* [PATCH net-next v2 2/9] net: dsa: mv88e6xxx: move hidden registers operations in own file
From: Marek Behún @ 2019-08-23 21:25 UTC (permalink / raw)
To: netdev
Cc: Andrew Lunn, Vivien Didelot, Florian Fainelli, Vladimir Oltean,
Marek Behún
In-Reply-To: <20190823212603.13456-1-marek.behun@nic.cz>
This patch moves the functions operating on the hidden debug registers
into it's own file, port_hidden.c. The functions prefix is renamed from
mv88e6390_hidden_ to mv88e6xxx_port_hidden_, to be consistent with the
rest of this driver.
Signed-off-by: Marek Behún <marek.behun@nic.cz>
---
drivers/net/dsa/mv88e6xxx/Makefile | 1 +
drivers/net/dsa/mv88e6xxx/chip.c | 58 +-------------------
drivers/net/dsa/mv88e6xxx/port.h | 6 +++
drivers/net/dsa/mv88e6xxx/port_hidden.c | 70 +++++++++++++++++++++++++
4 files changed, 79 insertions(+), 56 deletions(-)
create mode 100644 drivers/net/dsa/mv88e6xxx/port_hidden.c
diff --git a/drivers/net/dsa/mv88e6xxx/Makefile b/drivers/net/dsa/mv88e6xxx/Makefile
index e85755dde90b..aa645ff86f64 100644
--- a/drivers/net/dsa/mv88e6xxx/Makefile
+++ b/drivers/net/dsa/mv88e6xxx/Makefile
@@ -10,6 +10,7 @@ mv88e6xxx-$(CONFIG_NET_DSA_MV88E6XXX_GLOBAL2) += global2_scratch.o
mv88e6xxx-$(CONFIG_NET_DSA_MV88E6XXX_PTP) += hwtstamp.o
mv88e6xxx-objs += phy.o
mv88e6xxx-objs += port.o
+mv88e6xxx-objs += port_hidden.o
mv88e6xxx-$(CONFIG_NET_DSA_MV88E6XXX_PTP) += ptp.o
mv88e6xxx-objs += serdes.o
mv88e6xxx-objs += smi.o
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index d0bf98c10b2b..47927df6d8e0 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -2317,60 +2317,6 @@ static int mv88e6xxx_stats_setup(struct mv88e6xxx_chip *chip)
return mv88e6xxx_g1_stats_clear(chip);
}
-/* The mv88e6390 has some hidden registers used for debug and
- * development. The errata also makes use of them.
- */
-static int mv88e6390_hidden_write(struct mv88e6xxx_chip *chip, int port,
- int reg, u16 val)
-{
- u16 ctrl;
- int err;
-
- err = mv88e6xxx_port_write(chip, PORT_RESERVED_1A_DATA_PORT,
- PORT_RESERVED_1A, val);
- if (err)
- return err;
-
- ctrl = PORT_RESERVED_1A_BUSY | PORT_RESERVED_1A_WRITE |
- PORT_RESERVED_1A_BLOCK | port << PORT_RESERVED_1A_PORT_SHIFT |
- reg;
-
- return mv88e6xxx_port_write(chip, PORT_RESERVED_1A_CTRL_PORT,
- PORT_RESERVED_1A, ctrl);
-}
-
-static int mv88e6390_hidden_wait(struct mv88e6xxx_chip *chip)
-{
- int bit = __bf_shf(PORT_RESERVED_1A_BUSY);
-
- return mv88e6xxx_wait_bit(chip, PORT_RESERVED_1A_CTRL_PORT,
- PORT_RESERVED_1A, bit, 0);
-}
-
-
-static int mv88e6390_hidden_read(struct mv88e6xxx_chip *chip, int port,
- int reg, u16 *val)
-{
- u16 ctrl;
- int err;
-
- ctrl = PORT_RESERVED_1A_BUSY | PORT_RESERVED_1A_READ |
- PORT_RESERVED_1A_BLOCK | port << PORT_RESERVED_1A_PORT_SHIFT |
- reg;
-
- err = mv88e6xxx_port_write(chip, PORT_RESERVED_1A_CTRL_PORT,
- PORT_RESERVED_1A, ctrl);
- if (err)
- return err;
-
- err = mv88e6390_hidden_wait(chip);
- if (err)
- return err;
-
- return mv88e6xxx_port_read(chip, PORT_RESERVED_1A_DATA_PORT,
- PORT_RESERVED_1A, val);
-}
-
/* Check if the errata has already been applied. */
static bool mv88e6390_setup_errata_applied(struct mv88e6xxx_chip *chip)
{
@@ -2379,7 +2325,7 @@ static bool mv88e6390_setup_errata_applied(struct mv88e6xxx_chip *chip)
u16 val;
for (port = 0; port < mv88e6xxx_num_ports(chip); port++) {
- err = mv88e6390_hidden_read(chip, port, 0, &val);
+ err = mv88e6xxx_port_hidden_read(chip, port, 0, &val);
if (err) {
dev_err(chip->dev,
"Error reading hidden register: %d\n", err);
@@ -2412,7 +2358,7 @@ static int mv88e6390_setup_errata(struct mv88e6xxx_chip *chip)
}
for (port = 0; port < mv88e6xxx_num_ports(chip); port++) {
- err = mv88e6390_hidden_write(chip, port, 0, 0x01c0);
+ err = mv88e6xxx_port_hidden_write(chip, port, 0, 0x01c0);
if (err)
return err;
}
diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h
index 1abf5ea033e2..2b251ba30e52 100644
--- a/drivers/net/dsa/mv88e6xxx/port.h
+++ b/drivers/net/dsa/mv88e6xxx/port.h
@@ -353,4 +353,10 @@ int mv88e6095_port_set_upstream_port(struct mv88e6xxx_chip *chip, int port,
int mv88e6xxx_port_disable_learn_limit(struct mv88e6xxx_chip *chip, int port);
int mv88e6xxx_port_disable_pri_override(struct mv88e6xxx_chip *chip, int port);
+int mv88e6xxx_port_hidden_write(struct mv88e6xxx_chip *chip, int port, int reg,
+ u16 val);
+int mv88e6xxx_port_hidden_wait(struct mv88e6xxx_chip *chip);
+int mv88e6xxx_port_hidden_read(struct mv88e6xxx_chip *chip, int port, int reg,
+ u16 *val);
+
#endif /* _MV88E6XXX_PORT_H */
diff --git a/drivers/net/dsa/mv88e6xxx/port_hidden.c b/drivers/net/dsa/mv88e6xxx/port_hidden.c
new file mode 100644
index 000000000000..37520b6b8c89
--- /dev/null
+++ b/drivers/net/dsa/mv88e6xxx/port_hidden.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Marvell 88E6xxx Switch Hidden Registers support
+ *
+ * Copyright (c) 2008 Marvell Semiconductor
+ *
+ * Copyright (c) 2019 Andrew Lunn <andrew@lunn.ch>
+ */
+
+#include <linux/bitfield.h>
+
+#include "chip.h"
+#include "port.h"
+
+/* The mv88e6390 and mv88e6341 have some hidden registers used for debug and
+ * development. The errata also makes use of them.
+ */
+int mv88e6xxx_port_hidden_write(struct mv88e6xxx_chip *chip, int port, int reg,
+ u16 val)
+{
+ u16 ctrl;
+ int err;
+
+ err = mv88e6xxx_port_write(chip, MV88E6XXX_PORT_RESERVED_1A_DATA_PORT,
+ MV88E6XXX_PORT_RESERVED_1A, val);
+ if (err)
+ return err;
+
+ ctrl = MV88E6XXX_PORT_RESERVED_1A_BUSY |
+ MV88E6XXX_PORT_RESERVED_1A_WRITE |
+ MV88E6XXX_PORT_RESERVED_1A_BLOCK |
+ port << MV88E6XXX_PORT_RESERVED_1A_PORT_SHIFT |
+ reg;
+
+ return mv88e6xxx_port_write(chip, MV88E6XXX_PORT_RESERVED_1A_CTRL_PORT,
+ MV88E6XXX_PORT_RESERVED_1A, ctrl);
+}
+
+int mv88e6xxx_port_hidden_wait(struct mv88e6xxx_chip *chip)
+{
+ int bit = __bf_shf(MV88E6XXX_PORT_RESERVED_1A_BUSY);
+
+ return mv88e6xxx_wait_bit(chip, MV88E6XXX_PORT_RESERVED_1A_CTRL_PORT,
+ MV88E6XXX_PORT_RESERVED_1A, bit, 0);
+}
+
+int mv88e6xxx_port_hidden_read(struct mv88e6xxx_chip *chip, int port, int reg,
+ u16 *val)
+{
+ u16 ctrl;
+ int err;
+
+ ctrl = MV88E6XXX_PORT_RESERVED_1A_BUSY |
+ MV88E6XXX_PORT_RESERVED_1A_READ |
+ MV88E6XXX_PORT_RESERVED_1A_BLOCK |
+ port << MV88E6XXX_PORT_RESERVED_1A_PORT_SHIFT |
+ reg;
+
+ err = mv88e6xxx_port_write(chip, MV88E6XXX_PORT_RESERVED_1A_CTRL_PORT,
+ MV88E6XXX_PORT_RESERVED_1A, ctrl);
+ if (err)
+ return err;
+
+ err = mv88e6xxx_port_hidden_wait(chip);
+ if (err)
+ return err;
+
+ return mv88e6xxx_port_read(chip, MV88E6XXX_PORT_RESERVED_1A_DATA_PORT,
+ MV88E6XXX_PORT_RESERVED_1A, val);
+}
--
2.21.0
^ permalink raw reply related
* [PATCH net-next v2 5/9] net: dsa: mv88e6xxx: add serdes_get_lane method for Topaz family
From: Marek Behún @ 2019-08-23 21:25 UTC (permalink / raw)
To: netdev
Cc: Andrew Lunn, Vivien Didelot, Florian Fainelli, Vladimir Oltean,
Marek Behún
In-Reply-To: <20190823212603.13456-1-marek.behun@nic.cz>
The Topaz family has only one SERDES, on port 5, with address 0x15.
Currently we have MV88E6341_ADDR_SERDES macro used in the
mv88e6341_serdes_power method. Rename the macro to MV88E6341_PORT5_LANE
and use the new mv88e6xxx_serdes_get_lane method in
mv88e6341_serdes_power.
Signed-off-by: Marek Behún <marek.behun@nic.cz>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
---
drivers/net/dsa/mv88e6xxx/chip.c | 2 ++
drivers/net/dsa/mv88e6xxx/serdes.c | 25 ++++++++++++++++++++++---
drivers/net/dsa/mv88e6xxx/serdes.h | 3 ++-
3 files changed, 26 insertions(+), 4 deletions(-)
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index dfffeaf925a4..6343af09fb1e 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -2928,6 +2928,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = {
.vtu_getnext = mv88e6352_g1_vtu_getnext,
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
.serdes_power = mv88e6341_serdes_power,
+ .serdes_get_lane = mv88e6341_serdes_get_lane,
.gpio_ops = &mv88e6352_gpio_ops,
.phylink_validate = mv88e6341_phylink_validate,
};
@@ -3622,6 +3623,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = {
.vtu_getnext = mv88e6352_g1_vtu_getnext,
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
.serdes_power = mv88e6341_serdes_power,
+ .serdes_get_lane = mv88e6341_serdes_get_lane,
.gpio_ops = &mv88e6352_gpio_ops,
.avb_ops = &mv88e6390_avb_ops,
.ptp_ops = &mv88e6352_ptp_ops,
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c
index 523f58c57972..1f40130bfb68 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.c
+++ b/drivers/net/dsa/mv88e6xxx/serdes.c
@@ -298,6 +298,21 @@ int mv88e6xxx_serdes_get_lane(struct mv88e6xxx_chip *chip, int port)
return chip->info->ops->serdes_get_lane(chip, port);
}
+int mv88e6341_serdes_get_lane(struct mv88e6xxx_chip *chip, int port)
+{
+ u8 cmode = chip->ports[port].cmode;
+
+ if (port != 5)
+ return -ENODEV;
+
+ if (cmode == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
+ cmode == MV88E6XXX_PORT_STS_CMODE_SGMII ||
+ cmode == MV88E6XXX_PORT_STS_CMODE_2500BASEX)
+ return MV88E6341_PORT5_LANE;
+
+ return -ENODEV;
+}
+
int mv88e6390_serdes_get_lane(struct mv88e6xxx_chip *chip, int port)
{
u8 cmode = chip->ports[port].cmode;
@@ -747,15 +762,19 @@ void mv88e6390_serdes_irq_free(struct mv88e6xxx_chip *chip, int port)
int mv88e6341_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on)
{
u8 cmode = chip->ports[port].cmode;
+ int lane;
- if (port != 5)
+ lane = mv88e6xxx_serdes_get_lane(chip, port);
+ if (lane == -ENODEV)
return 0;
+ if (lane < 0)
+ return lane;
+
if (cmode == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
cmode == MV88E6XXX_PORT_STS_CMODE_SGMII ||
cmode == MV88E6XXX_PORT_STS_CMODE_2500BASEX)
- return mv88e6390_serdes_power_sgmii(chip, MV88E6341_ADDR_SERDES,
- on);
+ return mv88e6390_serdes_power_sgmii(chip, lane, on);
return 0;
}
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h
index f2ca3bcc3893..de6f1939c541 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.h
+++ b/drivers/net/dsa/mv88e6xxx/serdes.h
@@ -28,7 +28,7 @@
#define MV88E6352_SERDES_INT_STATUS 0x13
-#define MV88E6341_ADDR_SERDES 0x15
+#define MV88E6341_PORT5_LANE 0x15
#define MV88E6390_PORT9_LANE0 0x09
#define MV88E6390_PORT9_LANE1 0x12
@@ -75,6 +75,7 @@
#define MV88E6390_SGMII_PHY_STATUS_LINK BIT(10)
int mv88e6xxx_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
+int mv88e6341_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
int mv88e6390_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
int mv88e6390x_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
int mv88e6341_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on);
--
2.21.0
^ permalink raw reply related
* [PATCH net-next v2 1/9] net: dsa: mv88e6xxx: support 2500base-x in SGMII IRQ handler
From: Marek Behún @ 2019-08-23 21:25 UTC (permalink / raw)
To: netdev
Cc: Andrew Lunn, Vivien Didelot, Florian Fainelli, Vladimir Oltean,
Marek Behún
In-Reply-To: <20190823212603.13456-1-marek.behun@nic.cz>
The mv88e6390_serdes_irq_link_sgmii IRQ handler reads the SERDES PHY
status register to determine speed, among other things. If cmode of the
port is set to 2500base-x, though, the PHY still reports 1000 Mbps (the
PHY register itself does not differentiate between 1000 Mbps and 2500
Mbps - it thinks it is running at 1000 Mbps, although clock is 2.5x
faster).
Look at the cmode and set SPEED_2500 if cmode is set to 2500base-x.
Also tell mv88e6xxx_port_setup_mac the PHY interface mode corresponding
to current cmode in terms of phy_interface_t.
Signed-off-by: Marek Behún <marek.behun@nic.cz>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Vladimir Oltean <olteanv@gmail.com>
Cc: Vivien Didelot <vivien.didelot@gmail.com>
---
drivers/net/dsa/mv88e6xxx/serdes.c | 23 +++++++++++++++++++++--
1 file changed, 21 insertions(+), 2 deletions(-)
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c
index 20c526c2a9ee..678aaba3d019 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.c
+++ b/drivers/net/dsa/mv88e6xxx/serdes.c
@@ -505,9 +505,11 @@ int mv88e6390x_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on)
static void mv88e6390_serdes_irq_link_sgmii(struct mv88e6xxx_chip *chip,
int port, int lane)
{
+ u8 cmode = chip->ports[port].cmode;
struct dsa_switch *ds = chip->ds;
int duplex = DUPLEX_UNKNOWN;
int speed = SPEED_UNKNOWN;
+ phy_interface_t mode;
int link, err;
u16 status;
@@ -527,7 +529,10 @@ static void mv88e6390_serdes_irq_link_sgmii(struct mv88e6xxx_chip *chip,
switch (status & MV88E6390_SGMII_PHY_STATUS_SPEED_MASK) {
case MV88E6390_SGMII_PHY_STATUS_SPEED_1000:
- speed = SPEED_1000;
+ if (cmode == MV88E6XXX_PORT_STS_CMODE_2500BASEX)
+ speed = SPEED_2500;
+ else
+ speed = SPEED_1000;
break;
case MV88E6390_SGMII_PHY_STATUS_SPEED_100:
speed = SPEED_100;
@@ -541,8 +546,22 @@ static void mv88e6390_serdes_irq_link_sgmii(struct mv88e6xxx_chip *chip,
}
}
+ switch (cmode) {
+ case MV88E6XXX_PORT_STS_CMODE_SGMII:
+ mode = PHY_INTERFACE_MODE_SGMII;
+ break;
+ case MV88E6XXX_PORT_STS_CMODE_1000BASE_X:
+ mode = PHY_INTERFACE_MODE_1000BASEX;
+ break;
+ case MV88E6XXX_PORT_STS_CMODE_2500BASEX:
+ mode = PHY_INTERFACE_MODE_2500BASEX;
+ break;
+ default:
+ mode = PHY_INTERFACE_MODE_NA;
+ }
+
err = mv88e6xxx_port_setup_mac(chip, port, link, speed, duplex,
- PAUSE_OFF, PHY_INTERFACE_MODE_NA);
+ PAUSE_OFF, mode);
if (err)
dev_err(chip->dev, "can't propagate PHY settings to MAC: %d\n",
err);
--
2.21.0
^ permalink raw reply related
* [PATCH net-next v2 3/9] net: dsa: mv88e6xxx: fix port hidden register macros
From: Marek Behún @ 2019-08-23 21:25 UTC (permalink / raw)
To: netdev
Cc: Andrew Lunn, Vivien Didelot, Florian Fainelli, Vladimir Oltean,
Marek Behún
In-Reply-To: <20190823212603.13456-1-marek.behun@nic.cz>
In order to be uniform with the rest of the driver, prepend hidden
register macro names with the MV88E6XXX_ prefix. Also do not use the
BIT() macro nor bit shifts, to be consistent with rest of port.h macro
definitions.
Signed-off-by: Marek Behún <marek.behun@nic.cz>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
---
drivers/net/dsa/mv88e6xxx/port.h | 16 ++++++++--------
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h
index 2b251ba30e52..58aecf5a7cb4 100644
--- a/drivers/net/dsa/mv88e6xxx/port.h
+++ b/drivers/net/dsa/mv88e6xxx/port.h
@@ -261,14 +261,14 @@
#define MV88E6095_PORT_IEEE_PRIO_REMAP_4567 0x19
/* Offset 0x1a: Magic undocumented errata register */
-#define PORT_RESERVED_1A 0x1a
-#define PORT_RESERVED_1A_BUSY BIT(15)
-#define PORT_RESERVED_1A_WRITE BIT(14)
-#define PORT_RESERVED_1A_READ 0
-#define PORT_RESERVED_1A_PORT_SHIFT 5
-#define PORT_RESERVED_1A_BLOCK (0xf << 10)
-#define PORT_RESERVED_1A_CTRL_PORT 4
-#define PORT_RESERVED_1A_DATA_PORT 5
+#define MV88E6XXX_PORT_RESERVED_1A 0x1a
+#define MV88E6XXX_PORT_RESERVED_1A_BUSY 0x8000
+#define MV88E6XXX_PORT_RESERVED_1A_WRITE 0x4000
+#define MV88E6XXX_PORT_RESERVED_1A_READ 0x0000
+#define MV88E6XXX_PORT_RESERVED_1A_PORT_SHIFT 5
+#define MV88E6XXX_PORT_RESERVED_1A_BLOCK 0x3c00
+#define MV88E6XXX_PORT_RESERVED_1A_CTRL_PORT 0x04
+#define MV88E6XXX_PORT_RESERVED_1A_DATA_PORT 0x05
int mv88e6xxx_port_read(struct mv88e6xxx_chip *chip, int port, int reg,
u16 *val);
--
2.21.0
^ permalink raw reply related
* Re: [PATCH v2 2/5] spi: spi-fsl-dspi: Exit the ISR with IRQ_NONE when it's not ours
From: Mark Brown @ 2019-08-23 21:03 UTC (permalink / raw)
To: Vladimir Oltean; +Cc: linux-spi, lkml, devicetree, netdev
In-Reply-To: <CA+h21hrj6VjceGJFz7XuS9DFjy=Fb5SHTYUuOWkagtsWf0Egbg@mail.gmail.com>
[-- Attachment #1: Type: text/plain, Size: 3563 bytes --]
On Fri, Aug 23, 2019 at 03:06:52PM +0300, Vladimir Oltean wrote:
> - You left change requests in the initial patchset I submitted, but
> you partially applied the series anyway. You didn't give me a chance
> to respin the whole series and put the shared IRQ fix on top, so it
> applies on old trees as well. No problem, I sent two versions of the
> patch.
Right, and this is fine. A big part of this is that it's just
generally bad practice to not have fixes at the front of the
series, I'd flag this up as a problem even if the code was all
new and there was no question of applying as a bug fix. It's
something that's noticable just at the level of looking at the
shape of the series without even looking at the contents of the
patches, if the fix is actually a good one or anything like that.
In the context of this it made it look like the reason you'd had
to do two versions.
> So I didn't put any target version in the patch titles this time,
> although arguably it would have been clearer to you that there's a
> patch for-5.4 and another version of it for-4.20 (which i *think* is
> how I should submit a fix, I don't see any branch for inclusion in
> stable trees per se).
Not for 4.20, for v5.3 - we basically only fix Linus' tree
directly, anything else gets backported from there unless it's
super important. I don't think anyone is updating v4.20 at all
these days, the version number change from v4 to v5 was totally
arbatrary.
> Yes, I did send a cover letter for a single patch. I thought it's
> harder to miss than a note hidden under patch 2/5 of one series, and
> in the note section of the other's. I think you could have also made
If you're sending a multi-patch series it's of course good to
send a cover letter, it's just single patches where it's adding
overhead.
> No problem, you missed the link between the two. I sent you a link to
> the lkml archive. You said "I'm not online enough to readily follow
> that link right now". Please teach me - I really don't know - how can
It's not that I missed the link between them, it's that what I'd
expected to see was the fix being the first patch in the series
for -next and for that fix to look substantially the same with at
most some context difference. I wasn't expecting to see a
completely different patch that wasn't at the start of the
series, had the fix been at the start of the series it'd have
been fairly clear what was going on but the refactoring patch
looked like the main reason you'd needed different versions (it's
certainly why they don't visually resemble each other).
In other words it looked like you'd sent a different fix because
the fix you'd done for -next was based on the first patch in the
series rather than there also being some context changes.
> I make links between patchsets easier for you to follow, if you don't
> read cover letters and you can't access lkml? I promise I'll use that
> method next time.
Like I said include a plain text description of what you're
linking to (eg, the subject line from a mail).
> > I do frequently catch up on my mail on flights or while otherwise
> > travelling so this is even more pressing for me than just being about
> > making things a bit easier to read.
> Maybe you simply should do something else while traveling, just saying.
I could also add in the coffee shop I sometimes work from which
doesn't have WiFi or mobile coverage. Besides, like that part of
the text does say it's also a usability thing, having to fire up
a web browser to figure out what's being described is a stumbling
block.
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply
* [PATCH bpf] bpf: fix use after free in prog symbol exposure
From: Daniel Borkmann @ 2019-08-23 20:14 UTC (permalink / raw)
To: ast; +Cc: bpf, netdev, Daniel Borkmann, syzbot+bd3bba6ff3fcea7a6ec6,
Song Liu
syzkaller managed to trigger the warning in bpf_jit_free() which checks via
bpf_prog_kallsyms_verify_off() for potentially unlinked JITed BPF progs
in kallsyms, and subsequently trips over GPF when walking kallsyms entries:
[...]
8021q: adding VLAN 0 to HW filter on device batadv0
8021q: adding VLAN 0 to HW filter on device batadv0
WARNING: CPU: 0 PID: 9869 at kernel/bpf/core.c:810 bpf_jit_free+0x1e8/0x2a0
Kernel panic - not syncing: panic_on_warn set ...
CPU: 0 PID: 9869 Comm: kworker/0:7 Not tainted 5.0.0-rc8+ #1
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Workqueue: events bpf_prog_free_deferred
Call Trace:
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x113/0x167 lib/dump_stack.c:113
panic+0x212/0x40b kernel/panic.c:214
__warn.cold.8+0x1b/0x38 kernel/panic.c:571
report_bug+0x1a4/0x200 lib/bug.c:186
fixup_bug arch/x86/kernel/traps.c:178 [inline]
do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:271
do_invalid_op+0x36/0x40 arch/x86/kernel/traps.c:290
invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:973
RIP: 0010:bpf_jit_free+0x1e8/0x2a0
Code: 02 4c 89 e2 83 e2 07 38 d0 7f 08 84 c0 0f 85 86 00 00 00 48 ba 00 02 00 00 00 00 ad de 0f b6 43 02 49 39 d6 0f 84 5f fe ff ff <0f> 0b e9 58 fe ff ff 48 b8 00 00 00 00 00 fc ff df 4c 89 e2 48 c1
RSP: 0018:ffff888092f67cd8 EFLAGS: 00010202
RAX: 0000000000000007 RBX: ffffc90001947000 RCX: ffffffff816e9d88
RDX: dead000000000200 RSI: 0000000000000008 RDI: ffff88808769f7f0
RBP: ffff888092f67d00 R08: fffffbfff1394059 R09: fffffbfff1394058
R10: fffffbfff1394058 R11: ffffffff89ca02c7 R12: ffffc90001947002
R13: ffffc90001947020 R14: ffffffff881eca80 R15: ffff88808769f7e8
BUG: unable to handle kernel paging request at fffffbfff400d000
#PF error: [normal kernel read fault]
PGD 21ffee067 P4D 21ffee067 PUD 21ffed067 PMD 9f942067 PTE 0
Oops: 0000 [#1] PREEMPT SMP KASAN
CPU: 0 PID: 9869 Comm: kworker/0:7 Not tainted 5.0.0-rc8+ #1
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Workqueue: events bpf_prog_free_deferred
RIP: 0010:bpf_get_prog_addr_region kernel/bpf/core.c:495 [inline]
RIP: 0010:bpf_tree_comp kernel/bpf/core.c:558 [inline]
RIP: 0010:__lt_find include/linux/rbtree_latch.h:115 [inline]
RIP: 0010:latch_tree_find include/linux/rbtree_latch.h:208 [inline]
RIP: 0010:bpf_prog_kallsyms_find+0x107/0x2e0 kernel/bpf/core.c:632
Code: 00 f0 ff ff 44 38 c8 7f 08 84 c0 0f 85 fa 00 00 00 41 f6 45 02 01 75 02 0f 0b 48 39 da 0f 82 92 00 00 00 48 89 d8 48 c1 e8 03 <42> 0f b6 04 30 84 c0 74 08 3c 03 0f 8e 45 01 00 00 8b 03 48 c1 e0
[...]
Upon further debugging, it turns out that whenever we trigger this
issue, the kallsyms removal in bpf_prog_ksym_node_del() was /skipped/
but yet bpf_jit_free() reported that the entry is /in use/.
Problem is that symbol exposure via bpf_prog_kallsyms_add() but also
perf_event_bpf_event() were done /after/ bpf_prog_new_fd(). Once the
fd is exposed to the public, a parallel close request came in right
before we attempted to do the bpf_prog_kallsyms_add().
Given at this time the prog reference count is one, we start to rip
everything underneath us via bpf_prog_release() -> bpf_prog_put().
The memory is eventually released via deferred free, so we're seeing
that bpf_jit_free() has a kallsym entry because we added it from
bpf_prog_load() but /after/ bpf_prog_put() from the remote CPU.
Therefore, move both notifications /before/ we install the fd. The
issue was never seen between bpf_prog_alloc_id() and bpf_prog_new_fd()
because upon bpf_prog_get_fd_by_id() we'll take another reference to
the BPF prog, so we're still holding the original reference from the
bpf_prog_load().
Fixes: 6ee52e2a3fe4 ("perf, bpf: Introduce PERF_RECORD_BPF_EVENT")
Fixes: 74451e66d516 ("bpf: make jited programs visible in traces")
Reported-by: syzbot+bd3bba6ff3fcea7a6ec6@syzkaller.appspotmail.com
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Song Liu <songliubraving@fb.com>
---
kernel/bpf/syscall.c | 30 ++++++++++++++++++------------
1 file changed, 18 insertions(+), 12 deletions(-)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 5d141f16f6fa..272071e9112f 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1707,20 +1707,26 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
if (err)
goto free_used_maps;
- err = bpf_prog_new_fd(prog);
- if (err < 0) {
- /* failed to allocate fd.
- * bpf_prog_put() is needed because the above
- * bpf_prog_alloc_id() has published the prog
- * to the userspace and the userspace may
- * have refcnt-ed it through BPF_PROG_GET_FD_BY_ID.
- */
- bpf_prog_put(prog);
- return err;
- }
-
+ /* Upon success of bpf_prog_alloc_id(), the BPF prog is
+ * effectively publicly exposed. However, retrieving via
+ * bpf_prog_get_fd_by_id() will take another reference,
+ * therefore it cannot be gone underneath us.
+ *
+ * Only for the time /after/ successful bpf_prog_new_fd()
+ * and before returning to userspace, we might just hold
+ * one reference and any parallel close on that fd could
+ * rip everything out. Hence, below notifications must
+ * happen before bpf_prog_new_fd().
+ *
+ * Also, any failure handling from this point onwards must
+ * be using bpf_prog_put() given the program is exposed.
+ */
bpf_prog_kallsyms_add(prog);
perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_LOAD, 0);
+
+ err = bpf_prog_new_fd(prog);
+ if (err < 0)
+ bpf_prog_put(prog);
return err;
free_used_maps:
--
2.21.0
^ permalink raw reply related
* Re: [PATCH v6 4/4] net: phy: realtek: Add LED configuration support for RTL8211E
From: Florian Fainelli @ 2019-08-23 19:58 UTC (permalink / raw)
To: Doug Anderson
Cc: Matthias Kaehlcke, Pavel Machek, David S . Miller, Rob Herring,
Mark Rutland, Andrew Lunn, Heiner Kallweit, netdev, devicetree,
LKML
In-Reply-To: <CAD=FV=WvWjcVX1YNxKsi_TmJP6vdBZ==bYOVGs2VjUqVhEjpuA@mail.gmail.com>
On 8/16/19 3:39 PM, Doug Anderson wrote:
> Hi,
>
> On Fri, Aug 16, 2019 at 3:12 PM Florian Fainelli <f.fainelli@gmail.com> wrote:
>>
>> On 8/16/19 2:27 PM, Matthias Kaehlcke wrote:
>>> On Fri, Aug 16, 2019 at 10:13:42PM +0200, Pavel Machek wrote:
>>>> On Tue 2019-08-13 12:11:47, Matthias Kaehlcke wrote:
>>>>> Add a .config_led hook which is called by the PHY core when
>>>>> configuration data for a PHY LED is available. Each LED can be
>>>>> configured to be solid 'off, solid 'on' for certain (or all)
>>>>> link speeds or to blink on RX/TX activity.
>>>>>
>>>>> Signed-off-by: Matthias Kaehlcke <mka@chromium.org>
>>>>
>>>> THis really needs to go through the LED subsystem,
>>>
>>> Sorry, I used what get_maintainers.pl threw at me, I should have
>>> manually cc-ed the LED list.
>>>
>>>> and use the same userland interfaces as the rest of the system.
>>>
>>> With the PHY maintainers we discussed to define a binding that is
>>> compatible with that of the LED one, to have the option to integrate
>>> it with the LED subsystem later. The integration itself is beyond the
>>> scope of this patchset.
>>>
>>> The PHY LED configuration is a low priority for the project I'm
>>> working on. I wanted to make an attempt to upstream it and spent
>>> already significantly more time on it than planned, if integration
>>> with the LED framework now is a requirement please consider this
>>> series abandonded.
>>
>> While I have an appreciation for how hard it can be to work in a
>> corporate environment while doing upstream first and working with
>> virtually unbounded goals (in time or scope) due to maintainers and
>> reviewers, that kind of statement can hinder your ability to establish
>> trust with peers in the community as it can be read as take it or leave it.
>
> You think so? I feel like Matthias is simply expressing the reality
> of the situation here and I'd rather see a statement like this posted
> than the series just silently dropped. Communication is good.
>
> In general on Chrome OS we don't spent lots of time tweaking with
> Ethernet and even less time tweaking with Ethernet on ARM boards where
> you might need a binding like this, so it's pretty hard to justify up
> the management chain spending massive amounts of resources on it. In
> this case we have two existing ARM boards which we're trying to uprev
> from 3.14 to 4.19 which were tweaking the Ethernet driver in some
> downstream code. We thought it would be nice to try to come up with a
> solution that could land upstream, which is usually what we try to do
> in these cases.
>
> Normally if there is some major architecture needed that can't fit in
> the scope of a project, we would do a downstream solution for the
> project and then fork off the task (maybe by a different Engineer or a
> contractor) to get a solution that can land upstream. ...but in this
> case it seems hard to justify because it's unlikely we would need it
> again anytime remotely soon.
>
> So I guess the alternatives to what Matthias did would have been:
>
> A) Don't even try to upstream. Seems worse. At least this way
> there's something a future person can start from and the discussion is
> rolling.
>
> B) Keep spending tons of time on something even though management
> doesn't want him to. Seems worse.
>
> C) Spend his nights and weekends working on this. Seems worse.
>
> D) Silently stop working on it without saying "I'm going to stop". Seems worse.
>
> ...unless you have a brilliant "E)" I think what Matthias did here is
> exactly right.
I must apologize for making that statement since it was not fair to
Matthias, and he has been clear about how much time he can spend on that
specific, please accept my apologies for that.
Having had many recent encounters with various people not driving
projects to completion lately (not specifically within Linux), it looks
like I am overly sensitive about flagging words and patch status that
may fall within that lexicon. The choice of word is what triggered me.
>
> BTW: I'm giving a talk on this topic next week at ELC [1]. If you're
> going to be there feel free to attend. ...or just read the slides if
> not.
I wish I could be there but that was not possible this year.
>
>
>> The LED subsystem integration can definitively come in later from my 2
>> cents perspective and this patch series as it stands is valuable and
>> avoids inventing new bindings.
>
> If something like this series can land and someone can later try to
> make the situation better then I think that would be awesome. I don't
> think Matthias is saying "I won't spin" or "I won't take feedback".
> He's just expressing that he can't keep working on this indefinitely.
>
>
>
> [1] https://ossna19.sched.com/event/PVSV/how-chrome-os-works-with-upstream-linux-douglas-anderson-google
>
> -Doug
>
--
Florian
^ permalink raw reply
* [PATCH] net/mlx5: fix a -Wstringop-truncation warning
From: Qian Cai @ 2019-08-23 19:56 UTC (permalink / raw)
To: saeedm
Cc: leon, davem, moshe, ferasda, eranbe, netdev, linux-rdma,
linux-kernel, Qian Cai
In file included from ./arch/powerpc/include/asm/paca.h:15,
from ./arch/powerpc/include/asm/current.h:13,
from ./include/linux/thread_info.h:21,
from ./include/asm-generic/preempt.h:5,
from ./arch/powerpc/include/generated/asm/preempt.h:1,
from ./include/linux/preempt.h:78,
from ./include/linux/spinlock.h:51,
from ./include/linux/wait.h:9,
from ./include/linux/completion.h:12,
from ./include/linux/mlx5/driver.h:37,
from
drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h:6,
from
drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c:33:
In function 'strncpy',
inlined from 'mlx5_fw_tracer_save_trace' at
drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c:549:2,
inlined from 'mlx5_tracer_print_trace' at
drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c:574:2:
./include/linux/string.h:305:9: warning: '__builtin_strncpy' output may
be truncated copying 256 bytes from a string of length 511
[-Wstringop-truncation]
return __builtin_strncpy(p, q, size);
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Fix it by using the new strscpy_pad() since the commit 458a3bf82df4
("lib/string: Add strscpy_pad() function") which will always
NUL-terminate the string, and avoid possibly leak data through the ring
buffer where non-admin account might enable these events through perf.
Fixes: fd1483fe1f9f ("net/mlx5: Add support for FW reporter dump")
Signed-off-by: Qian Cai <cai@lca.pw>
---
drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index 8a4930c8bf62..2011eaf15cc5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -546,7 +546,7 @@ static void mlx5_fw_tracer_save_trace(struct mlx5_fw_tracer *tracer,
trace_data->timestamp = timestamp;
trace_data->lost = lost;
trace_data->event_id = event_id;
- strncpy(trace_data->msg, msg, TRACE_STR_MSG);
+ strscpy_pad(trace_data->msg, msg, TRACE_STR_MSG);
tracer->st_arr.saved_traces_index =
(tracer->st_arr.saved_traces_index + 1) & (SAVED_TRACES_NUM - 1);
--
1.8.3.1
^ permalink raw reply related
* Re: [PATCH v2 0/2] Simplify mtty driver and mdev core
From: Alex Williamson @ 2019-08-23 19:43 UTC (permalink / raw)
To: Parav Pandit
Cc: Jiri Pirko, Jiri Pirko, David S . Miller, Kirti Wankhede,
Cornelia Huck, kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
cjia, netdev@vger.kernel.org
In-Reply-To: <AM0PR05MB486648FF7E6624F34842E425D1A40@AM0PR05MB4866.eurprd05.prod.outlook.com>
On Fri, 23 Aug 2019 18:00:30 +0000
Parav Pandit <parav@mellanox.com> wrote:
> > -----Original Message-----
> > From: Alex Williamson <alex.williamson@redhat.com>
> > Sent: Friday, August 23, 2019 10:47 PM
> > To: Parav Pandit <parav@mellanox.com>
> > Cc: Jiri Pirko <jiri@resnulli.us>; Jiri Pirko <jiri@mellanox.com>; David S . Miller
> > <davem@davemloft.net>; Kirti Wankhede <kwankhede@nvidia.com>; Cornelia
> > Huck <cohuck@redhat.com>; kvm@vger.kernel.org; linux-
> > kernel@vger.kernel.org; cjia <cjia@nvidia.com>; netdev@vger.kernel.org
> > Subject: Re: [PATCH v2 0/2] Simplify mtty driver and mdev core
> >
> > On Fri, 23 Aug 2019 16:14:04 +0000
> > Parav Pandit <parav@mellanox.com> wrote:
> >
> > > > > Idea is to have mdev alias as optional.
> > > > > Each mdev_parent says whether it wants mdev_core to generate an
> > > > > alias or not. So only networking device drivers would set it to true.
> > > > > For rest, alias won't be generated, and won't be compared either
> > > > > during creation time. User continue to provide only uuid.
> > > >
> > > > Ok
> > > >
> > > > > I am tempted to have alias collision detection only within
> > > > > children mdevs of the same parent, but doing so will always
> > > > > mandate to prefix in netdev name. And currently we are left with
> > > > > only 3 characters to prefix it, so that may not be good either.
> > > > > Hence, I think mdev core wide alias is better with 12 characters.
> > > >
> > > > I suppose it depends on the API, if the vendor driver can ask the
> > > > mdev core for an alias as part of the device creation process, then
> > > > it could manage the netdev namespace for all its devices, choosing
> > > > how many characters to use, and fail the creation if it can't meet a
> > > > uniqueness requirement. IOW, mdev-core would always provide a full
> > > > sha1 and therefore gets itself out of the uniqueness/collision aspects.
> > > >
> > > This doesn't work. At mdev core level 20 bytes sha1 are unique, so
> > > mdev core allowed to create a mdev.
> >
> > The mdev vendor driver has the opportunity to fail the device creation in
> > mdev_parent_ops.create().
> >
> That is not helpful for below reasons.
> 1. vendor driver doesn't have visibility in other vendor's alias.
> 2. Even for single vendor, it needs to maintain global list of devices to see collision.
> 3. multiple vendors needs to implement same scheme.
>
> Mdev core should be the owner. Shifting ownership from one layer to a
> lower layer in vendor driver doesn't solve the problem (if there is
> one, which I think doesn't exist).
>
> > > And then devlink core chooses
> > > only 6 bytes (12 characters) and there is collision. Things fall
> > > apart. Since mdev provides unique uuid based scheme, it's the mdev
> > > core's ownership to provide unique aliases.
> >
> > You're suggesting/contemplating multiple solutions here, 3-char
> > prefix + 12- char sha1 vs <parent netdev> + ?-char sha1. Also, the
> > 15-char total limit is imposed by an external subsystem, where the
> > vendor driver is the gateway between that subsystem and mdev. How
> > would mdev integrate with another subsystem that maybe only has
> > 9-chars available? Would the vendor driver API specify "I need an
> > alias" or would it specify "I need an X-char length alias"?
> Yes, Vendor driver should say how long the alias it wants.
> However before we implement that, I suggest let such
> vendor/user/driver arrive which needs that. Such variable length
> alias can be added at that time and even with that alias collision
> can be detected by single mdev module.
If we agree that different alias lengths are possible, then I would
request that minimally an mdev sample driver be modified to request an
alias with a length that can be adjusted without recompiling in order
to exercise the collision path.
If mdev-core is guaranteeing uniqueness, does this indicate that each
alias length constitutes a separate namespace? ie. strictly a
strcmp(), not a strncmp() to the shorter alias.
> > Does it make sense that mdev-core would fail creation of a device
> > if there's a collision in the 12-char address space between
> > different subsystems? For example, does enm0123456789ab really
> > collide with xyz0123456789ab?
> I think so, because at mdev level its 12-char alias matters.
> Choosing the prefix not adding prefix is really a user space choice.
>
> > So if
> > mdev were to provided a 40-char sha1, is it possible that the
> > vendor driver could consume this in its create callback, truncate
> > it to the number of chars required by the vendor driver's
> > subsystem, and determine whether a collision exists?
> We shouldn't shift the problem from mdev to multiple vendor drivers
> to detect collision.
>
> I still think that user providing alias is better because it knows
> the use-case system in use, and eliminates these collision issue.
How is a user provided alias immune from collisions? The burden is on
the user to provide both a unique uuid and a unique alias. That makes
it trivial to create a collision.
> > > > > I do not understand how an extra character reduces collision,
> > > > > if that's what you meant.
> > > >
> > > > If the default were for example 3-chars, we might already have
> > > > device 'abc'. A collision would expose one more char of the new
> > > > device, so we might add device with alias 'abcd'. I mentioned
> > > > previously that this leaves an issue for userspace that we can't
> > > > change the alias of device abc, so without additional
> > > > information, userspace can only determine via elimination the
> > > > mapping of alias to device, but userspace has more information
> > > > available to it in the form of sysfs links.
> > > > > Module options are almost not encouraged anymore with other
> > > > > subsystems/drivers.
> > > >
> > > > We don't live in a world of absolutes. I agree that the
> > > > defaults should work in the vast majority of cases. Requiring
> > > > a user to twiddle module options to make things work is
> > > > undesirable, verging on a bug. A module option to enable some
> > > > specific feature, unsafe condition, or test that is outside of
> > > > the typical use case is reasonable, imo.
> > > > > For testing collision rate, a sample user space script and
> > > > > sample mtty is easy and get us collision count too. We
> > > > > shouldn't put that using module option in production kernel.
> > > > > I practically have the code ready to play with; Changing 12
> > > > > to smaller value is easy with module reload.
> > > > >
> > > > > #define MDEV_ALIAS_LEN 12
> > > >
> > > > If it can't be tested with a shipping binary, it probably won't
> > > > be tested. Thanks,
> > > It is not the role of mdev core to expose collision
> > > efficiency/deficiency of the sha1. It can be tested outside before
> > > mdev choose to use it.
> >
> > The testing I'm considering is the user and kernel response to a
> > collision.
> > > I am saying we should test with 12 characters with 10,000 or more
> > > devices and see how collision occurs. Even if collision occurs,
> > > mdev returns EEXIST status indicating user to pick a different
> > > UUID for those rare conditions.
> >
> > The only way we're going to see collision with a 12-char sha1 is if
> > we burn the CPU cycles to find uuids that collide in that space.
> > 10,000 devices is not remotely enough to generate a collision in
> > that address space. That puts a prerequisite in place that in
> > order to test collision, someone needs to know certain magic
> > inputs. OTOH, if we could use a shorter abbreviation, collisions
> > are trivial to test experimentally. Thanks,
> Yes, and therefore a sane user who wants to create more mdevs,
> wouldn't intentionally stress it to see failures.
I don't understand this logic. I'm simply asking that we have a way to
test the collision behavior without changing the binary. The path
we're driving towards seems to be making this easier and easier. If
the vendor can request an alias of a specific length, then a sample
driver with a module option to set the desired alias length to 1-char
makes it trivially easy to induce a collision. It doesn't even need to
be exposed in a real driver. Besides, when do we ever get to design
interfaces that only worry about sane users??? Thanks,
Alex
^ permalink raw reply
* Re: [PATCH 12/16] arm64: prefer __section from compiler_attributes.h
From: Miguel Ojeda @ 2019-08-23 19:35 UTC (permalink / raw)
To: Nick Desaulniers
Cc: Will Deacon, Andrew Morton, Sedat Dilek, Josh Poimboeuf,
Yonghong Song, clang-built-linux, Catalin Marinas,
Alexei Starovoitov, Daniel Borkmann, Martin KaFai Lau, Song Liu,
Andrey Konovalov, Greg Kroah-Hartman, Enrico Weigelt,
Suzuki K Poulose, Thomas Gleixner, Masayoshi Mizuma,
Shaokun Zhang, Alexios Zavras, Allison Randal, Linux ARM,
linux-kernel, Network Development, bpf
In-Reply-To: <CANiq72nUyT-q3A9mTrYzPZ+J9Ya7Lns5MyTK7W7-7yXgFWc2xA@mail.gmail.com>
On Thu, Aug 15, 2019 at 11:12 AM Miguel Ojeda
<miguel.ojeda.sandonis@gmail.com> wrote:
>
> Btw, I guess that is the Oops you were mentioning in the cover letter?
Pinging about this...
Cheers,
Miguel
^ permalink raw reply
* Re: [PATCH 3/3] net: qca: update MODULE_AUTHOR() email address
From: Stefan Wahren @ 2019-08-23 19:16 UTC (permalink / raw)
To: Jean Delvare, Guenter Roeck, David S. Miller, Srinivas Kandagatla,
Shawn Guo, Sascha Hauer, Pengutronix Kernel Team, Fabio Estevam,
NXP Linux Team
Cc: linux-hwmon, netdev, linux-kernel, linux-arm-kernel
In-Reply-To: <1565720249-6549-3-git-send-email-wahrenst@gmx.net>
Am 13.08.19 um 20:17 schrieb Stefan Wahren:
> I2SE has been acquired by in-tech. So the email address listed in
> MODULE_AUTHOR() will be disabled in the near future. I only have access
> to QCA7000 boards at in-tech, so use my new company address.
>
> Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Gentle ping ...
^ permalink raw reply
* [PATCH v4 net-next 7/7] ip6tlvs: Validation of TX Destination and Hop-by-Hop options
From: Tom Herbert @ 2019-08-23 19:14 UTC (permalink / raw)
To: davem, netdev; +Cc: Tom Herbert, Tom Herbert
In-Reply-To: <1566587643-16594-1-git-send-email-tom@herbertland.com>
From: Tom Herbert <tom@quantonium.net>
Validate Destination and Hop-by-Hop options. This uses the information
in the TLV parameters table to validate various aspects of both
individual TLVs as well as a list of TLVs in an extension header.
There are two levels of validation that can be performed: simple checks
and deep checks. Simple checks validate only the most basic properties
such as that the TLV list fits into the EH. Deep checks do a fine
grained validation that includes perferred ordering, length limits,
and length alignment.
With proper permissions set in the TLV parameter table, this patch
allows non-privileged users to send TLVs. Given that TLVs are open
ended and potentially a source of DOS attack, deep checks are
performed to limit the format that a non-privileged user can send.
If deep checks are enabled, a canonical format for sending TLVs is
enforced (in adherence with the robustness principle). A TLV must
be well ordered with respect to the preferred order for the TLV.
Each TLV must be aligned as described in the parameter table. Minimal
padding (one padding TLV) is used to align TLVs. The length of the
extension header as well as the count of non-padding TLVs is checked
against max_*_opts_len and max_*_opts_cnt. For individual TLVs, length
limits and length alignment is checked.
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
include/net/ipeh.h | 22 +++
net/ipv6/datagram.c | 51 +++++--
net/ipv6/exthdrs_common.c | 382 ++++++++++++++++++++++++++++++++++++++++++++++
net/ipv6/ipv6_sockglue.c | 39 ++---
4 files changed, 455 insertions(+), 39 deletions(-)
diff --git a/include/net/ipeh.h b/include/net/ipeh.h
index 8474a43..e58a0f4 100644
--- a/include/net/ipeh.h
+++ b/include/net/ipeh.h
@@ -157,6 +157,28 @@ struct ipv6_txoptions *ipeh_renew_options(struct sock *sk,
struct ipv6_txoptions *ipeh_fixup_options(struct ipv6_txoptions *opt_space,
struct ipv6_txoptions *opt);
+int ipeh_opt_validate_tlvs(struct net *net,
+ struct tlv_param_table *tlv_param_table,
+ struct ipv6_opt_hdr *opt,
+ unsigned int optname, bool admin,
+ unsigned int max_len, unsigned int max_cnt);
+int ipeh_opt_validate_single_tlv(struct net *net,
+ struct tlv_param_table *tlv_param_table,
+ unsigned int optname, const __u8 *tlv,
+ size_t len, bool deleting, bool admin);
+int ipeh_opt_check_perm(struct net *net,
+ struct tlv_param_table *tlv_param_table,
+ struct ipv6_txoptions *txopt, int optname, bool admin);
+
+struct ipv6_txoptions *ipeh_txopt_from_opt(struct sock *sk,
+ struct tlv_param_table
+ *tlv_param_table,
+ struct ipv6_txoptions *opt,
+ int optname, char __user *optval,
+ unsigned int optlen,
+ unsigned int max_len,
+ unsigned int max_cnt);
+
/* Generic extension header TLV parser */
enum ipeh_parse_errors {
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 9ab897d..4b87773 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -837,7 +837,10 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
break;
case IPV6_2292HOPOPTS:
- case IPV6_HOPOPTS:
+ case IPV6_HOPOPTS: {
+ int max_len = net->ipv6.sysctl.max_hbh_opts_len;
+ int max_cnt = net->ipv6.sysctl.max_hbh_opts_cnt;
+
if (opt->hopopt || cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_opt_hdr))) {
err = -EINVAL;
goto exit_f;
@@ -849,15 +852,24 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
err = -EINVAL;
goto exit_f;
}
- if (!ns_capable(net->user_ns, CAP_NET_RAW)) {
- err = -EPERM;
+
+ err = ipeh_opt_validate_tlvs(net, &ipv6_tlv_param_table,
+ hdr, IPV6_HOPOPTS,
+ ns_capable(net->user_ns,
+ CAP_NET_RAW),
+ max_len, max_cnt);
+ if (err < 0)
goto exit_f;
- }
+
opt->opt_nflen += len;
opt->hopopt = hdr;
break;
+ }
+
+ case IPV6_2292DSTOPTS: {
+ int max_len = net->ipv6.sysctl.max_dst_opts_len;
+ int max_cnt = net->ipv6.sysctl.max_dst_opts_cnt;
- case IPV6_2292DSTOPTS:
if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_opt_hdr))) {
err = -EINVAL;
goto exit_f;
@@ -869,10 +881,14 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
err = -EINVAL;
goto exit_f;
}
- if (!ns_capable(net->user_ns, CAP_NET_RAW)) {
- err = -EPERM;
+ err = ipeh_opt_validate_tlvs(net, &ipv6_tlv_param_table,
+ hdr, IPV6_DSTOPTS,
+ ns_capable(net->user_ns,
+ CAP_NET_RAW),
+ max_len, max_cnt);
+ if (err < 0)
goto exit_f;
- }
+
if (opt->dst1opt) {
err = -EINVAL;
goto exit_f;
@@ -880,9 +896,13 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
opt->opt_flen += len;
opt->dst1opt = hdr;
break;
+ }
case IPV6_DSTOPTS:
- case IPV6_RTHDRDSTOPTS:
+ case IPV6_RTHDRDSTOPTS: {
+ int max_len = net->ipv6.sysctl.max_dst_opts_len;
+ int max_cnt = net->ipv6.sysctl.max_dst_opts_cnt;
+
if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_opt_hdr))) {
err = -EINVAL;
goto exit_f;
@@ -894,10 +914,15 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
err = -EINVAL;
goto exit_f;
}
- if (!ns_capable(net->user_ns, CAP_NET_RAW)) {
- err = -EPERM;
+
+ err = ipeh_opt_validate_tlvs(net, &ipv6_tlv_param_table,
+ hdr, IPV6_DSTOPTS,
+ ns_capable(net->user_ns,
+ CAP_NET_RAW),
+ max_len, max_cnt);
+ if (err < 0)
goto exit_f;
- }
+
if (cmsg->cmsg_type == IPV6_DSTOPTS) {
opt->opt_flen += len;
opt->dst1opt = hdr;
@@ -906,7 +931,7 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
opt->dst0opt = hdr;
}
break;
-
+ }
case IPV6_2292RTHDR:
case IPV6_RTHDR:
if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_rt_hdr))) {
diff --git a/net/ipv6/exthdrs_common.c b/net/ipv6/exthdrs_common.c
index b44c6fd..5df55bd 100644
--- a/net/ipv6/exthdrs_common.c
+++ b/net/ipv6/exthdrs_common.c
@@ -262,6 +262,318 @@ bool ipeh_parse_tlv(unsigned int class,
}
EXPORT_SYMBOL(ipeh_parse_tlv);
+/* TLV validation functions */
+
+/* Validate a single non-padding TLV */
+static int __ipeh_opt_validate_single_tlv(struct net *net, const __u8 *tlv,
+ struct tlv_proc *tproc,
+ unsigned int class, bool *deep_check,
+ bool deleting, bool admin)
+{
+ struct tlv_tx_params *tptx = &tproc->params.t;
+
+ if (tlv[0] < 2) /* Must be non-padding */
+ return -EINVAL;
+
+ /* Check permissions */
+ switch (admin ? tptx->admin_perm : tptx->user_perm) {
+ case IPEH_TLV_PERM_NO_CHECK:
+ /* Allowed with no deep checks */
+ *deep_check = false;
+ return 0;
+ case IPEH_TLV_PERM_WITH_CHECK:
+ /* Allowed with deep checks */
+ *deep_check = true;
+ break;
+ default:
+ /* No permission */
+ return -EPERM;
+ }
+
+ /* Perform deep checks on the TLV */
+
+ /* Check class */
+ if ((tptx->class & class) != class)
+ return -EINVAL;
+
+ /* Don't bother checking lengths when deleting, the TLV is only
+ * needed here for lookup
+ */
+ if (deleting) {
+ /* Don't bother with deep checks when deleting */
+ *deep_check = false;
+ } else {
+ /* Check length */
+ if (tlv[1] < tptx->min_data_len || tlv[1] > tptx->max_data_len)
+ return -EINVAL;
+
+ /* Check length alignment */
+ if ((tlv[1] % (tptx->data_len_mult + 1)) != tptx->data_len_off)
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static unsigned int optname_to_tlv_class(int optname)
+{
+ switch (optname) {
+ case IPV6_HOPOPTS:
+ return IPEH_TLV_CLASS_FLAG_HOPOPT;
+ case IPV6_RTHDRDSTOPTS:
+ return IPEH_TLV_CLASS_FLAG_RTRDSTOPT;
+ case IPV6_DSTOPTS:
+ return IPEH_TLV_CLASS_FLAG_DSTOPT;
+ default:
+ return -1U;
+ }
+}
+
+static int __ipeh_opt_validate_tlvs(struct net *net,
+ struct tlv_param_table *tlv_param_table,
+ struct ipv6_opt_hdr *opt,
+ unsigned int optname, bool deleting,
+ bool admin, unsigned int max_len,
+ unsigned int max_cnt)
+{
+ bool deep_check = !admin, did_deep_check = false;
+ unsigned int opt_len, tlv_len, offset;
+ unsigned int padding = 0, numpad = 0;
+ unsigned short prev_tlv_order = 0;
+ unsigned int class, cnt = 0;
+ struct tlv_tx_params *tptx;
+ int retc, ret = -EINVAL;
+ __u8 *tlv = (__u8 *)opt;
+ struct tlv_proc *tproc;
+
+ opt_len = ipv6_optlen(opt);
+ offset = sizeof(*opt);
+
+ class = optname_to_tlv_class(optname);
+
+ rcu_read_lock();
+
+ while (offset < opt_len) {
+ switch (tlv[offset]) {
+ case IPV6_TLV_PAD1:
+ tlv_len = 1;
+ padding++;
+ numpad++;
+ break;
+ case IPV6_TLV_PADN:
+ if (offset + 1 >= opt_len)
+ goto out;
+
+ tlv_len = tlv[offset + 1] + 2;
+
+ if (offset + tlv_len > opt_len)
+ goto out;
+
+ padding += tlv_len;
+ numpad++;
+ break;
+ default:
+ if (offset + 1 >= opt_len)
+ goto out;
+
+ tlv_len = tlv[offset + 1] + 2;
+
+ if (offset + tlv_len > opt_len)
+ goto out;
+
+ tproc = ipeh_tlv_get_proc(tlv_param_table,
+ &tlv[offset]);
+ tptx = &tproc->params.t;
+
+ retc = __ipeh_opt_validate_single_tlv(net, &tlv[offset],
+ tproc, class,
+ &deep_check,
+ deleting, admin);
+ if (retc < 0) {
+ ret = retc;
+ goto out;
+ }
+
+ if (deep_check) {
+ /* Check for too many options */
+ if (++cnt > max_cnt) {
+ ret = -E2BIG;
+ goto out;
+ }
+
+ /* Check order */
+ if (tptx->preferred_order < prev_tlv_order)
+ goto out;
+
+ /* Check alignment */
+ if ((offset % (tptx->align_mult + 1)) !=
+ tptx->align_off)
+ goto out;
+
+ /* Check for right amount of padding */
+ if (numpad > 1 || padding > tptx->align_mult)
+ goto out;
+
+ prev_tlv_order = tptx->preferred_order;
+
+ did_deep_check = true;
+ }
+ padding = 0;
+ numpad = 0;
+ }
+ offset += tlv_len;
+ }
+
+ /* Check trailing padding. Note this covers the case option list
+ * only contains padding.
+ */
+ if (deep_check && (numpad > 1 || padding > 7))
+ goto out;
+
+ /* If we did at least one deep check apply length limit */
+ if (did_deep_check && opt_len > max_len) {
+ ret = -EMSGSIZE;
+ goto out;
+ }
+
+ /* All good */
+ ret = 0;
+out:
+ rcu_read_unlock();
+
+ return ret;
+}
+
+/**
+ * ipeh_opt_validate_tlvs - Validate TLVs.
+ * @net: Current net
+ * @tlv_param_table: TLV parameter table
+ * @opt: The option header
+ * @optname: IPV6_HOPOPTS, IPV6_RTHDRDSTOPTS, or IPV6_DSTOPTS
+ * @admin: Set for privileged user
+ * @max_len: Maximum length for TLV
+ * @max_cnt: Maximum number of non-padding TLVs
+ *
+ * Description:
+ * Walks the TLVs in a list to verify that the TLV lengths and other
+ * parameters are in bounds for a Destination or Hop-by-Hop option.
+ * Return -EINVAL is there is a problem, zero otherwise.
+ */
+int ipeh_opt_validate_tlvs(struct net *net,
+ struct tlv_param_table *tlv_param_table,
+ struct ipv6_opt_hdr *opt, unsigned int optname,
+ bool admin, unsigned int max_len,
+ unsigned int max_cnt)
+{
+ return __ipeh_opt_validate_tlvs(net, tlv_param_table, opt, optname,
+ false, admin, max_len, max_cnt);
+}
+EXPORT_SYMBOL(ipeh_opt_validate_tlvs);
+
+/**
+ * ipeh_opt_validate_single_tlv - Check that a single TLV is valid.
+ * @net: Current net
+ * @tlv_param_table: TLV parameter table
+ * @optname: IPV6_HOPOPTS, IPV6_RTHDRDSTOPTS, or IPV6_DSTOPTS
+ * @tlv: The TLV as array of bytes
+ * @len: Length of buffer holding TLV
+ * @deleting: TLV is being deleted
+ * @admin: Set for privileged user
+ *
+ * Description:
+ * Validates a single TLV. The TLV must be non-padding type. The length
+ * of the TLV (as determined by the second byte that gives length of the
+ * option data) must match @len.
+ */
+int ipeh_opt_validate_single_tlv(struct net *net,
+ struct tlv_param_table *tlv_param_table,
+ unsigned int optname, const __u8 *tlv,
+ size_t len, bool deleting, bool admin)
+{
+ struct tlv_proc *tproc;
+ unsigned int class;
+ bool deep_check;
+ int ret = 0;
+
+ class = optname_to_tlv_class(optname);
+
+ if (tlv[0] < 2)
+ return -EINVAL;
+
+ if (len < 2)
+ return -EINVAL;
+
+ if (tlv[1] + 2 != len)
+ return -EINVAL;
+
+ rcu_read_lock();
+
+ tproc = ipeh_tlv_get_proc(tlv_param_table, tlv);
+
+ ret = __ipeh_opt_validate_single_tlv(net, tlv, tproc, class,
+ &deep_check, deleting, admin);
+
+ rcu_read_unlock();
+
+ return ret;
+}
+EXPORT_SYMBOL(ipeh_opt_validate_single_tlv);
+
+/**
+ * ipeh_opt_check_perm - Check that current capabilities allows modifying
+ * txopts.
+ * @net: Current net
+ * @tlv_param_table: TLV parameter table
+ * @txopts: TX options from the socket
+ * @optname: IPV6_HOPOPTS, IPV6_RTHDRDSTOPTS, or IPV6_DSTOPTS
+ * @admin: Set for privileged user
+ *
+ * Description:
+ *
+ * Checks whether the permissions of TLV that are set on a socket permit
+ * modificationr.
+ *
+ */
+int ipeh_opt_check_perm(struct net *net,
+ struct tlv_param_table *tlv_param_table,
+ struct ipv6_txoptions *txopt, int optname, bool admin)
+{
+ struct ipv6_opt_hdr *opt;
+ int retv = -EPERM;
+
+ if (!txopt)
+ return 0;
+
+ switch (optname) {
+ case IPV6_HOPOPTS:
+ opt = txopt->hopopt;
+ break;
+ case IPV6_RTHDRDSTOPTS:
+ opt = txopt->dst0opt;
+ break;
+ case IPV6_DSTOPTS:
+ opt = txopt->dst1opt;
+ break;
+ default:
+ goto out;
+ }
+
+ if (!opt) {
+ retv = 0;
+ goto out;
+ }
+
+ /* Just call the validate function on the options as being
+ * deleted.
+ */
+ retv = __ipeh_opt_validate_tlvs(net, tlv_param_table, opt, optname,
+ true, admin, -1U, -1U);
+
+out:
+ return retv;
+}
+EXPORT_SYMBOL(ipeh_opt_check_perm);
+
/* TLV parameter table functions and structures */
/* Default (unset) values for TLV parameters */
@@ -454,6 +766,76 @@ int __ipeh_tlv_unset(struct tlv_param_table *tlv_param_table,
}
EXPORT_SYMBOL(__ipeh_tlv_unset);
+/* Utility function tp create TX options from a setsockopt that is setting
+ * options on a socket.
+ */
+struct ipv6_txoptions *ipeh_txopt_from_opt(struct sock *sk,
+ struct tlv_param_table
+ *tlv_param_table,
+ struct ipv6_txoptions *opt,
+ int optname, char __user *optval,
+ unsigned int optlen,
+ unsigned int max_len,
+ unsigned int max_cnt)
+{
+ struct ipv6_opt_hdr *new = NULL;
+ struct net *net = sock_net(sk);
+ int retv;
+
+ /* remove any sticky options header with a zero option
+ * length, per RFC3542.
+ */
+ if (optlen == 0) {
+ optval = NULL;
+ } else if (!optval) {
+ return ERR_PTR(-EINVAL);
+ } else if (optlen < sizeof(struct ipv6_opt_hdr) ||
+ optlen & 0x7 || optlen > 8 * 255) {
+ return ERR_PTR(-EINVAL);
+ } else {
+ new = memdup_user(optval, optlen);
+ if (IS_ERR(new))
+ return (struct ipv6_txoptions *)new;
+ if (unlikely(ipv6_optlen(new) > optlen)) {
+ kfree(new);
+ return ERR_PTR(-EINVAL);
+ }
+ }
+
+ if (optname != IPV6_RTHDR) {
+ bool cap = ns_capable(net->user_ns, CAP_NET_RAW);
+
+ /* First check if we have permission to delete
+ * the existing options on the socket.
+ */
+ retv = ipeh_opt_check_perm(net, tlv_param_table,
+ opt, optname, cap);
+ if (retv < 0) {
+ kfree(new);
+ return ERR_PTR(retv);
+ }
+
+ /* Check permissions and other validations on new
+ * TLVs
+ */
+ if (new) {
+ retv = ipeh_opt_validate_tlvs(net, tlv_param_table,
+ new, optname, cap,
+ max_len, max_cnt);
+ if (retv < 0) {
+ kfree(new);
+ return ERR_PTR(retv);
+ }
+ }
+ }
+
+ opt = ipeh_renew_options(sk, opt, optname, new);
+ kfree(new);
+
+ return opt;
+}
+EXPORT_SYMBOL(ipeh_txopt_from_opt);
+
const struct nla_policy ipeh_tlv_nl_policy[IPEH_TLV_ATTR_MAX + 1] = {
[IPEH_TLV_ATTR_TYPE] = { .type = NLA_U8, },
[IPEH_TLV_ATTR_ORDER] = { .type = NLA_U16, },
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 8755ecc..b8e007ca 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -395,40 +395,27 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
case IPV6_RTHDR:
case IPV6_DSTOPTS:
{
+ unsigned int max_len = -1U, max_cnt = -1U;
struct ipv6_txoptions *opt;
- struct ipv6_opt_hdr *new = NULL;
- /* hop-by-hop / destination options are privileged option */
- retv = -EPERM;
- if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
+ switch (optname) {
+ case IPV6_HOPOPTS:
+ max_len = net->ipv6.sysctl.max_hbh_opts_len;
+ max_cnt = net->ipv6.sysctl.max_hbh_opts_cnt;
break;
-
- /* remove any sticky options header with a zero option
- * length, per RFC3542.
- */
- if (optlen == 0)
- optval = NULL;
- else if (!optval)
- goto e_inval;
- else if (optlen < sizeof(struct ipv6_opt_hdr) ||
- optlen & 0x7 || optlen > 8 * 255)
- goto e_inval;
- else {
- new = memdup_user(optval, optlen);
- if (IS_ERR(new)) {
- retv = PTR_ERR(new);
+ case IPV6_RTHDRDSTOPTS:
+ case IPV6_DSTOPTS:
+ max_len = net->ipv6.sysctl.max_dst_opts_len;
+ max_cnt = net->ipv6.sysctl.max_dst_opts_cnt;
break;
- }
- if (unlikely(ipv6_optlen(new) > optlen)) {
- kfree(new);
- goto e_inval;
- }
}
opt = rcu_dereference_protected(np->opt,
lockdep_sock_is_held(sk));
- opt = ipeh_renew_options(sk, opt, optname, new);
- kfree(new);
+ opt = ipeh_txopt_from_opt(sk, &ipv6_tlv_param_table, opt,
+ optname, optval, optlen, max_len,
+ max_cnt);
+
if (IS_ERR(opt)) {
retv = PTR_ERR(opt);
break;
--
2.7.4
^ permalink raw reply related
* [PATCH v4 net-next 6/7] ip6tlvs: Add netlink interface
From: Tom Herbert @ 2019-08-23 19:14 UTC (permalink / raw)
To: davem, netdev; +Cc: Tom Herbert, Tom Herbert
In-Reply-To: <1566587643-16594-1-git-send-email-tom@herbertland.com>
From: Tom Herbert <tom@quantonium.net>
Add a netlink interface to manage the TX TLV parameters. Managed
parameters include those for validating and sending TLVs being sent
such as alignment, TLV ordering, length limits, etc.
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
include/net/ipeh.h | 16 +++
include/net/ipv6.h | 1 +
include/uapi/linux/in6.h | 6 ++
include/uapi/linux/ipeh.h | 29 ++++++
net/ipv6/exthdrs_common.c | 238 +++++++++++++++++++++++++++++++++++++++++++++
net/ipv6/exthdrs_options.c | 81 ++++++++++++++-
6 files changed, 369 insertions(+), 2 deletions(-)
diff --git a/include/net/ipeh.h b/include/net/ipeh.h
index de6d9d0..8474a43 100644
--- a/include/net/ipeh.h
+++ b/include/net/ipeh.h
@@ -3,6 +3,7 @@
#define _NET_IPEH_H
#include <linux/skbuff.h>
+#include <net/genetlink.h>
/*
* Parsing tlv encoded headers.
@@ -106,6 +107,21 @@ static inline int ipeh_tlv_unset_proc(struct tlv_param_table *tlv_param_table,
return __ipeh_tlv_unset(tlv_param_table, type, false);
}
+extern const struct nla_policy ipeh_tlv_nl_policy[];
+
+int ipeh_tlv_nl_cmd_set(struct tlv_param_table *tlv_param_table,
+ struct genl_family *tlv_nl_family,
+ struct sk_buff *skb, struct genl_info *info);
+int ipeh_tlv_nl_cmd_unset(struct tlv_param_table *tlv_param_table,
+ struct genl_family *tlv_nl_family,
+ struct sk_buff *skb, struct genl_info *info);
+int ipeh_tlv_nl_cmd_get(struct tlv_param_table *tlv_param_table,
+ struct genl_family *tlv_nl_family,
+ struct sk_buff *skb, struct genl_info *info);
+int ipeh_tlv_nl_dump(struct tlv_param_table *tlv_param_table,
+ struct genl_family *tlv_nl_family,
+ struct sk_buff *skb, struct netlink_callback *cb);
+
/* ipeh_tlv_get_proc_by_type assumes rcu_read_lock is held */
static inline struct tlv_proc *ipeh_tlv_get_proc_by_type(
struct tlv_param_table *tlv_param_table, unsigned char type)
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 07bafad..51517a1 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -14,6 +14,7 @@
#include <linux/jhash.h>
#include <linux/refcount.h>
#include <linux/jump_label_ratelimit.h>
+#include <net/genetlink.h>
#include <net/if_inet6.h>
#include <net/ndisc.h>
#include <net/flow.h>
diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h
index 9f2273a..d5fe3d9 100644
--- a/include/uapi/linux/in6.h
+++ b/include/uapi/linux/in6.h
@@ -297,4 +297,10 @@ struct in6_flowlabel_req {
* ...
* MRT6_MAX
*/
+
+ /* NETLINK_GENERIC related info for IPv6 TLVs */
+
+#define IPV6_TLV_GENL_NAME "ipv6-tlv"
+#define IPV6_TLV_GENL_VERSION 0x1
+
#endif /* _UAPI_LINUX_IN6_H */
diff --git a/include/uapi/linux/ipeh.h b/include/uapi/linux/ipeh.h
index dbf0728..bac36a7 100644
--- a/include/uapi/linux/ipeh.h
+++ b/include/uapi/linux/ipeh.h
@@ -21,4 +21,33 @@ enum {
IPEH_TLV_PERM_MAX = IPEH_TLV_PERM_NO_CHECK
};
+/* NETLINK_GENERIC related info for IP TLVs */
+
+enum {
+ IPEH_TLV_ATTR_UNSPEC,
+ IPEH_TLV_ATTR_TYPE, /* u8, > 1 */
+ IPEH_TLV_ATTR_ORDER, /* u16 */
+ IPEH_TLV_ATTR_ADMIN_PERM, /* u8, perm value */
+ IPEH_TLV_ATTR_USER_PERM, /* u8, perm value */
+ IPEH_TLV_ATTR_CLASS, /* u8, 3 bit flags */
+ IPEH_TLV_ATTR_ALIGN_MULT, /* u8, 1 to 16 */
+ IPEH_TLV_ATTR_ALIGN_OFF, /* u8, 0 to 15 */
+ IPEH_TLV_ATTR_MIN_DATA_LEN, /* u8 (option data length) */
+ IPEH_TLV_ATTR_MAX_DATA_LEN, /* u8 (option data length) */
+ IPEH_TLV_ATTR_DATA_LEN_MULT, /* u8, 1 to 16 */
+ IPEH_TLV_ATTR_DATA_LEN_OFF, /* u8, 0 to 15 */
+
+ __IPEH_TLV_ATTR_MAX,
+};
+
+#define IPEH_TLV_ATTR_MAX (__IPEH_TLV_ATTR_MAX - 1)
+
+enum {
+ IPEH_TLV_CMD_SET,
+ IPEH_TLV_CMD_UNSET,
+ IPEH_TLV_CMD_GET,
+
+ __IPEH_TLV_CMD_MAX,
+};
+
#endif /* _UAPI_LINUX_IPEH_H */
diff --git a/net/ipv6/exthdrs_common.c b/net/ipv6/exthdrs_common.c
index 791f6e4..b44c6fd 100644
--- a/net/ipv6/exthdrs_common.c
+++ b/net/ipv6/exthdrs_common.c
@@ -454,6 +454,244 @@ int __ipeh_tlv_unset(struct tlv_param_table *tlv_param_table,
}
EXPORT_SYMBOL(__ipeh_tlv_unset);
+const struct nla_policy ipeh_tlv_nl_policy[IPEH_TLV_ATTR_MAX + 1] = {
+ [IPEH_TLV_ATTR_TYPE] = { .type = NLA_U8, },
+ [IPEH_TLV_ATTR_ORDER] = { .type = NLA_U16, },
+ [IPEH_TLV_ATTR_ADMIN_PERM] = { .type = NLA_U8, },
+ [IPEH_TLV_ATTR_USER_PERM] = { .type = NLA_U8, },
+ [IPEH_TLV_ATTR_CLASS] = { .type = NLA_U8, },
+ [IPEH_TLV_ATTR_ALIGN_MULT] = { .type = NLA_U8, },
+ [IPEH_TLV_ATTR_ALIGN_OFF] = { .type = NLA_U8, },
+ [IPEH_TLV_ATTR_MIN_DATA_LEN] = { .type = NLA_U8, },
+ [IPEH_TLV_ATTR_MAX_DATA_LEN] = { .type = NLA_U8, },
+ [IPEH_TLV_ATTR_DATA_LEN_OFF] = { .type = NLA_U8, },
+ [IPEH_TLV_ATTR_DATA_LEN_MULT] = { .type = NLA_U8, },
+};
+EXPORT_SYMBOL(ipeh_tlv_nl_policy);
+
+int ipeh_tlv_nl_cmd_set(struct tlv_param_table *tlv_param_table,
+ struct genl_family *tlv_nl_family,
+ struct sk_buff *skb, struct genl_info *info)
+{
+ struct tlv_params new_params;
+ struct tlv_proc *tproc;
+ unsigned char type;
+ unsigned int v;
+ int retv = -EINVAL;
+
+ if (!info->attrs[IPEH_TLV_ATTR_TYPE])
+ return -EINVAL;
+
+ type = nla_get_u8(info->attrs[IPEH_TLV_ATTR_TYPE]);
+ if (type < 2)
+ return -EINVAL;
+
+ rcu_read_lock();
+
+ /* Base new parameters on existing ones */
+ tproc = ipeh_tlv_get_proc_by_type(tlv_param_table, type);
+ new_params = tproc->params;
+
+ if (info->attrs[IPEH_TLV_ATTR_ORDER]) {
+ v = nla_get_u16(info->attrs[IPEH_TLV_ATTR_ORDER]);
+ new_params.t.preferred_order = v;
+ }
+
+ if (info->attrs[IPEH_TLV_ATTR_ADMIN_PERM]) {
+ v = nla_get_u8(info->attrs[IPEH_TLV_ATTR_ADMIN_PERM]);
+ if (v > IPEH_TLV_PERM_MAX)
+ goto out;
+ new_params.t.admin_perm = v;
+ }
+
+ if (info->attrs[IPEH_TLV_ATTR_USER_PERM]) {
+ v = nla_get_u8(info->attrs[IPEH_TLV_ATTR_USER_PERM]);
+ if (v > IPEH_TLV_PERM_MAX)
+ goto out;
+ new_params.t.user_perm = v;
+ }
+
+ if (info->attrs[IPEH_TLV_ATTR_CLASS]) {
+ v = nla_get_u8(info->attrs[IPEH_TLV_ATTR_CLASS]);
+ if (!v || (v & ~IPEH_TLV_CLASS_FLAG_MASK))
+ goto out;
+ new_params.t.class = v;
+ }
+
+ if (info->attrs[IPEH_TLV_ATTR_ALIGN_MULT]) {
+ v = nla_get_u8(info->attrs[IPEH_TLV_ATTR_ALIGN_MULT]);
+ if (v > 16 || v < 1)
+ goto out;
+ new_params.t.align_mult = v - 1;
+ }
+
+ if (info->attrs[IPEH_TLV_ATTR_ALIGN_OFF]) {
+ v = nla_get_u8(info->attrs[IPEH_TLV_ATTR_ALIGN_OFF]);
+ if (v > 15)
+ goto out;
+ new_params.t.align_off = v;
+ }
+
+ if (info->attrs[IPEH_TLV_ATTR_MAX_DATA_LEN])
+ new_params.t.max_data_len =
+ nla_get_u8(info->attrs[IPEH_TLV_ATTR_MAX_DATA_LEN]);
+
+ if (info->attrs[IPEH_TLV_ATTR_MIN_DATA_LEN])
+ new_params.t.min_data_len =
+ nla_get_u8(info->attrs[IPEH_TLV_ATTR_MIN_DATA_LEN]);
+
+ if (info->attrs[IPEH_TLV_ATTR_DATA_LEN_MULT]) {
+ v = nla_get_u8(info->attrs[IPEH_TLV_ATTR_DATA_LEN_MULT]);
+ if (v > 16 || v < 1)
+ goto out;
+ new_params.t.data_len_mult = v - 1;
+ }
+
+ if (info->attrs[IPEH_TLV_ATTR_DATA_LEN_OFF]) {
+ v = nla_get_u8(info->attrs[IPEH_TLV_ATTR_DATA_LEN_OFF]);
+ if (v > 15)
+ goto out;
+ new_params.t.data_len_off = v;
+ }
+
+ retv = ipeh_tlv_set_params(tlv_param_table, type, &new_params);
+
+out:
+ rcu_read_unlock();
+ return retv;
+}
+EXPORT_SYMBOL(ipeh_tlv_nl_cmd_set);
+
+int ipeh_tlv_nl_cmd_unset(struct tlv_param_table *tlv_param_table,
+ struct genl_family *tlv_nl_family,
+ struct sk_buff *skb, struct genl_info *info)
+{
+ unsigned char type;
+
+ if (!info->attrs[IPEH_TLV_ATTR_TYPE])
+ return -EINVAL;
+
+ type = nla_get_u8(info->attrs[IPEH_TLV_ATTR_TYPE]);
+ if (type < 2)
+ return -EINVAL;
+
+ return ipeh_tlv_unset_params(tlv_param_table, type);
+}
+EXPORT_SYMBOL(ipeh_tlv_nl_cmd_unset);
+
+static int tlv_fill_info(struct tlv_proc *tproc, unsigned char type,
+ struct sk_buff *msg, bool admin)
+{
+ struct tlv_params *tp = &tproc->params;
+ int ret = 0;
+
+ if (nla_put_u8(msg, IPEH_TLV_ATTR_TYPE, type) ||
+ nla_put_u16(msg, IPEH_TLV_ATTR_ORDER, tp->t.preferred_order) ||
+ nla_put_u8(msg, IPEH_TLV_ATTR_USER_PERM, tp->t.user_perm) ||
+ (admin && nla_put_u8(msg, IPEH_TLV_ATTR_ADMIN_PERM,
+ tp->t.admin_perm)) ||
+ nla_put_u8(msg, IPEH_TLV_ATTR_CLASS, tp->t.class) ||
+ nla_put_u8(msg, IPEH_TLV_ATTR_ALIGN_MULT, tp->t.align_mult + 1) ||
+ nla_put_u8(msg, IPEH_TLV_ATTR_ALIGN_OFF, tp->t.align_off) ||
+ nla_put_u8(msg, IPEH_TLV_ATTR_MIN_DATA_LEN, tp->t.min_data_len) ||
+ nla_put_u8(msg, IPEH_TLV_ATTR_MAX_DATA_LEN, tp->t.max_data_len) ||
+ nla_put_u8(msg, IPEH_TLV_ATTR_DATA_LEN_MULT,
+ tp->t.data_len_mult + 1) ||
+ nla_put_u8(msg, IPEH_TLV_ATTR_DATA_LEN_OFF, tp->t.data_len_off))
+ ret = -1;
+
+ return ret;
+}
+
+static int tlv_dump_info(struct tlv_proc *tproc, unsigned char type,
+ struct genl_family *tlv_nl_family, u32 portid,
+ u32 seq, u32 flags, struct sk_buff *skb, u8 cmd,
+ bool admin)
+{
+ void *hdr;
+
+ hdr = genlmsg_put(skb, portid, seq, tlv_nl_family, flags, cmd);
+ if (!hdr)
+ return -ENOMEM;
+
+ if (tlv_fill_info(tproc, type, skb, admin) < 0) {
+ genlmsg_cancel(skb, hdr);
+ return -EMSGSIZE;
+ }
+
+ genlmsg_end(skb, hdr);
+
+ return 0;
+}
+
+int ipeh_tlv_nl_cmd_get(struct tlv_param_table *tlv_param_table,
+ struct genl_family *tlv_nl_family,
+ struct sk_buff *skb, struct genl_info *info)
+{
+ struct tlv_proc *tproc;
+ struct sk_buff *msg;
+ unsigned char type;
+ int ret;
+
+ if (!info->attrs[IPEH_TLV_ATTR_TYPE])
+ return -EINVAL;
+
+ type = nla_get_u8(info->attrs[IPEH_TLV_ATTR_TYPE]);
+ if (type < 2)
+ return -EINVAL;
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ rcu_read_lock();
+
+ tproc = ipeh_tlv_get_proc_by_type(tlv_param_table, type);
+ ret = tlv_dump_info(tproc, type, tlv_nl_family, info->snd_portid,
+ info->snd_seq, 0, msg, info->genlhdr->cmd,
+ netlink_capable(skb, CAP_NET_ADMIN));
+
+ rcu_read_unlock();
+
+ if (ret < 0) {
+ nlmsg_free(msg);
+ return ret;
+ }
+
+ return genlmsg_reply(msg, info);
+}
+EXPORT_SYMBOL(ipeh_tlv_nl_cmd_get);
+
+int ipeh_tlv_nl_dump(struct tlv_param_table *tlv_param_table,
+ struct genl_family *tlv_nl_family,
+ struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct tlv_proc *tproc;
+ int idx = 0, ret, i;
+
+ rcu_read_lock();
+
+ for (i = 2; i < 256; i++) {
+ if (idx++ < cb->args[0])
+ continue;
+
+ tproc = ipeh_tlv_get_proc_by_type(tlv_param_table, i);
+ ret = tlv_dump_info(tproc, i, tlv_nl_family,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, NLM_F_MULTI,
+ skb, IPEH_TLV_CMD_GET,
+ netlink_capable(cb->skb, CAP_NET_ADMIN));
+ if (ret)
+ break;
+ }
+
+ rcu_read_unlock();
+
+ cb->args[0] = idx;
+ return skb->len;
+}
+EXPORT_SYMBOL(ipeh_tlv_nl_dump);
+
int ipeh_exthdrs_init(struct tlv_param_table *tlv_param_table,
const struct tlv_proc_init *tlv_init_params,
int num_init_params)
diff --git a/net/ipv6/exthdrs_options.c b/net/ipv6/exthdrs_options.c
index 3b50b58..c1889f6 100644
--- a/net/ipv6/exthdrs_options.c
+++ b/net/ipv6/exthdrs_options.c
@@ -6,6 +6,7 @@
#include <linux/socket.h>
#include <linux/types.h>
#include <net/calipso.h>
+#include <net/genetlink.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
#if IS_ENABLED(CONFIG_IPV6_MIP6)
@@ -253,13 +254,89 @@ static const struct tlv_proc_init tlv_ipv6_init_params[] __initconst = {
struct tlv_param_table __rcu ipv6_tlv_param_table;
EXPORT_SYMBOL(ipv6_tlv_param_table);
+static int ipv6_tlv_nl_cmd_set(struct sk_buff *skb, struct genl_info *info);
+static int ipv6_tlv_nl_cmd_unset(struct sk_buff *skb, struct genl_info *info);
+static int ipv6_tlv_nl_cmd_get(struct sk_buff *skb, struct genl_info *info);
+static int ipv6_tlv_nl_dump(struct sk_buff *skb, struct netlink_callback *cb);
+
+static const struct genl_ops ipv6_tlv_nl_ops[] = {
+{
+ .cmd = IPEH_TLV_CMD_SET,
+ .doit = ipv6_tlv_nl_cmd_set,
+ .flags = GENL_ADMIN_PERM,
+},
+{
+ .cmd = IPEH_TLV_CMD_UNSET,
+ .doit = ipv6_tlv_nl_cmd_unset,
+ .flags = GENL_ADMIN_PERM,
+},
+{
+ .cmd = IPEH_TLV_CMD_GET,
+ .doit = ipv6_tlv_nl_cmd_get,
+ .dumpit = ipv6_tlv_nl_dump,
+},
+};
+
+struct genl_family ipv6_tlv_nl_family __ro_after_init = {
+ .hdrsize = 0,
+ .name = IPV6_TLV_GENL_NAME,
+ .version = IPV6_TLV_GENL_VERSION,
+ .maxattr = IPEH_TLV_ATTR_MAX,
+ .policy = ipeh_tlv_nl_policy,
+ .netnsok = true,
+ .parallel_ops = true,
+ .ops = ipv6_tlv_nl_ops,
+ .n_ops = ARRAY_SIZE(ipv6_tlv_nl_ops),
+ .module = THIS_MODULE,
+};
+
+static int ipv6_tlv_nl_cmd_set(struct sk_buff *skb, struct genl_info *info)
+{
+ return ipeh_tlv_nl_cmd_set(&ipv6_tlv_param_table, &ipv6_tlv_nl_family,
+ skb, info);
+}
+
+static int ipv6_tlv_nl_cmd_unset(struct sk_buff *skb, struct genl_info *info)
+{
+ return ipeh_tlv_nl_cmd_unset(&ipv6_tlv_param_table, &ipv6_tlv_nl_family,
+ skb, info);
+}
+
+static int ipv6_tlv_nl_cmd_get(struct sk_buff *skb, struct genl_info *info)
+{
+ return ipeh_tlv_nl_cmd_get(&ipv6_tlv_param_table, &ipv6_tlv_nl_family,
+ skb, info);
+}
+
+static int ipv6_tlv_nl_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ return ipeh_tlv_nl_dump(&ipv6_tlv_param_table, &ipv6_tlv_nl_family,
+ skb, cb);
+}
+
int __init ipv6_exthdrs_options_init(void)
{
- return ipeh_exthdrs_init(&ipv6_tlv_param_table, tlv_ipv6_init_params,
- ARRAY_SIZE(tlv_ipv6_init_params));
+ int err;
+
+ err = genl_register_family(&ipv6_tlv_nl_family);
+ if (err)
+ goto genl_fail;
+
+ ipeh_exthdrs_init(&ipv6_tlv_param_table, tlv_ipv6_init_params,
+ ARRAY_SIZE(tlv_ipv6_init_params));
+ if (err)
+ goto ipv6_fail;
+
+ return 0;
+
+ipv6_fail:
+ genl_unregister_family(&ipv6_tlv_nl_family);
+genl_fail:
+ return err;
}
void ipv6_exthdrs_options_exit(void)
{
ipeh_exthdrs_fini(&ipv6_tlv_param_table);
+ genl_unregister_family(&ipv6_tlv_nl_family);
}
--
2.7.4
^ permalink raw reply related
* [PATCH v4 net-next 5/7] ip6tlvs: Add TX parameters
From: Tom Herbert @ 2019-08-23 19:14 UTC (permalink / raw)
To: davem, netdev; +Cc: Tom Herbert, Tom Herbert
In-Reply-To: <1566587643-16594-1-git-send-email-tom@herbertland.com>
From: Tom Herbert <tom@quantonium.net>
Define a number of transmit parameters for TLV Parameter table
definitions. These will be used for validating TLVs that are set
on a socket.
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
include/net/ipeh.h | 18 ++++++++++++++++
include/uapi/linux/ipeh.h | 8 +++++++
net/ipv6/exthdrs_common.c | 53 +++++++++++++++++++++++++++++++++++++++++++++-
net/ipv6/exthdrs_options.c | 45 +++++++++++++++++++++++++++++++++++++++
4 files changed, 123 insertions(+), 1 deletion(-)
diff --git a/include/net/ipeh.h b/include/net/ipeh.h
index aaa2910..de6d9d0 100644
--- a/include/net/ipeh.h
+++ b/include/net/ipeh.h
@@ -20,6 +20,17 @@ struct tlv_rx_params {
};
struct tlv_tx_params {
+ unsigned char admin_perm : 2;
+ unsigned char user_perm : 2;
+ unsigned char class : 3;
+ unsigned char rsvd : 1;
+ unsigned char align_mult : 4;
+ unsigned char align_off : 4;
+ unsigned char data_len_mult : 4;
+ unsigned char data_len_off : 4;
+ unsigned char min_data_len;
+ unsigned char max_data_len;
+ unsigned short preferred_order;
};
struct tlv_params {
@@ -54,6 +65,13 @@ struct tlv_param_table {
extern struct tlv_param_table ipv6_tlv_param_table;
+/* Preferred TLV ordering for HBH and Dest options (placed by increasing order)
+ */
+#define IPEH_TLV_PREF_ORDER_HAO 10
+#define IPEH_TLV_PREF_ORDER_ROUTERALERT 20
+#define IPEH_TLV_PREF_ORDER_JUMBO 30
+#define IPEH_TLV_PREF_ORDER_CALIPSO 40
+
int __ipeh_tlv_set(struct tlv_param_table *tlv_param_table,
unsigned char type, const struct tlv_params *params,
const struct tlv_ops *ops);
diff --git a/include/uapi/linux/ipeh.h b/include/uapi/linux/ipeh.h
index c4302b7..dbf0728 100644
--- a/include/uapi/linux/ipeh.h
+++ b/include/uapi/linux/ipeh.h
@@ -13,4 +13,12 @@
IPEH_TLV_CLASS_FLAG_RTRDSTOPT | \
IPEH_TLV_CLASS_FLAG_DSTOPT)
+/* TLV permissions values */
+enum {
+ IPEH_TLV_PERM_NONE,
+ IPEH_TLV_PERM_WITH_CHECK,
+ IPEH_TLV_PERM_NO_CHECK,
+ IPEH_TLV_PERM_MAX = IPEH_TLV_PERM_NO_CHECK
+};
+
#endif /* _UAPI_LINUX_IPEH_H */
diff --git a/net/ipv6/exthdrs_common.c b/net/ipv6/exthdrs_common.c
index cc8db9e..791f6e4 100644
--- a/net/ipv6/exthdrs_common.c
+++ b/net/ipv6/exthdrs_common.c
@@ -3,6 +3,7 @@
/* Extension header and TLV library code that is not specific to IPv6. */
#include <linux/export.h>
#include <net/ipv6.h>
+#include <uapi/linux/ipeh.h>
struct ipv6_txoptions *
ipeh_dup_options(struct sock *sk, struct ipv6_txoptions *opt)
@@ -265,6 +266,13 @@ EXPORT_SYMBOL(ipeh_parse_tlv);
/* Default (unset) values for TLV parameters */
static const struct tlv_proc tlv_default_proc = {
+ .params.t = {
+ .admin_perm = IPEH_TLV_PERM_NO_CHECK,
+ .user_perm = IPEH_TLV_PERM_NONE,
+ .align_mult = (4 - 1), /* Default alignment: 4n + 2 */
+ .align_off = 2,
+ .max_data_len = 255,
+ },
};
static DEFINE_MUTEX(tlv_mutex);
@@ -284,16 +292,45 @@ static void tlv_param_table_release(struct rcu_head *rcu)
}
/* mutex held */
+static int check_order(struct tlv_param_table_data *tpt, unsigned char type,
+ unsigned short order)
+{
+ int i;
+
+ if (!order)
+ return -EINVAL;
+
+ for (i = 2; i < 256; i++) {
+ struct tlv_type *ttype = &tpt->types[tpt->entries[i]];
+
+ if (!tpt->entries[i])
+ continue;
+
+ if (order == ttype->proc.params.t.preferred_order &&
+ i != type)
+ return -EALREADY;
+ }
+
+ return 0;
+}
+
+/* mutex held */
static int __tlv_set_one(struct tlv_param_table *tlv_param_table,
unsigned char type, const struct tlv_params *params,
const struct tlv_ops *ops)
{
struct tlv_param_table_data *tpt, *told;
struct tlv_type *ttype;
+ int retv;
told = rcu_dereference_protected(tlv_param_table->data,
lockdep_is_held(&tlv_mutex));
+ /* Check preferred order */
+ retv = check_order(told, type, params->t.preferred_order);
+ if (retv)
+ return retv;
+
/* Create new TLV table. If there is no exsiting entry then we are
* adding a new one to the table, else we're modifying an entry.
*/
@@ -422,7 +459,7 @@ int ipeh_exthdrs_init(struct tlv_param_table *tlv_param_table,
int num_init_params)
{
struct tlv_param_table_data *tpt;
- int pos = 0, i;
+ int pos = 0, i, j;
size_t tsize;
tsize = tlv_param_table_size(num_init_params + 1);
@@ -448,6 +485,20 @@ int ipeh_exthdrs_init(struct tlv_param_table *tlv_param_table,
goto err_inval;
}
+ if (WARN_ON(!tpi->proc.params.t.preferred_order)) {
+ /* Preferred order must be non-zero */
+ goto err_inval;
+ }
+
+ for (j = 0; j < i; j++) {
+ const struct tlv_proc_init *tpix = &tlv_init_params[j];
+
+ if (WARN_ON(tpi->proc.params.t.preferred_order ==
+ tpix->proc.params.t.preferred_order)) {
+ /* Preferred order must be unique */
+ goto err_inval;
+ }
+ }
tpt->types[pos].proc = tpi->proc;
tpt->entries[tpi->type] = pos;
}
diff --git a/net/ipv6/exthdrs_options.c b/net/ipv6/exthdrs_options.c
index d4b373e..3b50b58 100644
--- a/net/ipv6/exthdrs_options.c
+++ b/net/ipv6/exthdrs_options.c
@@ -183,6 +183,17 @@ static const struct tlv_proc_init tlv_ipv6_init_params[] __initconst = {
.proc.ops.func = ipv6_dest_hao,
.proc.params.r.class = IPEH_TLV_CLASS_FLAG_DSTOPT,
+
+ .proc.params.t = {
+ .preferred_order = IPEH_TLV_PREF_ORDER_HAO,
+ .admin_perm = IPEH_TLV_PERM_NO_CHECK,
+ .user_perm = IPEH_TLV_PERM_NONE,
+ .class = IPEH_TLV_CLASS_FLAG_DSTOPT,
+ .align_mult = (8 - 1), /* Align to 8n + 6 */
+ .align_off = 6,
+ .min_data_len = 16,
+ .max_data_len = 16,
+ },
},
#endif
{
@@ -190,18 +201,52 @@ static const struct tlv_proc_init tlv_ipv6_init_params[] __initconst = {
.proc.ops.func = ipv6_hop_ra,
.proc.params.r.class = IPEH_TLV_CLASS_FLAG_HOPOPT,
+
+ .proc.params.t = {
+ .preferred_order = IPEH_TLV_PREF_ORDER_ROUTERALERT,
+ .admin_perm = IPEH_TLV_PERM_NO_CHECK,
+ .user_perm = IPEH_TLV_PERM_NONE,
+ .class = IPEH_TLV_CLASS_FLAG_HOPOPT,
+ .align_mult = (2 - 1), /* Align to 2n */
+ .min_data_len = 2,
+ .max_data_len = 2,
+ },
},
{
.type = IPV6_TLV_JUMBO,
.proc.ops.func = ipv6_hop_jumbo,
.proc.params.r.class = IPEH_TLV_CLASS_FLAG_HOPOPT,
+
+ .proc.params.t = {
+ .preferred_order = IPEH_TLV_PREF_ORDER_JUMBO,
+ .admin_perm = IPEH_TLV_PERM_NO_CHECK,
+ .user_perm = IPEH_TLV_PERM_NONE,
+ .class = IPEH_TLV_CLASS_FLAG_HOPOPT,
+ .align_mult = (4 - 1), /* Align to 4n + 2 */
+ .align_off = 2,
+ .min_data_len = 4,
+ .max_data_len = 4,
+ },
},
{
.type = IPV6_TLV_CALIPSO,
.proc.ops.func = ipv6_hop_calipso,
.proc.params.r.class = IPEH_TLV_CLASS_FLAG_HOPOPT,
+
+ .proc.params.t = {
+ .preferred_order = IPEH_TLV_PREF_ORDER_CALIPSO,
+ .admin_perm = IPEH_TLV_PERM_NO_CHECK,
+ .user_perm = IPEH_TLV_PERM_NONE,
+ .class = IPEH_TLV_CLASS_FLAG_HOPOPT,
+ .align_mult = (4 - 1), /* Align to 4n + 2 */
+ .align_off = 2,
+ .min_data_len = 8,
+ .max_data_len = 252,
+ .data_len_mult = (4 - 1),
+ /* Length is multiple of 4 */
+ },
},
};
--
2.7.4
^ permalink raw reply related
* [PATCH v4 net-next 4/7] ip6tlvs: Registration of TLV handlers and parameters
From: Tom Herbert @ 2019-08-23 19:14 UTC (permalink / raw)
To: davem, netdev; +Cc: Tom Herbert, Tom Herbert
In-Reply-To: <1566587643-16594-1-git-send-email-tom@herbertland.com>
From: Tom Herbert <tom@quantonium.net>
Create a single TLV parameter table that holds meta information for IPv6
Hop-by-Hop and Destination TLVs. The data structure is composed of a 256
element array of u8's (one entry for each TLV type to allow O(1)
lookup). Each entry provides an offset into an array of TLV proc data
structures which follows the array of u8s. The TLV proc data structure
contains parameters and handler functions for receiving and transmitting
TLVs. The zeroth element in the TLV proc array provides default
parameters for TLVs.
A class attribute indicates the type of extension header in which the
TLV may be used (e.g. Hop-by-Hop options, Destination options, or
Destination options before the routing header).
Functions are defined to manipulate entries in the TLV parameter table.
* tlv_{set|unset}_proc set a TLV proc entry (ops and parameters)
* tlv_{set|unset}_params set parameters only
Receive TLV lookup and processing is modified to be a lookup in the TLV
parameter table. An init table containing parameters for TLVs supported
by the kernel is used to initialize the TLV table.
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
include/net/ipeh.h | 107 ++++++++++++++++--
include/net/ipv6.h | 3 +
include/uapi/linux/ipeh.h | 16 +++
net/ipv6/exthdrs.c | 14 ++-
net/ipv6/exthdrs_common.c | 271 +++++++++++++++++++++++++++++++++++++++++----
net/ipv6/exthdrs_options.c | 63 +++++++----
6 files changed, 421 insertions(+), 53 deletions(-)
create mode 100644 include/uapi/linux/ipeh.h
diff --git a/include/net/ipeh.h b/include/net/ipeh.h
index c1aa7b6..aaa2910 100644
--- a/include/net/ipeh.h
+++ b/include/net/ipeh.h
@@ -11,13 +11,105 @@
* and false, if it failed.
* It MUST NOT touch skb->h.
*/
-struct tlvtype_proc {
- int type;
- bool (*func)(struct sk_buff *skb, int offset);
+struct tlv_ops {
+ bool (*func)(unsigned int class, struct sk_buff *skb, int offset);
};
-extern const struct tlvtype_proc tlvprocdestopt_lst[];
-extern const struct tlvtype_proc tlvprochopopt_lst[];
+struct tlv_rx_params {
+ unsigned char class : 4;
+};
+
+struct tlv_tx_params {
+};
+
+struct tlv_params {
+ struct tlv_rx_params r;
+ struct tlv_tx_params t;
+};
+
+struct tlv_proc {
+ struct tlv_ops ops;
+ struct tlv_params params;
+};
+
+struct tlv_type {
+ struct tlv_proc proc;
+};
+
+struct tlv_proc_init {
+ int type;
+ struct tlv_proc proc;
+};
+
+struct tlv_param_table_data {
+ unsigned char entries[256];
+ unsigned char count;
+ struct rcu_head rcu;
+ struct tlv_type types[0];
+};
+
+struct tlv_param_table {
+ struct tlv_param_table_data __rcu *data;
+};
+
+extern struct tlv_param_table ipv6_tlv_param_table;
+
+int __ipeh_tlv_set(struct tlv_param_table *tlv_param_table,
+ unsigned char type, const struct tlv_params *params,
+ const struct tlv_ops *ops);
+
+static inline int ipeh_tlv_set_params(struct tlv_param_table *tlv_param_table,
+ unsigned char type,
+ const struct tlv_params *params)
+{
+ return __ipeh_tlv_set(tlv_param_table, type, params, NULL);
+}
+
+static inline int ipeh_tlv_set_proc(struct tlv_param_table *tlv_param_table,
+ unsigned char type,
+ const struct tlv_proc *proc)
+{
+ return __ipeh_tlv_set(tlv_param_table, type,
+ &proc->params, &proc->ops);
+}
+
+int __ipeh_tlv_unset(struct tlv_param_table *tlv_param_table,
+ unsigned char type, bool params_only);
+
+static inline int ipeh_tlv_unset_params(struct tlv_param_table *tlv_param_table,
+ unsigned char type)
+{
+ return __ipeh_tlv_unset(tlv_param_table, type, true);
+}
+
+static inline int ipeh_tlv_unset_proc(struct tlv_param_table *tlv_param_table,
+ unsigned char type)
+{
+ return __ipeh_tlv_unset(tlv_param_table, type, false);
+}
+
+/* ipeh_tlv_get_proc_by_type assumes rcu_read_lock is held */
+static inline struct tlv_proc *ipeh_tlv_get_proc_by_type(
+ struct tlv_param_table *tlv_param_table, unsigned char type)
+{
+ struct tlv_param_table_data *tpt =
+ rcu_dereference(tlv_param_table->data);
+
+ return &tpt->types[tpt->entries[type]].proc;
+}
+
+/* ipeh_tlv_get_proc assumes rcu_read_lock is held */
+static inline struct tlv_proc *ipeh_tlv_get_proc(
+ struct tlv_param_table *tlv_param_table,
+ const __u8 *tlv)
+{
+ return ipeh_tlv_get_proc_by_type(tlv_param_table, tlv[0]);
+}
+
+int ipeh_exthdrs_init(struct tlv_param_table *tlv_param_table,
+ const struct tlv_proc_init *init_params,
+ int num_init_params);
+void ipeh_exthdrs_fini(struct tlv_param_table *tlv_param_table);
struct ipv6_txoptions;
struct ipv6_opt_hdr;
@@ -51,8 +143,9 @@ enum ipeh_parse_errors {
#define IPEH_TLV_PAD1 0
#define IPEH_TLV_PADN 1
-bool ipeh_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb,
- int max_count, int off, int len,
+bool ipeh_parse_tlv(unsigned int class,
+ struct tlv_param_table *tlv_param_table,
+ struct sk_buff *skb, int max_count, int off, int len,
bool (*parse_error)(struct sk_buff *skb,
int off, enum ipeh_parse_errors error));
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 1c6878b..07bafad 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -429,6 +429,9 @@ int ip6_ra_control(struct sock *sk, int sel);
int ipv6_parse_hopopts(struct sk_buff *skb);
+int ipv6_exthdrs_options_init(void);
+void ipv6_exthdrs_options_exit(void);
+
bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb,
const struct inet6_skb_parm *opt);
struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
diff --git a/include/uapi/linux/ipeh.h b/include/uapi/linux/ipeh.h
new file mode 100644
index 0000000..c4302b7
--- /dev/null
+++ b/include/uapi/linux/ipeh.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* ipeh.h - IP extension header TLV management */
+
+#ifndef _UAPI_LINUX_IPEH_H
+#define _UAPI_LINUX_IPEH_H
+
+/* Flags for EH type that can use a TLV option */
+#define IPEH_TLV_CLASS_FLAG_HOPOPT BIT(0)
+#define IPEH_TLV_CLASS_FLAG_RTRDSTOPT BIT(1)
+#define IPEH_TLV_CLASS_FLAG_DSTOPT BIT(2)
+
+#define IPEH_TLV_CLASS_FLAG_MASK (IPEH_TLV_CLASS_FLAG_HOPOPT | \
+ IPEH_TLV_CLASS_FLAG_RTRDSTOPT | \
+ IPEH_TLV_CLASS_FLAG_DSTOPT)
+
+#endif /* _UAPI_LINUX_IPEH_H */
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 939d27c..0847d49 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -47,6 +47,7 @@
#ifdef CONFIG_IPV6_SEG6_HMAC
#include <net/seg6_hmac.h>
#endif
+#include <uapi/linux/ipeh.h>
#include <linux/uaccess.h>
@@ -131,7 +132,8 @@ static int ipv6_destopt_rcv(struct sk_buff *skb)
dstbuf = opt->dst1;
#endif
- if (ipeh_parse_tlv(tlvprocdestopt_lst, skb,
+ if (ipeh_parse_tlv(IPEH_TLV_CLASS_FLAG_DSTOPT,
+ &ipv6_tlv_param_table, skb,
init_net.ipv6.sysctl.max_dst_opts_cnt,
2, extlen - 2, ipv6_parse_error)) {
skb->transport_header += extlen;
@@ -514,8 +516,13 @@ int __init ipv6_exthdrs_init(void)
if (ret)
goto out_destopt;
+ ret = ipv6_exthdrs_options_init();
+ if (ret)
+ goto out_nodata;
out:
return ret;
+out_nodata:
+ inet6_del_protocol(&nodata_protocol, IPPROTO_NONE);
out_destopt:
inet6_del_protocol(&destopt_protocol, IPPROTO_DSTOPTS);
out_rthdr:
@@ -525,6 +532,7 @@ int __init ipv6_exthdrs_init(void)
void ipv6_exthdrs_exit(void)
{
+ ipv6_exthdrs_options_exit();
inet6_del_protocol(&nodata_protocol, IPPROTO_NONE);
inet6_del_protocol(&destopt_protocol, IPPROTO_DSTOPTS);
inet6_del_protocol(&rthdr_protocol, IPPROTO_ROUTING);
@@ -555,8 +563,8 @@ int ipv6_parse_hopopts(struct sk_buff *skb)
goto fail_and_free;
opt->flags |= IP6SKB_HOPBYHOP;
- if (ipeh_parse_tlv(tlvprochopopt_lst, skb,
- init_net.ipv6.sysctl.max_hbh_opts_cnt,
+ if (ipeh_parse_tlv(IPEH_TLV_CLASS_FLAG_HOPOPT, &ipv6_tlv_param_table,
+ skb, init_net.ipv6.sysctl.max_hbh_opts_cnt,
2, extlen - 2, ipv6_parse_error)) {
skb->transport_header += extlen;
opt = IP6CB(skb);
diff --git a/net/ipv6/exthdrs_common.c b/net/ipv6/exthdrs_common.c
index 99a0911..cc8db9e 100644
--- a/net/ipv6/exthdrs_common.c
+++ b/net/ipv6/exthdrs_common.c
@@ -150,13 +150,14 @@ EXPORT_SYMBOL_GPL(ipeh_fixup_options);
* - off is offset from skb_transport_header where first TLV is
* - len is length of TLV block
*/
-bool ipeh_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb,
- int max_count, int off, int len,
+bool ipeh_parse_tlv(unsigned int class,
+ struct tlv_param_table *tlv_param_table,
+ struct sk_buff *skb, int max_count, int off, int len,
bool (*parse_error)(struct sk_buff *skb,
int off, enum ipeh_parse_errors error))
{
const unsigned char *nh = skb_network_header(skb);
- const struct tlvtype_proc *curr;
+ const struct tlv_proc *curr;
bool disallow_unknowns = false;
int tlv_count = 0;
int padlen = 0;
@@ -168,8 +169,10 @@ bool ipeh_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb,
if (skb_transport_offset(skb) + off + len > skb_headlen(skb)) {
if (!parse_error(skb, skb_transport_offset(skb),
- IPEH_PARSE_ERR_EH_TOOBIG))
- goto bad;
+ IPEH_PARSE_ERR_EH_TOOBIG)) {
+ kfree_skb(skb);
+ return false;
+ }
len = skb_headlen(skb) - skb_transport_offset(skb) - off;
}
@@ -177,6 +180,8 @@ bool ipeh_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb,
/* ops function based offset on network header */
off += skb_network_header_len(skb);
+ rcu_read_lock();
+
while (len > 0) {
int optlen = nh[off + 1] + 2;
int i;
@@ -221,26 +226,22 @@ bool ipeh_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb,
tlv_count++;
if (tlv_count > max_count &&
- parse_error(skb, off, IPEH_PARSE_ERR_OPT_TOOMANY))
+ !parse_error(skb, off, IPEH_PARSE_ERR_OPT_TOOMANY))
goto bad;
- for (curr = procs; curr->type >= 0; curr++) {
- if (curr->type == nh[off]) {
- /* type specific length/alignment
- * checks will be performed in the
- * func().
- */
- if (curr->func(skb, off) == false)
- return false;
- break;
- }
- }
- if (curr->type < 0 &&
- !parse_error(skb, off,
+ curr = ipeh_tlv_get_proc(tlv_param_table, &nh[off]);
+ if ((curr->params.r.class & class) && curr->ops.func) {
+ /* Handler will apply additional checks to
+ * the TLV
+ */
+ if (!curr->ops.func(class, skb, off))
+ return false;
+ } else if (!parse_error(skb, off,
disallow_unknowns ?
IPEH_PARSE_ERR_OPT_UNK_DISALW :
- IPEH_PARSE_ERR_OPT_UNK))
+ IPEH_PARSE_ERR_OPT_UNK)) {
goto bad;
+ }
padlen = 0;
break;
@@ -249,10 +250,238 @@ bool ipeh_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb,
len -= optlen;
}
- if (len == 0)
+ if (len == 0) {
+ rcu_read_unlock();
return true;
+ }
bad:
+ rcu_read_unlock();
kfree_skb(skb);
return false;
}
EXPORT_SYMBOL(ipeh_parse_tlv);
+
+/* TLV parameter table functions and structures */
+
+/* Default (unset) values for TLV parameters */
+static const struct tlv_proc tlv_default_proc = {
+};
+
+static DEFINE_MUTEX(tlv_mutex);
+
+static size_t tlv_param_table_size(unsigned char count)
+{
+ return sizeof(struct tlv_param_table_data) +
+ (count * sizeof(struct tlv_type));
+}
+
+static void tlv_param_table_release(struct rcu_head *rcu)
+{
+ struct tlv_param_table_data *tpt =
+ container_of(rcu, struct tlv_param_table_data, rcu);
+
+ kvfree(tpt);
+}
+
+/* mutex held */
+static int __tlv_set_one(struct tlv_param_table *tlv_param_table,
+ unsigned char type, const struct tlv_params *params,
+ const struct tlv_ops *ops)
+{
+ struct tlv_param_table_data *tpt, *told;
+ struct tlv_type *ttype;
+
+ told = rcu_dereference_protected(tlv_param_table->data,
+ lockdep_is_held(&tlv_mutex));
+
+ /* Create new TLV table. If there is no exsiting entry then we are
+ * adding a new one to the table, else we're modifying an entry.
+ */
+ tpt = kvmalloc(tlv_param_table_size(told->count + !told->entries[type]),
+ GFP_KERNEL);
+ if (!tpt)
+ return -ENOMEM;
+
+ memcpy(tpt, told, tlv_param_table_size(told->count));
+
+ if (!told->entries[type]) {
+ memset(&tpt->types[told->count], 0, sizeof(struct tlv_type));
+ tpt->entries[type] = told->count;
+ tpt->count = told->count + 1;
+ }
+
+ ttype = &tpt->types[tpt->entries[type]];
+
+ ttype->proc.params = *params;
+ ttype->proc.ops = ops ? *ops : tlv_default_proc.ops;
+
+ rcu_assign_pointer(tlv_param_table->data, tpt);
+ call_rcu(&told->rcu, tlv_param_table_release);
+
+ return 0;
+}
+
+int __ipeh_tlv_set(struct tlv_param_table *tlv_param_table, unsigned char type,
+ const struct tlv_params *params, const struct tlv_ops *ops)
+{
+ int retv;
+
+ if (type < 2)
+ return -EINVAL;
+
+ mutex_lock(&tlv_mutex);
+ retv = __tlv_set_one(tlv_param_table, type, params, ops);
+ mutex_unlock(&tlv_mutex);
+
+ return retv;
+}
+EXPORT_SYMBOL(__ipeh_tlv_set);
+
+/* mutex held */
+static int __tlv_unset_one(struct tlv_param_table *tlv_param_table,
+ unsigned char type)
+{
+ struct tlv_param_table_data *tpt, *told;
+ unsigned int i, pos;
+
+ told = rcu_dereference_protected(tlv_param_table->data,
+ lockdep_is_held(&tlv_mutex));
+
+ if (!told->entries[type])
+ return 0;
+
+ tpt = kvmalloc(tlv_param_table_size(told->count - 1),
+ GFP_KERNEL);
+ if (!tpt)
+ return -ENOMEM;
+
+ pos = told->entries[type];
+
+ memcpy(tpt->types, told->types, pos * sizeof(struct tlv_type));
+ memcpy(&tpt->types[pos], &told->types[pos + 1],
+ (told->count - pos - 1) * sizeof(struct tlv_type));
+
+ for (i = 0; i < 256; i++) {
+ if (told->entries[i] > pos)
+ tpt->entries[i] = told->entries[i] - 1;
+ else
+ tpt->entries[i] = told->entries[i];
+ }
+
+ /* Clear entry for type being unset (point to default params) */
+ tpt->entries[type] = 0;
+
+ tpt->count = told->count - 1;
+
+ rcu_assign_pointer(tlv_param_table->data, tpt);
+ call_rcu(&told->rcu, tlv_param_table_release);
+
+ return 0;
+}
+
+/* tlv_internal_proc_type is used to check it the TLV proc was set
+ * internally. This is deduced by checking if any operations are defined.
+ */
+static bool tlv_internal_proc_type(struct tlv_proc *proc)
+{
+ return !!proc->ops.func;
+}
+
+int __ipeh_tlv_unset(struct tlv_param_table *tlv_param_table,
+ unsigned char type, bool params_only)
+{
+ struct tlv_proc *tproc;
+ int retv;
+
+ if (type < 2)
+ return -EINVAL;
+
+ mutex_lock(&tlv_mutex);
+
+ tproc = ipeh_tlv_get_proc_by_type(tlv_param_table, type);
+
+ if (params_only && tlv_internal_proc_type(tproc)) {
+ /* TLV was set by internal source, so maintain the
+ * non-parameter fields (i.e. the operations).
+ */
+ retv = __tlv_set_one(tlv_param_table, type,
+ &tlv_default_proc.params,
+ &tproc->ops);
+ } else {
+ retv = __tlv_unset_one(tlv_param_table, type);
+ }
+
+ mutex_unlock(&tlv_mutex);
+
+ return retv;
+}
+EXPORT_SYMBOL(__ipeh_tlv_unset);
+
+int ipeh_exthdrs_init(struct tlv_param_table *tlv_param_table,
+ const struct tlv_proc_init *tlv_init_params,
+ int num_init_params)
+{
+ struct tlv_param_table_data *tpt;
+ int pos = 0, i;
+ size_t tsize;
+
+ tsize = tlv_param_table_size(num_init_params + 1);
+
+ tpt = kvmalloc(tsize, GFP_KERNEL);
+ if (!tpt)
+ return -ENOMEM;
+
+ memset(tpt, 0, tsize);
+
+ /* Zeroth TLV proc entry is default */
+ tpt->types[pos++].proc = tlv_default_proc;
+
+ for (i = 0; i < num_init_params; i++, pos++) {
+ const struct tlv_proc_init *tpi = &tlv_init_params[i];
+
+ if (WARN_ON(tpi->type < 2)) {
+ /* Padding TLV initialized? */
+ goto err_inval;
+ }
+ if (WARN_ON(tpt->entries[tpi->type])) {
+ /* TLV type already set */
+ goto err_inval;
+ }
+
+ tpt->types[pos].proc = tpi->proc;
+ tpt->entries[tpi->type] = pos;
+ }
+
+ tpt->count = pos;
+
+ RCU_INIT_POINTER(tlv_param_table->data, tpt);
+
+ return 0;
+
+err_inval:
+ kvfree(tpt);
+ return -EINVAL;
+}
+EXPORT_SYMBOL(ipeh_exthdrs_init);
+
+static void tlv_destroy_param_table(struct tlv_param_table *tlv_param_table)
+{
+ struct tlv_param_table_data *tpt;
+
+ mutex_lock(&tlv_mutex);
+
+ tpt = rcu_dereference_protected(tlv_param_table->data,
+ lockdep_is_held(&tlv_mutex));
+ if (tpt) {
+ rcu_assign_pointer(tlv_param_table->data, NULL);
+ call_rcu(&tpt->rcu, tlv_param_table_release);
+ }
+
+ mutex_unlock(&tlv_mutex);
+}
+
+void ipeh_exthdrs_fini(struct tlv_param_table *tlv_param_table)
+{
+ tlv_destroy_param_table(tlv_param_table);
+}
+EXPORT_SYMBOL(ipeh_exthdrs_fini);
diff --git a/net/ipv6/exthdrs_options.c b/net/ipv6/exthdrs_options.c
index 032e072..d4b373e 100644
--- a/net/ipv6/exthdrs_options.c
+++ b/net/ipv6/exthdrs_options.c
@@ -11,11 +11,12 @@
#if IS_ENABLED(CONFIG_IPV6_MIP6)
#include <net/xfrm.h>
#endif
+#include <uapi/linux/ipeh.h>
/* Destination options header */
#if IS_ENABLED(CONFIG_IPV6_MIP6)
-static bool ipv6_dest_hao(struct sk_buff *skb, int optoff)
+static bool ipv6_dest_hao(unsigned int class, struct sk_buff *skb, int optoff)
{
struct ipv6_destopt_hao *hao;
struct inet6_skb_parm *opt = IP6CB(skb);
@@ -74,16 +75,6 @@ static bool ipv6_dest_hao(struct sk_buff *skb, int optoff)
}
#endif
-const struct tlvtype_proc tlvprocdestopt_lst[] = {
-#if IS_ENABLED(CONFIG_IPV6_MIP6)
- {
- .type = IPV6_TLV_HAO,
- .func = ipv6_dest_hao,
- },
-#endif
- {-1, NULL}
-};
-
/* Hop-by-hop options */
/* Note: we cannot rely on skb_dst(skb) before we assign it in
@@ -102,7 +93,7 @@ static inline struct net *ipv6_skb_net(struct sk_buff *skb)
/* Router Alert as of RFC 2711 */
-static bool ipv6_hop_ra(struct sk_buff *skb, int optoff)
+static bool ipv6_hop_ra(unsigned int class, struct sk_buff *skb, int optoff)
{
const unsigned char *nh = skb_network_header(skb);
@@ -120,7 +111,7 @@ static bool ipv6_hop_ra(struct sk_buff *skb, int optoff)
/* Jumbo payload */
-static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff)
+static bool ipv6_hop_jumbo(unsigned int class, struct sk_buff *skb, int optoff)
{
const unsigned char *nh = skb_network_header(skb);
struct inet6_dev *idev = __in6_dev_get_safely(skb->dev);
@@ -164,7 +155,8 @@ static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff)
/* CALIPSO RFC 5570 */
-static bool ipv6_hop_calipso(struct sk_buff *skb, int optoff)
+static bool ipv6_hop_calipso(unsigned int class, struct sk_buff *skb,
+ int optoff)
{
const unsigned char *nh = skb_network_header(skb);
@@ -184,18 +176,45 @@ static bool ipv6_hop_calipso(struct sk_buff *skb, int optoff)
return false;
}
-const struct tlvtype_proc tlvprochopopt_lst[] = {
+static const struct tlv_proc_init tlv_ipv6_init_params[] __initconst = {
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
{
- .type = IPV6_TLV_ROUTERALERT,
- .func = ipv6_hop_ra,
+ .type = IPV6_TLV_HAO,
+
+ .proc.ops.func = ipv6_dest_hao,
+ .proc.params.r.class = IPEH_TLV_CLASS_FLAG_DSTOPT,
},
+#endif
{
- .type = IPV6_TLV_JUMBO,
- .func = ipv6_hop_jumbo,
+ .type = IPV6_TLV_ROUTERALERT,
+
+ .proc.ops.func = ipv6_hop_ra,
+ .proc.params.r.class = IPEH_TLV_CLASS_FLAG_HOPOPT,
},
{
- .type = IPV6_TLV_CALIPSO,
- .func = ipv6_hop_calipso,
+ .type = IPV6_TLV_JUMBO,
+
+ .proc.ops.func = ipv6_hop_jumbo,
+ .proc.params.r.class = IPEH_TLV_CLASS_FLAG_HOPOPT,
+ },
+ {
+ .type = IPV6_TLV_CALIPSO,
+
+ .proc.ops.func = ipv6_hop_calipso,
+ .proc.params.r.class = IPEH_TLV_CLASS_FLAG_HOPOPT,
},
- { -1, }
};
+
+struct tlv_param_table __rcu ipv6_tlv_param_table;
+EXPORT_SYMBOL(ipv6_tlv_param_table);
+
+int __init ipv6_exthdrs_options_init(void)
+{
+ return ipeh_exthdrs_init(&ipv6_tlv_param_table, tlv_ipv6_init_params,
+ ARRAY_SIZE(tlv_ipv6_init_params));
+}
+
+void ipv6_exthdrs_options_exit(void)
+{
+ ipeh_exthdrs_fini(&ipv6_tlv_param_table);
+}
--
2.7.4
^ permalink raw reply related
* [PATCH v4 net-next 3/7] ipeh: Generic TLV parser
From: Tom Herbert @ 2019-08-23 19:13 UTC (permalink / raw)
To: davem, netdev; +Cc: Tom Herbert, Tom Herbert
In-Reply-To: <1566587643-16594-1-git-send-email-tom@herbertland.com>
From: Tom Herbert <tom@quantonium.net>
Create a generic TLV parser. This will be used with various
extension headers that carry options including Destination,
Hop-by-Hop, Segment Routing TLVs, and other cases of simple
stateless parsing.
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
include/net/ipeh.h | 25 ++++++++
net/ipv6/exthdrs.c | 159 +++++++++++-----------------------------------
net/ipv6/exthdrs_common.c | 114 +++++++++++++++++++++++++++++++++
3 files changed, 177 insertions(+), 121 deletions(-)
diff --git a/include/net/ipeh.h b/include/net/ipeh.h
index 3b24831..c1aa7b6 100644
--- a/include/net/ipeh.h
+++ b/include/net/ipeh.h
@@ -31,4 +31,29 @@ struct ipv6_txoptions *ipeh_renew_options(struct sock *sk,
struct ipv6_txoptions *ipeh_fixup_options(struct ipv6_txoptions *opt_space,
struct ipv6_txoptions *opt);
+/* Generic extension header TLV parser */
+
+enum ipeh_parse_errors {
+ IPEH_PARSE_ERR_PAD1, /* Excessive PAD1 */
+ IPEH_PARSE_ERR_PADN, /* Excessive PADN */
+ IPEH_PARSE_ERR_PADNZ, /* Non-zero padding data */
+ IPEH_PARSE_ERR_EH_TOOBIG, /* Length of EH exceeds limit */
+ IPEH_PARSE_ERR_OPT_TOOBIG, /* Option size exceeds limit */
+ IPEH_PARSE_ERR_OPT_TOOMANY, /* Option count exceeds limit */
+ IPEH_PARSE_ERR_OPT_UNK_DISALW, /* Unknown option disallowed */
+ IPEH_PARSE_ERR_OPT_UNK, /* Unknown option */
+};
+
+/* The generic TLV parser assumes that the type value of PAD1 is 0, and PADN
+ * is 1. This is true for Destination, Hop-by-Hop and current definition
+ * of Segment Routing TLVs.
+ */
+#define IPEH_TLV_PAD1 0
+#define IPEH_TLV_PADN 1
+
+bool ipeh_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb,
+ int max_count, int off, int len,
+ bool (*parse_error)(struct sk_buff *skb,
+ int off, enum ipeh_parse_errors error));
+
#endif /* _NET_IPEH_H */
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index e12d3a5..939d27c 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -54,135 +54,50 @@
Generic functions
*********************/
-/* An unknown option is detected, decide what to do */
-
-static bool ip6_tlvopt_unknown(struct sk_buff *skb, int optoff,
- bool disallow_unknowns)
+/* Handle parse errors from ipeh generic TLV parser */
+static bool ipv6_parse_error(struct sk_buff *skb, int off,
+ enum ipeh_parse_errors error)
{
- if (disallow_unknowns) {
- /* If unknown TLVs are disallowed by configuration
- * then always silently drop packet. Note this also
- * means no ICMP parameter problem is sent which
- * could be a good property to mitigate a reflection DOS
- * attack.
- */
-
- goto drop;
- }
-
- switch ((skb_network_header(skb)[optoff] & 0xC0) >> 6) {
- case 0: /* ignore */
- return true;
-
- case 1: /* drop packet */
- break;
-
- case 3: /* Send ICMP if not a multicast address and drop packet */
- /* Actually, it is redundant check. icmp_send
- will recheck in any case.
- */
- if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr))
+ switch (error) {
+ case IPEH_PARSE_ERR_OPT_UNK_DISALW:
+ /* Disallow unknown skip */
+ if (((skb_network_header(skb)[off] & 0xC0) >> 6) == 0) {
+ /* Silent drop */
break;
+ }
/* fall through */
- case 2: /* send ICMP PARM PROB regardless and drop packet */
- icmpv6_param_prob(skb, ICMPV6_UNK_OPTION, optoff);
- return false;
- }
-
-drop:
- kfree_skb(skb);
- return false;
-}
+ case IPEH_PARSE_ERR_OPT_UNK:
+ switch ((skb_network_header(skb)[off] & 0xC0) >> 6) {
+ case 0: /* ignore */
+ return true;
-/* Parse tlv encoded option header (hop-by-hop or destination) */
-
-static bool ip6_parse_tlv(const struct tlvtype_proc *procs,
- struct sk_buff *skb,
- int max_count)
-{
- int len = (skb_transport_header(skb)[1] + 1) << 3;
- const unsigned char *nh = skb_network_header(skb);
- int off = skb_network_header_len(skb);
- const struct tlvtype_proc *curr;
- bool disallow_unknowns = false;
- int tlv_count = 0;
- int padlen = 0;
-
- if (unlikely(max_count < 0)) {
- disallow_unknowns = true;
- max_count = -max_count;
- }
-
- if (skb_transport_offset(skb) + len > skb_headlen(skb))
- goto bad;
-
- off += 2;
- len -= 2;
-
- while (len > 0) {
- int optlen = nh[off + 1] + 2;
- int i;
-
- switch (nh[off]) {
- case IPV6_TLV_PAD1:
- optlen = 1;
- padlen++;
- if (padlen > 7)
- goto bad;
+ case 1: /* drop packet */
break;
- case IPV6_TLV_PADN:
- /* RFC 2460 states that the purpose of PadN is
- * to align the containing header to multiples
- * of 8. 7 is therefore the highest valid value.
- * See also RFC 4942, Section 2.1.9.5.
- */
- padlen += optlen;
- if (padlen > 7)
- goto bad;
- /* RFC 4942 recommends receiving hosts to
- * actively check PadN payload to contain
- * only zeroes.
+ case 3: /* Send ICMP if not a multicast address and drop packet
+ *
+ * Actually, it is redundant check. icmp_send
+ * will recheck in any case.
*/
- for (i = 2; i < optlen; i++) {
- if (nh[off + i] != 0)
- goto bad;
- }
- break;
+ if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr))
+ break;
- default: /* Other TLV code so scan list */
- if (optlen > len)
- goto bad;
-
- tlv_count++;
- if (tlv_count > max_count)
- goto bad;
-
- for (curr = procs; curr->type >= 0; curr++) {
- if (curr->type == nh[off]) {
- /* type specific length/alignment
- checks will be performed in the
- func(). */
- if (curr->func(skb, off) == false)
- return false;
- break;
- }
- }
- if (curr->type < 0 &&
- !ip6_tlvopt_unknown(skb, off, disallow_unknowns))
- return false;
-
- padlen = 0;
+ /* fall through */
+ case 2: /* send ICMP PARM PROB regardless and drop packet */
+ icmpv6_send(skb, ICMPV6_PARAMPROB,
+ ICMPV6_UNK_OPTION, off);
break;
}
- off += optlen;
- len -= optlen;
+ break;
+ default:
+ break;
}
- if (len == 0)
- return true;
-bad:
- kfree_skb(skb);
+ /* Will be dropping packet */
+
+ __IP6_INC_STATS(dev_net(skb->dev), __in6_dev_get(skb->dev),
+ IPSTATS_MIB_INHDRERRORS);
+
return false;
}
@@ -216,8 +131,9 @@ static int ipv6_destopt_rcv(struct sk_buff *skb)
dstbuf = opt->dst1;
#endif
- if (ip6_parse_tlv(tlvprocdestopt_lst, skb,
- init_net.ipv6.sysctl.max_dst_opts_cnt)) {
+ if (ipeh_parse_tlv(tlvprocdestopt_lst, skb,
+ init_net.ipv6.sysctl.max_dst_opts_cnt,
+ 2, extlen - 2, ipv6_parse_error)) {
skb->transport_header += extlen;
opt = IP6CB(skb);
#if IS_ENABLED(CONFIG_IPV6_MIP6)
@@ -639,8 +555,9 @@ int ipv6_parse_hopopts(struct sk_buff *skb)
goto fail_and_free;
opt->flags |= IP6SKB_HOPBYHOP;
- if (ip6_parse_tlv(tlvprochopopt_lst, skb,
- init_net.ipv6.sysctl.max_hbh_opts_cnt)) {
+ if (ipeh_parse_tlv(tlvprochopopt_lst, skb,
+ init_net.ipv6.sysctl.max_hbh_opts_cnt,
+ 2, extlen - 2, ipv6_parse_error)) {
skb->transport_header += extlen;
opt = IP6CB(skb);
opt->nhoff = sizeof(struct ipv6hdr);
diff --git a/net/ipv6/exthdrs_common.c b/net/ipv6/exthdrs_common.c
index 2c68184..99a0911 100644
--- a/net/ipv6/exthdrs_common.c
+++ b/net/ipv6/exthdrs_common.c
@@ -142,3 +142,117 @@ struct ipv6_txoptions *ipeh_fixup_options(struct ipv6_txoptions *opt_space,
return opt;
}
EXPORT_SYMBOL_GPL(ipeh_fixup_options);
+
+/* Generic extension header TLV parser
+ *
+ * Arguments:
+ * - skb_transport_header points to the extension header containing options
+ * - off is offset from skb_transport_header where first TLV is
+ * - len is length of TLV block
+ */
+bool ipeh_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb,
+ int max_count, int off, int len,
+ bool (*parse_error)(struct sk_buff *skb,
+ int off, enum ipeh_parse_errors error))
+{
+ const unsigned char *nh = skb_network_header(skb);
+ const struct tlvtype_proc *curr;
+ bool disallow_unknowns = false;
+ int tlv_count = 0;
+ int padlen = 0;
+
+ if (unlikely(max_count < 0)) {
+ disallow_unknowns = true;
+ max_count = -max_count;
+ }
+
+ if (skb_transport_offset(skb) + off + len > skb_headlen(skb)) {
+ if (!parse_error(skb, skb_transport_offset(skb),
+ IPEH_PARSE_ERR_EH_TOOBIG))
+ goto bad;
+
+ len = skb_headlen(skb) - skb_transport_offset(skb) - off;
+ }
+
+ /* ops function based offset on network header */
+ off += skb_network_header_len(skb);
+
+ while (len > 0) {
+ int optlen = nh[off + 1] + 2;
+ int i;
+
+ switch (nh[off]) {
+ case IPEH_TLV_PAD1:
+ optlen = 1;
+ padlen++;
+ if (padlen > 7 &&
+ !parse_error(skb, off, IPEH_PARSE_ERR_PAD1))
+ goto bad;
+
+ break;
+
+ case IPEH_TLV_PADN:
+ /* RFC 2460 states that the purpose of PadN is
+ * to align the containing header to multiples
+ * of 8. 7 is therefore the highest valid value.
+ * See also RFC 4942, Section 2.1.9.5.
+ */
+ padlen += optlen;
+ if (padlen > 7 &&
+ !parse_error(skb, off, IPEH_PARSE_ERR_PADN))
+ goto bad;
+
+ /* RFC 4942 recommends receiving hosts to
+ * actively check PadN payload to contain
+ * only zeroes.
+ */
+ for (i = 2; i < optlen; i++) {
+ if (nh[off + i] != 0 &&
+ !parse_error(skb, off + i,
+ IPEH_PARSE_ERR_PADNZ))
+ goto bad;
+ }
+ break;
+
+ default: /* Other TLV code so scan list */
+ if (optlen > len &&
+ !parse_error(skb, off, IPEH_PARSE_ERR_OPT_TOOBIG))
+ goto bad;
+
+ tlv_count++;
+ if (tlv_count > max_count &&
+ parse_error(skb, off, IPEH_PARSE_ERR_OPT_TOOMANY))
+ goto bad;
+
+ for (curr = procs; curr->type >= 0; curr++) {
+ if (curr->type == nh[off]) {
+ /* type specific length/alignment
+ * checks will be performed in the
+ * func().
+ */
+ if (curr->func(skb, off) == false)
+ return false;
+ break;
+ }
+ }
+ if (curr->type < 0 &&
+ !parse_error(skb, off,
+ disallow_unknowns ?
+ IPEH_PARSE_ERR_OPT_UNK_DISALW :
+ IPEH_PARSE_ERR_OPT_UNK))
+ goto bad;
+
+ padlen = 0;
+ break;
+ }
+ off += optlen;
+ len -= optlen;
+ }
+
+ if (len == 0)
+ return true;
+bad:
+ kfree_skb(skb);
+ return false;
+}
+EXPORT_SYMBOL(ipeh_parse_tlv);
--
2.7.4
^ permalink raw reply related
* [PATCH v4 net-next 2/7] ipeh: Move generic EH functions to exthdrs_common.c
From: Tom Herbert @ 2019-08-23 19:13 UTC (permalink / raw)
To: davem, netdev; +Cc: Tom Herbert, Tom Herbert
In-Reply-To: <1566587643-16594-1-git-send-email-tom@herbertland.com>
From: Tom Herbert <tom@quantonium.net>
Move generic functions in exthdrs.c to new exthdrs_common.c so that
exthdrs.c only contains functions that are specific to IPv6 processing,
and exthdrs_common.c contains functions that are generic. These
functions include those that will be used with IPv4 extension headers.
Generic extension header related functions are prefixed by ipeh_.
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
include/net/ipeh.h | 12 ++++
include/net/ipv6.h | 9 ---
net/dccp/ipv6.c | 2 +-
net/ipv6/Kconfig | 4 ++
net/ipv6/Makefile | 1 +
net/ipv6/calipso.c | 6 +-
net/ipv6/exthdrs.c | 138 --------------------------------------------
net/ipv6/exthdrs_common.c | 144 ++++++++++++++++++++++++++++++++++++++++++++++
net/ipv6/ipv6_sockglue.c | 2 +-
net/ipv6/raw.c | 2 +-
net/ipv6/tcp_ipv6.c | 2 +-
net/ipv6/udp.c | 2 +-
net/l2tp/l2tp_ip6.c | 2 +-
net/sctp/ipv6.c | 2 +-
14 files changed, 171 insertions(+), 157 deletions(-)
create mode 100644 net/ipv6/exthdrs_common.c
diff --git a/include/net/ipeh.h b/include/net/ipeh.h
index ec2d186..3b24831 100644
--- a/include/net/ipeh.h
+++ b/include/net/ipeh.h
@@ -19,4 +19,16 @@ struct tlvtype_proc {
extern const struct tlvtype_proc tlvprocdestopt_lst[];
extern const struct tlvtype_proc tlvprochopopt_lst[];
+struct ipv6_txoptions;
+struct ipv6_opt_hdr;
+
+struct ipv6_txoptions *ipeh_dup_options(struct sock *sk,
+ struct ipv6_txoptions *opt);
+struct ipv6_txoptions *ipeh_renew_options(struct sock *sk,
+ struct ipv6_txoptions *opt,
+ int newtype,
+ struct ipv6_opt_hdr *newopt);
+struct ipv6_txoptions *ipeh_fixup_options(struct ipv6_txoptions *opt_space,
+ struct ipv6_txoptions *opt);
+
#endif /* _NET_IPEH_H */
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index ec10fca..1c6878b 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -429,15 +429,6 @@ int ip6_ra_control(struct sock *sk, int sel);
int ipv6_parse_hopopts(struct sk_buff *skb);
-struct ipv6_txoptions *ipv6_dup_options(struct sock *sk,
- struct ipv6_txoptions *opt);
-struct ipv6_txoptions *ipv6_renew_options(struct sock *sk,
- struct ipv6_txoptions *opt,
- int newtype,
- struct ipv6_opt_hdr *newopt);
-struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space,
- struct ipv6_txoptions *opt);
-
bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb,
const struct inet6_skb_parm *opt);
struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 1b7381f..0b83a04 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -514,7 +514,7 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
if (!opt)
opt = rcu_dereference(np->opt);
if (opt) {
- opt = ipv6_dup_options(newsk, opt);
+ opt = ipeh_dup_options(newsk, opt);
RCU_INIT_POINTER(newnp->opt, opt);
}
inet_csk(newsk)->icsk_ext_hdr_len = 0;
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index ae1344e..700fcea 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -3,9 +3,13 @@
# IPv6 configuration
#
+config EXTHDRS
+ bool
+
# IPv6 as module will cause a CRASH if you try to unload it
menuconfig IPV6
tristate "The IPv6 protocol"
+ select EXTHDRS
default y
---help---
Support for IP version 6 (IPv6).
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index df3919b..0bcab81 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -44,6 +44,7 @@ obj-$(CONFIG_IPV6_SIT) += sit.o
obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o
obj-$(CONFIG_IPV6_GRE) += ip6_gre.o
obj-$(CONFIG_IPV6_FOU) += fou6.o
+obj-$(CONFIG_EXTHDRS) += exthdrs_common.o
obj-y += addrconf_core.o exthdrs_core.o ip6_checksum.o ip6_icmp.o
obj-$(CONFIG_INET) += output_core.o protocol.o $(ipv6-offload)
diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c
index 221c81f..9c84848 100644
--- a/net/ipv6/calipso.c
+++ b/net/ipv6/calipso.c
@@ -785,7 +785,7 @@ static int calipso_opt_update(struct sock *sk, struct ipv6_opt_hdr *hop)
{
struct ipv6_txoptions *old = txopt_get(inet6_sk(sk)), *txopts;
- txopts = ipv6_renew_options(sk, old, IPV6_HOPOPTS, hop);
+ txopts = ipeh_renew_options(sk, old, IPV6_HOPOPTS, hop);
txopt_put(old);
if (IS_ERR(txopts))
return PTR_ERR(txopts);
@@ -1207,7 +1207,7 @@ static int calipso_req_setattr(struct request_sock *req,
if (IS_ERR(new))
return PTR_ERR(new);
- txopts = ipv6_renew_options(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, new);
+ txopts = ipeh_renew_options(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, new);
kfree(new);
@@ -1244,7 +1244,7 @@ static void calipso_req_delattr(struct request_sock *req)
if (calipso_opt_del(req_inet->ipv6_opt->hopopt, &new))
return; /* Nothing to do */
- txopts = ipv6_renew_options(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, new);
+ txopts = ipeh_renew_options(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, new);
if (!IS_ERR(txopts)) {
txopts = xchg(&req_inet->ipv6_opt, txopts);
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 664491e..e12d3a5 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -784,144 +784,6 @@ void ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 *pr
}
EXPORT_SYMBOL(ipv6_push_frag_opts);
-struct ipv6_txoptions *
-ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt)
-{
- struct ipv6_txoptions *opt2;
-
- opt2 = sock_kmalloc(sk, opt->tot_len, GFP_ATOMIC);
- if (opt2) {
- long dif = (char *)opt2 - (char *)opt;
- memcpy(opt2, opt, opt->tot_len);
- if (opt2->hopopt)
- *((char **)&opt2->hopopt) += dif;
- if (opt2->dst0opt)
- *((char **)&opt2->dst0opt) += dif;
- if (opt2->dst1opt)
- *((char **)&opt2->dst1opt) += dif;
- if (opt2->srcrt)
- *((char **)&opt2->srcrt) += dif;
- refcount_set(&opt2->refcnt, 1);
- }
- return opt2;
-}
-EXPORT_SYMBOL_GPL(ipv6_dup_options);
-
-static void ipv6_renew_option(int renewtype,
- struct ipv6_opt_hdr **dest,
- struct ipv6_opt_hdr *old,
- struct ipv6_opt_hdr *new,
- int newtype, char **p)
-{
- struct ipv6_opt_hdr *src;
-
- src = (renewtype == newtype ? new : old);
- if (!src)
- return;
-
- memcpy(*p, src, ipv6_optlen(src));
- *dest = (struct ipv6_opt_hdr *)*p;
- *p += CMSG_ALIGN(ipv6_optlen(*dest));
-}
-
-/**
- * ipv6_renew_options - replace a specific ext hdr with a new one.
- *
- * @sk: sock from which to allocate memory
- * @opt: original options
- * @newtype: option type to replace in @opt
- * @newopt: new option of type @newtype to replace (user-mem)
- * @newoptlen: length of @newopt
- *
- * Returns a new set of options which is a copy of @opt with the
- * option type @newtype replaced with @newopt.
- *
- * @opt may be NULL, in which case a new set of options is returned
- * containing just @newopt.
- *
- * @newopt may be NULL, in which case the specified option type is
- * not copied into the new set of options.
- *
- * The new set of options is allocated from the socket option memory
- * buffer of @sk.
- */
-struct ipv6_txoptions *
-ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt,
- int newtype, struct ipv6_opt_hdr *newopt)
-{
- int tot_len = 0;
- char *p;
- struct ipv6_txoptions *opt2;
-
- if (opt) {
- if (newtype != IPV6_HOPOPTS && opt->hopopt)
- tot_len += CMSG_ALIGN(ipv6_optlen(opt->hopopt));
- if (newtype != IPV6_RTHDRDSTOPTS && opt->dst0opt)
- tot_len += CMSG_ALIGN(ipv6_optlen(opt->dst0opt));
- if (newtype != IPV6_RTHDR && opt->srcrt)
- tot_len += CMSG_ALIGN(ipv6_optlen(opt->srcrt));
- if (newtype != IPV6_DSTOPTS && opt->dst1opt)
- tot_len += CMSG_ALIGN(ipv6_optlen(opt->dst1opt));
- }
-
- if (newopt)
- tot_len += CMSG_ALIGN(ipv6_optlen(newopt));
-
- if (!tot_len)
- return NULL;
-
- tot_len += sizeof(*opt2);
- opt2 = sock_kmalloc(sk, tot_len, GFP_ATOMIC);
- if (!opt2)
- return ERR_PTR(-ENOBUFS);
-
- memset(opt2, 0, tot_len);
- refcount_set(&opt2->refcnt, 1);
- opt2->tot_len = tot_len;
- p = (char *)(opt2 + 1);
-
- ipv6_renew_option(IPV6_HOPOPTS, &opt2->hopopt,
- (opt ? opt->hopopt : NULL),
- newopt, newtype, &p);
- ipv6_renew_option(IPV6_RTHDRDSTOPTS, &opt2->dst0opt,
- (opt ? opt->dst0opt : NULL),
- newopt, newtype, &p);
- ipv6_renew_option(IPV6_RTHDR,
- (struct ipv6_opt_hdr **)&opt2->srcrt,
- (opt ? (struct ipv6_opt_hdr *)opt->srcrt : NULL),
- newopt, newtype, &p);
- ipv6_renew_option(IPV6_DSTOPTS, &opt2->dst1opt,
- (opt ? opt->dst1opt : NULL),
- newopt, newtype, &p);
-
- opt2->opt_nflen = (opt2->hopopt ? ipv6_optlen(opt2->hopopt) : 0) +
- (opt2->dst0opt ? ipv6_optlen(opt2->dst0opt) : 0) +
- (opt2->srcrt ? ipv6_optlen(opt2->srcrt) : 0);
- opt2->opt_flen = (opt2->dst1opt ? ipv6_optlen(opt2->dst1opt) : 0);
-
- return opt2;
-}
-
-struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space,
- struct ipv6_txoptions *opt)
-{
- /*
- * ignore the dest before srcrt unless srcrt is being included.
- * --yoshfuji
- */
- if (opt && opt->dst0opt && !opt->srcrt) {
- if (opt_space != opt) {
- memcpy(opt_space, opt, sizeof(*opt_space));
- opt = opt_space;
- }
- opt->opt_nflen -= ipv6_optlen(opt->dst0opt);
- opt->dst0opt = NULL;
- }
-
- return opt;
-}
-EXPORT_SYMBOL_GPL(ipv6_fixup_options);
-
/**
* fl6_update_dst - update flowi destination address with info given
* by srcrt option, if any.
diff --git a/net/ipv6/exthdrs_common.c b/net/ipv6/exthdrs_common.c
new file mode 100644
index 0000000..2c68184
--- /dev/null
+++ b/net/ipv6/exthdrs_common.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Extension header and TLV library code that is not specific to IPv6. */
+#include <linux/export.h>
+#include <net/ipv6.h>
+
+struct ipv6_txoptions *
+ipeh_dup_options(struct sock *sk, struct ipv6_txoptions *opt)
+{
+ struct ipv6_txoptions *opt2;
+
+ opt2 = sock_kmalloc(sk, opt->tot_len, GFP_ATOMIC);
+ if (opt2) {
+ long dif = (char *)opt2 - (char *)opt;
+
+ memcpy(opt2, opt, opt->tot_len);
+ if (opt2->hopopt)
+ *((char **)&opt2->hopopt) += dif;
+ if (opt2->dst0opt)
+ *((char **)&opt2->dst0opt) += dif;
+ if (opt2->dst1opt)
+ *((char **)&opt2->dst1opt) += dif;
+ if (opt2->srcrt)
+ *((char **)&opt2->srcrt) += dif;
+ refcount_set(&opt2->refcnt, 1);
+ }
+ return opt2;
+}
+EXPORT_SYMBOL_GPL(ipeh_dup_options);
+
+static void ipeh_renew_option(int renewtype,
+ struct ipv6_opt_hdr **dest,
+ struct ipv6_opt_hdr *old,
+ struct ipv6_opt_hdr *new,
+ int newtype, char **p)
+{
+ struct ipv6_opt_hdr *src;
+
+ src = (renewtype == newtype ? new : old);
+ if (!src)
+ return;
+
+ memcpy(*p, src, ipv6_optlen(src));
+ *dest = (struct ipv6_opt_hdr *)*p;
+ *p += CMSG_ALIGN(ipv6_optlen(*dest));
+}
+
+/**
+ * ipeh_renew_options - replace a specific ext hdr with a new one.
+ *
+ * @sk: sock from which to allocate memory
+ * @opt: original options
+ * @newtype: option type to replace in @opt
+ * @newopt: new option of type @newtype to replace (user-mem)
+ * @newoptlen: length of @newopt
+ *
+ * Returns a new set of options which is a copy of @opt with the
+ * option type @newtype replaced with @newopt.
+ *
+ * @opt may be NULL, in which case a new set of options is returned
+ * containing just @newopt.
+ *
+ * @newopt may be NULL, in which case the specified option type is
+ * not copied into the new set of options.
+ *
+ * The new set of options is allocated from the socket option memory
+ * buffer of @sk.
+ */
+struct ipv6_txoptions *
+ipeh_renew_options(struct sock *sk, struct ipv6_txoptions *opt,
+ int newtype, struct ipv6_opt_hdr *newopt)
+{
+ int tot_len = 0;
+ char *p;
+ struct ipv6_txoptions *opt2;
+
+ if (opt) {
+ if (newtype != IPV6_HOPOPTS && opt->hopopt)
+ tot_len += CMSG_ALIGN(ipv6_optlen(opt->hopopt));
+ if (newtype != IPV6_RTHDRDSTOPTS && opt->dst0opt)
+ tot_len += CMSG_ALIGN(ipv6_optlen(opt->dst0opt));
+ if (newtype != IPV6_RTHDR && opt->srcrt)
+ tot_len += CMSG_ALIGN(ipv6_optlen(opt->srcrt));
+ if (newtype != IPV6_DSTOPTS && opt->dst1opt)
+ tot_len += CMSG_ALIGN(ipv6_optlen(opt->dst1opt));
+ }
+
+ if (newopt)
+ tot_len += CMSG_ALIGN(ipv6_optlen(newopt));
+
+ if (!tot_len)
+ return NULL;
+
+ tot_len += sizeof(*opt2);
+ opt2 = sock_kmalloc(sk, tot_len, GFP_ATOMIC);
+ if (!opt2)
+ return ERR_PTR(-ENOBUFS);
+
+ memset(opt2, 0, tot_len);
+ refcount_set(&opt2->refcnt, 1);
+ opt2->tot_len = tot_len;
+ p = (char *)(opt2 + 1);
+
+ ipeh_renew_option(IPV6_HOPOPTS, &opt2->hopopt,
+ (opt ? opt->hopopt : NULL),
+ newopt, newtype, &p);
+ ipeh_renew_option(IPV6_RTHDRDSTOPTS, &opt2->dst0opt,
+ (opt ? opt->dst0opt : NULL),
+ newopt, newtype, &p);
+ ipeh_renew_option(IPV6_RTHDR,
+ (struct ipv6_opt_hdr **)&opt2->srcrt,
+ (opt ? (struct ipv6_opt_hdr *)opt->srcrt : NULL),
+ newopt, newtype, &p);
+ ipeh_renew_option(IPV6_DSTOPTS, &opt2->dst1opt,
+ (opt ? opt->dst1opt : NULL),
+ newopt, newtype, &p);
+
+ opt2->opt_nflen = (opt2->hopopt ? ipv6_optlen(opt2->hopopt) : 0) +
+ (opt2->dst0opt ? ipv6_optlen(opt2->dst0opt) : 0) +
+ (opt2->srcrt ? ipv6_optlen(opt2->srcrt) : 0);
+ opt2->opt_flen = (opt2->dst1opt ? ipv6_optlen(opt2->dst1opt) : 0);
+
+ return opt2;
+}
+EXPORT_SYMBOL(ipeh_renew_options);
+
+struct ipv6_txoptions *ipeh_fixup_options(struct ipv6_txoptions *opt_space,
+ struct ipv6_txoptions *opt)
+{
+ /* ignore the dest before srcrt unless srcrt is being included.
+ * --yoshfuji
+ */
+ if (opt && opt->dst0opt && !opt->srcrt) {
+ if (opt_space != opt) {
+ memcpy(opt_space, opt, sizeof(*opt_space));
+ opt = opt_space;
+ }
+ opt->opt_nflen -= ipv6_optlen(opt->dst0opt);
+ opt->dst0opt = NULL;
+ }
+
+ return opt;
+}
+EXPORT_SYMBOL_GPL(ipeh_fixup_options);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 264c292..8755ecc 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -427,7 +427,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
opt = rcu_dereference_protected(np->opt,
lockdep_sock_is_held(sk));
- opt = ipv6_renew_options(sk, opt, optname, new);
+ opt = ipeh_renew_options(sk, opt, optname, new);
kfree(new);
if (IS_ERR(opt)) {
retv = PTR_ERR(opt);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 8a61319..5834ca4 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -888,7 +888,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
}
if (flowlabel)
opt = fl6_merge_options(&opt_space, flowlabel, opt);
- opt = ipv6_fixup_options(&opt_space, opt);
+ opt = ipeh_fixup_options(&opt_space, opt);
fl6.flowi6_proto = proto;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 87f44d3..6bbf24f 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1243,7 +1243,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
if (!opt)
opt = rcu_dereference(np->opt);
if (opt) {
- opt = ipv6_dup_options(newsk, opt);
+ opt = ipeh_dup_options(newsk, opt);
RCU_INIT_POINTER(newnp->opt, opt);
}
inet_csk(newsk)->icsk_ext_hdr_len = 0;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 827fe73..02ab20e 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1384,7 +1384,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
}
if (flowlabel)
opt = fl6_merge_options(&opt_space, flowlabel, opt);
- opt = ipv6_fixup_options(&opt_space, opt);
+ opt = ipeh_fixup_options(&opt_space, opt);
ipc6.opt = opt;
fl6.flowi6_proto = sk->sk_protocol;
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 687e23a..bc4925c 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -590,7 +590,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
}
if (flowlabel)
opt = fl6_merge_options(&opt_space, flowlabel, opt);
- opt = ipv6_fixup_options(&opt_space, opt);
+ opt = ipeh_fixup_options(&opt_space, opt);
ipc6.opt = opt;
fl6.flowi6_proto = sk->sk_protocol;
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index e5f2fc7..b5b1349 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -441,7 +441,7 @@ static void sctp_v6_copy_ip_options(struct sock *sk, struct sock *newsk)
rcu_read_lock();
opt = rcu_dereference(np->opt);
if (opt) {
- opt = ipv6_dup_options(newsk, opt);
+ opt = ipeh_dup_options(newsk, opt);
if (!opt)
pr_err("%s: Failed to copy ip options\n", __func__);
}
--
2.7.4
^ permalink raw reply related
* [PATCH v4 net-next 1/7] ipeh: Create exthdrs_options.c and ipeh.h
From: Tom Herbert @ 2019-08-23 19:13 UTC (permalink / raw)
To: davem, netdev; +Cc: Tom Herbert, Tom Herbert
In-Reply-To: <1566587643-16594-1-git-send-email-tom@herbertland.com>
From: Tom Herbert <tom@quantonium.net>
Create exthdrs_options.c to hold code related to specific Hop-by-Hop
and Destination extension header options. Move related functions in
exthdrs.c to the new file.
Create include net/ipeh.h to contain common definitions for IP extension
headers.
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
include/net/ipeh.h | 22 +++++
include/net/ipv6.h | 1 +
net/ipv6/Makefile | 2 +-
net/ipv6/exthdrs.c | 204 ---------------------------------------------
net/ipv6/exthdrs_options.c | 201 ++++++++++++++++++++++++++++++++++++++++++++
5 files changed, 225 insertions(+), 205 deletions(-)
create mode 100644 include/net/ipeh.h
create mode 100644 net/ipv6/exthdrs_options.c
diff --git a/include/net/ipeh.h b/include/net/ipeh.h
new file mode 100644
index 0000000..ec2d186
--- /dev/null
+++ b/include/net/ipeh.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _NET_IPEH_H
+#define _NET_IPEH_H
+
+#include <linux/skbuff.h>
+
+/*
+ * Parsing tlv encoded headers.
+ *
+ * Parsing function "func" returns true, if parsing succeed
+ * and false, if it failed.
+ * It MUST NOT touch skb->h.
+ */
+struct tlvtype_proc {
+ int type;
+ bool (*func)(struct sk_buff *skb, int offset);
+};
+
+extern const struct tlvtype_proc tlvprocdestopt_lst[];
+extern const struct tlvtype_proc tlvprochopopt_lst[];
+
+#endif /* _NET_IPEH_H */
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 8dfc656..ec10fca 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -20,6 +20,7 @@
#include <net/flow_dissector.h>
#include <net/snmp.h>
#include <net/netns/hash.h>
+#include <net/ipeh.h>
#define SIN6_LEN_RFC2133 24
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index 8ccf355..df3919b 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -10,7 +10,7 @@ ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \
route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \
raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o ping.o \
exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o \
- udp_offload.o seg6.o fib6_notifier.o
+ udp_offload.o seg6.o fib6_notifier.o exthdrs_options.o
ipv6-offload := ip6_offload.o tcpv6_offload.o exthdrs_offload.o
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index ab5add0..664491e 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -39,7 +39,6 @@
#include <net/ndisc.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
-#include <net/calipso.h>
#if IS_ENABLED(CONFIG_IPV6_MIP6)
#include <net/xfrm.h>
#endif
@@ -51,19 +50,6 @@
#include <linux/uaccess.h>
-/*
- * Parsing tlv encoded headers.
- *
- * Parsing function "func" returns true, if parsing succeed
- * and false, if it failed.
- * It MUST NOT touch skb->h.
- */
-
-struct tlvtype_proc {
- int type;
- bool (*func)(struct sk_buff *skb, int offset);
-};
-
/*********************
Generic functions
*********************/
@@ -200,80 +186,6 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs,
return false;
}
-/*****************************
- Destination options header.
- *****************************/
-
-#if IS_ENABLED(CONFIG_IPV6_MIP6)
-static bool ipv6_dest_hao(struct sk_buff *skb, int optoff)
-{
- struct ipv6_destopt_hao *hao;
- struct inet6_skb_parm *opt = IP6CB(skb);
- struct ipv6hdr *ipv6h = ipv6_hdr(skb);
- int ret;
-
- if (opt->dsthao) {
- net_dbg_ratelimited("hao duplicated\n");
- goto discard;
- }
- opt->dsthao = opt->dst1;
- opt->dst1 = 0;
-
- hao = (struct ipv6_destopt_hao *)(skb_network_header(skb) + optoff);
-
- if (hao->length != 16) {
- net_dbg_ratelimited("hao invalid option length = %d\n",
- hao->length);
- goto discard;
- }
-
- if (!(ipv6_addr_type(&hao->addr) & IPV6_ADDR_UNICAST)) {
- net_dbg_ratelimited("hao is not an unicast addr: %pI6\n",
- &hao->addr);
- goto discard;
- }
-
- ret = xfrm6_input_addr(skb, (xfrm_address_t *)&ipv6h->daddr,
- (xfrm_address_t *)&hao->addr, IPPROTO_DSTOPTS);
- if (unlikely(ret < 0))
- goto discard;
-
- if (skb_cloned(skb)) {
- if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
- goto discard;
-
- /* update all variable using below by copied skbuff */
- hao = (struct ipv6_destopt_hao *)(skb_network_header(skb) +
- optoff);
- ipv6h = ipv6_hdr(skb);
- }
-
- if (skb->ip_summed == CHECKSUM_COMPLETE)
- skb->ip_summed = CHECKSUM_NONE;
-
- swap(ipv6h->saddr, hao->addr);
-
- if (skb->tstamp == 0)
- __net_timestamp(skb);
-
- return true;
-
- discard:
- kfree_skb(skb);
- return false;
-}
-#endif
-
-static const struct tlvtype_proc tlvprocdestopt_lst[] = {
-#if IS_ENABLED(CONFIG_IPV6_MIP6)
- {
- .type = IPV6_TLV_HAO,
- .func = ipv6_dest_hao,
- },
-#endif
- {-1, NULL}
-};
-
static int ipv6_destopt_rcv(struct sk_buff *skb)
{
struct inet6_dev *idev = __in6_dev_get(skb->dev);
@@ -702,122 +614,6 @@ void ipv6_exthdrs_exit(void)
inet6_del_protocol(&rthdr_protocol, IPPROTO_ROUTING);
}
-/**********************************
- Hop-by-hop options.
- **********************************/
-
-/*
- * Note: we cannot rely on skb_dst(skb) before we assign it in ip6_route_input().
- */
-static inline struct inet6_dev *ipv6_skb_idev(struct sk_buff *skb)
-{
- return skb_dst(skb) ? ip6_dst_idev(skb_dst(skb)) : __in6_dev_get(skb->dev);
-}
-
-static inline struct net *ipv6_skb_net(struct sk_buff *skb)
-{
- return skb_dst(skb) ? dev_net(skb_dst(skb)->dev) : dev_net(skb->dev);
-}
-
-/* Router Alert as of RFC 2711 */
-
-static bool ipv6_hop_ra(struct sk_buff *skb, int optoff)
-{
- const unsigned char *nh = skb_network_header(skb);
-
- if (nh[optoff + 1] == 2) {
- IP6CB(skb)->flags |= IP6SKB_ROUTERALERT;
- memcpy(&IP6CB(skb)->ra, nh + optoff + 2, sizeof(IP6CB(skb)->ra));
- return true;
- }
- net_dbg_ratelimited("ipv6_hop_ra: wrong RA length %d\n",
- nh[optoff + 1]);
- kfree_skb(skb);
- return false;
-}
-
-/* Jumbo payload */
-
-static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff)
-{
- const unsigned char *nh = skb_network_header(skb);
- struct inet6_dev *idev = __in6_dev_get_safely(skb->dev);
- struct net *net = ipv6_skb_net(skb);
- u32 pkt_len;
-
- if (nh[optoff + 1] != 4 || (optoff & 3) != 2) {
- net_dbg_ratelimited("ipv6_hop_jumbo: wrong jumbo opt length/alignment %d\n",
- nh[optoff+1]);
- __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
- goto drop;
- }
-
- pkt_len = ntohl(*(__be32 *)(nh + optoff + 2));
- if (pkt_len <= IPV6_MAXPLEN) {
- __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
- icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, optoff+2);
- return false;
- }
- if (ipv6_hdr(skb)->payload_len) {
- __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
- icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, optoff);
- return false;
- }
-
- if (pkt_len > skb->len - sizeof(struct ipv6hdr)) {
- __IP6_INC_STATS(net, idev, IPSTATS_MIB_INTRUNCATEDPKTS);
- goto drop;
- }
-
- if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr)))
- goto drop;
-
- IP6CB(skb)->flags |= IP6SKB_JUMBOGRAM;
- return true;
-
-drop:
- kfree_skb(skb);
- return false;
-}
-
-/* CALIPSO RFC 5570 */
-
-static bool ipv6_hop_calipso(struct sk_buff *skb, int optoff)
-{
- const unsigned char *nh = skb_network_header(skb);
-
- if (nh[optoff + 1] < 8)
- goto drop;
-
- if (nh[optoff + 6] * 4 + 8 > nh[optoff + 1])
- goto drop;
-
- if (!calipso_validate(skb, nh + optoff))
- goto drop;
-
- return true;
-
-drop:
- kfree_skb(skb);
- return false;
-}
-
-static const struct tlvtype_proc tlvprochopopt_lst[] = {
- {
- .type = IPV6_TLV_ROUTERALERT,
- .func = ipv6_hop_ra,
- },
- {
- .type = IPV6_TLV_JUMBO,
- .func = ipv6_hop_jumbo,
- },
- {
- .type = IPV6_TLV_CALIPSO,
- .func = ipv6_hop_calipso,
- },
- { -1, }
-};
-
int ipv6_parse_hopopts(struct sk_buff *skb)
{
struct inet6_skb_parm *opt = IP6CB(skb);
diff --git a/net/ipv6/exthdrs_options.c b/net/ipv6/exthdrs_options.c
new file mode 100644
index 0000000..032e072
--- /dev/null
+++ b/net/ipv6/exthdrs_options.c
@@ -0,0 +1,201 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/errno.h>
+#include <linux/in6.h>
+#include <linux/net.h>
+#include <linux/netdevice.h>
+#include <linux/socket.h>
+#include <linux/types.h>
+#include <net/calipso.h>
+#include <net/ipv6.h>
+#include <net/ip6_route.h>
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
+#include <net/xfrm.h>
+#endif
+
+/* Destination options header */
+
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
+static bool ipv6_dest_hao(struct sk_buff *skb, int optoff)
+{
+ struct ipv6_destopt_hao *hao;
+ struct inet6_skb_parm *opt = IP6CB(skb);
+ struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+ int ret;
+
+ if (opt->dsthao) {
+ net_dbg_ratelimited("hao duplicated\n");
+ goto discard;
+ }
+ opt->dsthao = opt->dst1;
+ opt->dst1 = 0;
+
+ hao = (struct ipv6_destopt_hao *)(skb_network_header(skb) + optoff);
+
+ if (hao->length != 16) {
+ net_dbg_ratelimited("hao invalid option length = %d\n",
+ hao->length);
+ goto discard;
+ }
+
+ if (!(ipv6_addr_type(&hao->addr) & IPV6_ADDR_UNICAST)) {
+ net_dbg_ratelimited("hao is not an unicast addr: %pI6\n",
+ &hao->addr);
+ goto discard;
+ }
+
+ ret = xfrm6_input_addr(skb, (xfrm_address_t *)&ipv6h->daddr,
+ (xfrm_address_t *)&hao->addr, IPPROTO_DSTOPTS);
+ if (unlikely(ret < 0))
+ goto discard;
+
+ if (skb_cloned(skb)) {
+ if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+ goto discard;
+
+ /* update all variable using below by copied skbuff */
+ hao = (struct ipv6_destopt_hao *)(skb_network_header(skb) +
+ optoff);
+ ipv6h = ipv6_hdr(skb);
+ }
+
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
+ skb->ip_summed = CHECKSUM_NONE;
+
+ swap(ipv6h->saddr, hao->addr);
+
+ if (skb->tstamp == 0)
+ __net_timestamp(skb);
+
+ return true;
+
+ discard:
+ kfree_skb(skb);
+ return false;
+}
+#endif
+
+const struct tlvtype_proc tlvprocdestopt_lst[] = {
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
+ {
+ .type = IPV6_TLV_HAO,
+ .func = ipv6_dest_hao,
+ },
+#endif
+ {-1, NULL}
+};
+
+/* Hop-by-hop options */
+
+/* Note: we cannot rely on skb_dst(skb) before we assign it in
+ * ip6_route_input().
+ */
+static inline struct inet6_dev *ipv6_skb_idev(struct sk_buff *skb)
+{
+ return skb_dst(skb) ? ip6_dst_idev(skb_dst(skb)) :
+ __in6_dev_get(skb->dev);
+}
+
+static inline struct net *ipv6_skb_net(struct sk_buff *skb)
+{
+ return skb_dst(skb) ? dev_net(skb_dst(skb)->dev) : dev_net(skb->dev);
+}
+
+/* Router Alert as of RFC 2711 */
+
+static bool ipv6_hop_ra(struct sk_buff *skb, int optoff)
+{
+ const unsigned char *nh = skb_network_header(skb);
+
+ if (nh[optoff + 1] == 2) {
+ IP6CB(skb)->flags |= IP6SKB_ROUTERALERT;
+ memcpy(&IP6CB(skb)->ra, nh + optoff + 2,
+ sizeof(IP6CB(skb)->ra));
+ return true;
+ }
+ net_dbg_ratelimited("%s: wrong RA length %d\n",
+ __func__, nh[optoff + 1]);
+ kfree_skb(skb);
+ return false;
+}
+
+/* Jumbo payload */
+
+static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff)
+{
+ const unsigned char *nh = skb_network_header(skb);
+ struct inet6_dev *idev = __in6_dev_get_safely(skb->dev);
+ struct net *net = ipv6_skb_net(skb);
+ u32 pkt_len;
+
+ if (nh[optoff + 1] != 4 || (optoff & 3) != 2) {
+ net_dbg_ratelimited("%s: wrong jumbo opt length/alignment %d\n",
+ __func__, nh[optoff + 1]);
+ __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
+ goto drop;
+ }
+
+ pkt_len = ntohl(*(__be32 *)(nh + optoff + 2));
+ if (pkt_len <= IPV6_MAXPLEN) {
+ __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
+ icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, optoff + 2);
+ return false;
+ }
+ if (ipv6_hdr(skb)->payload_len) {
+ __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
+ icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, optoff);
+ return false;
+ }
+
+ if (pkt_len > skb->len - sizeof(struct ipv6hdr)) {
+ __IP6_INC_STATS(net, idev, IPSTATS_MIB_INTRUNCATEDPKTS);
+ goto drop;
+ }
+
+ if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr)))
+ goto drop;
+
+ IP6CB(skb)->flags |= IP6SKB_JUMBOGRAM;
+ return true;
+
+drop:
+ kfree_skb(skb);
+ return false;
+}
+
+/* CALIPSO RFC 5570 */
+
+static bool ipv6_hop_calipso(struct sk_buff *skb, int optoff)
+{
+ const unsigned char *nh = skb_network_header(skb);
+
+ if (nh[optoff + 1] < 8)
+ goto drop;
+
+ if (nh[optoff + 6] * 4 + 8 > nh[optoff + 1])
+ goto drop;
+
+ if (!calipso_validate(skb, nh + optoff))
+ goto drop;
+
+ return true;
+
+drop:
+ kfree_skb(skb);
+ return false;
+}
+
+const struct tlvtype_proc tlvprochopopt_lst[] = {
+ {
+ .type = IPV6_TLV_ROUTERALERT,
+ .func = ipv6_hop_ra,
+ },
+ {
+ .type = IPV6_TLV_JUMBO,
+ .func = ipv6_hop_jumbo,
+ },
+ {
+ .type = IPV6_TLV_CALIPSO,
+ .func = ipv6_hop_calipso,
+ },
+ { -1, }
+};
--
2.7.4
^ permalink raw reply related
* [PATCH v4 net-next 0/7] ipv6: Extension header infrastructure
From: Tom Herbert @ 2019-08-23 19:13 UTC (permalink / raw)
To: davem, netdev; +Cc: Tom Herbert
This patchset improves the IPv6 extension header infrastructure
to make extension headers more usable and scalable.
- Reorganize extension header files to separate out common
API components
- Create common TLV handler that will can be used in other use
cases (e.g. segment routing TLVs, UDP options)
- Allow registration of TLV handlers
- Elaborate on the TLV tables to include more characteristics
- Add a netlink interface to set TLV parameters (such as
alignment requirements, authorization to send, etc.)
- Enhance validation of TLVs being sent. Validation is strict
(unless overridden by admin) following that sending clause
of the robustness principle
- Allow non-privileged users to set Hop-by-Hop and Destination
Options if authorized by the admin
v2:
- Fix build errors from missing include file.
v3:
- Fix kbuild issue for ipv6_opt_hdr declared inside parameter list
in ipeh.h
v4:
- Resubmit
Tom Herbert (7):
ipeh: Create exthdrs_options.c and ipeh.h
ipeh: Move generic EH functions to exthdrs_common.c
ipeh: Generic TLV parser
ip6tlvs: Registration of TLV handlers and parameters
ip6tlvs: Add TX parameters
ip6tlvs: Add netlink interface
ip6tlvs: Validation of TX Destination and Hop-by-Hop options
include/net/ipeh.h | 208 ++++++++
include/net/ipv6.h | 12 +-
include/uapi/linux/in6.h | 6 +
include/uapi/linux/ipeh.h | 53 ++
net/dccp/ipv6.c | 2 +-
net/ipv6/Kconfig | 4 +
net/ipv6/Makefile | 3 +-
net/ipv6/calipso.c | 6 +-
net/ipv6/datagram.c | 51 +-
net/ipv6/exthdrs.c | 505 ++-----------------
net/ipv6/exthdrs_common.c | 1158 ++++++++++++++++++++++++++++++++++++++++++++
net/ipv6/exthdrs_options.c | 342 +++++++++++++
net/ipv6/ipv6_sockglue.c | 39 +-
net/ipv6/raw.c | 2 +-
net/ipv6/tcp_ipv6.c | 2 +-
net/ipv6/udp.c | 2 +-
net/l2tp/l2tp_ip6.c | 2 +-
net/sctp/ipv6.c | 2 +-
18 files changed, 1881 insertions(+), 518 deletions(-)
create mode 100644 include/net/ipeh.h
create mode 100644 include/uapi/linux/ipeh.h
create mode 100644 net/ipv6/exthdrs_common.c
create mode 100644 net/ipv6/exthdrs_options.c
--
2.7.4
^ permalink raw reply
* [PATCH] net: intel: Cleanup e1000 - add space between }}
From: Forrest Fleming @ 2019-08-23 19:14 UTC (permalink / raw)
To: Jeff Kirsher
Cc: Forrest Fleming, David S. Miller, intel-wired-lan, netdev,
linux-kernel
suggested by checkpatch
Signed-off-by: Forrest Fleming <ffleming@gmail.com>
---
.../net/ethernet/intel/e1000/e1000_param.c | 28 +++++++++----------
1 file changed, 14 insertions(+), 14 deletions(-)
diff --git a/drivers/net/ethernet/intel/e1000/e1000_param.c b/drivers/net/ethernet/intel/e1000/e1000_param.c
index d3f29ffe1e47..1a1f2f0237f9 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_param.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_param.c
@@ -266,7 +266,7 @@ void e1000_check_options(struct e1000_adapter *adapter)
.arg = { .r = {
.min = E1000_MIN_TXD,
.max = mac_type < e1000_82544 ? E1000_MAX_TXD : E1000_MAX_82544_TXD
- }}
+ } }
};
if (num_TxDescriptors > bd) {
@@ -295,7 +295,7 @@ void e1000_check_options(struct e1000_adapter *adapter)
.min = E1000_MIN_RXD,
.max = mac_type < e1000_82544 ? E1000_MAX_RXD :
E1000_MAX_82544_RXD
- }}
+ } }
};
if (num_RxDescriptors > bd) {
@@ -341,7 +341,7 @@ void e1000_check_options(struct e1000_adapter *adapter)
.err = "reading default settings from EEPROM",
.def = E1000_FC_DEFAULT,
.arg = { .l = { .nr = ARRAY_SIZE(fc_list),
- .p = fc_list }}
+ .p = fc_list } }
};
if (num_FlowControl > bd) {
@@ -359,7 +359,7 @@ void e1000_check_options(struct e1000_adapter *adapter)
.err = "using default of " __MODULE_STRING(DEFAULT_TIDV),
.def = DEFAULT_TIDV,
.arg = { .r = { .min = MIN_TXDELAY,
- .max = MAX_TXDELAY }}
+ .max = MAX_TXDELAY } }
};
if (num_TxIntDelay > bd) {
@@ -377,7 +377,7 @@ void e1000_check_options(struct e1000_adapter *adapter)
.err = "using default of " __MODULE_STRING(DEFAULT_TADV),
.def = DEFAULT_TADV,
.arg = { .r = { .min = MIN_TXABSDELAY,
- .max = MAX_TXABSDELAY }}
+ .max = MAX_TXABSDELAY } }
};
if (num_TxAbsIntDelay > bd) {
@@ -395,7 +395,7 @@ void e1000_check_options(struct e1000_adapter *adapter)
.err = "using default of " __MODULE_STRING(DEFAULT_RDTR),
.def = DEFAULT_RDTR,
.arg = { .r = { .min = MIN_RXDELAY,
- .max = MAX_RXDELAY }}
+ .max = MAX_RXDELAY } }
};
if (num_RxIntDelay > bd) {
@@ -413,7 +413,7 @@ void e1000_check_options(struct e1000_adapter *adapter)
.err = "using default of " __MODULE_STRING(DEFAULT_RADV),
.def = DEFAULT_RADV,
.arg = { .r = { .min = MIN_RXABSDELAY,
- .max = MAX_RXABSDELAY }}
+ .max = MAX_RXABSDELAY } }
};
if (num_RxAbsIntDelay > bd) {
@@ -431,7 +431,7 @@ void e1000_check_options(struct e1000_adapter *adapter)
.err = "using default of " __MODULE_STRING(DEFAULT_ITR),
.def = DEFAULT_ITR,
.arg = { .r = { .min = MIN_ITR,
- .max = MAX_ITR }}
+ .max = MAX_ITR } }
};
if (num_InterruptThrottleRate > bd) {
@@ -545,7 +545,7 @@ static void e1000_check_copper_options(struct e1000_adapter *adapter)
{ 0, "" },
{ SPEED_10, "" },
{ SPEED_100, "" },
- { SPEED_1000, "" }};
+ { SPEED_1000, "" } };
opt = (struct e1000_option) {
.type = list_option,
@@ -553,7 +553,7 @@ static void e1000_check_copper_options(struct e1000_adapter *adapter)
.err = "parameter ignored",
.def = 0,
.arg = { .l = { .nr = ARRAY_SIZE(speed_list),
- .p = speed_list }}
+ .p = speed_list } }
};
if (num_Speed > bd) {
@@ -567,7 +567,7 @@ static void e1000_check_copper_options(struct e1000_adapter *adapter)
static const struct e1000_opt_list dplx_list[] = {
{ 0, "" },
{ HALF_DUPLEX, "" },
- { FULL_DUPLEX, "" }};
+ { FULL_DUPLEX, "" } };
opt = (struct e1000_option) {
.type = list_option,
@@ -575,7 +575,7 @@ static void e1000_check_copper_options(struct e1000_adapter *adapter)
.err = "parameter ignored",
.def = 0,
.arg = { .l = { .nr = ARRAY_SIZE(dplx_list),
- .p = dplx_list }}
+ .p = dplx_list } }
};
if (num_Duplex > bd) {
@@ -623,7 +623,7 @@ static void e1000_check_copper_options(struct e1000_adapter *adapter)
{ 0x2c, AA "1000/FD, 100/FD, 100/HD" },
{ 0x2d, AA "1000/FD, 100/FD, 100/HD, 10/HD" },
{ 0x2e, AA "1000/FD, 100/FD, 100/HD, 10/FD" },
- { 0x2f, AA "1000/FD, 100/FD, 100/HD, 10/FD, 10/HD" }};
+ { 0x2f, AA "1000/FD, 100/FD, 100/HD, 10/FD, 10/HD" } };
opt = (struct e1000_option) {
.type = list_option,
@@ -631,7 +631,7 @@ static void e1000_check_copper_options(struct e1000_adapter *adapter)
.err = "parameter ignored",
.def = AUTONEG_ADV_DEFAULT,
.arg = { .l = { .nr = ARRAY_SIZE(an_list),
- .p = an_list }}
+ .p = an_list } }
};
if (num_AutoNeg > bd) {
--
2.17.1
^ permalink raw reply related
* RE: Is bug 200755 in anyone's queue??
From: Steve Zabele @ 2019-08-23 19:02 UTC (permalink / raw)
To: netdev
Cc: shum, vladimir116, saifi.khan, saifi.khan, daniel, on2k16nm,
'Stephen Hemminger'
In-Reply-To: <20190716070246.0745ee6f@hermes.lan>
Hi folks,
Is there a way to find out where the SO_REUSEPORT bug reported a year ago in
August (and apparently has been a bug with kernels later than 4.4) is being
addressed?
The bug characteristics, simple standalone test code demonstrating the bug,
and an assessment of the likely location/cause of the bug within the kernel
are all described here
https://bugzilla.kernel.org/show_bug.cgi?id=200755
I'm really hoping this gets fixed so we can move forward on updating our
kernels/Ubuntu release from our aging 4.4/16.04 release
Thanks!
Steve
-----Original Message-----
From: Stephen Hemminger [mailto:stephen@networkplumber.org]
Sent: Tuesday, July 16, 2019 10:03 AM
To: Steve Zabele
Cc: shum@canndrew.org; vladimir116@gmail.com; saifi.khan@DataSynergy.org;
saifi.khan@strikr.in; daniel@iogearbox.net; on2k16nm@gmail.com
Subject: Re: Is bug 200755 in anyone's queue??
On Tue, 16 Jul 2019 09:43:24 -0400
"Steve Zabele" <zabele@comcast.net> wrote:
> I came across bug report 200755 trying to figure out why some code I had
> provided to customers a while ago no longer works with the current Linux
> kernel. See
>
> https://bugzilla.kernel.org/show_bug.cgi?id=200755
>
> I've verified that, as reported, 'connect' no longer works for UDP.
> Moreover, it appears it has been broken since the 4.5 kernel has been
> released.
>
>
>
> It does also appear that the intended new feature of doing round robin
> assignments to different UDP sockets opened with SO_REUSEPORT also does
not
> work as described.
>
>
>
> Since the original bug report was made nearly a year ago for the 4.14
kernel
> (and the bug is also still present in the 4.15 kernel) I'm curious if
anyone
> is on the hook to get this fixed any time soon.
>
>
>
> I'd rather not have to do my own demultiplexing using a single socket in
> user space to work around what is clearly a (maybe not so recently
> introduced) kernel bug if at all possible. My code had worked just fine on
> 3.X kernels, and appears to work okay up through 4.4.
>
Kernel developers do not use bugzilla, I forward bug reports
to netdev@vger.kernel.org (after filtering).
^ permalink raw reply
* RE: Is bug 200755 in anyone's queue??
From: Steve Zabele @ 2019-08-23 19:04 UTC (permalink / raw)
To: 'Steve Zabele', netdev
Cc: shum, vladimir116, saifi.khan, daniel, on2k16nm,
'Stephen Hemminger'
In-Reply-To: <20190716070246.0745ee6f@hermes.lan>
Hi folks,
Is there a way to find out where the SO_REUSEPORT bug reported a year ago in
August (and apparently has been a bug with kernels later than 4.4) is being
addressed?
The bug characteristics, simple standalone test code demonstrating the bug,
and an assessment of the likely location/cause of the bug within the kernel
are all described here
https://bugzilla.kernel.org/show_bug.cgi?id=200755
I'm really hoping this gets fixed so we can move forward on updating our
kernels/Ubuntu release from our aging 4.4/16.04 release
Thanks!
Steve
-----Original Message-----
From: Stephen Hemminger [mailto:stephen@networkplumber.org]
Sent: Tuesday, July 16, 2019 10:03 AM
To: Steve Zabele
Cc: shum@canndrew.org; vladimir116@gmail.com; saifi.khan@DataSynergy.org;
saifi.khan@strikr.in; daniel@iogearbox.net; on2k16nm@gmail.com
Subject: Re: Is bug 200755 in anyone's queue??
On Tue, 16 Jul 2019 09:43:24 -0400
"Steve Zabele" <zabele@comcast.net> wrote:
> I came across bug report 200755 trying to figure out why some code I had
> provided to customers a while ago no longer works with the current Linux
> kernel. See
>
> https://bugzilla.kernel.org/show_bug.cgi?id=200755
>
> I've verified that, as reported, 'connect' no longer works for UDP.
> Moreover, it appears it has been broken since the 4.5 kernel has been
> released.
>
>
>
> It does also appear that the intended new feature of doing round robin
> assignments to different UDP sockets opened with SO_REUSEPORT also does
not
> work as described.
>
>
>
> Since the original bug report was made nearly a year ago for the 4.14
kernel
> (and the bug is also still present in the 4.15 kernel) I'm curious if
anyone
> is on the hook to get this fixed any time soon.
>
>
>
> I'd rather not have to do my own demultiplexing using a single socket in
> user space to work around what is clearly a (maybe not so recently
> introduced) kernel bug if at all possible. My code had worked just fine on
> 3.X kernels, and appears to work okay up through 4.4.
>
Kernel developers do not use bugzilla, I forward bug reports
to netdev@vger.kernel.org (after filtering).
^ permalink raw reply
* Re: New skb extension for use by LSMs (skb "security blob")?
From: Casey Schaufler @ 2019-08-23 18:56 UTC (permalink / raw)
To: David Miller; +Cc: fw, paul, netdev, linux-security-module, selinux, casey
In-Reply-To: <20190822.153642.10800077338364583.davem@davemloft.net>
On 8/22/2019 3:36 PM, David Miller wrote:
> From: Casey Schaufler <casey@schaufler-ca.com>
> Date: Thu, 22 Aug 2019 15:34:44 -0700
>
>> On 8/22/2019 3:28 PM, David Miller wrote:
>>> From: Casey Schaufler <casey@schaufler-ca.com>
>>> Date: Thu, 22 Aug 2019 14:59:37 -0700
>>>
>>>> Sure, you *can* do that, but it would be insane to do so.
>>> We look up the neighbour table entries on every single packet we
>>> transmit from the kernel in the same exact way.
>>>
>>> And it was exactly to get rid of a pointer in a data structure.
>> I very much expect that the lifecycle management issues would
>> be completely different, but I'll admit to having little understanding
>> of the details of the neighbour table.
> Neighbour table entries can live anywhere from essentially forever down
> to several microseconds.
>
> If your hash is good, and you use RCU locking on the read side, it's a
> single pointer dereference in cost.
The secmark is the data used by the netfilter system.
While it would be (Turing compatible, after all) possible,
we're talking multiple attributes with different lifecycles
being managed in a table (list, whatever) that may expand
explosively. Using a single ID to reference into a table that
could contain:
secmark from iptables for SELinux
secmark from iptables for AppArmor
SELinux secid/context for the packet
AppArmor secid/context for the packet
will be hairy. In the netfilter processing we may have to
allocate a new table entry. There's no way to identify that
the entry is no longer necessary, as there is no lifecycle
on a secmark. Is it possible to come up with something that
will limp along? Possibly. If there's a blob pointer, we know
how to do all this effectively.
^ permalink raw reply
* [PATCH net-next v2 06/10] net: sched: conditionally obtain rtnl lock in cls hw offloads API
From: Vlad Buslov @ 2019-08-23 18:50 UTC (permalink / raw)
To: netdev; +Cc: jhs, xiyou.wangcong, jiri, davem, jakub.kicinski, pablo,
Vlad Buslov
In-Reply-To: <20190823185056.12536-1-vladbu@mellanox.com>
In order to remove dependency on rtnl lock from offloads code of
classifiers, take rtnl lock conditionally before executing driver
callbacks. Only obtain rtnl lock if block is bound to devices that require
it.
Block bind/unbind code is rtnl-locked and obtains block->cb_lock while
holding rtnl lock. Obtain locks in same order in tc_setup_cb_*() functions
to prevent deadlock.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
---
Changes from V1 to V2:
- Speculatively read block->lockeddevcnt in tc_setup_cb_*() to obtain
rtnl mutex without retry when block is bound to locked device.
net/sched/cls_api.c | 65 +++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 65 insertions(+)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 87954f5370a4..f2dcecf34c6f 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -3076,11 +3076,28 @@ __tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type,
int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type,
void *type_data, bool err_stop, bool rtnl_held)
{
+ bool take_rtnl = READ_ONCE(block->lockeddevcnt);
int ok_count;
+retry:
+ if (take_rtnl)
+ rtnl_lock();
down_read(&block->cb_lock);
+ /* Need to obtain rtnl lock if block is bound to devs that require it.
+ * In block bind code cb_lock is obtained while holding rtnl, so we must
+ * obtain the locks in same order here.
+ */
+ if (!rtnl_held && !take_rtnl && block->lockeddevcnt) {
+ up_read(&block->cb_lock);
+ take_rtnl = true;
+ goto retry;
+ }
+
ok_count = __tc_setup_cb_call(block, type, type_data, err_stop);
+
up_read(&block->cb_lock);
+ if (take_rtnl)
+ rtnl_unlock();
return ok_count;
}
EXPORT_SYMBOL(tc_setup_cb_call);
@@ -3095,9 +3112,23 @@ int tc_setup_cb_add(struct tcf_block *block, struct tcf_proto *tp,
enum tc_setup_type type, void *type_data, bool err_stop,
u32 *flags, unsigned int *in_hw_count, bool rtnl_held)
{
+ bool take_rtnl = READ_ONCE(block->lockeddevcnt);
int ok_count;
+retry:
+ if (take_rtnl)
+ rtnl_lock();
down_read(&block->cb_lock);
+ /* Need to obtain rtnl lock if block is bound to devs that require it.
+ * In block bind code cb_lock is obtained while holding rtnl, so we must
+ * obtain the locks in same order here.
+ */
+ if (!rtnl_held && !take_rtnl && block->lockeddevcnt) {
+ up_read(&block->cb_lock);
+ take_rtnl = true;
+ goto retry;
+ }
+
/* Make sure all netdevs sharing this block are offload-capable. */
if (block->nooffloaddevcnt && err_stop) {
ok_count = -EOPNOTSUPP;
@@ -3115,6 +3146,8 @@ int tc_setup_cb_add(struct tcf_block *block, struct tcf_proto *tp,
ok_count, true);
err_unlock:
up_read(&block->cb_lock);
+ if (take_rtnl)
+ rtnl_unlock();
return ok_count < 0 ? ok_count : 0;
}
EXPORT_SYMBOL(tc_setup_cb_add);
@@ -3131,9 +3164,23 @@ int tc_setup_cb_replace(struct tcf_block *block, struct tcf_proto *tp,
u32 *new_flags, unsigned int *new_in_hw_count,
bool rtnl_held)
{
+ bool take_rtnl = READ_ONCE(block->lockeddevcnt);
int ok_count;
+retry:
+ if (take_rtnl)
+ rtnl_lock();
down_read(&block->cb_lock);
+ /* Need to obtain rtnl lock if block is bound to devs that require it.
+ * In block bind code cb_lock is obtained while holding rtnl, so we must
+ * obtain the locks in same order here.
+ */
+ if (!rtnl_held && !take_rtnl && block->lockeddevcnt) {
+ up_read(&block->cb_lock);
+ take_rtnl = true;
+ goto retry;
+ }
+
/* Make sure all netdevs sharing this block are offload-capable. */
if (block->nooffloaddevcnt && err_stop) {
ok_count = -EOPNOTSUPP;
@@ -3155,6 +3202,8 @@ int tc_setup_cb_replace(struct tcf_block *block, struct tcf_proto *tp,
new_flags, ok_count, true);
err_unlock:
up_read(&block->cb_lock);
+ if (take_rtnl)
+ rtnl_unlock();
return ok_count < 0 ? ok_count : 0;
}
EXPORT_SYMBOL(tc_setup_cb_replace);
@@ -3167,9 +3216,23 @@ int tc_setup_cb_destroy(struct tcf_block *block, struct tcf_proto *tp,
enum tc_setup_type type, void *type_data, bool err_stop,
u32 *flags, unsigned int *in_hw_count, bool rtnl_held)
{
+ bool take_rtnl = READ_ONCE(block->lockeddevcnt);
int ok_count;
+retry:
+ if (take_rtnl)
+ rtnl_lock();
down_read(&block->cb_lock);
+ /* Need to obtain rtnl lock if block is bound to devs that require it.
+ * In block bind code cb_lock is obtained while holding rtnl, so we must
+ * obtain the locks in same order here.
+ */
+ if (!rtnl_held && !take_rtnl && block->lockeddevcnt) {
+ up_read(&block->cb_lock);
+ take_rtnl = true;
+ goto retry;
+ }
+
ok_count = __tc_setup_cb_call(block, type, type_data, err_stop);
tc_cls_offload_cnt_reset(block, tp, in_hw_count, flags);
@@ -3177,6 +3240,8 @@ int tc_setup_cb_destroy(struct tcf_block *block, struct tcf_proto *tp,
tp->ops->hw_del(tp, type_data);
up_read(&block->cb_lock);
+ if (take_rtnl)
+ rtnl_unlock();
return ok_count < 0 ? ok_count : 0;
}
EXPORT_SYMBOL(tc_setup_cb_destroy);
--
2.21.0
^ permalink raw reply related
* [PATCH net-next v2 08/10] net: sched: take reference to action dev before calling offloads
From: Vlad Buslov @ 2019-08-23 18:50 UTC (permalink / raw)
To: netdev
Cc: jhs, xiyou.wangcong, jiri, davem, jakub.kicinski, pablo,
Vlad Buslov, Jiri Pirko
In-Reply-To: <20190823185056.12536-1-vladbu@mellanox.com>
In order to remove dependency on rtnl lock when calling hardware offload
API, take reference to action mirred dev when initializing flow_action
structure in tc_setup_flow_action(). Implement function
tc_cleanup_flow_action(), use it to release the device after hardware
offload API is done using it.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
include/net/pkt_cls.h | 2 ++
net/sched/cls_api.c | 32 ++++++++++++++++++++++++++++++++
net/sched/cls_flower.c | 2 ++
3 files changed, 36 insertions(+)
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index a48824bc1489..e553fc80eb23 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -505,6 +505,8 @@ tcf_match_indev(struct sk_buff *skb, int ifindex)
int tc_setup_flow_action(struct flow_action *flow_action,
const struct tcf_exts *exts, bool rtnl_held);
+void tc_cleanup_flow_action(struct flow_action *flow_action);
+
int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type,
void *type_data, bool err_stop, bool rtnl_held);
int tc_setup_cb_add(struct tcf_block *block, struct tcf_proto *tp,
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index cb835d581b77..622146aafb06 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -3260,6 +3260,27 @@ int tc_setup_cb_reoffload(struct tcf_block *block, struct tcf_proto *tp,
}
EXPORT_SYMBOL(tc_setup_cb_reoffload);
+void tc_cleanup_flow_action(struct flow_action *flow_action)
+{
+ struct flow_action_entry *entry;
+ int i;
+
+ flow_action_for_each(i, entry, flow_action) {
+ switch (entry->id) {
+ case FLOW_ACTION_REDIRECT:
+ case FLOW_ACTION_MIRRED:
+ case FLOW_ACTION_REDIRECT_INGRESS:
+ case FLOW_ACTION_MIRRED_INGRESS:
+ if (entry->dev)
+ dev_put(entry->dev);
+ break;
+ default:
+ break;
+ }
+ }
+}
+EXPORT_SYMBOL(tc_cleanup_flow_action);
+
int tc_setup_flow_action(struct flow_action *flow_action,
const struct tcf_exts *exts, bool rtnl_held)
{
@@ -3289,15 +3310,23 @@ int tc_setup_flow_action(struct flow_action *flow_action,
} else if (is_tcf_mirred_egress_redirect(act)) {
entry->id = FLOW_ACTION_REDIRECT;
entry->dev = tcf_mirred_dev(act);
+ if (entry->dev)
+ dev_hold(entry->dev);
} else if (is_tcf_mirred_egress_mirror(act)) {
entry->id = FLOW_ACTION_MIRRED;
entry->dev = tcf_mirred_dev(act);
+ if (entry->dev)
+ dev_hold(entry->dev);
} else if (is_tcf_mirred_ingress_redirect(act)) {
entry->id = FLOW_ACTION_REDIRECT_INGRESS;
entry->dev = tcf_mirred_dev(act);
+ if (entry->dev)
+ dev_hold(entry->dev);
} else if (is_tcf_mirred_ingress_mirror(act)) {
entry->id = FLOW_ACTION_MIRRED_INGRESS;
entry->dev = tcf_mirred_dev(act);
+ if (entry->dev)
+ dev_hold(entry->dev);
} else if (is_tcf_vlan(act)) {
switch (tcf_vlan_action(act)) {
case TCA_VLAN_ACT_PUSH:
@@ -3405,6 +3434,9 @@ int tc_setup_flow_action(struct flow_action *flow_action,
if (!rtnl_held)
rtnl_unlock();
+ if (err)
+ tc_cleanup_flow_action(flow_action);
+
return err;
}
EXPORT_SYMBOL(tc_setup_flow_action);
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index d47d4e84d4e5..df141a67c17f 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -465,6 +465,7 @@ static int fl_hw_replace_filter(struct tcf_proto *tp,
err = tc_setup_cb_add(block, tp, TC_SETUP_CLSFLOWER, &cls_flower,
skip_sw, &f->flags, &f->in_hw_count, true);
+ tc_cleanup_flow_action(&cls_flower.rule->action);
kfree(cls_flower.rule);
if (err) {
@@ -1838,6 +1839,7 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb,
TC_SETUP_CLSFLOWER, &cls_flower,
cb_priv, &f->flags,
&f->in_hw_count);
+ tc_cleanup_flow_action(&cls_flower.rule->action);
kfree(cls_flower.rule);
if (err && add && tc_skip_sw(f->flags)) {
--
2.21.0
^ permalink raw reply related
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