* RE: [PATCH v2] ARM: net: JIT compiler for packet filters
From: Nicolas Pitre @ 2011-12-23 2:26 UTC (permalink / raw)
To: David Laight; +Cc: Dave Martin, Mircea Gherzan, netdev, linux, linux-arm-kernel
In-Reply-To: <AE90C24D6B3A694183C094C60CF0A2F6D8AF25@saturn3.aculab.com>
On Thu, 22 Dec 2011, David Laight wrote:
> > In principle, the condition could be __LINUX_ARM_ARCH__ < 5, since the
> > bx instruction is guaranteed to be available on all ARMv5 CPUs and
> > later (ARMv5T is not required).
>
> Can't this code look at the actual cpu being used, and
> generate the relevant 'return' instruction?
> (Instead of trying to use some compile-time value.)
There is really no point doing so. We intend to ultimately have a
kernel that may support ARMv5 and lower, and another kernel to support
ARMv6 and ARMv7. So in a given context, either bx is always available
(ARMv6+) or never required (ARMv5-).
Nicolas
^ permalink raw reply
* Re: linux-next: Tree for Dec 22 (netdev/stmmac)
From: Randy Dunlap @ 2011-12-23 1:37 UTC (permalink / raw)
To: Stephen Rothwell; +Cc: linux-next, LKML, Netdev
In-Reply-To: <20111222172039.dc704e5bbfc3d91a844897b3@canb.auug.org.au>
On 12/21/2011 10:20 PM, Stephen Rothwell wrote:
> Hi all,
>
> This will probably be the last linux-next tree until the new year (unless
> I get exceedingly bored :-)).
goody :)
WARNING: modpost: missing MODULE_LICENSE() in drivers/net/ethernet/stmicro/stmmac/stmmac.o
see include/linux/module.h for more information
--
~Randy
*** Remember to use Documentation/SubmitChecklist when testing your code ***
^ permalink raw reply
* Re: netem: Gilbert, Simple Gilbert, Bernouli loss model broken
From: Stephen Hemminger @ 2011-12-23 1:10 UTC (permalink / raw)
To: Marcus Wermuth; +Cc: netdev
In-Reply-To: <CAFXUZ_G7oAT9v1B4NNm5c2nxUpU_-zXNV47XzcyKNKgsDLjQzA@mail.gmail.com>
On Tue, 8 Nov 2011 12:40:29 +0100
Marcus Wermuth <marcus.wermuth@gmail.com> wrote:
> Hey,
>
> I wanted to try the netem extension to setup a loss via Gilbert,
> Simple Gilbert, Bernouli loss model[1]. Kernel support is included
> since several releases. But configuration as demonstrated in [1] does
> not work at all. It seems that the userspace part in iproute is
> missing, the original patch from the authors does not work.
>
> Does anybody know about that?
>
> Bye, Marcus
>
> (I'm not subscribed to netdev-list)
>
> [1] http://netgroup.uniroma2.it/twiki/bin/view.cgi/Main/NetemCLG
I just wrote, tested and support for the loss model parameters
in iproute. Check the latest checkin in the git repo. Also the man
page has been fixed to reflect the implemented options.
^ permalink raw reply
* [PATCH v5] ARM: net: JIT compiler for packet filters
From: Mircea Gherzan @ 2011-12-23 0:53 UTC (permalink / raw)
To: linux-arm-kernel; +Cc: mgherzan, netdev, linux, eric.dumazet
Based of Matt Evans's PPC64 implementation.
The compiler generates ARM instructions but interworking is
supported for Thumb2 kernels.
Supports both little and big endian. Unaligned loads are emitted
for ARMv6+. Not all the BPF opcodes that deal with ancillary data
are supported. The scratch memory of the filter lives on the stack.
Hardware integer division is used if it is available.
Enabled in the same way as for x86-64 and PPC64:
echo 1 > /proc/sys/net/core/bpf_jit_enable
A value greater than 1 enables opcode output.
Signed-off-by: Mircea Gherzan <mgherzan@gmail.com>
---
Changes in v5:
* replace SEEN_LEN with SEEN_SKB
* set ctx->seen when handling some ancillary data opcodes
Changes in v4:
* first check if the JIT compiler is enabled
* fix the code generation for the LDX_MSH opcode
Changes in v3:
* no longer depend on EABI and !Thumb2
* add BLX "emulation" for ARMv4 without Thumb
* use the integer divide instruction on Cortex-A15
* fix the handling of the DIV_K opcode
* use a C wrapper for __aeabi_uidiv
* fix the generation of the epilogue (non-FP case)
Changes in v2:
* enable the compiler only for ARMv5+ because of the BLX instruction
* use the same comparison for the ARM version checks
* use misaligned accesses on ARMv6
* fix the SEEN_MEM
* fix the mem_words_used()
arch/arm/Kconfig | 1 +
arch/arm/Makefile | 1 +
arch/arm/net/Makefile | 3 +
arch/arm/net/bpf_jit_32.c | 888 +++++++++++++++++++++++++++++++++++++++++++++
arch/arm/net/bpf_jit_32.h | 180 +++++++++
5 files changed, 1073 insertions(+), 0 deletions(-)
create mode 100644 arch/arm/net/Makefile
create mode 100644 arch/arm/net/bpf_jit_32.c
create mode 100644 arch/arm/net/bpf_jit_32.h
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index abba5b8..0014b4b 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -30,6 +30,7 @@ config ARM
select HAVE_SPARSE_IRQ
select GENERIC_IRQ_SHOW
select CPU_PM if (SUSPEND || CPU_IDLE)
+ select HAVE_BPF_JIT
help
The ARM series is a line of low-power-consumption RISC chip designs
licensed by ARM Ltd and targeted at embedded applications and
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index dfcf3b0..8810a10 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -255,6 +255,7 @@ core-$(CONFIG_VFP) += arch/arm/vfp/
# If we have a machine-specific directory, then include it in the build.
core-y += arch/arm/kernel/ arch/arm/mm/ arch/arm/common/
+core-y += arch/arm/net/
core-y += $(machdirs) $(platdirs)
drivers-$(CONFIG_OPROFILE) += arch/arm/oprofile/
diff --git a/arch/arm/net/Makefile b/arch/arm/net/Makefile
new file mode 100644
index 0000000..c2c1084
--- /dev/null
+++ b/arch/arm/net/Makefile
@@ -0,0 +1,3 @@
+# ARM-specific networking code
+
+obj-$(CONFIG_BPF_JIT) += bpf_jit_32.o
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
new file mode 100644
index 0000000..b9bea0c
--- /dev/null
+++ b/arch/arm/net/bpf_jit_32.c
@@ -0,0 +1,888 @@
+/*
+ * Just-In-Time compiler for BPF filters on 32bit ARM
+ *
+ * Copyright (c) 2011 Mircea Gherzan <mgherzan@gmail.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/compiler.h>
+#include <linux/filter.h>
+#include <linux/moduleloader.h>
+#include <linux/netdevice.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <asm/cacheflush.h>
+#include <asm/hwcap.h>
+
+#include "bpf_jit_32.h"
+
+/*
+ * ABI:
+ *
+ * r0 scratch register
+ * r4 BPF register A
+ * r5 BPF register X
+ * r6 pointer to the skb
+ * r7 skb->data
+ * r8 skb_headlen(skb)
+ */
+
+#define r_scratch ARM_R0
+/* r1-r3 are (also) used for the unaligned loads on the non-ARMv7 slowpath */
+#define r_off ARM_R1
+#define r_A ARM_R4
+#define r_X ARM_R5
+#define r_skb ARM_R6
+#define r_skb_data ARM_R7
+#define r_skb_hl ARM_R8
+
+#define SCRATCH_SP_OFFSET 0
+#define SCRATCH_OFF(k) (SCRATCH_SP_OFFSET + (k))
+
+#define SEEN_MEM ((1 << BPF_MEMWORDS) - 1)
+#define SEEN_MEM_WORD(k) (1 << (k))
+#define SEEN_X (1 << BPF_MEMWORDS)
+#define SEEN_CALL (1 << (BPF_MEMWORDS + 1))
+#define SEEN_SKB (1 << (BPF_MEMWORDS + 2))
+#define SEEN_DATA (1 << (BPF_MEMWORDS + 3))
+
+struct jit_ctx {
+ const struct sk_filter *skf;
+ unsigned idx;
+ unsigned prologue_bytes;
+ int ret0_fp_idx;
+ u32 seen;
+ u32 *offsets;
+ u32 *target;
+#if __LINUX_ARM_ARCH__ < 7
+ u16 epilogue_bytes;
+ u16 imm_count;
+ u32 *imms;
+#endif
+};
+
+int bpf_jit_enable __read_mostly;
+
+static u8 jit_get_skb_b(struct sk_buff *skb, unsigned offset)
+{
+ u8 ret;
+ skb_copy_bits(skb, offset, &ret, 1);
+ return ret;
+}
+
+static u16 jit_get_skb_h(struct sk_buff *skb, unsigned offset)
+{
+ u16 ret;
+ skb_copy_bits(skb, offset, &ret, 2);
+ return ntohs(ret);
+}
+
+static u32 jit_get_skb_w(struct sk_buff *skb, unsigned offset)
+{
+ u32 ret;
+ skb_copy_bits(skb, offset, &ret, 4);
+ return ntohl(ret);
+}
+
+/*
+ * Wrapper that handles both OABI and EABI and assures Thumb2 interworking
+ * (where the assembly routines like __aeabi_uidiv could cause problems).
+ */
+static u32 jit_udiv(u32 dividend, u32 divisor)
+{
+ return dividend / divisor;
+}
+
+static inline void _emit(int cond, u32 inst, struct jit_ctx *ctx)
+{
+ if (ctx->target != NULL)
+ ctx->target[ctx->idx] = inst | (cond << 28);
+
+ ctx->idx++;
+}
+
+/*
+ * Emit an instruction that will be executed unconditionally.
+ */
+static inline void emit(u32 inst, struct jit_ctx *ctx)
+{
+ _emit(ARM_COND_AL, inst, ctx);
+}
+
+static u16 saved_regs(struct jit_ctx *ctx)
+{
+ u16 ret = 0;
+
+ if (ctx->skf->len > 1)
+ ret |= 1 << r_A;
+
+#ifdef CONFIG_FRAME_POINTER
+ ret |= (1 << ARM_FP) | (1 << ARM_IP) | (1 << ARM_LR) | (1 << ARM_PC);
+#else
+ if (ctx->seen & SEEN_CALL)
+ ret |= 1 << ARM_LR;
+#endif
+ if (ctx->seen & (SEEN_DATA | SEEN_SKB))
+ ret |= 1 << r_skb;
+ if (ctx->seen & SEEN_DATA)
+ ret |= (1 << r_skb_data) | (1 << r_skb_hl);
+ if (ctx->seen & SEEN_X)
+ ret |= 1 << r_X;
+
+ return ret;
+}
+
+static inline int mem_words_used(struct jit_ctx *ctx)
+{
+ u32 words = ctx->seen & SEEN_MEM;
+ /* yes, we do waste some stack space IF there are "holes" in the set" */
+ return 32 - __builtin_clz(words);
+}
+
+static inline bool is_load_to_a(u16 inst)
+{
+ switch (inst) {
+ case BPF_S_LD_W_LEN:
+ case BPF_S_LD_W_ABS:
+ case BPF_S_LD_H_ABS:
+ case BPF_S_LD_B_ABS:
+ case BPF_S_ANC_CPU:
+ case BPF_S_ANC_IFINDEX:
+ case BPF_S_ANC_MARK:
+ case BPF_S_ANC_PROTOCOL:
+ case BPF_S_ANC_RXHASH:
+ case BPF_S_ANC_QUEUE:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static void build_prologue(struct jit_ctx *ctx)
+{
+ u16 reg_set = saved_regs(ctx);
+ u16 first_inst = ctx->skf->insns[0].code;
+ u16 off;
+
+#ifdef CONFIG_FRAME_POINTER
+ emit(ARM_MOV_R(ARM_IP, ARM_SP), ctx);
+ emit(ARM_PUSH(reg_set), ctx);
+ emit(ARM_SUB_I(ARM_FP, ARM_IP, 4), ctx);
+#else
+ if (reg_set)
+ emit(ARM_PUSH(reg_set), ctx);
+#endif
+
+ if (ctx->seen & (SEEN_DATA | SEEN_SKB))
+ emit(ARM_MOV_R(r_skb, ARM_R0), ctx);
+
+ if (ctx->seen & SEEN_DATA) {
+ off = offsetof(struct sk_buff, data);
+ emit(ARM_LDR_I(r_skb_data, r_skb, off), ctx);
+ /* headlen = len - data_len */
+ off = offsetof(struct sk_buff, len);
+ emit(ARM_LDR_I(r_skb_hl, r_skb, off), ctx);
+ off = offsetof(struct sk_buff, data_len);
+ emit(ARM_LDR_I(r_scratch, r_skb, off), ctx);
+ emit(ARM_SUB_R(r_skb_hl, r_skb_hl, r_scratch), ctx);
+ }
+
+ if (ctx->seen & SEEN_X)
+ emit(ARM_MOV_I(r_X, 0), ctx);
+
+ /* do not leak kernel data to userspace */
+ if ((first_inst != BPF_S_RET_K) && !(is_load_to_a(first_inst)))
+ emit(ARM_MOV_I(r_A, 0), ctx);
+
+ /* stack space for the BPF_MEM words */
+ if (ctx->seen & SEEN_MEM)
+ emit(ARM_SUB_I(ARM_SP, ARM_SP, mem_words_used(ctx) * 4), ctx);
+}
+
+static void build_epilogue(struct jit_ctx *ctx)
+{
+ u16 reg_set = saved_regs(ctx);
+
+ if (ctx->seen & SEEN_MEM)
+ emit(ARM_ADD_I(ARM_SP, ARM_SP, mem_words_used(ctx) * 4), ctx);
+
+ reg_set &= ~(1 << ARM_LR);
+
+#ifdef CONFIG_FRAME_POINTER
+ /* the first instruction of the prologue was: mov ip, sp */
+ reg_set &= ~(1 << ARM_IP);
+ reg_set |= (1 << ARM_SP);
+ emit(ARM_LDM(ARM_SP, reg_set), ctx);
+#else
+ if (ctx->seen) {
+ if (ctx->seen & SEEN_CALL)
+ reg_set |= 1 << ARM_PC;
+ emit(ARM_POP(reg_set), ctx);
+ }
+
+ if (!(ctx->seen & SEEN_CALL))
+ emit(ARM_BX(ARM_LR), ctx);
+#endif
+}
+
+static int16_t imm8m(u32 x)
+{
+ u32 rot;
+
+ for (rot = 0; rot < 16; rot++)
+ if ((x & ~ror32(0xff, 2 * rot)) == 0)
+ return rol32(x, 2 * rot) | (rot << 8);
+
+ return -1;
+}
+
+#if __LINUX_ARM_ARCH__ < 7
+
+static u16 imm_offset(u32 k, struct jit_ctx *ctx)
+{
+ unsigned i = 0, offset;
+ u16 imm;
+
+ /* on the "fake" run we just count them (duplicates included) */
+ if (ctx->target == NULL) {
+ ctx->imm_count++;
+ return 0;
+ }
+
+ while ((i < ctx->imm_count) && ctx->imms[i]) {
+ if (ctx->imms[i] == k)
+ break;
+ i++;
+ }
+
+ if (ctx->imms[i] == 0)
+ ctx->imms[i] = k;
+
+ /* constants go just after the epilogue */
+ offset = ctx->offsets[ctx->skf->len];
+ offset += ctx->prologue_bytes;
+ offset += ctx->epilogue_bytes;
+ offset += i * 4;
+
+ ctx->target[offset / 4] = k;
+
+ /* PC in ARM mode == address of the instruction + 8 */
+ imm = offset - (8 + ctx->idx * 4);
+
+ return imm;
+}
+
+#endif /* __LINUX_ARM_ARCH__ */
+
+/*
+ * Move an immediate that's not an imm8m to a core register.
+ */
+static inline void emit_mov_i_no8m(int rd, u32 val, struct jit_ctx *ctx)
+{
+#if __LINUX_ARM_ARCH__ < 7
+ emit(ARM_LDR_I(rd, ARM_PC, imm_offset(val, ctx)), ctx);
+#else
+ emit(ARM_MOVW(rd, val & 0xffff), ctx);
+ if (val > 0xffff)
+ emit(ARM_MOVT(rd, val >> 16), ctx);
+#endif
+}
+
+static inline void emit_mov_i(int rd, u32 val, struct jit_ctx *ctx)
+{
+ int imm12 = imm8m(val);
+
+ if (imm12 >= 0)
+ emit(ARM_MOV_I(rd, imm12), ctx);
+ else
+ emit_mov_i_no8m(rd, val, ctx);
+}
+
+#if __LINUX_ARM_ARCH__ < 6
+
+static void emit_load_be32(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
+{
+ _emit(cond, ARM_LDRB_I(ARM_R3, r_addr, 1), ctx);
+ _emit(cond, ARM_LDRB_I(ARM_R1, r_addr, 0), ctx);
+ _emit(cond, ARM_LDRB_I(ARM_R2, r_addr, 3), ctx);
+ _emit(cond, ARM_LSL_I(ARM_R3, ARM_R3, 16), ctx);
+ _emit(cond, ARM_LDRB_I(ARM_R0, r_addr, 2), ctx);
+ _emit(cond, ARM_ORR_S(ARM_R3, ARM_R3, ARM_R1, SRTYPE_LSL, 24), ctx);
+ _emit(cond, ARM_ORR_R(ARM_R3, ARM_R3, ARM_R2), ctx);
+ _emit(cond, ARM_ORR_S(r_res, ARM_R3, ARM_R0, SRTYPE_LSL, 8), ctx);
+}
+
+static void emit_load_be16(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
+{
+ _emit(cond, ARM_LDRB_I(ARM_R1, r_addr, 0), ctx);
+ _emit(cond, ARM_LDRB_I(ARM_R2, r_addr, 1), ctx);
+ _emit(cond, ARM_ORR_S(r_res, ARM_R2, ARM_R1, SRTYPE_LSL, 8), ctx);
+}
+
+static inline void emit_swap16(u8 r_dst, u8 r_src, struct jit_ctx *ctx)
+{
+ emit(ARM_LSL_R(ARM_R1, r_src, 8), ctx);
+ emit(ARM_ORR_S(r_dst, ARM_R1, r_src, SRTYPE_LSL, 8), ctx);
+ emit(ARM_LSL_I(r_dst, r_dst, 8), ctx);
+ emit(ARM_LSL_R(r_dst, r_dst, 8), ctx);
+}
+
+#else /* ARMv6+ */
+
+static void emit_load_be32(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
+{
+ _emit(cond, ARM_LDR_I(r_res, r_addr, 0), ctx);
+#ifdef __LITTLE_ENDIAN
+ _emit(cond, ARM_REV(r_res, r_res), ctx);
+#endif
+}
+
+static void emit_load_be16(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
+{
+ _emit(cond, ARM_LDRH_I(r_res, r_addr, 0), ctx);
+#ifdef __LITTLE_ENDIAN
+ _emit(cond, ARM_REV16(r_res, r_res), ctx);
+#endif
+}
+
+static inline void emit_swap16(u8 r_dst __maybe_unused,
+ u8 r_src __maybe_unused,
+ struct jit_ctx *ctx __maybe_unused)
+{
+#ifdef __LITTLE_ENDIAN
+ emit(ARM_REV16(r_dst, r_src), ctx);
+#endif
+}
+
+#endif /* __LINUX_ARM_ARCH__ < 6 */
+
+
+/* Compute the immediate value for a PC-relative branch. */
+static inline u32 b_imm(unsigned tgt, struct jit_ctx *ctx)
+{
+ u32 imm;
+
+ if (ctx->target == NULL)
+ return 0;
+ /*
+ * BPF allows only forward jumps and the offset of the target is
+ * still the one computed during the first pass.
+ */
+ imm = ctx->offsets[tgt] + ctx->prologue_bytes - (ctx->idx * 4 + 8);
+
+ return imm >> 2;
+}
+
+#define OP_IMM3(op, r1, r2, imm_val, ctx) \
+ do { \
+ imm12 = imm8m(imm_val); \
+ if (imm12 < 0) { \
+ emit_mov_i_no8m(r_scratch, imm_val, ctx); \
+ emit(op ## _R((r1), (r2), r_scratch), ctx); \
+ } else { \
+ emit(op ## _I((r1), (r2), imm12), ctx); \
+ } \
+ } while (0)
+
+static inline void emit_err_ret(u8 cond, struct jit_ctx *ctx)
+{
+ if (ctx->ret0_fp_idx >= 0) {
+ _emit(cond, ARM_B(b_imm(ctx->ret0_fp_idx, ctx)), ctx);
+ /* NOP to keep the size constant between passes */
+ emit(ARM_MOV_R(ARM_R0, ARM_R0), ctx);
+ } else {
+ _emit(cond, ARM_MOV_I(ARM_R0, 0), ctx);
+ _emit(cond, ARM_B(b_imm(ctx->skf->len, ctx)), ctx);
+ }
+}
+
+static inline void emit_blx_r(u8 tgt_reg, struct jit_ctx *ctx)
+{
+#if __LINUX_ARM_ARCH__ < 5
+ emit(ARM_MOV_R(ARM_LR, ARM_PC), ctx);
+
+ if (elf_hwcap & HWCAP_THUMB)
+ emit(ARM_BX(tgt_reg), ctx);
+ else
+ emit(ARM_MOV_R(ARM_PC, tgt_reg), ctx);
+#else
+ emit(ARM_BLX_R(tgt_reg), ctx);
+#endif
+}
+
+static inline void emit_udiv(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx)
+{
+#if __LINUX_ARM_ARCH__ == 7
+ if (elf_hwcap & HWCAP_IDIVA) {
+ emit(ARM_UDIV(rd, rm, rn), ctx);
+ return;
+ }
+#endif
+ if (rm != ARM_R0)
+ emit(ARM_MOV_R(ARM_R0, rm), ctx);
+ if (rn != ARM_R1)
+ emit(ARM_MOV_R(ARM_R1, rn), ctx);
+
+ ctx->seen |= SEEN_CALL;
+ emit_mov_i(ARM_R3, (u32)jit_udiv, ctx);
+ emit_blx_r(ARM_R3, ctx);
+
+ if (rd != ARM_R0)
+ emit(ARM_MOV_R(rd, ARM_R0), ctx);
+}
+
+static int build_body(struct jit_ctx *ctx)
+{
+ void *load_func[] = {jit_get_skb_b, jit_get_skb_h, jit_get_skb_w};
+ const struct sk_filter *prog = ctx->skf;
+ const struct sock_filter *inst;
+ unsigned i, load_order, off, condt, condf;
+ int imm12;
+ u32 k;
+
+ for (i = 0; i < prog->len; i++) {
+ inst = &(prog->insns[i]);
+ /* K as an immediate value operand */
+ k = inst->k;
+
+ /* compute offsets only in the fake pass */
+ if (ctx->target == NULL)
+ ctx->offsets[i] = ctx->idx * 4;
+
+ switch (inst->code) {
+ case BPF_S_LD_IMM:
+ emit_mov_i(r_A, k, ctx);
+ break;
+ case BPF_S_LD_W_LEN:
+ ctx->seen |= SEEN_SKB;
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4);
+ emit(ARM_LDR_I(r_A, r_skb,
+ offsetof(struct sk_buff, len)), ctx);
+ break;
+ case BPF_S_LD_MEM:
+ /* A = scratch[k] */
+ ctx->seen |= SEEN_MEM_WORD(k);
+ emit(ARM_LDR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx);
+ break;
+ case BPF_S_LD_W_ABS:
+ load_order = 2;
+ goto load;
+ case BPF_S_LD_H_ABS:
+ load_order = 1;
+ goto load;
+ case BPF_S_LD_B_ABS:
+ load_order = 0;
+load:
+ emit_mov_i(r_off, k, ctx);
+load_common:
+ ctx->seen |= SEEN_DATA | SEEN_CALL;
+
+ if (load_order > 0) {
+ emit(ARM_SUB_I(r_scratch, r_skb_hl,
+ 1 << load_order), ctx);
+ emit(ARM_CMP_R(r_scratch, r_off), ctx);
+ condt = ARM_COND_HS;
+ } else {
+ emit(ARM_CMP_R(r_skb_hl, r_off), ctx);
+ condt = ARM_COND_HI;
+ }
+
+ _emit(condt, ARM_ADD_R(r_scratch, r_off, r_skb_data),
+ ctx);
+
+ if (load_order == 0)
+ _emit(condt, ARM_LDRB_I(r_A, r_scratch, 0),
+ ctx);
+ else if (load_order == 1)
+ emit_load_be16(condt, r_A, r_scratch, ctx);
+ else if (load_order == 2)
+ emit_load_be32(condt, r_A, r_scratch, ctx);
+
+ _emit(condt, ARM_B(b_imm(i + 1, ctx)), ctx);
+
+ /* the slowpath */
+ emit_mov_i(ARM_R3, (u32)load_func[load_order], ctx);
+ emit(ARM_MOV_R(ARM_R0, r_skb), ctx);
+ /* the offset is already in R1 */
+ emit_blx_r(ARM_R3, ctx);
+ emit(ARM_MOV_R(r_A, ARM_R0), ctx);
+ break;
+ case BPF_S_LD_W_IND:
+ load_order = 2;
+ goto load_ind;
+ case BPF_S_LD_H_IND:
+ load_order = 1;
+ goto load_ind;
+ case BPF_S_LD_B_IND:
+ load_order = 0;
+load_ind:
+ OP_IMM3(ARM_ADD, r_off, r_X, k, ctx);
+ goto load_common;
+ case BPF_S_LDX_IMM:
+ ctx->seen |= SEEN_X;
+ emit_mov_i(r_X, k, ctx);
+ break;
+ case BPF_S_LDX_W_LEN:
+ ctx->seen |= SEEN_X | SEEN_SKB;
+ emit(ARM_LDR_I(r_X, r_skb,
+ offsetof(struct sk_buff, len)), ctx);
+ break;
+ case BPF_S_LDX_MEM:
+ ctx->seen |= SEEN_X | SEEN_MEM_WORD(k);
+ emit(ARM_LDR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx);
+ break;
+ case BPF_S_LDX_B_MSH:
+ /* x = ((*(frame + k)) & 0xf) << 2; */
+ ctx->seen |= SEEN_X | SEEN_DATA | SEEN_CALL;
+ /* offset in r1: we might have to take the slow path */
+ emit_mov_i(r_off, k, ctx);
+ emit(ARM_CMP_R(r_skb_hl, r_off), ctx);
+
+ /* load in r0: common with the slowpath */
+ _emit(ARM_COND_HI, ARM_LDRB_R(ARM_R0, r_skb_data,
+ ARM_R1), ctx);
+ /*
+ * emit_mov_i() might generate one or two instructions,
+ * the same holds for emit_blx_r()
+ */
+ _emit(ARM_COND_HI, ARM_B(b_imm(i + 1, ctx) - 2), ctx);
+
+ emit(ARM_MOV_R(ARM_R0, r_skb), ctx);
+ /* r_off is r1 */
+ emit_mov_i(ARM_R3, (u32)jit_get_skb_b, ctx);
+ emit_blx_r(ARM_R3, ctx);
+
+ emit(ARM_ORR_I(r_X, ARM_R0, 0x00f), ctx);
+ emit(ARM_LSL_I(r_X, r_X, 2), ctx);
+ break;
+ case BPF_S_ST:
+ ctx->seen |= SEEN_MEM_WORD(k);
+ emit(ARM_STR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx);
+ break;
+ case BPF_S_STX:
+ ctx->seen |= SEEN_MEM_WORD(k) | SEEN_X;
+ emit(ARM_STR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx);
+ break;
+ case BPF_S_ALU_ADD_K:
+ /* A += K */
+ OP_IMM3(ARM_ADD, r_A, r_A, k, ctx);
+ break;
+ case BPF_S_ALU_ADD_X:
+ ctx->seen |= SEEN_X;
+ emit(ARM_ADD_R(r_A, r_A, r_X), ctx);
+ break;
+ case BPF_S_ALU_SUB_K:
+ /* A -= K */
+ OP_IMM3(ARM_SUB, r_A, r_A, k, ctx);
+ break;
+ case BPF_S_ALU_SUB_X:
+ ctx->seen |= SEEN_X;
+ emit(ARM_SUB_R(r_A, r_A, r_X), ctx);
+ break;
+ case BPF_S_ALU_MUL_K:
+ /* A *= K */
+ emit_mov_i(r_scratch, k, ctx);
+ emit(ARM_MUL(r_A, r_A, r_scratch), ctx);
+ break;
+ case BPF_S_ALU_MUL_X:
+ ctx->seen |= SEEN_X;
+ emit(ARM_MUL(r_A, r_A, r_X), ctx);
+ break;
+ case BPF_S_ALU_DIV_K:
+ /* current k == reciprocal_value(userspace k) */
+ emit_mov_i(r_scratch, k, ctx);
+ /* A = top 32 bits of the product */
+ emit(ARM_UMULL(r_scratch, r_A, r_A, r_scratch), ctx);
+ break;
+ case BPF_S_ALU_DIV_X:
+ ctx->seen |= SEEN_X;
+ emit(ARM_CMP_I(r_X, 0), ctx);
+ emit_err_ret(ARM_COND_EQ, ctx);
+ emit_udiv(r_A, r_A, r_X, ctx);
+ break;
+ case BPF_S_ALU_OR_K:
+ /* A |= K */
+ OP_IMM3(ARM_ORR, r_A, r_A, k, ctx);
+ break;
+ case BPF_S_ALU_OR_X:
+ ctx->seen |= SEEN_X;
+ emit(ARM_ORR_I(r_A, r_A, r_X), ctx);
+ break;
+ case BPF_S_ALU_AND_K:
+ /* A &= K */
+ OP_IMM3(ARM_AND, r_A, r_A, k, ctx);
+ break;
+ case BPF_S_ALU_AND_X:
+ ctx->seen |= SEEN_X;
+ emit(ARM_AND_R(r_A, r_A, r_X), ctx);
+ break;
+ case BPF_S_ALU_LSH_K:
+ if (unlikely(k > 31))
+ return -1;
+ emit(ARM_LSL_I(r_A, r_A, k), ctx);
+ break;
+ case BPF_S_ALU_LSH_X:
+ ctx->seen |= SEEN_X;
+ emit(ARM_LSL_R(r_A, r_A, r_X), ctx);
+ break;
+ case BPF_S_ALU_RSH_K:
+ if (unlikely(k > 31))
+ return -1;
+ emit(ARM_LSR_I(r_A, r_A, k), ctx);
+ break;
+ case BPF_S_ALU_RSH_X:
+ ctx->seen |= SEEN_X;
+ emit(ARM_LSR_R(r_A, r_A, r_X), ctx);
+ break;
+ case BPF_S_JMP_JA:
+ /* pc += K */
+ emit(ARM_B(b_imm(i + k, ctx)), ctx);
+ break;
+ case BPF_S_JMP_JEQ_K:
+ /* pc += (A == K) ? pc->jt : pc->jf */
+ condt = ARM_COND_EQ;
+ condf = ARM_COND_NE;
+ goto cmp_imm;
+ case BPF_S_JMP_JGT_K:
+ /* pc += (A > K) ? pc->jt : pc->jf */
+ condt = ARM_COND_HI;
+ condf = ARM_COND_LS;
+ goto cmp_imm;
+ case BPF_S_JMP_JGE_K:
+ /* pc += (A >= K) ? pc->jt : pc->jf */
+ condt = ARM_COND_HI;
+ condf = ARM_COND_LS;
+ /* (x >= y) IFF (x > y - 1) */
+ if (unlikely(k == 0))
+ return -1;
+ k--;
+cmp_imm:
+ imm12 = imm8m(k);
+ if (imm12 < 0) {
+ emit_mov_i_no8m(r_scratch, k, ctx);
+ emit(ARM_CMP_R(r_A, r_scratch), ctx);
+ } else {
+ emit(ARM_CMP_I(r_A, imm12), ctx);
+ }
+cond_jump:
+ if (inst->jt)
+ _emit(condt, ARM_B(b_imm(i + inst->jt + 1,
+ ctx)), ctx);
+ if (inst->jf)
+ _emit(condf, ARM_B(b_imm(i + inst->jf + 1,
+ ctx)), ctx);
+ break;
+ case BPF_S_JMP_JEQ_X:
+ /* pc += (A == X) ? pc->jt : pc->jf */
+ condt = ARM_COND_EQ;
+ condf = ARM_COND_NE;
+ goto cmp_x;
+ case BPF_S_JMP_JGT_X:
+ /* pc += (A > X) ? pc->jt : pc->jf */
+ condt = ARM_COND_HI;
+ condf = ARM_COND_LS;
+ goto cmp_x;
+ case BPF_S_JMP_JGE_X:
+ /* pc += (A >= X) ? pc->jt : pc->jf */
+ condt = ARM_COND_CS;
+ condf = ARM_COND_CC;
+cmp_x:
+ ctx->seen |= SEEN_X;
+ emit(ARM_CMP_R(r_A, r_X), ctx);
+ goto cond_jump;
+ case BPF_S_JMP_JSET_K:
+ /* pc += (A & K) ? pc->jt : pc->jf */
+ condt = ARM_COND_NE;
+ /* not set iff all zeroes iff Z==1 iff EQ */
+ condf = ARM_COND_EQ;
+
+ imm12 = imm8m(k);
+ if (imm12 < 0) {
+ emit_mov_i_no8m(r_scratch, k, ctx);
+ emit(ARM_TST_R(r_A, r_scratch), ctx);
+ } else {
+ emit(ARM_TST_I(r_A, imm12), ctx);
+ }
+ goto cond_jump;
+ case BPF_S_JMP_JSET_X:
+ /* pc += (A & X) ? pc->jt : pc->jf */
+ condt = ARM_COND_NE;
+ condf = ARM_COND_EQ;
+ emit(ARM_TST_R(r_A, r_X), ctx);
+ goto cond_jump;
+ case BPF_S_RET_A:
+ emit(ARM_MOV_R(ARM_R0, r_A), ctx);
+ goto b_epilogue;
+ case BPF_S_RET_K:
+ if ((k == 0) && (ctx->ret0_fp_idx < 0))
+ ctx->ret0_fp_idx = i;
+ emit_mov_i(ARM_R0, k, ctx);
+b_epilogue:
+ if (i != ctx->skf->len - 1)
+ emit(ARM_B(b_imm(prog->len, ctx)), ctx);
+ break;
+ case BPF_S_MISC_TAX:
+ /* X = A */
+ emit(ARM_MOV_R(r_X, r_A), ctx);
+ break;
+ case BPF_S_MISC_TXA:
+ /* A = X */
+ emit(ARM_MOV_R(r_A, r_X), ctx);
+ break;
+ case BPF_S_ANC_PROTOCOL:
+ /* A = ntohs(skb->protocol) */
+ ctx->seen |= SEEN_SKB;
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
+ protocol) != 2);
+ off = offsetof(struct sk_buff, protocol);
+ emit(ARM_LDRH_I(r_scratch, r_skb, off), ctx);
+ emit_swap16(r_A, r_scratch, ctx);
+ break;
+ case BPF_S_ANC_CPU:
+ /* A = current_thread_info()->cpu */
+ emit_mov_i(r_scratch, (~(THREAD_SIZE - 1)), ctx);
+ emit(ARM_ADD_R(r_scratch, ARM_SP, r_scratch), ctx);
+
+ BUILD_BUG_ON(FIELD_SIZEOF(struct thread_info, cpu) != 4);
+ off = offsetof(struct thread_info, cpu);
+ emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
+ break;
+ case BPF_S_ANC_IFINDEX:
+ /* A = skb->dev->ifindex */
+ ctx->seen |= SEEN_SKB;
+ off = offsetof(struct sk_buff, dev);
+ emit(ARM_LDR_I(r_scratch, r_skb, off), ctx);
+
+ emit(ARM_CMP_I(r_scratch, 0), ctx);
+ emit_err_ret(ARM_COND_EQ, ctx);
+
+ BUILD_BUG_ON(FIELD_SIZEOF(struct net_device,
+ ifindex) != 4);
+ off = offsetof(struct net_device, ifindex);
+ emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
+ break;
+ case BPF_S_ANC_MARK:
+ ctx->seen |= SEEN_SKB;
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
+ off = offsetof(struct sk_buff, mark);
+ emit(ARM_LDR_I(r_A, r_skb, off), ctx);
+ break;
+ case BPF_S_ANC_RXHASH:
+ ctx->seen |= SEEN_SKB;
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, rxhash) != 4);
+ off = offsetof(struct sk_buff, rxhash);
+ emit(ARM_LDR_I(r_A, r_skb, off), ctx);
+ break;
+ case BPF_S_ANC_QUEUE:
+ ctx->seen |= SEEN_SKB;
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
+ queue_mapping) != 2);
+ BUILD_BUG_ON(offsetof(struct sk_buff,
+ queue_mapping) > 0xff);
+ off = offsetof(struct sk_buff, queue_mapping);
+ emit(ARM_LDRH_I(r_A, r_skb, off), ctx);
+ break;
+ default:
+ return -1;
+ }
+ }
+
+ /* compute offsets only during the first pass */
+ if (ctx->target == NULL)
+ ctx->offsets[i] = ctx->idx * 4;
+
+ return 0;
+}
+
+
+void bpf_jit_compile(struct sk_filter *fp)
+{
+ struct jit_ctx ctx;
+ unsigned tmp_idx;
+ unsigned alloc_size;
+
+ if (!bpf_jit_enable)
+ return;
+
+ memset(&ctx, 0, sizeof(ctx));
+ ctx.skf = fp;
+ ctx.ret0_fp_idx = -1;
+
+ ctx.offsets = kzalloc(GFP_KERNEL, 4 * (ctx.skf->len + 1));
+ if (ctx.offsets == NULL)
+ return;
+
+ /* fake pass to fill in the ctx->seen */
+ if (unlikely(build_body(&ctx)))
+ goto out;
+
+ tmp_idx = ctx.idx;
+ build_prologue(&ctx);
+ ctx.prologue_bytes = (ctx.idx - tmp_idx) * 4;
+
+#if __LINUX_ARM_ARCH__ < 7
+ tmp_idx = ctx.idx;
+ build_epilogue(&ctx);
+ ctx.epilogue_bytes = (ctx.idx - tmp_idx) * 4;
+
+ ctx.idx += ctx.imm_count;
+ if (ctx.imm_count) {
+ ctx.imms = kzalloc(GFP_KERNEL, 4 * ctx.imm_count);
+ if (ctx.imms == NULL)
+ goto out;
+ }
+#else
+ /* there's nothing after the epilogue on ARMv7 */
+ build_epilogue(&ctx);
+#endif
+
+ alloc_size = 4 * ctx.idx;
+ ctx.target = module_alloc(alloc_size > sizeof(struct work_struct) ?
+ alloc_size : sizeof(struct work_struct));
+ if (unlikely(ctx.target == NULL))
+ goto out;
+
+ ctx.idx = 0;
+ build_prologue(&ctx);
+ build_body(&ctx);
+ build_epilogue(&ctx);
+
+ flush_icache_range((u32)ctx.target, (u32)(ctx.target + ctx.idx));
+
+#if __LINUX_ARM_ARCH__ < 7
+ if (ctx.imm_count)
+ kfree(ctx.imms);
+#endif
+
+ if (bpf_jit_enable > 1)
+ print_hex_dump(KERN_INFO, "BPF JIT code: ",
+ DUMP_PREFIX_ADDRESS, 16, 4, ctx.target,
+ alloc_size, false);
+
+ fp->bpf_func = (void *)ctx.target;
+out:
+ kfree(ctx.offsets);
+ return;
+}
+
+static void bpf_jit_free_worker(struct work_struct *work)
+{
+ module_free(NULL, work);
+}
+
+void bpf_jit_free(struct sk_filter *fp)
+{
+ struct work_struct *work;
+
+ if (fp->bpf_func != sk_run_filter) {
+ work = (struct work_struct *)fp->bpf_func;
+
+ INIT_WORK(work, bpf_jit_free_worker);
+ schedule_work(work);
+ }
+}
+
diff --git a/arch/arm/net/bpf_jit_32.h b/arch/arm/net/bpf_jit_32.h
new file mode 100644
index 0000000..d55f3f3
--- /dev/null
+++ b/arch/arm/net/bpf_jit_32.h
@@ -0,0 +1,180 @@
+/*
+ * Just-In-Time compiler for BPF filters on 32bit ARM
+ *
+ * Copyright (c) 2011 Mircea Gherzan <mgherzan@gmail.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.
+ */
+
+#ifndef PFILTER_OPCODES_ARM_H
+#define PFILTER_OPCODES_ARM_H
+
+#define ARM_R0 0
+#define ARM_R1 1
+#define ARM_R2 2
+#define ARM_R3 3
+#define ARM_R4 4
+#define ARM_R5 5
+#define ARM_R6 6
+#define ARM_R7 7
+#define ARM_R8 8
+#define ARM_R9 9
+#define ARM_R10 10
+#define ARM_FP 11
+#define ARM_IP 12
+#define ARM_SP 13
+#define ARM_LR 14
+#define ARM_PC 15
+
+#define ARM_COND_EQ 0x0
+#define ARM_COND_NE 0x1
+#define ARM_COND_CS 0x2
+#define ARM_COND_HS ARM_COND_CS
+#define ARM_COND_CC 0x3
+#define ARM_COND_LO ARM_COND_CC
+#define ARM_COND_MI 0x4
+#define ARM_COND_PL 0x5
+#define ARM_COND_VS 0x6
+#define ARM_COND_VC 0x7
+#define ARM_COND_HI 0x8
+#define ARM_COND_LS 0x9
+#define ARM_COND_GE 0xa
+#define ARM_COND_LT 0xb
+#define ARM_COND_GT 0xc
+#define ARM_COND_LE 0xd
+#define ARM_COND_AL 0xe
+
+/* register shift types */
+#define SRTYPE_LSL 0
+#define SRTYPE_LSR 1
+#define SRTYPE_ASR 2
+#define SRTYPE_ROR 3
+
+#define ARM_INST_ADD_R 0x00800000
+#define ARM_INST_ADD_I 0x02800000
+
+#define ARM_INST_AND_R 0x00000000
+#define ARM_INST_AND_I 0x02000000
+
+#define ARM_INST_B 0x0a000000
+#define ARM_INST_BX 0x012FFF10
+#define ARM_INST_BLX_R 0x012fff30
+
+#define ARM_INST_CMP_R 0x01500000
+#define ARM_INST_CMP_I 0x03500000
+
+#define ARM_INST_LDRB_I 0x05d00000
+#define ARM_INST_LDRB_R 0x07d00000
+#define ARM_INST_LDRH_I 0x01d000b0
+#define ARM_INST_LDR_I 0x05900000
+
+#define ARM_INST_LDM 0x08900000
+
+#define ARM_INST_LSL_I 0x01a00000
+#define ARM_INST_LSL_R 0x01a00010
+
+#define ARM_INST_LSR_I 0x01a00020
+#define ARM_INST_LSR_R 0x01a00030
+
+#define ARM_INST_MOV_R 0x01a00000
+#define ARM_INST_MOV_I 0x03a00000
+#define ARM_INST_MOVW 0x03000000
+#define ARM_INST_MOVT 0x03400000
+
+#define ARM_INST_MUL 0x00000090
+
+#define ARM_INST_POP 0x08bd0000
+#define ARM_INST_PUSH 0x092d0000
+
+#define ARM_INST_REV 0x06bf0f30
+#define ARM_INST_REV16 0x06bf0fb0
+
+#define ARM_INST_ORR_R 0x01800000
+#define ARM_INST_ORR_I 0x03800000
+
+#define ARM_INST_SUB_R 0x00400000
+#define ARM_INST_SUB_I 0x02400000
+
+#define ARM_INST_STR_I 0x05800000
+
+#define ARM_INST_TST_R 0x01100000
+#define ARM_INST_TST_I 0x03100000
+
+#define ARM_INST_UDIV 0x0730f010
+
+#define ARM_INST_UMULL 0x00800090
+
+/* register */
+#define _AL3_R(op, rd, rn, rm) ((op ## _R) | (rd) << 12 | (rn) << 16 | (rm))
+/* immediate */
+#define _AL3_I(op, rd, rn, imm) ((op ## _I) | (rd) << 12 | (rn) << 16 | (imm))
+
+#define ARM_ADD_R(rd, rn, rm) _AL3_R(ARM_INST_ADD, rd, rn, rm)
+#define ARM_ADD_I(rd, rn, imm) _AL3_I(ARM_INST_ADD, rd, rn, imm)
+
+#define ARM_AND_R(rd, rn, rm) _AL3_R(ARM_INST_AND, rd, rn, rm)
+#define ARM_AND_I(rd, rn, imm) _AL3_I(ARM_INST_AND, rd, rn, imm)
+
+#define ARM_B(imm24) (ARM_INST_B | (imm24))
+#define ARM_BX(rm) (ARM_INST_BX | (rm))
+#define ARM_BLX_R(rm) (ARM_INST_BLX_R | (rm))
+
+#define ARM_CMP_R(rn, rm) _AL3_R(ARM_INST_CMP, 0, rn, rm)
+#define ARM_CMP_I(rn, imm) _AL3_I(ARM_INST_CMP, 0, rn, imm)
+
+#define ARM_LDR_I(rt, rn, off) (ARM_INST_LDR_I | (rt) << 12 | (rn) << 16 \
+ | (off))
+#define ARM_LDRB_I(rt, rn, off) (ARM_INST_LDRB_I | (rt) << 12 | (rn) << 16 \
+ | (off))
+#define ARM_LDRB_R(rt, rn, rm) (ARM_INST_LDRB_R | (rt) << 12 | (rn) << 16 \
+ | (rm))
+#define ARM_LDRH_I(rt, rn, off) (ARM_INST_LDRH_I | (rt) << 12 | (rn) << 16 \
+ | (((off) & 0xf0) << 4) | ((off) & 0xf))
+
+#define ARM_LDM(rn, regs) (ARM_INST_LDM | (rn) << 16 | (regs))
+
+#define ARM_LSL_R(rd, rn, rm) (_AL3_R(ARM_INST_LSL, rd, 0, rn) | (rm) << 8)
+#define ARM_LSL_I(rd, rn, imm) (_AL3_R(ARM_INST_LSL, rd, 0, rn) | (imm) << 7)
+
+#define ARM_LSR_R(rd, rn, rm) (_AL3_R(ARM_INST_LSR, rd, 0, rn) | (rm) << 8)
+#define ARM_LSR_I(rd, rn, imm) (_AL3_R(ARM_INST_LSR, rd, 0, rn) | (imm) << 7)
+
+#define ARM_MOV_R(rd, rm) _AL3_R(ARM_INST_MOV, rd, 0, rm)
+#define ARM_MOV_I(rd, imm) _AL3_I(ARM_INST_MOV, rd, 0, imm)
+
+#define ARM_MOVW(rd, imm) \
+ (ARM_INST_MOVW | ((imm) >> 12) << 16 | (rd) << 12 | ((imm) & 0x0fff))
+
+#define ARM_MOVT(rd, imm) \
+ (ARM_INST_MOVT | ((imm) >> 12) << 16 | (rd) << 12 | ((imm) & 0x0fff))
+
+#define ARM_MUL(rd, rm, rn) (ARM_INST_MUL | (rd) << 16 | (rm) << 8 | (rn))
+
+#define ARM_POP(regs) (ARM_INST_POP | (regs))
+#define ARM_PUSH(regs) (ARM_INST_PUSH | (regs))
+
+#define ARM_ORR_R(rd, rn, rm) _AL3_R(ARM_INST_ORR, rd, rn, rm)
+#define ARM_ORR_I(rd, rn, imm) _AL3_I(ARM_INST_ORR, rd, rn, imm)
+#define ARM_ORR_S(rd, rn, rm, type, rs) \
+ (ARM_ORR_R(rd, rn, rm) | (type) << 5 | (rs) << 7)
+
+#define ARM_REV(rd, rm) (ARM_INST_REV | (rd) << 12 | (rm))
+#define ARM_REV16(rd, rm) (ARM_INST_REV16 | (rd) << 12 | (rm))
+
+#define ARM_SUB_R(rd, rn, rm) _AL3_R(ARM_INST_SUB, rd, rn, rm)
+#define ARM_SUB_I(rd, rn, imm) _AL3_I(ARM_INST_SUB, rd, rn, imm)
+
+#define ARM_STR_I(rt, rn, off) (ARM_INST_STR_I | (rt) << 12 | (rn) << 16 \
+ | (off))
+
+#define ARM_TST_R(rn, rm) _AL3_R(ARM_INST_TST, 0, rn, rm)
+#define ARM_TST_I(rn, imm) _AL3_I(ARM_INST_TST, 0, rn, imm)
+
+#define ARM_UDIV(rd, rn, rm) (ARM_INST_UDIV | (rd) << 16 | (rn) | (rm) << 8)
+
+#define ARM_UMULL(rd_lo, rd_hi, rn, rm) (ARM_INST_UMULL | (rd_hi) << 16 \
+ | (rd_lo) << 12 | (rm) << 8 | rn)
+
+#endif /* PFILTER_OPCODES_ARM_H */
--
1.7.7.3
^ permalink raw reply related
* Re: [RFC] iproute2: split up ip man page?
From: Stephen Hemminger @ 2011-12-23 0:29 UTC (permalink / raw)
To: Hagen Paul Pfeifer; +Cc: netdev
In-Reply-To: <20111223001003.GD4767@hell>
On Fri, 23 Dec 2011 01:10:03 +0100
Hagen Paul Pfeifer <hagen@jauu.net> wrote:
> * Stephen Hemminger | 2011-12-22 10:37:23 [-0800]:
>
> >Ok, the ip man page is now broken up. I tried to fix some of the
> >incorrect grammar and usage as well. The pages still need editing for
> >readability.
>
> Great! Commit 1b1177ed5f3 synched kernel headers. Should I rebase my iproute
> netem rate patch (and again update include/linux/pkt_sched.h for net-next) or
> keep you aware of this?
>
> Hagen
I am fixing netem loss stuff now. Fixing broken gimodel.
After 3.2 is released, the will merge in support for 3.3 features.
^ permalink raw reply
* [PATCH 2/2] bna: Add debugfs interface.
From: kgudipat @ 2011-12-22 23:30 UTC (permalink / raw)
To: davem, netdev; +Cc: adapter_linux_open_src_team, kgudipat, rmody
From: Krishna Gudipati <kgudipat@brocade.com>
Change details:
- Add debugfs support to obtain firmware trace, saved firmware trace on
an IOC crash, driver info and read/write to registers.
- debugfs hierarchy:
bna/pci_dev:<pci_name>
where the pci_name corresponds to the one under /sys/bus/pci/drivers/bna
- Following are the new debugfs entries added:
fwtrc: collect current firmware trace.
fwsave: collect last saved fw trace as a result of firmware crash.
regwr: write one word to chip register
regrd: read one or more words from chip register.
drvinfo: collect the driver information.
Signed-off-by: Krishna Gudipati <kgudipat@brocade.com>
---
drivers/net/ethernet/brocade/bna/Makefile | 2 +-
drivers/net/ethernet/brocade/bna/bfa_cee.c | 35 ++
drivers/net/ethernet/brocade/bna/bfa_cee.h | 4 +-
drivers/net/ethernet/brocade/bna/bfa_ioc.c | 121 +++++
drivers/net/ethernet/brocade/bna/bfa_ioc.h | 6 +
drivers/net/ethernet/brocade/bna/bfi.h | 2 +
drivers/net/ethernet/brocade/bna/bna_enet.c | 5 +-
drivers/net/ethernet/brocade/bna/bnad.c | 15 +
drivers/net/ethernet/brocade/bna/bnad.h | 18 +
drivers/net/ethernet/brocade/bna/bnad_debugfs.c | 623 +++++++++++++++++++++++
10 files changed, 827 insertions(+), 4 deletions(-)
create mode 100644 drivers/net/ethernet/brocade/bna/bnad_debugfs.c
diff --git a/drivers/net/ethernet/brocade/bna/Makefile b/drivers/net/ethernet/brocade/bna/Makefile
index 74d3abc..6027302 100644
--- a/drivers/net/ethernet/brocade/bna/Makefile
+++ b/drivers/net/ethernet/brocade/bna/Makefile
@@ -5,7 +5,7 @@
obj-$(CONFIG_BNA) += bna.o
-bna-objs := bnad.o bnad_ethtool.o bna_enet.o bna_tx_rx.o
+bna-objs := bnad.o bnad_ethtool.o bnad_debugfs.o bna_enet.o bna_tx_rx.o
bna-objs += bfa_msgq.o bfa_ioc.o bfa_ioc_ct.o bfa_cee.o
bna-objs += cna_fwimg.o
diff --git a/drivers/net/ethernet/brocade/bna/bfa_cee.c b/drivers/net/ethernet/brocade/bna/bfa_cee.c
index 8e62718..29f284f 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_cee.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_cee.c
@@ -185,6 +185,41 @@ bfa_nw_cee_mem_claim(struct bfa_cee *cee, u8 *dma_kva, u64 dma_pa)
}
/**
+ * bfa_cee_get_attr()
+ *
+ * @brief Send the request to the f/w to fetch CEE attributes.
+ *
+ * @param[in] Pointer to the CEE module data structure.
+ *
+ * @return Status
+ */
+enum bfa_status
+bfa_nw_cee_get_attr(struct bfa_cee *cee, struct bfa_cee_attr *attr,
+ bfa_cee_get_attr_cbfn_t cbfn, void *cbarg)
+{
+ struct bfi_cee_get_req *cmd;
+
+ BUG_ON(!((cee != NULL) && (cee->ioc != NULL)));
+ if (!bfa_nw_ioc_is_operational(cee->ioc))
+ return BFA_STATUS_IOC_FAILURE;
+
+ if (cee->get_attr_pending == true)
+ return BFA_STATUS_DEVBUSY;
+
+ cee->get_attr_pending = true;
+ cmd = (struct bfi_cee_get_req *) cee->get_cfg_mb.msg;
+ cee->attr = attr;
+ cee->cbfn.get_attr_cbfn = cbfn;
+ cee->cbfn.get_attr_cbarg = cbarg;
+ bfi_h2i_set(cmd->mh, BFI_MC_CEE, BFI_CEE_H2I_GET_CFG_REQ,
+ bfa_ioc_portid(cee->ioc));
+ bfa_dma_be_addr_set(cmd->dma_addr, cee->attr_dma.pa);
+ bfa_nw_ioc_mbox_queue(cee->ioc, &cee->get_cfg_mb, NULL, NULL);
+
+ return BFA_STATUS_OK;
+}
+
+/**
* bfa_cee_isrs()
*
* @brief Handles Mail-box interrupts for CEE module.
diff --git a/drivers/net/ethernet/brocade/bna/bfa_cee.h b/drivers/net/ethernet/brocade/bna/bfa_cee.h
index 58d54e9..93fde63 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_cee.h
+++ b/drivers/net/ethernet/brocade/bna/bfa_cee.h
@@ -59,5 +59,7 @@ u32 bfa_nw_cee_meminfo(void);
void bfa_nw_cee_mem_claim(struct bfa_cee *cee, u8 *dma_kva,
u64 dma_pa);
void bfa_nw_cee_attach(struct bfa_cee *cee, struct bfa_ioc *ioc, void *dev);
-
+enum bfa_status bfa_nw_cee_get_attr(struct bfa_cee *cee,
+ struct bfa_cee_attr *attr,
+ bfa_cee_get_attr_cbfn_t cbfn, void *cbarg);
#endif /* __BFA_CEE_H__ */
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
index 1d13044..abfad27 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
@@ -74,6 +74,7 @@ static void bfa_ioc_check_attr_wwns(struct bfa_ioc *ioc);
static void bfa_ioc_event_notify(struct bfa_ioc *, enum bfa_ioc_event);
static void bfa_ioc_disable_comp(struct bfa_ioc *ioc);
static void bfa_ioc_lpu_stop(struct bfa_ioc *ioc);
+static void bfa_nw_ioc_debug_save_ftrc(struct bfa_ioc *ioc);
static void bfa_ioc_fail_notify(struct bfa_ioc *ioc);
static void bfa_ioc_pf_enabled(struct bfa_ioc *ioc);
static void bfa_ioc_pf_disabled(struct bfa_ioc *ioc);
@@ -997,6 +998,7 @@ bfa_iocpf_sm_disabled(struct bfa_iocpf *iocpf, enum iocpf_event event)
static void
bfa_iocpf_sm_initfail_sync_entry(struct bfa_iocpf *iocpf)
{
+ bfa_nw_ioc_debug_save_ftrc(iocpf->ioc);
bfa_ioc_hw_sem_get(iocpf->ioc);
}
@@ -1743,6 +1745,114 @@ bfa_ioc_mbox_flush(struct bfa_ioc *ioc)
bfa_q_deq(&mod->cmd_q, &cmd);
}
+/**
+ * Read data from SMEM to host through PCI memmap
+ *
+ * @param[in] ioc memory for IOC
+ * @param[in] tbuf app memory to store data from smem
+ * @param[in] soff smem offset
+ * @param[in] sz size of smem in bytes
+ */
+static int
+bfa_nw_ioc_smem_read(struct bfa_ioc *ioc, void *tbuf, u32 soff, u32 sz)
+{
+ u32 pgnum, loff, r32;
+ int i, len;
+ u32 *buf = tbuf;
+
+ pgnum = PSS_SMEM_PGNUM(ioc->ioc_regs.smem_pg0, soff);
+ loff = PSS_SMEM_PGOFF(soff);
+
+ /*
+ * Hold semaphore to serialize pll init and fwtrc.
+ */
+ if (bfa_nw_ioc_sem_get(ioc->ioc_regs.ioc_init_sem_reg) == 0)
+ return 1;
+
+ writel(pgnum, ioc->ioc_regs.host_page_num_fn);
+
+ len = sz/sizeof(u32);
+ for (i = 0; i < len; i++) {
+ r32 = swab32(readl((loff) + (ioc->ioc_regs.smem_page_start)));
+ buf[i] = be32_to_cpu(r32);
+ loff += sizeof(u32);
+
+ /**
+ * handle page offset wrap around
+ */
+ loff = PSS_SMEM_PGOFF(loff);
+ if (loff == 0) {
+ pgnum++;
+ writel(pgnum, ioc->ioc_regs.host_page_num_fn);
+ }
+ }
+
+ writel(PSS_SMEM_PGNUM(ioc->ioc_regs.smem_pg0, 0),
+ ioc->ioc_regs.host_page_num_fn);
+
+ /*
+ * release semaphore
+ */
+ readl(ioc->ioc_regs.ioc_init_sem_reg);
+ writel(1, ioc->ioc_regs.ioc_init_sem_reg);
+ return 0;
+}
+
+/**
+ * Retrieve saved firmware trace from a prior IOC failure.
+ */
+int
+bfa_nw_ioc_debug_fwtrc(struct bfa_ioc *ioc, void *trcdata, int *trclen)
+{
+ u32 loff = BFI_IOC_TRC_OFF + BNA_DBG_FWTRC_LEN * ioc->port_id;
+ int tlen, status = 0;
+
+ tlen = *trclen;
+ if (tlen > BNA_DBG_FWTRC_LEN)
+ tlen = BNA_DBG_FWTRC_LEN;
+
+ status = bfa_nw_ioc_smem_read(ioc, trcdata, loff, tlen);
+ *trclen = tlen;
+ return status;
+}
+
+/**
+ * Save firmware trace if configured.
+ */
+static void
+bfa_nw_ioc_debug_save_ftrc(struct bfa_ioc *ioc)
+{
+ int tlen;
+
+ if (ioc->dbg_fwsave_once) {
+ ioc->dbg_fwsave_once = 0;
+ if (ioc->dbg_fwsave_len) {
+ tlen = ioc->dbg_fwsave_len;
+ bfa_nw_ioc_debug_fwtrc(ioc, ioc->dbg_fwsave, &tlen);
+ }
+ }
+}
+
+/**
+ * Retrieve saved firmware trace from a prior IOC failure.
+ */
+int
+bfa_nw_ioc_debug_fwsave(struct bfa_ioc *ioc, void *trcdata, int *trclen)
+{
+ int tlen;
+
+ if (ioc->dbg_fwsave_len == 0)
+ return BFA_STATUS_ENOFSAVE;
+
+ tlen = *trclen;
+ if (tlen > ioc->dbg_fwsave_len)
+ tlen = ioc->dbg_fwsave_len;
+
+ memcpy(trcdata, ioc->dbg_fwsave, tlen);
+ *trclen = tlen;
+ return BFA_STATUS_OK;
+}
+
static void
bfa_ioc_fail_notify(struct bfa_ioc *ioc)
{
@@ -1751,6 +1861,7 @@ bfa_ioc_fail_notify(struct bfa_ioc *ioc)
*/
ioc->cbfn->hbfail_cbfn(ioc->bfa);
bfa_ioc_event_notify(ioc, BFA_IOC_E_FAILED);
+ bfa_nw_ioc_debug_save_ftrc(ioc);
}
/**
@@ -2058,6 +2169,16 @@ bfa_nw_ioc_disable(struct bfa_ioc *ioc)
bfa_fsm_send_event(ioc, IOC_E_DISABLE);
}
+/**
+ * Initialize memory for saving firmware trace.
+ */
+void
+bfa_nw_ioc_debug_memclaim(struct bfa_ioc *ioc, void *dbg_fwsave)
+{
+ ioc->dbg_fwsave = dbg_fwsave;
+ ioc->dbg_fwsave_len = ioc->iocpf.auto_recover ? BNA_DBG_FWTRC_LEN : 0;
+}
+
static u32
bfa_ioc_smem_pgnum(struct bfa_ioc *ioc, u32 fmaddr)
{
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.h b/drivers/net/ethernet/brocade/bna/bfa_ioc.h
index fc108c7..3b4460f 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc.h
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.h
@@ -27,6 +27,8 @@
#define BFA_IOC_HWSEM_TOV 500 /* msecs */
#define BFA_IOC_HB_TOV 500 /* msecs */
#define BFA_IOC_POLL_TOV 200 /* msecs */
+#define BNA_DBG_FWTRC_LEN (BFI_IOC_TRC_ENTS * BFI_IOC_TRC_ENT_SZ + \
+ BFI_IOC_TRC_HDR_SZ)
/**
* PCI device information required by IOC
@@ -306,6 +308,7 @@ void bfa_nw_ioc_disable(struct bfa_ioc *ioc);
void bfa_nw_ioc_error_isr(struct bfa_ioc *ioc);
bool bfa_nw_ioc_is_disabled(struct bfa_ioc *ioc);
+bool bfa_nw_ioc_is_operational(struct bfa_ioc *ioc);
void bfa_nw_ioc_get_attr(struct bfa_ioc *ioc, struct bfa_ioc_attr *ioc_attr);
void bfa_nw_ioc_notify_register(struct bfa_ioc *ioc,
struct bfa_ioc_notify *notify);
@@ -317,6 +320,9 @@ void bfa_nw_ioc_fwver_get(struct bfa_ioc *ioc,
bool bfa_nw_ioc_fwver_cmp(struct bfa_ioc *ioc,
struct bfi_ioc_image_hdr *fwhdr);
mac_t bfa_nw_ioc_get_mac(struct bfa_ioc *ioc);
+void bfa_nw_ioc_debug_memclaim(struct bfa_ioc *ioc, void *dbg_fwsave);
+int bfa_nw_ioc_debug_fwtrc(struct bfa_ioc *ioc, void *trcdata, int *trclen);
+int bfa_nw_ioc_debug_fwsave(struct bfa_ioc *ioc, void *trcdata, int *trclen);
/*
* Timeout APIs
diff --git a/drivers/net/ethernet/brocade/bna/bfi.h b/drivers/net/ethernet/brocade/bna/bfi.h
index 8230970..0d9df69 100644
--- a/drivers/net/ethernet/brocade/bna/bfi.h
+++ b/drivers/net/ethernet/brocade/bna/bfi.h
@@ -257,6 +257,8 @@ struct bfi_ioc_getattr_reply {
*/
#define BFI_IOC_TRC_OFF (0x4b00)
#define BFI_IOC_TRC_ENTS 256
+#define BFI_IOC_TRC_ENT_SZ 16
+#define BFI_IOC_TRC_HDR_SZ 32
#define BFI_IOC_FW_SIGNATURE (0xbfadbfad)
#define BFI_IOC_MD5SUM_SZ 4
diff --git a/drivers/net/ethernet/brocade/bna/bna_enet.c b/drivers/net/ethernet/brocade/bna/bna_enet.c
index bcfe296..9ccc586 100644
--- a/drivers/net/ethernet/brocade/bna/bna_enet.c
+++ b/drivers/net/ethernet/brocade/bna/bna_enet.c
@@ -1727,6 +1727,7 @@ bna_ioceth_init(struct bna_ioceth *ioceth, struct bna *bna,
bfa_nw_ioc_mem_claim(&ioceth->ioc, kva, dma);
kva = res_info[BNA_RES_MEM_T_FWTRC].res_u.mem_info.mdl[0].kva;
+ bfa_nw_ioc_debug_memclaim(&ioceth->ioc, kva);
/**
* Attach common modules (Diag, SFP, CEE, Port) and claim respective
@@ -1910,8 +1911,8 @@ bna_res_req(struct bna_res_info *res_info)
/* Virtual memory for retreiving fw_trc */
res_info[BNA_RES_MEM_T_FWTRC].res_type = BNA_RES_T_MEM;
res_info[BNA_RES_MEM_T_FWTRC].res_u.mem_info.mem_type = BNA_MEM_T_KVA;
- res_info[BNA_RES_MEM_T_FWTRC].res_u.mem_info.num = 0;
- res_info[BNA_RES_MEM_T_FWTRC].res_u.mem_info.len = 0;
+ res_info[BNA_RES_MEM_T_FWTRC].res_u.mem_info.num = 1;
+ res_info[BNA_RES_MEM_T_FWTRC].res_u.mem_info.len = BNA_DBG_FWTRC_LEN;
/* DMA memory for retreiving stats */
res_info[BNA_RES_MEM_T_STATS].res_type = BNA_RES_T_MEM;
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index 741f2e4..2eddbaa 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -44,6 +44,11 @@ static uint bnad_ioc_auto_recover = 1;
module_param(bnad_ioc_auto_recover, uint, 0444);
MODULE_PARM_DESC(bnad_ioc_auto_recover, "Enable / Disable auto recovery");
+static uint bna_debugfs_enable = 1;
+module_param(bna_debugfs_enable, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(bna_debugfs_enable, "Enables debugfs feature, default=1,"
+ " Range[false:0|true:1]");
+
/*
* Global variables
*/
@@ -3312,6 +3317,10 @@ bnad_pci_probe(struct pci_dev *pdev,
/* Set link to down state */
netif_carrier_off(netdev);
+ /* Setup the debugfs node for this bfad */
+ if (bna_debugfs_enable)
+ bnad_debugfs_init(bnad);
+
/* Get resource requirement form bna */
spin_lock_irqsave(&bnad->bna_lock, flags);
bna_res_req(&bnad->res_info[0]);
@@ -3433,6 +3442,9 @@ disable_ioceth:
res_free:
bnad_res_free(bnad, &bnad->res_info[0], BNA_RES_T_MAX);
drv_uninit:
+ /* Remove the debugfs node for this bnad */
+ kfree(bnad->regdata);
+ bnad_debugfs_uninit(bnad);
bnad_uninit(bnad);
pci_uninit:
bnad_pci_uninit(pdev);
@@ -3479,6 +3491,9 @@ bnad_pci_remove(struct pci_dev *pdev)
mutex_unlock(&bnad->conf_mutex);
bnad_remove_from_list(bnad);
bnad_lock_uninit(bnad);
+ /* Remove the debugfs node for this bnad */
+ kfree(bnad->regdata);
+ bnad_debugfs_uninit(bnad);
bnad_uninit(bnad);
free_netdev(netdev);
}
diff --git a/drivers/net/ethernet/brocade/bna/bnad.h b/drivers/net/ethernet/brocade/bna/bnad.h
index 459030c..c975ce6 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.h
+++ b/drivers/net/ethernet/brocade/bna/bnad.h
@@ -328,6 +328,20 @@ struct bnad {
char adapter_name[BNAD_NAME_LEN];
char port_name[BNAD_NAME_LEN];
char mbox_irq_name[BNAD_NAME_LEN];
+
+ /* debugfs specific data */
+ char *regdata;
+ u32 reglen;
+ struct dentry *bnad_dentry_files[5];
+ struct dentry *port_debugfs_root;
+};
+
+struct bnad_drvinfo {
+ struct bfa_ioc_attr ioc_attr;
+ struct bfa_cee_attr cee_attr;
+ struct bfa_flash_attr flash_attr;
+ u32 cee_status;
+ u32 flash_status;
};
/*
@@ -368,6 +382,10 @@ extern void bnad_netdev_qstats_fill(struct bnad *bnad,
extern void bnad_netdev_hwstats_fill(struct bnad *bnad,
struct rtnl_link_stats64 *stats);
+/* Debugfs */
+void bnad_debugfs_init(struct bnad *bnad);
+void bnad_debugfs_uninit(struct bnad *bnad);
+
/**
* MACROS
*/
diff --git a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c
new file mode 100644
index 0000000..592ad39
--- /dev/null
+++ b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c
@@ -0,0 +1,623 @@
+/*
+ * Linux network driver for Brocade Converged Network Adapter.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License (GPL) Version 2 as
+ * published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+/*
+ * Copyright (c) 2005-2011 Brocade Communications Systems, Inc.
+ * All rights reserved
+ * www.brocade.com
+ */
+
+#include <linux/debugfs.h>
+#include <linux/module.h>
+#include "bnad.h"
+
+/*
+ * BNA debufs interface
+ *
+ * To access the interface, debugfs file system should be mounted
+ * if not already mounted using:
+ * mount -t debugfs none /sys/kernel/debug
+ *
+ * BNA Hierarchy:
+ * - bna/pci_dev:<pci_name>
+ * where the pci_name corresponds to the one under /sys/bus/pci/drivers/bna
+ *
+ * Debugging service available per pci_dev:
+ * fwtrc: To collect current firmware trace.
+ * fwsave: To collect last saved fw trace as a result of firmware crash.
+ * regwr: To write one word to chip register
+ * regrd: To read one or more words from chip register.
+ */
+
+struct bnad_debug_info {
+ char *debug_buffer;
+ void *i_private;
+ int buffer_len;
+};
+
+static int
+bnad_debugfs_open_fwtrc(struct inode *inode, struct file *file)
+{
+ struct bnad *bnad = inode->i_private;
+ struct bnad_debug_info *fw_debug;
+ unsigned long flags;
+ int rc;
+
+ fw_debug = kzalloc(sizeof(struct bnad_debug_info), GFP_KERNEL);
+ if (!fw_debug)
+ return -ENOMEM;
+
+ fw_debug->buffer_len = BNA_DBG_FWTRC_LEN;
+
+ fw_debug->debug_buffer = kzalloc(fw_debug->buffer_len, GFP_KERNEL);
+ if (!fw_debug->debug_buffer) {
+ kfree(fw_debug);
+ fw_debug = NULL;
+ pr_warn("bna %s: Failed to allocate fwtrc buffer\n",
+ pci_name(bnad->pcidev));
+ return -ENOMEM;
+ }
+
+ spin_lock_irqsave(&bnad->bna_lock, flags);
+ rc = bfa_nw_ioc_debug_fwtrc(&bnad->bna.ioceth.ioc,
+ fw_debug->debug_buffer,
+ &fw_debug->buffer_len);
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ if (rc != BFA_STATUS_OK) {
+ kfree(fw_debug->debug_buffer);
+ fw_debug->debug_buffer = NULL;
+ kfree(fw_debug);
+ fw_debug = NULL;
+ pr_warn("bnad %s: Failed to collect fwtrc\n",
+ pci_name(bnad->pcidev));
+ return -ENOMEM;
+ }
+
+ file->private_data = fw_debug;
+
+ return 0;
+}
+
+static int
+bnad_debugfs_open_fwsave(struct inode *inode, struct file *file)
+{
+ struct bnad *bnad = inode->i_private;
+ struct bnad_debug_info *fw_debug;
+ unsigned long flags;
+ int rc;
+
+ fw_debug = kzalloc(sizeof(struct bnad_debug_info), GFP_KERNEL);
+ if (!fw_debug)
+ return -ENOMEM;
+
+ fw_debug->buffer_len = BNA_DBG_FWTRC_LEN;
+
+ fw_debug->debug_buffer = kzalloc(fw_debug->buffer_len, GFP_KERNEL);
+ if (!fw_debug->debug_buffer) {
+ kfree(fw_debug);
+ fw_debug = NULL;
+ pr_warn("bna %s: Failed to allocate fwsave buffer\n",
+ pci_name(bnad->pcidev));
+ return -ENOMEM;
+ }
+
+ spin_lock_irqsave(&bnad->bna_lock, flags);
+ rc = bfa_nw_ioc_debug_fwsave(&bnad->bna.ioceth.ioc,
+ fw_debug->debug_buffer,
+ &fw_debug->buffer_len);
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ if (rc != BFA_STATUS_OK && rc != BFA_STATUS_ENOFSAVE) {
+ kfree(fw_debug->debug_buffer);
+ fw_debug->debug_buffer = NULL;
+ kfree(fw_debug);
+ fw_debug = NULL;
+ pr_warn("bna %s: Failed to collect fwsave\n",
+ pci_name(bnad->pcidev));
+ return -ENOMEM;
+ }
+
+ file->private_data = fw_debug;
+
+ return 0;
+}
+
+static int
+bnad_debugfs_open_reg(struct inode *inode, struct file *file)
+{
+ struct bnad_debug_info *reg_debug;
+
+ reg_debug = kzalloc(sizeof(struct bnad_debug_info), GFP_KERNEL);
+ if (!reg_debug)
+ return -ENOMEM;
+
+ reg_debug->i_private = inode->i_private;
+
+ file->private_data = reg_debug;
+
+ return 0;
+}
+
+static int
+bnad_get_debug_drvinfo(struct bnad *bnad, void *buffer, u32 len)
+{
+ struct bnad_drvinfo *drvinfo = (struct bnad_drvinfo *) buffer;
+ struct bnad_iocmd_comp fcomp;
+ unsigned long flags = 0;
+ int ret = BFA_STATUS_FAILED;
+
+ /* Get IOC info */
+ spin_lock_irqsave(&bnad->bna_lock, flags);
+ bfa_nw_ioc_get_attr(&bnad->bna.ioceth.ioc, &drvinfo->ioc_attr);
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+
+ /* Retrieve CEE related info */
+ fcomp.bnad = bnad;
+ fcomp.comp_status = 0;
+ init_completion(&fcomp.comp);
+ spin_lock_irqsave(&bnad->bna_lock, flags);
+ ret = bfa_nw_cee_get_attr(&bnad->bna.cee, &drvinfo->cee_attr,
+ bnad_cb_completion, &fcomp);
+ if (ret != BFA_STATUS_OK) {
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ goto out;
+ }
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ wait_for_completion(&fcomp.comp);
+ drvinfo->cee_status = fcomp.comp_status;
+
+ /* Retrieve flash partition info */
+ fcomp.comp_status = 0;
+ init_completion(&fcomp.comp);
+ spin_lock_irqsave(&bnad->bna_lock, flags);
+ ret = bfa_nw_flash_get_attr(&bnad->bna.flash, &drvinfo->flash_attr,
+ bnad_cb_completion, &fcomp);
+ if (ret != BFA_STATUS_OK) {
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ goto out;
+ }
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ wait_for_completion(&fcomp.comp);
+ drvinfo->flash_status = fcomp.comp_status;
+out:
+ return ret;
+}
+
+static int
+bnad_debugfs_open_drvinfo(struct inode *inode, struct file *file)
+{
+ struct bnad *bnad = inode->i_private;
+ struct bnad_debug_info *drv_info;
+ int rc;
+
+ drv_info = kzalloc(sizeof(struct bnad_debug_info), GFP_KERNEL);
+ if (!drv_info)
+ return -ENOMEM;
+
+ drv_info->buffer_len = sizeof(struct bnad_drvinfo);
+
+ drv_info->debug_buffer = kzalloc(drv_info->buffer_len, GFP_KERNEL);
+ if (!drv_info->debug_buffer) {
+ kfree(drv_info);
+ drv_info = NULL;
+ pr_warn("bna %s: Failed to allocate drv info buffer\n",
+ pci_name(bnad->pcidev));
+ return -ENOMEM;
+ }
+
+ mutex_lock(&bnad->conf_mutex);
+ rc = bnad_get_debug_drvinfo(bnad, drv_info->debug_buffer,
+ drv_info->buffer_len);
+ mutex_unlock(&bnad->conf_mutex);
+ if (rc != BFA_STATUS_OK) {
+ kfree(drv_info->debug_buffer);
+ drv_info->debug_buffer = NULL;
+ kfree(drv_info);
+ drv_info = NULL;
+ pr_warn("bna %s: Failed to collect drvinfo\n",
+ pci_name(bnad->pcidev));
+ return -ENOMEM;
+ }
+
+ file->private_data = drv_info;
+
+ return 0;
+}
+
+/* Changes the current file position */
+static loff_t
+bnad_debugfs_lseek(struct file *file, loff_t offset, int orig)
+{
+ loff_t pos = file->f_pos;
+ struct bnad_debug_info *debug = file->private_data;
+
+ if (!debug)
+ return -EINVAL;
+
+ switch (orig) {
+ case 0:
+ file->f_pos = offset;
+ break;
+ case 1:
+ file->f_pos += offset;
+ break;
+ case 2:
+ file->f_pos = debug->buffer_len - offset;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (file->f_pos < 0 || file->f_pos > debug->buffer_len) {
+ file->f_pos = pos;
+ return -EINVAL;
+ }
+
+ return file->f_pos;
+}
+
+static ssize_t
+bnad_debugfs_read(struct file *file, char __user *buf,
+ size_t nbytes, loff_t *pos)
+{
+ struct bnad_debug_info *debug = file->private_data;
+
+ if (!debug || !debug->debug_buffer)
+ return 0;
+
+ return simple_read_from_buffer(buf, nbytes, pos,
+ debug->debug_buffer, debug->buffer_len);
+}
+
+#define BFA_REG_CT_ADDRSZ (0x40000)
+#define BFA_REG_CB_ADDRSZ (0x20000)
+#define BFA_REG_ADDRSZ(__ioc) \
+ ((u32)(bfa_asic_id_ctc(bfa_ioc_devid(__ioc)) ? \
+ BFA_REG_CT_ADDRSZ : BFA_REG_CB_ADDRSZ))
+#define BFA_REG_ADDRMSK(__ioc) (BFA_REG_ADDRSZ(__ioc) - 1)
+
+/*
+ * Function to check if the register offset passed is valid.
+ */
+static int
+bna_reg_offset_check(struct bfa_ioc *ioc, u32 offset, u32 len)
+{
+ u8 area;
+
+ /* check [16:15] */
+ area = (offset >> 15) & 0x7;
+ if (area == 0) {
+ /* PCIe core register */
+ if ((offset + (len<<2)) > 0x8000) /* 8k dwords or 32KB */
+ return BFA_STATUS_EINVAL;
+ } else if (area == 0x1) {
+ /* CB 32 KB memory page */
+ if ((offset + (len<<2)) > 0x10000) /* 8k dwords or 32KB */
+ return BFA_STATUS_EINVAL;
+ } else {
+ /* CB register space 64KB */
+ if ((offset + (len<<2)) > BFA_REG_ADDRMSK(ioc))
+ return BFA_STATUS_EINVAL;
+ }
+ return BFA_STATUS_OK;
+}
+
+static ssize_t
+bnad_debugfs_read_regrd(struct file *file, char __user *buf,
+ size_t nbytes, loff_t *pos)
+{
+ struct bnad_debug_info *regrd_debug = file->private_data;
+ struct bnad *bnad = (struct bnad *)regrd_debug->i_private;
+ ssize_t rc;
+
+ if (!bnad->regdata)
+ return 0;
+
+ rc = simple_read_from_buffer(buf, nbytes, pos,
+ bnad->regdata, bnad->reglen);
+
+ if ((*pos + nbytes) >= bnad->reglen) {
+ kfree(bnad->regdata);
+ bnad->regdata = NULL;
+ bnad->reglen = 0;
+ }
+
+ return rc;
+}
+
+static ssize_t
+bnad_debugfs_write_regrd(struct file *file, const char __user *buf,
+ size_t nbytes, loff_t *ppos)
+{
+ struct bnad_debug_info *regrd_debug = file->private_data;
+ struct bnad *bnad = (struct bnad *)regrd_debug->i_private;
+ struct bfa_ioc *ioc = &bnad->bna.ioceth.ioc;
+ int addr, len, rc, i;
+ u32 *regbuf;
+ void __iomem *rb, *reg_addr;
+ unsigned long flags;
+ void *kern_buf;
+
+ /* Allocate memory to store the user space buf */
+ kern_buf = kzalloc(nbytes, GFP_KERNEL);
+ if (!kern_buf) {
+ pr_warn("bna %s: Failed to allocate user buffer\n",
+ pci_name(bnad->pcidev));
+ return -ENOMEM;
+ }
+
+ if (copy_from_user(kern_buf, (void __user *)buf, nbytes)) {
+ kfree(kern_buf);
+ return -ENOMEM;
+ }
+
+ rc = sscanf(kern_buf, "%x:%x", &addr, &len);
+ if (rc < 2) {
+ pr_warn("bna %s: Failed to read user buffer\n",
+ pci_name(bnad->pcidev));
+ kfree(kern_buf);
+ return -EINVAL;
+ }
+
+ kfree(kern_buf);
+ kfree(bnad->regdata);
+ bnad->regdata = NULL;
+ bnad->reglen = 0;
+
+ bnad->regdata = kzalloc(len << 2, GFP_KERNEL);
+ if (!bnad->regdata) {
+ pr_warn("bna %s: Failed to allocate regrd buffer\n",
+ pci_name(bnad->pcidev));
+ return -ENOMEM;
+ }
+
+ bnad->reglen = len << 2;
+ rb = bfa_ioc_bar0(ioc);
+ addr &= BFA_REG_ADDRMSK(ioc);
+
+ /* offset and len sanity check */
+ rc = bna_reg_offset_check(ioc, addr, len);
+ if (rc) {
+ pr_warn("bna %s: Failed reg offset check\n",
+ pci_name(bnad->pcidev));
+ kfree(bnad->regdata);
+ bnad->regdata = NULL;
+ bnad->reglen = 0;
+ return -EINVAL;
+ }
+
+ reg_addr = rb + addr;
+ regbuf = (u32 *)bnad->regdata;
+ spin_lock_irqsave(&bnad->bna_lock, flags);
+ for (i = 0; i < len; i++) {
+ *regbuf = readl(reg_addr);
+ regbuf++;
+ reg_addr += sizeof(u32);
+ }
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+
+ return nbytes;
+}
+
+static ssize_t
+bnad_debugfs_write_regwr(struct file *file, const char __user *buf,
+ size_t nbytes, loff_t *ppos)
+{
+ struct bnad_debug_info *debug = file->private_data;
+ struct bnad *bnad = (struct bnad *)debug->i_private;
+ struct bfa_ioc *ioc = &bnad->bna.ioceth.ioc;
+ int addr, val, rc;
+ void __iomem *reg_addr;
+ unsigned long flags;
+ void *kern_buf;
+
+ /* Allocate memory to store the user space buf */
+ kern_buf = kzalloc(nbytes, GFP_KERNEL);
+ if (!kern_buf) {
+ pr_warn("bna %s: Failed to allocate user buffer\n",
+ pci_name(bnad->pcidev));
+ return -ENOMEM;
+ }
+
+ if (copy_from_user(kern_buf, (void __user *)buf, nbytes)) {
+ kfree(kern_buf);
+ return -ENOMEM;
+ }
+
+ rc = sscanf(kern_buf, "%x:%x", &addr, &val);
+ if (rc < 2) {
+ pr_warn("bna %s: Failed to read user buffer\n",
+ pci_name(bnad->pcidev));
+ kfree(kern_buf);
+ return -EINVAL;
+ }
+ kfree(kern_buf);
+
+ addr &= BFA_REG_ADDRMSK(ioc); /* offset only 17 bit and word align */
+
+ /* offset and len sanity check */
+ rc = bna_reg_offset_check(ioc, addr, 1);
+ if (rc) {
+ pr_warn("bna %s: Failed reg offset check\n",
+ pci_name(bnad->pcidev));
+ return -EINVAL;
+ }
+
+ reg_addr = (bfa_ioc_bar0(ioc)) + addr;
+ spin_lock_irqsave(&bnad->bna_lock, flags);
+ writel(val, reg_addr);
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+
+ return nbytes;
+}
+
+static int
+bnad_debugfs_release(struct inode *inode, struct file *file)
+{
+ struct bnad_debug_info *debug = file->private_data;
+
+ if (!debug)
+ return 0;
+
+ file->private_data = NULL;
+ kfree(debug);
+ return 0;
+}
+
+static int
+bnad_debugfs_buffer_release(struct inode *inode, struct file *file)
+{
+ struct bnad_debug_info *debug = file->private_data;
+
+ if (!debug)
+ return 0;
+
+ kfree(debug->debug_buffer);
+
+ file->private_data = NULL;
+ kfree(debug);
+ debug = NULL;
+ return 0;
+}
+
+static const struct file_operations bnad_debugfs_op_fwtrc = {
+ .owner = THIS_MODULE,
+ .open = bnad_debugfs_open_fwtrc,
+ .llseek = bnad_debugfs_lseek,
+ .read = bnad_debugfs_read,
+ .release = bnad_debugfs_buffer_release,
+};
+
+static const struct file_operations bnad_debugfs_op_fwsave = {
+ .owner = THIS_MODULE,
+ .open = bnad_debugfs_open_fwsave,
+ .llseek = bnad_debugfs_lseek,
+ .read = bnad_debugfs_read,
+ .release = bnad_debugfs_buffer_release,
+};
+
+static const struct file_operations bnad_debugfs_op_regrd = {
+ .owner = THIS_MODULE,
+ .open = bnad_debugfs_open_reg,
+ .llseek = bnad_debugfs_lseek,
+ .read = bnad_debugfs_read_regrd,
+ .write = bnad_debugfs_write_regrd,
+ .release = bnad_debugfs_release,
+};
+
+static const struct file_operations bnad_debugfs_op_regwr = {
+ .owner = THIS_MODULE,
+ .open = bnad_debugfs_open_reg,
+ .llseek = bnad_debugfs_lseek,
+ .write = bnad_debugfs_write_regwr,
+ .release = bnad_debugfs_release,
+};
+
+static const struct file_operations bnad_debugfs_op_drvinfo = {
+ .owner = THIS_MODULE,
+ .open = bnad_debugfs_open_drvinfo,
+ .llseek = bnad_debugfs_lseek,
+ .read = bnad_debugfs_read,
+ .release = bnad_debugfs_buffer_release,
+};
+
+struct bnad_debugfs_entry {
+ const char *name;
+ mode_t mode;
+ const struct file_operations *fops;
+};
+
+static const struct bnad_debugfs_entry bnad_debugfs_files[] = {
+ { "fwtrc", S_IFREG|S_IRUGO, &bnad_debugfs_op_fwtrc, },
+ { "fwsave", S_IFREG|S_IRUGO, &bnad_debugfs_op_fwsave, },
+ { "regrd", S_IFREG|S_IRUGO|S_IWUSR, &bnad_debugfs_op_regrd, },
+ { "regwr", S_IFREG|S_IWUSR, &bnad_debugfs_op_regwr, },
+ { "drvinfo", S_IFREG|S_IRUGO, &bnad_debugfs_op_drvinfo, },
+};
+
+static struct dentry *bna_debugfs_root;
+static atomic_t bna_debugfs_port_count;
+
+/* Initialize debugfs interface for BNA */
+void
+bnad_debugfs_init(struct bnad *bnad)
+{
+ const struct bnad_debugfs_entry *file;
+ char name[64];
+ int i;
+
+ /* Setup the BNA debugfs root directory*/
+ if (!bna_debugfs_root) {
+ bna_debugfs_root = debugfs_create_dir("bna", NULL);
+ atomic_set(&bna_debugfs_port_count, 0);
+ if (!bna_debugfs_root) {
+ pr_warn("BNA: debugfs root dir creation failed\n");
+ return;
+ }
+ }
+
+ /* Setup the pci_dev debugfs directory for the port */
+ snprintf(name, sizeof(name), "pci_dev:%s", pci_name(bnad->pcidev));
+ if (!bnad->port_debugfs_root) {
+ bnad->port_debugfs_root =
+ debugfs_create_dir(name, bna_debugfs_root);
+ if (!bnad->port_debugfs_root) {
+ pr_warn("bna pci_dev %s: root dir creation failed\n",
+ pci_name(bnad->pcidev));
+ return;
+ }
+
+ atomic_inc(&bna_debugfs_port_count);
+
+ for (i = 0; i < ARRAY_SIZE(bnad_debugfs_files); i++) {
+ file = &bnad_debugfs_files[i];
+ bnad->bnad_dentry_files[i] =
+ debugfs_create_file(file->name,
+ file->mode,
+ bnad->port_debugfs_root,
+ bnad,
+ file->fops);
+ if (!bnad->bnad_dentry_files[i]) {
+ pr_warn(
+ "BNA pci_dev:%s: create %s entry failed\n",
+ pci_name(bnad->pcidev), file->name);
+ return;
+ }
+ }
+ }
+}
+
+/* Uninitialize debugfs interface for BNA */
+void
+bnad_debugfs_uninit(struct bnad *bnad)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(bnad_debugfs_files); i++) {
+ if (bnad->bnad_dentry_files[i]) {
+ debugfs_remove(bnad->bnad_dentry_files[i]);
+ bnad->bnad_dentry_files[i] = NULL;
+ }
+ }
+
+ /* Remove the pci_dev debugfs directory for the port */
+ if (bnad->port_debugfs_root) {
+ debugfs_remove(bnad->port_debugfs_root);
+ bnad->port_debugfs_root = NULL;
+ atomic_dec(&bna_debugfs_port_count);
+ }
+
+ /* Remove the BNA debugfs root directory */
+ if (atomic_read(&bna_debugfs_port_count) == 0) {
+ debugfs_remove(bna_debugfs_root);
+ bna_debugfs_root = NULL;
+ }
+}
--
1.7.3.rc1
^ permalink raw reply related
* [PATCH 0/2] bna: Enable ethtool flash management and debugfs interface.
From: kgudipat @ 2011-12-22 23:29 UTC (permalink / raw)
To: davem, netdev; +Cc: adapter_linux_open_src_team, kgudipat, rmody
From: Krishna Gudipati <kgudipat@brocade.com>
Hi Dave,
The following patch-set enhances BNA ethtool to support flash management
using eeprom entry points and also enables debugfs support for BNA driver to
collect firmware traces, saved firmware trace in the flash on an IOC crash and to
perform register reads/writes.
The patch is compiled and tested against latest net-next kernel.
Thanks,
Krishna
Krishna Gudipati (2):
bna: Added flash sub-module and ethtool eeprom entry points.
bna: Add debugfs interface.
drivers/net/ethernet/brocade/bna/Makefile | 2 +-
drivers/net/ethernet/brocade/bna/bfa_cee.c | 35 ++
drivers/net/ethernet/brocade/bna/bfa_cee.h | 4 +-
drivers/net/ethernet/brocade/bna/bfa_defs.h | 98 +++--
drivers/net/ethernet/brocade/bna/bfa_ioc.c | 493 ++++++++++++++++++
drivers/net/ethernet/brocade/bna/bfa_ioc.h | 54 ++
drivers/net/ethernet/brocade/bna/bfi.h | 97 ++++
drivers/net/ethernet/brocade/bna/bna_enet.c | 13 +-
drivers/net/ethernet/brocade/bna/bna_types.h | 1 +
drivers/net/ethernet/brocade/bna/bnad.c | 52 ++-
drivers/net/ethernet/brocade/bna/bnad.h | 27 +
drivers/net/ethernet/brocade/bna/bnad_debugfs.c | 623 +++++++++++++++++++++++
drivers/net/ethernet/brocade/bna/bnad_ethtool.c | 142 +++++-
13 files changed, 1598 insertions(+), 43 deletions(-)
create mode 100644 drivers/net/ethernet/brocade/bna/bnad_debugfs.c
--
1.7.3.rc1
^ permalink raw reply
* Re: [RFC] iproute2: split up ip man page?
From: Hagen Paul Pfeifer @ 2011-12-23 0:10 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: netdev
In-Reply-To: <20111222103723.59a035df@nehalam.linuxnetplumber.net>
* Stephen Hemminger | 2011-12-22 10:37:23 [-0800]:
>Ok, the ip man page is now broken up. I tried to fix some of the
>incorrect grammar and usage as well. The pages still need editing for
>readability.
Great! Commit 1b1177ed5f3 synched kernel headers. Should I rebase my iproute
netem rate patch (and again update include/linux/pkt_sched.h for net-next) or
keep you aware of this?
Hagen
^ permalink raw reply
* [PATCH 1/2] bna: Added flash sub-module and ethtool eeprom entry points.
From: kgudipat @ 2011-12-22 23:29 UTC (permalink / raw)
To: davem, netdev; +Cc: adapter_linux_open_src_team, kgudipat, rmody
From: Krishna Gudipati <kgudipat@brocade.com>
Change details:
- The patch adds flash sub-module to the bna driver.
- Added ethtool set_eeprom() and get_eeprom() entry points to
support flash partition read/write operations.
Signed-off-by: Krishna Gudipati <kgudipat@brocade.com>
---
drivers/net/ethernet/brocade/bna/bfa_defs.h | 98 ++++---
drivers/net/ethernet/brocade/bna/bfa_ioc.c | 372 +++++++++++++++++++++++
drivers/net/ethernet/brocade/bna/bfa_ioc.h | 48 +++
drivers/net/ethernet/brocade/bna/bfi.h | 95 ++++++
drivers/net/ethernet/brocade/bna/bna_enet.c | 8 +-
drivers/net/ethernet/brocade/bna/bna_types.h | 1 +
drivers/net/ethernet/brocade/bna/bnad.c | 37 +++-
drivers/net/ethernet/brocade/bna/bnad.h | 9 +
drivers/net/ethernet/brocade/bna/bnad_ethtool.c | 142 +++++++++-
9 files changed, 771 insertions(+), 39 deletions(-)
diff --git a/drivers/net/ethernet/brocade/bna/bfa_defs.h b/drivers/net/ethernet/brocade/bna/bfa_defs.h
index 2f12d68..871c630 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_defs.h
+++ b/drivers/net/ethernet/brocade/bna/bfa_defs.h
@@ -219,41 +219,39 @@ enum {
* All numerical fields are in big-endian format.
*/
struct bfa_mfg_block {
- u8 version; /*!< manufacturing block version */
- u8 mfg_sig[3]; /*!< characters 'M', 'F', 'G' */
- u16 mfgsize; /*!< mfg block size */
- u16 u16_chksum; /*!< old u16 checksum */
- char brcd_serialnum[STRSZ(BFA_MFG_SERIALNUM_SIZE)];
- char brcd_partnum[STRSZ(BFA_MFG_PARTNUM_SIZE)];
- u8 mfg_day; /*!< manufacturing day */
- u8 mfg_month; /*!< manufacturing month */
- u16 mfg_year; /*!< manufacturing year */
- u64 mfg_wwn; /*!< wwn base for this adapter */
- u8 num_wwn; /*!< number of wwns assigned */
- u8 mfg_speeds; /*!< speeds allowed for this adapter */
- u8 rsv[2];
- char supplier_id[STRSZ(BFA_MFG_SUPPLIER_ID_SIZE)];
- char supplier_partnum[STRSZ(BFA_MFG_SUPPLIER_PARTNUM_SIZE)];
- char
- supplier_serialnum[STRSZ(BFA_MFG_SUPPLIER_SERIALNUM_SIZE)];
- char
- supplier_revision[STRSZ(BFA_MFG_SUPPLIER_REVISION_SIZE)];
- mac_t mfg_mac; /*!< mac address */
- u8 num_mac; /*!< number of mac addresses */
- u8 rsv2;
- u32 card_type; /*!< card type */
- char cap_nic; /*!< capability nic */
- char cap_cna; /*!< capability cna */
- char cap_hba; /*!< capability hba */
- char cap_fc16g; /*!< capability fc 16g */
- char cap_sriov; /*!< capability sriov */
- char cap_mezz; /*!< capability mezz */
- u8 rsv3;
- u8 mfg_nports; /*!< number of ports */
- char media[8]; /*!< xfi/xaui */
- char initial_mode[8];/*!< initial mode: hba/cna/nic */
- u8 rsv4[84];
- u8 md5_chksum[BFA_MFG_CHKSUM_SIZE]; /*!< md5 checksum */
+ u8 version; /* manufacturing block version */
+ u8 mfg_sig[3]; /* characters 'M', 'F', 'G' */
+ u16 mfgsize; /* mfg block size */
+ u16 u16_chksum; /* old u16 checksum */
+ char brcd_serialnum[STRSZ(BFA_MFG_SERIALNUM_SIZE)];
+ char brcd_partnum[STRSZ(BFA_MFG_PARTNUM_SIZE)];
+ u8 mfg_day; /* manufacturing day */
+ u8 mfg_month; /* manufacturing month */
+ u16 mfg_year; /* manufacturing year */
+ u64 mfg_wwn; /* wwn base for this adapter */
+ u8 num_wwn; /* number of wwns assigned */
+ u8 mfg_speeds; /* speeds allowed for this adapter */
+ u8 rsv[2];
+ char supplier_id[STRSZ(BFA_MFG_SUPPLIER_ID_SIZE)];
+ char supplier_partnum[STRSZ(BFA_MFG_SUPPLIER_PARTNUM_SIZE)];
+ char supplier_serialnum[STRSZ(BFA_MFG_SUPPLIER_SERIALNUM_SIZE)];
+ char supplier_revision[STRSZ(BFA_MFG_SUPPLIER_REVISION_SIZE)];
+ mac_t mfg_mac; /* base mac address */
+ u8 num_mac; /* number of mac addresses */
+ u8 rsv2;
+ u32 card_type; /* card type */
+ char cap_nic; /* capability nic */
+ char cap_cna; /* capability cna */
+ char cap_hba; /* capability hba */
+ char cap_fc16g; /* capability fc 16g */
+ char cap_sriov; /* capability sriov */
+ char cap_mezz; /* capability mezz */
+ u8 rsv3;
+ u8 mfg_nports; /* number of ports */
+ char media[8]; /* xfi/xaui */
+ char initial_mode[8]; /* initial mode: hba/cna/nic */
+ u8 rsv4[84];
+ u8 md5_chksum[BFA_MFG_CHKSUM_SIZE]; /* md5 checksum */
};
#pragma pack()
@@ -293,4 +291,34 @@ enum bfa_mode {
BFA_MODE_NIC = 3
};
+/*
+ * Flash module specific
+ */
+#define BFA_FLASH_PART_ENTRY_SIZE 32 /* partition entry size */
+#define BFA_FLASH_PART_MAX 32 /* maximal # of partitions */
+#define BFA_TOTAL_FLASH_SIZE 0x400000
+#define BFA_FLASH_PART_MFG 7
+
+/*
+ * flash partition attributes
+ */
+struct bfa_flash_part_attr {
+ u32 part_type; /* partition type */
+ u32 part_instance; /* partition instance */
+ u32 part_off; /* partition offset */
+ u32 part_size; /* partition size */
+ u32 part_len; /* partition content length */
+ u32 part_status; /* partition status */
+ char rsv[BFA_FLASH_PART_ENTRY_SIZE - 24];
+};
+
+/*
+ * flash attributes
+ */
+struct bfa_flash_attr {
+ u32 status; /* flash overall status */
+ u32 npart; /* num of partitions */
+ struct bfa_flash_part_attr part[BFA_FLASH_PART_MAX];
+};
+
#endif /* __BFA_DEFS_H__ */
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
index b0307a0..1d13044 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
@@ -2172,6 +2172,15 @@ bfa_nw_ioc_is_disabled(struct bfa_ioc *ioc)
}
/**
+ * return true if IOC is operational
+ */
+bool
+bfa_nw_ioc_is_operational(struct bfa_ioc *ioc)
+{
+ return bfa_fsm_cmp_state(ioc, bfa_ioc_sm_op);
+}
+
+/**
* Add to IOC heartbeat failure notification queue. To be used by common
* modules such as cee, port, diag.
*/
@@ -2471,3 +2480,366 @@ bfa_ioc_poll_fwinit(struct bfa_ioc *ioc)
msecs_to_jiffies(BFA_IOC_POLL_TOV));
}
}
+
+/*
+ * Flash module specific
+ */
+
+/*
+ * FLASH DMA buffer should be big enough to hold both MFG block and
+ * asic block(64k) at the same time and also should be 2k aligned to
+ * avoid write segement to cross sector boundary.
+ */
+#define BFA_FLASH_SEG_SZ 2048
+#define BFA_FLASH_DMA_BUF_SZ \
+ roundup(0x010000 + sizeof(struct bfa_mfg_block), BFA_FLASH_SEG_SZ)
+
+static void
+bfa_flash_cb(struct bfa_flash *flash)
+{
+ flash->op_busy = 0;
+ if (flash->cbfn)
+ flash->cbfn(flash->cbarg, flash->status);
+}
+
+static void
+bfa_flash_notify(void *cbarg, enum bfa_ioc_event event)
+{
+ struct bfa_flash *flash = cbarg;
+
+ switch (event) {
+ case BFA_IOC_E_DISABLED:
+ case BFA_IOC_E_FAILED:
+ if (flash->op_busy) {
+ flash->status = BFA_STATUS_IOC_FAILURE;
+ flash->cbfn(flash->cbarg, flash->status);
+ flash->op_busy = 0;
+ }
+ break;
+ default:
+ break;
+ }
+}
+
+/*
+ * Send flash write request.
+ *
+ * @param[in] cbarg - callback argument
+ */
+static void
+bfa_flash_write_send(struct bfa_flash *flash)
+{
+ struct bfi_flash_write_req *msg =
+ (struct bfi_flash_write_req *) flash->mb.msg;
+ u32 len;
+
+ msg->type = be32_to_cpu(flash->type);
+ msg->instance = flash->instance;
+ msg->offset = be32_to_cpu(flash->addr_off + flash->offset);
+ len = (flash->residue < BFA_FLASH_DMA_BUF_SZ) ?
+ flash->residue : BFA_FLASH_DMA_BUF_SZ;
+ msg->length = be32_to_cpu(len);
+
+ /* indicate if it's the last msg of the whole write operation */
+ msg->last = (len == flash->residue) ? 1 : 0;
+
+ bfi_h2i_set(msg->mh, BFI_MC_FLASH, BFI_FLASH_H2I_WRITE_REQ,
+ bfa_ioc_portid(flash->ioc));
+ bfa_alen_set(&msg->alen, len, flash->dbuf_pa);
+ memcpy(flash->dbuf_kva, flash->ubuf + flash->offset, len);
+ bfa_nw_ioc_mbox_queue(flash->ioc, &flash->mb, NULL, NULL);
+
+ flash->residue -= len;
+ flash->offset += len;
+}
+
+/*
+ * Send flash read request.
+ *
+ * @param[in] cbarg - callback argument
+ */
+static void
+bfa_flash_read_send(void *cbarg)
+{
+ struct bfa_flash *flash = cbarg;
+ struct bfi_flash_read_req *msg =
+ (struct bfi_flash_read_req *) flash->mb.msg;
+ u32 len;
+
+ msg->type = be32_to_cpu(flash->type);
+ msg->instance = flash->instance;
+ msg->offset = be32_to_cpu(flash->addr_off + flash->offset);
+ len = (flash->residue < BFA_FLASH_DMA_BUF_SZ) ?
+ flash->residue : BFA_FLASH_DMA_BUF_SZ;
+ msg->length = be32_to_cpu(len);
+ bfi_h2i_set(msg->mh, BFI_MC_FLASH, BFI_FLASH_H2I_READ_REQ,
+ bfa_ioc_portid(flash->ioc));
+ bfa_alen_set(&msg->alen, len, flash->dbuf_pa);
+ bfa_nw_ioc_mbox_queue(flash->ioc, &flash->mb, NULL, NULL);
+}
+
+/*
+ * Process flash response messages upon receiving interrupts.
+ *
+ * @param[in] flasharg - flash structure
+ * @param[in] msg - message structure
+ */
+static void
+bfa_flash_intr(void *flasharg, struct bfi_mbmsg *msg)
+{
+ struct bfa_flash *flash = flasharg;
+ u32 status;
+
+ union {
+ struct bfi_flash_query_rsp *query;
+ struct bfi_flash_write_rsp *write;
+ struct bfi_flash_read_rsp *read;
+ struct bfi_mbmsg *msg;
+ } m;
+
+ m.msg = msg;
+
+ /* receiving response after ioc failure */
+ if (!flash->op_busy && msg->mh.msg_id != BFI_FLASH_I2H_EVENT)
+ return;
+
+ switch (msg->mh.msg_id) {
+ case BFI_FLASH_I2H_QUERY_RSP:
+ status = be32_to_cpu(m.query->status);
+ if (status == BFA_STATUS_OK) {
+ u32 i;
+ struct bfa_flash_attr *attr, *f;
+
+ attr = (struct bfa_flash_attr *) flash->ubuf;
+ f = (struct bfa_flash_attr *) flash->dbuf_kva;
+ attr->status = be32_to_cpu(f->status);
+ attr->npart = be32_to_cpu(f->npart);
+ for (i = 0; i < attr->npart; i++) {
+ attr->part[i].part_type =
+ be32_to_cpu(f->part[i].part_type);
+ attr->part[i].part_instance =
+ be32_to_cpu(f->part[i].part_instance);
+ attr->part[i].part_off =
+ be32_to_cpu(f->part[i].part_off);
+ attr->part[i].part_size =
+ be32_to_cpu(f->part[i].part_size);
+ attr->part[i].part_len =
+ be32_to_cpu(f->part[i].part_len);
+ attr->part[i].part_status =
+ be32_to_cpu(f->part[i].part_status);
+ }
+ }
+ flash->status = status;
+ bfa_flash_cb(flash);
+ break;
+ case BFI_FLASH_I2H_WRITE_RSP:
+ status = be32_to_cpu(m.write->status);
+ if (status != BFA_STATUS_OK || flash->residue == 0) {
+ flash->status = status;
+ bfa_flash_cb(flash);
+ } else
+ bfa_flash_write_send(flash);
+ break;
+ case BFI_FLASH_I2H_READ_RSP:
+ status = be32_to_cpu(m.read->status);
+ if (status != BFA_STATUS_OK) {
+ flash->status = status;
+ bfa_flash_cb(flash);
+ } else {
+ u32 len = be32_to_cpu(m.read->length);
+ memcpy(flash->ubuf + flash->offset,
+ flash->dbuf_kva, len);
+ flash->residue -= len;
+ flash->offset += len;
+ if (flash->residue == 0) {
+ flash->status = status;
+ bfa_flash_cb(flash);
+ } else
+ bfa_flash_read_send(flash);
+ }
+ break;
+ case BFI_FLASH_I2H_BOOT_VER_RSP:
+ case BFI_FLASH_I2H_EVENT:
+ break;
+ default:
+ WARN_ON(1);
+ }
+}
+
+/*
+ * Flash memory info API.
+ */
+u32
+bfa_nw_flash_meminfo(void)
+{
+ return roundup(BFA_FLASH_DMA_BUF_SZ, BFA_DMA_ALIGN_SZ);
+}
+
+/*
+ * Flash attach API.
+ *
+ * @param[in] flash - flash structure
+ * @param[in] ioc - ioc structure
+ * @param[in] dev - device structure
+ */
+void
+bfa_nw_flash_attach(struct bfa_flash *flash, struct bfa_ioc *ioc, void *dev)
+{
+ flash->ioc = ioc;
+ flash->cbfn = NULL;
+ flash->cbarg = NULL;
+ flash->op_busy = 0;
+
+ bfa_nw_ioc_mbox_regisr(flash->ioc, BFI_MC_FLASH, bfa_flash_intr, flash);
+ bfa_q_qe_init(&flash->ioc_notify);
+ bfa_ioc_notify_init(&flash->ioc_notify, bfa_flash_notify, flash);
+ list_add_tail(&flash->ioc_notify.qe, &flash->ioc->notify_q);
+}
+
+/*
+ * Claim memory for flash
+ *
+ * @param[in] flash - flash structure
+ * @param[in] dm_kva - pointer to virtual memory address
+ * @param[in] dm_pa - physical memory address
+ */
+void
+bfa_nw_flash_memclaim(struct bfa_flash *flash, u8 *dm_kva, u64 dm_pa)
+{
+ flash->dbuf_kva = dm_kva;
+ flash->dbuf_pa = dm_pa;
+ memset(flash->dbuf_kva, 0, BFA_FLASH_DMA_BUF_SZ);
+ dm_kva += roundup(BFA_FLASH_DMA_BUF_SZ, BFA_DMA_ALIGN_SZ);
+ dm_pa += roundup(BFA_FLASH_DMA_BUF_SZ, BFA_DMA_ALIGN_SZ);
+}
+
+/*
+ * Get flash attribute.
+ *
+ * @param[in] flash - flash structure
+ * @param[in] attr - flash attribute structure
+ * @param[in] cbfn - callback function
+ * @param[in] cbarg - callback argument
+ *
+ * Return status.
+ */
+enum bfa_status
+bfa_nw_flash_get_attr(struct bfa_flash *flash, struct bfa_flash_attr *attr,
+ bfa_cb_flash cbfn, void *cbarg)
+{
+ struct bfi_flash_query_req *msg =
+ (struct bfi_flash_query_req *) flash->mb.msg;
+
+ if (!bfa_nw_ioc_is_operational(flash->ioc))
+ return BFA_STATUS_IOC_NON_OP;
+
+ if (flash->op_busy)
+ return BFA_STATUS_DEVBUSY;
+
+ flash->op_busy = 1;
+ flash->cbfn = cbfn;
+ flash->cbarg = cbarg;
+ flash->ubuf = (u8 *) attr;
+
+ bfi_h2i_set(msg->mh, BFI_MC_FLASH, BFI_FLASH_H2I_QUERY_REQ,
+ bfa_ioc_portid(flash->ioc));
+ bfa_alen_set(&msg->alen, sizeof(struct bfa_flash_attr), flash->dbuf_pa);
+ bfa_nw_ioc_mbox_queue(flash->ioc, &flash->mb, NULL, NULL);
+
+ return BFA_STATUS_OK;
+}
+
+/*
+ * Update flash partition.
+ *
+ * @param[in] flash - flash structure
+ * @param[in] type - flash partition type
+ * @param[in] instance - flash partition instance
+ * @param[in] buf - update data buffer
+ * @param[in] len - data buffer length
+ * @param[in] offset - offset relative to the partition starting address
+ * @param[in] cbfn - callback function
+ * @param[in] cbarg - callback argument
+ *
+ * Return status.
+ */
+enum bfa_status
+bfa_nw_flash_update_part(struct bfa_flash *flash, u32 type, u8 instance,
+ void *buf, u32 len, u32 offset,
+ bfa_cb_flash cbfn, void *cbarg)
+{
+ if (!bfa_nw_ioc_is_operational(flash->ioc))
+ return BFA_STATUS_IOC_NON_OP;
+
+ /*
+ * 'len' must be in word (4-byte) boundary
+ */
+ if (!len || (len & 0x03))
+ return BFA_STATUS_FLASH_BAD_LEN;
+
+ if (type == BFA_FLASH_PART_MFG)
+ return BFA_STATUS_EINVAL;
+
+ if (flash->op_busy)
+ return BFA_STATUS_DEVBUSY;
+
+ flash->op_busy = 1;
+ flash->cbfn = cbfn;
+ flash->cbarg = cbarg;
+ flash->type = type;
+ flash->instance = instance;
+ flash->residue = len;
+ flash->offset = 0;
+ flash->addr_off = offset;
+ flash->ubuf = buf;
+
+ bfa_flash_write_send(flash);
+
+ return BFA_STATUS_OK;
+}
+
+/*
+ * Read flash partition.
+ *
+ * @param[in] flash - flash structure
+ * @param[in] type - flash partition type
+ * @param[in] instance - flash partition instance
+ * @param[in] buf - read data buffer
+ * @param[in] len - data buffer length
+ * @param[in] offset - offset relative to the partition starting address
+ * @param[in] cbfn - callback function
+ * @param[in] cbarg - callback argument
+ *
+ * Return status.
+ */
+enum bfa_status
+bfa_nw_flash_read_part(struct bfa_flash *flash, u32 type, u8 instance,
+ void *buf, u32 len, u32 offset,
+ bfa_cb_flash cbfn, void *cbarg)
+{
+ if (!bfa_nw_ioc_is_operational(flash->ioc))
+ return BFA_STATUS_IOC_NON_OP;
+
+ /*
+ * 'len' must be in word (4-byte) boundary
+ */
+ if (!len || (len & 0x03))
+ return BFA_STATUS_FLASH_BAD_LEN;
+
+ if (flash->op_busy)
+ return BFA_STATUS_DEVBUSY;
+
+ flash->op_busy = 1;
+ flash->cbfn = cbfn;
+ flash->cbarg = cbarg;
+ flash->type = type;
+ flash->instance = instance;
+ flash->residue = len;
+ flash->offset = 0;
+ flash->addr_off = offset;
+ flash->ubuf = buf;
+
+ bfa_flash_read_send(flash);
+
+ return BFA_STATUS_OK;
+}
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.h b/drivers/net/ethernet/brocade/bna/bfa_ioc.h
index ca158d1..fc108c7 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc.h
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.h
@@ -68,6 +68,16 @@ __bfa_dma_be_addr_set(union bfi_addr_u *dma_addr, u64 pa)
dma_addr->a32.addr_hi = (u32) htonl(upper_32_bits(pa));
}
+#define bfa_alen_set(__alen, __len, __pa) \
+ __bfa_alen_set(__alen, __len, (u64)__pa)
+
+static inline void
+__bfa_alen_set(struct bfi_alen *alen, u32 len, u64 pa)
+{
+ alen->al_len = cpu_to_be32(len);
+ bfa_dma_be_addr_set(alen->al_addr, pa);
+}
+
struct bfa_ioc_regs {
void __iomem *hfn_mbox_cmd;
void __iomem *hfn_mbox;
@@ -322,4 +332,42 @@ void bfa_nw_iocpf_sem_timeout(void *ioc);
u32 *bfa_cb_image_get_chunk(enum bfi_asic_gen asic_gen, u32 off);
u32 bfa_cb_image_get_size(enum bfi_asic_gen asic_gen);
+/*
+ * Flash module specific
+ */
+typedef void (*bfa_cb_flash) (void *cbarg, enum bfa_status status);
+
+struct bfa_flash {
+ struct bfa_ioc *ioc; /* back pointer to ioc */
+ u32 type; /* partition type */
+ u8 instance; /* partition instance */
+ u8 rsv[3];
+ u32 op_busy; /* operation busy flag */
+ u32 residue; /* residual length */
+ u32 offset; /* offset */
+ enum bfa_status status; /* status */
+ u8 *dbuf_kva; /* dma buf virtual address */
+ u64 dbuf_pa; /* dma buf physical address */
+ bfa_cb_flash cbfn; /* user callback function */
+ void *cbarg; /* user callback arg */
+ u8 *ubuf; /* user supplied buffer */
+ u32 addr_off; /* partition address offset */
+ struct bfa_mbox_cmd mb; /* mailbox */
+ struct bfa_ioc_notify ioc_notify; /* ioc event notify */
+};
+
+enum bfa_status bfa_nw_flash_get_attr(struct bfa_flash *flash,
+ struct bfa_flash_attr *attr,
+ bfa_cb_flash cbfn, void *cbarg);
+enum bfa_status bfa_nw_flash_update_part(struct bfa_flash *flash,
+ u32 type, u8 instance, void *buf, u32 len, u32 offset,
+ bfa_cb_flash cbfn, void *cbarg);
+enum bfa_status bfa_nw_flash_read_part(struct bfa_flash *flash,
+ u32 type, u8 instance, void *buf, u32 len, u32 offset,
+ bfa_cb_flash cbfn, void *cbarg);
+u32 bfa_nw_flash_meminfo(void);
+void bfa_nw_flash_attach(struct bfa_flash *flash,
+ struct bfa_ioc *ioc, void *dev);
+void bfa_nw_flash_memclaim(struct bfa_flash *flash, u8 *dm_kva, u64 dm_pa);
+
#endif /* __BFA_IOC_H__ */
diff --git a/drivers/net/ethernet/brocade/bna/bfi.h b/drivers/net/ethernet/brocade/bna/bfi.h
index 7a1393a..8230970 100644
--- a/drivers/net/ethernet/brocade/bna/bfi.h
+++ b/drivers/net/ethernet/brocade/bna/bfi.h
@@ -83,6 +83,14 @@ union bfi_addr_u {
} a32;
};
+/**
+ * Generic DMA addr-len pair.
+ */
+struct bfi_alen {
+ union bfi_addr_u al_addr; /* DMA addr of buffer */
+ u32 al_len; /* length of buffer */
+};
+
/*
* Large Message structure - 128 Bytes size Msgs
*/
@@ -476,6 +484,93 @@ struct bfi_msgq_i2h_cmdq_copy_req {
u16 len;
};
+/*
+ * FLASH module specific
+ */
+enum bfi_flash_h2i_msgs {
+ BFI_FLASH_H2I_QUERY_REQ = 1,
+ BFI_FLASH_H2I_ERASE_REQ = 2,
+ BFI_FLASH_H2I_WRITE_REQ = 3,
+ BFI_FLASH_H2I_READ_REQ = 4,
+ BFI_FLASH_H2I_BOOT_VER_REQ = 5,
+};
+
+enum bfi_flash_i2h_msgs {
+ BFI_FLASH_I2H_QUERY_RSP = BFA_I2HM(1),
+ BFI_FLASH_I2H_ERASE_RSP = BFA_I2HM(2),
+ BFI_FLASH_I2H_WRITE_RSP = BFA_I2HM(3),
+ BFI_FLASH_I2H_READ_RSP = BFA_I2HM(4),
+ BFI_FLASH_I2H_BOOT_VER_RSP = BFA_I2HM(5),
+ BFI_FLASH_I2H_EVENT = BFA_I2HM(127),
+};
+
+/*
+ * Flash query request
+ */
+struct bfi_flash_query_req {
+ struct bfi_mhdr mh; /* Common msg header */
+ struct bfi_alen alen;
+};
+
+/*
+ * Flash write request
+ */
+struct bfi_flash_write_req {
+ struct bfi_mhdr mh; /* Common msg header */
+ struct bfi_alen alen;
+ u32 type; /* partition type */
+ u8 instance; /* partition instance */
+ u8 last;
+ u8 rsv[2];
+ u32 offset;
+ u32 length;
+};
+
+/*
+ * Flash read request
+ */
+struct bfi_flash_read_req {
+ struct bfi_mhdr mh; /* Common msg header */
+ u32 type; /* partition type */
+ u8 instance; /* partition instance */
+ u8 rsv[3];
+ u32 offset;
+ u32 length;
+ struct bfi_alen alen;
+};
+
+/*
+ * Flash query response
+ */
+struct bfi_flash_query_rsp {
+ struct bfi_mhdr mh; /* Common msg header */
+ u32 status;
+};
+
+/*
+ * Flash read response
+ */
+struct bfi_flash_read_rsp {
+ struct bfi_mhdr mh; /* Common msg header */
+ u32 type; /* partition type */
+ u8 instance; /* partition instance */
+ u8 rsv[3];
+ u32 status;
+ u32 length;
+};
+
+/*
+ * Flash write response
+ */
+struct bfi_flash_write_rsp {
+ struct bfi_mhdr mh; /* Common msg header */
+ u32 type; /* partition type */
+ u8 instance; /* partition instance */
+ u8 rsv[3];
+ u32 status;
+ u32 length;
+};
+
#pragma pack()
#endif /* __BFI_H__ */
diff --git a/drivers/net/ethernet/brocade/bna/bna_enet.c b/drivers/net/ethernet/brocade/bna/bna_enet.c
index 26f5c5a..bcfe296 100644
--- a/drivers/net/ethernet/brocade/bna/bna_enet.c
+++ b/drivers/net/ethernet/brocade/bna/bna_enet.c
@@ -1740,6 +1740,11 @@ bna_ioceth_init(struct bna_ioceth *ioceth, struct bna *bna,
kva += bfa_nw_cee_meminfo();
dma += bfa_nw_cee_meminfo();
+ bfa_nw_flash_attach(&bna->flash, &ioceth->ioc, bna);
+ bfa_nw_flash_memclaim(&bna->flash, kva, dma);
+ kva += bfa_nw_flash_meminfo();
+ dma += bfa_nw_flash_meminfo();
+
bfa_msgq_attach(&bna->msgq, &ioceth->ioc);
bfa_msgq_memclaim(&bna->msgq, kva, dma);
bfa_msgq_regisr(&bna->msgq, BFI_MC_ENET, bna_msgq_rsp_handler, bna);
@@ -1892,7 +1897,8 @@ bna_res_req(struct bna_res_info *res_info)
res_info[BNA_RES_MEM_T_COM].res_u.mem_info.num = 1;
res_info[BNA_RES_MEM_T_COM].res_u.mem_info.len = ALIGN(
(bfa_nw_cee_meminfo() +
- bfa_msgq_meminfo()), PAGE_SIZE);
+ bfa_nw_flash_meminfo() +
+ bfa_msgq_meminfo()), PAGE_SIZE);
/* DMA memory for retrieving IOC attributes */
res_info[BNA_RES_MEM_T_ATTR].res_type = BNA_RES_T_MEM;
diff --git a/drivers/net/ethernet/brocade/bna/bna_types.h b/drivers/net/ethernet/brocade/bna/bna_types.h
index d090fbf..8e57fc5 100644
--- a/drivers/net/ethernet/brocade/bna/bna_types.h
+++ b/drivers/net/ethernet/brocade/bna/bna_types.h
@@ -966,6 +966,7 @@ struct bna {
struct bna_ioceth ioceth;
struct bfa_cee cee;
+ struct bfa_flash flash;
struct bfa_msgq msgq;
struct bna_ethport ethport;
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index 197af04..741f2e4 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -48,7 +48,9 @@ MODULE_PARM_DESC(bnad_ioc_auto_recover, "Enable / Disable auto recovery");
* Global variables
*/
u32 bnad_rxqs_per_cq = 2;
-
+u32 bna_id;
+struct mutex bnad_list_mutex;
+LIST_HEAD(bnad_list);
static const u8 bnad_bcast_addr[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
/*
@@ -75,6 +77,23 @@ do { \
#define BNAD_TXRX_SYNC_MDELAY 250 /* 250 msecs */
+static void
+bnad_add_to_list(struct bnad *bnad)
+{
+ mutex_lock(&bnad_list_mutex);
+ list_add_tail(&bnad->list_entry, &bnad_list);
+ bnad->id = bna_id++;
+ mutex_unlock(&bnad_list_mutex);
+}
+
+static void
+bnad_remove_from_list(struct bnad *bnad)
+{
+ mutex_lock(&bnad_list_mutex);
+ list_del(&bnad->list_entry);
+ mutex_unlock(&bnad_list_mutex);
+}
+
/*
* Reinitialize completions in CQ, once Rx is taken down
*/
@@ -1084,6 +1103,16 @@ bnad_cb_enet_mtu_set(struct bnad *bnad)
complete(&bnad->bnad_completions.mtu_comp);
}
+void
+bnad_cb_completion(void *arg, enum bfa_status status)
+{
+ struct bnad_iocmd_comp *iocmd_comp =
+ (struct bnad_iocmd_comp *)arg;
+
+ iocmd_comp->comp_status = (u32) status;
+ complete(&iocmd_comp->comp);
+}
+
/* Resource allocation, free functions */
static void
@@ -3167,12 +3196,14 @@ bnad_lock_init(struct bnad *bnad)
{
spin_lock_init(&bnad->bna_lock);
mutex_init(&bnad->conf_mutex);
+ mutex_init(&bnad_list_mutex);
}
static void
bnad_lock_uninit(struct bnad *bnad)
{
mutex_destroy(&bnad->conf_mutex);
+ mutex_destroy(&bnad_list_mutex);
}
/* PCI Initialization */
@@ -3253,8 +3284,8 @@ bnad_pci_probe(struct pci_dev *pdev,
return err;
}
bnad = netdev_priv(netdev);
-
bnad_lock_init(bnad);
+ bnad_add_to_list(bnad);
mutex_lock(&bnad->conf_mutex);
/*
@@ -3407,6 +3438,7 @@ pci_uninit:
bnad_pci_uninit(pdev);
unlock_mutex:
mutex_unlock(&bnad->conf_mutex);
+ bnad_remove_from_list(bnad);
bnad_lock_uninit(bnad);
free_netdev(netdev);
return err;
@@ -3445,6 +3477,7 @@ bnad_pci_remove(struct pci_dev *pdev)
bnad_disable_msix(bnad);
bnad_pci_uninit(pdev);
mutex_unlock(&bnad->conf_mutex);
+ bnad_remove_from_list(bnad);
bnad_lock_uninit(bnad);
bnad_uninit(bnad);
free_netdev(netdev);
diff --git a/drivers/net/ethernet/brocade/bna/bnad.h b/drivers/net/ethernet/brocade/bna/bnad.h
index 5487ca4..459030c 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.h
+++ b/drivers/net/ethernet/brocade/bna/bnad.h
@@ -124,6 +124,12 @@ enum bnad_link_state {
BNAD_LS_UP = 1
};
+struct bnad_iocmd_comp {
+ struct bnad *bnad;
+ struct completion comp;
+ int comp_status;
+};
+
struct bnad_completion {
struct completion ioc_comp;
struct completion ucast_comp;
@@ -251,6 +257,8 @@ struct bnad_unmap_q {
struct bnad {
struct net_device *netdev;
+ u32 id;
+ struct list_head list_entry;
/* Data path */
struct bnad_tx_info tx_info[BNAD_MAX_TX];
@@ -340,6 +348,7 @@ extern int bnad_mac_addr_set_locked(struct bnad *bnad, u8 *mac_addr);
extern int bnad_enable_default_bcast(struct bnad *bnad);
extern void bnad_restore_vlans(struct bnad *bnad, u32 rx_id);
extern void bnad_set_ethtool_ops(struct net_device *netdev);
+extern void bnad_cb_completion(void *arg, enum bfa_status status);
/* Configuration & setup */
extern void bnad_tx_coalescing_timeo_set(struct bnad *bnad);
diff --git a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
index 38d5c66..5f7be5a 100644
--- a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
+++ b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
@@ -935,6 +935,143 @@ bnad_get_sset_count(struct net_device *netdev, int sset)
}
}
+static u32
+bnad_get_flash_partition_by_offset(struct bnad *bnad, u32 offset,
+ u32 *base_offset)
+{
+ struct bfa_flash_attr *flash_attr;
+ struct bnad_iocmd_comp fcomp;
+ u32 i, flash_part = 0, ret;
+ unsigned long flags = 0;
+
+ flash_attr = kzalloc(sizeof(struct bfa_flash_attr), GFP_KERNEL);
+ if (!flash_attr)
+ return -ENOMEM;
+
+ fcomp.bnad = bnad;
+ fcomp.comp_status = 0;
+
+ init_completion(&fcomp.comp);
+ spin_lock_irqsave(&bnad->bna_lock, flags);
+ ret = bfa_nw_flash_get_attr(&bnad->bna.flash, flash_attr,
+ bnad_cb_completion, &fcomp);
+ if (ret != BFA_STATUS_OK) {
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ kfree(flash_attr);
+ goto out_err;
+ }
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ wait_for_completion(&fcomp.comp);
+ ret = fcomp.comp_status;
+
+ /* Check for the flash type & base offset value */
+ if (ret == BFA_STATUS_OK) {
+ for (i = 0; i < flash_attr->npart; i++) {
+ if (offset >= flash_attr->part[i].part_off &&
+ offset < (flash_attr->part[i].part_off +
+ flash_attr->part[i].part_size)) {
+ flash_part = flash_attr->part[i].part_type;
+ *base_offset = flash_attr->part[i].part_off;
+ break;
+ }
+ }
+ }
+ kfree(flash_attr);
+ return flash_part;
+out_err:
+ return -EINVAL;
+}
+
+static int
+bnad_get_eeprom_len(struct net_device *netdev)
+{
+ return BFA_TOTAL_FLASH_SIZE;
+}
+
+static int
+bnad_get_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom,
+ u8 *bytes)
+{
+ struct bnad *bnad = netdev_priv(netdev);
+ struct bnad_iocmd_comp fcomp;
+ u32 flash_part = 0, base_offset = 0;
+ unsigned long flags = 0;
+ int ret = 0;
+
+ /* Check if the flash read request is valid */
+ if (eeprom->magic != (bnad->pcidev->vendor |
+ (bnad->pcidev->device << 16)))
+ return -EFAULT;
+
+ /* Query the flash partition based on the offset */
+ flash_part = bnad_get_flash_partition_by_offset(bnad,
+ eeprom->offset, &base_offset);
+ if (flash_part <= 0)
+ return -EFAULT;
+
+ fcomp.bnad = bnad;
+ fcomp.comp_status = 0;
+
+ init_completion(&fcomp.comp);
+ spin_lock_irqsave(&bnad->bna_lock, flags);
+ ret = bfa_nw_flash_read_part(&bnad->bna.flash, flash_part,
+ bnad->id, bytes, eeprom->len,
+ eeprom->offset - base_offset,
+ bnad_cb_completion, &fcomp);
+ if (ret != BFA_STATUS_OK) {
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ goto done;
+ }
+
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ wait_for_completion(&fcomp.comp);
+ ret = fcomp.comp_status;
+done:
+ return ret;
+}
+
+static int
+bnad_set_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom,
+ u8 *bytes)
+{
+ struct bnad *bnad = netdev_priv(netdev);
+ struct bnad_iocmd_comp fcomp;
+ u32 flash_part = 0, base_offset = 0;
+ unsigned long flags = 0;
+ int ret = 0;
+
+ /* Check if the flash update request is valid */
+ if (eeprom->magic != (bnad->pcidev->vendor |
+ (bnad->pcidev->device << 16)))
+ return -EINVAL;
+
+ /* Query the flash partition based on the offset */
+ flash_part = bnad_get_flash_partition_by_offset(bnad,
+ eeprom->offset, &base_offset);
+ if (flash_part <= 0)
+ return -EFAULT;
+
+ fcomp.bnad = bnad;
+ fcomp.comp_status = 0;
+
+ init_completion(&fcomp.comp);
+ spin_lock_irqsave(&bnad->bna_lock, flags);
+ ret = bfa_nw_flash_update_part(&bnad->bna.flash, flash_part,
+ bnad->id, bytes, eeprom->len,
+ eeprom->offset - base_offset,
+ bnad_cb_completion, &fcomp);
+ if (ret != BFA_STATUS_OK) {
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ goto done;
+ }
+
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ wait_for_completion(&fcomp.comp);
+ ret = fcomp.comp_status;
+done:
+ return ret;
+}
+
static struct ethtool_ops bnad_ethtool_ops = {
.get_settings = bnad_get_settings,
.set_settings = bnad_set_settings,
@@ -949,7 +1086,10 @@ static struct ethtool_ops bnad_ethtool_ops = {
.set_pauseparam = bnad_set_pauseparam,
.get_strings = bnad_get_strings,
.get_ethtool_stats = bnad_get_ethtool_stats,
- .get_sset_count = bnad_get_sset_count
+ .get_sset_count = bnad_get_sset_count,
+ .get_eeprom_len = bnad_get_eeprom_len,
+ .get_eeprom = bnad_get_eeprom,
+ .set_eeprom = bnad_set_eeprom,
};
void
--
1.7.3.rc1
^ permalink raw reply related
* [PATCH v2] rps: fix insufficient bounds checking in store_rps_dev_flow_table_cnt()
From: Xi Wang @ 2011-12-22 23:35 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Tom Herbert, David S. Miller, netdev
In-Reply-To: <1324493459-19764-1-git-send-email-xi.wang@gmail.com>
Setting a large rps_flow_cnt like (1 << 30) on 32-bit platform will
cause a kernel oops due to insufficient bounds checking.
if (count > 1<<30) {
/* Enforce a limit to prevent overflow */
return -EINVAL;
}
count = roundup_pow_of_two(count);
table = vmalloc(RPS_DEV_FLOW_TABLE_SIZE(count));
Note that the macro RPS_DEV_FLOW_TABLE_SIZE(count) is defined as:
... + (count * sizeof(struct rps_dev_flow))
where sizeof(struct rps_dev_flow) is 8. (1 << 30) * 8 will overflow
32 bits.
This patch replaces the magic number (1 << 30) with a symbolic bound.
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Xi Wang <xi.wang@gmail.com>
---
net/core/net-sysfs.c | 7 +++++--
1 files changed, 5 insertions(+), 2 deletions(-)
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index c71c434..385aefe 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -665,11 +665,14 @@ static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue,
if (count) {
int i;
- if (count > 1<<30) {
+ if (count > INT_MAX)
+ return -EINVAL;
+ count = roundup_pow_of_two(count);
+ if (count > (ULONG_MAX - sizeof(struct rps_dev_flow_table))
+ / sizeof(struct rps_dev_flow)) {
/* Enforce a limit to prevent overflow */
return -EINVAL;
}
- count = roundup_pow_of_two(count);
table = vmalloc(RPS_DEV_FLOW_TABLE_SIZE(count));
if (!table)
return -ENOMEM;
--
1.7.5.4
^ permalink raw reply related
* Re: 3.0.12 - unregister_pernet_gen_subsys hogging whole system
From: Nikola Ciprich @ 2011-12-22 21:52 UTC (permalink / raw)
To: linux-kernel mlist; +Cc: stable, netdev
In-Reply-To: <20111222151908.GA11020@pcnci.linuxbox.cz>
[-- Attachment #1: Type: text/plain, Size: 1882 bytes --]
> after updating one of our servers to 3.0.12 kernel, it became painfully slow (actually
> it's almost unusable).
>
> trying perf top, I see following:
>
> 27465.00 - 59.8% : unregister_pernet_gen_subsys
> 3144.00 - 6.8% : __start_notes
> 1211.00 - 2.6% : swiotlb_sync_sg
> 1155.00 - 2.5% : swiotlb_unmap_sg_attrs
> 621.00 - 1.4% : pci_pm_init
> 565.00 - 1.2% : swiotlb_map_sg_attrs
> 503.00 - 1.1% : cgroup_attach_task
crap, I was using too old perf binary - that might be reason why I wasn't able
to find any evidence of unregister_pernet_gen_subsys for 3.x kernels :)
I switched to 3.0.13 now (and actual perf) and it seems better..
Should the problem reappear, I'll report it..
sorry for the fuzz..
n.
>
> I wasn't too successfull trying to find something related, so I'd like to ask,
> which subsystem might be calling unregister_pernet_gen_subsys and why?
> I guess this is certaingly a bug... Could somebody please have a look at this?
> I'll provide all debugging information I can if needed..
>
> thanks a lot in advance
>
> with best regards
>
> nik
>
> --
> -------------------------------------
> Ing. Nikola CIPRICH
> LinuxBox.cz, s.r.o.
> 28. rijna 168, 709 01 Ostrava
>
> tel.: +420 596 603 142
> fax: +420 596 621 273
> mobil: +420 777 093 799
> www.linuxbox.cz
>
> mobil servis: +420 737 238 656
> email servis: servis@linuxbox.cz
> -------------------------------------
--
-------------------------------------
Ing. Nikola CIPRICH
LinuxBox.cz, s.r.o.
28. rijna 168, 709 01 Ostrava
tel.: +420 596 603 142
fax: +420 596 621 273
mobil: +420 777 093 799
www.linuxbox.cz
mobil servis: +420 737 238 656
email servis: servis@linuxbox.cz
-------------------------------------
[-- Attachment #2: Type: application/pgp-signature, Size: 198 bytes --]
^ permalink raw reply
* Re: [PATCH v9 3/9] socket: initial cgroup code.
From: Jason Baron @ 2011-12-22 21:10 UTC (permalink / raw)
To: Glauber Costa
Cc: davem, linux-kernel, paul, lizf, kamezawa.hiroyu, ebiederm,
gthelen, netdev, linux-mm, kirill, avagin, devel, eric.dumazet,
cgroups
In-Reply-To: <1323676029-5890-4-git-send-email-glommer@parallels.com>
On Mon, Dec 12, 2011 at 11:47:03AM +0400, Glauber Costa wrote:
> +
> +static bool mem_cgroup_is_root(struct mem_cgroup *memcg);
> +void sock_update_memcg(struct sock *sk)
> +{
> + /* A socket spends its whole life in the same cgroup */
> + if (sk->sk_cgrp) {
> + WARN_ON(1);
> + return;
> + }
> + if (static_branch(&memcg_socket_limit_enabled)) {
> + struct mem_cgroup *memcg;
> +
> + BUG_ON(!sk->sk_prot->proto_cgroup);
> +
> + rcu_read_lock();
> + memcg = mem_cgroup_from_task(current);
> + if (!mem_cgroup_is_root(memcg)) {
> + mem_cgroup_get(memcg);
> + sk->sk_cgrp = sk->sk_prot->proto_cgroup(memcg);
> + }
> + rcu_read_unlock();
> + }
> +}
> +EXPORT_SYMBOL(sock_update_memcg);
> +
> +void sock_release_memcg(struct sock *sk)
> +{
> + if (static_branch(&memcg_socket_limit_enabled) && sk->sk_cgrp) {
> + struct mem_cgroup *memcg;
> + WARN_ON(!sk->sk_cgrp->memcg);
> + memcg = sk->sk_cgrp->memcg;
> + mem_cgroup_put(memcg);
> + }
> +}
Hi Glauber,
I think for 'sock_release_memcg()', you want:
static inline sock_release_memcg(sk)
{
if (static_branch())
__sock_release_memcg();
}
And then re-define the current sock_release_memcg -> __sock_release_memcg().
In that way the straight line path is a single no-op. As currently
written, there is function call and then an immediate return.
Thanks,
-Jason
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply
* Re: [PATCH, v2] Xen: consolidate and simplify struct xenbus_driver instantiation
From: Ian Campbell @ 2011-12-22 20:38 UTC (permalink / raw)
To: Ben Hutchings
Cc: Jan Beulich, Konrad Rzeszutek Wilk, davem@davemloft.net,
dmitry.torokhov@gmail.com, FlorianSchandinat@gmx.de,
Jeremy Fitzhardinge, Jens Axboe, xen-devel@lists.xensource.com,
Konrad Rzeszutek Wilk, linux-kernel@vger.kernel.org,
netdev@vger.kernel.org
In-Reply-To: <1324565067.2897.2.camel@bwh-desktop>
On Thu, 2011-12-22 at 14:44 +0000, Ben Hutchings wrote:
> On Thu, 2011-12-22 at 11:57 +0000, Ian Campbell wrote:
> > On Thu, 2011-12-22 at 11:51 +0000, Jan Beulich wrote:
> > > >>> On 22.12.11 at 10:57, Ian Campbell <Ian.Campbell@citrix.com> wrote:
> > > > On Thu, 2011-12-22 at 09:08 +0000, Jan Beulich wrote:
> > > >> The 'name', 'owner', and 'mod_name' members are redundant with the
> > > >> identically named fields in the 'driver' sub-structure. Rather than
> > > >> switching each instance to specify these fields explicitly, introduce
> > > >> a macro to simplify this.
> > > >>
> > > >> Eliminate further redundancy by allowing the drvname argument to
> > > >> DEFINE_XENBUS_DRIVER() to be blank (in which case the first entry from
> > > >> the ID table will be used for .driver.name).
> > > >
> > > > Any reason not to always use DRV_NAME here (which is generally a bit
> > > > more specific e.g. "xen-foofront" rather than "foo") and rely on the id
> > > > table for the shorter names used in xenstore?
> > >
> > > That would imply that DRV_NAME is always defined, but I don't
> > > see this being the case.
> >
> > My mistake, I thought it was a Kbuild thing.
>
> You're maybe thinking of KBUILD_MODNAME.
Yes, I think I was.
Thanks,
Ian.
^ permalink raw reply
* Re: [PATCH 0/4] skb paged fragment destructors
From: David Miller @ 2011-12-22 19:34 UTC (permalink / raw)
To: mirqus; +Cc: Ian.Campbell, eric.dumazet, jesse.brandeburg, netdev
In-Reply-To: <CAHXqBFL7oHgeUvKpV3Z2ddhMK-5KEqXJsp7p_geiYWTH_zwtaA@mail.gmail.com>
From: Michał Mirosław <mirqus@gmail.com>
Date: Thu, 22 Dec 2011 20:29:30 +0100
> 2011/12/22 David Miller <davem@davemloft.net>:
>> From: Michał Mirosław <mirqus@gmail.com>
>> Date: Thu, 22 Dec 2011 19:34:21 +0100
>>
>>> 2011/12/22 Ian Campbell <Ian.Campbell@citrix.com>:
>>>> On Wed, 2011-12-21 at 19:28 +0000, David Miller wrote:
>>>>> From: Eric Dumazet <eric.dumazet@gmail.com>
>>>>> Date: Wed, 21 Dec 2011 15:02:18 +0100
>>>>> > No idea on this +2 point.
>>>>> I think I know, and I believe I instructed Alexey Kuznetsov to do
>>>>> this.
>>>>>
>>>>> When sendfile() is performed, we might start the SKB with the last few
>>>>> bytes of one page, and end the SKB with the first few bytes of another
>>>>> page.
>>>>>
>>>>> In order to fit a full 64K frame into an SKB in this situation we have
>>>>> to accomodate this case.
>>>> Thanks David, that makes sense.
>>>>
>>>> However I think you only actually need 1 extra page for that. If the
>>>> data in frag[0] starts at $offset then frag[16] will need to have
>>>> $offset bytes in it. e.g.
>>>> 4096-$offset + 4096*15 + $offset = 65536
>>>> which == 17 pages rather than 18.
>>>>
>>>> The following documents the status quo but I could update to switch to +
>>>> 1 instead if there are no flaws in the above logic...
>>>
>>> Since max IP datagram is 64K-1, adding ethernet and possibly VLAN
>>> headers makes the max size slightly above 64K and then you have
>>> 64K/PAGE_SIZE+2 pages appear in worst case.
>>
>> Headers go into the linear area, so they are not relevant for these
>> calculations.
>
> Does this hold for LRO'ed packets and packets sent via PF_PACKET socket?
LRO is for receive, not packets we build on transmit, and in any event
have their headers also pulled into the linear area before the stack
sees it.
For PF_PACKET, in the packet_snd() case it uses a linear SKB and in
the tpacket_snd() case it uses a linear SKB as well.
^ permalink raw reply
* Re: [PATCH 0/4] skb paged fragment destructors
From: Michał Mirosław @ 2011-12-22 19:29 UTC (permalink / raw)
To: David Miller; +Cc: Ian.Campbell, eric.dumazet, jesse.brandeburg, netdev
In-Reply-To: <20111222.134344.1685328354280164155.davem@davemloft.net>
2011/12/22 David Miller <davem@davemloft.net>:
> From: Michał Mirosław <mirqus@gmail.com>
> Date: Thu, 22 Dec 2011 19:34:21 +0100
>
>> 2011/12/22 Ian Campbell <Ian.Campbell@citrix.com>:
>>> On Wed, 2011-12-21 at 19:28 +0000, David Miller wrote:
>>>> From: Eric Dumazet <eric.dumazet@gmail.com>
>>>> Date: Wed, 21 Dec 2011 15:02:18 +0100
>>>> > No idea on this +2 point.
>>>> I think I know, and I believe I instructed Alexey Kuznetsov to do
>>>> this.
>>>>
>>>> When sendfile() is performed, we might start the SKB with the last few
>>>> bytes of one page, and end the SKB with the first few bytes of another
>>>> page.
>>>>
>>>> In order to fit a full 64K frame into an SKB in this situation we have
>>>> to accomodate this case.
>>> Thanks David, that makes sense.
>>>
>>> However I think you only actually need 1 extra page for that. If the
>>> data in frag[0] starts at $offset then frag[16] will need to have
>>> $offset bytes in it. e.g.
>>> 4096-$offset + 4096*15 + $offset = 65536
>>> which == 17 pages rather than 18.
>>>
>>> The following documents the status quo but I could update to switch to +
>>> 1 instead if there are no flaws in the above logic...
>>
>> Since max IP datagram is 64K-1, adding ethernet and possibly VLAN
>> headers makes the max size slightly above 64K and then you have
>> 64K/PAGE_SIZE+2 pages appear in worst case.
>
> Headers go into the linear area, so they are not relevant for these
> calculations.
Does this hold for LRO'ed packets and packets sent via PF_PACKET socket?
Best Regards,
Michał Mirosław
^ permalink raw reply
* Re: [PATCH] drivers/net/usb/asix: fixed asix_get_wol reported wrong wol status issue
From: Grant Grundler @ 2011-12-22 19:02 UTC (permalink / raw)
To: ASIX Allan Email [office]
Cc: davem, netdev, linux-kernel, Freddy Xin, Eugene,
ASIX Louis [蘇威陸]
In-Reply-To: <000c01ccc098$6b6c6690$424533b0$@com.tw>
On Thu, Dec 22, 2011 at 2:56 AM, ASIX Allan Email [office]
<allan@asix.com.tw> wrote:
> Dear David,
>
> This is my first time to submit the driver patch onto Linux kernel mainline source. Please correct me if anything is wrong on my submission way or email format. Thanks a lot for your great helps.
Hi Allan,
Thanks for submitting the patch. I can advise as well since this
probably won't get applied due to how the email is "structured".
Your email which includes the patch needs to follow the "patch format"
described in Documentation/SubmittingPatches (see linux source tree).
Your email should have three main sections:
1) commit log entry + signed-off-by lines followed by one line with
"---" (and nothing else). This text summarizes *why* the patch is
needed: what bug it fixes or feature it enables.
2) optional comments/information about the testing of the patch (e.g.
"tested on Samsung Chromebook" or other comments that do NOT belong in
the commit log entry above. This section can be empty - not required.
3) "diff -u" format patch (this is what "git diff" will produce).
Do not append any other emails or additional text.
thanks!
grant
>
> ========
> Fixed the asix_get_wol() routine reported wrong wol status issue.
> This fix had been verified on x86 Linux kernel 3.0.0-12-generic system with AX88772A/AX88772/Belkin AX88178 USB dongles, and the wol function works fine (can be waked up by receiving the magic packets).
>
> Signed-off-by: Allan Chou <allan@asix.com.tw>
> Tested-by: Allan Chou <allan@asix.com.tw>
> ---
> diff --uprN a/drivers/net/usb/asix.c b/drivers/net/usb/asix.c
> --- a/drivers/net/usb/asix.c 2011-12-15 14:01:49.000000000 +0800
> +++ b/drivers/net/usb/asix.c 2011-12-22 18:20:39.000000000 +0800
> @@ -36,7 +36,7 @@
> #include <linux/usb/usbnet.h>
> #include <linux/slab.h>
>
> -#define DRIVER_VERSION "08-Nov-2011"
> +#define DRIVER_VERSION "22-Dec-2011"
> #define DRIVER_NAME "asix"
>
> /* ASIX AX8817X based USB 2.0 Ethernet Devices */
> @@ -689,6 +689,10 @@ asix_get_wol(struct net_device *net, str
> }
> wolinfo->supported = WAKE_PHY | WAKE_MAGIC;
> wolinfo->wolopts = 0;
> + if (opt & AX_MONITOR_LINK)
> + wolinfo->wolopts |= WAKE_PHY;
> + if (opt & AX_MONITOR_MAGIC)
> + wolinfo->wolopts |= WAKE_MAGIC;
> }
>
> static int
>
>
> ---
> Best regards,
> Allan Chou
> Technical Support Division
> ASIX Electronics Corporation
> TEL: 886-3-5799500 ext.228
> FAX: 886-3-5799558
> E-mail: allan@asix.com.tw
> http://www.asix.com.tw/
>
>
> -----Original Message-----
> From: allan [mailto:allan@asix.com.tw]
> Sent: Saturday, December 17, 2011 10:36 AM
> To: 'Grant Grundler'
> Cc: 'Eugene'; 'netdev@vger.kernel.org'; 'Freddy Xin'; 'ASIX Louis [蘇威陸]'
> Subject: RE: drivers/net/usb/asix: bug in asix_get_wol
>
> Dear Grant,
>
> I will double check this issue and submit the revised patch to Linux kernel mainline source next week. Thanks a lot for your great helps.
>
>
> ---
> Best regards,
> Allan Chou
> Technical Support Division
> ASIX Electronics Corporation
> TEL: 886-3-5799500 ext.228
> FAX: 886-3-5799558
> E-mail: allan@asix.com.tw
> http://www.asix.com.tw/
>
> -----Original Message-----
> From: grundler@google.com [mailto:grundler@google.com] On Behalf Of Grant Grundler
> Sent: Saturday, December 17, 2011 6:16 AM
> To: ASIX Allan Email [office]
> Cc: Eugene; netdev@vger.kernel.org; Freddy Xin; ASIX Louis [蘇威陸]
> Subject: Re: drivers/net/usb/asix: bug in asix_get_wol
>
> On Thu, Dec 15, 2011 at 9:15 PM, ASIX Allan Email [office]
> <allan@asix.com.tw> wrote:
>> Resend without attachment due to below email server error.
> ...
>> -----Original Message-----
>> From: ASIX Allan Email [office] [mailto:allan@asix.com.tw]
>> Sent: Friday, December 16, 2011 11:38 AM
>> To: 'Grant Grundler'; 'Eugene'
>> Cc: 'netdev@vger.kernel.org'; 'Freddy Xin'; ASIX Louis [蘇威陸]
>> Subject: RE: drivers/net/usb/asix: bug in asix_get_wol
>> Importance: High
>>
>> Dear Grant and Eugene,
>>
>> Please refer to the attached file and below statements to modify the
>> asix_get_wol() routine and let us know if this suggestion can solve
>> your issues or not? Thanks a lot.
>
> Allan,
> Thanks for the response but it doesn't answer my previous question.
> Let me ask the same question differently.
>
> Does WOL support in asix driver need more than the four lines of code?
> Ie does MONITOR_MODE need to be enabled or anything like that?
>
>> ================
>> static void
>> asix_get_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo)
>> {
>> struct usbnet *dev = netdev_priv(net);
>> u8 opt;
>>
>> if (asix_read_cmd(dev, AX_CMD_READ_MONITOR_MODE, 0, 0, 1, &opt) < 0) {
>> wolinfo->supported = 0;
>> wolinfo->wolopts = 0;
>> return;
>> }
>> wolinfo->supported = WAKE_PHY | WAKE_MAGIC;
>> wolinfo->wolopts = 0;
>> if (opt & AX_MONITOR_LINK)
>> wolinfo->wolopts |= WAKE_PHY;
>> if (opt & AX_MONITOR_MAGIC)
>> wolinfo->wolopts |= WAKE_MAGIC;
>> }
>
> This looks remarkably similar to the code Eugene said enables WOL for
> him (and it works). I not able to find any difference.
>
> If you believe it was a mistake to remove these four lines of code,
> please submit a patch (See Documentation/SubmittingPatches) to add
> them back. You can add a "Tested-by: Eugene <elubarsky@gmail.com>"
> line after your own "Signed-off-by:" in the patch.
>
> thanks!
> grant
>
>
^ permalink raw reply
* [PATCH 2/2] netlink: wake up netlink listeners sooner (v2)
From: Stephen Hemminger @ 2011-12-22 18:52 UTC (permalink / raw)
To: davem; +Cc: netdev
In-Reply-To: <20111222185201.592156795@vyatta.com>
[-- Attachment #1: netlink-congest.patch --]
[-- Type: text/plain, Size: 712 bytes --]
This patch changes it to yield sooner at halfway instead. Still not a cure-all
for listener overrun if listner is slow, but works much reliably.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
---
v2 - use shift to avoid expensive integer division
--- a/net/netlink/af_netlink.c 2011-12-21 15:15:09.446373421 -0800
+++ b/net/netlink/af_netlink.c 2011-12-21 15:22:35.632062577 -0800
@@ -959,7 +959,7 @@ static int netlink_broadcast_deliver(str
skb_set_owner_r(skb, sk);
skb_queue_tail(&sk->sk_receive_queue, skb);
sk->sk_data_ready(sk, skb->len);
- return atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf;
+ return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1);
}
return -1;
}
^ permalink raw reply
* [PATCH 0/2] netlink patches
From: Stephen Hemminger @ 2011-12-22 18:52 UTC (permalink / raw)
To: davem; +Cc: netdev
^ permalink raw reply
* [PATCH 1/2] netlink: af_netlink cleanup (v2)
From: Stephen Hemminger @ 2011-12-22 18:52 UTC (permalink / raw)
To: davem; +Cc: netdev
In-Reply-To: <20111222185201.592156795@vyatta.com>
[-- Attachment #1: netlink-deinline.patch --]
[-- Type: text/plain, Size: 4401 bytes --]
Don't inline functions that cover several lines, and do inline
the trivial ones. Also make some arguments const.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
---
v2 - cleanup indentation of functions after change
--- a/net/netlink/af_netlink.c 2011-12-21 15:03:32.740915909 -0800
+++ b/net/netlink/af_netlink.c 2011-12-21 15:07:44.807155562 -0800
@@ -98,7 +98,7 @@ static inline struct netlink_sock *nlk_s
return container_of(sk, struct netlink_sock, sk);
}
-static inline int netlink_is_kernel(struct sock *sk)
+static inline int netlink_is_kernel(const struct sock *sk)
{
return nlk_sk(sk)->flags & NETLINK_KERNEL_SOCKET;
}
@@ -139,12 +139,12 @@ static atomic_t nl_table_users = ATOMIC_
static ATOMIC_NOTIFIER_HEAD(netlink_chain);
-static u32 netlink_group_mask(u32 group)
+static inline u32 netlink_group_mask(u32 group)
{
return group ? 1 << (group - 1) : 0;
}
-static struct hlist_head *nl_pid_hashfn(struct nl_pid_hash *hash, u32 pid)
+static inline struct hlist_head *nl_pid_hashfn(struct nl_pid_hash *hash, u32 pid)
{
return &hash->table[jhash_1word(pid, hash->rnd) & hash->mask];
}
@@ -226,8 +226,7 @@ netlink_unlock_table(void)
wake_up(&nl_table_wait);
}
-static inline struct sock *netlink_lookup(struct net *net, int protocol,
- u32 pid)
+static struct sock *netlink_lookup(struct net *net, int protocol, u32 pid)
{
struct nl_pid_hash *hash = &nl_table[protocol].hash;
struct hlist_head *head;
@@ -248,7 +247,7 @@ found:
return sk;
}
-static inline struct hlist_head *nl_pid_hash_zalloc(size_t size)
+static struct hlist_head *nl_pid_hash_zalloc(size_t size)
{
if (size <= PAGE_SIZE)
return kzalloc(size, GFP_ATOMIC);
@@ -258,7 +257,7 @@ static inline struct hlist_head *nl_pid_
get_order(size));
}
-static inline void nl_pid_hash_free(struct hlist_head *table, size_t size)
+static void nl_pid_hash_free(struct hlist_head *table, size_t size)
{
if (size <= PAGE_SIZE)
kfree(table);
@@ -578,7 +577,7 @@ retry:
return err;
}
-static inline int netlink_capable(struct socket *sock, unsigned int flag)
+static inline int netlink_capable(const struct socket *sock, unsigned int flag)
{
return (nl_table[sock->sk->sk_protocol].nl_nonroot & flag) ||
capable(CAP_NET_ADMIN);
@@ -846,8 +845,7 @@ void netlink_detachskb(struct sock *sk,
sock_put(sk);
}
-static inline struct sk_buff *netlink_trim(struct sk_buff *skb,
- gfp_t allocation)
+static struct sk_buff *netlink_trim(struct sk_buff *skb, gfp_t allocation)
{
int delta;
@@ -871,7 +869,7 @@ static inline struct sk_buff *netlink_tr
return skb;
}
-static inline void netlink_rcv_wake(struct sock *sk)
+static void netlink_rcv_wake(struct sock *sk)
{
struct netlink_sock *nlk = nlk_sk(sk);
@@ -881,7 +879,7 @@ static inline void netlink_rcv_wake(stru
wake_up_interruptible(&nlk->wait);
}
-static inline int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb)
+static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb)
{
int ret;
struct netlink_sock *nlk = nlk_sk(sk);
@@ -952,8 +950,7 @@ int netlink_has_listeners(struct sock *s
}
EXPORT_SYMBOL_GPL(netlink_has_listeners);
-static inline int netlink_broadcast_deliver(struct sock *sk,
- struct sk_buff *skb)
+static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb)
{
struct netlink_sock *nlk = nlk_sk(sk);
@@ -982,7 +979,7 @@ struct netlink_broadcast_data {
void *tx_data;
};
-static inline int do_one_broadcast(struct sock *sk,
+static int do_one_broadcast(struct sock *sk,
struct netlink_broadcast_data *p)
{
struct netlink_sock *nlk = nlk_sk(sk);
@@ -1110,8 +1107,7 @@ struct netlink_set_err_data {
int code;
};
-static inline int do_one_set_err(struct sock *sk,
- struct netlink_set_err_data *p)
+static int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p)
{
struct netlink_sock *nlk = nlk_sk(sk);
int ret = 0;
--- a/net/netlink/genetlink.c 2011-12-21 15:03:32.724915740 -0800
+++ b/net/netlink/genetlink.c 2011-12-21 15:03:34.992939390 -0800
@@ -106,7 +106,7 @@ static struct genl_ops *genl_get_cmd(u8
/* Of course we are going to have problems once we hit
* 2^16 alive types, but that can only happen by year 2K
*/
-static inline u16 genl_generate_id(void)
+static u16 genl_generate_id(void)
{
static u16 id_gen_idx = GENL_MIN_ID;
int i;
^ permalink raw reply
* Re: linux-3.0.x regression with ipv4 routes having mtu
From: David Miller @ 2011-12-22 18:51 UTC (permalink / raw)
To: steffen.klassert; +Cc: timo.teras, netdev
In-Reply-To: <20111222102526.GT6348@secunet.com>
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Thu, 22 Dec 2011 11:25:26 +0100
> Actually, I'm getting some doubts on the concept of caching
> the metrics on the inetpeer. How should we handle the case when
> we have multiple routes with different metrics to the same
> destination? As it is, we can cache just one of them on the
> inetpeer.
In such cases the metrics won't be perfect.
Actually, we have two kinds of metrics and it might be best in the
long term to seperate them out explicitly.
We have "loose" metrics (such as all the TCP measurements) which,
if incorrect, will lead to suboptimal performance but will not
dramatically effect connectivity.
Then we have "strict" metrics like PMTU information and redirects,
which could have more fatal consequences if wrong.
The core issue is I want to keep these things tied only to destination
address, it is the only sane way to get the routing cache removed.
Sockets and the packet forwarding path in the future will be using
routes that cover whole subnets, or even the default route. There
will be no "rt->rt_dst" and there will also be not attached inetpeer.
The inetpeer, or something like it, will be managed seperately.
Therefore metrics will need to be calculated using both objects (rt
and inetpeer).
This is one of the longer term design issues we face in the routing
cache removal and for which I don't have exact plans for yet. I'm
still concentrating on "ref-less" neighbour entries, so once I finish
that work I can think more seriously about metrics in a world without
the routing cache.
^ permalink raw reply
* Re: [PATCH 0/4] skb paged fragment destructors
From: David Miller @ 2011-12-22 18:43 UTC (permalink / raw)
To: mirqus; +Cc: Ian.Campbell, eric.dumazet, jesse.brandeburg, netdev
In-Reply-To: <CAHXqBF+U8g16M8_MvFSmOWrLrfiAnuOzn0Mzn9uurLpQym+m4A@mail.gmail.com>
From: Michał Mirosław <mirqus@gmail.com>
Date: Thu, 22 Dec 2011 19:34:21 +0100
> 2011/12/22 Ian Campbell <Ian.Campbell@citrix.com>:
>> On Wed, 2011-12-21 at 19:28 +0000, David Miller wrote:
>>> From: Eric Dumazet <eric.dumazet@gmail.com>
>>> Date: Wed, 21 Dec 2011 15:02:18 +0100
>>> > No idea on this +2 point.
>>> I think I know, and I believe I instructed Alexey Kuznetsov to do
>>> this.
>>>
>>> When sendfile() is performed, we might start the SKB with the last few
>>> bytes of one page, and end the SKB with the first few bytes of another
>>> page.
>>>
>>> In order to fit a full 64K frame into an SKB in this situation we have
>>> to accomodate this case.
>> Thanks David, that makes sense.
>>
>> However I think you only actually need 1 extra page for that. If the
>> data in frag[0] starts at $offset then frag[16] will need to have
>> $offset bytes in it. e.g.
>> 4096-$offset + 4096*15 + $offset = 65536
>> which == 17 pages rather than 18.
>>
>> The following documents the status quo but I could update to switch to +
>> 1 instead if there are no flaws in the above logic...
>
> Since max IP datagram is 64K-1, adding ethernet and possibly VLAN
> headers makes the max size slightly above 64K and then you have
> 64K/PAGE_SIZE+2 pages appear in worst case.
Headers go into the linear area, so they are not relevant for these
calculations.
^ permalink raw reply
* Re: [RFC] iproute2: split up ip man page?
From: Stephen Hemminger @ 2011-12-22 18:37 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: netdev
In-Reply-To: <20111207131514.6815f813@nehalam.linuxnetplumber.net>
On Wed, 7 Dec 2011 13:15:14 -0800
Stephen Hemminger <shemminger@vyatta.com> wrote:
> The current ip man page is both incomplete and so big that
> the actual functions get lost easily.
>
> I propose splitting the the pages for the subfunction
> into sub pages. The man command appears
> to be smart enough to handle:
> man tc htb
>
> and pickup the manpage for /usr/share/man/man1/tc-htb.8.gz
> Why not do the same thing for ip command?
>
> The base ip page would just be a place holder that covered the
> generic arguments.
>
>
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
Ok, the ip man page is now broken up. I tried to fix some of the
incorrect grammar and usage as well. The pages still need editing for
readability.
Added a few examples as well.
Please download from the git repository and send me any comments
or changes.
git://git.kernel.org/pub/scm/linux/kernel/git/shemminger/iproute2.git
^ permalink raw reply
* Re: [PATCH 0/4] skb paged fragment destructors
From: Michał Mirosław @ 2011-12-22 18:34 UTC (permalink / raw)
To: Ian Campbell
Cc: David Miller, eric.dumazet@gmail.com, jesse.brandeburg@intel.com,
netdev@vger.kernel.org
In-Reply-To: <1324550017.7877.77.camel@zakaz.uk.xensource.com>
2011/12/22 Ian Campbell <Ian.Campbell@citrix.com>:
> On Wed, 2011-12-21 at 19:28 +0000, David Miller wrote:
>> From: Eric Dumazet <eric.dumazet@gmail.com>
>> Date: Wed, 21 Dec 2011 15:02:18 +0100
>> > No idea on this +2 point.
>> I think I know, and I believe I instructed Alexey Kuznetsov to do
>> this.
>>
>> When sendfile() is performed, we might start the SKB with the last few
>> bytes of one page, and end the SKB with the first few bytes of another
>> page.
>>
>> In order to fit a full 64K frame into an SKB in this situation we have
>> to accomodate this case.
> Thanks David, that makes sense.
>
> However I think you only actually need 1 extra page for that. If the
> data in frag[0] starts at $offset then frag[16] will need to have
> $offset bytes in it. e.g.
> 4096-$offset + 4096*15 + $offset = 65536
> which == 17 pages rather than 18.
>
> The following documents the status quo but I could update to switch to +
> 1 instead if there are no flaws in the above logic...
Since max IP datagram is 64K-1, adding ethernet and possibly VLAN
headers makes the max size slightly above 64K and then you have
64K/PAGE_SIZE+2 pages appear in worst case.
Best Regards,
Michał Mirosław
^ permalink raw reply
* Re: BUG: unable to handle kernel NULL pointer dereference in ipv6_select_ident
From: David Miller @ 2011-12-22 18:29 UTC (permalink / raw)
To: eric.dumazet; +Cc: bootc, linux-kernel, netdev, steffen.klassert
In-Reply-To: <1324575692.2586.6.camel@edumazet-laptop>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Thu, 22 Dec 2011 18:41:32 +0100
> IPv6 needs multicast capabilities, so maybe balance-rr bonding mode is
> not propagating multicat filters properly on both nics.
>
> It might be a problem on one of your NIC.
This is my impression too, definitely some kind of multicast problem.
^ permalink raw reply
* Re: [PATCH 0/4] skb paged fragment destructors
From: David Miller @ 2011-12-22 18:20 UTC (permalink / raw)
To: Ian.Campbell; +Cc: eric.dumazet, jesse.brandeburg, netdev
In-Reply-To: <1324550017.7877.77.camel@zakaz.uk.xensource.com>
From: Ian Campbell <Ian.Campbell@citrix.com>
Date: Thu, 22 Dec 2011 10:33:36 +0000
> On Wed, 2011-12-21 at 19:28 +0000, David Miller wrote:
>> From: Eric Dumazet <eric.dumazet@gmail.com>
>> Date: Wed, 21 Dec 2011 15:02:18 +0100
>>
>> > No idea on this +2 point.
>>
>> I think I know, and I believe I instructed Alexey Kuznetsov to do
>> this.
>>
>> When sendfile() is performed, we might start the SKB with the last few
>> bytes of one page, and end the SKB with the first few bytes of another
>> page.
>>
>> In order to fit a full 64K frame into an SKB in this situation we have
>> to accomodate this case.
>
> Thanks David, that makes sense.
>
> However I think you only actually need 1 extra page for that. If the
> data in frag[0] starts at $offset then frag[16] will need to have
> $offset bytes in it. e.g.
> 4096-$offset + 4096*15 + $offset = 65536
> which == 17 pages rather than 18.
>
> The following documents the status quo but I could update to switch to +
> 1 instead if there are no flaws in the above logic...
Indeed, you're right. Please change this to 1 and document it, and we
can put that change into net-next, thanks a lot!
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox