Merge branch '10GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue
Jeff Kirsher says:
====================
10GbE Intel Wired LAN Driver Updates 2018-02-26
This series contains updates to ixgbe and ixgbevf only.
Colin Ian King cleans up redundant variable assignments.
Tonghao Zhang updates ixgbe to avoid writing to the hardware when the
redirection table has not changed.
Jake fixes the driver logic for checking and clearing receive timestamp
hangs so that when the PTP_RX_TIMESTAMP_IN_REGISTER flag is set, we no
longer need to check for receive timestamp hangs, which in turn will
stop the spurious log messages.
Emil updates ixgbevf with several features and improvements done in
other drivers, starting with the handling of page addresses so that we
always refer to them using a void pointer. Added a 'legacy-rx' flag to
allow switching between the old and new receive code paths. Added
support for using 3K buggers in order 1 page. Updated the driver to
ensure that calls to ixgbevf_open() are rtnl lock protected and improved
the error handling when setting up multiple queues. Added support for
providing a buffer with head room and tail room to allow for shared
info, NET_SKB_PAD, and NET_IP_ALIGN, so that we can start using
build_skb to build frames instead of using memcpy() the headers.
Updated the logic of handling rings closer to ixgbe. Consolidated the
receive paths to reduce duplication when we expand them in the future.
Added build_skb() support to ixgbevf.
====================
Signed-off-by: David S. Miller <[email protected]>
diff --git a/arch/arm/boot/dts/armada-370-rd.dts b/arch/arm/boot/dts/armada-370-rd.dts
index 8b2fa9a..c28afb2 100644
--- a/arch/arm/boot/dts/armada-370-rd.dts
+++ b/arch/arm/boot/dts/armada-370-rd.dts
@@ -56,6 +56,7 @@
/dts-v1/;
#include <dt-bindings/input/input.h>
+#include <dt-bindings/interrupt-controller/irq.h>
#include <dt-bindings/gpio/gpio.h>
#include "armada-370.dtsi"
@@ -243,6 +244,8 @@
#address-cells = <1>;
#size-cells = <0>;
reg = <0x10>;
+ interrupt-controller;
+ #interrupt-cells = <2>;
ports {
#address-cells = <1>;
@@ -278,6 +281,35 @@
};
};
};
+
+ mdio {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ switchphy0: switchphy@0 {
+ reg = <0>;
+ interrupt-parent = <&switch>;
+ interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
+ };
+
+ switchphy1: switchphy@1 {
+ reg = <1>;
+ interrupt-parent = <&switch>;
+ interrupts = <1 IRQ_TYPE_LEVEL_HIGH>;
+ };
+
+ switchphy2: switchphy@2 {
+ reg = <2>;
+ interrupt-parent = <&switch>;
+ interrupts = <2 IRQ_TYPE_LEVEL_HIGH>;
+ };
+
+ switchphy3: switchphy@3 {
+ reg = <3>;
+ interrupt-parent = <&switch>;
+ interrupts = <3 IRQ_TYPE_LEVEL_HIGH>;
+ };
+ };
};
};
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 45e4eb5..cbf94d4 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -61,7 +61,12 @@ static bool is_imm8(int value)
static bool is_simm32(s64 value)
{
- return value == (s64) (s32) value;
+ return value == (s64)(s32)value;
+}
+
+static bool is_uimm32(u64 value)
+{
+ return value == (u64)(u32)value;
}
/* mov dst, src */
@@ -212,7 +217,7 @@ struct jit_context {
/* emit x64 prologue code for BPF program and check it's size.
* bpf_tail_call helper will skip it while jumping into another program
*/
-static void emit_prologue(u8 **pprog, u32 stack_depth)
+static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
{
u8 *prog = *pprog;
int cnt = 0;
@@ -247,18 +252,21 @@ static void emit_prologue(u8 **pprog, u32 stack_depth)
/* mov qword ptr [rbp+24],r15 */
EMIT4(0x4C, 0x89, 0x7D, 24);
- /* Clear the tail call counter (tail_call_cnt): for eBPF tail calls
- * we need to reset the counter to 0. It's done in two instructions,
- * resetting rax register to 0 (xor on eax gets 0 extended), and
- * moving it to the counter location.
- */
+ if (!ebpf_from_cbpf) {
+ /* Clear the tail call counter (tail_call_cnt): for eBPF tail
+ * calls we need to reset the counter to 0. It's done in two
+ * instructions, resetting rax register to 0, and moving it
+ * to the counter location.
+ */
- /* xor eax, eax */
- EMIT2(0x31, 0xc0);
- /* mov qword ptr [rbp+32], rax */
- EMIT4(0x48, 0x89, 0x45, 32);
+ /* xor eax, eax */
+ EMIT2(0x31, 0xc0);
+ /* mov qword ptr [rbp+32], rax */
+ EMIT4(0x48, 0x89, 0x45, 32);
- BUILD_BUG_ON(cnt != PROLOGUE_SIZE);
+ BUILD_BUG_ON(cnt != PROLOGUE_SIZE);
+ }
+
*pprog = prog;
}
@@ -356,6 +364,86 @@ static void emit_load_skb_data_hlen(u8 **pprog)
*pprog = prog;
}
+static void emit_mov_imm32(u8 **pprog, bool sign_propagate,
+ u32 dst_reg, const u32 imm32)
+{
+ u8 *prog = *pprog;
+ u8 b1, b2, b3;
+ int cnt = 0;
+
+ /* optimization: if imm32 is positive, use 'mov %eax, imm32'
+ * (which zero-extends imm32) to save 2 bytes.
+ */
+ if (sign_propagate && (s32)imm32 < 0) {
+ /* 'mov %rax, imm32' sign extends imm32 */
+ b1 = add_1mod(0x48, dst_reg);
+ b2 = 0xC7;
+ b3 = 0xC0;
+ EMIT3_off32(b1, b2, add_1reg(b3, dst_reg), imm32);
+ goto done;
+ }
+
+ /* optimization: if imm32 is zero, use 'xor %eax, %eax'
+ * to save 3 bytes.
+ */
+ if (imm32 == 0) {
+ if (is_ereg(dst_reg))
+ EMIT1(add_2mod(0x40, dst_reg, dst_reg));
+ b2 = 0x31; /* xor */
+ b3 = 0xC0;
+ EMIT2(b2, add_2reg(b3, dst_reg, dst_reg));
+ goto done;
+ }
+
+ /* mov %eax, imm32 */
+ if (is_ereg(dst_reg))
+ EMIT1(add_1mod(0x40, dst_reg));
+ EMIT1_off32(add_1reg(0xB8, dst_reg), imm32);
+done:
+ *pprog = prog;
+}
+
+static void emit_mov_imm64(u8 **pprog, u32 dst_reg,
+ const u32 imm32_hi, const u32 imm32_lo)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+
+ if (is_uimm32(((u64)imm32_hi << 32) | (u32)imm32_lo)) {
+ /* For emitting plain u32, where sign bit must not be
+ * propagated LLVM tends to load imm64 over mov32
+ * directly, so save couple of bytes by just doing
+ * 'mov %eax, imm32' instead.
+ */
+ emit_mov_imm32(&prog, false, dst_reg, imm32_lo);
+ } else {
+ /* movabsq %rax, imm64 */
+ EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg));
+ EMIT(imm32_lo, 4);
+ EMIT(imm32_hi, 4);
+ }
+
+ *pprog = prog;
+}
+
+static void emit_mov_reg(u8 **pprog, bool is64, u32 dst_reg, u32 src_reg)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+
+ if (is64) {
+ /* mov dst, src */
+ EMIT_mov(dst_reg, src_reg);
+ } else {
+ /* mov32 dst, src */
+ if (is_ereg(dst_reg) || is_ereg(src_reg))
+ EMIT1(add_2mod(0x40, dst_reg, src_reg));
+ EMIT2(0x89, add_2reg(0xC0, dst_reg, src_reg));
+ }
+
+ *pprog = prog;
+}
+
static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
int oldproglen, struct jit_context *ctx)
{
@@ -369,7 +457,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
int proglen = 0;
u8 *prog = temp;
- emit_prologue(&prog, bpf_prog->aux->stack_depth);
+ emit_prologue(&prog, bpf_prog->aux->stack_depth,
+ bpf_prog_was_classic(bpf_prog));
if (seen_ld_abs)
emit_load_skb_data_hlen(&prog);
@@ -378,7 +467,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
const s32 imm32 = insn->imm;
u32 dst_reg = insn->dst_reg;
u32 src_reg = insn->src_reg;
- u8 b1 = 0, b2 = 0, b3 = 0;
+ u8 b2 = 0, b3 = 0;
s64 jmp_offset;
u8 jmp_cond;
bool reload_skb_data;
@@ -414,16 +503,11 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
EMIT2(b2, add_2reg(0xC0, dst_reg, src_reg));
break;
- /* mov dst, src */
case BPF_ALU64 | BPF_MOV | BPF_X:
- EMIT_mov(dst_reg, src_reg);
- break;
-
- /* mov32 dst, src */
case BPF_ALU | BPF_MOV | BPF_X:
- if (is_ereg(dst_reg) || is_ereg(src_reg))
- EMIT1(add_2mod(0x40, dst_reg, src_reg));
- EMIT2(0x89, add_2reg(0xC0, dst_reg, src_reg));
+ emit_mov_reg(&prog,
+ BPF_CLASS(insn->code) == BPF_ALU64,
+ dst_reg, src_reg);
break;
/* neg dst */
@@ -486,58 +570,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
break;
case BPF_ALU64 | BPF_MOV | BPF_K:
- /* optimization: if imm32 is positive,
- * use 'mov eax, imm32' (which zero-extends imm32)
- * to save 2 bytes
- */
- if (imm32 < 0) {
- /* 'mov rax, imm32' sign extends imm32 */
- b1 = add_1mod(0x48, dst_reg);
- b2 = 0xC7;
- b3 = 0xC0;
- EMIT3_off32(b1, b2, add_1reg(b3, dst_reg), imm32);
- break;
- }
-
case BPF_ALU | BPF_MOV | BPF_K:
- /* optimization: if imm32 is zero, use 'xor <dst>,<dst>'
- * to save 3 bytes.
- */
- if (imm32 == 0) {
- if (is_ereg(dst_reg))
- EMIT1(add_2mod(0x40, dst_reg, dst_reg));
- b2 = 0x31; /* xor */
- b3 = 0xC0;
- EMIT2(b2, add_2reg(b3, dst_reg, dst_reg));
- break;
- }
-
- /* mov %eax, imm32 */
- if (is_ereg(dst_reg))
- EMIT1(add_1mod(0x40, dst_reg));
- EMIT1_off32(add_1reg(0xB8, dst_reg), imm32);
+ emit_mov_imm32(&prog, BPF_CLASS(insn->code) == BPF_ALU64,
+ dst_reg, imm32);
break;
case BPF_LD | BPF_IMM | BPF_DW:
- /* optimization: if imm64 is zero, use 'xor <dst>,<dst>'
- * to save 7 bytes.
- */
- if (insn[0].imm == 0 && insn[1].imm == 0) {
- b1 = add_2mod(0x48, dst_reg, dst_reg);
- b2 = 0x31; /* xor */
- b3 = 0xC0;
- EMIT3(b1, b2, add_2reg(b3, dst_reg, dst_reg));
-
- insn++;
- i++;
- break;
- }
-
- /* movabsq %rax, imm64 */
- EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg));
- EMIT(insn[0].imm, 4);
- EMIT(insn[1].imm, 4);
-
+ emit_mov_imm64(&prog, dst_reg, insn[1].imm, insn[0].imm);
insn++;
i++;
break;
@@ -594,36 +633,38 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
case BPF_ALU | BPF_MUL | BPF_X:
case BPF_ALU64 | BPF_MUL | BPF_K:
case BPF_ALU64 | BPF_MUL | BPF_X:
- EMIT1(0x50); /* push rax */
- EMIT1(0x52); /* push rdx */
+ {
+ bool is64 = BPF_CLASS(insn->code) == BPF_ALU64;
+
+ if (dst_reg != BPF_REG_0)
+ EMIT1(0x50); /* push rax */
+ if (dst_reg != BPF_REG_3)
+ EMIT1(0x52); /* push rdx */
/* mov r11, dst_reg */
EMIT_mov(AUX_REG, dst_reg);
if (BPF_SRC(insn->code) == BPF_X)
- /* mov rax, src_reg */
- EMIT_mov(BPF_REG_0, src_reg);
+ emit_mov_reg(&prog, is64, BPF_REG_0, src_reg);
else
- /* mov rax, imm32 */
- EMIT3_off32(0x48, 0xC7, 0xC0, imm32);
+ emit_mov_imm32(&prog, is64, BPF_REG_0, imm32);
- if (BPF_CLASS(insn->code) == BPF_ALU64)
+ if (is64)
EMIT1(add_1mod(0x48, AUX_REG));
else if (is_ereg(AUX_REG))
EMIT1(add_1mod(0x40, AUX_REG));
/* mul(q) r11 */
EMIT2(0xF7, add_1reg(0xE0, AUX_REG));
- /* mov r11, rax */
- EMIT_mov(AUX_REG, BPF_REG_0);
-
- EMIT1(0x5A); /* pop rdx */
- EMIT1(0x58); /* pop rax */
-
- /* mov dst_reg, r11 */
- EMIT_mov(dst_reg, AUX_REG);
+ if (dst_reg != BPF_REG_3)
+ EMIT1(0x5A); /* pop rdx */
+ if (dst_reg != BPF_REG_0) {
+ /* mov dst_reg, rax */
+ EMIT_mov(dst_reg, BPF_REG_0);
+ EMIT1(0x58); /* pop rax */
+ }
break;
-
+ }
/* shifts */
case BPF_ALU | BPF_LSH | BPF_K:
case BPF_ALU | BPF_RSH | BPF_K:
@@ -641,7 +682,11 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
case BPF_RSH: b3 = 0xE8; break;
case BPF_ARSH: b3 = 0xF8; break;
}
- EMIT3(0xC1, add_1reg(b3, dst_reg), imm32);
+
+ if (imm32 == 1)
+ EMIT2(0xD1, add_1reg(b3, dst_reg));
+ else
+ EMIT3(0xC1, add_1reg(b3, dst_reg), imm32);
break;
case BPF_ALU | BPF_LSH | BPF_X:
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index e1b5c5c..24486f9 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -253,9 +253,8 @@ static void mv88e6xxx_g1_irq_unmask(struct irq_data *d)
chip->g1_irq.masked &= ~(1 << n);
}
-static irqreturn_t mv88e6xxx_g1_irq_thread_fn(int irq, void *dev_id)
+static irqreturn_t mv88e6xxx_g1_irq_thread_work(struct mv88e6xxx_chip *chip)
{
- struct mv88e6xxx_chip *chip = dev_id;
unsigned int nhandled = 0;
unsigned int sub_irq;
unsigned int n;
@@ -280,6 +279,13 @@ static irqreturn_t mv88e6xxx_g1_irq_thread_fn(int irq, void *dev_id)
return (nhandled > 0 ? IRQ_HANDLED : IRQ_NONE);
}
+static irqreturn_t mv88e6xxx_g1_irq_thread_fn(int irq, void *dev_id)
+{
+ struct mv88e6xxx_chip *chip = dev_id;
+
+ return mv88e6xxx_g1_irq_thread_work(chip);
+}
+
static void mv88e6xxx_g1_irq_bus_lock(struct irq_data *d)
{
struct mv88e6xxx_chip *chip = irq_data_get_irq_chip_data(d);
@@ -335,7 +341,7 @@ static const struct irq_domain_ops mv88e6xxx_g1_irq_domain_ops = {
.xlate = irq_domain_xlate_twocell,
};
-static void mv88e6xxx_g1_irq_free(struct mv88e6xxx_chip *chip)
+static void mv88e6xxx_g1_irq_free_common(struct mv88e6xxx_chip *chip)
{
int irq, virq;
u16 mask;
@@ -344,8 +350,6 @@ static void mv88e6xxx_g1_irq_free(struct mv88e6xxx_chip *chip)
mask &= ~GENMASK(chip->g1_irq.nirqs, 0);
mv88e6xxx_g1_write(chip, MV88E6XXX_G1_CTL1, mask);
- free_irq(chip->irq, chip);
-
for (irq = 0; irq < chip->g1_irq.nirqs; irq++) {
virq = irq_find_mapping(chip->g1_irq.domain, irq);
irq_dispose_mapping(virq);
@@ -354,7 +358,14 @@ static void mv88e6xxx_g1_irq_free(struct mv88e6xxx_chip *chip)
irq_domain_remove(chip->g1_irq.domain);
}
-static int mv88e6xxx_g1_irq_setup(struct mv88e6xxx_chip *chip)
+static void mv88e6xxx_g1_irq_free(struct mv88e6xxx_chip *chip)
+{
+ mv88e6xxx_g1_irq_free(chip);
+
+ free_irq(chip->irq, chip);
+}
+
+static int mv88e6xxx_g1_irq_setup_common(struct mv88e6xxx_chip *chip)
{
int err, irq, virq;
u16 reg, mask;
@@ -387,13 +398,6 @@ static int mv88e6xxx_g1_irq_setup(struct mv88e6xxx_chip *chip)
if (err)
goto out_disable;
- err = request_threaded_irq(chip->irq, NULL,
- mv88e6xxx_g1_irq_thread_fn,
- IRQF_ONESHOT | IRQF_TRIGGER_FALLING,
- dev_name(chip->dev), chip);
- if (err)
- goto out_disable;
-
return 0;
out_disable:
@@ -411,6 +415,62 @@ static int mv88e6xxx_g1_irq_setup(struct mv88e6xxx_chip *chip)
return err;
}
+static int mv88e6xxx_g1_irq_setup(struct mv88e6xxx_chip *chip)
+{
+ int err;
+
+ err = mv88e6xxx_g1_irq_setup_common(chip);
+ if (err)
+ return err;
+
+ err = request_threaded_irq(chip->irq, NULL,
+ mv88e6xxx_g1_irq_thread_fn,
+ IRQF_ONESHOT | IRQF_TRIGGER_FALLING,
+ dev_name(chip->dev), chip);
+ if (err)
+ mv88e6xxx_g1_irq_free_common(chip);
+
+ return err;
+}
+
+static void mv88e6xxx_irq_poll(struct kthread_work *work)
+{
+ struct mv88e6xxx_chip *chip = container_of(work,
+ struct mv88e6xxx_chip,
+ irq_poll_work.work);
+ mv88e6xxx_g1_irq_thread_work(chip);
+
+ kthread_queue_delayed_work(chip->kworker, &chip->irq_poll_work,
+ msecs_to_jiffies(100));
+}
+
+static int mv88e6xxx_irq_poll_setup(struct mv88e6xxx_chip *chip)
+{
+ int err;
+
+ err = mv88e6xxx_g1_irq_setup_common(chip);
+ if (err)
+ return err;
+
+ kthread_init_delayed_work(&chip->irq_poll_work,
+ mv88e6xxx_irq_poll);
+
+ chip->kworker = kthread_create_worker(0, dev_name(chip->dev));
+ if (IS_ERR(chip->kworker))
+ return PTR_ERR(chip->kworker);
+
+ kthread_queue_delayed_work(chip->kworker, &chip->irq_poll_work,
+ msecs_to_jiffies(100));
+
+ return 0;
+}
+
+static void mv88e6xxx_irq_poll_free(struct mv88e6xxx_chip *chip)
+{
+ kthread_cancel_delayed_work_sync(&chip->irq_poll_work);
+ kthread_destroy_worker(chip->kworker);
+}
+
int mv88e6xxx_wait(struct mv88e6xxx_chip *chip, int addr, int reg, u16 mask)
{
int i;
@@ -4034,33 +4094,34 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
goto out;
}
- if (chip->irq > 0) {
- /* Has to be performed before the MDIO bus is created,
- * because the PHYs will link there interrupts to these
- * interrupt controllers
- */
- mutex_lock(&chip->reg_lock);
+ /* Has to be performed before the MDIO bus is created, because
+ * the PHYs will link there interrupts to these interrupt
+ * controllers
+ */
+ mutex_lock(&chip->reg_lock);
+ if (chip->irq > 0)
err = mv88e6xxx_g1_irq_setup(chip);
- mutex_unlock(&chip->reg_lock);
+ else
+ err = mv88e6xxx_irq_poll_setup(chip);
+ mutex_unlock(&chip->reg_lock);
+ if (err)
+ goto out;
+
+ if (chip->info->g2_irqs > 0) {
+ err = mv88e6xxx_g2_irq_setup(chip);
if (err)
- goto out;
-
- if (chip->info->g2_irqs > 0) {
- err = mv88e6xxx_g2_irq_setup(chip);
- if (err)
- goto out_g1_irq;
- }
-
- err = mv88e6xxx_g1_atu_prob_irq_setup(chip);
- if (err)
- goto out_g2_irq;
-
- err = mv88e6xxx_g1_vtu_prob_irq_setup(chip);
- if (err)
- goto out_g1_atu_prob_irq;
+ goto out_g1_irq;
}
+ err = mv88e6xxx_g1_atu_prob_irq_setup(chip);
+ if (err)
+ goto out_g2_irq;
+
+ err = mv88e6xxx_g1_vtu_prob_irq_setup(chip);
+ if (err)
+ goto out_g1_atu_prob_irq;
+
err = mv88e6xxx_mdios_register(chip, np);
if (err)
goto out_g1_vtu_prob_irq;
@@ -4074,20 +4135,19 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
out_mdio:
mv88e6xxx_mdios_unregister(chip);
out_g1_vtu_prob_irq:
- if (chip->irq > 0)
- mv88e6xxx_g1_vtu_prob_irq_free(chip);
+ mv88e6xxx_g1_vtu_prob_irq_free(chip);
out_g1_atu_prob_irq:
- if (chip->irq > 0)
- mv88e6xxx_g1_atu_prob_irq_free(chip);
+ mv88e6xxx_g1_atu_prob_irq_free(chip);
out_g2_irq:
- if (chip->info->g2_irqs > 0 && chip->irq > 0)
+ if (chip->info->g2_irqs > 0)
mv88e6xxx_g2_irq_free(chip);
out_g1_irq:
- if (chip->irq > 0) {
- mutex_lock(&chip->reg_lock);
+ mutex_lock(&chip->reg_lock);
+ if (chip->irq > 0)
mv88e6xxx_g1_irq_free(chip);
- mutex_unlock(&chip->reg_lock);
- }
+ else
+ mv88e6xxx_irq_poll_free(chip);
+ mutex_unlock(&chip->reg_lock);
out:
return err;
}
diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index 97d7915f3..d6a1391 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -15,6 +15,7 @@
#include <linux/if_vlan.h>
#include <linux/irq.h>
#include <linux/gpio/consumer.h>
+#include <linux/kthread.h>
#include <linux/phy.h>
#include <linux/ptp_clock_kernel.h>
#include <linux/timecounter.h>
@@ -245,6 +246,8 @@ struct mv88e6xxx_chip {
int watchdog_irq;
int atu_prob_irq;
int vtu_prob_irq;
+ struct kthread_worker *kworker;
+ struct kthread_delayed_work irq_poll_work;
/* GPIO resources */
u8 gpio_data[2];
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
index d27fa57..059eb32 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
@@ -270,6 +270,8 @@ static int mlxsw_sp_kvdl_part_init(struct mlxsw_sp *mlxsw_sp,
case MLXSW_SP_KVDL_PART_LARGE_CHUNKS:
resource_id = MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS;
break;
+ default:
+ return -EINVAL;
}
err = devlink_resource_size_get(devlink, resource_id, &resource_size);
@@ -278,7 +280,7 @@ static int mlxsw_sp_kvdl_part_init(struct mlxsw_sp *mlxsw_sp,
resource_size = info->end_index - info->start_index + 1;
}
- nr_entries = resource_size / info->alloc_size;
+ nr_entries = div_u64(resource_size, info->alloc_size);
usage_size = BITS_TO_LONGS(nr_entries) * sizeof(unsigned long);
part = kzalloc(sizeof(*part) + usage_size, GFP_KERNEL);
if (!part)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index f9f53af..917663a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1882,14 +1882,10 @@ mlxsw_sp_bridge_8021d_port_join(struct mlxsw_sp_bridge_device *bridge_device,
struct netlink_ext_ack *extack)
{
struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
+ struct net_device *dev = bridge_port->dev;
u16 vid;
- if (!is_vlan_dev(bridge_port->dev)) {
- NL_SET_ERR_MSG_MOD(extack, "Only VLAN devices can be enslaved to a VLAN-unaware bridge");
- return -EINVAL;
- }
- vid = vlan_dev_vlan_id(bridge_port->dev);
-
+ vid = is_vlan_dev(dev) ? vlan_dev_vlan_id(dev) : 1;
mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
if (WARN_ON(!mlxsw_sp_port_vlan))
return -EINVAL;
@@ -1912,8 +1908,10 @@ mlxsw_sp_bridge_8021d_port_leave(struct mlxsw_sp_bridge_device *bridge_device,
struct mlxsw_sp_port *mlxsw_sp_port)
{
struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
- u16 vid = vlan_dev_vlan_id(bridge_port->dev);
+ struct net_device *dev = bridge_port->dev;
+ u16 vid;
+ vid = is_vlan_dev(dev) ? vlan_dev_vlan_id(dev) : 1;
mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
if (WARN_ON(!mlxsw_sp_port_vlan))
return;
diff --git a/drivers/net/ethernet/natsemi/jazzsonic.c b/drivers/net/ethernet/natsemi/jazzsonic.c
index d5b2888..51fa82b 100644
--- a/drivers/net/ethernet/natsemi/jazzsonic.c
+++ b/drivers/net/ethernet/natsemi/jazzsonic.c
@@ -60,14 +60,6 @@ do { \
*((volatile unsigned int *)dev->base_addr+(reg)) = (val); \
} while (0)
-
-/* use 0 for production, 1 for verification, >1 for debug */
-#ifdef SONIC_DEBUG
-static unsigned int sonic_debug = SONIC_DEBUG;
-#else
-static unsigned int sonic_debug = 1;
-#endif
-
/*
* We cannot use station (ethernet) address prefixes to detect the
* sonic controller since these are board manufacturer depended.
@@ -117,7 +109,6 @@ static const struct net_device_ops sonic_netdev_ops = {
static int sonic_probe1(struct net_device *dev)
{
- static unsigned version_printed;
unsigned int silicon_revision;
unsigned int val;
struct sonic_local *lp = netdev_priv(dev);
@@ -133,26 +124,17 @@ static int sonic_probe1(struct net_device *dev)
* the expected location.
*/
silicon_revision = SONIC_READ(SONIC_SR);
- if (sonic_debug > 1)
- printk("SONIC Silicon Revision = 0x%04x\n",silicon_revision);
-
i = 0;
while (known_revisions[i] != 0xffff &&
known_revisions[i] != silicon_revision)
i++;
if (known_revisions[i] == 0xffff) {
- printk("SONIC ethernet controller not found (0x%4x)\n",
- silicon_revision);
+ pr_info("SONIC ethernet controller not found (0x%4x)\n",
+ silicon_revision);
goto out;
}
- if (sonic_debug && version_printed++ == 0)
- printk(version);
-
- printk(KERN_INFO "%s: Sonic ethernet found at 0x%08lx, ",
- dev_name(lp->device), dev->base_addr);
-
/*
* Put the sonic into software reset, then
* retrieve and print the ethernet address.
@@ -245,12 +227,16 @@ static int jazz_sonic_probe(struct platform_device *pdev)
err = sonic_probe1(dev);
if (err)
goto out;
+
+ pr_info("SONIC ethernet @%08lx, MAC %pM, IRQ %d\n",
+ dev->base_addr, dev->dev_addr, dev->irq);
+
+ sonic_msg_init(dev);
+
err = register_netdev(dev);
if (err)
goto out1;
- printk("%s: MAC %pM IRQ %d\n", dev->name, dev->dev_addr, dev->irq);
-
return 0;
out1:
@@ -262,8 +248,6 @@ static int jazz_sonic_probe(struct platform_device *pdev)
}
MODULE_DESCRIPTION("Jazz SONIC ethernet driver");
-module_param(sonic_debug, int, 0);
-MODULE_PARM_DESC(sonic_debug, "jazzsonic debug level (1-4)");
MODULE_ALIAS("platform:jazzsonic");
#include "sonic.c"
diff --git a/drivers/net/ethernet/natsemi/macsonic.c b/drivers/net/ethernet/natsemi/macsonic.c
index b922ab5..0937fc2 100644
--- a/drivers/net/ethernet/natsemi/macsonic.c
+++ b/drivers/net/ethernet/natsemi/macsonic.c
@@ -60,8 +60,6 @@
#include <asm/macints.h>
#include <asm/mac_via.h>
-static char mac_sonic_string[] = "macsonic";
-
#include "sonic.h"
/* These should basically be bus-size and endian independent (since
@@ -72,15 +70,6 @@ static char mac_sonic_string[] = "macsonic";
#define SONIC_WRITE(reg,val) (nubus_writew(val, dev->base_addr + (reg * 4) \
+ lp->reg_offset))
-/* use 0 for production, 1 for verification, >1 for debug */
-#ifdef SONIC_DEBUG
-static unsigned int sonic_debug = SONIC_DEBUG;
-#else
-static unsigned int sonic_debug = 1;
-#endif
-
-static int sonic_version_printed;
-
/* For onboard SONIC */
#define ONBOARD_SONIC_REGISTERS 0x50F0A000
#define ONBOARD_SONIC_PROM_BASE 0x50f08000
@@ -313,11 +302,6 @@ static int mac_onboard_sonic_probe(struct net_device *dev)
int sr;
bool commslot = macintosh_config->expansion_type == MAC_EXP_PDS_COMM;
- if (!MACH_IS_MAC)
- return -ENODEV;
-
- printk(KERN_INFO "Checking for internal Macintosh ethernet (SONIC).. ");
-
/* Bogus probing, on the models which may or may not have
Ethernet (BTW, the Ethernet *is* always at the same
address, and nothing else lives there, at least if Apple's
@@ -327,13 +311,11 @@ static int mac_onboard_sonic_probe(struct net_device *dev)
card_present = hwreg_present((void*)ONBOARD_SONIC_REGISTERS);
if (!card_present) {
- printk("none.\n");
+ pr_info("Onboard/comm-slot SONIC not found\n");
return -ENODEV;
}
}
- printk("yes\n");
-
/* Danger! My arms are flailing wildly! You *must* set lp->reg_offset
* and dev->base_addr before using SONIC_READ() or SONIC_WRITE() */
dev->base_addr = ONBOARD_SONIC_REGISTERS;
@@ -342,18 +324,10 @@ static int mac_onboard_sonic_probe(struct net_device *dev)
else
dev->irq = IRQ_NUBUS_9;
- if (!sonic_version_printed) {
- printk(KERN_INFO "%s", version);
- sonic_version_printed = 1;
- }
- printk(KERN_INFO "%s: onboard / comm-slot SONIC at 0x%08lx\n",
- dev_name(lp->device), dev->base_addr);
-
/* The PowerBook's SONIC is 16 bit always. */
if (macintosh_config->ident == MAC_MODEL_PB520) {
lp->reg_offset = 0;
lp->dma_bitmode = SONIC_BITMODE16;
- sr = SONIC_READ(SONIC_SR);
} else if (commslot) {
/* Some of the comm-slot cards are 16 bit. But some
of them are not. The 32-bit cards use offset 2 and
@@ -370,22 +344,21 @@ static int mac_onboard_sonic_probe(struct net_device *dev)
else {
lp->dma_bitmode = SONIC_BITMODE16;
lp->reg_offset = 0;
- sr = SONIC_READ(SONIC_SR);
}
} else {
/* All onboard cards are at offset 2 with 32 bit DMA. */
lp->reg_offset = 2;
lp->dma_bitmode = SONIC_BITMODE32;
- sr = SONIC_READ(SONIC_SR);
}
- printk(KERN_INFO
- "%s: revision 0x%04x, using %d bit DMA and register offset %d\n",
- dev_name(lp->device), sr, lp->dma_bitmode?32:16, lp->reg_offset);
-#if 0 /* This is sometimes useful to find out how MacOS configured the card. */
- printk(KERN_INFO "%s: DCR: 0x%04x, DCR2: 0x%04x\n", dev_name(lp->device),
- SONIC_READ(SONIC_DCR) & 0xffff, SONIC_READ(SONIC_DCR2) & 0xffff);
-#endif
+ pr_info("Onboard/comm-slot SONIC, revision 0x%04x, %d bit DMA, register offset %d\n",
+ SONIC_READ(SONIC_SR), lp->dma_bitmode ? 32 : 16,
+ lp->reg_offset);
+
+ /* This is sometimes useful to find out how MacOS configured the card */
+ pr_debug("%s: DCR=0x%04x, DCR2=0x%04x\n", __func__,
+ SONIC_READ(SONIC_DCR) & 0xffff,
+ SONIC_READ(SONIC_DCR2) & 0xffff);
/* Software reset, then initialize control registers. */
SONIC_WRITE(SONIC_CMD, SONIC_CR_RST);
@@ -406,11 +379,14 @@ static int mac_onboard_sonic_probe(struct net_device *dev)
/* Now look for the MAC address. */
mac_onboard_sonic_ethernet_addr(dev);
+ pr_info("SONIC ethernet @%08lx, MAC %pM, IRQ %d\n",
+ dev->base_addr, dev->dev_addr, dev->irq);
+
/* Shared init code */
return macsonic_init(dev);
}
-static int mac_nubus_sonic_ethernet_addr(struct net_device *dev,
+static int mac_sonic_nubus_ethernet_addr(struct net_device *dev,
unsigned long prom_addr, int id)
{
int i;
@@ -449,70 +425,49 @@ static int macsonic_ident(struct nubus_rsrc *fres)
return -1;
}
-static int mac_nubus_sonic_probe(struct net_device *dev)
+static int mac_sonic_nubus_probe_board(struct nubus_board *board, int id,
+ struct net_device *dev)
{
- static int slots;
- struct nubus_rsrc *ndev = NULL;
struct sonic_local* lp = netdev_priv(dev);
unsigned long base_addr, prom_addr;
u16 sonic_dcr;
- int id = -1;
int reg_offset, dma_bitmode;
- /* Find the first SONIC that hasn't been initialized already */
- for_each_func_rsrc(ndev) {
- if (ndev->category != NUBUS_CAT_NETWORK ||
- ndev->type != NUBUS_TYPE_ETHERNET)
- continue;
-
- /* Have we seen it already? */
- if (slots & (1<<ndev->board->slot))
- continue;
- slots |= 1<<ndev->board->slot;
-
- /* Is it one of ours? */
- if ((id = macsonic_ident(ndev)) != -1)
- break;
- }
-
- if (ndev == NULL)
- return -ENODEV;
-
switch (id) {
case MACSONIC_DUODOCK:
- base_addr = ndev->board->slot_addr + DUODOCK_SONIC_REGISTERS;
- prom_addr = ndev->board->slot_addr + DUODOCK_SONIC_PROM_BASE;
+ base_addr = board->slot_addr + DUODOCK_SONIC_REGISTERS;
+ prom_addr = board->slot_addr + DUODOCK_SONIC_PROM_BASE;
sonic_dcr = SONIC_DCR_EXBUS | SONIC_DCR_RFT0 | SONIC_DCR_RFT1 |
SONIC_DCR_TFT0;
reg_offset = 2;
dma_bitmode = SONIC_BITMODE32;
break;
case MACSONIC_APPLE:
- base_addr = ndev->board->slot_addr + APPLE_SONIC_REGISTERS;
- prom_addr = ndev->board->slot_addr + APPLE_SONIC_PROM_BASE;
+ base_addr = board->slot_addr + APPLE_SONIC_REGISTERS;
+ prom_addr = board->slot_addr + APPLE_SONIC_PROM_BASE;
sonic_dcr = SONIC_DCR_BMS | SONIC_DCR_RFT1 | SONIC_DCR_TFT0;
reg_offset = 0;
dma_bitmode = SONIC_BITMODE32;
break;
case MACSONIC_APPLE16:
- base_addr = ndev->board->slot_addr + APPLE_SONIC_REGISTERS;
- prom_addr = ndev->board->slot_addr + APPLE_SONIC_PROM_BASE;
+ base_addr = board->slot_addr + APPLE_SONIC_REGISTERS;
+ prom_addr = board->slot_addr + APPLE_SONIC_PROM_BASE;
sonic_dcr = SONIC_DCR_EXBUS | SONIC_DCR_RFT1 | SONIC_DCR_TFT0 |
SONIC_DCR_PO1 | SONIC_DCR_BMS;
reg_offset = 0;
dma_bitmode = SONIC_BITMODE16;
break;
case MACSONIC_DAYNALINK:
- base_addr = ndev->board->slot_addr + APPLE_SONIC_REGISTERS;
- prom_addr = ndev->board->slot_addr + DAYNALINK_PROM_BASE;
+ base_addr = board->slot_addr + APPLE_SONIC_REGISTERS;
+ prom_addr = board->slot_addr + DAYNALINK_PROM_BASE;
sonic_dcr = SONIC_DCR_RFT1 | SONIC_DCR_TFT0 |
SONIC_DCR_PO1 | SONIC_DCR_BMS;
reg_offset = 0;
dma_bitmode = SONIC_BITMODE16;
break;
case MACSONIC_DAYNA:
- base_addr = ndev->board->slot_addr + DAYNA_SONIC_REGISTERS;
- prom_addr = ndev->board->slot_addr + DAYNA_SONIC_MAC_ADDR;
+ base_addr = board->slot_addr + DAYNA_SONIC_REGISTERS;
+ prom_addr = board->slot_addr + DAYNA_SONIC_MAC_ADDR;
sonic_dcr = SONIC_DCR_BMS |
SONIC_DCR_RFT1 | SONIC_DCR_TFT0 | SONIC_DCR_PO1;
reg_offset = 0;
@@ -528,21 +483,16 @@ static int mac_nubus_sonic_probe(struct net_device *dev)
dev->base_addr = base_addr;
lp->reg_offset = reg_offset;
lp->dma_bitmode = dma_bitmode;
- dev->irq = SLOT2IRQ(ndev->board->slot);
+ dev->irq = SLOT2IRQ(board->slot);
- if (!sonic_version_printed) {
- printk(KERN_INFO "%s", version);
- sonic_version_printed = 1;
- }
- printk(KERN_INFO "%s: %s in slot %X\n",
- dev_name(lp->device), ndev->board->name, ndev->board->slot);
- printk(KERN_INFO "%s: revision 0x%04x, using %d bit DMA and register offset %d\n",
- dev_name(lp->device), SONIC_READ(SONIC_SR), dma_bitmode?32:16, reg_offset);
+ dev_info(&board->dev, "%s, revision 0x%04x, %d bit DMA, register offset %d\n",
+ board->name, SONIC_READ(SONIC_SR),
+ lp->dma_bitmode ? 32 : 16, lp->reg_offset);
-#if 0 /* This is sometimes useful to find out how MacOS configured the card. */
- printk(KERN_INFO "%s: DCR: 0x%04x, DCR2: 0x%04x\n", dev_name(lp->device),
- SONIC_READ(SONIC_DCR) & 0xffff, SONIC_READ(SONIC_DCR2) & 0xffff);
-#endif
+ /* This is sometimes useful to find out how MacOS configured the card */
+ dev_dbg(&board->dev, "%s: DCR=0x%04x, DCR2=0x%04x\n", __func__,
+ SONIC_READ(SONIC_DCR) & 0xffff,
+ SONIC_READ(SONIC_DCR2) & 0xffff);
/* Software reset, then initialize control registers. */
SONIC_WRITE(SONIC_CMD, SONIC_CR_RST);
@@ -557,14 +507,17 @@ static int mac_nubus_sonic_probe(struct net_device *dev)
SONIC_WRITE(SONIC_ISR, 0x7fff);
/* Now look for the MAC address. */
- if (mac_nubus_sonic_ethernet_addr(dev, prom_addr, id) != 0)
+ if (mac_sonic_nubus_ethernet_addr(dev, prom_addr, id) != 0)
return -ENODEV;
+ dev_info(&board->dev, "SONIC ethernet @%08lx, MAC %pM, IRQ %d\n",
+ dev->base_addr, dev->dev_addr, dev->irq);
+
/* Shared init code */
return macsonic_init(dev);
}
-static int mac_sonic_probe(struct platform_device *pdev)
+static int mac_sonic_platform_probe(struct platform_device *pdev)
{
struct net_device *dev;
struct sonic_local *lp;
@@ -579,21 +532,15 @@ static int mac_sonic_probe(struct platform_device *pdev)
SET_NETDEV_DEV(dev, &pdev->dev);
platform_set_drvdata(pdev, dev);
- /* This will catch fatal stuff like -ENOMEM as well as success */
err = mac_onboard_sonic_probe(dev);
- if (err == 0)
- goto found;
- if (err != -ENODEV)
- goto out;
- err = mac_nubus_sonic_probe(dev);
- if (err)
- goto out;
-found:
- err = register_netdev(dev);
if (err)
goto out;
- printk("%s: MAC %pM IRQ %d\n", dev->name, dev->dev_addr, dev->irq);
+ sonic_msg_init(dev);
+
+ err = register_netdev(dev);
+ if (err)
+ goto out;
return 0;
@@ -604,13 +551,11 @@ static int mac_sonic_probe(struct platform_device *pdev)
}
MODULE_DESCRIPTION("Macintosh SONIC ethernet driver");
-module_param(sonic_debug, int, 0);
-MODULE_PARM_DESC(sonic_debug, "macsonic debug level (1-4)");
MODULE_ALIAS("platform:macsonic");
#include "sonic.c"
-static int mac_sonic_device_remove(struct platform_device *pdev)
+static int mac_sonic_platform_remove(struct platform_device *pdev)
{
struct net_device *dev = platform_get_drvdata(pdev);
struct sonic_local* lp = netdev_priv(dev);
@@ -623,12 +568,105 @@ static int mac_sonic_device_remove(struct platform_device *pdev)
return 0;
}
-static struct platform_driver mac_sonic_driver = {
- .probe = mac_sonic_probe,
- .remove = mac_sonic_device_remove,
- .driver = {
- .name = mac_sonic_string,
+static struct platform_driver mac_sonic_platform_driver = {
+ .probe = mac_sonic_platform_probe,
+ .remove = mac_sonic_platform_remove,
+ .driver = {
+ .name = "macsonic",
},
};
-module_platform_driver(mac_sonic_driver);
+static int mac_sonic_nubus_probe(struct nubus_board *board)
+{
+ struct net_device *ndev;
+ struct sonic_local *lp;
+ struct nubus_rsrc *fres;
+ int id = -1;
+ int err;
+
+ /* The platform driver will handle a PDS or Comm Slot card (even if
+ * it has a pseudoslot declaration ROM).
+ */
+ if (macintosh_config->expansion_type == MAC_EXP_PDS_COMM)
+ return -ENODEV;
+
+ for_each_board_func_rsrc(board, fres) {
+ if (fres->category != NUBUS_CAT_NETWORK ||
+ fres->type != NUBUS_TYPE_ETHERNET)
+ continue;
+
+ id = macsonic_ident(fres);
+ if (id != -1)
+ break;
+ }
+ if (!fres)
+ return -ENODEV;
+
+ ndev = alloc_etherdev(sizeof(struct sonic_local));
+ if (!ndev)
+ return -ENOMEM;
+
+ lp = netdev_priv(ndev);
+ lp->device = &board->dev;
+ SET_NETDEV_DEV(ndev, &board->dev);
+
+ err = mac_sonic_nubus_probe_board(board, id, ndev);
+ if (err)
+ goto out;
+
+ sonic_msg_init(ndev);
+
+ err = register_netdev(ndev);
+ if (err)
+ goto out;
+
+ nubus_set_drvdata(board, ndev);
+
+ return 0;
+
+out:
+ free_netdev(ndev);
+ return err;
+}
+
+static int mac_sonic_nubus_remove(struct nubus_board *board)
+{
+ struct net_device *ndev = nubus_get_drvdata(board);
+ struct sonic_local *lp = netdev_priv(ndev);
+
+ unregister_netdev(ndev);
+ dma_free_coherent(lp->device,
+ SIZEOF_SONIC_DESC * SONIC_BUS_SCALE(lp->dma_bitmode),
+ lp->descriptors, lp->descriptors_laddr);
+ free_netdev(ndev);
+
+ return 0;
+}
+
+static struct nubus_driver mac_sonic_nubus_driver = {
+ .probe = mac_sonic_nubus_probe,
+ .remove = mac_sonic_nubus_remove,
+ .driver = {
+ .name = "macsonic-nubus",
+ .owner = THIS_MODULE,
+ },
+};
+
+static int perr, nerr;
+
+static int __init mac_sonic_init(void)
+{
+ perr = platform_driver_register(&mac_sonic_platform_driver);
+ nerr = nubus_driver_register(&mac_sonic_nubus_driver);
+ return 0;
+}
+module_init(mac_sonic_init);
+
+static void __exit mac_sonic_exit(void)
+{
+ if (!perr)
+ platform_driver_unregister(&mac_sonic_platform_driver);
+ if (!nerr)
+ nubus_driver_unregister(&mac_sonic_nubus_driver);
+}
+module_exit(mac_sonic_exit);
diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c
index 612c7a4..7ed0848 100644
--- a/drivers/net/ethernet/natsemi/sonic.c
+++ b/drivers/net/ethernet/natsemi/sonic.c
@@ -33,7 +33,21 @@
* the NetBSD file "sys/arch/mac68k/dev/if_sn.c".
*/
+static unsigned int version_printed;
+static int sonic_debug = -1;
+module_param(sonic_debug, int, 0);
+MODULE_PARM_DESC(sonic_debug, "debug message level");
+
+static void sonic_msg_init(struct net_device *dev)
+{
+ struct sonic_local *lp = netdev_priv(dev);
+
+ lp->msg_enable = netif_msg_init(sonic_debug, 0);
+
+ if (version_printed++ == 0)
+ netif_dbg(lp, drv, dev, "%s", version);
+}
/*
* Open/initialize the SONIC controller.
@@ -47,8 +61,7 @@ static int sonic_open(struct net_device *dev)
struct sonic_local *lp = netdev_priv(dev);
int i;
- if (sonic_debug > 2)
- printk("sonic_open: initializing sonic driver.\n");
+ netif_dbg(lp, ifup, dev, "%s: initializing sonic driver\n", __func__);
for (i = 0; i < SONIC_NUM_RRS; i++) {
struct sk_buff *skb = netdev_alloc_skb(dev, SONIC_RBSIZE + 2);
@@ -95,8 +108,7 @@ static int sonic_open(struct net_device *dev)
netif_start_queue(dev);
- if (sonic_debug > 2)
- printk("sonic_open: Initialization done.\n");
+ netif_dbg(lp, ifup, dev, "%s: Initialization done\n", __func__);
return 0;
}
@@ -110,8 +122,7 @@ static int sonic_close(struct net_device *dev)
struct sonic_local *lp = netdev_priv(dev);
int i;
- if (sonic_debug > 2)
- printk("sonic_close\n");
+ netif_dbg(lp, ifdown, dev, "%s\n", __func__);
netif_stop_queue(dev);
@@ -205,8 +216,7 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev)
int length;
int entry = lp->next_tx;
- if (sonic_debug > 2)
- printk("sonic_send_packet: skb=%p, dev=%p\n", skb, dev);
+ netif_dbg(lp, tx_queued, dev, "%s: skb=%p\n", __func__, skb);
length = skb->len;
if (length < ETH_ZLEN) {
@@ -252,14 +262,12 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev)
lp->next_tx = (entry + 1) & SONIC_TDS_MASK;
if (lp->tx_skb[lp->next_tx] != NULL) {
/* The ring is full, the ISR has yet to process the next TD. */
- if (sonic_debug > 3)
- printk("%s: stopping queue\n", dev->name);
+ netif_dbg(lp, tx_queued, dev, "%s: stopping queue\n", __func__);
netif_stop_queue(dev);
/* after this packet, wait for ISR to free up some TDAs */
} else netif_start_queue(dev);
- if (sonic_debug > 2)
- printk("sonic_send_packet: issuing Tx command\n");
+ netif_dbg(lp, tx_queued, dev, "%s: issuing Tx command\n", __func__);
SONIC_WRITE(SONIC_CMD, SONIC_CR_TXP);
@@ -281,8 +289,7 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
do {
if (status & SONIC_INT_PKTRX) {
- if (sonic_debug > 2)
- printk("%s: packet rx\n", dev->name);
+ netif_dbg(lp, intr, dev, "%s: packet rx\n", __func__);
sonic_rx(dev); /* got packet(s) */
SONIC_WRITE(SONIC_ISR, SONIC_INT_PKTRX); /* clear the interrupt */
}
@@ -299,8 +306,7 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
* still being allocated by sonic_send_packet (status clear & tx_skb[entry] clear)
*/
- if (sonic_debug > 2)
- printk("%s: tx done\n", dev->name);
+ netif_dbg(lp, intr, dev, "%s: tx done\n", __func__);
while (lp->tx_skb[entry] != NULL) {
if ((td_status = sonic_tda_get(dev, entry, SONIC_TD_STATUS)) == 0)
@@ -346,20 +352,20 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
* check error conditions
*/
if (status & SONIC_INT_RFO) {
- if (sonic_debug > 1)
- printk("%s: rx fifo overrun\n", dev->name);
+ netif_dbg(lp, rx_err, dev, "%s: rx fifo overrun\n",
+ __func__);
lp->stats.rx_fifo_errors++;
SONIC_WRITE(SONIC_ISR, SONIC_INT_RFO); /* clear the interrupt */
}
if (status & SONIC_INT_RDE) {
- if (sonic_debug > 1)
- printk("%s: rx descriptors exhausted\n", dev->name);
+ netif_dbg(lp, rx_err, dev, "%s: rx descriptors exhausted\n",
+ __func__);
lp->stats.rx_dropped++;
SONIC_WRITE(SONIC_ISR, SONIC_INT_RDE); /* clear the interrupt */
}
if (status & SONIC_INT_RBAE) {
- if (sonic_debug > 1)
- printk("%s: rx buffer area exceeded\n", dev->name);
+ netif_dbg(lp, rx_err, dev, "%s: rx buffer area exceeded\n",
+ __func__);
lp->stats.rx_dropped++;
SONIC_WRITE(SONIC_ISR, SONIC_INT_RBAE); /* clear the interrupt */
}
@@ -380,8 +386,9 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
/* transmit error */
if (status & SONIC_INT_TXER) {
- if ((SONIC_READ(SONIC_TCR) & SONIC_TCR_FU) && (sonic_debug > 2))
- printk(KERN_ERR "%s: tx fifo underrun\n", dev->name);
+ if (SONIC_READ(SONIC_TCR) & SONIC_TCR_FU)
+ netif_dbg(lp, tx_err, dev, "%s: tx fifo underrun\n",
+ __func__);
SONIC_WRITE(SONIC_ISR, SONIC_INT_TXER); /* clear the interrupt */
}
@@ -475,8 +482,8 @@ static void sonic_rx(struct net_device *dev)
if (lp->cur_rwp >= lp->rra_end) lp->cur_rwp = lp->rra_laddr & 0xffff;
SONIC_WRITE(SONIC_RWP, lp->cur_rwp);
if (SONIC_READ(SONIC_ISR) & SONIC_INT_RBE) {
- if (sonic_debug > 2)
- printk("%s: rx buffer exhausted\n", dev->name);
+ netif_dbg(lp, rx_err, dev, "%s: rx buffer exhausted\n",
+ __func__);
SONIC_WRITE(SONIC_ISR, SONIC_INT_RBE); /* clear the flag */
}
} else
@@ -542,9 +549,8 @@ static void sonic_multicast_list(struct net_device *dev)
(netdev_mc_count(dev) > 15)) {
rcr |= SONIC_RCR_AMC;
} else {
- if (sonic_debug > 2)
- printk("sonic_multicast_list: mc_count %d\n",
- netdev_mc_count(dev));
+ netif_dbg(lp, ifup, dev, "%s: mc_count %d\n", __func__,
+ netdev_mc_count(dev));
sonic_set_cam_enable(dev, 1); /* always enable our own address */
i = 1;
netdev_for_each_mc_addr(ha, dev) {
@@ -562,8 +568,7 @@ static void sonic_multicast_list(struct net_device *dev)
}
}
- if (sonic_debug > 2)
- printk("sonic_multicast_list: setting RCR=%x\n", rcr);
+ netif_dbg(lp, ifup, dev, "%s: setting RCR=%x\n", __func__, rcr);
SONIC_WRITE(SONIC_RCR, rcr);
}
@@ -596,8 +601,8 @@ static int sonic_init(struct net_device *dev)
/*
* initialize the receive resource area
*/
- if (sonic_debug > 2)
- printk("sonic_init: initialize receive resource area\n");
+ netif_dbg(lp, ifup, dev, "%s: initialize receive resource area\n",
+ __func__);
for (i = 0; i < SONIC_NUM_RRS; i++) {
u16 bufadr_l = (unsigned long)lp->rx_laddr[i] & 0xffff;
@@ -622,8 +627,7 @@ static int sonic_init(struct net_device *dev)
SONIC_WRITE(SONIC_EOBC, (SONIC_RBSIZE >> 1) - (lp->dma_bitmode ? 2 : 1));
/* load the resource pointers */
- if (sonic_debug > 3)
- printk("sonic_init: issuing RRRA command\n");
+ netif_dbg(lp, ifup, dev, "%s: issuing RRRA command\n", __func__);
SONIC_WRITE(SONIC_CMD, SONIC_CR_RRRA);
i = 0;
@@ -632,16 +636,17 @@ static int sonic_init(struct net_device *dev)
break;
}
- if (sonic_debug > 2)
- printk("sonic_init: status=%x i=%d\n", SONIC_READ(SONIC_CMD), i);
+ netif_dbg(lp, ifup, dev, "%s: status=%x, i=%d\n", __func__,
+ SONIC_READ(SONIC_CMD), i);
/*
* Initialize the receive descriptors so that they
* become a circular linked list, ie. let the last
* descriptor point to the first again.
*/
- if (sonic_debug > 2)
- printk("sonic_init: initialize receive descriptors\n");
+ netif_dbg(lp, ifup, dev, "%s: initialize receive descriptors\n",
+ __func__);
+
for (i=0; i<SONIC_NUM_RDS; i++) {
sonic_rda_put(dev, i, SONIC_RD_STATUS, 0);
sonic_rda_put(dev, i, SONIC_RD_PKTLEN, 0);
@@ -664,8 +669,9 @@ static int sonic_init(struct net_device *dev)
/*
* initialize transmit descriptors
*/
- if (sonic_debug > 2)
- printk("sonic_init: initialize transmit descriptors\n");
+ netif_dbg(lp, ifup, dev, "%s: initialize transmit descriptors\n",
+ __func__);
+
for (i = 0; i < SONIC_NUM_TDS; i++) {
sonic_tda_put(dev, i, SONIC_TD_STATUS, 0);
sonic_tda_put(dev, i, SONIC_TD_CONFIG, 0);
@@ -712,10 +718,8 @@ static int sonic_init(struct net_device *dev)
if (SONIC_READ(SONIC_ISR) & SONIC_INT_LCD)
break;
}
- if (sonic_debug > 2) {
- printk("sonic_init: CMD=%x, ISR=%x\n, i=%d",
- SONIC_READ(SONIC_CMD), SONIC_READ(SONIC_ISR), i);
- }
+ netif_dbg(lp, ifup, dev, "%s: CMD=%x, ISR=%x, i=%d\n", __func__,
+ SONIC_READ(SONIC_CMD), SONIC_READ(SONIC_ISR), i);
/*
* enable receiver, disable loopback
@@ -731,9 +735,8 @@ static int sonic_init(struct net_device *dev)
if ((cmd & SONIC_CR_RXEN) == 0 || (cmd & SONIC_CR_STP) == 0)
printk(KERN_ERR "sonic_init: failed, status=%x\n", cmd);
- if (sonic_debug > 2)
- printk("sonic_init: new status=%x\n",
- SONIC_READ(SONIC_CMD));
+ netif_dbg(lp, ifup, dev, "%s: new status=%x\n", __func__,
+ SONIC_READ(SONIC_CMD));
return 0;
}
diff --git a/drivers/net/ethernet/natsemi/sonic.h b/drivers/net/ethernet/natsemi/sonic.h
index 421b1a2..2b27f70 100644
--- a/drivers/net/ethernet/natsemi/sonic.h
+++ b/drivers/net/ethernet/natsemi/sonic.h
@@ -319,6 +319,7 @@ struct sonic_local {
unsigned int eol_rx;
unsigned int eol_tx; /* last unacked transmit packet */
unsigned int next_tx; /* next free TD */
+ int msg_enable;
struct device *device; /* generic device */
struct net_device_stats stats;
};
@@ -336,6 +337,7 @@ static struct net_device_stats *sonic_get_stats(struct net_device *dev);
static void sonic_multicast_list(struct net_device *dev);
static int sonic_init(struct net_device *dev);
static void sonic_tx_timeout(struct net_device *dev);
+static void sonic_msg_init(struct net_device *dev);
/* Internal inlines for reading/writing DMA buffers. Note that bus
size and endianness matter here, whereas they don't for registers,
diff --git a/drivers/net/ethernet/natsemi/xtsonic.c b/drivers/net/ethernet/natsemi/xtsonic.c
index 1817dee..e1b886e 100644
--- a/drivers/net/ethernet/natsemi/xtsonic.c
+++ b/drivers/net/ethernet/natsemi/xtsonic.c
@@ -73,14 +73,6 @@ extern void xtboard_get_ether_addr(unsigned char *buf);
#define SONIC_WRITE(reg,val) \
*((volatile unsigned int *)dev->base_addr+reg) = val
-
-/* Use 0 for production, 1 for verification, and >2 for debug */
-#ifdef SONIC_DEBUG
-static unsigned int sonic_debug = SONIC_DEBUG;
-#else
-static unsigned int sonic_debug = 1;
-#endif
-
/*
* We cannot use station (ethernet) address prefixes to detect the
* sonic controller since these are board manufacturer depended.
@@ -130,7 +122,6 @@ static const struct net_device_ops xtsonic_netdev_ops = {
static int __init sonic_probe1(struct net_device *dev)
{
- static unsigned version_printed = 0;
unsigned int silicon_revision;
struct sonic_local *lp = netdev_priv(dev);
unsigned int base_addr = dev->base_addr;
@@ -146,23 +137,17 @@ static int __init sonic_probe1(struct net_device *dev)
* the expected location.
*/
silicon_revision = SONIC_READ(SONIC_SR);
- if (sonic_debug > 1)
- printk("SONIC Silicon Revision = 0x%04x\n",silicon_revision);
-
i = 0;
while ((known_revisions[i] != 0xffff) &&
(known_revisions[i] != silicon_revision))
i++;
if (known_revisions[i] == 0xffff) {
- printk("SONIC ethernet controller not found (0x%4x)\n",
- silicon_revision);
+ pr_info("SONIC ethernet controller not found (0x%4x)\n",
+ silicon_revision);
return -ENODEV;
}
- if (sonic_debug && version_printed++ == 0)
- printk(version);
-
/*
* Put the sonic into software reset, then retrieve ethernet address.
* Note: we are assuming that the boot-loader has initialized the cam.
@@ -273,12 +258,15 @@ int xtsonic_probe(struct platform_device *pdev)
if ((err = sonic_probe1(dev)))
goto out;
+
+ pr_info("SONIC ethernet @%08lx, MAC %pM, IRQ %d\n",
+ dev->base_addr, dev->dev_addr, dev->irq);
+
+ sonic_msg_init(dev);
+
if ((err = register_netdev(dev)))
goto out1;
- printk("%s: SONIC ethernet @%08lx, MAC %pM, IRQ %d\n", dev->name,
- dev->base_addr, dev->dev_addr, dev->irq);
-
return 0;
out1:
@@ -290,8 +278,6 @@ int xtsonic_probe(struct platform_device *pdev)
}
MODULE_DESCRIPTION("Xtensa XT2000 SONIC ethernet driver");
-module_param(sonic_debug, int, 0);
-MODULE_PARM_DESC(sonic_debug, "xtsonic debug level (1-4)");
#include "sonic.c"
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index d7d5a6d..d3e1bc0 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -123,8 +123,8 @@ static const u16 sh_eth_offset_gigabit[SH_ETH_MAX_REGISTER_OFFSET] = {
[TSU_FWSL0] = 0x0030,
[TSU_FWSL1] = 0x0034,
[TSU_FWSLC] = 0x0038,
- [TSU_QTAG0] = 0x0040,
- [TSU_QTAG1] = 0x0044,
+ [TSU_QTAGM0] = 0x0040,
+ [TSU_QTAGM1] = 0x0044,
[TSU_FWSR] = 0x0050,
[TSU_FWINMK] = 0x0054,
[TSU_ADQT0] = 0x0048,
@@ -752,6 +752,7 @@ static struct sh_eth_cpu_data sh7757_data = {
.rpadir = 1,
.rpadir_value = 2 << 16,
.rtrate = 1,
+ .dual_port = 1,
};
#define SH_GIGA_ETH_BASE 0xfee00000UL
@@ -830,6 +831,7 @@ static struct sh_eth_cpu_data sh7757_data_giga = {
.no_trimd = 1,
.no_ade = 1,
.tsu = 1,
+ .dual_port = 1,
};
/* SH7734 */
@@ -900,6 +902,7 @@ static struct sh_eth_cpu_data sh7763_data = {
.tsu = 1,
.irq_flags = IRQF_SHARED,
.magic = 1,
+ .dual_port = 1,
};
static struct sh_eth_cpu_data sh7619_data = {
@@ -932,6 +935,7 @@ static struct sh_eth_cpu_data sh771x_data = {
EESIPR_RRFIP | EESIPR_RTLFIP | EESIPR_RTSFIP |
EESIPR_PREIP | EESIPR_CERFIP,
.tsu = 1,
+ .dual_port = 1,
};
static void sh_eth_set_default_cpu_data(struct sh_eth_cpu_data *cd)
@@ -2097,8 +2101,6 @@ static size_t __sh_eth_get_regs(struct net_device *ndev, u32 *buf)
add_tsu_reg(TSU_FWSL0);
add_tsu_reg(TSU_FWSL1);
add_tsu_reg(TSU_FWSLC);
- add_tsu_reg(TSU_QTAG0);
- add_tsu_reg(TSU_QTAG1);
add_tsu_reg(TSU_QTAGM0);
add_tsu_reg(TSU_QTAGM1);
add_tsu_reg(TSU_FWSR);
@@ -2917,7 +2919,7 @@ static int sh_eth_vlan_rx_kill_vid(struct net_device *ndev,
/* SuperH's TSU register init function */
static void sh_eth_tsu_init(struct sh_eth_private *mdp)
{
- if (sh_eth_is_rz_fast_ether(mdp)) {
+ if (!mdp->cd->dual_port) {
sh_eth_tsu_write(mdp, 0, TSU_TEN); /* Disable all CAM entry */
sh_eth_tsu_write(mdp, TSU_FWSLC_POSTENU | TSU_FWSLC_POSTENL,
TSU_FWSLC); /* Enable POST registers */
@@ -2934,13 +2936,8 @@ static void sh_eth_tsu_init(struct sh_eth_private *mdp)
sh_eth_tsu_write(mdp, 0, TSU_FWSL0);
sh_eth_tsu_write(mdp, 0, TSU_FWSL1);
sh_eth_tsu_write(mdp, TSU_FWSLC_POSTENU | TSU_FWSLC_POSTENL, TSU_FWSLC);
- if (sh_eth_is_gether(mdp)) {
- sh_eth_tsu_write(mdp, 0, TSU_QTAG0); /* Disable QTAG(0->1) */
- sh_eth_tsu_write(mdp, 0, TSU_QTAG1); /* Disable QTAG(1->0) */
- } else {
- sh_eth_tsu_write(mdp, 0, TSU_QTAGM0); /* Disable QTAG(0->1) */
- sh_eth_tsu_write(mdp, 0, TSU_QTAGM1); /* Disable QTAG(1->0) */
- }
+ sh_eth_tsu_write(mdp, 0, TSU_QTAGM0); /* Disable QTAG(0->1) */
+ sh_eth_tsu_write(mdp, 0, TSU_QTAGM1); /* Disable QTAG(1->0) */
sh_eth_tsu_write(mdp, 0, TSU_FWSR); /* all interrupt status clear */
sh_eth_tsu_write(mdp, 0, TSU_FWINMK); /* Disable all interrupt */
sh_eth_tsu_write(mdp, 0, TSU_TEN); /* Disable all CAM entry */
diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h
index a6753cc..5bbaf9e 100644
--- a/drivers/net/ethernet/renesas/sh_eth.h
+++ b/drivers/net/ethernet/renesas/sh_eth.h
@@ -118,8 +118,8 @@ enum {
TSU_FWSL0,
TSU_FWSL1,
TSU_FWSLC,
- TSU_QTAG0,
- TSU_QTAG1,
+ TSU_QTAG0, /* Same as TSU_QTAGM0 */
+ TSU_QTAG1, /* Same as TSU_QTAGM1 */
TSU_QTAGM0,
TSU_QTAGM1,
TSU_FWSR,
@@ -509,6 +509,7 @@ struct sh_eth_cpu_data {
unsigned rmiimode:1; /* EtherC has RMIIMODE register */
unsigned rtrate:1; /* EtherC has RTRATE register */
unsigned magic:1; /* EtherC has ECMR.MPDE and ECSR.MPD */
+ unsigned dual_port:1; /* Dual EtherC/E-DMAC */
};
struct sh_eth_private {
diff --git a/drivers/net/ethernet/sfc/falcon/enum.h b/drivers/net/ethernet/sfc/falcon/enum.h
index 30a1136..4824fcf 100644
--- a/drivers/net/ethernet/sfc/falcon/enum.h
+++ b/drivers/net/ethernet/sfc/falcon/enum.h
@@ -81,7 +81,6 @@ enum ef4_loopback_mode {
(1 << LOOPBACK_XAUI) | \
(1 << LOOPBACK_GMII) | \
(1 << LOOPBACK_SGMII) | \
- (1 << LOOPBACK_SGMII) | \
(1 << LOOPBACK_XGBR) | \
(1 << LOOPBACK_XFI) | \
(1 << LOOPBACK_XAUI_FAR) | \
diff --git a/drivers/net/xen-netback/rx.c b/drivers/net/xen-netback/rx.c
index b1cf7c6..ef58870 100644
--- a/drivers/net/xen-netback/rx.c
+++ b/drivers/net/xen-netback/rx.c
@@ -419,7 +419,7 @@ static void xenvif_rx_extra_slot(struct xenvif_queue *queue,
BUG();
}
-void xenvif_rx_skb(struct xenvif_queue *queue)
+static void xenvif_rx_skb(struct xenvif_queue *queue)
{
struct xenvif_pkt_state pkt;
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index a7f16e0..8a45666 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -96,7 +96,7 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
#define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) \
({ \
int __ret = 0; \
- if (cgroup_bpf_enabled && sk) { \
+ if (cgroup_bpf_enabled) { \
__ret = __cgroup_bpf_run_filter_sk(sk, \
BPF_CGROUP_INET_SOCK_CREATE); \
} \
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 276932d..fdb691b 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -20,7 +20,6 @@
#include <linux/set_memory.h>
#include <linux/kallsyms.h>
-#include <net/xdp.h>
#include <net/sch_generic.h>
#include <uapi/linux/filter.h>
@@ -30,6 +29,7 @@ struct sk_buff;
struct sock;
struct seccomp_data;
struct bpf_prog_aux;
+struct xdp_rxq_info;
/* ArgX, context and stack frame pointer register positions. Note,
* Arg1, Arg2, Arg3, etc are used as argument mappings of function
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 5fb69a8..3c74b16 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -508,10 +508,6 @@ static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
static const int caller_saved[CALLER_SAVED_REGS] = {
BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5
};
-#define CALLEE_SAVED_REGS 5
-static const int callee_saved[CALLEE_SAVED_REGS] = {
- BPF_REG_6, BPF_REG_7, BPF_REG_8, BPF_REG_9
-};
static void __mark_reg_not_init(struct bpf_reg_state *reg);
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 27a5523..690e78c 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -362,7 +362,7 @@ static void dec_net_namespaces(struct ucounts *ucounts)
dec_ucount(ucounts, UCOUNT_NET_NAMESPACES);
}
-static struct kmem_cache *net_cachep;
+static struct kmem_cache *net_cachep __ro_after_init;
static struct workqueue_struct *netns_wq;
static struct net *net_alloc(void)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1a7485a..96d36b81 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -77,8 +77,8 @@
#include <linux/capability.h>
#include <linux/user_namespace.h>
-struct kmem_cache *skbuff_head_cache __read_mostly;
-static struct kmem_cache *skbuff_fclone_cache __read_mostly;
+struct kmem_cache *skbuff_head_cache __ro_after_init;
+static struct kmem_cache *skbuff_fclone_cache __ro_after_init;
int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS;
EXPORT_SYMBOL(sysctl_max_skb_frags);
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 5530cd6..62243a8 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -50,6 +50,7 @@
#define VERSION "0.409"
+#include <linux/cache.h>
#include <linux/uaccess.h>
#include <linux/bitops.h>
#include <linux/types.h>
@@ -191,8 +192,8 @@ static size_t tnode_free_size;
*/
static const int sync_pages = 128;
-static struct kmem_cache *fn_alias_kmem __read_mostly;
-static struct kmem_cache *trie_leaf_kmem __read_mostly;
+static struct kmem_cache *fn_alias_kmem __ro_after_init;
+static struct kmem_cache *trie_leaf_kmem __ro_after_init;
static inline struct tnode *tn_info(struct key_vector *kv)
{
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index 914d569..1f04bd9 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -6,6 +6,7 @@
* Authors: Andrey V. Savochkin <[email protected]>
*/
+#include <linux/cache.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/slab.h>
@@ -51,7 +52,7 @@
* daddr: unchangeable
*/
-static struct kmem_cache *peer_cachep __read_mostly;
+static struct kmem_cache *peer_cachep __ro_after_init;
void inet_peer_base_init(struct inet_peer_base *bp)
{
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 7c7ac9d..591d1fc 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -28,6 +28,7 @@
#include <linux/uaccess.h>
#include <linux/types.h>
+#include <linux/cache.h>
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/timer.h>
@@ -96,7 +97,7 @@ static DEFINE_SPINLOCK(mfc_unres_lock);
* In this case data path is free of exclusive locks at all.
*/
-static struct kmem_cache *mrt_cachep __read_mostly;
+static struct kmem_cache *mrt_cachep __ro_after_init;
static struct mr_table *ipmr_new_table(struct net *net, u32 id);
static void ipmr_free_table(struct mr_table *mrt);
diff --git a/net/socket.c b/net/socket.c
index ab58e57..645d32b4 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -233,7 +233,7 @@ static int move_addr_to_user(struct sockaddr_storage *kaddr, int klen,
return __put_user(klen, ulen);
}
-static struct kmem_cache *sock_inode_cachep __read_mostly;
+static struct kmem_cache *sock_inode_cachep __ro_after_init;
static struct inode *sock_alloc_inode(struct super_block *sb)
{
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index ec3fc8d..2c2a587 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -43,6 +43,7 @@
hostprogs-y += xdp_monitor
hostprogs-y += xdp_rxq_info
hostprogs-y += syscall_tp
+hostprogs-y += cpustat
# Libbpf dependencies
LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o
@@ -93,6 +94,7 @@
xdp_monitor-objs := bpf_load.o $(LIBBPF) xdp_monitor_user.o
xdp_rxq_info-objs := bpf_load.o $(LIBBPF) xdp_rxq_info_user.o
syscall_tp-objs := bpf_load.o $(LIBBPF) syscall_tp_user.o
+cpustat-objs := bpf_load.o $(LIBBPF) cpustat_user.o
# Tell kbuild to always build the programs
always := $(hostprogs-y)
@@ -144,6 +146,7 @@
always += xdp_rxq_info_kern.o
always += xdp2skb_meta_kern.o
always += syscall_tp_kern.o
+always += cpustat_kern.o
HOSTCFLAGS += -I$(objtree)/usr/include
HOSTCFLAGS += -I$(srctree)/tools/lib/
@@ -188,6 +191,7 @@
HOSTLOADLIBES_xdp_monitor += -lelf
HOSTLOADLIBES_xdp_rxq_info += -lelf
HOSTLOADLIBES_syscall_tp += -lelf
+HOSTLOADLIBES_cpustat += -lelf
# Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
# make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
diff --git a/samples/bpf/cpustat_kern.c b/samples/bpf/cpustat_kern.c
new file mode 100644
index 0000000..68c84da
--- /dev/null
+++ b/samples/bpf/cpustat_kern.c
@@ -0,0 +1,281 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/version.h>
+#include <linux/ptrace.h>
+#include <uapi/linux/bpf.h>
+#include "bpf_helpers.h"
+
+/*
+ * The CPU number, cstate number and pstate number are based
+ * on 96boards Hikey with octa CA53 CPUs.
+ *
+ * Every CPU have three idle states for cstate:
+ * WFI, CPU_OFF, CLUSTER_OFF
+ *
+ * Every CPU have 5 operating points:
+ * 208MHz, 432MHz, 729MHz, 960MHz, 1200MHz
+ *
+ * This code is based on these assumption and other platforms
+ * need to adjust these definitions.
+ */
+#define MAX_CPU 8
+#define MAX_PSTATE_ENTRIES 5
+#define MAX_CSTATE_ENTRIES 3
+
+static int cpu_opps[] = { 208000, 432000, 729000, 960000, 1200000 };
+
+/*
+ * my_map structure is used to record cstate and pstate index and
+ * timestamp (Idx, Ts), when new event incoming we need to update
+ * combination for new state index and timestamp (Idx`, Ts`).
+ *
+ * Based on (Idx, Ts) and (Idx`, Ts`) we can calculate the time
+ * interval for the previous state: Duration(Idx) = Ts` - Ts.
+ *
+ * Every CPU has one below array for recording state index and
+ * timestamp, and record for cstate and pstate saperately:
+ *
+ * +--------------------------+
+ * | cstate timestamp |
+ * +--------------------------+
+ * | cstate index |
+ * +--------------------------+
+ * | pstate timestamp |
+ * +--------------------------+
+ * | pstate index |
+ * +--------------------------+
+ */
+#define MAP_OFF_CSTATE_TIME 0
+#define MAP_OFF_CSTATE_IDX 1
+#define MAP_OFF_PSTATE_TIME 2
+#define MAP_OFF_PSTATE_IDX 3
+#define MAP_OFF_NUM 4
+
+struct bpf_map_def SEC("maps") my_map = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(u64),
+ .max_entries = MAX_CPU * MAP_OFF_NUM,
+};
+
+/* cstate_duration records duration time for every idle state per CPU */
+struct bpf_map_def SEC("maps") cstate_duration = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(u64),
+ .max_entries = MAX_CPU * MAX_CSTATE_ENTRIES,
+};
+
+/* pstate_duration records duration time for every operating point per CPU */
+struct bpf_map_def SEC("maps") pstate_duration = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(u64),
+ .max_entries = MAX_CPU * MAX_PSTATE_ENTRIES,
+};
+
+/*
+ * The trace events for cpu_idle and cpu_frequency are taken from:
+ * /sys/kernel/debug/tracing/events/power/cpu_idle/format
+ * /sys/kernel/debug/tracing/events/power/cpu_frequency/format
+ *
+ * These two events have same format, so define one common structure.
+ */
+struct cpu_args {
+ u64 pad;
+ u32 state;
+ u32 cpu_id;
+};
+
+/* calculate pstate index, returns MAX_PSTATE_ENTRIES for failure */
+static u32 find_cpu_pstate_idx(u32 frequency)
+{
+ u32 i;
+
+ for (i = 0; i < sizeof(cpu_opps) / sizeof(u32); i++) {
+ if (frequency == cpu_opps[i])
+ return i;
+ }
+
+ return i;
+}
+
+SEC("tracepoint/power/cpu_idle")
+int bpf_prog1(struct cpu_args *ctx)
+{
+ u64 *cts, *pts, *cstate, *pstate, prev_state, cur_ts, delta;
+ u32 key, cpu, pstate_idx;
+ u64 *val;
+
+ if (ctx->cpu_id > MAX_CPU)
+ return 0;
+
+ cpu = ctx->cpu_id;
+
+ key = cpu * MAP_OFF_NUM + MAP_OFF_CSTATE_TIME;
+ cts = bpf_map_lookup_elem(&my_map, &key);
+ if (!cts)
+ return 0;
+
+ key = cpu * MAP_OFF_NUM + MAP_OFF_CSTATE_IDX;
+ cstate = bpf_map_lookup_elem(&my_map, &key);
+ if (!cstate)
+ return 0;
+
+ key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_TIME;
+ pts = bpf_map_lookup_elem(&my_map, &key);
+ if (!pts)
+ return 0;
+
+ key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_IDX;
+ pstate = bpf_map_lookup_elem(&my_map, &key);
+ if (!pstate)
+ return 0;
+
+ prev_state = *cstate;
+ *cstate = ctx->state;
+
+ if (!*cts) {
+ *cts = bpf_ktime_get_ns();
+ return 0;
+ }
+
+ cur_ts = bpf_ktime_get_ns();
+ delta = cur_ts - *cts;
+ *cts = cur_ts;
+
+ /*
+ * When state doesn't equal to (u32)-1, the cpu will enter
+ * one idle state; for this case we need to record interval
+ * for the pstate.
+ *
+ * OPP2
+ * +---------------------+
+ * OPP1 | |
+ * ---------+ |
+ * | Idle state
+ * +---------------
+ *
+ * |<- pstate duration ->|
+ * ^ ^
+ * pts cur_ts
+ */
+ if (ctx->state != (u32)-1) {
+
+ /* record pstate after have first cpu_frequency event */
+ if (!*pts)
+ return 0;
+
+ delta = cur_ts - *pts;
+
+ pstate_idx = find_cpu_pstate_idx(*pstate);
+ if (pstate_idx >= MAX_PSTATE_ENTRIES)
+ return 0;
+
+ key = cpu * MAX_PSTATE_ENTRIES + pstate_idx;
+ val = bpf_map_lookup_elem(&pstate_duration, &key);
+ if (val)
+ __sync_fetch_and_add((long *)val, delta);
+
+ /*
+ * When state equal to (u32)-1, the cpu just exits from one
+ * specific idle state; for this case we need to record
+ * interval for the pstate.
+ *
+ * OPP2
+ * -----------+
+ * | OPP1
+ * | +-----------
+ * | Idle state |
+ * +---------------------+
+ *
+ * |<- cstate duration ->|
+ * ^ ^
+ * cts cur_ts
+ */
+ } else {
+
+ key = cpu * MAX_CSTATE_ENTRIES + prev_state;
+ val = bpf_map_lookup_elem(&cstate_duration, &key);
+ if (val)
+ __sync_fetch_and_add((long *)val, delta);
+ }
+
+ /* Update timestamp for pstate as new start time */
+ if (*pts)
+ *pts = cur_ts;
+
+ return 0;
+}
+
+SEC("tracepoint/power/cpu_frequency")
+int bpf_prog2(struct cpu_args *ctx)
+{
+ u64 *pts, *cstate, *pstate, prev_state, cur_ts, delta;
+ u32 key, cpu, pstate_idx;
+ u64 *val;
+
+ cpu = ctx->cpu_id;
+
+ key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_TIME;
+ pts = bpf_map_lookup_elem(&my_map, &key);
+ if (!pts)
+ return 0;
+
+ key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_IDX;
+ pstate = bpf_map_lookup_elem(&my_map, &key);
+ if (!pstate)
+ return 0;
+
+ key = cpu * MAP_OFF_NUM + MAP_OFF_CSTATE_IDX;
+ cstate = bpf_map_lookup_elem(&my_map, &key);
+ if (!cstate)
+ return 0;
+
+ prev_state = *pstate;
+ *pstate = ctx->state;
+
+ if (!*pts) {
+ *pts = bpf_ktime_get_ns();
+ return 0;
+ }
+
+ cur_ts = bpf_ktime_get_ns();
+ delta = cur_ts - *pts;
+ *pts = cur_ts;
+
+ /* When CPU is in idle, bail out to skip pstate statistics */
+ if (*cstate != (u32)(-1))
+ return 0;
+
+ /*
+ * The cpu changes to another different OPP (in below diagram
+ * change frequency from OPP3 to OPP1), need recording interval
+ * for previous frequency OPP3 and update timestamp as start
+ * time for new frequency OPP1.
+ *
+ * OPP3
+ * +---------------------+
+ * OPP2 | |
+ * ---------+ |
+ * | OPP1
+ * +---------------
+ *
+ * |<- pstate duration ->|
+ * ^ ^
+ * pts cur_ts
+ */
+ pstate_idx = find_cpu_pstate_idx(*pstate);
+ if (pstate_idx >= MAX_PSTATE_ENTRIES)
+ return 0;
+
+ key = cpu * MAX_PSTATE_ENTRIES + pstate_idx;
+ val = bpf_map_lookup_elem(&pstate_duration, &key);
+ if (val)
+ __sync_fetch_and_add((long *)val, delta);
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/cpustat_user.c b/samples/bpf/cpustat_user.c
new file mode 100644
index 0000000..2b4cd1a
--- /dev/null
+++ b/samples/bpf/cpustat_user.c
@@ -0,0 +1,219 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <sched.h>
+#include <string.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <linux/bpf.h>
+#include <locale.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <sys/wait.h>
+
+#include "libbpf.h"
+#include "bpf_load.h"
+
+#define MAX_CPU 8
+#define MAX_PSTATE_ENTRIES 5
+#define MAX_CSTATE_ENTRIES 3
+#define MAX_STARS 40
+
+#define CPUFREQ_MAX_SYSFS_PATH "/sys/devices/system/cpu/cpu0/cpufreq/scaling_max_freq"
+#define CPUFREQ_LOWEST_FREQ "208000"
+#define CPUFREQ_HIGHEST_FREQ "12000000"
+
+struct cpu_stat_data {
+ unsigned long cstate[MAX_CSTATE_ENTRIES];
+ unsigned long pstate[MAX_PSTATE_ENTRIES];
+};
+
+static struct cpu_stat_data stat_data[MAX_CPU];
+
+static void cpu_stat_print(void)
+{
+ int i, j;
+ char state_str[sizeof("cstate-9")];
+ struct cpu_stat_data *data;
+
+ /* Clear screen */
+ printf("\033[2J");
+
+ /* Header */
+ printf("\nCPU states statistics:\n");
+ printf("%-10s ", "state(ms)");
+
+ for (i = 0; i < MAX_CSTATE_ENTRIES; i++) {
+ sprintf(state_str, "cstate-%d", i);
+ printf("%-11s ", state_str);
+ }
+
+ for (i = 0; i < MAX_PSTATE_ENTRIES; i++) {
+ sprintf(state_str, "pstate-%d", i);
+ printf("%-11s ", state_str);
+ }
+
+ printf("\n");
+
+ for (j = 0; j < MAX_CPU; j++) {
+ data = &stat_data[j];
+
+ printf("CPU-%-6d ", j);
+ for (i = 0; i < MAX_CSTATE_ENTRIES; i++)
+ printf("%-11ld ", data->cstate[i] / 1000000);
+
+ for (i = 0; i < MAX_PSTATE_ENTRIES; i++)
+ printf("%-11ld ", data->pstate[i] / 1000000);
+
+ printf("\n");
+ }
+}
+
+static void cpu_stat_update(int cstate_fd, int pstate_fd)
+{
+ unsigned long key, value;
+ int c, i;
+
+ for (c = 0; c < MAX_CPU; c++) {
+ for (i = 0; i < MAX_CSTATE_ENTRIES; i++) {
+ key = c * MAX_CSTATE_ENTRIES + i;
+ bpf_map_lookup_elem(cstate_fd, &key, &value);
+ stat_data[c].cstate[i] = value;
+ }
+
+ for (i = 0; i < MAX_PSTATE_ENTRIES; i++) {
+ key = c * MAX_PSTATE_ENTRIES + i;
+ bpf_map_lookup_elem(pstate_fd, &key, &value);
+ stat_data[c].pstate[i] = value;
+ }
+ }
+}
+
+/*
+ * This function is copied from 'idlestat' tool function
+ * idlestat_wake_all() in idlestate.c.
+ *
+ * It sets the self running task affinity to cpus one by one so can wake up
+ * the specific CPU to handle scheduling; this results in all cpus can be
+ * waken up once and produce ftrace event 'trace_cpu_idle'.
+ */
+static int cpu_stat_inject_cpu_idle_event(void)
+{
+ int rcpu, i, ret;
+ cpu_set_t cpumask;
+ cpu_set_t original_cpumask;
+
+ ret = sysconf(_SC_NPROCESSORS_CONF);
+ if (ret < 0)
+ return -1;
+
+ rcpu = sched_getcpu();
+ if (rcpu < 0)
+ return -1;
+
+ /* Keep track of the CPUs we will run on */
+ sched_getaffinity(0, sizeof(original_cpumask), &original_cpumask);
+
+ for (i = 0; i < ret; i++) {
+
+ /* Pointless to wake up ourself */
+ if (i == rcpu)
+ continue;
+
+ /* Pointless to wake CPUs we will not run on */
+ if (!CPU_ISSET(i, &original_cpumask))
+ continue;
+
+ CPU_ZERO(&cpumask);
+ CPU_SET(i, &cpumask);
+
+ sched_setaffinity(0, sizeof(cpumask), &cpumask);
+ }
+
+ /* Enable all the CPUs of the original mask */
+ sched_setaffinity(0, sizeof(original_cpumask), &original_cpumask);
+ return 0;
+}
+
+/*
+ * It's possible to have no any frequency change for long time and cannot
+ * get ftrace event 'trace_cpu_frequency' for long period, this introduces
+ * big deviation for pstate statistics.
+ *
+ * To solve this issue, below code forces to set 'scaling_max_freq' to 208MHz
+ * for triggering ftrace event 'trace_cpu_frequency' and then recovery back to
+ * the maximum frequency value 1.2GHz.
+ */
+static int cpu_stat_inject_cpu_frequency_event(void)
+{
+ int len, fd;
+
+ fd = open(CPUFREQ_MAX_SYSFS_PATH, O_WRONLY);
+ if (fd < 0) {
+ printf("failed to open scaling_max_freq, errno=%d\n", errno);
+ return fd;
+ }
+
+ len = write(fd, CPUFREQ_LOWEST_FREQ, strlen(CPUFREQ_LOWEST_FREQ));
+ if (len < 0) {
+ printf("failed to open scaling_max_freq, errno=%d\n", errno);
+ goto err;
+ }
+
+ len = write(fd, CPUFREQ_HIGHEST_FREQ, strlen(CPUFREQ_HIGHEST_FREQ));
+ if (len < 0) {
+ printf("failed to open scaling_max_freq, errno=%d\n", errno);
+ goto err;
+ }
+
+err:
+ close(fd);
+ return len;
+}
+
+static void int_exit(int sig)
+{
+ cpu_stat_inject_cpu_idle_event();
+ cpu_stat_inject_cpu_frequency_event();
+ cpu_stat_update(map_fd[1], map_fd[2]);
+ cpu_stat_print();
+ exit(0);
+}
+
+int main(int argc, char **argv)
+{
+ char filename[256];
+ int ret;
+
+ snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+ if (load_bpf_file(filename)) {
+ printf("%s", bpf_log_buf);
+ return 1;
+ }
+
+ ret = cpu_stat_inject_cpu_idle_event();
+ if (ret < 0)
+ return 1;
+
+ ret = cpu_stat_inject_cpu_frequency_event();
+ if (ret < 0)
+ return 1;
+
+ signal(SIGINT, int_exit);
+ signal(SIGTERM, int_exit);
+
+ while (1) {
+ cpu_stat_update(map_fd[1], map_fd[2]);
+ cpu_stat_print();
+ sleep(5);
+ }
+
+ return 0;
+}
diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c
index d54e91eb..b701b5c 100644
--- a/samples/bpf/xdp_redirect_user.c
+++ b/samples/bpf/xdp_redirect_user.c
@@ -20,6 +20,7 @@
#include <string.h>
#include <unistd.h>
#include <libgen.h>
+#include <sys/resource.h>
#include "bpf_load.h"
#include "bpf_util.h"
@@ -75,6 +76,7 @@ static void usage(const char *prog)
int main(int argc, char **argv)
{
+ struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
const char *optstr = "SN";
char filename[256];
int ret, opt, key = 0;
@@ -98,6 +100,11 @@ int main(int argc, char **argv)
return 1;
}
+ if (setrlimit(RLIMIT_MEMLOCK, &r)) {
+ perror("setrlimit(RLIMIT_MEMLOCK)");
+ return 1;
+ }
+
ifindex_in = strtoul(argv[optind], NULL, 0);
ifindex_out = strtoul(argv[optind + 1], NULL, 0);
printf("input: %d output: %d\n", ifindex_in, ifindex_out);
diff --git a/samples/sockmap/Makefile b/samples/sockmap/Makefile
index 73f1da4..9bf2881 100644
--- a/samples/sockmap/Makefile
+++ b/samples/sockmap/Makefile
@@ -2,7 +2,7 @@
hostprogs-y := sockmap
# Libbpf dependencies
-LIBBPF := ../../tools/lib/bpf/bpf.o
+LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o
HOSTCFLAGS += -I$(objtree)/usr/include
HOSTCFLAGS += -I$(srctree)/tools/lib/
diff --git a/samples/sockmap/sockmap_user.c b/samples/sockmap/sockmap_user.c
index 7c25c0c..95a54a8 100644
--- a/samples/sockmap/sockmap_user.c
+++ b/samples/sockmap/sockmap_user.c
@@ -566,6 +566,7 @@ int main(int argc, char **argv)
else
fprintf(stderr, "unknown test\n");
out:
+ bpf_prog_detach2(prog_fd[2], cg_fd, BPF_CGROUP_SOCK_OPS);
close(s1);
close(s2);
close(p1);
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 5c43c18..8567a858 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -35,12 +35,14 @@
include ../lib.mk
-BPFOBJ := $(OUTPUT)/libbpf.a cgroup_helpers.c
+BPFOBJ := $(OUTPUT)/libbpf.a
$(TEST_GEN_PROGS): $(BPFOBJ)
$(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/libbpf.a
+$(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
+
.PHONY: force
# force a rebuild of BPFOBJ when its dependencies are updated
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c
index 95a370f..5d73db4 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf_user.c
+++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c
@@ -11,6 +11,8 @@
#include <linux/ptrace.h>
#include <linux/bpf.h>
#include <sys/ioctl.h>
+#include <sys/time.h>
+#include <sys/resource.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
@@ -42,6 +44,7 @@ static int bpf_find_map(const char *test, struct bpf_object *obj,
int main(int argc, char **argv)
{
+ struct rlimit limit = { RLIM_INFINITY, RLIM_INFINITY };
const char *file = "test_tcpbpf_kern.o";
struct tcpbpf_globals g = {0};
int cg_fd, prog_fd, map_fd;
@@ -54,6 +57,9 @@ int main(int argc, char **argv)
int pid;
int rv;
+ if (setrlimit(RLIMIT_MEMLOCK, &limit) < 0)
+ perror("Unable to lift memlock rlimit");
+
if (argc > 1 && strcmp(argv[1], "-d") == 0)
debug_flag = true;
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index c73592fa..2164d21 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -57,6 +57,9 @@
#define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS (1 << 0)
#define F_LOAD_WITH_STRICT_ALIGNMENT (1 << 1)
+#define UNPRIV_SYSCTL "kernel/unprivileged_bpf_disabled"
+static bool unpriv_disabled = false;
+
struct bpf_test {
const char *descr;
struct bpf_insn insns[MAX_INSNS];
@@ -11163,6 +11166,95 @@ static struct bpf_test tests[] = {
.result = REJECT,
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
+ {
+ "jit: lsh, rsh, arsh by 1",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_MOV64_IMM(BPF_REG_1, 0xff),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 1),
+ BPF_ALU32_IMM(BPF_LSH, BPF_REG_1, 1),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0x3fc, 1),
+ BPF_EXIT_INSN(),
+ BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 1),
+ BPF_ALU32_IMM(BPF_RSH, BPF_REG_1, 1),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0xff, 1),
+ BPF_EXIT_INSN(),
+ BPF_ALU64_IMM(BPF_ARSH, BPF_REG_1, 1),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0x7f, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_IMM(BPF_REG_0, 2),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .retval = 2,
+ },
+ {
+ "jit: mov32 for ldimm64, 1",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 2),
+ BPF_LD_IMM64(BPF_REG_1, 0xfeffffffffffffffULL),
+ BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 32),
+ BPF_LD_IMM64(BPF_REG_2, 0xfeffffffULL),
+ BPF_JMP_REG(BPF_JEQ, BPF_REG_1, BPF_REG_2, 1),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .retval = 2,
+ },
+ {
+ "jit: mov32 for ldimm64, 2",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_LD_IMM64(BPF_REG_1, 0x1ffffffffULL),
+ BPF_LD_IMM64(BPF_REG_2, 0xffffffffULL),
+ BPF_JMP_REG(BPF_JEQ, BPF_REG_1, BPF_REG_2, 1),
+ BPF_MOV64_IMM(BPF_REG_0, 2),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .retval = 2,
+ },
+ {
+ "jit: various mul tests",
+ .insns = {
+ BPF_LD_IMM64(BPF_REG_2, 0xeeff0d413122ULL),
+ BPF_LD_IMM64(BPF_REG_0, 0xfefefeULL),
+ BPF_LD_IMM64(BPF_REG_1, 0xefefefULL),
+ BPF_ALU64_REG(BPF_MUL, BPF_REG_0, BPF_REG_1),
+ BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_2, 2),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ BPF_LD_IMM64(BPF_REG_3, 0xfefefeULL),
+ BPF_ALU64_REG(BPF_MUL, BPF_REG_3, BPF_REG_1),
+ BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV32_REG(BPF_REG_2, BPF_REG_2),
+ BPF_LD_IMM64(BPF_REG_0, 0xfefefeULL),
+ BPF_ALU32_REG(BPF_MUL, BPF_REG_0, BPF_REG_1),
+ BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_2, 2),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ BPF_LD_IMM64(BPF_REG_3, 0xfefefeULL),
+ BPF_ALU32_REG(BPF_MUL, BPF_REG_3, BPF_REG_1),
+ BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ BPF_LD_IMM64(BPF_REG_0, 0x952a7bbcULL),
+ BPF_LD_IMM64(BPF_REG_1, 0xfefefeULL),
+ BPF_LD_IMM64(BPF_REG_2, 0xeeff0d413122ULL),
+ BPF_ALU32_REG(BPF_MUL, BPF_REG_2, BPF_REG_1),
+ BPF_JMP_REG(BPF_JEQ, BPF_REG_2, BPF_REG_0, 2),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_IMM(BPF_REG_0, 2),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .retval = 2,
+ },
+
};
static int probe_filter_length(const struct bpf_insn *fp)
@@ -11317,7 +11409,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
goto fail_log;
}
if (!strstr(bpf_vlog, expected_err) && !reject_from_alignment) {
- printf("FAIL\nUnexpected error message!\n");
+ printf("FAIL\nUnexpected error message!\n\tEXP: %s\n\tRES: %s\n",
+ expected_err, bpf_vlog);
goto fail_log;
}
}
@@ -11401,9 +11494,20 @@ static int set_admin(bool admin)
return ret;
}
+static void get_unpriv_disabled()
+{
+ char buf[2];
+ FILE *fd;
+
+ fd = fopen("/proc/sys/"UNPRIV_SYSCTL, "r");
+ if (fgets(buf, 2, fd) == buf && atoi(buf))
+ unpriv_disabled = true;
+ fclose(fd);
+}
+
static int do_test(bool unpriv, unsigned int from, unsigned int to)
{
- int i, passes = 0, errors = 0;
+ int i, passes = 0, errors = 0, skips = 0;
for (i = from; i < to; i++) {
struct bpf_test *test = &tests[i];
@@ -11411,7 +11515,10 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to)
/* Program types that are not supported by non-root we
* skip right away.
*/
- if (!test->prog_type) {
+ if (!test->prog_type && unpriv_disabled) {
+ printf("#%d/u %s SKIP\n", i, test->descr);
+ skips++;
+ } else if (!test->prog_type) {
if (!unpriv)
set_admin(false);
printf("#%d/u %s ", i, test->descr);
@@ -11420,13 +11527,17 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to)
set_admin(true);
}
- if (!unpriv) {
+ if (unpriv) {
+ printf("#%d/p %s SKIP\n", i, test->descr);
+ skips++;
+ } else {
printf("#%d/p %s ", i, test->descr);
do_test_single(test, false, &passes, &errors);
}
}
- printf("Summary: %d PASSED, %d FAILED\n", passes, errors);
+ printf("Summary: %d PASSED, %d SKIPPED, %d FAILED\n", passes,
+ skips, errors);
return errors ? EXIT_FAILURE : EXIT_SUCCESS;
}
@@ -11454,6 +11565,13 @@ int main(int argc, char **argv)
}
}
+ get_unpriv_disabled();
+ if (unpriv && unpriv_disabled) {
+ printf("Cannot run as unprivileged user with sysctl %s.\n",
+ UNPRIV_SYSCTL);
+ return EXIT_FAILURE;
+ }
+
setrlimit(RLIMIT_MEMLOCK, unpriv ? &rlim : &rinf);
return do_test(unpriv, from, to);
}
diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py
index b3754b9a..7b50775 100755
--- a/tools/testing/selftests/tc-testing/tdc.py
+++ b/tools/testing/selftests/tc-testing/tdc.py
@@ -15,6 +15,7 @@
import json
import subprocess
import time
+import traceback
from collections import OrderedDict
from string import Template
@@ -23,6 +24,13 @@
import TdcPlugin
+
+class PluginMgrTestFail(Exception):
+ def __init__(self, stage, output, message):
+ self.stage = stage
+ self.output = output
+ self.message = message
+
class PluginMgr:
def __init__(self, argparser):
super().__init__()
@@ -135,7 +143,7 @@
return proc, foutput
-def prepare_env(args, pm, stage, prefix, cmdlist):
+def prepare_env(args, pm, stage, prefix, cmdlist, output = None):
"""
Execute the setup/teardown commands for a test case.
Optionally terminate test execution if the command fails.
@@ -164,7 +172,9 @@
print("\n{} *** Aborting test run.".format(prefix), file=sys.stderr)
print("\n\n{} *** stdout ***".format(proc.stdout), file=sys.stderr)
print("\n\n{} *** stderr ***".format(proc.stderr), file=sys.stderr)
- raise Exception('"{}" did not complete successfully'.format(prefix))
+ raise PluginMgrTestFail(
+ stage, output,
+ '"{}" did not complete successfully'.format(prefix))
def run_one_test(pm, args, index, tidx):
result = True
@@ -194,8 +204,11 @@
match_pattern = re.compile(
str(tidx["matchPattern"]), re.DOTALL | re.MULTILINE)
(p, procout) = exec_cmd(args, pm, 'verify', tidx["verifyCmd"])
- match_index = re.findall(match_pattern, procout)
- if len(match_index) != int(tidx["matchCount"]):
+ if procout:
+ match_index = re.findall(match_pattern, procout)
+ if len(match_index) != int(tidx["matchCount"]):
+ result = False
+ elif int(tidx["matchCount"]) != 0:
result = False
if not result:
@@ -204,9 +217,12 @@
tap += tresult
if result == False:
- tap += procout
+ if procout:
+ tap += procout
+ else:
+ tap += 'No output!\n'
- prepare_env(args, pm, 'teardown', '-----> teardown stage', tidx['teardown'])
+ prepare_env(args, pm, 'teardown', '-----> teardown stage', tidx['teardown'], procout)
pm.call_post_case()
index += 1
@@ -227,30 +243,70 @@
index = 1
tap = str(index) + ".." + str(tcount) + "\n"
badtest = None
+ stage = None
+ emergency_exit = False
+ emergency_exit_message = ''
- pm.call_pre_suite(tcount, [tidx['id'] for tidx in testlist])
+ try:
+ pm.call_pre_suite(tcount, [tidx['id'] for tidx in testlist])
+ except Exception as ee:
+ ex_type, ex, ex_tb = sys.exc_info()
+ print('Exception {} {} (caught in pre_suite).'.
+ format(ex_type, ex))
+ # when the extra print statements are uncommented,
+ # the traceback does not appear between them
+ # (it appears way earlier in the tdc.py output)
+ # so don't bother ...
+ # print('--------------------(')
+ # print('traceback')
+ traceback.print_tb(ex_tb)
+ # print('--------------------)')
+ emergency_exit_message = 'EMERGENCY EXIT, call_pre_suite failed with exception {} {}\n'.format(ex_type, ex)
+ emergency_exit = True
+ stage = 'pre-SUITE'
+ if emergency_exit:
+ pm.call_post_suite(index)
+ return emergency_exit_message
if args.verbose > 1:
- print('Run tests here')
+ print('give test rig 2 seconds to stabilize')
+ time.sleep(2)
for tidx in testlist:
if "flower" in tidx["category"] and args.device == None:
+ if args.verbose > 1:
+ print('Not executing test {} {} because DEV2 not defined'.
+ format(tidx['id'], tidx['name']))
continue
try:
badtest = tidx # in case it goes bad
tap += run_one_test(pm, args, index, tidx)
- except Exception as ee:
- print('Exception {} (caught in test_runner, running test {} {} {})'.
- format(ee, index, tidx['id'], tidx['name']))
+ except PluginMgrTestFail as pmtf:
+ ex_type, ex, ex_tb = sys.exc_info()
+ stage = pmtf.stage
+ message = pmtf.message
+ output = pmtf.output
+ print(message)
+ print('Exception {} {} (caught in test_runner, running test {} {} {} stage {})'.
+ format(ex_type, ex, index, tidx['id'], tidx['name'], stage))
+ print('---------------')
+ print('traceback')
+ traceback.print_tb(ex_tb)
+ print('---------------')
+ if stage == 'teardown':
+ print('accumulated output for this test:')
+ if pmtf.output:
+ print(pmtf.output)
+ print('---------------')
break
index += 1
# if we failed in setup or teardown,
- # fill in the remaining tests with not ok
+ # fill in the remaining tests with ok-skipped
count = index
tap += 'about to flush the tap output if tests need to be skipped\n'
if tcount + 1 != index:
for tidx in testlist[index - 1:]:
- msg = 'skipped - previous setup or teardown failed'
+ msg = 'skipped - previous {} failed'.format(stage)
tap += 'ok {} - {} # {} {} {}\n'.format(
count, tidx['id'], msg, index, badtest.get('id', '--Unknown--'))
count += 1
@@ -347,9 +403,9 @@
global NAMES
if args.path != None:
- NAMES['TC'] = args.path
+ NAMES['TC'] = args.path
if args.device != None:
- NAMES['DEV2'] = args.device
+ NAMES['DEV2'] = args.device
if not os.path.isfile(NAMES['TC']):
print("The specified tc path " + NAMES['TC'] + " does not exist.")
exit(1)
@@ -389,7 +445,7 @@
for c in alltests:
if (c["id"] == ""):
while True:
- newid = str('%04x' % random.randrange(16**4))
+ newid = str('{:04x}'.format(random.randrange(16**4)))
if (does_id_exist(alltests, newid)):
continue
else:
diff --git a/tools/testing/selftests/tc-testing/tdc_batch.py b/tools/testing/selftests/tc-testing/tdc_batch.py
index 707c6bf..52fa539 100755
--- a/tools/testing/selftests/tc-testing/tdc_batch.py
+++ b/tools/testing/selftests/tc-testing/tdc_batch.py
@@ -49,13 +49,13 @@
for i in range(0x100):
for j in range(0x100):
for k in range(0x100):
- mac = ("%02x:%02x:%02x" % (i, j, k))
+ mac = ("{:02x}:{:02x}:{:02x}".format(i, j, k))
src_mac = "e4:11:00:" + mac
dst_mac = "e4:12:00:" + mac
- cmd = ("filter add dev %s %s protocol ip parent ffff: flower %s "
- "src_mac %s dst_mac %s action drop %s" %
+ cmd = ("filter add dev {} {} protocol ip parent ffff: flower {} "
+ "src_mac {} dst_mac {} action drop {}".format
(device, prio, skip, src_mac, dst_mac, share_action))
- file.write("%s\n" % cmd)
+ file.write("{}\n".format(cmd))
index += 1
if index >= number:
file.close()
