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
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
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
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/
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>
}
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));
}
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 */
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);
* 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.
--- /dev/null
+/*
+ * 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;
+}
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;
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);
}
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);
}
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;
}
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 */
#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 {
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";
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;
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
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
be,pt %xcc, niagara4_patch
nop
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
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();
}
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;
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;
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 |
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 |
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;
}
}
*/
switch (sun4v_chip_type) {
case SUN4V_CHIP_SPARC_M7:
+ case SUN4V_CHIP_SPARC_M8:
case SUN4V_CHIP_SPARC_SN:
pagecv_flag = 0x00;
break;
*/
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;
}
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;
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 */
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
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
+++ /dev/null
-/*
- * 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 */
+++ /dev/null
-/*
- * 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 */
}
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
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)
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
/* 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??
__flush_invalidate_dcache_all();
__invalidate_icache_all();
}
+EXPORT_SYMBOL(local_flush_cache_range);
/*
* Remove any entry in the cache for this page.
__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)
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);
* 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,
*
* 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 */
/*
* 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)
{
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;
* 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,
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
* 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);
/**
- * 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
* @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)
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);
/**
* 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,
*/
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
/*
* 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);
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)
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;
}
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;
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);
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;
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) {
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);
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));
return -EBUSY;
}
- strlcpy(zram->compressor, compressor, sizeof(compressor));
+ strcpy(zram->compressor, compressor);
up_write(&zram->init_lock);
return len;
}
#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);
}
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;
}
}
+ memcpy(ctx->ipad, &istate.state, SHA1_DIGEST_SIZE);
+ memcpy(ctx->opad, &ostate.state, SHA1_DIGEST_SIZE);
+
return 0;
}
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
}
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.
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;
}
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)
{
}
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);
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;
}
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;
}
{
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;
}
* 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;
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;
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"
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;
};
}
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;
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)
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);
}
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;
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);
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);
req->status = -ECANCELED;
req->timeout = jiffies;
list_move(&req->list, &req_list);
- set_timeout(req->timeout);
+ set_timeout(&req->work, req->timeout);
break;
}
}
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;
}
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;
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;
if (atomic_dec_and_test(&file->device->refcount))
ib_uverbs_comp_dev(file->device);
+ kobject_put(&file->device->kobj);
kfree(file);
}
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) {
ib_uverbs_release_async_event_file);
kref_put(&file->ref, ib_uverbs_release_file);
- kobject_put(&dev->kobj);
return 0;
}
} 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 = {
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;
}
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);
unsigned long flags;
struct rw_semaphore vlan_rwsem;
+ struct mutex mcast_mutex;
struct rb_root path_tree;
struct list_head path_list;
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:
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)
++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) &&
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);
*/
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;
int i, wait_flushed = 0;
init_completion(&priv->ntbl.flushed);
+ set_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags);
spin_lock_irqsave(&priv->lock, flags);
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);
.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)
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);
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;
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;
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
/*
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;
}
{
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);
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);
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)
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);
/*
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;
};
{
struct log_data *ib;
struct procdata *pd = card->proclog;
- int i;
unsigned long flags;
if (!pd)
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 */
* 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);
*/
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,
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);
}
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;
}
* 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,
};
* @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,
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);
*/
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
* 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);
}
}
#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 | \
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.
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;
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++;
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 *);
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) {
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);
*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;
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
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);
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);
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;
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;
* 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)
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));
}
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;
}
[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;
#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
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);
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 {
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)) {
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,
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;
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);
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);
}
+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;
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);
}
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);
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);
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;
#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);
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.
*/
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;
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",
.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)
{
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)) {
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;
{
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++)
}
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:
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);
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)
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);
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;
}
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;
u32 max_chn;
u32 num_chn;
- refcount_t sc_offered;
+ atomic_t open_chn;
+ wait_queue_head_t subchan_open;
struct rndis_device *extension;
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;
}
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 */
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,
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;
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;
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);
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;
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);
}
/*
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);
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)
{
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);
}
}
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;
}
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;
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;
}
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)
{
static void ax88772_unbind(struct usbnet *dev, struct usb_interface *intf)
{
+ asix_rx_fixup_common_free(dev->driver_priv);
kfree(dev->driver_priv);
}
/* 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;
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)
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 */
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);
{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 */
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();
out:
skb_gro_remcsum_cleanup(skb, &grc);
+ skb->remcsum_offload = 0;
NAPI_GRO_CB(skb)->flush |= flush;
return pp;
}
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
DMI_MATCH(DMI_PRODUCT_FAMILY, "Intel_Strago"),
},
},
+ {
+ .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 = {
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 };
#define IRQ_STATUS 0x10
#define IRQ_WKUP 0x18
-#define NB_FUNCS 2
+#define NB_FUNCS 3
#define GPIO_PER_REG 32
/**
.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) \
{ \
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 = {
};
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),
{
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;
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,
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++;
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),
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 */
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;
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;
#include <linux/slab.h>
#include <linux/syscalls.h>
#include <linux/uaccess.h>
+#include <uapi/linux/sched/types.h>
#include "ptp_private.h"
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,
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;
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);
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);
}
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)
#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>
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;
};
/*
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 */
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 */
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;
};
/**
- * 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;
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;
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);
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;
}
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);
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,
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);
/*
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;
/* 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++;
/**
- * 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;
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;
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;
}
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);
static void __exit bnx2i_mod_exit(void)
{
struct bnx2i_hba *hba;
- unsigned cpu = 0;
mutex_lock(&bnx2i_dev_lock);
while (!list_empty(&adapter_list)) {
}
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);
#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
* 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);
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
}
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;
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)
"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);
}
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);
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) {}
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);
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: ",
#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"
struct mm_struct *mm;
struct vm_area_struct *vma;
enum clear_refs_types type;
+ struct mmu_gather tlb;
int itype;
int rv;
}
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))
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);
uffdio_copy.len);
mmput(ctx->mm);
} else {
- return -ENOSPC;
+ return -ESRCH;
}
if (unlikely(put_user(ret, &user_uffdio_copy->copy)))
return -EFAULT;
uffdio_zeropage.range.len);
mmput(ctx->mm);
} else {
- return -ENOSPC;
+ return -ESRCH;
}
if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage)))
return -EFAULT;
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)) {
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:
INIT_WORK(&ctx->discard_endio_work, xlog_discard_endio_work);
queue_work(xfs_discard_wq, &ctx->discard_endio_work);
+ bio_put(bio);
}
static void
#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);
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,
* 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.
#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
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;
};
#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,
/* 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;
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;
* @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;
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);
* 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.
* 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().
*
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;
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)
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
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
*/
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
* 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);
{
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)
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 */
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,
config->test_fs);
else
len += snprintf(buf+len, PAGE_SIZE - len,
- "fs:\tEMTPY\n");
+ "fs:\tEMPTY\n");
mutex_unlock(&test_dev->config_mutex);
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;
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;
unsigned int max)
{
int ret;
- long new;
+ unsigned long new;
- ret = kstrtol(buf, 10, &new);
+ ret = kstrtoul(buf, 10, &new);
if (ret)
return ret;
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) {
{
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;
#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,
#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
);
}
goto clear_pmdnuma;
}
+ /*
+ * 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.
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;
}
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);
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;
* 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 */
#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.
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);
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))
/* 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;
}
* 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;
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),
/* 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;
.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;
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
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? */
}
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;
}
};
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 */
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);
}
/* 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
* 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. */
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)) {
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;
* 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);
}
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;
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;
}
*/
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++;
* 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++;
* 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.
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;
* 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);
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);
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);
}
/* 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
}
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",
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;
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))
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;
/* 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
/* 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();
}
* 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
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;
{
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;
}
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;
}
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;
}
out:
NAPI_GRO_CB(skb)->flush |= flush;
skb_gro_remcsum_cleanup(skb, &grc);
+ skb->remcsum_offload = 0;
return pp;
}
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:
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);
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)
#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() */
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;
}
/* 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.
*/
}
}
+/* 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)
{
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);
* 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) {
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;
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);
{
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.
*/
(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);
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)) {
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);
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;
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
*/
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);
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))
.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,
.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),
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;
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
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:
{
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)
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;
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;
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;
[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;
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;
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,
/* 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);
use Getopt::Long qw(:config no_auto_abbrev);
use Cwd;
+use File::Find;
my $cur_path = fastgetcwd() . '/';
my $lk_path = "./";
my $pattern_depth = 0;
my $version = 0;
my $help = 0;
+my $find_maintainer_files = 0;
my $vcs_used = 0;
'sections!' => \$sections,
'fe|file-emails!' => \$file_emails,
'f|file' => \$from_filename,
+ 'find-maintainer-files' => \$find_maintainer_files,
'v|version' => \$version,
'h|help|usage' => \$help,
)) {
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
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")
use strict;
-my %map;
+my $P = $0;
-# sort comparison function
+# sort comparison functions
sub by_category($$) {
my ($a, $b) = @_;
$a =~ s/THE REST/ZZZZZZ/g;
$b =~ s/THE REST/ZZZZZZ/g;
- $a cmp $b;
+ return $a cmp $b;
}
-sub alpha_output {
- my $key;
- my $sort_method = \&by_category;
- my $sep = "";
-
- foreach $key (sort $sort_method keys %map) {
- if ($key ne " ") {
- print $sep . $key . "\n";
- $sep = "\n";
- }
- print $map{$key};
+sub by_pattern($$) {
+ 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;
}
}
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);
# 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
# 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
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)
* License as published by the Free Software Foundation.
*/
+#include <endian.h>
#include <asm/types.h>
#include <linux/types.h>
#include <stdint.h>
"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
"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
"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
"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
"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
"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
"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
"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
"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
projects / karo-tx-linux.git / commitdiff