest_vm_end, &clear_refs_walk); if (type == CLEAR_REFS_SOFT_DIRTY) mmu_notifier_invalidate_range_end(mm, 0, -1); - flush_tlb_mm(mm); + tlb_finish_mmu(&tlb, 0, -1); up_read(&mm->mmap_sem); out_mm: mmput(mm); diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 06ea26b8c996..b0d5897bc4e6 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1600,7 +1600,7 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, uffdio_copy.len); mmput(ctx->mm); } else { - return -ENOSPC; + return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_copy->copy))) return -EFAULT; @@ -1647,7 +1647,7 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, uffdio_zeropage.range.len); mmput(ctx->mm); } else { - return -ENOSPC; + return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage))) return -EFAULT; diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index ceef77c0416a..ff48f0096810 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -874,7 +874,6 @@ xfs_ialloc( case S_IFREG: case S_IFDIR: if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY)) { - uint64_t di_flags2 = 0; uint di_flags = 0; if (S_ISDIR(mode)) { @@ -911,20 +910,23 @@ xfs_ialloc( di_flags |= XFS_DIFLAG_NODEFRAG; if (pip->i_d.di_flags & XFS_DIFLAG_FILESTREAM) di_flags |= XFS_DIFLAG_FILESTREAM; - if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX) - di_flags2 |= XFS_DIFLAG2_DAX; ip->i_d.di_flags |= di_flags; - ip->i_d.di_flags2 |= di_flags2; } if (pip && (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY) && pip->i_d.di_version == 3 && ip->i_d.di_version == 3) { + uint64_t di_flags2 = 0; + if (pip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) { - ip->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE; + di_flags2 |= XFS_DIFLAG2_COWEXTSIZE; ip->i_d.di_cowextsize = pip->i_d.di_cowextsize; } + if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX) + di_flags2 |= XFS_DIFLAG2_DAX; + + ip->i_d.di_flags2 |= di_flags2; } /* FALLTHROUGH */ case S_IFLNK: diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index fbe72b134bef..43aa42a3a5d3 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -539,6 +539,7 @@ xlog_discard_endio( INIT_WORK(&ctx->discard_endio_work, xlog_discard_endio_work); queue_work(xfs_discard_wq, &ctx->discard_endio_work); + bio_put(bio); } static void diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 8afa4335e5b2..faddde44de8c 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -112,10 +112,11 @@ struct mmu_gather { #define HAVE_GENERIC_MMU_GATHER -void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end); +void arch_tlb_gather_mmu(struct mmu_gather *tlb, + struct mm_struct *mm, unsigned long start, unsigned long end); void tlb_flush_mmu(struct mmu_gather *tlb); -void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, - unsigned long end); +void arch_tlb_finish_mmu(struct mmu_gather *tlb, + unsigned long start, unsigned long end, bool force); extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size); diff --git a/include/linux/acpi.h b/include/linux/acpi.h index c749eef1daa1..27b4b6615263 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1209,6 +1209,7 @@ static inline bool acpi_has_watchdog(void) { return false; } #endif #ifdef CONFIG_ACPI_SPCR_TABLE +extern bool qdf2400_e44_present; int parse_spcr(bool earlycon); #else static inline int parse_spcr(bool earlycon) { return 0; } diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index b56573bf440d..82b30e638430 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -39,8 +39,6 @@ enum cpuhp_state { CPUHP_PCI_XGENE_DEAD, CPUHP_IOMMU_INTEL_DEAD, CPUHP_LUSTRE_CFS_DEAD, - CPUHP_SCSI_BNX2FC_DEAD, - CPUHP_SCSI_BNX2I_DEAD, CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, diff --git a/include/linux/device.h b/include/linux/device.h index 723cd54b94da..beabdbc08420 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -843,7 +843,7 @@ struct dev_links_info { * hibernation, system resume and during runtime PM transitions * along with subsystem-level and driver-level callbacks. * @pins: For device pin management. - * See Documentation/pinctrl.txt for details. + * See Documentation/driver-api/pinctl.rst for details. * @msi_list: Hosts MSI descriptors * @msi_domain: The generic MSI domain this device is using. * @numa_node: NUMA node this device is close to. diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 00ca5b86a753..d501d3956f13 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -689,7 +689,8 @@ i2c_unlock_adapter(struct i2c_adapter *adapter) #define I2C_CLASS_HWMON (1<<0) /* lm_sensors, ... */ #define I2C_CLASS_DDC (1<<3) /* DDC bus on graphics adapters */ #define I2C_CLASS_SPD (1<<7) /* Memory modules */ -#define I2C_CLASS_DEPRECATED (1<<8) /* Warn users that adapter will stop using classes */ +/* Warn users that the adapter doesn't support classes anymore */ +#define I2C_CLASS_DEPRECATED (1<<8) /* Internal numbers to terminate lists */ #define I2C_CLIENT_END 0xfffeU diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 497f2b3a5a62..97f1b465d04f 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -105,6 +105,11 @@ struct st_sensor_fullscale { struct st_sensor_fullscale_avl fs_avl[ST_SENSORS_FULLSCALE_AVL_MAX]; }; +struct st_sensor_sim { + u8 addr; + u8 value; +}; + /** * struct st_sensor_bdu - ST sensor device block data update * @addr: address of the register. @@ -197,6 +202,7 @@ struct st_sensor_transfer_function { * @bdu: Block data update register. * @das: Data Alignment Selection register. * @drdy_irq: Data ready register of the sensor. + * @sim: SPI serial interface mode register of the sensor. * @multi_read_bit: Use or not particular bit for [I2C/SPI] multi-read. * @bootime: samples to discard when sensor passing from power-down to power-up. */ @@ -213,6 +219,7 @@ struct st_sensor_settings { struct st_sensor_bdu bdu; struct st_sensor_das das; struct st_sensor_data_ready_irq drdy_irq; + struct st_sensor_sim sim; bool multi_read_bit; unsigned int bootime; }; diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index aad5d81dfb44..b54517c05e9a 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -620,6 +620,7 @@ struct mlx4_caps { u32 dmfs_high_rate_qpn_base; u32 dmfs_high_rate_qpn_range; u32 vf_caps; + bool wol_port[MLX4_MAX_PORTS + 1]; struct mlx4_rate_limit_caps rl_caps; }; diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 6f41270d80c0..f378dc0e7eaf 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -212,7 +212,6 @@ struct mlx5_wqe_ctrl_seg { #define MLX5_WQE_CTRL_OPCODE_MASK 0xff #define MLX5_WQE_CTRL_WQE_INDEX_MASK 0x00ffff00 #define MLX5_WQE_CTRL_WQE_INDEX_SHIFT 8 -#define MLX5_WQE_AV_EXT 0x80000000 enum { MLX5_ETH_WQE_L3_INNER_CSUM = 1 << 4, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7f384bb62d8e..3cadee0a3508 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -487,14 +487,12 @@ struct mm_struct { /* numa_scan_seq prevents two threads setting pte_numa */ int numa_scan_seq; #endif -#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION) /* * An operation with batched TLB flushing is going on. Anything that * can move process memory needs to flush the TLB when moving a * PROT_NONE or PROT_NUMA mapped page. */ - bool tlb_flush_pending; -#endif + atomic_t tlb_flush_pending; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* See flush_tlb_batched_pending() */ bool tlb_flush_batched; @@ -522,46 +520,60 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) return mm->cpu_vm_mask_var; } -#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION) +struct mmu_gather; +extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, + unsigned long start, unsigned long end); +extern void tlb_finish_mmu(struct mmu_gather *tlb, + unsigned long start, unsigned long end); + /* * Memory barriers to keep this state in sync are graciously provided by * the page table locks, outside of which no page table modifications happen. - * The barriers below prevent the compiler from re-ordering the instructions - * around the memory barriers that are already present in the code. + * The barriers are used to ensure the order between tlb_flush_pending updates, + * which happen while the lock is not taken, and the PTE updates, which happen + * while the lock is taken, are serialized. */ static inline bool mm_tlb_flush_pending(struct mm_struct *mm) { - barrier(); - return mm->tlb_flush_pending; + return atomic_read(&mm->tlb_flush_pending) > 0; +} + +/* + * Returns true if there are two above TLB batching threads in parallel. + */ +static inline bool mm_tlb_flush_nested(struct mm_struct *mm) +{ + return atomic_read(&mm->tlb_flush_pending) > 1; +} + +static inline void init_tlb_flush_pending(struct mm_struct *mm) +{ + atomic_set(&mm->tlb_flush_pending, 0); } -static inline void set_tlb_flush_pending(struct mm_struct *mm) + +static inline void inc_tlb_flush_pending(struct mm_struct *mm) { - mm->tlb_flush_pending = true; + atomic_inc(&mm->tlb_flush_pending); /* - * Guarantee that the tlb_flush_pending store does not leak into the + * Guarantee that the tlb_flush_pending increase does not leak into the * critical section updating the page tables */ smp_mb__before_spinlock(); } + /* Clearing is done after a TLB flush, which also provides a barrier. */ -static inline void clear_tlb_flush_pending(struct mm_struct *mm) -{ - barrier(); - mm->tlb_flush_pending = false; -} -#else -static inline bool mm_tlb_flush_pending(struct mm_struct *mm) -{ - return false; -} -static inline void set_tlb_flush_pending(struct mm_struct *mm) -{ -} -static inline void clear_tlb_flush_pending(struct mm_struct *mm) +static inline void dec_tlb_flush_pending(struct mm_struct *mm) { + /* + * Guarantee that the tlb_flush_pending does not not leak into the + * critical section, since we must order the PTE change and changes to + * the pending TLB flush indication. We could have relied on TLB flush + * as a memory barrier, but this behavior is not clearly documented. + */ + smp_mb__before_atomic(); + atomic_dec(&mm->tlb_flush_pending); } -#endif struct vm_fault; diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 892148c448cc..5216d2eb2289 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -681,10 +681,10 @@ struct nand_buffers { * @tWW_min: WP# transition to WE# low */ struct nand_sdr_timings { - u32 tBERS_max; + u64 tBERS_max; u32 tCCS_min; - u32 tPROG_max; - u32 tR_max; + u64 tPROG_max; + u64 tR_max; u32 tALH_min; u32 tADL_min; u32 tALS_min; diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 6c8c5d8041b7..2591878c1d48 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -346,6 +346,11 @@ struct nvme_fc_remote_port { * indicating an FC transport Aborted status. * Entrypoint is Mandatory. * + * @defer_rcv: Called by the transport to signal the LLLD that it has + * begun processing of a previously received NVME CMD IU. The LLDD + * is now free to re-use the rcv buffer associated with the + * nvmefc_tgt_fcp_req. + * * @max_hw_queues: indicates the maximum number of hw queues the LLDD * supports for cpu affinitization. * Value is Mandatory. Must be at least 1. @@ -846,6 +851,8 @@ struct nvmet_fc_target_template { struct nvmefc_tgt_fcp_req *fcpreq); void (*fcp_req_release)(struct nvmet_fc_target_port *tgtport, struct nvmefc_tgt_fcp_req *fcpreq); + void (*defer_rcv)(struct nvmet_fc_target_port *tgtport, + struct nvmefc_tgt_fcp_req *fcpreq); u32 max_hw_queues; u16 max_sgl_segments; diff --git a/include/linux/pci.h b/include/linux/pci.h index 4869e66dd659..a75c13673852 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1067,6 +1067,7 @@ void pcie_flr(struct pci_dev *dev); int __pci_reset_function(struct pci_dev *dev); int __pci_reset_function_locked(struct pci_dev *dev); int pci_reset_function(struct pci_dev *dev); +int pci_reset_function_locked(struct pci_dev *dev); int pci_try_reset_function(struct pci_dev *dev); int pci_probe_reset_slot(struct pci_slot *slot); int pci_reset_slot(struct pci_slot *slot); diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index 231d3075815a..e91d1b6a260d 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -81,8 +81,8 @@ * it. * @PIN_CONFIG_OUTPUT: this will configure the pin as an output and drive a * value on the line. Use argument 1 to indicate high level, argument 0 to - * indicate low level. (Please see Documentation/pinctrl.txt, section - * "GPIO mode pitfalls" for a discussion around this parameter.) + * indicate low level. (Please see Documentation/driver-api/pinctl.rst, + * section "GPIO mode pitfalls" for a discussion around this parameter.) * @PIN_CONFIG_POWER_SOURCE: if the pin can select between different power * supplies, the argument to this parameter (on a custom format) tells * the driver which alternative power source to use. diff --git a/include/linux/platform_data/st_sensors_pdata.h b/include/linux/platform_data/st_sensors_pdata.h index 79b0e4cdb814..f8274b0c6888 100644 --- a/include/linux/platform_data/st_sensors_pdata.h +++ b/include/linux/platform_data/st_sensors_pdata.h @@ -17,10 +17,12 @@ * Available only for accelerometer and pressure sensors. * Accelerometer DRDY on LSM330 available only on pin 1 (see datasheet). * @open_drain: set the interrupt line to be open drain if possible. + * @spi_3wire: enable spi-3wire mode. */ struct st_sensors_platform_data { u8 drdy_int_pin; bool open_drain; + bool spi_3wire; }; #endif /* ST_SENSORS_PDATA_H */ diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index a026bfd089db..51349d124ee5 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -99,6 +99,11 @@ struct system_device_crosststamp; * parameter func: the desired function to use. * parameter chan: the function channel index to use. * + * @do_work: Request driver to perform auxiliary (periodic) operations + * Driver should return delay of the next auxiliary work scheduling + * time (>=0) or negative value in case further scheduling + * is not required. + * * Drivers should embed their ptp_clock_info within a private * structure, obtaining a reference to it using container_of(). * @@ -126,6 +131,7 @@ struct ptp_clock_info { struct ptp_clock_request *request, int on); int (*verify)(struct ptp_clock_info *ptp, unsigned int pin, enum ptp_pin_function func, unsigned int chan); + long (*do_aux_work)(struct ptp_clock_info *ptp); }; struct ptp_clock; @@ -211,6 +217,16 @@ extern int ptp_clock_index(struct ptp_clock *ptp); int ptp_find_pin(struct ptp_clock *ptp, enum ptp_pin_function func, unsigned int chan); +/** + * ptp_schedule_worker() - schedule ptp auxiliary work + * + * @ptp: The clock obtained from ptp_clock_register(). + * @delay: number of jiffies to wait before queuing + * See kthread_queue_delayed_work() for more info. + */ + +int ptp_schedule_worker(struct ptp_clock *ptp, unsigned long delay); + #else static inline struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, struct device *parent) @@ -225,6 +241,10 @@ static inline int ptp_clock_index(struct ptp_clock *ptp) static inline int ptp_find_pin(struct ptp_clock *ptp, enum ptp_pin_function func, unsigned int chan) { return -1; } +static inline int ptp_schedule_worker(struct ptp_clock *ptp, + unsigned long delay) +{ return -EOPNOTSUPP; } + #endif #endif diff --git a/include/linux/sync_file.h b/include/linux/sync_file.h index 5726107963b2..0ad87c434ae6 100644 --- a/include/linux/sync_file.h +++ b/include/linux/sync_file.h @@ -43,12 +43,13 @@ struct sync_file { #endif wait_queue_head_t wq; + unsigned long flags; struct dma_fence *fence; struct dma_fence_cb cb; }; -#define POLL_ENABLED DMA_FENCE_FLAG_USER_BITS +#define POLL_ENABLED 0 struct sync_file *sync_file_create(struct dma_fence *fence); struct dma_fence *sync_file_get_fence(int fd); diff --git a/include/net/tcp.h b/include/net/tcp.h index 70483296157f..ada65e767b28 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1916,6 +1916,16 @@ extern void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq, u64 xmit_time); extern void tcp_rack_reo_timeout(struct sock *sk); +/* At how many usecs into the future should the RTO fire? */ +static inline s64 tcp_rto_delta_us(const struct sock *sk) +{ + const struct sk_buff *skb = tcp_write_queue_head(sk); + u32 rto = inet_csk(sk)->icsk_rto; + u64 rto_time_stamp_us = skb->skb_mstamp + jiffies_to_usecs(rto); + + return rto_time_stamp_us - tcp_sk(sk)->tcp_mstamp; +} + /* * Save and compile IPv4 options, return a pointer to it */ diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index 0ca1fb08805b..fb87d32f5e51 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -786,6 +786,7 @@ struct iscsi_np { int np_sock_type; enum np_thread_state_table np_thread_state; bool enabled; + atomic_t np_reset_count; enum iscsi_timer_flags_table np_login_timer_flags; u32 np_exports; enum np_flags_table np_flags; diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h index 26c54f6d595d..ad4eb2863e70 100644 --- a/include/uapi/drm/msm_drm.h +++ b/include/uapi/drm/msm_drm.h @@ -171,7 +171,7 @@ struct drm_msm_gem_submit_cmd { __u32 size; /* in, cmdstream size */ __u32 pad; __u32 nr_relocs; /* in, number of submit_reloc's */ - __u64 __user relocs; /* in, ptr to array of submit_reloc's */ + __u64 relocs; /* in, ptr to array of submit_reloc's */ }; /* Each buffer referenced elsewhere in the cmdstream submit (ie. the @@ -215,8 +215,8 @@ struct drm_msm_gem_submit { __u32 fence; /* out */ __u32 nr_bos; /* in, number of submit_bo's */ __u32 nr_cmds; /* in, number of submit_cmd's */ - __u64 __user bos; /* in, ptr to array of submit_bo's */ - __u64 __user cmds; /* in, ptr to array of submit_cmd's */ + __u64 bos; /* in, ptr to array of submit_bo's */ + __u64 cmds; /* in, ptr to array of submit_cmd's */ __s32 fence_fd; /* in/out fence fd (see MSM_SUBMIT_FENCE_FD_IN/OUT) */ }; diff --git a/kernel/fork.c b/kernel/fork.c index 17921b0390b4..e075b7780421 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -807,7 +807,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm_init_aio(mm); mm_init_owner(mm, p); mmu_notifier_mm_init(mm); - clear_tlb_flush_pending(mm); + init_tlb_flush_pending(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS mm->pmd_huge_pte = NULL; #endif diff --git a/kernel/futex.c b/kernel/futex.c index 16dbe4c93895..f50b434756c1 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -670,13 +670,14 @@ again: * this reference was taken by ihold under the page lock * pinning the inode in place so i_lock was unnecessary. The * only way for this check to fail is if the inode was - * truncated in parallel so warn for now if this happens. + * truncated in parallel which is almost certainly an + * application bug. In such a case, just retry. * * We are not calling into get_futex_key_refs() in file-backed * cases, therefore a successful atomic_inc return below will * guarantee that get_futex_key() will still imply smp_mb(); (B). */ - if (WARN_ON_ONCE(!atomic_inc_not_zero(&inode->i_count))) { + if (!atomic_inc_not_zero(&inode->i_count)) { rcu_read_unlock(); put_page(page); diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 222317721c5a..0972a8e09d08 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1650,7 +1650,7 @@ static unsigned long minimum_image_size(unsigned long saveable) { unsigned long size; - size = global_page_state(NR_SLAB_RECLAIMABLE) + size = global_node_page_state(NR_SLAB_RECLAIMABLE) + global_node_page_state(NR_ACTIVE_ANON) + global_node_page_state(NR_INACTIVE_ANON) + global_node_page_state(NR_ACTIVE_FILE) diff --git a/lib/fault-inject.c b/lib/fault-inject.c index 7d315fdb9f13..cf7b129b0b2b 100644 --- a/lib/fault-inject.c +++ b/lib/fault-inject.c @@ -110,10 +110,12 @@ bool should_fail(struct fault_attr *attr, ssize_t size) if (in_task()) { unsigned int fail_nth = READ_ONCE(current->fail_nth); - if (fail_nth && !WRITE_ONCE(current->fail_nth, fail_nth - 1)) - goto fail; + if (fail_nth) { + if (!WRITE_ONCE(current->fail_nth, fail_nth - 1)) + goto fail; - return false; + return false; + } } /* No need to check any other properties if the probability is 0 */ diff --git a/lib/test_kmod.c b/lib/test_kmod.c index 6c1d678bcf8b..ff9148969b92 100644 --- a/lib/test_kmod.c +++ b/lib/test_kmod.c @@ -485,7 +485,7 @@ static ssize_t config_show(struct device *dev, config->test_driver); else len += snprintf(buf+len, PAGE_SIZE - len, - "driver:\tEMTPY\n"); + "driver:\tEMPTY\n"); if (config->test_fs) len += snprintf(buf+len, PAGE_SIZE - len, @@ -493,7 +493,7 @@ static ssize_t config_show(struct device *dev, config->test_fs); else len += snprintf(buf+len, PAGE_SIZE - len, - "fs:\tEMTPY\n"); + "fs:\tEMPTY\n"); mutex_unlock(&test_dev->config_mutex); @@ -746,11 +746,11 @@ static int trigger_config_run_type(struct kmod_test_device *test_dev, strlen(test_str)); break; case TEST_KMOD_FS_TYPE: - break; kfree_const(config->test_fs); config->test_driver = NULL; copied = config_copy_test_fs(config, test_str, strlen(test_str)); + break; default: mutex_unlock(&test_dev->config_mutex); return -EINVAL; @@ -880,10 +880,10 @@ static int test_dev_config_update_uint_sync(struct kmod_test_device *test_dev, int (*test_sync)(struct kmod_test_device *test_dev)) { int ret; - long new; + unsigned long new; unsigned int old_val; - ret = kstrtol(buf, 10, &new); + ret = kstrtoul(buf, 10, &new); if (ret) return ret; @@ -918,9 +918,9 @@ static int test_dev_config_update_uint_range(struct kmod_test_device *test_dev, unsigned int max) { int ret; - long new; + unsigned long new; - ret = kstrtol(buf, 10, &new); + ret = kstrtoul(buf, 10, &new); if (ret) return ret; @@ -1146,7 +1146,7 @@ static struct kmod_test_device *register_test_dev_kmod(void) struct kmod_test_device *test_dev = NULL; int ret; - mutex_unlock(®_dev_mutex); + mutex_lock(®_dev_mutex); /* int should suffice for number of devices, test for wrap */ if (unlikely(num_test_devs + 1) < 0) { diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c index 9075aa54e955..b06d9fe23a28 100644 --- a/mm/balloon_compaction.c +++ b/mm/balloon_compaction.c @@ -24,7 +24,7 @@ struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info) { unsigned long flags; struct page *page = alloc_page(balloon_mapping_gfp_mask() | - __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_ZERO); + __GFP_NOMEMALLOC | __GFP_NORETRY); if (!page) return NULL; diff --git a/mm/debug.c b/mm/debug.c index db1cd26d8752..5715448ab0b5 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -124,9 +124,7 @@ void dump_mm(const struct mm_struct *mm) #ifdef CONFIG_NUMA_BALANCING "numa_next_scan %lu numa_scan_offset %lu numa_scan_seq %d\n" #endif -#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION) "tlb_flush_pending %d\n" -#endif "def_flags: %#lx(%pGv)\n", mm, mm->mmap, mm->vmacache_seqnum, mm->task_size, @@ -158,9 +156,7 @@ void dump_mm(const struct mm_struct *mm) #ifdef CONFIG_NUMA_BALANCING mm->numa_next_scan, mm->numa_scan_offset, mm->numa_scan_seq, #endif -#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION) - mm->tlb_flush_pending, -#endif + atomic_read(&mm->tlb_flush_pending), mm->def_flags, &mm->def_flags ); } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 86975dec0ba1..216114f6ef0b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1496,6 +1496,13 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) } /* + * The page_table_lock above provides a memory barrier + * with change_protection_range. + */ + if (mm_tlb_flush_pending(vma->vm_mm)) + flush_tlb_range(vma, haddr, haddr + HPAGE_PMD_SIZE); + + /* * Migrate the THP to the requested node, returns with page unlocked * and access rights restored. */ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index a1a0ac0ad6f6..31e207cb399b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4062,9 +4062,9 @@ out: return ret; out_release_unlock: spin_unlock(ptl); -out_release_nounlock: if (vm_shared) unlock_page(page); +out_release_nounlock: put_page(page); goto out; } @@ -1038,7 +1038,8 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, goto out_unlock; if (pte_write(*pvmw.pte) || pte_dirty(*pvmw.pte) || - (pte_protnone(*pvmw.pte) && pte_savedwrite(*pvmw.pte))) { + (pte_protnone(*pvmw.pte) && pte_savedwrite(*pvmw.pte)) || + mm_tlb_flush_pending(mm)) { pte_t entry; swapped = PageSwapCache(page); diff --git a/mm/memory.c b/mm/memory.c index f65beaad319b..e158f7ac6730 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -215,12 +215,8 @@ static bool tlb_next_batch(struct mmu_gather *tlb) return true; } -/* tlb_gather_mmu - * Called to initialize an (on-stack) mmu_gather structure for page-table - * tear-down from @mm. The @fullmm argument is used when @mm is without - * users and we're going to destroy the full address space (exit/execve). - */ -void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end) +void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, + unsigned long start, unsigned long end) { tlb->mm = mm; @@ -275,10 +271,14 @@ void tlb_flush_mmu(struct mmu_gather *tlb) * Called at the end of the shootdown operation to free up any resources * that were required. */ -void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) +void arch_tlb_finish_mmu(struct mmu_gather *tlb, + unsigned long start, unsigned long end, bool force) { struct mmu_gather_batch *batch, *next; + if (force) + __tlb_adjust_range(tlb, start, end - start); + tlb_flush_mmu(tlb); /* keep the page table cache within bounds */ @@ -398,6 +398,34 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table) #endif /* CONFIG_HAVE_RCU_TABLE_FREE */ +/* tlb_gather_mmu + * Called to initialize an (on-stack) mmu_gather structure for page-table + * tear-down from @mm. The @fullmm argument is used when @mm is without + * users and we're going to destroy the full address space (exit/execve). + */ +void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + arch_tlb_gather_mmu(tlb, mm, start, end); + inc_tlb_flush_pending(tlb->mm); +} + +void tlb_finish_mmu(struct mmu_gather *tlb, + unsigned long start, unsigned long end) +{ + /* + * If there are parallel threads are doing PTE changes on same range + * under non-exclusive lock(e.g., mmap_sem read-side) but defer TLB + * flush by batching, a thread has stable TLB entry can fail to flush + * the TLB by observing pte_none|!pte_dirty, for example so flush TLB + * forcefully if we detect parallel PTE batching threads. + */ + bool force = mm_tlb_flush_nested(tlb->mm); + + arch_tlb_finish_mmu(tlb, start, end, force); + dec_tlb_flush_pending(tlb->mm); +} + /* * Note: this doesn't free the actual pages themselves. That * has been handled earlier when unmapping all the memory regions. diff --git a/mm/migrate.c b/mm/migrate.c index 627671551873..d68a41da6abb 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1937,12 +1937,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, put_page(new_page); goto out_fail; } - /* - * We are not sure a pending tlb flush here is for a huge page - * mapping or not. Hence use the tlb range variant - */ - if (mm_tlb_flush_pending(mm)) - flush_tlb_range(vma, mmun_start, mmun_end); /* Prepare a page as a migration target */ __SetPageLocked(new_page); diff --git a/mm/mprotect.c b/mm/mprotect.c index 4180ad8cc9c5..bd0f409922cb 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -244,7 +244,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma, BUG_ON(addr >= end); pgd = pgd_offset(mm, addr); flush_cache_range(vma, addr, end); - set_tlb_flush_pending(mm); + inc_tlb_flush_pending(mm); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) @@ -256,7 +256,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma, /* Only flush the TLB if we actually modified any entries: */ if (pages) flush_tlb_range(vma, start, end); - clear_tlb_flush_pending(mm); + dec_tlb_flush_pending(mm); return pages; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index fc32aa81f359..6d00f746c2fd 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4458,8 +4458,9 @@ long si_mem_available(void) * Part of the reclaimable slab consists of items that are in use, * and cannot be freed. Cap this estimate at the low watermark. */ - available += global_page_state(NR_SLAB_RECLAIMABLE) - - min(global_page_state(NR_SLAB_RECLAIMABLE) / 2, wmark_low); + available += global_node_page_state(NR_SLAB_RECLAIMABLE) - + min(global_node_page_state(NR_SLAB_RECLAIMABLE) / 2, + wmark_low); if (available < 0) available = 0; @@ -4602,8 +4603,8 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) global_node_page_state(NR_FILE_DIRTY), global_node_page_state(NR_WRITEBACK), global_node_page_state(NR_UNSTABLE_NFS), - global_page_state(NR_SLAB_RECLAIMABLE), - global_page_state(NR_SLAB_UNRECLAIMABLE), + global_node_page_state(NR_SLAB_RECLAIMABLE), + global_node_page_state(NR_SLAB_UNRECLAIMABLE), global_node_page_state(NR_FILE_MAPPED), global_node_page_state(NR_SHMEM), global_page_state(NR_PAGETABLE), @@ -7668,7 +7669,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, /* Make sure the range is really isolated. */ if (test_pages_isolated(outer_start, end, false)) { - pr_info("%s: [%lx, %lx) PFNs busy\n", + pr_info_ratelimited("%s: [%lx, %lx) PFNs busy\n", __func__, outer_start, end); ret = -EBUSY; goto done; diff --git a/mm/rmap.c b/mm/rmap.c index c8993c63eb25..c1286d47aa1f 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -888,10 +888,10 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, .flags = PVMW_SYNC, }; int *cleaned = arg; + bool invalidation_needed = false; while (page_vma_mapped_walk(&pvmw)) { int ret = 0; - address = pvmw.address; if (pvmw.pte) { pte_t entry; pte_t *pte = pvmw.pte; @@ -899,11 +899,11 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, if (!pte_dirty(*pte) && !pte_write(*pte)) continue; - flush_cache_page(vma, address, pte_pfn(*pte)); - entry = ptep_clear_flush(vma, address, pte); + flush_cache_page(vma, pvmw.address, pte_pfn(*pte)); + entry = ptep_clear_flush(vma, pvmw.address, pte); entry = pte_wrprotect(entry); entry = pte_mkclean(entry); - set_pte_at(vma->vm_mm, address, pte, entry); + set_pte_at(vma->vm_mm, pvmw.address, pte, entry); ret = 1; } else { #ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE @@ -913,11 +913,11 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, if (!pmd_dirty(*pmd) && !pmd_write(*pmd)) continue; - flush_cache_page(vma, address, page_to_pfn(page)); - entry = pmdp_huge_clear_flush(vma, address, pmd); + flush_cache_page(vma, pvmw.address, page_to_pfn(page)); + entry = pmdp_huge_clear_flush(vma, pvmw.address, pmd); entry = pmd_wrprotect(entry); entry = pmd_mkclean(entry); - set_pmd_at(vma->vm_mm, address, pmd, entry); + set_pmd_at(vma->vm_mm, pvmw.address, pmd, entry); ret = 1; #else /* unexpected pmd-mapped page? */ @@ -926,11 +926,16 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, } if (ret) { - mmu_notifier_invalidate_page(vma->vm_mm, address); (*cleaned)++; + invalidation_needed = true; } } + if (invalidation_needed) { + mmu_notifier_invalidate_range(vma->vm_mm, address, + address + (1UL << compound_order(page))); + } + return true; } @@ -1323,7 +1328,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, }; pte_t pteval; struct page *subpage; - bool ret = true; + bool ret = true, invalidation_needed = false; enum ttu_flags flags = (enum ttu_flags)arg; /* munlock has nothing to gain from examining un-locked vmas */ @@ -1363,11 +1368,9 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, VM_BUG_ON_PAGE(!pvmw.pte, page); subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); - address = pvmw.address; - if (!(flags & TTU_IGNORE_ACCESS)) { - if (ptep_clear_flush_young_notify(vma, address, + if (ptep_clear_flush_young_notify(vma, pvmw.address, pvmw.pte)) { ret = false; page_vma_mapped_walk_done(&pvmw); @@ -1376,7 +1379,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } /* Nuke the page table entry. */ - flush_cache_page(vma, address, pte_pfn(*pvmw.pte)); + flush_cache_page(vma, pvmw.address, pte_pfn(*pvmw.pte)); if (should_defer_flush(mm, flags)) { /* * We clear the PTE but do not flush so potentially @@ -1386,11 +1389,12 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * transition on a cached TLB entry is written through * and traps if the PTE is unmapped. */ - pteval = ptep_get_and_clear(mm, address, pvmw.pte); + pteval = ptep_get_and_clear(mm, pvmw.address, + pvmw.pte); set_tlb_ubc_flush_pending(mm, pte_dirty(pteval)); } else { - pteval = ptep_clear_flush(vma, address, pvmw.pte); + pteval = ptep_clear_flush(vma, pvmw.address, pvmw.pte); } /* Move the dirty bit to the page. Now the pte is gone. */ @@ -1405,12 +1409,12 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, if (PageHuge(page)) { int nr = 1 << compound_order(page); hugetlb_count_sub(nr, mm); - set_huge_swap_pte_at(mm, address, + set_huge_swap_pte_at(mm, pvmw.address, pvmw.pte, pteval, vma_mmu_pagesize(vma)); } else { dec_mm_counter(mm, mm_counter(page)); - set_pte_at(mm, address, pvmw.pte, pteval); + set_pte_at(mm, pvmw.address, pvmw.pte, pteval); } } else if (pte_unused(pteval)) { @@ -1434,7 +1438,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); - set_pte_at(mm, address, pvmw.pte, swp_pte); + set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte); } else if (PageAnon(page)) { swp_entry_t entry = { .val = page_private(subpage) }; pte_t swp_pte; @@ -1460,7 +1464,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * If the page was redirtied, it cannot be * discarded. Remap the page to page table. */ - set_pte_at(mm, address, pvmw.pte, pteval); + set_pte_at(mm, pvmw.address, pvmw.pte, pteval); SetPageSwapBacked(page); ret = false; page_vma_mapped_walk_done(&pvmw); @@ -1468,7 +1472,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } if (swap_duplicate(entry) < 0) { - set_pte_at(mm, address, pvmw.pte, pteval); + set_pte_at(mm, pvmw.address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; @@ -1484,14 +1488,18 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); - set_pte_at(mm, address, pvmw.pte, swp_pte); + set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte); } else dec_mm_counter(mm, mm_counter_file(page)); discard: page_remove_rmap(subpage, PageHuge(page)); put_page(page); - mmu_notifier_invalidate_page(mm, address); + invalidation_needed = true; } + + if (invalidation_needed) + mmu_notifier_invalidate_range(mm, address, + address + (1UL << compound_order(page))); return ret; } diff --git a/mm/shmem.c b/mm/shmem.c index b0aa6075d164..6540e5982444 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1022,7 +1022,11 @@ static int shmem_setattr(struct dentry *dentry, struct iattr *attr) */ if (IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE)) { spin_lock(&sbinfo->shrinklist_lock); - if (list_empty(&info->shrinklist)) { + /* + * _careful to defend against unlocked access to + * ->shrink_list in shmem_unused_huge_shrink() + */ + if (list_empty_careful(&info->shrinklist)) { list_add_tail(&info->shrinklist, &sbinfo->shrinklist); sbinfo->shrinklist_len++; @@ -1817,7 +1821,11 @@ alloc_nohuge: page = shmem_alloc_and_acct_page(gfp, info, sbinfo, * to shrink under memory pressure. */ spin_lock(&sbinfo->shrinklist_lock); - if (list_empty(&info->shrinklist)) { + /* + * _careful to defend against unlocked access to + * ->shrink_list in shmem_unused_huge_shrink() + */ + if (list_empty_careful(&info->shrinklist)) { list_add_tail(&info->shrinklist, &sbinfo->shrinklist); sbinfo->shrinklist_len++; diff --git a/mm/util.c b/mm/util.c index 7b07ec852e01..9ecddf568fe3 100644 --- a/mm/util.c +++ b/mm/util.c @@ -633,7 +633,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) * which are reclaimable, under pressure. The dentry * cache and most inode caches should fall into this */ - free += global_page_state(NR_SLAB_RECLAIMABLE); + free += global_node_page_state(NR_SLAB_RECLAIMABLE); /* * Leave reserved pages. The pages are not for anonymous pages. diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index e1133bc634b5..8a3ce79b1307 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1549,9 +1549,41 @@ batadv_tt_global_entry_has_orig(const struct batadv_tt_global_entry *entry, return found; } +/** + * batadv_tt_global_sync_flags - update TT sync flags + * @tt_global: the TT global entry to update sync flags in + * + * Updates the sync flag bits in the tt_global flag attribute with a logical + * OR of all sync flags from any of its TT orig entries. + */ +static void +batadv_tt_global_sync_flags(struct batadv_tt_global_entry *tt_global) +{ + struct batadv_tt_orig_list_entry *orig_entry; + const struct hlist_head *head; + u16 flags = BATADV_NO_FLAGS; + + rcu_read_lock(); + head = &tt_global->orig_list; + hlist_for_each_entry_rcu(orig_entry, head, list) + flags |= orig_entry->flags; + rcu_read_unlock(); + + flags |= tt_global->common.flags & (~BATADV_TT_SYNC_MASK); + tt_global->common.flags = flags; +} + +/** + * batadv_tt_global_orig_entry_add - add or update a TT orig entry + * @tt_global: the TT global entry to add an orig entry in + * @orig_node: the originator to add an orig entry for + * @ttvn: translation table version number of this changeset + * @flags: TT sync flags + */ static void batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global, - struct batadv_orig_node *orig_node, int ttvn) + struct batadv_orig_node *orig_node, int ttvn, + u8 flags) { struct batadv_tt_orig_list_entry *orig_entry; @@ -1561,7 +1593,8 @@ batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global, * was added during a "temporary client detection" */ orig_entry->ttvn = ttvn; - goto out; + orig_entry->flags = flags; + goto sync_flags; } orig_entry = kmem_cache_zalloc(batadv_tt_orig_cache, GFP_ATOMIC); @@ -1573,6 +1606,7 @@ batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global, batadv_tt_global_size_inc(orig_node, tt_global->common.vid); orig_entry->orig_node = orig_node; orig_entry->ttvn = ttvn; + orig_entry->flags = flags; kref_init(&orig_entry->refcount); spin_lock_bh(&tt_global->list_lock); @@ -1582,6 +1616,8 @@ batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global, spin_unlock_bh(&tt_global->list_lock); atomic_inc(&tt_global->orig_list_count); +sync_flags: + batadv_tt_global_sync_flags(tt_global); out: if (orig_entry) batadv_tt_orig_list_entry_put(orig_entry); @@ -1703,10 +1739,10 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, } /* the change can carry possible "attribute" flags like the - * TT_CLIENT_WIFI, therefore they have to be copied in the + * TT_CLIENT_TEMP, therefore they have to be copied in the * client entry */ - common->flags |= flags; + common->flags |= flags & (~BATADV_TT_SYNC_MASK); /* If there is the BATADV_TT_CLIENT_ROAM flag set, there is only * one originator left in the list and we previously received a @@ -1723,7 +1759,8 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, } add_orig_entry: /* add the new orig_entry (if needed) or update it */ - batadv_tt_global_orig_entry_add(tt_global_entry, orig_node, ttvn); + batadv_tt_global_orig_entry_add(tt_global_entry, orig_node, ttvn, + flags & BATADV_TT_SYNC_MASK); batadv_dbg(BATADV_DBG_TT, bat_priv, "Creating new global tt entry: %pM (vid: %d, via %pM)\n", @@ -1946,6 +1983,7 @@ batadv_tt_global_dump_subentry(struct sk_buff *msg, u32 portid, u32 seq, struct batadv_tt_orig_list_entry *orig, bool best) { + u16 flags = (common->flags & (~BATADV_TT_SYNC_MASK)) | orig->flags; void *hdr; struct batadv_orig_node_vlan *vlan; u8 last_ttvn; @@ -1975,7 +2013,7 @@ batadv_tt_global_dump_subentry(struct sk_buff *msg, u32 portid, u32 seq, nla_put_u8(msg, BATADV_ATTR_TT_LAST_TTVN, last_ttvn) || nla_put_u32(msg, BATADV_ATTR_TT_CRC32, crc) || nla_put_u16(msg, BATADV_ATTR_TT_VID, common->vid) || - nla_put_u32(msg, BATADV_ATTR_TT_FLAGS, common->flags)) + nla_put_u32(msg, BATADV_ATTR_TT_FLAGS, flags)) goto nla_put_failure; if (best && nla_put_flag(msg, BATADV_ATTR_FLAG_BEST)) @@ -2589,6 +2627,7 @@ static u32 batadv_tt_global_crc(struct batadv_priv *bat_priv, unsigned short vid) { struct batadv_hashtable *hash = bat_priv->tt.global_hash; + struct batadv_tt_orig_list_entry *tt_orig; struct batadv_tt_common_entry *tt_common; struct batadv_tt_global_entry *tt_global; struct hlist_head *head; @@ -2627,8 +2666,9 @@ static u32 batadv_tt_global_crc(struct batadv_priv *bat_priv, /* find out if this global entry is announced by this * originator */ - if (!batadv_tt_global_entry_has_orig(tt_global, - orig_node)) + tt_orig = batadv_tt_global_orig_entry_find(tt_global, + orig_node); + if (!tt_orig) continue; /* use network order to read the VID: this ensures that @@ -2640,10 +2680,12 @@ static u32 batadv_tt_global_crc(struct batadv_priv *bat_priv, /* compute the CRC on flags that have to be kept in sync * among nodes */ - flags = tt_common->flags & BATADV_TT_SYNC_MASK; + flags = tt_orig->flags; crc_tmp = crc32c(crc_tmp, &flags, sizeof(flags)); crc ^= crc32c(crc_tmp, tt_common->addr, ETH_ALEN); + + batadv_tt_orig_list_entry_put(tt_orig); } rcu_read_unlock(); } diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index ea43a6449247..a62795868794 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1260,6 +1260,7 @@ struct batadv_tt_global_entry { * struct batadv_tt_orig_list_entry - orig node announcing a non-mesh client * @orig_node: pointer to orig node announcing this non-mesh client * @ttvn: translation table version number which added the non-mesh client + * @flags: per orig entry TT sync flags * @list: list node for batadv_tt_global_entry::orig_list * @refcount: number of contexts the object is used * @rcu: struct used for freeing in an RCU-safe manner @@ -1267,6 +1268,7 @@ struct batadv_tt_global_entry { struct batadv_tt_orig_list_entry { struct batadv_orig_node *orig_node; u8 ttvn; + u8 flags; struct hlist_node list; struct kref refcount; struct rcu_head rcu; diff --git a/net/core/dev.c b/net/core/dev.c index 8515f8fe0460..ce15a06d5558 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2739,7 +2739,7 @@ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) { if (tx_path) return skb->ip_summed != CHECKSUM_PARTIAL && - skb->ip_summed != CHECKSUM_NONE; + skb->ip_summed != CHECKSUM_UNNECESSARY; return skb->ip_summed == CHECKSUM_NONE; } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 76c2077c3f5b..2e548eca3489 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1731,6 +1731,13 @@ static __net_init int inet_init_net(struct net *net) net->ipv4.sysctl_ip_prot_sock = PROT_SOCK; #endif + /* Some igmp sysctl, whose values are always used */ + net->ipv4.sysctl_igmp_max_memberships = 20; + net->ipv4.sysctl_igmp_max_msf = 10; + /* IGMP reports for link-local multicast groups are enabled by default */ + net->ipv4.sysctl_igmp_llm_reports = 1; + net->ipv4.sysctl_igmp_qrv = 2; + return 0; } diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index c4c6e1969ed0..2ae8f54cb321 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1523,9 +1523,17 @@ unsigned char *cipso_v4_optptr(const struct sk_buff *skb) int taglen; for (optlen = iph->ihl*4 - sizeof(struct iphdr); optlen > 0; ) { - if (optptr[0] == IPOPT_CIPSO) + switch (optptr[0]) { + case IPOPT_CIPSO: return optptr; - taglen = optptr[1]; + case IPOPT_END: + return NULL; + case IPOPT_NOOP: + taglen = 1; + break; + default: + taglen = optptr[1]; + } optlen -= taglen; optptr += taglen; } diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 8e0257d01200..1540db65241a 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -450,6 +450,7 @@ out_unlock: out: NAPI_GRO_CB(skb)->flush |= flush; skb_gro_remcsum_cleanup(skb, &grc); + skb->remcsum_offload = 0; return pp; } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 28f14afd0dd3..498706b072fb 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2974,12 +2974,6 @@ static int __net_init igmp_net_init(struct net *net) goto out_sock; } - /* Sysctl initialization */ - net->ipv4.sysctl_igmp_max_memberships = 20; - net->ipv4.sysctl_igmp_max_msf = 10; - /* IGMP reports for link-local multicast groups are enabled by default */ - net->ipv4.sysctl_igmp_llm_reports = 1; - net->ipv4.sysctl_igmp_qrv = 2; return 0; out_sock: diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 50c74cd890bc..e153c40c2436 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -965,11 +965,12 @@ static int __ip_append_data(struct sock *sk, csummode = CHECKSUM_PARTIAL; cork->length += length; - if ((((length + (skb ? skb->len : fragheaderlen)) > mtu) || - (skb && skb_is_gso(skb))) && + if ((skb && skb_is_gso(skb)) || + (((length + (skb ? skb->len : fragheaderlen)) > mtu) && + (skb_queue_len(queue) <= 1) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) && - (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) { + (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx)) { err = ip_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, maxfraglen, flags); @@ -1288,6 +1289,7 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, return -EINVAL; if ((size + skb->len > mtu) && + (skb_queue_len(&sk->sk_write_queue) == 1) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO)) { if (skb->ip_summed != CHECKSUM_PARTIAL) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2920e0cb09f8..53de1424c13c 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -107,6 +107,7 @@ int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2; #define FLAG_ORIG_SACK_ACKED 0x200 /* Never retransmitted data are (s)acked */ #define FLAG_SND_UNA_ADVANCED 0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */ #define FLAG_DSACKING_ACK 0x800 /* SACK blocks contained D-SACK info */ +#define FLAG_SET_XMIT_TIMER 0x1000 /* Set TLP or RTO timer */ #define FLAG_SACK_RENEGING 0x2000 /* snd_una advanced to a sacked seq */ #define FLAG_UPDATE_TS_RECENT 0x4000 /* tcp_replace_ts_recent() */ #define FLAG_NO_CHALLENGE_ACK 0x8000 /* do not call tcp_send_challenge_ack() */ @@ -2520,8 +2521,8 @@ static inline void tcp_end_cwnd_reduction(struct sock *sk) return; /* Reset cwnd to ssthresh in CWR or Recovery (unless it's undone) */ - if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR || - (tp->undo_marker && tp->snd_ssthresh < TCP_INFINITE_SSTHRESH)) { + if (tp->snd_ssthresh < TCP_INFINITE_SSTHRESH && + (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR || tp->undo_marker)) { tp->snd_cwnd = tp->snd_ssthresh; tp->snd_cwnd_stamp = tcp_jiffies32; } @@ -3004,10 +3005,7 @@ void tcp_rearm_rto(struct sock *sk) /* Offset the time elapsed after installing regular RTO */ if (icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { - struct sk_buff *skb = tcp_write_queue_head(sk); - u64 rto_time_stamp = skb->skb_mstamp + - jiffies_to_usecs(rto); - s64 delta_us = rto_time_stamp - tp->tcp_mstamp; + s64 delta_us = tcp_rto_delta_us(sk); /* delta_us may not be positive if the socket is locked * when the retrans timer fires and is rescheduled. */ @@ -3019,6 +3017,13 @@ void tcp_rearm_rto(struct sock *sk) } } +/* Try to schedule a loss probe; if that doesn't work, then schedule an RTO. */ +static void tcp_set_xmit_timer(struct sock *sk) +{ + if (!tcp_schedule_loss_probe(sk)) + tcp_rearm_rto(sk); +} + /* If we get here, the whole TSO packet has not been acked. */ static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb) { @@ -3180,7 +3185,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, ca_rtt_us, sack->rate); if (flag & FLAG_ACKED) { - tcp_rearm_rto(sk); + flag |= FLAG_SET_XMIT_TIMER; /* set TLP or RTO timer */ if (unlikely(icsk->icsk_mtup.probe_size && !after(tp->mtu_probe.probe_seq_end, tp->snd_una))) { tcp_mtup_probe_success(sk); @@ -3208,7 +3213,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, * after when the head was last (re)transmitted. Otherwise the * timeout may continue to extend in loss recovery. */ - tcp_rearm_rto(sk); + flag |= FLAG_SET_XMIT_TIMER; /* set TLP or RTO timer */ } if (icsk->icsk_ca_ops->pkts_acked) { @@ -3580,9 +3585,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (after(ack, tp->snd_nxt)) goto invalid_ack; - if (icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) - tcp_rearm_rto(sk); - if (after(ack, prior_snd_una)) { flag |= FLAG_SND_UNA_ADVANCED; icsk->icsk_retransmits = 0; @@ -3647,18 +3649,20 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, &acked, &sack_state); + if (tp->tlp_high_seq) + tcp_process_tlp_ack(sk, ack, flag); + /* If needed, reset TLP/RTO timer; RACK may later override this. */ + if (flag & FLAG_SET_XMIT_TIMER) + tcp_set_xmit_timer(sk); + if (tcp_ack_is_dubious(sk, flag)) { is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit); } - if (tp->tlp_high_seq) - tcp_process_tlp_ack(sk, ack, flag); if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) sk_dst_confirm(sk); - if (icsk->icsk_pending == ICSK_TIME_RETRANS) - tcp_schedule_loss_probe(sk); delivered = tp->delivered - delivered; /* freshly ACKed or SACKed */ lost = tp->lost - lost; /* freshly marked lost */ tcp_rate_gen(sk, delivered, lost, sack_state.rate); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 2f1588bf73da..b7661a68d498 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2377,24 +2377,15 @@ bool tcp_schedule_loss_probe(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - u32 timeout, tlp_time_stamp, rto_time_stamp; u32 rtt = usecs_to_jiffies(tp->srtt_us >> 3); + u32 timeout, rto_delta_us; - /* No consecutive loss probes. */ - if (WARN_ON(icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)) { - tcp_rearm_rto(sk); - return false; - } /* Don't do any loss probe on a Fast Open connection before 3WHS * finishes. */ if (tp->fastopen_rsk) return false; - /* TLP is only scheduled when next timer event is RTO. */ - if (icsk->icsk_pending != ICSK_TIME_RETRANS) - return false; - /* Schedule a loss probe in 2*RTT for SACK capable connections * in Open state, that are either limited by cwnd or application. */ @@ -2417,14 +2408,10 @@ bool tcp_schedule_loss_probe(struct sock *sk) (rtt + (rtt >> 1) + TCP_DELACK_MAX)); timeout = max_t(u32, timeout, msecs_to_jiffies(10)); - /* If RTO is shorter, just schedule TLP in its place. */ - tlp_time_stamp = tcp_jiffies32 + timeout; - rto_time_stamp = (u32)inet_csk(sk)->icsk_timeout; - if ((s32)(tlp_time_stamp - rto_time_stamp) > 0) { - s32 delta = rto_time_stamp - tcp_jiffies32; - if (delta > 0) - timeout = delta; - } + /* If the RTO formula yields an earlier time, then use that time. */ + rto_delta_us = tcp_rto_delta_us(sk); /* How far in future is RTO? */ + if (rto_delta_us > 0) + timeout = min_t(u32, timeout, usecs_to_jiffies(rto_delta_us)); inet_csk_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout, TCP_RTO_MAX); @@ -3449,6 +3436,10 @@ int tcp_connect(struct sock *sk) int err; tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB); + + if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) + return -EHOSTUNREACH; /* Routing failure or similar. */ + tcp_connect_init(sk); if (unlikely(tp->repair)) { diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index c0feeeef962a..e906014890b6 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -652,7 +652,8 @@ static void tcp_keepalive_timer (unsigned long data) goto death; } - if (!sock_flag(sk, SOCK_KEEPOPEN) || sk->sk_state == TCP_CLOSE) + if (!sock_flag(sk, SOCK_KEEPOPEN) || + ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT))) goto out; elapsed = keepalive_time_when(tp); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index e6276fa3750b..a7c804f73990 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -802,7 +802,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4) if (is_udplite) /* UDP-Lite */ csum = udplite_csum(skb); - else if (sk->sk_no_check_tx) { /* UDP csum disabled */ + else if (sk->sk_no_check_tx && !skb_is_gso(skb)) { /* UDP csum off */ skb->ip_summed = CHECKSUM_NONE; goto send; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 781250151d40..0932c85b42af 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -235,7 +235,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, if (uh->check == 0) uh->check = CSUM_MANGLED_0; - skb->ip_summed = CHECKSUM_NONE; + skb->ip_summed = CHECKSUM_UNNECESSARY; /* If there is no outer header we can fake a checksum offload * due to the fact that we have already done the checksum in diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 162efba0d0cd..2dfe50d8d609 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1381,11 +1381,12 @@ emsgsize: */ cork->length += length; - if ((((length + (skb ? skb->len : headersize)) > mtu) || - (skb && skb_is_gso(skb))) && + if ((skb && skb_is_gso(skb)) || + (((length + (skb ? skb->len : headersize)) > mtu) && + (skb_queue_len(queue) <= 1) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) && - (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) { + (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk))) { err = ip6_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, exthdrlen, transhdrlen, mtu, flags, fl6); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 4d30c96a819d..a640fbcba15d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2351,6 +2351,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu if (on_link) nrt->rt6i_flags &= ~RTF_GATEWAY; + nrt->rt6i_protocol = RTPROT_REDIRECT; nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; if (ip6_ins_rt(nrt)) @@ -2461,6 +2462,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net, .fc_dst_len = prefixlen, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO | RTF_UP | RTF_PREF(pref), + .fc_protocol = RTPROT_RA, .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = net, @@ -2513,6 +2515,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, .fc_ifindex = dev->ifindex, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | RTF_UP | RTF_EXPIRES | RTF_PREF(pref), + .fc_protocol = RTPROT_RA, .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = dev_net(dev), @@ -3424,14 +3427,6 @@ static int rt6_fill_node(struct net *net, rtm->rtm_flags = 0; rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_protocol = rt->rt6i_protocol; - if (rt->rt6i_flags & RTF_DYNAMIC) - rtm->rtm_protocol = RTPROT_REDIRECT; - else if (rt->rt6i_flags & RTF_ADDRCONF) { - if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ROUTEINFO)) - rtm->rtm_protocol = RTPROT_RA; - else - rtm->rtm_protocol = RTPROT_KERNEL; - } if (rt->rt6i_flags & RTF_CACHE) rtm->rtm_flags |= RTM_F_CLONED; diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index a2267f80febb..e7d378c032cb 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -72,7 +72,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, if (uh->check == 0) uh->check = CSUM_MANGLED_0; - skb->ip_summed = CHECKSUM_NONE; + skb->ip_summed = CHECKSUM_UNNECESSARY; /* If there is no outer header we can fake a checksum offload * due to the fact that we have already done the checksum in diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 0615c2a950fa..008a45ca3112 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3700,14 +3700,19 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) - return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; if (val > INT_MAX) return -EINVAL; - po->tp_reserve = val; - return 0; + lock_sock(sk); + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { + ret = -EBUSY; + } else { + po->tp_reserve = val; + ret = 0; + } + release_sock(sk); + return ret; } case PACKET_LOSS: { diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index e10624aa6959..9722bf839d9d 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -1015,8 +1015,10 @@ void rds_ib_recv_cqe_handler(struct rds_ib_connection *ic, if (rds_ib_ring_empty(&ic->i_recv_ring)) rds_ib_stats_inc(s_ib_rx_ring_empty); - if (rds_ib_ring_low(&ic->i_recv_ring)) + if (rds_ib_ring_low(&ic->i_recv_ring)) { rds_ib_recv_refill(conn, 0, GFP_NOWAIT); + rds_ib_stats_inc(s_ib_rx_refill_from_cq); + } } int rds_ib_recv_path(struct rds_conn_path *cp) @@ -1029,6 +1031,7 @@ int rds_ib_recv_path(struct rds_conn_path *cp) if (rds_conn_up(conn)) { rds_ib_attempt_ack(ic); rds_ib_recv_refill(conn, 0, GFP_KERNEL); + rds_ib_stats_inc(s_ib_rx_refill_from_thread); } return ret; diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 36f0ced9e60c..d516ba8178b8 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -36,8 +36,8 @@ static struct tc_action_ops act_ipt_ops; static unsigned int xt_net_id; static struct tc_action_ops act_xt_ops; -static int ipt_init_target(struct xt_entry_target *t, char *table, - unsigned int hook) +static int ipt_init_target(struct net *net, struct xt_entry_target *t, + char *table, unsigned int hook) { struct xt_tgchk_param par; struct xt_target *target; @@ -49,8 +49,9 @@ static int ipt_init_target(struct xt_entry_target *t, char *table, return PTR_ERR(target); t->u.kernel.target = target; + memset(&par, 0, sizeof(par)); + par.net = net; par.table = table; - par.entryinfo = NULL; par.target = target; par.targinfo = t->data; par.hook_mask = hook; @@ -91,10 +92,11 @@ static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = { [TCA_IPT_TARG] = { .len = sizeof(struct xt_entry_target) }, }; -static int __tcf_ipt_init(struct tc_action_net *tn, struct nlattr *nla, +static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla, struct nlattr *est, struct tc_action **a, const struct tc_action_ops *ops, int ovr, int bind) { + struct tc_action_net *tn = net_generic(net, id); struct nlattr *tb[TCA_IPT_MAX + 1]; struct tcf_ipt *ipt; struct xt_entry_target *td, *t; @@ -159,7 +161,7 @@ static int __tcf_ipt_init(struct tc_action_net *tn, struct nlattr *nla, if (unlikely(!t)) goto err2; - err = ipt_init_target(t, tname, hook); + err = ipt_init_target(net, t, tname, hook); if (err < 0) goto err3; @@ -193,18 +195,16 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind) { - struct tc_action_net *tn = net_generic(net, ipt_net_id); - - return __tcf_ipt_init(tn, nla, est, a, &act_ipt_ops, ovr, bind); + return __tcf_ipt_init(net, ipt_net_id, nla, est, a, &act_ipt_ops, ovr, + bind); } static int tcf_xt_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind) { - struct tc_action_net *tn = net_generic(net, xt_net_id); - - return __tcf_ipt_init(tn, nla, est, a, &act_xt_ops, ovr, bind); + return __tcf_ipt_init(net, xt_net_id, nla, est, a, &act_xt_ops, ovr, + bind); } static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a, diff --git a/net/tipc/node.c b/net/tipc/node.c index aeef8011ac7d..9b4dcb6a16b5 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1455,10 +1455,8 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb, /* Initiate synch mode if applicable */ if ((usr == TUNNEL_PROTOCOL) && (mtyp == SYNCH_MSG) && (oseqno == 1)) { syncpt = iseqno + exp_pkts - 1; - if (!tipc_link_is_up(l)) { - tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT); + if (!tipc_link_is_up(l)) __tipc_node_link_up(n, bearer_id, xmitq); - } if (n->state == SELF_UP_PEER_UP) { n->sync_point = syncpt; tipc_link_fsm_evt(l, LINK_SYNCH_BEGIN_EVT); diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 3bd5f4f30235..bc443201d3ef 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -18,6 +18,7 @@ my $V = '0.26'; use Getopt::Long qw(:config no_auto_abbrev); use Cwd; +use File::Find; my $cur_path = fastgetcwd() . '/'; my $lk_path = "./"; @@ -58,6 +59,7 @@ my $from_filename = 0; my $pattern_depth = 0; my $version = 0; my $help = 0; +my $find_maintainer_files = 0; my $vcs_used = 0; @@ -249,6 +251,7 @@ if (!GetOptions( 'sections!' => \$sections, 'fe|file-emails!' => \$file_emails, 'f|file' => \$from_filename, + 'find-maintainer-files' => \$find_maintainer_files, 'v|version' => \$version, 'h|help|usage' => \$help, )) { @@ -307,36 +310,74 @@ if (!top_of_kernel_tree($lk_path)) { my @typevalue = (); my %keyword_hash; +my @mfiles = (); -open (my $maint, '<', "${lk_path}MAINTAINERS") - or die "$P: Can't open MAINTAINERS: $!\n"; -while (<$maint>) { - my $line = $_; - - if ($line =~ m/^([A-Z]):\s*(.*)/) { - my $type = $1; - my $value = $2; - - ##Filename pattern matching - if ($type eq "F" || $type eq "X") { - $value =~ s@\.@\\\.@g; ##Convert . to \. - $value =~ s/\*/\.\*/g; ##Convert * to .* - $value =~ s/\?/\./g; ##Convert ? to . - ##if pattern is a directory and it lacks a trailing slash, add one - if ((-d $value)) { - $value =~ s@([^/])$@$1/@; +sub read_maintainer_file { + my ($file) = @_; + + open (my $maint, '<', "$file") + or die "$P: Can't open MAINTAINERS file '$file': $!\n"; + while (<$maint>) { + my $line = $_; + + if ($line =~ m/^([A-Z]):\s*(.*)/) { + my $type = $1; + my $value = $2; + + ##Filename pattern matching + if ($type eq "F" || $type eq "X") { + $value =~ s@\.@\\\.@g; ##Convert . to \. + $value =~ s/\*/\.\*/g; ##Convert * to .* + $value =~ s/\?/\./g; ##Convert ? to . + ##if pattern is a directory and it lacks a trailing slash, add one + if ((-d $value)) { + $value =~ s@([^/])$@$1/@; + } + } elsif ($type eq "K") { + $keyword_hash{@typevalue} = $value; } - } elsif ($type eq "K") { - $keyword_hash{@typevalue} = $value; + push(@typevalue, "$type:$value"); + } elsif (!(/^\s*$/ || /^\s*\#/)) { + $line =~ s/\n$//g; + push(@typevalue, $line); } - push(@typevalue, "$type:$value"); - } elsif (!/^(\s)*$/) { - $line =~ s/\n$//g; - push(@typevalue, $line); } + close($maint); +} + +sub find_is_maintainer_file { + my ($file) = $_; + return if ($file !~ m@/MAINTAINERS$@); + $file = $File::Find::name; + return if (! -f $file); + push(@mfiles, $file); } -close($maint); +sub find_ignore_git { + return grep { $_ !~ /^\.git$/; } @_; +} + +if (-d "${lk_path}MAINTAINERS") { + opendir(DIR, "${lk_path}MAINTAINERS") or die $!; + my @files = readdir(DIR); + closedir(DIR); + foreach my $file (@files) { + push(@mfiles, "${lk_path}MAINTAINERS/$file") if ($file !~ /^\./); + } +} + +if ($find_maintainer_files) { + find( { wanted => \&find_is_maintainer_file, + preprocess => \&find_ignore_git, + no_chdir => 1, + }, "${lk_path}"); +} else { + push(@mfiles, "${lk_path}MAINTAINERS") if -f "${lk_path}MAINTAINERS"; +} + +foreach my $file (@mfiles) { + read_maintainer_file("$file"); +} # # Read mail address map @@ -873,7 +914,7 @@ sub top_of_kernel_tree { if ( (-f "${lk_path}COPYING") && (-f "${lk_path}CREDITS") && (-f "${lk_path}Kbuild") - && (-f "${lk_path}MAINTAINERS") + && (-e "${lk_path}MAINTAINERS") && (-f "${lk_path}Makefile") && (-f "${lk_path}README") && (-d "${lk_path}Documentation") diff --git a/scripts/parse-maintainers.pl b/scripts/parse-maintainers.pl index a0fe34349b24..e40b53db7f9f 100644 --- a/scripts/parse-maintainers.pl +++ b/scripts/parse-maintainers.pl @@ -2,9 +2,9 @@ use strict; -my %map; +my $P = $0; -# sort comparison function +# sort comparison functions sub by_category($$) { my ($a, $b) = @_; @@ -15,20 +15,33 @@ sub by_category($$) { $a =~ s/THE REST/ZZZZZZ/g; $b =~ s/THE REST/ZZZZZZ/g; - $a cmp $b; + return $a cmp $b; } -sub alpha_output { - my $key; - my $sort_method = \&by_category; - my $sep = ""; - - foreach $key (sort $sort_method keys %map) { - if ($key ne " ") { - print $sep . $key . "\n"; - $sep = "\n"; - } - print $map{$key}; +sub by_pattern($$) { + my ($a, $b) = @_; + my $preferred_order = 'MRPLSWTQBCFXNK'; + + my $a1 = uc(substr($a, 0, 1)); + my $b1 = uc(substr($b, 0, 1)); + + my $a_index = index($preferred_order, $a1); + my $b_index = index($preferred_order, $b1); + + $a_index = 1000 if ($a_index == -1); + $b_index = 1000 if ($b_index == -1); + + if (($a1 =~ /^F$/ && $b1 =~ /^F$/) || + ($a1 =~ /^X$/ && $b1 =~ /^X$/)) { + return $a cmp $b; + } + + if ($a_index < $b_index) { + return -1; + } elsif ($a_index == $b_index) { + return 0; + } else { + return 1; } } @@ -39,39 +52,77 @@ sub trim { return $s; } +sub alpha_output { + my ($hashref, $filename) = (@_); + + open(my $file, '>', "$filename") or die "$P: $filename: open failed - $!\n"; + foreach my $key (sort by_category keys %$hashref) { + if ($key eq " ") { + chomp $$hashref{$key}; + print $file $$hashref{$key}; + } else { + print $file "\n" . $key . "\n"; + foreach my $pattern (sort by_pattern split('\n', %$hashref{$key})) { + print $file ($pattern . "\n"); + } + } + } + close($file); +} + sub file_input { + my ($hashref, $filename) = (@_); + my $lastline = ""; my $case = " "; - $map{$case} = ""; + $$hashref{$case} = ""; + + open(my $file, '<', "$filename") or die "$P: $filename: open failed - $!\n"; - while (<>) { + while (<$file>) { my $line = $_; # Pattern line? if ($line =~ m/^([A-Z]):\s*(.*)/) { $line = $1 . ":\t" . trim($2) . "\n"; if ($lastline eq "") { - $map{$case} = $map{$case} . $line; + $$hashref{$case} = $$hashref{$case} . $line; next; } $case = trim($lastline); - exists $map{$case} and die "Header '$case' already exists"; - $map{$case} = $line; + exists $$hashref{$case} and die "Header '$case' already exists"; + $$hashref{$case} = $line; $lastline = ""; next; } if ($case eq " ") { - $map{$case} = $map{$case} . $lastline; + $$hashref{$case} = $$hashref{$case} . $lastline; $lastline = $line; next; } trim($lastline) eq "" or die ("Odd non-pattern line '$lastline' for '$case'"); $lastline = $line; } - $map{$case} = $map{$case} . $lastline; + $$hashref{$case} = $$hashref{$case} . $lastline; + close($file); } -&file_input; -&alpha_output; +my %hash; +my %new_hash; + +file_input(\%hash, "MAINTAINERS"); + +foreach my $type (@ARGV) { + foreach my $key (keys %hash) { + if ($key =~ /$type/ || $hash{$key} =~ /$type/) { + $new_hash{$key} = $hash{$key}; + delete $hash{$key}; + } + } +} + +alpha_output(\%hash, "MAINTAINERS.new"); +alpha_output(\%new_hash, "SECTION.new"); + exit(0); diff --git a/tools/build/feature/test-bpf.c b/tools/build/feature/test-bpf.c index 7598361ef1f1..da2172ff9662 100644 --- a/tools/build/feature/test-bpf.c +++ b/tools/build/feature/test-bpf.c @@ -11,6 +11,8 @@ # define __NR_bpf 280 # elif defined(__sparc__) # define __NR_bpf 349 +# elif defined(__s390__) +# define __NR_bpf 351 # else # error __NR_bpf not defined. libbpf does not support your arch. # endif diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 256f571f2ab5..e5bbb090bf88 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -39,6 +39,8 @@ # define __NR_bpf 280 # elif defined(__sparc__) # define __NR_bpf 349 +# elif defined(__s390__) +# define __NR_bpf 351 # else # error __NR_bpf not defined. libbpf does not support your arch. # endif diff --git a/tools/testing/selftests/bpf/test_pkt_md_access.c b/tools/testing/selftests/bpf/test_pkt_md_access.c index 71729d47eb85..7956302ecdf2 100644 --- a/tools/testing/selftests/bpf/test_pkt_md_access.c +++ b/tools/testing/selftests/bpf/test_pkt_md_access.c @@ -12,12 +12,23 @@ int _version SEC("version") = 1; +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ #define TEST_FIELD(TYPE, FIELD, MASK) \ { \ TYPE tmp = *(volatile TYPE *)&skb->FIELD; \ if (tmp != ((*(volatile __u32 *)&skb->FIELD) & MASK)) \ return TC_ACT_SHOT; \ } +#else +#define TEST_FIELD_OFFSET(a, b) ((sizeof(a) - sizeof(b)) / sizeof(b)) +#define TEST_FIELD(TYPE, FIELD, MASK) \ + { \ + TYPE tmp = *((volatile TYPE *)&skb->FIELD + \ + TEST_FIELD_OFFSET(skb->FIELD, TYPE)); \ + if (tmp != ((*(volatile __u32 *)&skb->FIELD) & MASK)) \ + return TC_ACT_SHOT; \ + } +#endif SEC("test1") int process(struct __sk_buff *skb) diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index addea82f76c9..d3ed7324105e 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -8,6 +8,7 @@ * License as published by the Free Software Foundation. */ +#include <endian.h> #include <asm/types.h> #include <linux/types.h> #include <stdint.h> @@ -1098,7 +1099,7 @@ static struct bpf_test tests[] = { "check skb->hash byte load permitted", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), -#ifdef __LITTLE_ENDIAN +#if __BYTE_ORDER == __LITTLE_ENDIAN BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, offsetof(struct __sk_buff, hash)), #else @@ -1135,7 +1136,7 @@ static struct bpf_test tests[] = { "check skb->hash byte load not permitted 3", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), -#ifdef __LITTLE_ENDIAN +#if __BYTE_ORDER == __LITTLE_ENDIAN BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, offsetof(struct __sk_buff, hash) + 3), #else @@ -1244,7 +1245,7 @@ static struct bpf_test tests[] = { "check skb->hash half load permitted", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), -#ifdef __LITTLE_ENDIAN +#if __BYTE_ORDER == __LITTLE_ENDIAN BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, offsetof(struct __sk_buff, hash)), #else @@ -1259,7 +1260,7 @@ static struct bpf_test tests[] = { "check skb->hash half load not permitted", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), -#ifdef __LITTLE_ENDIAN +#if __BYTE_ORDER == __LITTLE_ENDIAN BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, offsetof(struct __sk_buff, hash) + 2), #else @@ -5422,7 +5423,7 @@ static struct bpf_test tests[] = { "check bpf_perf_event_data->sample_period byte load permitted", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), -#ifdef __LITTLE_ENDIAN +#if __BYTE_ORDER == __LITTLE_ENDIAN BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, offsetof(struct bpf_perf_event_data, sample_period)), #else @@ -5438,7 +5439,7 @@ static struct bpf_test tests[] = { "check bpf_perf_event_data->sample_period half load permitted", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), -#ifdef __LITTLE_ENDIAN +#if __BYTE_ORDER == __LITTLE_ENDIAN BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, offsetof(struct bpf_perf_event_data, sample_period)), #else @@ -5454,7 +5455,7 @@ static struct bpf_test tests[] = { "check bpf_perf_event_data->sample_period word load permitted", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), -#ifdef __LITTLE_ENDIAN +#if __BYTE_ORDER == __LITTLE_ENDIAN BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, offsetof(struct bpf_perf_event_data, sample_period)), #else @@ -5481,7 +5482,7 @@ static struct bpf_test tests[] = { "check skb->data half load not permitted", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), -#ifdef __LITTLE_ENDIAN +#if __BYTE_ORDER == __LITTLE_ENDIAN BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, offsetof(struct __sk_buff, data)), #else @@ -5497,7 +5498,7 @@ static struct bpf_test tests[] = { "check skb->tc_classid half load not permitted for lwt prog", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), -#ifdef __LITTLE_ENDIAN +#if __BYTE_ORDER == __LITTLE_ENDIAN BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, offsetof(struct __sk_buff, tc_classid)), #else |