Re: Linux 5.8.15

From: Greg Kroah-Hartman
Date: Wed Oct 14 2020 - 06:12:59 EST


diff --git a/Makefile b/Makefile
index 33ceda527e5e..6c787cd1cb51 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
VERSION = 5
PATCHLEVEL = 8
-SUBLEVEL = 14
+SUBLEVEL = 15
EXTRAVERSION =
NAME = Kleptomaniac Octopus

diff --git a/arch/arm64/crypto/aes-neonbs-core.S b/arch/arm64/crypto/aes-neonbs-core.S
index b357164379f6..63a52ad9a75c 100644
--- a/arch/arm64/crypto/aes-neonbs-core.S
+++ b/arch/arm64/crypto/aes-neonbs-core.S
@@ -788,7 +788,7 @@ SYM_FUNC_START_LOCAL(__xts_crypt8)

0: mov bskey, x21
mov rounds, x22
- br x7
+ br x16
SYM_FUNC_END(__xts_crypt8)

.macro __xts_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7
@@ -806,7 +806,7 @@ SYM_FUNC_END(__xts_crypt8)
uzp1 v30.4s, v30.4s, v25.4s
ld1 {v25.16b}, [x24]

-99: adr x7, \do8
+99: adr x16, \do8
bl __xts_crypt8

ldp q16, q17, [sp, #.Lframe_local_offset]
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index e229d95f470b..7c1dadf14f56 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -515,6 +515,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
#else
dtb_early_va = (void *)dtb_pa;
#endif
+ dtb_early_pa = dtb_pa;
}

static inline void setup_vm_final(void)
diff --git a/block/partitions/ibm.c b/block/partitions/ibm.c
index d6e18df9c53c..4b044e620d35 100644
--- a/block/partitions/ibm.c
+++ b/block/partitions/ibm.c
@@ -305,8 +305,6 @@ int ibm_partition(struct parsed_partitions *state)
if (!disk->fops->getgeo)
goto out_exit;
fn = symbol_get(dasd_biodasdinfo);
- if (!fn)
- goto out_exit;
blocksize = bdev_logical_block_size(bdev);
if (blocksize <= 0)
goto out_symbol;
@@ -326,7 +324,7 @@ int ibm_partition(struct parsed_partitions *state)
geo->start = get_start_sect(bdev);
if (disk->fops->getgeo(bdev, geo))
goto out_freeall;
- if (fn(disk, info)) {
+ if (!fn || fn(disk, info)) {
kfree(info);
info = NULL;
}
@@ -370,7 +368,8 @@ int ibm_partition(struct parsed_partitions *state)
out_nogeo:
kfree(info);
out_symbol:
- symbol_put(dasd_biodasdinfo);
+ if (fn)
+ symbol_put(dasd_biodasdinfo);
out_exit:
return res;
}
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index ef722f04f88a..72108404718f 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -651,6 +651,7 @@ struct compat_cdrom_generic_command {
compat_int_t stat;
compat_caddr_t sense;
unsigned char data_direction;
+ unsigned char pad[3];
compat_int_t quiet;
compat_int_t timeout;
compat_caddr_t reserved[1];
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 6e813b13d698..02154d8b1c0d 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -838,7 +838,7 @@ static __poll_t lineevent_poll(struct file *filep,

static ssize_t lineevent_get_size(void)
{
-#ifdef __x86_64__
+#if defined(CONFIG_X86_64) && !defined(CONFIG_UML)
/* i386 has no padding after 'id' */
if (in_ia32_syscall()) {
struct compat_gpioeevent_data {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index e59c01a83dac..9a3267f06376 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -1052,6 +1052,7 @@ static int amdgpu_ttm_tt_pin_userptr(struct ttm_tt *ttm)

release_sg:
kfree(ttm->sg);
+ ttm->sg = NULL;
return r;
}

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
index 949d10ef8304..6dd1f3f8d990 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
@@ -568,7 +568,7 @@ struct hdcp_workqueue *hdcp_create_workqueue(struct amdgpu_device *adev, struct
int i = 0;

hdcp_work = kcalloc(max_caps, sizeof(*hdcp_work), GFP_KERNEL);
- if (hdcp_work == NULL)
+ if (ZERO_OR_NULL_PTR(hdcp_work))
return NULL;

hdcp_work->srm = kcalloc(PSP_HDCP_SRM_FIRST_GEN_MAX_SIZE, sizeof(*hdcp_work->srm), GFP_KERNEL);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
index 9ee8cf8267c8..43f7adff6cb7 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
@@ -563,6 +563,8 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
struct smu10_hwmgr *data = hwmgr->backend;
uint32_t min_sclk = hwmgr->display_config->min_core_set_clock;
uint32_t min_mclk = hwmgr->display_config->min_mem_set_clock/100;
+ uint32_t index_fclk = data->clock_vol_info.vdd_dep_on_fclk->count - 1;
+ uint32_t index_socclk = data->clock_vol_info.vdd_dep_on_socclk->count - 1;

if (hwmgr->smu_version < 0x1E3700) {
pr_info("smu firmware version too old, can not set dpm level\n");
@@ -676,13 +678,13 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetHardMinFclkByFreq,
hwmgr->display_config->num_display > 3 ?
- SMU10_UMD_PSTATE_PEAK_FCLK :
+ data->clock_vol_info.vdd_dep_on_fclk->entries[0].clk :
min_mclk,
NULL);

smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetHardMinSocclkByFreq,
- SMU10_UMD_PSTATE_MIN_SOCCLK,
+ data->clock_vol_info.vdd_dep_on_socclk->entries[0].clk,
NULL);
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetHardMinVcn,
@@ -695,11 +697,11 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
NULL);
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetSoftMaxFclkByFreq,
- SMU10_UMD_PSTATE_PEAK_FCLK,
+ data->clock_vol_info.vdd_dep_on_fclk->entries[index_fclk].clk,
NULL);
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetSoftMaxSocclkByFreq,
- SMU10_UMD_PSTATE_PEAK_SOCCLK,
+ data->clock_vol_info.vdd_dep_on_socclk->entries[index_socclk].clk,
NULL);
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetSoftMaxVcn,
diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.c b/drivers/gpu/drm/nouveau/nouveau_mem.c
index c002f8968507..9682f30ab6f6 100644
--- a/drivers/gpu/drm/nouveau/nouveau_mem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_mem.c
@@ -176,6 +176,8 @@ void
nouveau_mem_del(struct ttm_mem_reg *reg)
{
struct nouveau_mem *mem = nouveau_mem(reg);
+ if (!mem)
+ return;
nouveau_mem_fini(mem);
kfree(reg->mm_node);
reg->mm_node = NULL;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index 5b90c2a1bf3d..7c2e5db840be 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -3149,6 +3149,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
case 0x168: device->chip = &nv168_chipset; break;
default:
nvdev_error(device, "unknown chipset (%08x)\n", boot0);
+ ret = -ENODEV;
goto done;
}

diff --git a/drivers/i2c/busses/i2c-meson.c b/drivers/i2c/busses/i2c-meson.c
index c5dec572fc48..ef73a42577cc 100644
--- a/drivers/i2c/busses/i2c-meson.c
+++ b/drivers/i2c/busses/i2c-meson.c
@@ -5,6 +5,7 @@
* Copyright (C) 2014 Beniamino Galvani <b.galvani@xxxxxxxxx>
*/

+#include <linux/bitfield.h>
#include <linux/clk.h>
#include <linux/completion.h>
#include <linux/i2c.h>
@@ -33,12 +34,17 @@
#define REG_CTRL_ACK_IGNORE BIT(1)
#define REG_CTRL_STATUS BIT(2)
#define REG_CTRL_ERROR BIT(3)
-#define REG_CTRL_CLKDIV_SHIFT 12
-#define REG_CTRL_CLKDIV_MASK GENMASK(21, 12)
-#define REG_CTRL_CLKDIVEXT_SHIFT 28
-#define REG_CTRL_CLKDIVEXT_MASK GENMASK(29, 28)
+#define REG_CTRL_CLKDIV GENMASK(21, 12)
+#define REG_CTRL_CLKDIVEXT GENMASK(29, 28)
+
+#define REG_SLV_ADDR GENMASK(7, 0)
+#define REG_SLV_SDA_FILTER GENMASK(10, 8)
+#define REG_SLV_SCL_FILTER GENMASK(13, 11)
+#define REG_SLV_SCL_LOW GENMASK(27, 16)
+#define REG_SLV_SCL_LOW_EN BIT(28)

#define I2C_TIMEOUT_MS 500
+#define FILTER_DELAY 15

enum {
TOKEN_END = 0,
@@ -133,19 +139,24 @@ static void meson_i2c_set_clk_div(struct meson_i2c *i2c, unsigned int freq)
unsigned long clk_rate = clk_get_rate(i2c->clk);
unsigned int div;

- div = DIV_ROUND_UP(clk_rate, freq * i2c->data->div_factor);
+ div = DIV_ROUND_UP(clk_rate, freq);
+ div -= FILTER_DELAY;
+ div = DIV_ROUND_UP(div, i2c->data->div_factor);

/* clock divider has 12 bits */
- if (div >= (1 << 12)) {
+ if (div > GENMASK(11, 0)) {
dev_err(i2c->dev, "requested bus frequency too low\n");
- div = (1 << 12) - 1;
+ div = GENMASK(11, 0);
}

- meson_i2c_set_mask(i2c, REG_CTRL, REG_CTRL_CLKDIV_MASK,
- (div & GENMASK(9, 0)) << REG_CTRL_CLKDIV_SHIFT);
+ meson_i2c_set_mask(i2c, REG_CTRL, REG_CTRL_CLKDIV,
+ FIELD_PREP(REG_CTRL_CLKDIV, div & GENMASK(9, 0)));
+
+ meson_i2c_set_mask(i2c, REG_CTRL, REG_CTRL_CLKDIVEXT,
+ FIELD_PREP(REG_CTRL_CLKDIVEXT, div >> 10));

- meson_i2c_set_mask(i2c, REG_CTRL, REG_CTRL_CLKDIVEXT_MASK,
- (div >> 10) << REG_CTRL_CLKDIVEXT_SHIFT);
+ /* Disable HIGH/LOW mode */
+ meson_i2c_set_mask(i2c, REG_SLAVE_ADDR, REG_SLV_SCL_LOW_EN, 0);

dev_dbg(i2c->dev, "%s: clk %lu, freq %u, div %u\n", __func__,
clk_rate, freq, div);
@@ -280,7 +291,10 @@ static void meson_i2c_do_start(struct meson_i2c *i2c, struct i2c_msg *msg)
token = (msg->flags & I2C_M_RD) ? TOKEN_SLAVE_ADDR_READ :
TOKEN_SLAVE_ADDR_WRITE;

- writel(msg->addr << 1, i2c->regs + REG_SLAVE_ADDR);
+
+ meson_i2c_set_mask(i2c, REG_SLAVE_ADDR, REG_SLV_ADDR,
+ FIELD_PREP(REG_SLV_ADDR, msg->addr << 1));
+
meson_i2c_add_token(i2c, TOKEN_START);
meson_i2c_add_token(i2c, token);
}
@@ -357,16 +371,12 @@ static int meson_i2c_xfer_messages(struct i2c_adapter *adap,
struct meson_i2c *i2c = adap->algo_data;
int i, ret = 0;

- clk_enable(i2c->clk);
-
for (i = 0; i < num; i++) {
ret = meson_i2c_xfer_msg(i2c, msgs + i, i == num - 1, atomic);
if (ret)
break;
}

- clk_disable(i2c->clk);
-
return ret ?: i;
}

@@ -435,7 +445,7 @@ static int meson_i2c_probe(struct platform_device *pdev)
return ret;
}

- ret = clk_prepare(i2c->clk);
+ ret = clk_prepare_enable(i2c->clk);
if (ret < 0) {
dev_err(&pdev->dev, "can't prepare clock\n");
return ret;
@@ -457,10 +467,14 @@ static int meson_i2c_probe(struct platform_device *pdev)

ret = i2c_add_adapter(&i2c->adap);
if (ret < 0) {
- clk_unprepare(i2c->clk);
+ clk_disable_unprepare(i2c->clk);
return ret;
}

+ /* Disable filtering */
+ meson_i2c_set_mask(i2c, REG_SLAVE_ADDR,
+ REG_SLV_SDA_FILTER | REG_SLV_SCL_FILTER, 0);
+
meson_i2c_set_clk_div(i2c, timings.bus_freq_hz);

return 0;
@@ -471,7 +485,7 @@ static int meson_i2c_remove(struct platform_device *pdev)
struct meson_i2c *i2c = platform_get_drvdata(pdev);

i2c_del_adapter(&i2c->adap);
- clk_unprepare(i2c->clk);
+ clk_disable_unprepare(i2c->clk);

return 0;
}
diff --git a/drivers/i2c/busses/i2c-owl.c b/drivers/i2c/busses/i2c-owl.c
index 672f1f239bd6..a163b8f308c1 100644
--- a/drivers/i2c/busses/i2c-owl.c
+++ b/drivers/i2c/busses/i2c-owl.c
@@ -176,6 +176,9 @@ static irqreturn_t owl_i2c_interrupt(int irq, void *_dev)
fifostat = readl(i2c_dev->base + OWL_I2C_REG_FIFOSTAT);
if (fifostat & OWL_I2C_FIFOSTAT_RNB) {
i2c_dev->err = -ENXIO;
+ /* Clear NACK error bit by writing "1" */
+ owl_i2c_update_reg(i2c_dev->base + OWL_I2C_REG_FIFOSTAT,
+ OWL_I2C_FIFOSTAT_RNB, true);
goto stop;
}

@@ -183,6 +186,9 @@ static irqreturn_t owl_i2c_interrupt(int irq, void *_dev)
stat = readl(i2c_dev->base + OWL_I2C_REG_STAT);
if (stat & OWL_I2C_STAT_BEB) {
i2c_dev->err = -EIO;
+ /* Clear BUS error bit by writing "1" */
+ owl_i2c_update_reg(i2c_dev->base + OWL_I2C_REG_STAT,
+ OWL_I2C_STAT_BEB, true);
goto stop;
}

diff --git a/drivers/input/misc/ati_remote2.c b/drivers/input/misc/ati_remote2.c
index 305f0160506a..8a36d78fed63 100644
--- a/drivers/input/misc/ati_remote2.c
+++ b/drivers/input/misc/ati_remote2.c
@@ -68,7 +68,7 @@ static int ati_remote2_get_channel_mask(char *buffer,
{
pr_debug("%s()\n", __func__);

- return sprintf(buffer, "0x%04x", *(unsigned int *)kp->arg);
+ return sprintf(buffer, "0x%04x\n", *(unsigned int *)kp->arg);
}

static int ati_remote2_set_mode_mask(const char *val,
@@ -84,7 +84,7 @@ static int ati_remote2_get_mode_mask(char *buffer,
{
pr_debug("%s()\n", __func__);

- return sprintf(buffer, "0x%02x", *(unsigned int *)kp->arg);
+ return sprintf(buffer, "0x%02x\n", *(unsigned int *)kp->arg);
}

static unsigned int channel_mask = ATI_REMOTE2_MAX_CHANNEL_MASK;
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index fbe0b0cc56ed..24a84d294fd0 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -2617,7 +2617,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
}

/* Setup the PASID entry for requests without PASID: */
- spin_lock(&iommu->lock);
+ spin_lock_irqsave(&iommu->lock, flags);
if (hw_pass_through && domain_type_is_si(domain))
ret = intel_pasid_setup_pass_through(iommu, domain,
dev, PASID_RID2PASID);
@@ -2627,7 +2627,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
else
ret = intel_pasid_setup_second_level(iommu, domain,
dev, PASID_RID2PASID);
- spin_unlock(&iommu->lock);
+ spin_unlock_irqrestore(&iommu->lock, flags);
if (ret) {
dev_err(dev, "Setup RID2PASID failed\n");
dmar_remove_one_dev_info(dev);
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index 4b1eb89b401d..1ad518821157 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -190,7 +190,7 @@ static void mmc_queue_setup_discard(struct request_queue *q,
q->limits.discard_granularity = card->pref_erase << 9;
/* granularity must not be greater than max. discard */
if (card->pref_erase > max_discard)
- q->limits.discard_granularity = 0;
+ q->limits.discard_granularity = SECTOR_SIZE;
if (mmc_can_secure_erase_trim(card))
blk_queue_flag_set(QUEUE_FLAG_SECERASE, q);
}
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 500aa3e19a4c..fddf7c502355 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1195,6 +1195,7 @@ static void bond_setup_by_slave(struct net_device *bond_dev,

bond_dev->type = slave_dev->type;
bond_dev->hard_header_len = slave_dev->hard_header_len;
+ bond_dev->needed_headroom = slave_dev->needed_headroom;
bond_dev->addr_len = slave_dev->addr_len;

memcpy(bond_dev->broadcast, slave_dev->broadcast,
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index 7c167a394b76..259a612da003 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -1105,8 +1105,21 @@ static int vsc9959_prevalidate_phy_mode(struct ocelot *ocelot, int port,
}
}

+/* Watermark encode
+ * Bit 8: Unit; 0:1, 1:16
+ * Bit 7-0: Value to be multiplied with unit
+ */
+static u16 vsc9959_wm_enc(u16 value)
+{
+ if (value >= BIT(8))
+ return BIT(8) | (value / 16);
+
+ return value;
+}
+
static const struct ocelot_ops vsc9959_ops = {
.reset = vsc9959_reset,
+ .wm_enc = vsc9959_wm_enc,
};

static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot)
@@ -1215,8 +1228,28 @@ static void vsc9959_mdio_bus_free(struct ocelot *ocelot)
static void vsc9959_sched_speed_set(struct ocelot *ocelot, int port,
u32 speed)
{
+ u8 tas_speed;
+
+ switch (speed) {
+ case SPEED_10:
+ tas_speed = OCELOT_SPEED_10;
+ break;
+ case SPEED_100:
+ tas_speed = OCELOT_SPEED_100;
+ break;
+ case SPEED_1000:
+ tas_speed = OCELOT_SPEED_1000;
+ break;
+ case SPEED_2500:
+ tas_speed = OCELOT_SPEED_2500;
+ break;
+ default:
+ tas_speed = OCELOT_SPEED_1000;
+ break;
+ }
+
ocelot_rmw_rix(ocelot,
- QSYS_TAG_CONFIG_LINK_SPEED(speed),
+ QSYS_TAG_CONFIG_LINK_SPEED(tas_speed),
QSYS_TAG_CONFIG_LINK_SPEED_M,
QSYS_TAG_CONFIG, port);
}
diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
index cbaa1924afbe..706e959bf02a 100644
--- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
+++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
@@ -1219,7 +1219,7 @@ static int octeon_mgmt_open(struct net_device *netdev)
*/
if (netdev->phydev) {
netif_carrier_off(netdev);
- phy_start_aneg(netdev->phydev);
+ phy_start(netdev->phydev);
}

netif_wake_queue(netdev);
@@ -1247,8 +1247,10 @@ static int octeon_mgmt_stop(struct net_device *netdev)
napi_disable(&p->napi);
netif_stop_queue(netdev);

- if (netdev->phydev)
+ if (netdev->phydev) {
+ phy_stop(netdev->phydev);
phy_disconnect(netdev->phydev);
+ }

netif_carrier_off(netdev);

diff --git a/drivers/net/ethernet/huawei/hinic/Kconfig b/drivers/net/ethernet/huawei/hinic/Kconfig
index 936e2dd3bb13..b47bd5440c5f 100644
--- a/drivers/net/ethernet/huawei/hinic/Kconfig
+++ b/drivers/net/ethernet/huawei/hinic/Kconfig
@@ -6,6 +6,7 @@
config HINIC
tristate "Huawei Intelligent PCIE Network Interface Card"
depends on (PCI_MSI && (X86 || ARM64))
+ select NET_DEVLINK
help
This driver supports HiNIC PCIE Ethernet cards.
To compile this driver as part of the kernel, choose Y here.
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c
index 583fd24c29cf..29e88e25a4a4 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c
@@ -112,6 +112,26 @@ static u32 get_hw_cons_idx(struct hinic_api_cmd_chain *chain)
return HINIC_API_CMD_STATUS_GET(val, CONS_IDX);
}

+static void dump_api_chain_reg(struct hinic_api_cmd_chain *chain)
+{
+ u32 addr, val;
+
+ addr = HINIC_CSR_API_CMD_STATUS_ADDR(chain->chain_type);
+ val = hinic_hwif_read_reg(chain->hwif, addr);
+
+ dev_err(&chain->hwif->pdev->dev, "Chain type: 0x%x, cpld error: 0x%x, check error: 0x%x, current fsm: 0x%x\n",
+ chain->chain_type, HINIC_API_CMD_STATUS_GET(val, CPLD_ERR),
+ HINIC_API_CMD_STATUS_GET(val, CHKSUM_ERR),
+ HINIC_API_CMD_STATUS_GET(val, FSM));
+
+ dev_err(&chain->hwif->pdev->dev, "Chain hw current ci: 0x%x\n",
+ HINIC_API_CMD_STATUS_GET(val, CONS_IDX));
+
+ addr = HINIC_CSR_API_CMD_CHAIN_PI_ADDR(chain->chain_type);
+ val = hinic_hwif_read_reg(chain->hwif, addr);
+ dev_err(&chain->hwif->pdev->dev, "Chain hw current pi: 0x%x\n", val);
+}
+
/**
* chain_busy - check if the chain is still processing last requests
* @chain: chain to check
@@ -131,8 +151,10 @@ static int chain_busy(struct hinic_api_cmd_chain *chain)

/* check for a space for a new command */
if (chain->cons_idx == MASKED_IDX(chain, prod_idx + 1)) {
- dev_err(&pdev->dev, "API CMD chain %d is busy\n",
- chain->chain_type);
+ dev_err(&pdev->dev, "API CMD chain %d is busy, cons_idx: %d, prod_idx: %d\n",
+ chain->chain_type, chain->cons_idx,
+ chain->prod_idx);
+ dump_api_chain_reg(chain);
return -EBUSY;
}
break;
@@ -332,6 +354,7 @@ static int wait_for_api_cmd_completion(struct hinic_api_cmd_chain *chain)
err = wait_for_status_poll(chain);
if (err) {
dev_err(&pdev->dev, "API CMD Poll status timeout\n");
+ dump_api_chain_reg(chain);
break;
}
break;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h
index 0ba00fd828df..6d1654b050ad 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h
@@ -103,10 +103,14 @@
HINIC_API_CMD_STATUS_HEADER_##member##_MASK)

#define HINIC_API_CMD_STATUS_CONS_IDX_SHIFT 0
+#define HINIC_API_CMD_STATUS_FSM_SHIFT 24
#define HINIC_API_CMD_STATUS_CHKSUM_ERR_SHIFT 28
+#define HINIC_API_CMD_STATUS_CPLD_ERR_SHIFT 30

#define HINIC_API_CMD_STATUS_CONS_IDX_MASK 0xFFFFFF
+#define HINIC_API_CMD_STATUS_FSM_MASK 0xFU
#define HINIC_API_CMD_STATUS_CHKSUM_ERR_MASK 0x3
+#define HINIC_API_CMD_STATUS_CPLD_ERR_MASK 0x1U

#define HINIC_API_CMD_STATUS_GET(val, member) \
(((val) >> HINIC_API_CMD_STATUS_##member##_SHIFT) & \
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
index cb5b6e5f787f..e0eb294779ec 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
@@ -401,6 +401,7 @@ static int cmdq_sync_cmd_direct_resp(struct hinic_cmdq *cmdq,

spin_unlock_bh(&cmdq->cmdq_lock);

+ hinic_dump_ceq_info(cmdq->hwdev);
return -ETIMEDOUT;
}

@@ -807,6 +808,7 @@ static int init_cmdqs_ctxt(struct hinic_hwdev *hwdev,

cmdq_type = HINIC_CMDQ_SYNC;
for (; cmdq_type < HINIC_MAX_CMDQ_TYPES; cmdq_type++) {
+ cmdqs->cmdq[cmdq_type].hwdev = hwdev;
err = init_cmdq(&cmdqs->cmdq[cmdq_type],
&cmdqs->saved_wqs[cmdq_type], cmdq_type,
db_area[cmdq_type]);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h
index 3e4b0aef9fe6..f40c31e1879f 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h
@@ -130,6 +130,8 @@ struct hinic_cmdq_ctxt {
};

struct hinic_cmdq {
+ struct hinic_hwdev *hwdev;
+
struct hinic_wq *wq;

enum hinic_cmdq_type cmdq_type;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
index b735bc537508..298ceb930cc6 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
@@ -253,9 +253,9 @@ static int init_fw_ctxt(struct hinic_hwdev *hwdev)
&fw_ctxt, sizeof(fw_ctxt),
&fw_ctxt, &out_size);
if (err || (out_size != sizeof(fw_ctxt)) || fw_ctxt.status) {
- dev_err(&pdev->dev, "Failed to init FW ctxt, ret = %d\n",
- fw_ctxt.status);
- return -EFAULT;
+ dev_err(&pdev->dev, "Failed to init FW ctxt, err: %d, status: 0x%x, out size: 0x%x\n",
+ err, fw_ctxt.status, out_size);
+ return -EIO;
}

return 0;
@@ -420,9 +420,9 @@ static int get_base_qpn(struct hinic_hwdev *hwdev, u16 *base_qpn)
&cmd_base_qpn, sizeof(cmd_base_qpn),
&cmd_base_qpn, &out_size);
if (err || (out_size != sizeof(cmd_base_qpn)) || cmd_base_qpn.status) {
- dev_err(&pdev->dev, "Failed to get base qpn, status = %d\n",
- cmd_base_qpn.status);
- return -EFAULT;
+ dev_err(&pdev->dev, "Failed to get base qpn, err: %d, status: 0x%x, out size: 0x%x\n",
+ err, cmd_base_qpn.status, out_size);
+ return -EIO;
}

*base_qpn = cmd_base_qpn.qpn;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
index 397936cac304..ca8cb68a8d20 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
@@ -953,3 +953,42 @@ void hinic_ceqs_free(struct hinic_ceqs *ceqs)
for (q_id = 0; q_id < ceqs->num_ceqs; q_id++)
remove_eq(&ceqs->ceq[q_id]);
}
+
+void hinic_dump_ceq_info(struct hinic_hwdev *hwdev)
+{
+ struct hinic_eq *eq = NULL;
+ u32 addr, ci, pi;
+ int q_id;
+
+ for (q_id = 0; q_id < hwdev->func_to_io.ceqs.num_ceqs; q_id++) {
+ eq = &hwdev->func_to_io.ceqs.ceq[q_id];
+ addr = EQ_CONS_IDX_REG_ADDR(eq);
+ ci = hinic_hwif_read_reg(hwdev->hwif, addr);
+ addr = EQ_PROD_IDX_REG_ADDR(eq);
+ pi = hinic_hwif_read_reg(hwdev->hwif, addr);
+ dev_err(&hwdev->hwif->pdev->dev, "Ceq id: %d, ci: 0x%08x, sw_ci: 0x%08x, pi: 0x%x, tasklet_state: 0x%lx, wrap: %d, ceqe: 0x%x\n",
+ q_id, ci, eq->cons_idx, pi,
+ eq->ceq_tasklet.state,
+ eq->wrapped, be32_to_cpu(*(__be32 *)(GET_CURR_CEQ_ELEM(eq))));
+ }
+}
+
+void hinic_dump_aeq_info(struct hinic_hwdev *hwdev)
+{
+ struct hinic_aeq_elem *aeqe_pos = NULL;
+ struct hinic_eq *eq = NULL;
+ u32 addr, ci, pi;
+ int q_id;
+
+ for (q_id = 0; q_id < hwdev->aeqs.num_aeqs; q_id++) {
+ eq = &hwdev->aeqs.aeq[q_id];
+ addr = EQ_CONS_IDX_REG_ADDR(eq);
+ ci = hinic_hwif_read_reg(hwdev->hwif, addr);
+ addr = EQ_PROD_IDX_REG_ADDR(eq);
+ pi = hinic_hwif_read_reg(hwdev->hwif, addr);
+ aeqe_pos = GET_CURR_AEQ_ELEM(eq);
+ dev_err(&hwdev->hwif->pdev->dev, "Aeq id: %d, ci: 0x%08x, pi: 0x%x, work_state: 0x%x, wrap: %d, desc: 0x%x\n",
+ q_id, ci, pi, work_busy(&eq->aeq_work.work),
+ eq->wrapped, be32_to_cpu(aeqe_pos->desc));
+ }
+}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h
index 74b9ff90640c..43065fc70869 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h
@@ -162,7 +162,7 @@ enum hinic_eqe_state {

struct hinic_aeq_elem {
u8 data[HINIC_AEQE_DATA_SIZE];
- u32 desc;
+ __be32 desc;
};

struct hinic_eq_work {
@@ -254,4 +254,8 @@ int hinic_ceqs_init(struct hinic_ceqs *ceqs, struct hinic_hwif *hwif,

void hinic_ceqs_free(struct hinic_ceqs *ceqs);

+void hinic_dump_ceq_info(struct hinic_hwdev *hwdev);
+
+void hinic_dump_aeq_info(struct hinic_hwdev *hwdev);
+
#endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
index cf127d896ba6..bc8925c0c982 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
@@ -21,6 +21,8 @@

#define WAIT_HWIF_READY_TIMEOUT 10000

+#define HINIC_SELFTEST_RESULT 0x883C
+
/**
* hinic_msix_attr_set - set message attribute for msix entry
* @hwif: the HW interface of a pci function device
@@ -369,6 +371,26 @@ u16 hinic_pf_id_of_vf_hw(struct hinic_hwif *hwif)
return HINIC_FA0_GET(attr0, PF_IDX);
}

+static void __print_selftest_reg(struct hinic_hwif *hwif)
+{
+ u32 addr, attr0, attr1;
+
+ addr = HINIC_CSR_FUNC_ATTR1_ADDR;
+ attr1 = hinic_hwif_read_reg(hwif, addr);
+
+ if (attr1 == HINIC_PCIE_LINK_DOWN) {
+ dev_err(&hwif->pdev->dev, "PCIE is link down\n");
+ return;
+ }
+
+ addr = HINIC_CSR_FUNC_ATTR0_ADDR;
+ attr0 = hinic_hwif_read_reg(hwif, addr);
+ if (HINIC_FA0_GET(attr0, FUNC_TYPE) != HINIC_VF &&
+ !HINIC_FA0_GET(attr0, PCI_INTF_IDX))
+ dev_err(&hwif->pdev->dev, "Selftest reg: 0x%08x\n",
+ hinic_hwif_read_reg(hwif, HINIC_SELFTEST_RESULT));
+}
+
/**
* hinic_init_hwif - initialize the hw interface
* @hwif: the HW interface of a pci function device
@@ -398,6 +420,7 @@ int hinic_init_hwif(struct hinic_hwif *hwif, struct pci_dev *pdev)
err = wait_hwif_ready(hwif);
if (err) {
dev_err(&pdev->dev, "HW interface is not ready\n");
+ __print_selftest_reg(hwif);
goto err_hwif_ready;
}

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
index 0872e035faa1..c06f2253151e 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
@@ -12,6 +12,8 @@
#include <linux/types.h>
#include <asm/byteorder.h>

+#define HINIC_PCIE_LINK_DOWN 0xFFFFFFFF
+
#define HINIC_DMA_ATTR_ST_SHIFT 0
#define HINIC_DMA_ATTR_AT_SHIFT 8
#define HINIC_DMA_ATTR_PH_SHIFT 10
@@ -249,13 +251,17 @@ struct hinic_hwif {

static inline u32 hinic_hwif_read_reg(struct hinic_hwif *hwif, u32 reg)
{
- return be32_to_cpu(readl(hwif->cfg_regs_bar + reg));
+ u32 out = readl(hwif->cfg_regs_bar + reg);
+
+ return be32_to_cpu(*(__be32 *)&out);
}

static inline void hinic_hwif_write_reg(struct hinic_hwif *hwif, u32 reg,
u32 val)
{
- writel(cpu_to_be32(val), hwif->cfg_regs_bar + reg);
+ __be32 in = cpu_to_be32(val);
+
+ writel(*(u32 *)&in, hwif->cfg_regs_bar + reg);
}

int hinic_msix_attr_set(struct hinic_hwif *hwif, u16 msix_index,
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c
index bc2f87e6cb5d..47c93f946b94 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c
@@ -650,6 +650,7 @@ wait_for_mbox_seg_completion(struct hinic_mbox_func_to_func *func_to_func,
if (!wait_for_completion_timeout(done, jif)) {
dev_err(&hwdev->hwif->pdev->dev, "Send mailbox segment timeout\n");
dump_mox_reg(hwdev);
+ hinic_dump_aeq_info(hwdev);
return -ETIMEDOUT;
}

@@ -897,6 +898,7 @@ int hinic_mbox_to_func(struct hinic_mbox_func_to_func *func_to_func,
set_mbox_to_func_event(func_to_func, EVENT_TIMEOUT);
dev_err(&func_to_func->hwif->pdev->dev,
"Send mbox msg timeout, msg_id: %d\n", msg_info.msg_id);
+ hinic_dump_aeq_info(func_to_func->hwdev);
err = -ETIMEDOUT;
goto err_send_mbox;
}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
index 7fe39a155b32..070288c8b4f3 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
@@ -276,6 +276,7 @@ static int msg_to_mgmt_sync(struct hinic_pf_to_mgmt *pf_to_mgmt,

if (!wait_for_completion_timeout(recv_done, timeo)) {
dev_err(&pdev->dev, "MGMT timeout, MSG id = %d\n", msg_id);
+ hinic_dump_aeq_info(pf_to_mgmt->hwdev);
err = -ETIMEDOUT;
goto unlock_sync_msg;
}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c
index 175c0ee00038..2be7c254cca9 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_port.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c
@@ -58,11 +58,11 @@ static int change_mac(struct hinic_dev *nic_dev, const u8 *addr,
sizeof(port_mac_cmd),
&port_mac_cmd, &out_size);
if (err || out_size != sizeof(port_mac_cmd) ||
- (port_mac_cmd.status &&
- port_mac_cmd.status != HINIC_PF_SET_VF_ALREADY &&
- port_mac_cmd.status != HINIC_MGMT_STATUS_EXIST)) {
- dev_err(&pdev->dev, "Failed to change MAC, ret = %d\n",
- port_mac_cmd.status);
+ (port_mac_cmd.status &&
+ (port_mac_cmd.status != HINIC_PF_SET_VF_ALREADY || !HINIC_IS_VF(hwif)) &&
+ port_mac_cmd.status != HINIC_MGMT_STATUS_EXIST)) {
+ dev_err(&pdev->dev, "Failed to change MAC, err: %d, status: 0x%x, out size: 0x%x\n",
+ err, port_mac_cmd.status, out_size);
return -EFAULT;
}

@@ -129,8 +129,8 @@ int hinic_port_get_mac(struct hinic_dev *nic_dev, u8 *addr)
&port_mac_cmd, sizeof(port_mac_cmd),
&port_mac_cmd, &out_size);
if (err || (out_size != sizeof(port_mac_cmd)) || port_mac_cmd.status) {
- dev_err(&pdev->dev, "Failed to get mac, ret = %d\n",
- port_mac_cmd.status);
+ dev_err(&pdev->dev, "Failed to get mac, err: %d, status: 0x%x, out size: 0x%x\n",
+ err, port_mac_cmd.status, out_size);
return -EFAULT;
}

@@ -172,9 +172,9 @@ int hinic_port_set_mtu(struct hinic_dev *nic_dev, int new_mtu)
err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_CHANGE_MTU,
&port_mtu_cmd, sizeof(port_mtu_cmd),
&port_mtu_cmd, &out_size);
- if (err || (out_size != sizeof(port_mtu_cmd)) || port_mtu_cmd.status) {
- dev_err(&pdev->dev, "Failed to set mtu, ret = %d\n",
- port_mtu_cmd.status);
+ if (err || out_size != sizeof(port_mtu_cmd) || port_mtu_cmd.status) {
+ dev_err(&pdev->dev, "Failed to set mtu, err: %d, status: 0x%x, out size: 0x%x\n",
+ err, port_mtu_cmd.status, out_size);
return -EFAULT;
}

@@ -264,8 +264,8 @@ int hinic_port_link_state(struct hinic_dev *nic_dev,
&link_cmd, sizeof(link_cmd),
&link_cmd, &out_size);
if (err || (out_size != sizeof(link_cmd)) || link_cmd.status) {
- dev_err(&pdev->dev, "Failed to get link state, ret = %d\n",
- link_cmd.status);
+ dev_err(&pdev->dev, "Failed to get link state, err: %d, status: 0x%x, out size: 0x%x\n",
+ err, link_cmd.status, out_size);
return -EINVAL;
}

@@ -298,8 +298,8 @@ int hinic_port_set_state(struct hinic_dev *nic_dev, enum hinic_port_state state)
&port_state, sizeof(port_state),
&port_state, &out_size);
if (err || (out_size != sizeof(port_state)) || port_state.status) {
- dev_err(&pdev->dev, "Failed to set port state, ret = %d\n",
- port_state.status);
+ dev_err(&pdev->dev, "Failed to set port state, err: %d, status: 0x%x, out size: 0x%x\n",
+ err, port_state.status, out_size);
return -EFAULT;
}

@@ -330,8 +330,8 @@ int hinic_port_set_func_state(struct hinic_dev *nic_dev,
&func_state, sizeof(func_state),
&func_state, &out_size);
if (err || (out_size != sizeof(func_state)) || func_state.status) {
- dev_err(&pdev->dev, "Failed to set port func state, ret = %d\n",
- func_state.status);
+ dev_err(&pdev->dev, "Failed to set port func state, err: %d, status: 0x%x, out size: 0x%x\n",
+ err, func_state.status, out_size);
return -EFAULT;
}

@@ -361,9 +361,9 @@ int hinic_port_get_cap(struct hinic_dev *nic_dev,
port_cap, &out_size);
if (err || (out_size != sizeof(*port_cap)) || port_cap->status) {
dev_err(&pdev->dev,
- "Failed to get port capabilities, ret = %d\n",
- port_cap->status);
- return -EINVAL;
+ "Failed to get port capabilities, err: %d, status: 0x%x, out size: 0x%x\n",
+ err, port_cap->status, out_size);
+ return -EIO;
}

return 0;
@@ -393,9 +393,9 @@ int hinic_port_set_tso(struct hinic_dev *nic_dev, enum hinic_tso_state state)
&tso_cfg, &out_size);
if (err || out_size != sizeof(tso_cfg) || tso_cfg.status) {
dev_err(&pdev->dev,
- "Failed to set port tso, ret = %d\n",
- tso_cfg.status);
- return -EINVAL;
+ "Failed to set port tso, err: %d, status: 0x%x, out size: 0x%x\n",
+ err, tso_cfg.status, out_size);
+ return -EIO;
}

return 0;
@@ -423,9 +423,9 @@ int hinic_set_rx_csum_offload(struct hinic_dev *nic_dev, u32 en)
&rx_csum_cfg, &out_size);
if (err || !out_size || rx_csum_cfg.status) {
dev_err(&pdev->dev,
- "Failed to set rx csum offload, ret = %d\n",
- rx_csum_cfg.status);
- return -EINVAL;
+ "Failed to set rx csum offload, err: %d, status: 0x%x, out size: 0x%x\n",
+ err, rx_csum_cfg.status, out_size);
+ return -EIO;
}

return 0;
@@ -480,9 +480,9 @@ int hinic_set_max_qnum(struct hinic_dev *nic_dev, u8 num_rqs)
&rq_num, &out_size);
if (err || !out_size || rq_num.status) {
dev_err(&pdev->dev,
- "Failed to rxq number, ret = %d\n",
- rq_num.status);
- return -EINVAL;
+ "Failed to set rxq number, err: %d, status: 0x%x, out size: 0x%x\n",
+ err, rq_num.status, out_size);
+ return -EIO;
}

return 0;
@@ -508,9 +508,9 @@ static int hinic_set_rx_lro(struct hinic_dev *nic_dev, u8 ipv4_en, u8 ipv6_en,
&lro_cfg, &out_size);
if (err || !out_size || lro_cfg.status) {
dev_err(&pdev->dev,
- "Failed to set lro offload, ret = %d\n",
- lro_cfg.status);
- return -EINVAL;
+ "Failed to set lro offload, err: %d, status: 0x%x, out size: 0x%x\n",
+ err, lro_cfg.status, out_size);
+ return -EIO;
}

return 0;
@@ -542,10 +542,10 @@ static int hinic_set_rx_lro_timer(struct hinic_dev *nic_dev, u32 timer_value)

if (err || !out_size || lro_timer.status) {
dev_err(&pdev->dev,
- "Failed to set lro timer, ret = %d\n",
- lro_timer.status);
+ "Failed to set lro timer, err: %d, status: 0x%x, out size: 0x%x\n",
+ err, lro_timer.status, out_size);

- return -EINVAL;
+ return -EIO;
}

return 0;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
index efab2dd2c889..b757f7057b8f 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
@@ -38,11 +38,10 @@ static int hinic_set_mac(struct hinic_hwdev *hwdev, const u8 *mac_addr,
err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_MAC, &mac_info,
sizeof(mac_info), &mac_info, &out_size);
if (err || out_size != sizeof(mac_info) ||
- (mac_info.status && mac_info.status != HINIC_PF_SET_VF_ALREADY &&
- mac_info.status != HINIC_MGMT_STATUS_EXIST)) {
- dev_err(&hwdev->func_to_io.hwif->pdev->dev, "Failed to change MAC, ret = %d\n",
- mac_info.status);
- return -EFAULT;
+ (mac_info.status && mac_info.status != HINIC_MGMT_STATUS_EXIST)) {
+ dev_err(&hwdev->func_to_io.hwif->pdev->dev, "Failed to set MAC, err: %d, status: 0x%x, out size: 0x%x\n",
+ err, mac_info.status, out_size);
+ return -EIO;
}

return 0;
@@ -452,8 +451,7 @@ struct hinic_sriov_info *hinic_get_sriov_info_by_pcidev(struct pci_dev *pdev)

static int hinic_check_mac_info(u8 status, u16 vlan_id)
{
- if ((status && status != HINIC_MGMT_STATUS_EXIST &&
- status != HINIC_PF_SET_VF_ALREADY) ||
+ if ((status && status != HINIC_MGMT_STATUS_EXIST) ||
(vlan_id & CHECK_IPSU_15BIT &&
status == HINIC_MGMT_STATUS_EXIST))
return -EINVAL;
@@ -495,12 +493,6 @@ static int hinic_update_mac(struct hinic_hwdev *hwdev, u8 *old_mac,
return -EINVAL;
}

- if (mac_info.status == HINIC_PF_SET_VF_ALREADY) {
- dev_warn(&hwdev->hwif->pdev->dev,
- "PF has already set VF MAC. Ignore update operation\n");
- return HINIC_PF_SET_VF_ALREADY;
- }
-
if (mac_info.status == HINIC_MGMT_STATUS_EXIST)
dev_warn(&hwdev->hwif->pdev->dev, "MAC is repeated. Ignore update operation\n");

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index d338efe5f3f5..91343e2d3a14 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -3777,7 +3777,6 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
return err;
}

-#ifdef CONFIG_PM
/**
* iavf_suspend - Power management suspend routine
* @pdev: PCI device information struct
@@ -3785,11 +3784,10 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
*
* Called when the system (VM) is entering sleep/suspend.
**/
-static int iavf_suspend(struct pci_dev *pdev, pm_message_t state)
+static int __maybe_unused iavf_suspend(struct device *dev_d)
{
- struct net_device *netdev = pci_get_drvdata(pdev);
+ struct net_device *netdev = dev_get_drvdata(dev_d);
struct iavf_adapter *adapter = netdev_priv(netdev);
- int retval = 0;

netif_device_detach(netdev);

@@ -3807,12 +3805,6 @@ static int iavf_suspend(struct pci_dev *pdev, pm_message_t state)

clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);

- retval = pci_save_state(pdev);
- if (retval)
- return retval;
-
- pci_disable_device(pdev);
-
return 0;
}

@@ -3822,24 +3814,13 @@ static int iavf_suspend(struct pci_dev *pdev, pm_message_t state)
*
* Called when the system (VM) is resumed from sleep/suspend.
**/
-static int iavf_resume(struct pci_dev *pdev)
+static int __maybe_unused iavf_resume(struct device *dev_d)
{
- struct iavf_adapter *adapter = pci_get_drvdata(pdev);
- struct net_device *netdev = adapter->netdev;
+ struct pci_dev *pdev = to_pci_dev(dev_d);
+ struct net_device *netdev = pci_get_drvdata(pdev);
+ struct iavf_adapter *adapter = netdev_priv(netdev);
u32 err;

- pci_set_power_state(pdev, PCI_D0);
- pci_restore_state(pdev);
- /* pci_restore_state clears dev->state_saved so call
- * pci_save_state to restore it.
- */
- pci_save_state(pdev);
-
- err = pci_enable_device_mem(pdev);
- if (err) {
- dev_err(&pdev->dev, "Cannot enable PCI device from suspend.\n");
- return err;
- }
pci_set_master(pdev);

rtnl_lock();
@@ -3863,7 +3844,6 @@ static int iavf_resume(struct pci_dev *pdev)
return err;
}

-#endif /* CONFIG_PM */
/**
* iavf_remove - Device Removal Routine
* @pdev: PCI device information struct
@@ -3965,16 +3945,15 @@ static void iavf_remove(struct pci_dev *pdev)
pci_disable_device(pdev);
}

+static SIMPLE_DEV_PM_OPS(iavf_pm_ops, iavf_suspend, iavf_resume);
+
static struct pci_driver iavf_driver = {
- .name = iavf_driver_name,
- .id_table = iavf_pci_tbl,
- .probe = iavf_probe,
- .remove = iavf_remove,
-#ifdef CONFIG_PM
- .suspend = iavf_suspend,
- .resume = iavf_resume,
-#endif
- .shutdown = iavf_shutdown,
+ .name = iavf_driver_name,
+ .id_table = iavf_pci_tbl,
+ .probe = iavf_probe,
+ .remove = iavf_remove,
+ .driver.pm = &iavf_pm_ops,
+ .shutdown = iavf_shutdown,
};

/**
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 2e3a39cea2c0..4c5845a0965a 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -240,7 +240,7 @@ static int ice_get_free_slot(void *array, int size, int curr)
* ice_vsi_delete - delete a VSI from the switch
* @vsi: pointer to VSI being removed
*/
-void ice_vsi_delete(struct ice_vsi *vsi)
+static void ice_vsi_delete(struct ice_vsi *vsi)
{
struct ice_pf *pf = vsi->back;
struct ice_vsi_ctx *ctxt;
@@ -307,7 +307,7 @@ static void ice_vsi_free_arrays(struct ice_vsi *vsi)
*
* Returns 0 on success, negative on failure
*/
-int ice_vsi_clear(struct ice_vsi *vsi)
+static int ice_vsi_clear(struct ice_vsi *vsi)
{
struct ice_pf *pf = NULL;
struct device *dev;
@@ -557,7 +557,7 @@ static int ice_vsi_get_qs(struct ice_vsi *vsi)
* ice_vsi_put_qs - Release queues from VSI to PF
* @vsi: the VSI that is going to release queues
*/
-void ice_vsi_put_qs(struct ice_vsi *vsi)
+static void ice_vsi_put_qs(struct ice_vsi *vsi)
{
struct ice_pf *pf = vsi->back;
int i;
@@ -1190,6 +1190,18 @@ static void ice_vsi_clear_rings(struct ice_vsi *vsi)
{
int i;

+ /* Avoid stale references by clearing map from vector to ring */
+ if (vsi->q_vectors) {
+ ice_for_each_q_vector(vsi, i) {
+ struct ice_q_vector *q_vector = vsi->q_vectors[i];
+
+ if (q_vector) {
+ q_vector->tx.ring = NULL;
+ q_vector->rx.ring = NULL;
+ }
+ }
+ }
+
if (vsi->tx_rings) {
for (i = 0; i < vsi->alloc_txq; i++) {
if (vsi->tx_rings[i]) {
@@ -2254,7 +2266,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
if (status) {
dev_err(dev, "VSI %d failed lan queue config, error %s\n",
vsi->vsi_num, ice_stat_str(status));
- goto unroll_vector_base;
+ goto unroll_clear_rings;
}

/* Add switch rule to drop all Tx Flow Control Frames, of look up
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index d80e6afa4511..2954b30e6ec7 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -43,10 +43,6 @@ int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena, bool vlan_promisc);

void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create);

-void ice_vsi_delete(struct ice_vsi *vsi);
-
-int ice_vsi_clear(struct ice_vsi *vsi);
-
#ifdef CONFIG_DCB
int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc);
#endif /* CONFIG_DCB */
@@ -77,8 +73,6 @@ bool ice_is_reset_in_progress(unsigned long *state);
void
ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio);

-void ice_vsi_put_qs(struct ice_vsi *vsi);
-
void ice_vsi_dis_irq(struct ice_vsi *vsi);

void ice_vsi_free_irq(struct ice_vsi *vsi);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 4cbd49c87568..4b52f1dea7f3 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2605,10 +2605,8 @@ static int ice_setup_pf_sw(struct ice_pf *pf)
return -EBUSY;

vsi = ice_pf_vsi_setup(pf, pf->hw.port_info);
- if (!vsi) {
- status = -ENOMEM;
- goto unroll_vsi_setup;
- }
+ if (!vsi)
+ return -ENOMEM;

status = ice_cfg_netdev(vsi);
if (status) {
@@ -2655,12 +2653,7 @@ static int ice_setup_pf_sw(struct ice_pf *pf)
}

unroll_vsi_setup:
- if (vsi) {
- ice_vsi_free_q_vectors(vsi);
- ice_vsi_delete(vsi);
- ice_vsi_put_qs(vsi);
- ice_vsi_clear(vsi);
- }
+ ice_vsi_release(vsi);
return status;
}

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 7d5d9d34f4e4..69a234e83b8b 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -3372,24 +3372,15 @@ static int mvneta_txq_sw_init(struct mvneta_port *pp,
txq->last_desc = txq->size - 1;

txq->buf = kmalloc_array(txq->size, sizeof(*txq->buf), GFP_KERNEL);
- if (!txq->buf) {
- dma_free_coherent(pp->dev->dev.parent,
- txq->size * MVNETA_DESC_ALIGNED_SIZE,
- txq->descs, txq->descs_phys);
+ if (!txq->buf)
return -ENOMEM;
- }

/* Allocate DMA buffers for TSO MAC/IP/TCP headers */
txq->tso_hdrs = dma_alloc_coherent(pp->dev->dev.parent,
txq->size * TSO_HEADER_SIZE,
&txq->tso_hdrs_phys, GFP_KERNEL);
- if (!txq->tso_hdrs) {
- kfree(txq->buf);
- dma_free_coherent(pp->dev->dev.parent,
- txq->size * MVNETA_DESC_ALIGNED_SIZE,
- txq->descs, txq->descs_phys);
+ if (!txq->tso_hdrs)
return -ENOMEM;
- }

/* Setup XPS mapping */
if (txq_number > 1)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
index 387e33fa417a..2718fe201c14 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
@@ -17,7 +17,7 @@

static const u16 msgs_offset = ALIGN(sizeof(struct mbox_hdr), MBOX_MSG_ALIGN);

-void otx2_mbox_reset(struct otx2_mbox *mbox, int devid)
+void __otx2_mbox_reset(struct otx2_mbox *mbox, int devid)
{
void *hw_mbase = mbox->hwbase + (devid * MBOX_SIZE);
struct otx2_mbox_dev *mdev = &mbox->dev[devid];
@@ -26,13 +26,21 @@ void otx2_mbox_reset(struct otx2_mbox *mbox, int devid)
tx_hdr = hw_mbase + mbox->tx_start;
rx_hdr = hw_mbase + mbox->rx_start;

- spin_lock(&mdev->mbox_lock);
mdev->msg_size = 0;
mdev->rsp_size = 0;
tx_hdr->num_msgs = 0;
tx_hdr->msg_size = 0;
rx_hdr->num_msgs = 0;
rx_hdr->msg_size = 0;
+}
+EXPORT_SYMBOL(__otx2_mbox_reset);
+
+void otx2_mbox_reset(struct otx2_mbox *mbox, int devid)
+{
+ struct otx2_mbox_dev *mdev = &mbox->dev[devid];
+
+ spin_lock(&mdev->mbox_lock);
+ __otx2_mbox_reset(mbox, devid);
spin_unlock(&mdev->mbox_lock);
}
EXPORT_SYMBOL(otx2_mbox_reset);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 6dfd0f90cd70..ab433789d2c3 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -93,6 +93,7 @@ struct mbox_msghdr {
};

void otx2_mbox_reset(struct otx2_mbox *mbox, int devid);
+void __otx2_mbox_reset(struct otx2_mbox *mbox, int devid);
void otx2_mbox_destroy(struct otx2_mbox *mbox);
int otx2_mbox_init(struct otx2_mbox *mbox, void __force *hwbase,
struct pci_dev *pdev, void __force *reg_base,
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index dcf25a092008..b89dde2c8b08 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -463,6 +463,7 @@ void rvu_nix_freemem(struct rvu *rvu);
int rvu_get_nixlf_count(struct rvu *rvu);
void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int npalf);
int nix_get_nixlf(struct rvu *rvu, u16 pcifunc, int *nixlf, int *nix_blkaddr);
+int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add);

/* NPC APIs */
int rvu_npc_init(struct rvu *rvu);
@@ -477,7 +478,7 @@ void rvu_npc_disable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf);
void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf);
void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
int nixlf, u64 chan);
-void rvu_npc_disable_bcast_entry(struct rvu *rvu, u16 pcifunc);
+void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, bool enable);
int rvu_npc_update_rxvlan(struct rvu *rvu, u16 pcifunc, int nixlf);
void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf);
void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 36953d4f51c7..3495b3a6828c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -17,7 +17,6 @@
#include "npc.h"
#include "cgx.h"

-static int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add);
static int rvu_nix_get_bpid(struct rvu *rvu, struct nix_bp_cfg_req *req,
int type, int chan_id);

@@ -2020,7 +2019,7 @@ static int nix_update_mce_list(struct nix_mce_list *mce_list,
return 0;
}

-static int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add)
+int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add)
{
int err = 0, idx, next_idx, last_idx;
struct nix_mce_list *mce_list;
@@ -2065,7 +2064,7 @@ static int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add)

/* Disable MCAM entry in NPC */
if (!mce_list->count) {
- rvu_npc_disable_bcast_entry(rvu, pcifunc);
+ rvu_npc_enable_bcast_entry(rvu, pcifunc, false);
goto end;
}

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 0a214084406a..fbaf9bcd83f2 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -530,7 +530,7 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
NIX_INTF_RX, &entry, true);
}

-void rvu_npc_disable_bcast_entry(struct rvu *rvu, u16 pcifunc)
+void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, bool enable)
{
struct npc_mcam *mcam = &rvu->hw->mcam;
int blkaddr, index;
@@ -543,7 +543,7 @@ void rvu_npc_disable_bcast_entry(struct rvu *rvu, u16 pcifunc)
pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK;

index = npc_get_nixlf_mcam_index(mcam, pcifunc, 0, NIXLF_BCAST_ENTRY);
- npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false);
+ npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
}

void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
@@ -622,23 +622,35 @@ static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc,
nixlf, NIXLF_UCAST_ENTRY);
npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);

- /* For PF, ena/dis promisc and bcast MCAM match entries */
- if (pcifunc & RVU_PFVF_FUNC_MASK)
+ /* For PF, ena/dis promisc and bcast MCAM match entries.
+ * For VFs add/delete from bcast list when RX multicast
+ * feature is present.
+ */
+ if (pcifunc & RVU_PFVF_FUNC_MASK && !rvu->hw->cap.nix_rx_multicast)
return;

/* For bcast, enable/disable only if it's action is not
* packet replication, incase if action is replication
- * then this PF's nixlf is removed from bcast replication
+ * then this PF/VF's nixlf is removed from bcast replication
* list.
*/
- index = npc_get_nixlf_mcam_index(mcam, pcifunc,
+ index = npc_get_nixlf_mcam_index(mcam, pcifunc & ~RVU_PFVF_FUNC_MASK,
nixlf, NIXLF_BCAST_ENTRY);
bank = npc_get_bank(mcam, index);
*(u64 *)&action = rvu_read64(rvu, blkaddr,
NPC_AF_MCAMEX_BANKX_ACTION(index & (mcam->banksize - 1), bank));
- if (action.op != NIX_RX_ACTIONOP_MCAST)
+
+ /* VFs will not have BCAST entry */
+ if (action.op != NIX_RX_ACTIONOP_MCAST &&
+ !(pcifunc & RVU_PFVF_FUNC_MASK)) {
npc_enable_mcam_entry(rvu, mcam,
blkaddr, index, enable);
+ } else {
+ nix_update_bcast_mce_list(rvu, pcifunc, enable);
+ /* Enable PF's BCAST entry for packet replication */
+ rvu_npc_enable_bcast_entry(rvu, pcifunc, enable);
+ }
+
if (enable)
rvu_npc_enable_promisc_entry(rvu, pcifunc, nixlf);
else
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index 75a8c407e815..2fb45670aca4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -370,8 +370,8 @@ static int otx2_forward_vf_mbox_msgs(struct otx2_nic *pf,
dst_mbox = &pf->mbox;
dst_size = dst_mbox->mbox.tx_size -
ALIGN(sizeof(*mbox_hdr), MBOX_MSG_ALIGN);
- /* Check if msgs fit into destination area */
- if (mbox_hdr->msg_size > dst_size)
+ /* Check if msgs fit into destination area and has valid size */
+ if (mbox_hdr->msg_size > dst_size || !mbox_hdr->msg_size)
return -EINVAL;

dst_mdev = &dst_mbox->mbox.dev[0];
@@ -526,10 +526,10 @@ static void otx2_pfvf_mbox_up_handler(struct work_struct *work)

end:
offset = mbox->rx_start + msg->next_msgoff;
+ if (mdev->msgs_acked == (vf_mbox->up_num_msgs - 1))
+ __otx2_mbox_reset(mbox, 0);
mdev->msgs_acked++;
}
-
- otx2_mbox_reset(mbox, vf_idx);
}

static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq)
@@ -803,10 +803,11 @@ static void otx2_pfaf_mbox_handler(struct work_struct *work)
msg = (struct mbox_msghdr *)(mdev->mbase + offset);
otx2_process_pfaf_mbox_msg(pf, msg);
offset = mbox->rx_start + msg->next_msgoff;
+ if (mdev->msgs_acked == (af_mbox->num_msgs - 1))
+ __otx2_mbox_reset(mbox, 0);
mdev->msgs_acked++;
}

- otx2_mbox_reset(mbox, 0);
}

static void otx2_handle_link_event(struct otx2_nic *pf)
@@ -1560,10 +1561,13 @@ int otx2_open(struct net_device *netdev)

err = otx2_rxtx_enable(pf, true);
if (err)
- goto err_free_cints;
+ goto err_tx_stop_queues;

return 0;

+err_tx_stop_queues:
+ netif_tx_stop_all_queues(netdev);
+ netif_carrier_off(netdev);
err_free_cints:
otx2_free_cints(pf, qidx);
vec = pci_irq_vector(pf->pdev,
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index b04f5429d72d..334eab976ee4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -524,6 +524,7 @@ static void otx2_sqe_add_hdr(struct otx2_nic *pfvf, struct otx2_snd_queue *sq,
sqe_hdr->ol3type = NIX_SENDL3TYPE_IP4_CKSUM;
} else if (skb->protocol == htons(ETH_P_IPV6)) {
proto = ipv6_hdr(skb)->nexthdr;
+ sqe_hdr->ol3type = NIX_SENDL3TYPE_IP6;
}

if (proto == IPPROTO_TCP)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
index 92a3db69a6cd..2f90f1721441 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
@@ -99,10 +99,10 @@ static void otx2vf_vfaf_mbox_handler(struct work_struct *work)
msg = (struct mbox_msghdr *)(mdev->mbase + offset);
otx2vf_process_vfaf_mbox_msg(af_mbox->pfvf, msg);
offset = mbox->rx_start + msg->next_msgoff;
+ if (mdev->msgs_acked == (af_mbox->num_msgs - 1))
+ __otx2_mbox_reset(mbox, 0);
mdev->msgs_acked++;
}
-
- otx2_mbox_reset(mbox, 0);
}

static int otx2vf_process_mbox_msg_up(struct otx2_nic *vf,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 1d91a0d0ab1d..2b597ac365f8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -69,12 +69,10 @@ enum {
MLX5_CMD_DELIVERY_STAT_CMD_DESCR_ERR = 0x10,
};

-static struct mlx5_cmd_work_ent *alloc_cmd(struct mlx5_cmd *cmd,
- struct mlx5_cmd_msg *in,
- struct mlx5_cmd_msg *out,
- void *uout, int uout_size,
- mlx5_cmd_cbk_t cbk,
- void *context, int page_queue)
+static struct mlx5_cmd_work_ent *
+cmd_alloc_ent(struct mlx5_cmd *cmd, struct mlx5_cmd_msg *in,
+ struct mlx5_cmd_msg *out, void *uout, int uout_size,
+ mlx5_cmd_cbk_t cbk, void *context, int page_queue)
{
gfp_t alloc_flags = cbk ? GFP_ATOMIC : GFP_KERNEL;
struct mlx5_cmd_work_ent *ent;
@@ -83,6 +81,7 @@ static struct mlx5_cmd_work_ent *alloc_cmd(struct mlx5_cmd *cmd,
if (!ent)
return ERR_PTR(-ENOMEM);

+ ent->idx = -EINVAL;
ent->in = in;
ent->out = out;
ent->uout = uout;
@@ -91,10 +90,16 @@ static struct mlx5_cmd_work_ent *alloc_cmd(struct mlx5_cmd *cmd,
ent->context = context;
ent->cmd = cmd;
ent->page_queue = page_queue;
+ refcount_set(&ent->refcnt, 1);

return ent;
}

+static void cmd_free_ent(struct mlx5_cmd_work_ent *ent)
+{
+ kfree(ent);
+}
+
static u8 alloc_token(struct mlx5_cmd *cmd)
{
u8 token;
@@ -109,7 +114,7 @@ static u8 alloc_token(struct mlx5_cmd *cmd)
return token;
}

-static int alloc_ent(struct mlx5_cmd *cmd)
+static int cmd_alloc_index(struct mlx5_cmd *cmd)
{
unsigned long flags;
int ret;
@@ -123,7 +128,7 @@ static int alloc_ent(struct mlx5_cmd *cmd)
return ret < cmd->max_reg_cmds ? ret : -ENOMEM;
}

-static void free_ent(struct mlx5_cmd *cmd, int idx)
+static void cmd_free_index(struct mlx5_cmd *cmd, int idx)
{
unsigned long flags;

@@ -132,6 +137,22 @@ static void free_ent(struct mlx5_cmd *cmd, int idx)
spin_unlock_irqrestore(&cmd->alloc_lock, flags);
}

+static void cmd_ent_get(struct mlx5_cmd_work_ent *ent)
+{
+ refcount_inc(&ent->refcnt);
+}
+
+static void cmd_ent_put(struct mlx5_cmd_work_ent *ent)
+{
+ if (!refcount_dec_and_test(&ent->refcnt))
+ return;
+
+ if (ent->idx >= 0)
+ cmd_free_index(ent->cmd, ent->idx);
+
+ cmd_free_ent(ent);
+}
+
static struct mlx5_cmd_layout *get_inst(struct mlx5_cmd *cmd, int idx)
{
return cmd->cmd_buf + (idx << cmd->log_stride);
@@ -219,11 +240,6 @@ static void poll_timeout(struct mlx5_cmd_work_ent *ent)
ent->ret = -ETIMEDOUT;
}

-static void free_cmd(struct mlx5_cmd_work_ent *ent)
-{
- kfree(ent);
-}
-
static int verify_signature(struct mlx5_cmd_work_ent *ent)
{
struct mlx5_cmd_mailbox *next = ent->out->next;
@@ -837,11 +853,22 @@ static void cb_timeout_handler(struct work_struct *work)
struct mlx5_core_dev *dev = container_of(ent->cmd, struct mlx5_core_dev,
cmd);

+ mlx5_cmd_eq_recover(dev);
+
+ /* Maybe got handled by eq recover ? */
+ if (!test_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state)) {
+ mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) Async, recovered after timeout\n", ent->idx,
+ mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in));
+ goto out; /* phew, already handled */
+ }
+
ent->ret = -ETIMEDOUT;
- mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
- mlx5_command_str(msg_to_opcode(ent->in)),
- msg_to_opcode(ent->in));
+ mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) Async, timeout. Will cause a leak of a command resource\n",
+ ent->idx, mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in));
mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
+
+out:
+ cmd_ent_put(ent); /* for the cmd_ent_get() took on schedule delayed work */
}

static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg);
@@ -856,6 +883,25 @@ static bool opcode_allowed(struct mlx5_cmd *cmd, u16 opcode)
return cmd->allowed_opcode == opcode;
}

+static int cmd_alloc_index_retry(struct mlx5_cmd *cmd)
+{
+ unsigned long alloc_end = jiffies + msecs_to_jiffies(1000);
+ int idx;
+
+retry:
+ idx = cmd_alloc_index(cmd);
+ if (idx < 0 && time_before(jiffies, alloc_end)) {
+ /* Index allocation can fail on heavy load of commands. This is a temporary
+ * situation as the current command already holds the semaphore, meaning that
+ * another command completion is being handled and it is expected to release
+ * the entry index soon.
+ */
+ cpu_relax();
+ goto retry;
+ }
+ return idx;
+}
+
static void cmd_work_handler(struct work_struct *work)
{
struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work);
@@ -873,14 +919,14 @@ static void cmd_work_handler(struct work_struct *work)
sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem;
down(sem);
if (!ent->page_queue) {
- alloc_ret = alloc_ent(cmd);
+ alloc_ret = cmd_alloc_index_retry(cmd);
if (alloc_ret < 0) {
mlx5_core_err_rl(dev, "failed to allocate command entry\n");
if (ent->callback) {
ent->callback(-EAGAIN, ent->context);
mlx5_free_cmd_msg(dev, ent->out);
free_msg(dev, ent->in);
- free_cmd(ent);
+ cmd_ent_put(ent);
} else {
ent->ret = -EAGAIN;
complete(&ent->done);
@@ -916,8 +962,8 @@ static void cmd_work_handler(struct work_struct *work)
ent->ts1 = ktime_get_ns();
cmd_mode = cmd->mode;

- if (ent->callback)
- schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
+ if (ent->callback && schedule_delayed_work(&ent->cb_timeout_work, cb_timeout))
+ cmd_ent_get(ent);
set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state);

/* Skip sending command to fw if internal error */
@@ -933,13 +979,10 @@ static void cmd_work_handler(struct work_struct *work)
MLX5_SET(mbox_out, ent->out, syndrome, drv_synd);

mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
- /* no doorbell, no need to keep the entry */
- free_ent(cmd, ent->idx);
- if (ent->callback)
- free_cmd(ent);
return;
}

+ cmd_ent_get(ent); /* for the _real_ FW event on completion */
/* ring doorbell after the descriptor is valid */
mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx);
wmb();
@@ -983,6 +1026,35 @@ static const char *deliv_status_to_str(u8 status)
}
}

+enum {
+ MLX5_CMD_TIMEOUT_RECOVER_MSEC = 5 * 1000,
+};
+
+static void wait_func_handle_exec_timeout(struct mlx5_core_dev *dev,
+ struct mlx5_cmd_work_ent *ent)
+{
+ unsigned long timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_RECOVER_MSEC);
+
+ mlx5_cmd_eq_recover(dev);
+
+ /* Re-wait on the ent->done after executing the recovery flow. If the
+ * recovery flow (or any other recovery flow running simultaneously)
+ * has recovered an EQE, it should cause the entry to be completed by
+ * the command interface.
+ */
+ if (wait_for_completion_timeout(&ent->done, timeout)) {
+ mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) recovered after timeout\n", ent->idx,
+ mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in));
+ return;
+ }
+
+ mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) No done completion\n", ent->idx,
+ mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in));
+
+ ent->ret = -ETIMEDOUT;
+ mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
+}
+
static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
{
unsigned long timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC);
@@ -994,12 +1066,10 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
ent->ret = -ECANCELED;
goto out_err;
}
- if (cmd->mode == CMD_MODE_POLLING || ent->polling) {
+ if (cmd->mode == CMD_MODE_POLLING || ent->polling)
wait_for_completion(&ent->done);
- } else if (!wait_for_completion_timeout(&ent->done, timeout)) {
- ent->ret = -ETIMEDOUT;
- mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
- }
+ else if (!wait_for_completion_timeout(&ent->done, timeout))
+ wait_func_handle_exec_timeout(dev, ent);

out_err:
err = ent->ret;
@@ -1039,11 +1109,16 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
if (callback && page_queue)
return -EINVAL;

- ent = alloc_cmd(cmd, in, out, uout, uout_size, callback, context,
- page_queue);
+ ent = cmd_alloc_ent(cmd, in, out, uout, uout_size,
+ callback, context, page_queue);
if (IS_ERR(ent))
return PTR_ERR(ent);

+ /* put for this ent is when consumed, depending on the use case
+ * 1) (!callback) blocking flow: by caller after wait_func completes
+ * 2) (callback) flow: by mlx5_cmd_comp_handler() when ent is handled
+ */
+
ent->token = token;
ent->polling = force_polling;

@@ -1062,12 +1137,10 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
}

if (callback)
- goto out;
+ goto out; /* mlx5_cmd_comp_handler() will put(ent) */

err = wait_func(dev, ent);
- if (err == -ETIMEDOUT)
- goto out;
- if (err == -ECANCELED)
+ if (err == -ETIMEDOUT || err == -ECANCELED)
goto out_free;

ds = ent->ts2 - ent->ts1;
@@ -1085,7 +1158,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
*status = ent->status;

out_free:
- free_cmd(ent);
+ cmd_ent_put(ent);
out:
return err;
}
@@ -1516,14 +1589,19 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force
if (!forced) {
mlx5_core_err(dev, "Command completion arrived after timeout (entry idx = %d).\n",
ent->idx);
- free_ent(cmd, ent->idx);
- free_cmd(ent);
+ cmd_ent_put(ent);
}
continue;
}

- if (ent->callback)
- cancel_delayed_work(&ent->cb_timeout_work);
+ if (ent->callback && cancel_delayed_work(&ent->cb_timeout_work))
+ cmd_ent_put(ent); /* timeout work was canceled */
+
+ if (!forced || /* Real FW completion */
+ pci_channel_offline(dev->pdev) || /* FW is inaccessible */
+ dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
+ cmd_ent_put(ent);
+
if (ent->page_queue)
sem = &cmd->pages_sem;
else
@@ -1545,10 +1623,6 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force
ent->ret, deliv_status_to_str(ent->status), ent->status);
}

- /* only real completion will free the entry slot */
- if (!forced)
- free_ent(cmd, ent->idx);
-
if (ent->callback) {
ds = ent->ts2 - ent->ts1;
if (ent->op < MLX5_CMD_OP_MAX) {
@@ -1576,10 +1650,13 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force
free_msg(dev, ent->in);

err = err ? err : ent->status;
- if (!forced)
- free_cmd(ent);
+ /* final consumer is done, release ent */
+ cmd_ent_put(ent);
callback(err, context);
} else {
+ /* release wait_func() so mlx5_cmd_invoke()
+ * can make the final ent_put()
+ */
complete(&ent->done);
}
up(sem);
@@ -1589,8 +1666,11 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force

void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev)
{
+ struct mlx5_cmd *cmd = &dev->cmd;
+ unsigned long bitmask;
unsigned long flags;
u64 vector;
+ int i;

/* wait for pending handlers to complete */
mlx5_eq_synchronize_cmd_irq(dev);
@@ -1599,11 +1679,20 @@ void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev)
if (!vector)
goto no_trig;

+ bitmask = vector;
+ /* we must increment the allocated entries refcount before triggering the completions
+ * to guarantee pending commands will not get freed in the meanwhile.
+ * For that reason, it also has to be done inside the alloc_lock.
+ */
+ for_each_set_bit(i, &bitmask, (1 << cmd->log_sz))
+ cmd_ent_get(cmd->ent_arr[i]);
vector |= MLX5_TRIGGERED_CMD_COMP;
spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags);

mlx5_core_dbg(dev, "vector 0x%llx\n", vector);
mlx5_cmd_comp_handler(dev, vector, true);
+ for_each_set_bit(i, &bitmask, (1 << cmd->log_sz))
+ cmd_ent_put(cmd->ent_arr[i]);
return;

no_trig:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 76b23ba7a468..cb3857e136d6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -90,7 +90,12 @@ struct page_pool;
#define MLX5_MPWRQ_PAGES_PER_WQE BIT(MLX5_MPWRQ_WQE_PAGE_ORDER)

#define MLX5_MTT_OCTW(npages) (ALIGN(npages, 8) / 2)
-#define MLX5E_REQUIRED_WQE_MTTS (ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8))
+/* Add another page to MLX5E_REQUIRED_WQE_MTTS as a buffer between
+ * WQEs, This page will absorb write overflow by the hardware, when
+ * receiving packets larger than MTU. These oversize packets are
+ * dropped by the driver at a later stage.
+ */
+#define MLX5E_REQUIRED_WQE_MTTS (ALIGN(MLX5_MPWRQ_PAGES_PER_WQE + 1, 8))
#define MLX5E_LOG_ALIGNED_MPWQE_PPW (ilog2(MLX5E_REQUIRED_WQE_MTTS))
#define MLX5E_REQUIRED_MTTS(wqes) (wqes * MLX5E_REQUIRED_WQE_MTTS)
#define MLX5E_MAX_RQ_NUM_MTTS \
@@ -621,6 +626,7 @@ struct mlx5e_rq {
u32 rqn;
struct mlx5_core_dev *mdev;
struct mlx5_core_mkey umr_mkey;
+ struct mlx5e_dma_info wqe_overflow;

/* XDP read-mostly */
struct xdp_rxq_info xdp_rxq;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index 98e909bf3c1e..3e32264cf613 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -566,6 +566,9 @@ int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u16 fec_policy)
if (fec_policy >= (1 << MLX5E_FEC_LLRS_272_257_1) && !fec_50g_per_lane)
return -EOPNOTSUPP;

+ if (fec_policy && !mlx5e_fec_in_caps(dev, fec_policy))
+ return -EOPNOTSUPP;
+
MLX5_SET(pplm_reg, in, local_port, 1);
err = mlx5_core_access_reg(dev, in, sz, out, sz, MLX5_REG_PPLM, 0, 0);
if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c
index c3d167fa944c..6a9d783d129b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c
@@ -109,11 +109,25 @@ static void mlx5e_rep_neigh_stats_work(struct work_struct *work)
rtnl_unlock();
}

+struct neigh_update_work {
+ struct work_struct work;
+ struct neighbour *n;
+ struct mlx5e_neigh_hash_entry *nhe;
+};
+
+static void mlx5e_release_neigh_update_work(struct neigh_update_work *update_work)
+{
+ neigh_release(update_work->n);
+ mlx5e_rep_neigh_entry_release(update_work->nhe);
+ kfree(update_work);
+}
+
static void mlx5e_rep_neigh_update(struct work_struct *work)
{
- struct mlx5e_neigh_hash_entry *nhe =
- container_of(work, struct mlx5e_neigh_hash_entry, neigh_update_work);
- struct neighbour *n = nhe->n;
+ struct neigh_update_work *update_work = container_of(work, struct neigh_update_work,
+ work);
+ struct mlx5e_neigh_hash_entry *nhe = update_work->nhe;
+ struct neighbour *n = update_work->n;
struct mlx5e_encap_entry *e;
unsigned char ha[ETH_ALEN];
struct mlx5e_priv *priv;
@@ -145,30 +159,42 @@ static void mlx5e_rep_neigh_update(struct work_struct *work)
mlx5e_rep_update_flows(priv, e, neigh_connected, ha);
mlx5e_encap_put(priv, e);
}
- mlx5e_rep_neigh_entry_release(nhe);
rtnl_unlock();
- neigh_release(n);
+ mlx5e_release_neigh_update_work(update_work);
}

-static void mlx5e_rep_queue_neigh_update_work(struct mlx5e_priv *priv,
- struct mlx5e_neigh_hash_entry *nhe,
- struct neighbour *n)
+static struct neigh_update_work *mlx5e_alloc_neigh_update_work(struct mlx5e_priv *priv,
+ struct neighbour *n)
{
- /* Take a reference to ensure the neighbour and mlx5 encap
- * entry won't be destructed until we drop the reference in
- * delayed work.
- */
- neigh_hold(n);
+ struct neigh_update_work *update_work;
+ struct mlx5e_neigh_hash_entry *nhe;
+ struct mlx5e_neigh m_neigh = {};

- /* This assignment is valid as long as the the neigh reference
- * is taken
- */
- nhe->n = n;
+ update_work = kzalloc(sizeof(*update_work), GFP_ATOMIC);
+ if (WARN_ON(!update_work))
+ return NULL;

- if (!queue_work(priv->wq, &nhe->neigh_update_work)) {
- mlx5e_rep_neigh_entry_release(nhe);
- neigh_release(n);
+ m_neigh.dev = n->dev;
+ m_neigh.family = n->ops->family;
+ memcpy(&m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
+
+ /* Obtain reference to nhe as last step in order not to release it in
+ * atomic context.
+ */
+ rcu_read_lock();
+ nhe = mlx5e_rep_neigh_entry_lookup(priv, &m_neigh);
+ rcu_read_unlock();
+ if (!nhe) {
+ kfree(update_work);
+ return NULL;
}
+
+ INIT_WORK(&update_work->work, mlx5e_rep_neigh_update);
+ neigh_hold(n);
+ update_work->n = n;
+ update_work->nhe = nhe;
+
+ return update_work;
}

static int mlx5e_rep_netevent_event(struct notifier_block *nb,
@@ -180,7 +206,7 @@ static int mlx5e_rep_netevent_event(struct notifier_block *nb,
struct net_device *netdev = rpriv->netdev;
struct mlx5e_priv *priv = netdev_priv(netdev);
struct mlx5e_neigh_hash_entry *nhe = NULL;
- struct mlx5e_neigh m_neigh = {};
+ struct neigh_update_work *update_work;
struct neigh_parms *p;
struct neighbour *n;
bool found = false;
@@ -195,17 +221,11 @@ static int mlx5e_rep_netevent_event(struct notifier_block *nb,
#endif
return NOTIFY_DONE;

- m_neigh.dev = n->dev;
- m_neigh.family = n->ops->family;
- memcpy(&m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
-
- rcu_read_lock();
- nhe = mlx5e_rep_neigh_entry_lookup(priv, &m_neigh);
- rcu_read_unlock();
- if (!nhe)
+ update_work = mlx5e_alloc_neigh_update_work(priv, n);
+ if (!update_work)
return NOTIFY_DONE;

- mlx5e_rep_queue_neigh_update_work(priv, nhe, n);
+ queue_work(priv->wq, &update_work->work);
break;

case NETEVENT_DELAY_PROBE_TIME_UPDATE:
@@ -351,7 +371,6 @@ int mlx5e_rep_neigh_entry_create(struct mlx5e_priv *priv,

(*nhe)->priv = priv;
memcpy(&(*nhe)->m_neigh, &e->m_neigh, sizeof(e->m_neigh));
- INIT_WORK(&(*nhe)->neigh_update_work, mlx5e_rep_neigh_update);
spin_lock_init(&(*nhe)->encap_list_lock);
INIT_LIST_HEAD(&(*nhe)->encap_list);
refcount_set(&(*nhe)->refcnt, 1);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index 73d3dc07331f..713dc210f710 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -217,6 +217,9 @@ static int __mlx5e_add_vlan_rule(struct mlx5e_priv *priv,
break;
}

+ if (WARN_ONCE(*rule_p, "VLAN rule already exists type %d", rule_type))
+ return 0;
+
*rule_p = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);

if (IS_ERR(*rule_p)) {
@@ -397,8 +400,7 @@ static void mlx5e_add_vlan_rules(struct mlx5e_priv *priv)
for_each_set_bit(i, priv->fs.vlan.active_svlans, VLAN_N_VID)
mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_MATCH_STAG_VID, i);

- if (priv->fs.vlan.cvlan_filter_disabled &&
- !(priv->netdev->flags & IFF_PROMISC))
+ if (priv->fs.vlan.cvlan_filter_disabled)
mlx5e_add_any_vid_rules(priv);
}

@@ -415,8 +417,12 @@ static void mlx5e_del_vlan_rules(struct mlx5e_priv *priv)
for_each_set_bit(i, priv->fs.vlan.active_svlans, VLAN_N_VID)
mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_MATCH_STAG_VID, i);

- if (priv->fs.vlan.cvlan_filter_disabled &&
- !(priv->netdev->flags & IFF_PROMISC))
+ WARN_ON_ONCE(!(test_bit(MLX5E_STATE_DESTROYING, &priv->state)));
+
+ /* must be called after DESTROY bit is set and
+ * set_rx_mode is called and flushed
+ */
+ if (priv->fs.vlan.cvlan_filter_disabled)
mlx5e_del_any_vid_rules(priv);
}

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index cccf65fc116e..f8a20dd81437 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -258,12 +258,17 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq,

static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev,
u64 npages, u8 page_shift,
- struct mlx5_core_mkey *umr_mkey)
+ struct mlx5_core_mkey *umr_mkey,
+ dma_addr_t filler_addr)
{
- int inlen = MLX5_ST_SZ_BYTES(create_mkey_in);
+ struct mlx5_mtt *mtt;
+ int inlen;
void *mkc;
u32 *in;
int err;
+ int i;
+
+ inlen = MLX5_ST_SZ_BYTES(create_mkey_in) + sizeof(*mtt) * npages;

in = kvzalloc(inlen, GFP_KERNEL);
if (!in)
@@ -283,6 +288,18 @@ static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev,
MLX5_SET(mkc, mkc, translations_octword_size,
MLX5_MTT_OCTW(npages));
MLX5_SET(mkc, mkc, log_page_size, page_shift);
+ MLX5_SET(create_mkey_in, in, translations_octword_actual_size,
+ MLX5_MTT_OCTW(npages));
+
+ /* Initialize the mkey with all MTTs pointing to a default
+ * page (filler_addr). When the channels are activated, UMR
+ * WQEs will redirect the RX WQEs to the actual memory from
+ * the RQ's pool, while the gaps (wqe_overflow) remain mapped
+ * to the default page.
+ */
+ mtt = MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt);
+ for (i = 0 ; i < npages ; i++)
+ mtt[i].ptag = cpu_to_be64(filler_addr);

err = mlx5_core_create_mkey(mdev, umr_mkey, in, inlen);

@@ -294,7 +311,8 @@ static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq
{
u64 num_mtts = MLX5E_REQUIRED_MTTS(mlx5_wq_ll_get_size(&rq->mpwqe.wq));

- return mlx5e_create_umr_mkey(mdev, num_mtts, PAGE_SHIFT, &rq->umr_mkey);
+ return mlx5e_create_umr_mkey(mdev, num_mtts, PAGE_SHIFT, &rq->umr_mkey,
+ rq->wqe_overflow.addr);
}

static inline u64 mlx5e_get_mpwqe_offset(struct mlx5e_rq *rq, u16 wqe_ix)
@@ -362,6 +380,28 @@ static void mlx5e_rq_err_cqe_work(struct work_struct *recover_work)
mlx5e_reporter_rq_cqe_err(rq);
}

+static int mlx5e_alloc_mpwqe_rq_drop_page(struct mlx5e_rq *rq)
+{
+ rq->wqe_overflow.page = alloc_page(GFP_KERNEL);
+ if (!rq->wqe_overflow.page)
+ return -ENOMEM;
+
+ rq->wqe_overflow.addr = dma_map_page(rq->pdev, rq->wqe_overflow.page, 0,
+ PAGE_SIZE, rq->buff.map_dir);
+ if (dma_mapping_error(rq->pdev, rq->wqe_overflow.addr)) {
+ __free_page(rq->wqe_overflow.page);
+ return -ENOMEM;
+ }
+ return 0;
+}
+
+static void mlx5e_free_mpwqe_rq_drop_page(struct mlx5e_rq *rq)
+{
+ dma_unmap_page(rq->pdev, rq->wqe_overflow.addr, PAGE_SIZE,
+ rq->buff.map_dir);
+ __free_page(rq->wqe_overflow.page);
+}
+
static int mlx5e_alloc_rq(struct mlx5e_channel *c,
struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk,
@@ -421,6 +461,10 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
if (err)
goto err_rq_wq_destroy;

+ err = mlx5e_alloc_mpwqe_rq_drop_page(rq);
+ if (err)
+ goto err_rq_wq_destroy;
+
rq->mpwqe.wq.db = &rq->mpwqe.wq.db[MLX5_RCV_DBR];

wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq);
@@ -459,7 +503,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,

err = mlx5e_create_rq_umr_mkey(mdev, rq);
if (err)
- goto err_rq_wq_destroy;
+ goto err_rq_drop_page;
rq->mkey_be = cpu_to_be32(rq->umr_mkey.key);

err = mlx5e_rq_alloc_mpwqe_info(rq, c);
@@ -598,6 +642,8 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
kvfree(rq->mpwqe.info);
mlx5_core_destroy_mkey(mdev, &rq->umr_mkey);
+err_rq_drop_page:
+ mlx5e_free_mpwqe_rq_drop_page(rq);
break;
default: /* MLX5_WQ_TYPE_CYCLIC */
kvfree(rq->wqe.frags);
@@ -631,6 +677,7 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq)
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
kvfree(rq->mpwqe.info);
mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey);
+ mlx5e_free_mpwqe_rq_drop_page(rq);
break;
default: /* MLX5_WQ_TYPE_CYCLIC */
kvfree(rq->wqe.frags);
@@ -4276,6 +4323,21 @@ void mlx5e_del_vxlan_port(struct net_device *netdev, struct udp_tunnel_info *ti)
mlx5e_vxlan_queue_work(priv, be16_to_cpu(ti->port), 0);
}

+static bool mlx5e_gre_tunnel_inner_proto_offload_supported(struct mlx5_core_dev *mdev,
+ struct sk_buff *skb)
+{
+ switch (skb->inner_protocol) {
+ case htons(ETH_P_IP):
+ case htons(ETH_P_IPV6):
+ case htons(ETH_P_TEB):
+ return true;
+ case htons(ETH_P_MPLS_UC):
+ case htons(ETH_P_MPLS_MC):
+ return MLX5_CAP_ETH(mdev, tunnel_stateless_mpls_over_gre);
+ }
+ return false;
+}
+
static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
struct sk_buff *skb,
netdev_features_t features)
@@ -4298,7 +4360,9 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,

switch (proto) {
case IPPROTO_GRE:
- return features;
+ if (mlx5e_gre_tunnel_inner_proto_offload_supported(priv->mdev, skb))
+ return features;
+ break;
case IPPROTO_IPIP:
case IPPROTO_IPV6:
if (mlx5e_tunnel_proto_supported(priv->mdev, IPPROTO_IPIP))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 1d5669801484..fcaabafb2e56 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -133,12 +133,6 @@ struct mlx5e_neigh_hash_entry {
/* encap list sharing the same neigh */
struct list_head encap_list;

- /* valid only when the neigh reference is taken during
- * neigh_update_work workqueue callback.
- */
- struct neighbour *n;
- struct work_struct neigh_update_work;
-
/* neigh hash entry can be deleted only when the refcount is zero.
* refcount is needed to avoid neigh hash entry removal by TC, while
* it's used by the neigh notification call.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 31ef9f8420c8..22a19d391e17 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -189,6 +189,29 @@ u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq_comp *eq)
return count_eqe;
}

+static void mlx5_eq_async_int_lock(struct mlx5_eq_async *eq, unsigned long *flags)
+ __acquires(&eq->lock)
+{
+ if (in_irq())
+ spin_lock(&eq->lock);
+ else
+ spin_lock_irqsave(&eq->lock, *flags);
+}
+
+static void mlx5_eq_async_int_unlock(struct mlx5_eq_async *eq, unsigned long *flags)
+ __releases(&eq->lock)
+{
+ if (in_irq())
+ spin_unlock(&eq->lock);
+ else
+ spin_unlock_irqrestore(&eq->lock, *flags);
+}
+
+enum async_eq_nb_action {
+ ASYNC_EQ_IRQ_HANDLER = 0,
+ ASYNC_EQ_RECOVER = 1,
+};
+
static int mlx5_eq_async_int(struct notifier_block *nb,
unsigned long action, void *data)
{
@@ -198,11 +221,14 @@ static int mlx5_eq_async_int(struct notifier_block *nb,
struct mlx5_eq_table *eqt;
struct mlx5_core_dev *dev;
struct mlx5_eqe *eqe;
+ unsigned long flags;
int num_eqes = 0;

dev = eq->dev;
eqt = dev->priv.eq_table;

+ mlx5_eq_async_int_lock(eq_async, &flags);
+
eqe = next_eqe_sw(eq);
if (!eqe)
goto out;
@@ -223,8 +249,19 @@ static int mlx5_eq_async_int(struct notifier_block *nb,

out:
eq_update_ci(eq, 1);
+ mlx5_eq_async_int_unlock(eq_async, &flags);

- return 0;
+ return unlikely(action == ASYNC_EQ_RECOVER) ? num_eqes : 0;
+}
+
+void mlx5_cmd_eq_recover(struct mlx5_core_dev *dev)
+{
+ struct mlx5_eq_async *eq = &dev->priv.eq_table->cmd_eq;
+ int eqes;
+
+ eqes = mlx5_eq_async_int(&eq->irq_nb, ASYNC_EQ_RECOVER, NULL);
+ if (eqes)
+ mlx5_core_warn(dev, "Recovered %d EQEs on cmd_eq\n", eqes);
}

static void init_eq_buf(struct mlx5_eq *eq)
@@ -569,6 +606,7 @@ setup_async_eq(struct mlx5_core_dev *dev, struct mlx5_eq_async *eq,
int err;

eq->irq_nb.notifier_call = mlx5_eq_async_int;
+ spin_lock_init(&eq->lock);

err = create_async_eq(dev, &eq->core, param);
if (err) {
@@ -656,8 +694,10 @@ static void destroy_async_eqs(struct mlx5_core_dev *dev)

cleanup_async_eq(dev, &table->pages_eq, "pages");
cleanup_async_eq(dev, &table->async_eq, "async");
+ mlx5_cmd_allowed_opcode(dev, MLX5_CMD_OP_DESTROY_EQ);
mlx5_cmd_use_polling(dev);
cleanup_async_eq(dev, &table->cmd_eq, "cmd");
+ mlx5_cmd_allowed_opcode(dev, CMD_ALLOWED_OPCODE_ALL);
mlx5_eq_notifier_unregister(dev, &table->cq_err_nb);
}

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
index 4aaca7400fb2..5c681e31983b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
@@ -37,6 +37,7 @@ struct mlx5_eq {
struct mlx5_eq_async {
struct mlx5_eq core;
struct notifier_block irq_nb;
+ spinlock_t lock; /* To avoid irq EQ handle races with resiliency flows */
};

struct mlx5_eq_comp {
@@ -81,6 +82,7 @@ void mlx5_cq_tasklet_cb(unsigned long data);
struct cpumask *mlx5_eq_comp_cpumask(struct mlx5_core_dev *dev, int ix);

u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq_comp *eq);
+void mlx5_cmd_eq_recover(struct mlx5_core_dev *dev);
void mlx5_eq_synchronize_async_irq(struct mlx5_core_dev *dev);
void mlx5_eq_synchronize_cmd_irq(struct mlx5_core_dev *dev);

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 373981a659c7..6fd974920394 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -115,7 +115,7 @@ static int request_irqs(struct mlx5_core_dev *dev, int nvec)
return 0;

err_request_irq:
- for (; i >= 0; i--) {
+ while (i--) {
struct mlx5_irq *irq = mlx5_irq_get(dev, i);
int irqn = pci_irq_vector(dev->pdev, i);

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index 5c020403342f..7cccc41dd69c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -292,13 +292,14 @@ mlxsw_sp_acl_tcam_group_add(struct mlxsw_sp_acl_tcam *tcam,
int err;

group->tcam = tcam;
- mutex_init(&group->lock);
INIT_LIST_HEAD(&group->region_list);

err = mlxsw_sp_acl_tcam_group_id_get(tcam, &group->id);
if (err)
return err;

+ mutex_init(&group->lock);
+
return 0;
}

diff --git a/drivers/net/ethernet/mscc/Makefile b/drivers/net/ethernet/mscc/Makefile
index 91b33b55054e..ad97a5cca6f9 100644
--- a/drivers/net/ethernet/mscc/Makefile
+++ b/drivers/net/ethernet/mscc/Makefile
@@ -2,4 +2,4 @@
obj-$(CONFIG_MSCC_OCELOT_SWITCH) += mscc_ocelot_common.o
mscc_ocelot_common-y := ocelot.o ocelot_io.o
mscc_ocelot_common-y += ocelot_regs.o ocelot_tc.o ocelot_police.o ocelot_ace.o ocelot_flower.o ocelot_ptp.o
-obj-$(CONFIG_MSCC_OCELOT_SWITCH_OCELOT) += ocelot_board.o
+obj-$(CONFIG_MSCC_OCELOT_SWITCH_OCELOT) += ocelot_vsc7514.o
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index d0b79cca5184..61bbb7a09004 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -396,18 +396,6 @@ static void ocelot_vlan_init(struct ocelot *ocelot)
}
}

-/* Watermark encode
- * Bit 8: Unit; 0:1, 1:16
- * Bit 7-0: Value to be multiplied with unit
- */
-static u16 ocelot_wm_enc(u16 value)
-{
- if (value >= BIT(8))
- return BIT(8) | (value / 16);
-
- return value;
-}
-
void ocelot_adjust_link(struct ocelot *ocelot, int port,
struct phy_device *phydev)
{
@@ -2012,7 +2000,8 @@ void ocelot_port_set_maxlen(struct ocelot *ocelot, int port, size_t sdu)
{
struct ocelot_port *ocelot_port = ocelot->ports[port];
int maxlen = sdu + ETH_HLEN + ETH_FCS_LEN;
- int atop_wm;
+ int pause_start, pause_stop;
+ int atop, atop_tot;

if (port == ocelot->npi) {
maxlen += OCELOT_TAG_LEN;
@@ -2025,20 +2014,20 @@ void ocelot_port_set_maxlen(struct ocelot *ocelot, int port, size_t sdu)

ocelot_port_writel(ocelot_port, maxlen, DEV_MAC_MAXLEN_CFG);

- /* Set Pause WM hysteresis
- * 152 = 6 * maxlen / OCELOT_BUFFER_CELL_SZ
- * 101 = 4 * maxlen / OCELOT_BUFFER_CELL_SZ
- */
- ocelot_write_rix(ocelot, SYS_PAUSE_CFG_PAUSE_ENA |
- SYS_PAUSE_CFG_PAUSE_STOP(101) |
- SYS_PAUSE_CFG_PAUSE_START(152), SYS_PAUSE_CFG, port);
+ /* Set Pause watermark hysteresis */
+ pause_start = 6 * maxlen / OCELOT_BUFFER_CELL_SZ;
+ pause_stop = 4 * maxlen / OCELOT_BUFFER_CELL_SZ;
+ ocelot_rmw_rix(ocelot, SYS_PAUSE_CFG_PAUSE_START(pause_start),
+ SYS_PAUSE_CFG_PAUSE_START_M, SYS_PAUSE_CFG, port);
+ ocelot_rmw_rix(ocelot, SYS_PAUSE_CFG_PAUSE_STOP(pause_stop),
+ SYS_PAUSE_CFG_PAUSE_STOP_M, SYS_PAUSE_CFG, port);

- /* Tail dropping watermark */
- atop_wm = (ocelot->shared_queue_sz - 9 * maxlen) /
+ /* Tail dropping watermarks */
+ atop_tot = (ocelot->shared_queue_sz - 9 * maxlen) /
OCELOT_BUFFER_CELL_SZ;
- ocelot_write_rix(ocelot, ocelot_wm_enc(9 * maxlen),
- SYS_ATOP, port);
- ocelot_write(ocelot, ocelot_wm_enc(atop_wm), SYS_ATOP_TOT_CFG);
+ atop = (9 * maxlen) / OCELOT_BUFFER_CELL_SZ;
+ ocelot_write_rix(ocelot, ocelot->ops->wm_enc(atop), SYS_ATOP, port);
+ ocelot_write(ocelot, ocelot->ops->wm_enc(atop_tot), SYS_ATOP_TOT_CFG);
}
EXPORT_SYMBOL(ocelot_port_set_maxlen);

@@ -2094,6 +2083,10 @@ void ocelot_init_port(struct ocelot *ocelot, int port)
ocelot_port_writel(ocelot_port, 0, DEV_MAC_FC_MAC_HIGH_CFG);
ocelot_port_writel(ocelot_port, 0, DEV_MAC_FC_MAC_LOW_CFG);

+ /* Enable transmission of pause frames */
+ ocelot_rmw_rix(ocelot, SYS_PAUSE_CFG_PAUSE_ENA, SYS_PAUSE_CFG_PAUSE_ENA,
+ SYS_PAUSE_CFG, port);
+
/* Drop frames with multicast source address */
ocelot_rmw_gix(ocelot, ANA_PORT_DROP_CFG_DROP_MC_SMAC_ENA,
ANA_PORT_DROP_CFG_DROP_MC_SMAC_ENA,
diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c
deleted file mode 100644
index 4a15d2ff8b70..000000000000
--- a/drivers/net/ethernet/mscc/ocelot_board.c
+++ /dev/null
@@ -1,626 +0,0 @@
-// SPDX-License-Identifier: (GPL-2.0 OR MIT)
-/*
- * Microsemi Ocelot Switch driver
- *
- * Copyright (c) 2017 Microsemi Corporation
- */
-#include <linux/interrupt.h>
-#include <linux/module.h>
-#include <linux/of_net.h>
-#include <linux/netdevice.h>
-#include <linux/of_mdio.h>
-#include <linux/of_platform.h>
-#include <linux/mfd/syscon.h>
-#include <linux/skbuff.h>
-#include <net/switchdev.h>
-
-#include <soc/mscc/ocelot_vcap.h>
-#include "ocelot.h"
-
-#define IFH_EXTRACT_BITFIELD64(x, o, w) (((x) >> (o)) & GENMASK_ULL((w) - 1, 0))
-#define VSC7514_VCAP_IS2_CNT 64
-#define VSC7514_VCAP_IS2_ENTRY_WIDTH 376
-#define VSC7514_VCAP_IS2_ACTION_WIDTH 99
-#define VSC7514_VCAP_PORT_CNT 11
-
-static int ocelot_parse_ifh(u32 *_ifh, struct frame_info *info)
-{
- u8 llen, wlen;
- u64 ifh[2];
-
- ifh[0] = be64_to_cpu(((__force __be64 *)_ifh)[0]);
- ifh[1] = be64_to_cpu(((__force __be64 *)_ifh)[1]);
-
- wlen = IFH_EXTRACT_BITFIELD64(ifh[0], 7, 8);
- llen = IFH_EXTRACT_BITFIELD64(ifh[0], 15, 6);
-
- info->len = OCELOT_BUFFER_CELL_SZ * wlen + llen - 80;
-
- info->timestamp = IFH_EXTRACT_BITFIELD64(ifh[0], 21, 32);
-
- info->port = IFH_EXTRACT_BITFIELD64(ifh[1], 43, 4);
-
- info->tag_type = IFH_EXTRACT_BITFIELD64(ifh[1], 16, 1);
- info->vid = IFH_EXTRACT_BITFIELD64(ifh[1], 0, 12);
-
- return 0;
-}
-
-static int ocelot_rx_frame_word(struct ocelot *ocelot, u8 grp, bool ifh,
- u32 *rval)
-{
- u32 val;
- u32 bytes_valid;
-
- val = ocelot_read_rix(ocelot, QS_XTR_RD, grp);
- if (val == XTR_NOT_READY) {
- if (ifh)
- return -EIO;
-
- do {
- val = ocelot_read_rix(ocelot, QS_XTR_RD, grp);
- } while (val == XTR_NOT_READY);
- }
-
- switch (val) {
- case XTR_ABORT:
- return -EIO;
- case XTR_EOF_0:
- case XTR_EOF_1:
- case XTR_EOF_2:
- case XTR_EOF_3:
- case XTR_PRUNED:
- bytes_valid = XTR_VALID_BYTES(val);
- val = ocelot_read_rix(ocelot, QS_XTR_RD, grp);
- if (val == XTR_ESCAPE)
- *rval = ocelot_read_rix(ocelot, QS_XTR_RD, grp);
- else
- *rval = val;
-
- return bytes_valid;
- case XTR_ESCAPE:
- *rval = ocelot_read_rix(ocelot, QS_XTR_RD, grp);
-
- return 4;
- default:
- *rval = val;
-
- return 4;
- }
-}
-
-static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg)
-{
- struct ocelot *ocelot = arg;
- int i = 0, grp = 0;
- int err = 0;
-
- if (!(ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)))
- return IRQ_NONE;
-
- do {
- struct skb_shared_hwtstamps *shhwtstamps;
- struct ocelot_port_private *priv;
- struct ocelot_port *ocelot_port;
- u64 tod_in_ns, full_ts_in_ns;
- struct frame_info info = {};
- struct net_device *dev;
- u32 ifh[4], val, *buf;
- struct timespec64 ts;
- int sz, len, buf_len;
- struct sk_buff *skb;
-
- for (i = 0; i < OCELOT_TAG_LEN / 4; i++) {
- err = ocelot_rx_frame_word(ocelot, grp, true, &ifh[i]);
- if (err != 4)
- break;
- }
-
- if (err != 4)
- break;
-
- /* At this point the IFH was read correctly, so it is safe to
- * presume that there is no error. The err needs to be reset
- * otherwise a frame could come in CPU queue between the while
- * condition and the check for error later on. And in that case
- * the new frame is just removed and not processed.
- */
- err = 0;
-
- ocelot_parse_ifh(ifh, &info);
-
- ocelot_port = ocelot->ports[info.port];
- priv = container_of(ocelot_port, struct ocelot_port_private,
- port);
- dev = priv->dev;
-
- skb = netdev_alloc_skb(dev, info.len);
-
- if (unlikely(!skb)) {
- netdev_err(dev, "Unable to allocate sk_buff\n");
- err = -ENOMEM;
- break;
- }
- buf_len = info.len - ETH_FCS_LEN;
- buf = (u32 *)skb_put(skb, buf_len);
-
- len = 0;
- do {
- sz = ocelot_rx_frame_word(ocelot, grp, false, &val);
- *buf++ = val;
- len += sz;
- } while (len < buf_len);
-
- /* Read the FCS */
- sz = ocelot_rx_frame_word(ocelot, grp, false, &val);
- /* Update the statistics if part of the FCS was read before */
- len -= ETH_FCS_LEN - sz;
-
- if (unlikely(dev->features & NETIF_F_RXFCS)) {
- buf = (u32 *)skb_put(skb, ETH_FCS_LEN);
- *buf = val;
- }
-
- if (sz < 0) {
- err = sz;
- break;
- }
-
- if (ocelot->ptp) {
- ocelot_ptp_gettime64(&ocelot->ptp_info, &ts);
-
- tod_in_ns = ktime_set(ts.tv_sec, ts.tv_nsec);
- if ((tod_in_ns & 0xffffffff) < info.timestamp)
- full_ts_in_ns = (((tod_in_ns >> 32) - 1) << 32) |
- info.timestamp;
- else
- full_ts_in_ns = (tod_in_ns & GENMASK_ULL(63, 32)) |
- info.timestamp;
-
- shhwtstamps = skb_hwtstamps(skb);
- memset(shhwtstamps, 0, sizeof(struct skb_shared_hwtstamps));
- shhwtstamps->hwtstamp = full_ts_in_ns;
- }
-
- /* Everything we see on an interface that is in the HW bridge
- * has already been forwarded.
- */
- if (ocelot->bridge_mask & BIT(info.port))
- skb->offload_fwd_mark = 1;
-
- skb->protocol = eth_type_trans(skb, dev);
- if (!skb_defer_rx_timestamp(skb))
- netif_rx(skb);
- dev->stats.rx_bytes += len;
- dev->stats.rx_packets++;
- } while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp));
-
- if (err)
- while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp))
- ocelot_read_rix(ocelot, QS_XTR_RD, grp);
-
- return IRQ_HANDLED;
-}
-
-static irqreturn_t ocelot_ptp_rdy_irq_handler(int irq, void *arg)
-{
- struct ocelot *ocelot = arg;
-
- ocelot_get_txtstamp(ocelot);
-
- return IRQ_HANDLED;
-}
-
-static const struct of_device_id mscc_ocelot_match[] = {
- { .compatible = "mscc,vsc7514-switch" },
- { }
-};
-MODULE_DEVICE_TABLE(of, mscc_ocelot_match);
-
-static int ocelot_reset(struct ocelot *ocelot)
-{
- int retries = 100;
- u32 val;
-
- regmap_field_write(ocelot->regfields[SYS_RESET_CFG_MEM_INIT], 1);
- regmap_field_write(ocelot->regfields[SYS_RESET_CFG_MEM_ENA], 1);
-
- do {
- msleep(1);
- regmap_field_read(ocelot->regfields[SYS_RESET_CFG_MEM_INIT],
- &val);
- } while (val && --retries);
-
- if (!retries)
- return -ETIMEDOUT;
-
- regmap_field_write(ocelot->regfields[SYS_RESET_CFG_MEM_ENA], 1);
- regmap_field_write(ocelot->regfields[SYS_RESET_CFG_CORE_ENA], 1);
-
- return 0;
-}
-
-static const struct ocelot_ops ocelot_ops = {
- .reset = ocelot_reset,
-};
-
-static const struct vcap_field vsc7514_vcap_is2_keys[] = {
- /* Common: 46 bits */
- [VCAP_IS2_TYPE] = { 0, 4},
- [VCAP_IS2_HK_FIRST] = { 4, 1},
- [VCAP_IS2_HK_PAG] = { 5, 8},
- [VCAP_IS2_HK_IGR_PORT_MASK] = { 13, 12},
- [VCAP_IS2_HK_RSV2] = { 25, 1},
- [VCAP_IS2_HK_HOST_MATCH] = { 26, 1},
- [VCAP_IS2_HK_L2_MC] = { 27, 1},
- [VCAP_IS2_HK_L2_BC] = { 28, 1},
- [VCAP_IS2_HK_VLAN_TAGGED] = { 29, 1},
- [VCAP_IS2_HK_VID] = { 30, 12},
- [VCAP_IS2_HK_DEI] = { 42, 1},
- [VCAP_IS2_HK_PCP] = { 43, 3},
- /* MAC_ETYPE / MAC_LLC / MAC_SNAP / OAM common */
- [VCAP_IS2_HK_L2_DMAC] = { 46, 48},
- [VCAP_IS2_HK_L2_SMAC] = { 94, 48},
- /* MAC_ETYPE (TYPE=000) */
- [VCAP_IS2_HK_MAC_ETYPE_ETYPE] = {142, 16},
- [VCAP_IS2_HK_MAC_ETYPE_L2_PAYLOAD0] = {158, 16},
- [VCAP_IS2_HK_MAC_ETYPE_L2_PAYLOAD1] = {174, 8},
- [VCAP_IS2_HK_MAC_ETYPE_L2_PAYLOAD2] = {182, 3},
- /* MAC_LLC (TYPE=001) */
- [VCAP_IS2_HK_MAC_LLC_L2_LLC] = {142, 40},
- /* MAC_SNAP (TYPE=010) */
- [VCAP_IS2_HK_MAC_SNAP_L2_SNAP] = {142, 40},
- /* MAC_ARP (TYPE=011) */
- [VCAP_IS2_HK_MAC_ARP_SMAC] = { 46, 48},
- [VCAP_IS2_HK_MAC_ARP_ADDR_SPACE_OK] = { 94, 1},
- [VCAP_IS2_HK_MAC_ARP_PROTO_SPACE_OK] = { 95, 1},
- [VCAP_IS2_HK_MAC_ARP_LEN_OK] = { 96, 1},
- [VCAP_IS2_HK_MAC_ARP_TARGET_MATCH] = { 97, 1},
- [VCAP_IS2_HK_MAC_ARP_SENDER_MATCH] = { 98, 1},
- [VCAP_IS2_HK_MAC_ARP_OPCODE_UNKNOWN] = { 99, 1},
- [VCAP_IS2_HK_MAC_ARP_OPCODE] = {100, 2},
- [VCAP_IS2_HK_MAC_ARP_L3_IP4_DIP] = {102, 32},
- [VCAP_IS2_HK_MAC_ARP_L3_IP4_SIP] = {134, 32},
- [VCAP_IS2_HK_MAC_ARP_DIP_EQ_SIP] = {166, 1},
- /* IP4_TCP_UDP / IP4_OTHER common */
- [VCAP_IS2_HK_IP4] = { 46, 1},
- [VCAP_IS2_HK_L3_FRAGMENT] = { 47, 1},
- [VCAP_IS2_HK_L3_FRAG_OFS_GT0] = { 48, 1},
- [VCAP_IS2_HK_L3_OPTIONS] = { 49, 1},
- [VCAP_IS2_HK_IP4_L3_TTL_GT0] = { 50, 1},
- [VCAP_IS2_HK_L3_TOS] = { 51, 8},
- [VCAP_IS2_HK_L3_IP4_DIP] = { 59, 32},
- [VCAP_IS2_HK_L3_IP4_SIP] = { 91, 32},
- [VCAP_IS2_HK_DIP_EQ_SIP] = {123, 1},
- /* IP4_TCP_UDP (TYPE=100) */
- [VCAP_IS2_HK_TCP] = {124, 1},
- [VCAP_IS2_HK_L4_SPORT] = {125, 16},
- [VCAP_IS2_HK_L4_DPORT] = {141, 16},
- [VCAP_IS2_HK_L4_RNG] = {157, 8},
- [VCAP_IS2_HK_L4_SPORT_EQ_DPORT] = {165, 1},
- [VCAP_IS2_HK_L4_SEQUENCE_EQ0] = {166, 1},
- [VCAP_IS2_HK_L4_URG] = {167, 1},
- [VCAP_IS2_HK_L4_ACK] = {168, 1},
- [VCAP_IS2_HK_L4_PSH] = {169, 1},
- [VCAP_IS2_HK_L4_RST] = {170, 1},
- [VCAP_IS2_HK_L4_SYN] = {171, 1},
- [VCAP_IS2_HK_L4_FIN] = {172, 1},
- [VCAP_IS2_HK_L4_1588_DOM] = {173, 8},
- [VCAP_IS2_HK_L4_1588_VER] = {181, 4},
- /* IP4_OTHER (TYPE=101) */
- [VCAP_IS2_HK_IP4_L3_PROTO] = {124, 8},
- [VCAP_IS2_HK_L3_PAYLOAD] = {132, 56},
- /* IP6_STD (TYPE=110) */
- [VCAP_IS2_HK_IP6_L3_TTL_GT0] = { 46, 1},
- [VCAP_IS2_HK_L3_IP6_SIP] = { 47, 128},
- [VCAP_IS2_HK_IP6_L3_PROTO] = {175, 8},
- /* OAM (TYPE=111) */
- [VCAP_IS2_HK_OAM_MEL_FLAGS] = {142, 7},
- [VCAP_IS2_HK_OAM_VER] = {149, 5},
- [VCAP_IS2_HK_OAM_OPCODE] = {154, 8},
- [VCAP_IS2_HK_OAM_FLAGS] = {162, 8},
- [VCAP_IS2_HK_OAM_MEPID] = {170, 16},
- [VCAP_IS2_HK_OAM_CCM_CNTS_EQ0] = {186, 1},
- [VCAP_IS2_HK_OAM_IS_Y1731] = {187, 1},
-};
-
-static const struct vcap_field vsc7514_vcap_is2_actions[] = {
- [VCAP_IS2_ACT_HIT_ME_ONCE] = { 0, 1},
- [VCAP_IS2_ACT_CPU_COPY_ENA] = { 1, 1},
- [VCAP_IS2_ACT_CPU_QU_NUM] = { 2, 3},
- [VCAP_IS2_ACT_MASK_MODE] = { 5, 2},
- [VCAP_IS2_ACT_MIRROR_ENA] = { 7, 1},
- [VCAP_IS2_ACT_LRN_DIS] = { 8, 1},
- [VCAP_IS2_ACT_POLICE_ENA] = { 9, 1},
- [VCAP_IS2_ACT_POLICE_IDX] = { 10, 9},
- [VCAP_IS2_ACT_POLICE_VCAP_ONLY] = { 19, 1},
- [VCAP_IS2_ACT_PORT_MASK] = { 20, 11},
- [VCAP_IS2_ACT_REW_OP] = { 31, 9},
- [VCAP_IS2_ACT_SMAC_REPLACE_ENA] = { 40, 1},
- [VCAP_IS2_ACT_RSV] = { 41, 2},
- [VCAP_IS2_ACT_ACL_ID] = { 43, 6},
- [VCAP_IS2_ACT_HIT_CNT] = { 49, 32},
-};
-
-static const struct vcap_props vsc7514_vcap_props[] = {
- [VCAP_IS2] = {
- .tg_width = 2,
- .sw_count = 4,
- .entry_count = VSC7514_VCAP_IS2_CNT,
- .entry_width = VSC7514_VCAP_IS2_ENTRY_WIDTH,
- .action_count = VSC7514_VCAP_IS2_CNT +
- VSC7514_VCAP_PORT_CNT + 2,
- .action_width = 99,
- .action_type_width = 1,
- .action_table = {
- [IS2_ACTION_TYPE_NORMAL] = {
- .width = 49,
- .count = 2
- },
- [IS2_ACTION_TYPE_SMAC_SIP] = {
- .width = 6,
- .count = 4
- },
- },
- .counter_words = 4,
- .counter_width = 32,
- },
-};
-
-static struct ptp_clock_info ocelot_ptp_clock_info = {
- .owner = THIS_MODULE,
- .name = "ocelot ptp",
- .max_adj = 0x7fffffff,
- .n_alarm = 0,
- .n_ext_ts = 0,
- .n_per_out = OCELOT_PTP_PINS_NUM,
- .n_pins = OCELOT_PTP_PINS_NUM,
- .pps = 0,
- .gettime64 = ocelot_ptp_gettime64,
- .settime64 = ocelot_ptp_settime64,
- .adjtime = ocelot_ptp_adjtime,
- .adjfine = ocelot_ptp_adjfine,
- .verify = ocelot_ptp_verify,
- .enable = ocelot_ptp_enable,
-};
-
-static int mscc_ocelot_probe(struct platform_device *pdev)
-{
- struct device_node *np = pdev->dev.of_node;
- struct device_node *ports, *portnp;
- int err, irq_xtr, irq_ptp_rdy;
- struct ocelot *ocelot;
- struct regmap *hsio;
- unsigned int i;
-
- struct {
- enum ocelot_target id;
- char *name;
- u8 optional:1;
- } io_target[] = {
- { SYS, "sys" },
- { REW, "rew" },
- { QSYS, "qsys" },
- { ANA, "ana" },
- { QS, "qs" },
- { S2, "s2" },
- { PTP, "ptp", 1 },
- };
-
- if (!np && !pdev->dev.platform_data)
- return -ENODEV;
-
- ocelot = devm_kzalloc(&pdev->dev, sizeof(*ocelot), GFP_KERNEL);
- if (!ocelot)
- return -ENOMEM;
-
- platform_set_drvdata(pdev, ocelot);
- ocelot->dev = &pdev->dev;
-
- for (i = 0; i < ARRAY_SIZE(io_target); i++) {
- struct regmap *target;
- struct resource *res;
-
- res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
- io_target[i].name);
-
- target = ocelot_regmap_init(ocelot, res);
- if (IS_ERR(target)) {
- if (io_target[i].optional) {
- ocelot->targets[io_target[i].id] = NULL;
- continue;
- }
- return PTR_ERR(target);
- }
-
- ocelot->targets[io_target[i].id] = target;
- }
-
- hsio = syscon_regmap_lookup_by_compatible("mscc,ocelot-hsio");
- if (IS_ERR(hsio)) {
- dev_err(&pdev->dev, "missing hsio syscon\n");
- return PTR_ERR(hsio);
- }
-
- ocelot->targets[HSIO] = hsio;
-
- err = ocelot_chip_init(ocelot, &ocelot_ops);
- if (err)
- return err;
-
- irq_xtr = platform_get_irq_byname(pdev, "xtr");
- if (irq_xtr < 0)
- return -ENODEV;
-
- err = devm_request_threaded_irq(&pdev->dev, irq_xtr, NULL,
- ocelot_xtr_irq_handler, IRQF_ONESHOT,
- "frame extraction", ocelot);
- if (err)
- return err;
-
- irq_ptp_rdy = platform_get_irq_byname(pdev, "ptp_rdy");
- if (irq_ptp_rdy > 0 && ocelot->targets[PTP]) {
- err = devm_request_threaded_irq(&pdev->dev, irq_ptp_rdy, NULL,
- ocelot_ptp_rdy_irq_handler,
- IRQF_ONESHOT, "ptp ready",
- ocelot);
- if (err)
- return err;
-
- /* Both the PTP interrupt and the PTP bank are available */
- ocelot->ptp = 1;
- }
-
- ports = of_get_child_by_name(np, "ethernet-ports");
- if (!ports) {
- dev_err(&pdev->dev, "no ethernet-ports child node found\n");
- return -ENODEV;
- }
-
- ocelot->num_phys_ports = of_get_child_count(ports);
-
- ocelot->ports = devm_kcalloc(&pdev->dev, ocelot->num_phys_ports,
- sizeof(struct ocelot_port *), GFP_KERNEL);
-
- ocelot->vcap_is2_keys = vsc7514_vcap_is2_keys;
- ocelot->vcap_is2_actions = vsc7514_vcap_is2_actions;
- ocelot->vcap = vsc7514_vcap_props;
-
- ocelot_init(ocelot);
- if (ocelot->ptp) {
- err = ocelot_init_timestamp(ocelot, &ocelot_ptp_clock_info);
- if (err) {
- dev_err(ocelot->dev,
- "Timestamp initialization failed\n");
- ocelot->ptp = 0;
- }
- }
-
- /* No NPI port */
- ocelot_configure_cpu(ocelot, -1, OCELOT_TAG_PREFIX_NONE,
- OCELOT_TAG_PREFIX_NONE);
-
- for_each_available_child_of_node(ports, portnp) {
- struct ocelot_port_private *priv;
- struct ocelot_port *ocelot_port;
- struct device_node *phy_node;
- phy_interface_t phy_mode;
- struct phy_device *phy;
- struct resource *res;
- struct phy *serdes;
- void __iomem *regs;
- char res_name[8];
- u32 port;
-
- if (of_property_read_u32(portnp, "reg", &port))
- continue;
-
- snprintf(res_name, sizeof(res_name), "port%d", port);
-
- res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
- res_name);
- regs = devm_ioremap_resource(&pdev->dev, res);
- if (IS_ERR(regs))
- continue;
-
- phy_node = of_parse_phandle(portnp, "phy-handle", 0);
- if (!phy_node)
- continue;
-
- phy = of_phy_find_device(phy_node);
- of_node_put(phy_node);
- if (!phy)
- continue;
-
- err = ocelot_probe_port(ocelot, port, regs, phy);
- if (err) {
- of_node_put(portnp);
- goto out_put_ports;
- }
-
- ocelot_port = ocelot->ports[port];
- priv = container_of(ocelot_port, struct ocelot_port_private,
- port);
-
- of_get_phy_mode(portnp, &phy_mode);
-
- ocelot_port->phy_mode = phy_mode;
-
- switch (ocelot_port->phy_mode) {
- case PHY_INTERFACE_MODE_NA:
- continue;
- case PHY_INTERFACE_MODE_SGMII:
- break;
- case PHY_INTERFACE_MODE_QSGMII:
- /* Ensure clock signals and speed is set on all
- * QSGMII links
- */
- ocelot_port_writel(ocelot_port,
- DEV_CLOCK_CFG_LINK_SPEED
- (OCELOT_SPEED_1000),
- DEV_CLOCK_CFG);
- break;
- default:
- dev_err(ocelot->dev,
- "invalid phy mode for port%d, (Q)SGMII only\n",
- port);
- of_node_put(portnp);
- err = -EINVAL;
- goto out_put_ports;
- }
-
- serdes = devm_of_phy_get(ocelot->dev, portnp, NULL);
- if (IS_ERR(serdes)) {
- err = PTR_ERR(serdes);
- if (err == -EPROBE_DEFER)
- dev_dbg(ocelot->dev, "deferring probe\n");
- else
- dev_err(ocelot->dev,
- "missing SerDes phys for port%d\n",
- port);
-
- of_node_put(portnp);
- goto out_put_ports;
- }
-
- priv->serdes = serdes;
- }
-
- register_netdevice_notifier(&ocelot_netdevice_nb);
- register_switchdev_notifier(&ocelot_switchdev_nb);
- register_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb);
-
- dev_info(&pdev->dev, "Ocelot switch probed\n");
-
-out_put_ports:
- of_node_put(ports);
- return err;
-}
-
-static int mscc_ocelot_remove(struct platform_device *pdev)
-{
- struct ocelot *ocelot = platform_get_drvdata(pdev);
-
- ocelot_deinit_timestamp(ocelot);
- ocelot_deinit(ocelot);
- unregister_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb);
- unregister_switchdev_notifier(&ocelot_switchdev_nb);
- unregister_netdevice_notifier(&ocelot_netdevice_nb);
-
- return 0;
-}
-
-static struct platform_driver mscc_ocelot_driver = {
- .probe = mscc_ocelot_probe,
- .remove = mscc_ocelot_remove,
- .driver = {
- .name = "ocelot-switch",
- .of_match_table = mscc_ocelot_match,
- },
-};
-
-module_platform_driver(mscc_ocelot_driver);
-
-MODULE_DESCRIPTION("Microsemi Ocelot switch driver");
-MODULE_AUTHOR("Alexandre Belloni <alexandre.belloni@xxxxxxxxxxx>");
-MODULE_LICENSE("Dual MIT/GPL");
diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
new file mode 100644
index 000000000000..66b58b242f77
--- /dev/null
+++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
@@ -0,0 +1,639 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Microsemi Ocelot Switch driver
+ *
+ * Copyright (c) 2017 Microsemi Corporation
+ */
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of_net.h>
+#include <linux/netdevice.h>
+#include <linux/of_mdio.h>
+#include <linux/of_platform.h>
+#include <linux/mfd/syscon.h>
+#include <linux/skbuff.h>
+#include <net/switchdev.h>
+
+#include <soc/mscc/ocelot_vcap.h>
+#include "ocelot.h"
+
+#define IFH_EXTRACT_BITFIELD64(x, o, w) (((x) >> (o)) & GENMASK_ULL((w) - 1, 0))
+#define VSC7514_VCAP_IS2_CNT 64
+#define VSC7514_VCAP_IS2_ENTRY_WIDTH 376
+#define VSC7514_VCAP_IS2_ACTION_WIDTH 99
+#define VSC7514_VCAP_PORT_CNT 11
+
+static int ocelot_parse_ifh(u32 *_ifh, struct frame_info *info)
+{
+ u8 llen, wlen;
+ u64 ifh[2];
+
+ ifh[0] = be64_to_cpu(((__force __be64 *)_ifh)[0]);
+ ifh[1] = be64_to_cpu(((__force __be64 *)_ifh)[1]);
+
+ wlen = IFH_EXTRACT_BITFIELD64(ifh[0], 7, 8);
+ llen = IFH_EXTRACT_BITFIELD64(ifh[0], 15, 6);
+
+ info->len = OCELOT_BUFFER_CELL_SZ * wlen + llen - 80;
+
+ info->timestamp = IFH_EXTRACT_BITFIELD64(ifh[0], 21, 32);
+
+ info->port = IFH_EXTRACT_BITFIELD64(ifh[1], 43, 4);
+
+ info->tag_type = IFH_EXTRACT_BITFIELD64(ifh[1], 16, 1);
+ info->vid = IFH_EXTRACT_BITFIELD64(ifh[1], 0, 12);
+
+ return 0;
+}
+
+static int ocelot_rx_frame_word(struct ocelot *ocelot, u8 grp, bool ifh,
+ u32 *rval)
+{
+ u32 val;
+ u32 bytes_valid;
+
+ val = ocelot_read_rix(ocelot, QS_XTR_RD, grp);
+ if (val == XTR_NOT_READY) {
+ if (ifh)
+ return -EIO;
+
+ do {
+ val = ocelot_read_rix(ocelot, QS_XTR_RD, grp);
+ } while (val == XTR_NOT_READY);
+ }
+
+ switch (val) {
+ case XTR_ABORT:
+ return -EIO;
+ case XTR_EOF_0:
+ case XTR_EOF_1:
+ case XTR_EOF_2:
+ case XTR_EOF_3:
+ case XTR_PRUNED:
+ bytes_valid = XTR_VALID_BYTES(val);
+ val = ocelot_read_rix(ocelot, QS_XTR_RD, grp);
+ if (val == XTR_ESCAPE)
+ *rval = ocelot_read_rix(ocelot, QS_XTR_RD, grp);
+ else
+ *rval = val;
+
+ return bytes_valid;
+ case XTR_ESCAPE:
+ *rval = ocelot_read_rix(ocelot, QS_XTR_RD, grp);
+
+ return 4;
+ default:
+ *rval = val;
+
+ return 4;
+ }
+}
+
+static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg)
+{
+ struct ocelot *ocelot = arg;
+ int i = 0, grp = 0;
+ int err = 0;
+
+ if (!(ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)))
+ return IRQ_NONE;
+
+ do {
+ struct skb_shared_hwtstamps *shhwtstamps;
+ struct ocelot_port_private *priv;
+ struct ocelot_port *ocelot_port;
+ u64 tod_in_ns, full_ts_in_ns;
+ struct frame_info info = {};
+ struct net_device *dev;
+ u32 ifh[4], val, *buf;
+ struct timespec64 ts;
+ int sz, len, buf_len;
+ struct sk_buff *skb;
+
+ for (i = 0; i < OCELOT_TAG_LEN / 4; i++) {
+ err = ocelot_rx_frame_word(ocelot, grp, true, &ifh[i]);
+ if (err != 4)
+ break;
+ }
+
+ if (err != 4)
+ break;
+
+ /* At this point the IFH was read correctly, so it is safe to
+ * presume that there is no error. The err needs to be reset
+ * otherwise a frame could come in CPU queue between the while
+ * condition and the check for error later on. And in that case
+ * the new frame is just removed and not processed.
+ */
+ err = 0;
+
+ ocelot_parse_ifh(ifh, &info);
+
+ ocelot_port = ocelot->ports[info.port];
+ priv = container_of(ocelot_port, struct ocelot_port_private,
+ port);
+ dev = priv->dev;
+
+ skb = netdev_alloc_skb(dev, info.len);
+
+ if (unlikely(!skb)) {
+ netdev_err(dev, "Unable to allocate sk_buff\n");
+ err = -ENOMEM;
+ break;
+ }
+ buf_len = info.len - ETH_FCS_LEN;
+ buf = (u32 *)skb_put(skb, buf_len);
+
+ len = 0;
+ do {
+ sz = ocelot_rx_frame_word(ocelot, grp, false, &val);
+ *buf++ = val;
+ len += sz;
+ } while (len < buf_len);
+
+ /* Read the FCS */
+ sz = ocelot_rx_frame_word(ocelot, grp, false, &val);
+ /* Update the statistics if part of the FCS was read before */
+ len -= ETH_FCS_LEN - sz;
+
+ if (unlikely(dev->features & NETIF_F_RXFCS)) {
+ buf = (u32 *)skb_put(skb, ETH_FCS_LEN);
+ *buf = val;
+ }
+
+ if (sz < 0) {
+ err = sz;
+ break;
+ }
+
+ if (ocelot->ptp) {
+ ocelot_ptp_gettime64(&ocelot->ptp_info, &ts);
+
+ tod_in_ns = ktime_set(ts.tv_sec, ts.tv_nsec);
+ if ((tod_in_ns & 0xffffffff) < info.timestamp)
+ full_ts_in_ns = (((tod_in_ns >> 32) - 1) << 32) |
+ info.timestamp;
+ else
+ full_ts_in_ns = (tod_in_ns & GENMASK_ULL(63, 32)) |
+ info.timestamp;
+
+ shhwtstamps = skb_hwtstamps(skb);
+ memset(shhwtstamps, 0, sizeof(struct skb_shared_hwtstamps));
+ shhwtstamps->hwtstamp = full_ts_in_ns;
+ }
+
+ /* Everything we see on an interface that is in the HW bridge
+ * has already been forwarded.
+ */
+ if (ocelot->bridge_mask & BIT(info.port))
+ skb->offload_fwd_mark = 1;
+
+ skb->protocol = eth_type_trans(skb, dev);
+ if (!skb_defer_rx_timestamp(skb))
+ netif_rx(skb);
+ dev->stats.rx_bytes += len;
+ dev->stats.rx_packets++;
+ } while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp));
+
+ if (err)
+ while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp))
+ ocelot_read_rix(ocelot, QS_XTR_RD, grp);
+
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t ocelot_ptp_rdy_irq_handler(int irq, void *arg)
+{
+ struct ocelot *ocelot = arg;
+
+ ocelot_get_txtstamp(ocelot);
+
+ return IRQ_HANDLED;
+}
+
+static const struct of_device_id mscc_ocelot_match[] = {
+ { .compatible = "mscc,vsc7514-switch" },
+ { }
+};
+MODULE_DEVICE_TABLE(of, mscc_ocelot_match);
+
+static int ocelot_reset(struct ocelot *ocelot)
+{
+ int retries = 100;
+ u32 val;
+
+ regmap_field_write(ocelot->regfields[SYS_RESET_CFG_MEM_INIT], 1);
+ regmap_field_write(ocelot->regfields[SYS_RESET_CFG_MEM_ENA], 1);
+
+ do {
+ msleep(1);
+ regmap_field_read(ocelot->regfields[SYS_RESET_CFG_MEM_INIT],
+ &val);
+ } while (val && --retries);
+
+ if (!retries)
+ return -ETIMEDOUT;
+
+ regmap_field_write(ocelot->regfields[SYS_RESET_CFG_MEM_ENA], 1);
+ regmap_field_write(ocelot->regfields[SYS_RESET_CFG_CORE_ENA], 1);
+
+ return 0;
+}
+
+/* Watermark encode
+ * Bit 8: Unit; 0:1, 1:16
+ * Bit 7-0: Value to be multiplied with unit
+ */
+static u16 ocelot_wm_enc(u16 value)
+{
+ if (value >= BIT(8))
+ return BIT(8) | (value / 16);
+
+ return value;
+}
+
+static const struct ocelot_ops ocelot_ops = {
+ .reset = ocelot_reset,
+ .wm_enc = ocelot_wm_enc,
+};
+
+static const struct vcap_field vsc7514_vcap_is2_keys[] = {
+ /* Common: 46 bits */
+ [VCAP_IS2_TYPE] = { 0, 4},
+ [VCAP_IS2_HK_FIRST] = { 4, 1},
+ [VCAP_IS2_HK_PAG] = { 5, 8},
+ [VCAP_IS2_HK_IGR_PORT_MASK] = { 13, 12},
+ [VCAP_IS2_HK_RSV2] = { 25, 1},
+ [VCAP_IS2_HK_HOST_MATCH] = { 26, 1},
+ [VCAP_IS2_HK_L2_MC] = { 27, 1},
+ [VCAP_IS2_HK_L2_BC] = { 28, 1},
+ [VCAP_IS2_HK_VLAN_TAGGED] = { 29, 1},
+ [VCAP_IS2_HK_VID] = { 30, 12},
+ [VCAP_IS2_HK_DEI] = { 42, 1},
+ [VCAP_IS2_HK_PCP] = { 43, 3},
+ /* MAC_ETYPE / MAC_LLC / MAC_SNAP / OAM common */
+ [VCAP_IS2_HK_L2_DMAC] = { 46, 48},
+ [VCAP_IS2_HK_L2_SMAC] = { 94, 48},
+ /* MAC_ETYPE (TYPE=000) */
+ [VCAP_IS2_HK_MAC_ETYPE_ETYPE] = {142, 16},
+ [VCAP_IS2_HK_MAC_ETYPE_L2_PAYLOAD0] = {158, 16},
+ [VCAP_IS2_HK_MAC_ETYPE_L2_PAYLOAD1] = {174, 8},
+ [VCAP_IS2_HK_MAC_ETYPE_L2_PAYLOAD2] = {182, 3},
+ /* MAC_LLC (TYPE=001) */
+ [VCAP_IS2_HK_MAC_LLC_L2_LLC] = {142, 40},
+ /* MAC_SNAP (TYPE=010) */
+ [VCAP_IS2_HK_MAC_SNAP_L2_SNAP] = {142, 40},
+ /* MAC_ARP (TYPE=011) */
+ [VCAP_IS2_HK_MAC_ARP_SMAC] = { 46, 48},
+ [VCAP_IS2_HK_MAC_ARP_ADDR_SPACE_OK] = { 94, 1},
+ [VCAP_IS2_HK_MAC_ARP_PROTO_SPACE_OK] = { 95, 1},
+ [VCAP_IS2_HK_MAC_ARP_LEN_OK] = { 96, 1},
+ [VCAP_IS2_HK_MAC_ARP_TARGET_MATCH] = { 97, 1},
+ [VCAP_IS2_HK_MAC_ARP_SENDER_MATCH] = { 98, 1},
+ [VCAP_IS2_HK_MAC_ARP_OPCODE_UNKNOWN] = { 99, 1},
+ [VCAP_IS2_HK_MAC_ARP_OPCODE] = {100, 2},
+ [VCAP_IS2_HK_MAC_ARP_L3_IP4_DIP] = {102, 32},
+ [VCAP_IS2_HK_MAC_ARP_L3_IP4_SIP] = {134, 32},
+ [VCAP_IS2_HK_MAC_ARP_DIP_EQ_SIP] = {166, 1},
+ /* IP4_TCP_UDP / IP4_OTHER common */
+ [VCAP_IS2_HK_IP4] = { 46, 1},
+ [VCAP_IS2_HK_L3_FRAGMENT] = { 47, 1},
+ [VCAP_IS2_HK_L3_FRAG_OFS_GT0] = { 48, 1},
+ [VCAP_IS2_HK_L3_OPTIONS] = { 49, 1},
+ [VCAP_IS2_HK_IP4_L3_TTL_GT0] = { 50, 1},
+ [VCAP_IS2_HK_L3_TOS] = { 51, 8},
+ [VCAP_IS2_HK_L3_IP4_DIP] = { 59, 32},
+ [VCAP_IS2_HK_L3_IP4_SIP] = { 91, 32},
+ [VCAP_IS2_HK_DIP_EQ_SIP] = {123, 1},
+ /* IP4_TCP_UDP (TYPE=100) */
+ [VCAP_IS2_HK_TCP] = {124, 1},
+ [VCAP_IS2_HK_L4_SPORT] = {125, 16},
+ [VCAP_IS2_HK_L4_DPORT] = {141, 16},
+ [VCAP_IS2_HK_L4_RNG] = {157, 8},
+ [VCAP_IS2_HK_L4_SPORT_EQ_DPORT] = {165, 1},
+ [VCAP_IS2_HK_L4_SEQUENCE_EQ0] = {166, 1},
+ [VCAP_IS2_HK_L4_URG] = {167, 1},
+ [VCAP_IS2_HK_L4_ACK] = {168, 1},
+ [VCAP_IS2_HK_L4_PSH] = {169, 1},
+ [VCAP_IS2_HK_L4_RST] = {170, 1},
+ [VCAP_IS2_HK_L4_SYN] = {171, 1},
+ [VCAP_IS2_HK_L4_FIN] = {172, 1},
+ [VCAP_IS2_HK_L4_1588_DOM] = {173, 8},
+ [VCAP_IS2_HK_L4_1588_VER] = {181, 4},
+ /* IP4_OTHER (TYPE=101) */
+ [VCAP_IS2_HK_IP4_L3_PROTO] = {124, 8},
+ [VCAP_IS2_HK_L3_PAYLOAD] = {132, 56},
+ /* IP6_STD (TYPE=110) */
+ [VCAP_IS2_HK_IP6_L3_TTL_GT0] = { 46, 1},
+ [VCAP_IS2_HK_L3_IP6_SIP] = { 47, 128},
+ [VCAP_IS2_HK_IP6_L3_PROTO] = {175, 8},
+ /* OAM (TYPE=111) */
+ [VCAP_IS2_HK_OAM_MEL_FLAGS] = {142, 7},
+ [VCAP_IS2_HK_OAM_VER] = {149, 5},
+ [VCAP_IS2_HK_OAM_OPCODE] = {154, 8},
+ [VCAP_IS2_HK_OAM_FLAGS] = {162, 8},
+ [VCAP_IS2_HK_OAM_MEPID] = {170, 16},
+ [VCAP_IS2_HK_OAM_CCM_CNTS_EQ0] = {186, 1},
+ [VCAP_IS2_HK_OAM_IS_Y1731] = {187, 1},
+};
+
+static const struct vcap_field vsc7514_vcap_is2_actions[] = {
+ [VCAP_IS2_ACT_HIT_ME_ONCE] = { 0, 1},
+ [VCAP_IS2_ACT_CPU_COPY_ENA] = { 1, 1},
+ [VCAP_IS2_ACT_CPU_QU_NUM] = { 2, 3},
+ [VCAP_IS2_ACT_MASK_MODE] = { 5, 2},
+ [VCAP_IS2_ACT_MIRROR_ENA] = { 7, 1},
+ [VCAP_IS2_ACT_LRN_DIS] = { 8, 1},
+ [VCAP_IS2_ACT_POLICE_ENA] = { 9, 1},
+ [VCAP_IS2_ACT_POLICE_IDX] = { 10, 9},
+ [VCAP_IS2_ACT_POLICE_VCAP_ONLY] = { 19, 1},
+ [VCAP_IS2_ACT_PORT_MASK] = { 20, 11},
+ [VCAP_IS2_ACT_REW_OP] = { 31, 9},
+ [VCAP_IS2_ACT_SMAC_REPLACE_ENA] = { 40, 1},
+ [VCAP_IS2_ACT_RSV] = { 41, 2},
+ [VCAP_IS2_ACT_ACL_ID] = { 43, 6},
+ [VCAP_IS2_ACT_HIT_CNT] = { 49, 32},
+};
+
+static const struct vcap_props vsc7514_vcap_props[] = {
+ [VCAP_IS2] = {
+ .tg_width = 2,
+ .sw_count = 4,
+ .entry_count = VSC7514_VCAP_IS2_CNT,
+ .entry_width = VSC7514_VCAP_IS2_ENTRY_WIDTH,
+ .action_count = VSC7514_VCAP_IS2_CNT +
+ VSC7514_VCAP_PORT_CNT + 2,
+ .action_width = 99,
+ .action_type_width = 1,
+ .action_table = {
+ [IS2_ACTION_TYPE_NORMAL] = {
+ .width = 49,
+ .count = 2
+ },
+ [IS2_ACTION_TYPE_SMAC_SIP] = {
+ .width = 6,
+ .count = 4
+ },
+ },
+ .counter_words = 4,
+ .counter_width = 32,
+ },
+};
+
+static struct ptp_clock_info ocelot_ptp_clock_info = {
+ .owner = THIS_MODULE,
+ .name = "ocelot ptp",
+ .max_adj = 0x7fffffff,
+ .n_alarm = 0,
+ .n_ext_ts = 0,
+ .n_per_out = OCELOT_PTP_PINS_NUM,
+ .n_pins = OCELOT_PTP_PINS_NUM,
+ .pps = 0,
+ .gettime64 = ocelot_ptp_gettime64,
+ .settime64 = ocelot_ptp_settime64,
+ .adjtime = ocelot_ptp_adjtime,
+ .adjfine = ocelot_ptp_adjfine,
+ .verify = ocelot_ptp_verify,
+ .enable = ocelot_ptp_enable,
+};
+
+static int mscc_ocelot_probe(struct platform_device *pdev)
+{
+ struct device_node *np = pdev->dev.of_node;
+ struct device_node *ports, *portnp;
+ int err, irq_xtr, irq_ptp_rdy;
+ struct ocelot *ocelot;
+ struct regmap *hsio;
+ unsigned int i;
+
+ struct {
+ enum ocelot_target id;
+ char *name;
+ u8 optional:1;
+ } io_target[] = {
+ { SYS, "sys" },
+ { REW, "rew" },
+ { QSYS, "qsys" },
+ { ANA, "ana" },
+ { QS, "qs" },
+ { S2, "s2" },
+ { PTP, "ptp", 1 },
+ };
+
+ if (!np && !pdev->dev.platform_data)
+ return -ENODEV;
+
+ ocelot = devm_kzalloc(&pdev->dev, sizeof(*ocelot), GFP_KERNEL);
+ if (!ocelot)
+ return -ENOMEM;
+
+ platform_set_drvdata(pdev, ocelot);
+ ocelot->dev = &pdev->dev;
+
+ for (i = 0; i < ARRAY_SIZE(io_target); i++) {
+ struct regmap *target;
+ struct resource *res;
+
+ res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+ io_target[i].name);
+
+ target = ocelot_regmap_init(ocelot, res);
+ if (IS_ERR(target)) {
+ if (io_target[i].optional) {
+ ocelot->targets[io_target[i].id] = NULL;
+ continue;
+ }
+ return PTR_ERR(target);
+ }
+
+ ocelot->targets[io_target[i].id] = target;
+ }
+
+ hsio = syscon_regmap_lookup_by_compatible("mscc,ocelot-hsio");
+ if (IS_ERR(hsio)) {
+ dev_err(&pdev->dev, "missing hsio syscon\n");
+ return PTR_ERR(hsio);
+ }
+
+ ocelot->targets[HSIO] = hsio;
+
+ err = ocelot_chip_init(ocelot, &ocelot_ops);
+ if (err)
+ return err;
+
+ irq_xtr = platform_get_irq_byname(pdev, "xtr");
+ if (irq_xtr < 0)
+ return -ENODEV;
+
+ err = devm_request_threaded_irq(&pdev->dev, irq_xtr, NULL,
+ ocelot_xtr_irq_handler, IRQF_ONESHOT,
+ "frame extraction", ocelot);
+ if (err)
+ return err;
+
+ irq_ptp_rdy = platform_get_irq_byname(pdev, "ptp_rdy");
+ if (irq_ptp_rdy > 0 && ocelot->targets[PTP]) {
+ err = devm_request_threaded_irq(&pdev->dev, irq_ptp_rdy, NULL,
+ ocelot_ptp_rdy_irq_handler,
+ IRQF_ONESHOT, "ptp ready",
+ ocelot);
+ if (err)
+ return err;
+
+ /* Both the PTP interrupt and the PTP bank are available */
+ ocelot->ptp = 1;
+ }
+
+ ports = of_get_child_by_name(np, "ethernet-ports");
+ if (!ports) {
+ dev_err(&pdev->dev, "no ethernet-ports child node found\n");
+ return -ENODEV;
+ }
+
+ ocelot->num_phys_ports = of_get_child_count(ports);
+
+ ocelot->ports = devm_kcalloc(&pdev->dev, ocelot->num_phys_ports,
+ sizeof(struct ocelot_port *), GFP_KERNEL);
+
+ ocelot->vcap_is2_keys = vsc7514_vcap_is2_keys;
+ ocelot->vcap_is2_actions = vsc7514_vcap_is2_actions;
+ ocelot->vcap = vsc7514_vcap_props;
+
+ ocelot_init(ocelot);
+ if (ocelot->ptp) {
+ err = ocelot_init_timestamp(ocelot, &ocelot_ptp_clock_info);
+ if (err) {
+ dev_err(ocelot->dev,
+ "Timestamp initialization failed\n");
+ ocelot->ptp = 0;
+ }
+ }
+
+ /* No NPI port */
+ ocelot_configure_cpu(ocelot, -1, OCELOT_TAG_PREFIX_NONE,
+ OCELOT_TAG_PREFIX_NONE);
+
+ for_each_available_child_of_node(ports, portnp) {
+ struct ocelot_port_private *priv;
+ struct ocelot_port *ocelot_port;
+ struct device_node *phy_node;
+ phy_interface_t phy_mode;
+ struct phy_device *phy;
+ struct resource *res;
+ struct phy *serdes;
+ void __iomem *regs;
+ char res_name[8];
+ u32 port;
+
+ if (of_property_read_u32(portnp, "reg", &port))
+ continue;
+
+ snprintf(res_name, sizeof(res_name), "port%d", port);
+
+ res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+ res_name);
+ regs = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(regs))
+ continue;
+
+ phy_node = of_parse_phandle(portnp, "phy-handle", 0);
+ if (!phy_node)
+ continue;
+
+ phy = of_phy_find_device(phy_node);
+ of_node_put(phy_node);
+ if (!phy)
+ continue;
+
+ err = ocelot_probe_port(ocelot, port, regs, phy);
+ if (err) {
+ of_node_put(portnp);
+ goto out_put_ports;
+ }
+
+ ocelot_port = ocelot->ports[port];
+ priv = container_of(ocelot_port, struct ocelot_port_private,
+ port);
+
+ of_get_phy_mode(portnp, &phy_mode);
+
+ ocelot_port->phy_mode = phy_mode;
+
+ switch (ocelot_port->phy_mode) {
+ case PHY_INTERFACE_MODE_NA:
+ continue;
+ case PHY_INTERFACE_MODE_SGMII:
+ break;
+ case PHY_INTERFACE_MODE_QSGMII:
+ /* Ensure clock signals and speed is set on all
+ * QSGMII links
+ */
+ ocelot_port_writel(ocelot_port,
+ DEV_CLOCK_CFG_LINK_SPEED
+ (OCELOT_SPEED_1000),
+ DEV_CLOCK_CFG);
+ break;
+ default:
+ dev_err(ocelot->dev,
+ "invalid phy mode for port%d, (Q)SGMII only\n",
+ port);
+ of_node_put(portnp);
+ err = -EINVAL;
+ goto out_put_ports;
+ }
+
+ serdes = devm_of_phy_get(ocelot->dev, portnp, NULL);
+ if (IS_ERR(serdes)) {
+ err = PTR_ERR(serdes);
+ if (err == -EPROBE_DEFER)
+ dev_dbg(ocelot->dev, "deferring probe\n");
+ else
+ dev_err(ocelot->dev,
+ "missing SerDes phys for port%d\n",
+ port);
+
+ of_node_put(portnp);
+ goto out_put_ports;
+ }
+
+ priv->serdes = serdes;
+ }
+
+ register_netdevice_notifier(&ocelot_netdevice_nb);
+ register_switchdev_notifier(&ocelot_switchdev_nb);
+ register_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb);
+
+ dev_info(&pdev->dev, "Ocelot switch probed\n");
+
+out_put_ports:
+ of_node_put(ports);
+ return err;
+}
+
+static int mscc_ocelot_remove(struct platform_device *pdev)
+{
+ struct ocelot *ocelot = platform_get_drvdata(pdev);
+
+ ocelot_deinit_timestamp(ocelot);
+ ocelot_deinit(ocelot);
+ unregister_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb);
+ unregister_switchdev_notifier(&ocelot_switchdev_nb);
+ unregister_netdevice_notifier(&ocelot_netdevice_nb);
+
+ return 0;
+}
+
+static struct platform_driver mscc_ocelot_driver = {
+ .probe = mscc_ocelot_probe,
+ .remove = mscc_ocelot_remove,
+ .driver = {
+ .name = "ocelot-switch",
+ .of_match_table = mscc_ocelot_match,
+ },
+};
+
+module_platform_driver(mscc_ocelot_driver);
+
+MODULE_DESCRIPTION("Microsemi Ocelot switch driver");
+MODULE_AUTHOR("Alexandre Belloni <alexandre.belloni@xxxxxxxxxxx>");
+MODULE_LICENSE("Dual MIT/GPL");
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index b660ddbe4025..fe173ea894e2 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2113,11 +2113,18 @@ static void rtl_release_firmware(struct rtl8169_private *tp)

void r8169_apply_firmware(struct rtl8169_private *tp)
{
+ int val;
+
/* TODO: release firmware if rtl_fw_write_firmware signals failure. */
if (tp->rtl_fw) {
rtl_fw_write_firmware(tp, tp->rtl_fw);
/* At least one firmware doesn't reset tp->ocp_base. */
tp->ocp_base = OCP_STD_PHY_BASE;
+
+ /* PHY soft reset may still be in progress */
+ phy_read_poll_timeout(tp->phydev, MII_BMCR, val,
+ !(val & BMCR_RESET),
+ 50000, 600000, true);
}
}

@@ -2951,7 +2958,7 @@ static void rtl_hw_start_8168f_1(struct rtl8169_private *tp)
{ 0x08, 0x0001, 0x0002 },
{ 0x09, 0x0000, 0x0080 },
{ 0x19, 0x0000, 0x0224 },
- { 0x00, 0x0000, 0x0004 },
+ { 0x00, 0x0000, 0x0008 },
{ 0x0c, 0x3df0, 0x0200 },
};

@@ -2968,7 +2975,7 @@ static void rtl_hw_start_8411(struct rtl8169_private *tp)
{ 0x06, 0x00c0, 0x0020 },
{ 0x0f, 0xffff, 0x5200 },
{ 0x19, 0x0000, 0x0224 },
- { 0x00, 0x0000, 0x0004 },
+ { 0x00, 0x0000, 0x0008 },
{ 0x0c, 0x3df0, 0x0200 },
};

diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index df89d09b253e..99f7aae102ce 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1342,51 +1342,6 @@ static inline int ravb_hook_irq(unsigned int irq, irq_handler_t handler,
return error;
}

-/* MDIO bus init function */
-static int ravb_mdio_init(struct ravb_private *priv)
-{
- struct platform_device *pdev = priv->pdev;
- struct device *dev = &pdev->dev;
- int error;
-
- /* Bitbang init */
- priv->mdiobb.ops = &bb_ops;
-
- /* MII controller setting */
- priv->mii_bus = alloc_mdio_bitbang(&priv->mdiobb);
- if (!priv->mii_bus)
- return -ENOMEM;
-
- /* Hook up MII support for ethtool */
- priv->mii_bus->name = "ravb_mii";
- priv->mii_bus->parent = dev;
- snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x",
- pdev->name, pdev->id);
-
- /* Register MDIO bus */
- error = of_mdiobus_register(priv->mii_bus, dev->of_node);
- if (error)
- goto out_free_bus;
-
- return 0;
-
-out_free_bus:
- free_mdio_bitbang(priv->mii_bus);
- return error;
-}
-
-/* MDIO bus release function */
-static int ravb_mdio_release(struct ravb_private *priv)
-{
- /* Unregister mdio bus */
- mdiobus_unregister(priv->mii_bus);
-
- /* Free bitbang info */
- free_mdio_bitbang(priv->mii_bus);
-
- return 0;
-}
-
/* Network device open function for Ethernet AVB */
static int ravb_open(struct net_device *ndev)
{
@@ -1395,13 +1350,6 @@ static int ravb_open(struct net_device *ndev)
struct device *dev = &pdev->dev;
int error;

- /* MDIO bus init */
- error = ravb_mdio_init(priv);
- if (error) {
- netdev_err(ndev, "failed to initialize MDIO\n");
- return error;
- }
-
napi_enable(&priv->napi[RAVB_BE]);
napi_enable(&priv->napi[RAVB_NC]);

@@ -1479,7 +1427,6 @@ static int ravb_open(struct net_device *ndev)
out_napi_off:
napi_disable(&priv->napi[RAVB_NC]);
napi_disable(&priv->napi[RAVB_BE]);
- ravb_mdio_release(priv);
return error;
}

@@ -1789,8 +1736,6 @@ static int ravb_close(struct net_device *ndev)
ravb_ring_free(ndev, RAVB_BE);
ravb_ring_free(ndev, RAVB_NC);

- ravb_mdio_release(priv);
-
return 0;
}

@@ -1942,6 +1887,51 @@ static const struct net_device_ops ravb_netdev_ops = {
.ndo_set_features = ravb_set_features,
};

+/* MDIO bus init function */
+static int ravb_mdio_init(struct ravb_private *priv)
+{
+ struct platform_device *pdev = priv->pdev;
+ struct device *dev = &pdev->dev;
+ int error;
+
+ /* Bitbang init */
+ priv->mdiobb.ops = &bb_ops;
+
+ /* MII controller setting */
+ priv->mii_bus = alloc_mdio_bitbang(&priv->mdiobb);
+ if (!priv->mii_bus)
+ return -ENOMEM;
+
+ /* Hook up MII support for ethtool */
+ priv->mii_bus->name = "ravb_mii";
+ priv->mii_bus->parent = dev;
+ snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x",
+ pdev->name, pdev->id);
+
+ /* Register MDIO bus */
+ error = of_mdiobus_register(priv->mii_bus, dev->of_node);
+ if (error)
+ goto out_free_bus;
+
+ return 0;
+
+out_free_bus:
+ free_mdio_bitbang(priv->mii_bus);
+ return error;
+}
+
+/* MDIO bus release function */
+static int ravb_mdio_release(struct ravb_private *priv)
+{
+ /* Unregister mdio bus */
+ mdiobus_unregister(priv->mii_bus);
+
+ /* Free bitbang info */
+ free_mdio_bitbang(priv->mii_bus);
+
+ return 0;
+}
+
static const struct of_device_id ravb_match_table[] = {
{ .compatible = "renesas,etheravb-r8a7790", .data = (void *)RCAR_GEN2 },
{ .compatible = "renesas,etheravb-r8a7794", .data = (void *)RCAR_GEN2 },
@@ -2184,6 +2174,13 @@ static int ravb_probe(struct platform_device *pdev)
eth_hw_addr_random(ndev);
}

+ /* MDIO bus init */
+ error = ravb_mdio_init(priv);
+ if (error) {
+ dev_err(&pdev->dev, "failed to initialize MDIO\n");
+ goto out_dma_free;
+ }
+
netif_napi_add(ndev, &priv->napi[RAVB_BE], ravb_poll, 64);
netif_napi_add(ndev, &priv->napi[RAVB_NC], ravb_poll, 64);

@@ -2205,6 +2202,8 @@ static int ravb_probe(struct platform_device *pdev)
out_napi_del:
netif_napi_del(&priv->napi[RAVB_NC]);
netif_napi_del(&priv->napi[RAVB_BE]);
+ ravb_mdio_release(priv);
+out_dma_free:
dma_free_coherent(ndev->dev.parent, priv->desc_bat_size, priv->desc_bat,
priv->desc_bat_dma);

@@ -2236,6 +2235,7 @@ static int ravb_remove(struct platform_device *pdev)
unregister_netdev(ndev);
netif_napi_del(&priv->napi[RAVB_NC]);
netif_napi_del(&priv->napi[RAVB_BE]);
+ ravb_mdio_release(priv);
pm_runtime_disable(&pdev->dev);
free_netdev(ndev);
platform_set_drvdata(pdev, NULL);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index 2ac9dfb3462c..9e6d60e75f85 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -653,7 +653,6 @@ static void intel_eth_pci_remove(struct pci_dev *pdev)

pci_free_irq_vectors(pdev);

- clk_disable_unprepare(priv->plat->stmmac_clk);
clk_unregister_fixed_rate(priv->plat->stmmac_clk);

pcim_iounmap_regions(pdev, BIT(0));
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 9c02fc754bf1..545696971f65 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -203,6 +203,8 @@ struct stmmac_priv {
int eee_enabled;
int eee_active;
int tx_lpi_timer;
+ int tx_lpi_enabled;
+ int eee_tw_timer;
unsigned int mode;
unsigned int chain_mode;
int extend_desc;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index eae11c585025..b82c6715f95f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -652,6 +652,7 @@ static int stmmac_ethtool_op_get_eee(struct net_device *dev,
edata->eee_enabled = priv->eee_enabled;
edata->eee_active = priv->eee_active;
edata->tx_lpi_timer = priv->tx_lpi_timer;
+ edata->tx_lpi_enabled = priv->tx_lpi_enabled;

return phylink_ethtool_get_eee(priv->phylink, edata);
}
@@ -662,24 +663,26 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev,
struct stmmac_priv *priv = netdev_priv(dev);
int ret;

- if (!edata->eee_enabled) {
+ if (!priv->dma_cap.eee)
+ return -EOPNOTSUPP;
+
+ if (priv->tx_lpi_enabled != edata->tx_lpi_enabled)
+ netdev_warn(priv->dev,
+ "Setting EEE tx-lpi is not supported\n");
+
+ if (!edata->eee_enabled)
stmmac_disable_eee_mode(priv);
- } else {
- /* We are asking for enabling the EEE but it is safe
- * to verify all by invoking the eee_init function.
- * In case of failure it will return an error.
- */
- edata->eee_enabled = stmmac_eee_init(priv);
- if (!edata->eee_enabled)
- return -EOPNOTSUPP;
- }

ret = phylink_ethtool_set_eee(priv->phylink, edata);
if (ret)
return ret;

- priv->eee_enabled = edata->eee_enabled;
- priv->tx_lpi_timer = edata->tx_lpi_timer;
+ if (edata->eee_enabled &&
+ priv->tx_lpi_timer != edata->tx_lpi_timer) {
+ priv->tx_lpi_timer = edata->tx_lpi_timer;
+ stmmac_eee_init(priv);
+ }
+
return 0;
}

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 73677c3b33b6..73465e5f5a41 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -94,7 +94,7 @@ static const u32 default_msg_level = (NETIF_MSG_DRV | NETIF_MSG_PROBE |
static int eee_timer = STMMAC_DEFAULT_LPI_TIMER;
module_param(eee_timer, int, 0644);
MODULE_PARM_DESC(eee_timer, "LPI tx expiration time in msec");
-#define STMMAC_LPI_T(x) (jiffies + msecs_to_jiffies(x))
+#define STMMAC_LPI_T(x) (jiffies + usecs_to_jiffies(x))

/* By default the driver will use the ring mode to manage tx and rx descriptors,
* but allow user to force to use the chain instead of the ring
@@ -370,7 +370,7 @@ static void stmmac_eee_ctrl_timer(struct timer_list *t)
struct stmmac_priv *priv = from_timer(priv, t, eee_ctrl_timer);

stmmac_enable_eee_mode(priv);
- mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(eee_timer));
+ mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer));
}

/**
@@ -383,7 +383,7 @@ static void stmmac_eee_ctrl_timer(struct timer_list *t)
*/
bool stmmac_eee_init(struct stmmac_priv *priv)
{
- int tx_lpi_timer = priv->tx_lpi_timer;
+ int eee_tw_timer = priv->eee_tw_timer;

/* Using PCS we cannot dial with the phy registers at this stage
* so we do not support extra feature like EEE.
@@ -403,7 +403,7 @@ bool stmmac_eee_init(struct stmmac_priv *priv)
if (priv->eee_enabled) {
netdev_dbg(priv->dev, "disable EEE\n");
del_timer_sync(&priv->eee_ctrl_timer);
- stmmac_set_eee_timer(priv, priv->hw, 0, tx_lpi_timer);
+ stmmac_set_eee_timer(priv, priv->hw, 0, eee_tw_timer);
}
mutex_unlock(&priv->lock);
return false;
@@ -411,11 +411,12 @@ bool stmmac_eee_init(struct stmmac_priv *priv)

if (priv->eee_active && !priv->eee_enabled) {
timer_setup(&priv->eee_ctrl_timer, stmmac_eee_ctrl_timer, 0);
- mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(eee_timer));
stmmac_set_eee_timer(priv, priv->hw, STMMAC_DEFAULT_LIT_LS,
- tx_lpi_timer);
+ eee_tw_timer);
}

+ mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer));
+
mutex_unlock(&priv->lock);
netdev_dbg(priv->dev, "Energy-Efficient Ethernet initialized\n");
return true;
@@ -930,6 +931,7 @@ static void stmmac_mac_link_down(struct phylink_config *config,

stmmac_mac_set(priv, priv->ioaddr, false);
priv->eee_active = false;
+ priv->tx_lpi_enabled = false;
stmmac_eee_init(priv);
stmmac_set_eee_pls(priv, priv->hw, false);
}
@@ -1027,6 +1029,7 @@ static void stmmac_mac_link_up(struct phylink_config *config,
if (phy && priv->dma_cap.eee) {
priv->eee_active = phy_init_eee(phy, 1) >= 0;
priv->eee_enabled = stmmac_eee_init(priv);
+ priv->tx_lpi_enabled = priv->eee_enabled;
stmmac_set_eee_pls(priv, priv->hw, true);
}
}
@@ -2057,7 +2060,7 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue)

if ((priv->eee_enabled) && (!priv->tx_path_in_lpi_mode)) {
stmmac_enable_eee_mode(priv);
- mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(eee_timer));
+ mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer));
}

/* We still have pending packets, let's call for a new scheduling */
@@ -2690,7 +2693,11 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
netdev_warn(priv->dev, "PTP init failed\n");
}

- priv->tx_lpi_timer = STMMAC_DEFAULT_TWT_LS;
+ priv->eee_tw_timer = STMMAC_DEFAULT_TWT_LS;
+
+ /* Convert the timer from msec to usec */
+ if (!priv->tx_lpi_timer)
+ priv->tx_lpi_timer = eee_timer * 1000;

if (priv->use_riwt) {
if (!priv->rx_riwt)
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 9159846b8b93..787ac2c8e74e 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -1077,6 +1077,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb)
struct macsec_rx_sa *rx_sa;
struct macsec_rxh_data *rxd;
struct macsec_dev *macsec;
+ unsigned int len;
sci_t sci;
u32 hdr_pn;
bool cbit;
@@ -1232,9 +1233,10 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb)
macsec_rxsc_put(rx_sc);

skb_orphan(skb);
+ len = skb->len;
ret = gro_cells_receive(&macsec->gro_cells, skb);
if (ret == NET_RX_SUCCESS)
- count_rx(dev, skb->len);
+ count_rx(dev, len);
else
macsec->secy.netdev->stats.rx_dropped++;

diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index e351d65533aa..06146ae4c6d8 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -217,6 +217,7 @@ config MDIO_THUNDER
depends on 64BIT
depends on PCI
select MDIO_CAVIUM
+ select MDIO_DEVRES
help
This driver supports the MDIO interfaces found on Cavium
ThunderX SoCs when the MDIO bus device appears as a PCI
diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index c7229d022a27..48ba757046ce 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -1,6 +1,5 @@
// SPDX-License-Identifier: GPL-2.0+
-/*
- * drivers/net/phy/realtek.c
+/* drivers/net/phy/realtek.c
*
* Driver for Realtek PHYs
*
@@ -32,9 +31,9 @@
#define RTL8211F_TX_DELAY BIT(8)
#define RTL8211F_RX_DELAY BIT(3)

-#define RTL8211E_TX_DELAY BIT(1)
-#define RTL8211E_RX_DELAY BIT(2)
-#define RTL8211E_MODE_MII_GMII BIT(3)
+#define RTL8211E_CTRL_DELAY BIT(13)
+#define RTL8211E_TX_DELAY BIT(12)
+#define RTL8211E_RX_DELAY BIT(11)

#define RTL8201F_ISR 0x1e
#define RTL8201F_IER 0x13
@@ -246,16 +245,16 @@ static int rtl8211e_config_init(struct phy_device *phydev)
/* enable TX/RX delay for rgmii-* modes, and disable them for rgmii. */
switch (phydev->interface) {
case PHY_INTERFACE_MODE_RGMII:
- val = 0;
+ val = RTL8211E_CTRL_DELAY | 0;
break;
case PHY_INTERFACE_MODE_RGMII_ID:
- val = RTL8211E_TX_DELAY | RTL8211E_RX_DELAY;
+ val = RTL8211E_CTRL_DELAY | RTL8211E_TX_DELAY | RTL8211E_RX_DELAY;
break;
case PHY_INTERFACE_MODE_RGMII_RXID:
- val = RTL8211E_RX_DELAY;
+ val = RTL8211E_CTRL_DELAY | RTL8211E_RX_DELAY;
break;
case PHY_INTERFACE_MODE_RGMII_TXID:
- val = RTL8211E_TX_DELAY;
+ val = RTL8211E_CTRL_DELAY | RTL8211E_TX_DELAY;
break;
default: /* the rest of the modes imply leaving delays as is. */
return 0;
@@ -263,11 +262,12 @@ static int rtl8211e_config_init(struct phy_device *phydev)

/* According to a sample driver there is a 0x1c config register on the
* 0xa4 extension page (0x7) layout. It can be used to disable/enable
- * the RX/TX delays otherwise controlled by RXDLY/TXDLY pins. It can
- * also be used to customize the whole configuration register:
- * 8:6 = PHY Address, 5:4 = Auto-Negotiation, 3 = Interface Mode Select,
- * 2 = RX Delay, 1 = TX Delay, 0 = SELRGV (see original PHY datasheet
- * for details).
+ * the RX/TX delays otherwise controlled by RXDLY/TXDLY pins.
+ * The configuration register definition:
+ * 14 = reserved
+ * 13 = Force Tx RX Delay controlled by bit12 bit11,
+ * 12 = RX Delay, 11 = TX Delay
+ * 10:0 = Test && debug settings reserved by realtek
*/
oldpage = phy_select_page(phydev, 0x7);
if (oldpage < 0)
@@ -277,7 +277,8 @@ static int rtl8211e_config_init(struct phy_device *phydev)
if (ret)
goto err_restore_page;

- ret = __phy_modify(phydev, 0x1c, RTL8211E_TX_DELAY | RTL8211E_RX_DELAY,
+ ret = __phy_modify(phydev, 0x1c, RTL8211E_CTRL_DELAY
+ | RTL8211E_TX_DELAY | RTL8211E_RX_DELAY,
val);

err_restore_page:
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 8c1e02752ff6..bcc4a4c011f1 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -287,7 +287,7 @@ static int __team_options_register(struct team *team,
for (i--; i >= 0; i--)
__team_option_inst_del_option(team, dst_opts[i]);

- i = option_count - 1;
+ i = option_count;
alloc_rollback:
for (i--; i >= 0; i--)
kfree(dst_opts[i]);
@@ -2112,6 +2112,7 @@ static void team_setup_by_port(struct net_device *dev,
dev->header_ops = port_dev->header_ops;
dev->type = port_dev->type;
dev->hard_header_len = port_dev->hard_header_len;
+ dev->needed_headroom = port_dev->needed_headroom;
dev->addr_len = port_dev->addr_len;
dev->mtu = port_dev->mtu;
memcpy(dev->broadcast, port_dev->broadcast, port_dev->addr_len);
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index a38e868e44d4..f0ef3706aad9 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -1823,6 +1823,7 @@ static const struct driver_info belkin_info = {
.status = ax88179_status,
.link_reset = ax88179_link_reset,
.reset = ax88179_reset,
+ .stop = ax88179_stop,
.flags = FLAG_ETHER | FLAG_FRAMING_AX,
.rx_fixup = ax88179_rx_fixup,
.tx_fixup = ax88179_tx_fixup,
diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c
index e7c630d37589..63a4da0b2d6d 100644
--- a/drivers/net/usb/rtl8150.c
+++ b/drivers/net/usb/rtl8150.c
@@ -274,12 +274,20 @@ static int write_mii_word(rtl8150_t * dev, u8 phy, __u8 indx, u16 reg)
return 1;
}

-static inline void set_ethernet_addr(rtl8150_t * dev)
+static void set_ethernet_addr(rtl8150_t *dev)
{
- u8 node_id[6];
+ u8 node_id[ETH_ALEN];
+ int ret;
+
+ ret = get_registers(dev, IDR, sizeof(node_id), node_id);

- get_registers(dev, IDR, sizeof(node_id), node_id);
- memcpy(dev->netdev->dev_addr, node_id, sizeof(node_id));
+ if (ret == sizeof(node_id)) {
+ ether_addr_copy(dev->netdev->dev_addr, node_id);
+ } else {
+ eth_hw_addr_random(dev->netdev);
+ netdev_notice(dev->netdev, "Assigned a random MAC address: %pM\n",
+ dev->netdev->dev_addr);
+ }
}

static int rtl8150_set_mac_address(struct net_device *netdev, void *p)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index ba38765dc490..c34927b1d806 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -63,6 +63,11 @@ static const unsigned long guest_offloads[] = {
VIRTIO_NET_F_GUEST_CSUM
};

+#define GUEST_OFFLOAD_LRO_MASK ((1ULL << VIRTIO_NET_F_GUEST_TSO4) | \
+ (1ULL << VIRTIO_NET_F_GUEST_TSO6) | \
+ (1ULL << VIRTIO_NET_F_GUEST_ECN) | \
+ (1ULL << VIRTIO_NET_F_GUEST_UFO))
+
struct virtnet_stat_desc {
char desc[ETH_GSTRING_LEN];
size_t offset;
@@ -2547,7 +2552,8 @@ static int virtnet_set_features(struct net_device *dev,
if (features & NETIF_F_LRO)
offloads = vi->guest_offloads_capable;
else
- offloads = 0;
+ offloads = vi->guest_offloads_capable &
+ ~GUEST_OFFLOAD_LRO_MASK;

err = virtnet_set_guest_offloads(vi, offloads);
if (err)
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 2818015324b8..336504b7531d 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1032,7 +1032,6 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
/* Use temporary descriptor to avoid touching bits multiple times */
union Vmxnet3_GenericDesc tempTxDesc;
#endif
- struct udphdr *udph;

count = txd_estimate(skb);

@@ -1135,8 +1134,7 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
gdesc->txd.om = VMXNET3_OM_ENCAP;
gdesc->txd.msscof = ctx.mss;

- udph = udp_hdr(skb);
- if (udph->check)
+ if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM)
gdesc->txd.oco = 1;
} else {
gdesc->txd.hlen = ctx.l4_offset + ctx.l4_hdr_size;
@@ -3371,6 +3369,7 @@ vmxnet3_probe_device(struct pci_dev *pdev,
.ndo_change_mtu = vmxnet3_change_mtu,
.ndo_fix_features = vmxnet3_fix_features,
.ndo_set_features = vmxnet3_set_features,
+ .ndo_features_check = vmxnet3_features_check,
.ndo_get_stats64 = vmxnet3_get_stats64,
.ndo_tx_timeout = vmxnet3_tx_timeout,
.ndo_set_rx_mode = vmxnet3_set_mc,
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c
index def27afa1c69..358667792004 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethtool.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c
@@ -267,6 +267,34 @@ netdev_features_t vmxnet3_fix_features(struct net_device *netdev,
return features;
}

+netdev_features_t vmxnet3_features_check(struct sk_buff *skb,
+ struct net_device *netdev,
+ netdev_features_t features)
+{
+ struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+
+ /* Validate if the tunneled packet is being offloaded by the device */
+ if (VMXNET3_VERSION_GE_4(adapter) &&
+ skb->encapsulation && skb->ip_summed == CHECKSUM_PARTIAL) {
+ u8 l4_proto = 0;
+
+ switch (vlan_get_protocol(skb)) {
+ case htons(ETH_P_IP):
+ l4_proto = ip_hdr(skb)->protocol;
+ break;
+ case htons(ETH_P_IPV6):
+ l4_proto = ipv6_hdr(skb)->nexthdr;
+ break;
+ default:
+ return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
+ }
+
+ if (l4_proto != IPPROTO_UDP)
+ return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
+ }
+ return features;
+}
+
static void vmxnet3_enable_encap_offloads(struct net_device *netdev)
{
struct vmxnet3_adapter *adapter = netdev_priv(netdev);
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index 5d2b062215a2..d958b92c9429 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -470,6 +470,10 @@ vmxnet3_rq_destroy_all(struct vmxnet3_adapter *adapter);
netdev_features_t
vmxnet3_fix_features(struct net_device *netdev, netdev_features_t features);

+netdev_features_t
+vmxnet3_features_check(struct sk_buff *skb,
+ struct net_device *netdev, netdev_features_t features);
+
int
vmxnet3_set_features(struct net_device *netdev, netdev_features_t features);

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 69165a8f7c1f..a9d5682cdea5 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3061,8 +3061,10 @@ static int nvme_dev_open(struct inode *inode, struct file *file)
}

nvme_get_ctrl(ctrl);
- if (!try_module_get(ctrl->ops->module))
+ if (!try_module_get(ctrl->ops->module)) {
+ nvme_put_ctrl(ctrl);
return -EINVAL;
+ }

file->private_data = ctrl;
return 0;
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 24467eea7399..9b3827a6f3a3 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -889,12 +889,11 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
else
flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST;

- /* can't zcopy slab pages */
- if (unlikely(PageSlab(page))) {
- ret = sock_no_sendpage(queue->sock, page, offset, len,
+ if (sendpage_ok(page)) {
+ ret = kernel_sendpage(queue->sock, page, offset, len,
flags);
} else {
- ret = kernel_sendpage(queue->sock, page, offset, len,
+ ret = sock_no_sendpage(queue->sock, page, offset, len,
flags);
}
if (ret <= 0)
diff --git a/drivers/platform/olpc/olpc-ec.c b/drivers/platform/olpc/olpc-ec.c
index 190e4a6186ef..f64b82824db2 100644
--- a/drivers/platform/olpc/olpc-ec.c
+++ b/drivers/platform/olpc/olpc-ec.c
@@ -439,7 +439,9 @@ static int olpc_ec_probe(struct platform_device *pdev)
&config);
if (IS_ERR(ec->dcon_rdev)) {
dev_err(&pdev->dev, "failed to register DCON regulator\n");
- return PTR_ERR(ec->dcon_rdev);
+ err = PTR_ERR(ec->dcon_rdev);
+ kfree(ec);
+ return err;
}

ec->dbgfs_dir = olpc_ec_setup_debugfs();
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index 0581a54cf562..a5ad36083b67 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -469,6 +469,7 @@ config FUJITSU_LAPTOP
depends on BACKLIGHT_CLASS_DEVICE
depends on ACPI_VIDEO || ACPI_VIDEO = n
select INPUT_SPARSEKMAP
+ select NEW_LEDS
select LEDS_CLASS
help
This is a driver for laptops built by Fujitsu:
@@ -1091,6 +1092,7 @@ config LG_LAPTOP
depends on ACPI_WMI
depends on INPUT
select INPUT_SPARSEKMAP
+ select NEW_LEDS
select LEDS_CLASS
help
This driver adds support for hotkeys as well as control of keyboard
diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index 6c42f73c1dfd..805ce604dee6 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -120,6 +120,10 @@ static struct quirk_entry quirk_asus_ga502i = {
.wmi_backlight_set_devstate = true,
};

+static struct quirk_entry quirk_asus_use_kbd_dock_devid = {
+ .use_kbd_dock_devid = true,
+};
+
static int dmi_matched(const struct dmi_system_id *dmi)
{
pr_info("Identified laptop model '%s'\n", dmi->ident);
@@ -493,6 +497,34 @@ static const struct dmi_system_id asus_quirks[] = {
},
.driver_data = &quirk_asus_ga502i,
},
+ {
+ .callback = dmi_matched,
+ .ident = "Asus Transformer T100TA / T100HA / T100CHI",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ /* Match *T100* */
+ DMI_MATCH(DMI_PRODUCT_NAME, "T100"),
+ },
+ .driver_data = &quirk_asus_use_kbd_dock_devid,
+ },
+ {
+ .callback = dmi_matched,
+ .ident = "Asus Transformer T101HA",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "T101HA"),
+ },
+ .driver_data = &quirk_asus_use_kbd_dock_devid,
+ },
+ {
+ .callback = dmi_matched,
+ .ident = "Asus Transformer T200TA",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "T200TA"),
+ },
+ .driver_data = &quirk_asus_use_kbd_dock_devid,
+ },
{},
};

diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 8f4acdc06b13..ae6289d37faf 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -365,12 +365,14 @@ static int asus_wmi_input_init(struct asus_wmi *asus)
if (err)
goto err_free_dev;

- result = asus_wmi_get_devstate_simple(asus, ASUS_WMI_DEVID_KBD_DOCK);
- if (result >= 0) {
- input_set_capability(asus->inputdev, EV_SW, SW_TABLET_MODE);
- input_report_switch(asus->inputdev, SW_TABLET_MODE, !result);
- } else if (result != -ENODEV) {
- pr_err("Error checking for keyboard-dock: %d\n", result);
+ if (asus->driver->quirks->use_kbd_dock_devid) {
+ result = asus_wmi_get_devstate_simple(asus, ASUS_WMI_DEVID_KBD_DOCK);
+ if (result >= 0) {
+ input_set_capability(asus->inputdev, EV_SW, SW_TABLET_MODE);
+ input_report_switch(asus->inputdev, SW_TABLET_MODE, !result);
+ } else if (result != -ENODEV) {
+ pr_err("Error checking for keyboard-dock: %d\n", result);
+ }
}

err = input_register_device(asus->inputdev);
@@ -2114,7 +2116,7 @@ static void asus_wmi_handle_event_code(int code, struct asus_wmi *asus)
return;
}

- if (code == NOTIFY_KBD_DOCK_CHANGE) {
+ if (asus->driver->quirks->use_kbd_dock_devid && code == NOTIFY_KBD_DOCK_CHANGE) {
result = asus_wmi_get_devstate_simple(asus,
ASUS_WMI_DEVID_KBD_DOCK);
if (result >= 0) {
diff --git a/drivers/platform/x86/asus-wmi.h b/drivers/platform/x86/asus-wmi.h
index 4f31b68642a0..1a95c172f94b 100644
--- a/drivers/platform/x86/asus-wmi.h
+++ b/drivers/platform/x86/asus-wmi.h
@@ -33,6 +33,7 @@ struct quirk_entry {
bool wmi_backlight_native;
bool wmi_backlight_set_devstate;
bool wmi_force_als_set;
+ bool use_kbd_dock_devid;
int wapf;
/*
* For machines with AMD graphic chips, it will send out WMI event
diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c
index e85d8e58320c..663197fecb20 100644
--- a/drivers/platform/x86/intel-vbtn.c
+++ b/drivers/platform/x86/intel-vbtn.c
@@ -15,9 +15,13 @@
#include <linux/platform_device.h>
#include <linux/suspend.h>

+/* Returned when NOT in tablet mode on some HP Stream x360 11 models */
+#define VGBS_TABLET_MODE_FLAG_ALT 0x10
/* When NOT in tablet mode, VGBS returns with the flag 0x40 */
-#define TABLET_MODE_FLAG 0x40
-#define DOCK_MODE_FLAG 0x80
+#define VGBS_TABLET_MODE_FLAG 0x40
+#define VGBS_DOCK_MODE_FLAG 0x80
+
+#define VGBS_TABLET_MODE_FLAGS (VGBS_TABLET_MODE_FLAG | VGBS_TABLET_MODE_FLAG_ALT)

MODULE_LICENSE("GPL");
MODULE_AUTHOR("AceLan Kao");
@@ -72,9 +76,9 @@ static void detect_tablet_mode(struct platform_device *device)
if (ACPI_FAILURE(status))
return;

- m = !(vgbs & TABLET_MODE_FLAG);
+ m = !(vgbs & VGBS_TABLET_MODE_FLAGS);
input_report_switch(priv->input_dev, SW_TABLET_MODE, m);
- m = (vgbs & DOCK_MODE_FLAG) ? 1 : 0;
+ m = (vgbs & VGBS_DOCK_MODE_FLAG) ? 1 : 0;
input_report_switch(priv->input_dev, SW_DOCK, m);
}

@@ -167,20 +171,54 @@ static bool intel_vbtn_has_buttons(acpi_handle handle)
return ACPI_SUCCESS(status);
}

+/*
+ * There are several laptops (non 2-in-1) models out there which support VGBS,
+ * but simply always return 0, which we translate to SW_TABLET_MODE=1. This in
+ * turn causes userspace (libinput) to suppress events from the builtin
+ * keyboard and touchpad, making the laptop essentially unusable.
+ *
+ * Since the problem of wrongly reporting SW_TABLET_MODE=1 in combination
+ * with libinput, leads to a non-usable system. Where as OTOH many people will
+ * not even notice when SW_TABLET_MODE is not being reported, a DMI based allow
+ * list is used here. This list mainly matches on the chassis-type of 2-in-1s.
+ *
+ * There are also some 2-in-1s which use the intel-vbtn ACPI interface to report
+ * SW_TABLET_MODE with a chassis-type of 8 ("Portable") or 10 ("Notebook"),
+ * these are matched on a per model basis, since many normal laptops with a
+ * possible broken VGBS ACPI-method also use these chassis-types.
+ */
+static const struct dmi_system_id dmi_switches_allow_list[] = {
+ {
+ .matches = {
+ DMI_EXACT_MATCH(DMI_CHASSIS_TYPE, "31" /* Convertible */),
+ },
+ },
+ {
+ .matches = {
+ DMI_EXACT_MATCH(DMI_CHASSIS_TYPE, "32" /* Detachable */),
+ },
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Venue 11 Pro 7130"),
+ },
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP Stream x360 Convertible PC 11"),
+ },
+ },
+ {} /* Array terminator */
+};
+
static bool intel_vbtn_has_switches(acpi_handle handle)
{
- const char *chassis_type = dmi_get_system_info(DMI_CHASSIS_TYPE);
unsigned long long vgbs;
acpi_status status;

- /*
- * Some normal laptops have a VGBS method despite being non-convertible
- * and their VGBS method always returns 0, causing detect_tablet_mode()
- * to report SW_TABLET_MODE=1 to userspace, which causes issues.
- * These laptops have a DMI chassis_type of 9 ("Laptop"), do not report
- * switches on any devices with a DMI chassis_type of 9.
- */
- if (chassis_type && strcmp(chassis_type, "9") == 0)
+ if (!dmi_check_system(dmi_switches_allow_list))
return false;

status = acpi_evaluate_integer(handle, "VGBS", NULL, &vgbs);
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 0f6fceda5fc0..fe8386ab363c 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -2569,7 +2569,7 @@ static void hotkey_compare_and_issue_event(struct tp_nvram_state *oldn,
*/
static int hotkey_kthread(void *data)
{
- struct tp_nvram_state s[2];
+ struct tp_nvram_state s[2] = { 0 };
u32 poll_mask, event_mask;
unsigned int si, so;
unsigned long t;
@@ -6829,8 +6829,10 @@ static int __init tpacpi_query_bcl_levels(acpi_handle handle)
list_for_each_entry(child, &device->children, node) {
acpi_status status = acpi_evaluate_object(child->handle, "_BCL",
NULL, &buffer);
- if (ACPI_FAILURE(status))
+ if (ACPI_FAILURE(status)) {
+ buffer.length = ACPI_ALLOCATE_BUFFER;
continue;
+ }

obj = (union acpi_object *)buffer.pointer;
if (!obj || (obj->type != ACPI_TYPE_PACKAGE)) {
diff --git a/drivers/tty/vt/selection.c b/drivers/tty/vt/selection.c
index 31bb3647a99c..8e74654c1b27 100644
--- a/drivers/tty/vt/selection.c
+++ b/drivers/tty/vt/selection.c
@@ -193,7 +193,7 @@ static int vc_selection_store_chars(struct vc_data *vc, bool unicode)
/* Allocate a new buffer before freeing the old one ... */
/* chars can take up to 4 bytes with unicode */
bp = kmalloc_array((vc_sel.end - vc_sel.start) / 2 + 1, unicode ? 4 : 1,
- GFP_KERNEL);
+ GFP_KERNEL | __GFP_NOWARN);
if (!bp) {
printk(KERN_WARNING "selection: kmalloc() failed\n");
clear_selection();
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index a54b60d6623f..e172c2efc663 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -527,6 +527,9 @@ static int vhost_vdpa_map(struct vhost_vdpa *v,
r = iommu_map(v->domain, iova, pa, size,
perm_to_iommu_flags(perm));

+ if (r)
+ vhost_iotlb_del_range(dev->iotlb, iova, iova + size - 1);
+
return r;
}

@@ -552,21 +555,19 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,
struct vhost_dev *dev = &v->vdev;
struct vhost_iotlb *iotlb = dev->iotlb;
struct page **page_list;
- unsigned long list_size = PAGE_SIZE / sizeof(struct page *);
+ struct vm_area_struct **vmas;
unsigned int gup_flags = FOLL_LONGTERM;
- unsigned long npages, cur_base, map_pfn, last_pfn = 0;
- unsigned long locked, lock_limit, pinned, i;
+ unsigned long map_pfn, last_pfn = 0;
+ unsigned long npages, lock_limit;
+ unsigned long i, nmap = 0;
u64 iova = msg->iova;
+ long pinned;
int ret = 0;

if (vhost_iotlb_itree_first(iotlb, msg->iova,
msg->iova + msg->size - 1))
return -EEXIST;

- page_list = (struct page **) __get_free_page(GFP_KERNEL);
- if (!page_list)
- return -ENOMEM;
-
if (msg->perm & VHOST_ACCESS_WO)
gup_flags |= FOLL_WRITE;

@@ -574,61 +575,86 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,
if (!npages)
return -EINVAL;

+ page_list = kvmalloc_array(npages, sizeof(struct page *), GFP_KERNEL);
+ vmas = kvmalloc_array(npages, sizeof(struct vm_area_struct *),
+ GFP_KERNEL);
+ if (!page_list || !vmas) {
+ ret = -ENOMEM;
+ goto free;
+ }
+
mmap_read_lock(dev->mm);

- locked = atomic64_add_return(npages, &dev->mm->pinned_vm);
lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-
- if (locked > lock_limit) {
+ if (npages + atomic64_read(&dev->mm->pinned_vm) > lock_limit) {
ret = -ENOMEM;
- goto out;
+ goto unlock;
}

- cur_base = msg->uaddr & PAGE_MASK;
- iova &= PAGE_MASK;
+ pinned = pin_user_pages(msg->uaddr & PAGE_MASK, npages, gup_flags,
+ page_list, vmas);
+ if (npages != pinned) {
+ if (pinned < 0) {
+ ret = pinned;
+ } else {
+ unpin_user_pages(page_list, pinned);
+ ret = -ENOMEM;
+ }
+ goto unlock;
+ }

- while (npages) {
- pinned = min_t(unsigned long, npages, list_size);
- ret = pin_user_pages(cur_base, pinned,
- gup_flags, page_list, NULL);
- if (ret != pinned)
- goto out;
-
- if (!last_pfn)
- map_pfn = page_to_pfn(page_list[0]);
-
- for (i = 0; i < ret; i++) {
- unsigned long this_pfn = page_to_pfn(page_list[i]);
- u64 csize;
-
- if (last_pfn && (this_pfn != last_pfn + 1)) {
- /* Pin a contiguous chunk of memory */
- csize = (last_pfn - map_pfn + 1) << PAGE_SHIFT;
- if (vhost_vdpa_map(v, iova, csize,
- map_pfn << PAGE_SHIFT,
- msg->perm))
- goto out;
- map_pfn = this_pfn;
- iova += csize;
+ iova &= PAGE_MASK;
+ map_pfn = page_to_pfn(page_list[0]);
+
+ /* One more iteration to avoid extra vdpa_map() call out of loop. */
+ for (i = 0; i <= npages; i++) {
+ unsigned long this_pfn;
+ u64 csize;
+
+ /* The last chunk may have no valid PFN next to it */
+ this_pfn = i < npages ? page_to_pfn(page_list[i]) : -1UL;
+
+ if (last_pfn && (this_pfn == -1UL ||
+ this_pfn != last_pfn + 1)) {
+ /* Pin a contiguous chunk of memory */
+ csize = last_pfn - map_pfn + 1;
+ ret = vhost_vdpa_map(v, iova, csize << PAGE_SHIFT,
+ map_pfn << PAGE_SHIFT,
+ msg->perm);
+ if (ret) {
+ /*
+ * Unpin the rest chunks of memory on the
+ * flight with no corresponding vdpa_map()
+ * calls having been made yet. On the other
+ * hand, vdpa_unmap() in the failure path
+ * is in charge of accounting the number of
+ * pinned pages for its own.
+ * This asymmetrical pattern of accounting
+ * is for efficiency to pin all pages at
+ * once, while there is no other callsite
+ * of vdpa_map() than here above.
+ */
+ unpin_user_pages(&page_list[nmap],
+ npages - nmap);
+ goto out;
}
-
- last_pfn = this_pfn;
+ atomic64_add(csize, &dev->mm->pinned_vm);
+ nmap += csize;
+ iova += csize << PAGE_SHIFT;
+ map_pfn = this_pfn;
}
-
- cur_base += ret << PAGE_SHIFT;
- npages -= ret;
+ last_pfn = this_pfn;
}

- /* Pin the rest chunk */
- ret = vhost_vdpa_map(v, iova, (last_pfn - map_pfn + 1) << PAGE_SHIFT,
- map_pfn << PAGE_SHIFT, msg->perm);
+ WARN_ON(nmap != npages);
out:
- if (ret) {
+ if (ret)
vhost_vdpa_unmap(v, msg->iova, msg->size);
- atomic64_sub(npages, &dev->mm->pinned_vm);
- }
+unlock:
mmap_read_unlock(dev->mm);
- free_page((unsigned long)page_list);
+free:
+ kvfree(vmas);
+ kvfree(page_list);
return ret;
}

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index d7b8df3edffc..5f0030e08688 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1283,6 +1283,11 @@ static bool vq_access_ok(struct vhost_virtqueue *vq, unsigned int num,
vring_used_t __user *used)

{
+ /* If an IOTLB device is present, the vring addresses are
+ * GIOVAs. Access validation occurs at prefetch time. */
+ if (vq->iotlb)
+ return true;
+
return access_ok(desc, vhost_get_desc_size(vq, num)) &&
access_ok(avail, vhost_get_avail_size(vq, num)) &&
access_ok(used, vhost_get_used_size(vq, num));
@@ -1376,10 +1381,6 @@ bool vhost_vq_access_ok(struct vhost_virtqueue *vq)
if (!vq_log_access_ok(vq, vq->log_base))
return false;

- /* Access validation occurs at prefetch time with IOTLB */
- if (vq->iotlb)
- return true;
-
return vq_access_ok(vq, vq->num, vq->desc, vq->avail, vq->used);
}
EXPORT_SYMBOL_GPL(vhost_vq_access_ok);
@@ -1511,8 +1512,7 @@ static long vhost_vring_set_addr(struct vhost_dev *d,
/* Also validate log access for used ring if enabled. */
if ((a.flags & (0x1 << VHOST_VRING_F_LOG)) &&
!log_access_ok(vq->log_base, a.log_guest_addr,
- sizeof *vq->used +
- vq->num * sizeof *vq->used->ring))
+ vhost_get_used_size(vq, vq->num)))
return -EINVAL;
}

diff --git a/drivers/video/console/newport_con.c b/drivers/video/console/newport_con.c
index df3c52d72159..8653950c56d4 100644
--- a/drivers/video/console/newport_con.c
+++ b/drivers/video/console/newport_con.c
@@ -35,12 +35,6 @@

#define FONT_DATA ((unsigned char *)font_vga_8x16.data)

-/* borrowed from fbcon.c */
-#define REFCOUNT(fd) (((int *)(fd))[-1])
-#define FNTSIZE(fd) (((int *)(fd))[-2])
-#define FNTCHARCNT(fd) (((int *)(fd))[-3])
-#define FONT_EXTRA_WORDS 3
-
static unsigned char *font_data[MAX_NR_CONSOLES];

static struct newport_regs *npregs;
@@ -522,6 +516,7 @@ static int newport_set_font(int unit, struct console_font *op)
FNTSIZE(new_data) = size;
FNTCHARCNT(new_data) = op->charcount;
REFCOUNT(new_data) = 0; /* usage counter */
+ FNTSUM(new_data) = 0;

p = new_data;
for (i = 0; i < op->charcount; i++) {
diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c
index 09cb46e94f40..3e82f632841d 100644
--- a/drivers/video/fbdev/core/fbcon.c
+++ b/drivers/video/fbdev/core/fbcon.c
@@ -2299,6 +2299,9 @@ static int fbcon_get_font(struct vc_data *vc, struct console_font *font)

if (font->width <= 8) {
j = vc->vc_font.height;
+ if (font->charcount * j > FNTSIZE(fontdata))
+ return -EINVAL;
+
for (i = 0; i < font->charcount; i++) {
memcpy(data, fontdata, j);
memset(data + j, 0, 32 - j);
@@ -2307,6 +2310,9 @@ static int fbcon_get_font(struct vc_data *vc, struct console_font *font)
}
} else if (font->width <= 16) {
j = vc->vc_font.height * 2;
+ if (font->charcount * j > FNTSIZE(fontdata))
+ return -EINVAL;
+
for (i = 0; i < font->charcount; i++) {
memcpy(data, fontdata, j);
memset(data + j, 0, 64 - j);
@@ -2314,6 +2320,9 @@ static int fbcon_get_font(struct vc_data *vc, struct console_font *font)
fontdata += j;
}
} else if (font->width <= 24) {
+ if (font->charcount * (vc->vc_font.height * sizeof(u32)) > FNTSIZE(fontdata))
+ return -EINVAL;
+
for (i = 0; i < font->charcount; i++) {
for (j = 0; j < vc->vc_font.height; j++) {
*data++ = fontdata[0];
@@ -2326,6 +2335,9 @@ static int fbcon_get_font(struct vc_data *vc, struct console_font *font)
}
} else {
j = vc->vc_font.height * 4;
+ if (font->charcount * j > FNTSIZE(fontdata))
+ return -EINVAL;
+
for (i = 0; i < font->charcount; i++) {
memcpy(data, fontdata, j);
memset(data + j, 0, 128 - j);
diff --git a/drivers/video/fbdev/core/fbcon.h b/drivers/video/fbdev/core/fbcon.h
index 78bb14c03643..9315b360c898 100644
--- a/drivers/video/fbdev/core/fbcon.h
+++ b/drivers/video/fbdev/core/fbcon.h
@@ -152,13 +152,6 @@ static inline int attr_col_ec(int shift, struct vc_data *vc,
#define attr_bgcol_ec(bgshift, vc, info) attr_col_ec(bgshift, vc, info, 0)
#define attr_fgcol_ec(fgshift, vc, info) attr_col_ec(fgshift, vc, info, 1)

-/* Font */
-#define REFCOUNT(fd) (((int *)(fd))[-1])
-#define FNTSIZE(fd) (((int *)(fd))[-2])
-#define FNTCHARCNT(fd) (((int *)(fd))[-3])
-#define FNTSUM(fd) (((int *)(fd))[-4])
-#define FONT_EXTRA_WORDS 4
-
/*
* Scroll Method
*/
diff --git a/drivers/video/fbdev/core/fbcon_rotate.c b/drivers/video/fbdev/core/fbcon_rotate.c
index c0d445294aa7..ac72d4f85f7d 100644
--- a/drivers/video/fbdev/core/fbcon_rotate.c
+++ b/drivers/video/fbdev/core/fbcon_rotate.c
@@ -14,6 +14,7 @@
#include <linux/fb.h>
#include <linux/vt_kern.h>
#include <linux/console.h>
+#include <linux/font.h>
#include <asm/types.h>
#include "fbcon.h"
#include "fbcon_rotate.h"
diff --git a/drivers/video/fbdev/core/tileblit.c b/drivers/video/fbdev/core/tileblit.c
index eb664dbf96f6..adff8d6ffe6f 100644
--- a/drivers/video/fbdev/core/tileblit.c
+++ b/drivers/video/fbdev/core/tileblit.c
@@ -13,6 +13,7 @@
#include <linux/fb.h>
#include <linux/vt_kern.h>
#include <linux/console.h>
+#include <linux/font.h>
#include <asm/types.h>
#include "fbcon.h"

diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 1d13d2e882ad..0fe8844b4bee 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -810,14 +810,32 @@ void afs_evict_inode(struct inode *inode)

static void afs_setattr_success(struct afs_operation *op)
{
- struct inode *inode = &op->file[0].vnode->vfs_inode;
+ struct afs_vnode_param *vp = &op->file[0];
+ struct inode *inode = &vp->vnode->vfs_inode;
+ loff_t old_i_size = i_size_read(inode);
+
+ op->setattr.old_i_size = old_i_size;
+ afs_vnode_commit_status(op, vp);
+ /* inode->i_size has now been changed. */
+
+ if (op->setattr.attr->ia_valid & ATTR_SIZE) {
+ loff_t size = op->setattr.attr->ia_size;
+ if (size > old_i_size)
+ pagecache_isize_extended(inode, old_i_size, size);
+ }
+}
+
+static void afs_setattr_edit_file(struct afs_operation *op)
+{
+ struct afs_vnode_param *vp = &op->file[0];
+ struct inode *inode = &vp->vnode->vfs_inode;

- afs_vnode_commit_status(op, &op->file[0]);
if (op->setattr.attr->ia_valid & ATTR_SIZE) {
- loff_t i_size = inode->i_size, size = op->setattr.attr->ia_size;
- if (size > i_size)
- pagecache_isize_extended(inode, i_size, size);
- truncate_pagecache(inode, size);
+ loff_t size = op->setattr.attr->ia_size;
+ loff_t i_size = op->setattr.old_i_size;
+
+ if (size < i_size)
+ truncate_pagecache(inode, size);
}
}

@@ -825,6 +843,7 @@ static const struct afs_operation_ops afs_setattr_operation = {
.issue_afs_rpc = afs_fs_setattr,
.issue_yfs_rpc = yfs_fs_setattr,
.success = afs_setattr_success,
+ .edit_dir = afs_setattr_edit_file,
};

/*
@@ -863,11 +882,16 @@ int afs_setattr(struct dentry *dentry, struct iattr *attr)
if (S_ISREG(vnode->vfs_inode.i_mode))
filemap_write_and_wait(vnode->vfs_inode.i_mapping);

+ /* Prevent any new writebacks from starting whilst we do this. */
+ down_write(&vnode->validate_lock);
+
op = afs_alloc_operation(((attr->ia_valid & ATTR_FILE) ?
afs_file_key(attr->ia_file) : NULL),
vnode->volume);
- if (IS_ERR(op))
- return PTR_ERR(op);
+ if (IS_ERR(op)) {
+ ret = PTR_ERR(op);
+ goto out_unlock;
+ }

afs_op_set_vnode(op, 0, vnode);
op->setattr.attr = attr;
@@ -880,5 +904,10 @@ int afs_setattr(struct dentry *dentry, struct iattr *attr)
op->file[0].update_ctime = 1;

op->ops = &afs_setattr_operation;
- return afs_do_sync_operation(op);
+ ret = afs_do_sync_operation(op);
+
+out_unlock:
+ up_write(&vnode->validate_lock);
+ _leave(" = %d", ret);
+ return ret;
}
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 792ac711985e..e1ebead2e505 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -810,6 +810,7 @@ struct afs_operation {
} store;
struct {
struct iattr *attr;
+ loff_t old_i_size;
} setattr;
struct afs_acl *acl;
struct yfs_acl *yacl;
diff --git a/fs/afs/write.c b/fs/afs/write.c
index a121c247d95a..0a98cf36e78a 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -738,11 +738,21 @@ static int afs_writepages_region(struct address_space *mapping,
int afs_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
+ struct afs_vnode *vnode = AFS_FS_I(mapping->host);
pgoff_t start, end, next;
int ret;

_enter("");

+ /* We have to be careful as we can end up racing with setattr()
+ * truncating the pagecache since the caller doesn't take a lock here
+ * to prevent it.
+ */
+ if (wbc->sync_mode == WB_SYNC_ALL)
+ down_read(&vnode->validate_lock);
+ else if (!down_read_trylock(&vnode->validate_lock))
+ return 0;
+
if (wbc->range_cyclic) {
start = mapping->writeback_index;
end = -1;
@@ -762,6 +772,7 @@ int afs_writepages(struct address_space *mapping,
ret = afs_writepages_region(mapping, wbc, start, end, &next);
}

+ up_read(&vnode->validate_lock);
_leave(" = %d", ret);
return ret;
}
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index eb86e4b88c73..e4a1c6afe35d 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -783,7 +783,9 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
/* replace the sysfs entry */
btrfs_sysfs_remove_devices_dir(fs_info->fs_devices, src_device);
btrfs_sysfs_update_devid(tgt_device);
- btrfs_rm_dev_replace_free_srcdev(src_device);
+ if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &src_device->dev_state))
+ btrfs_scratch_superblocks(fs_info, src_device->bdev,
+ src_device->name->str);

/* write back the superblocks */
trans = btrfs_start_transaction(root, 0);
@@ -792,6 +794,8 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,

mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);

+ btrfs_rm_dev_replace_free_srcdev(src_device);
+
return 0;
}

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 956eb0d6bc58..79e9a80bd37a 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1999,9 +1999,9 @@ static u64 btrfs_num_devices(struct btrfs_fs_info *fs_info)
return num_devices;
}

-static void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
- struct block_device *bdev,
- const char *device_path)
+void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
+ struct block_device *bdev,
+ const char *device_path)
{
struct btrfs_super_block *disk_super;
int copy_num;
@@ -2224,11 +2224,7 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_device *srcdev)
struct btrfs_fs_info *fs_info = srcdev->fs_info;
struct btrfs_fs_devices *fs_devices = srcdev->fs_devices;

- if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &srcdev->dev_state)) {
- /* zero out the old super if it is writable */
- btrfs_scratch_superblocks(fs_info, srcdev->bdev,
- srcdev->name->str);
- }
+ mutex_lock(&uuid_mutex);

btrfs_close_bdev(srcdev);
synchronize_rcu();
@@ -2258,6 +2254,7 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_device *srcdev)
close_fs_devices(fs_devices);
free_fs_devices(fs_devices);
}
+ mutex_unlock(&uuid_mutex);
}

void btrfs_destroy_dev_replace_tgtdev(struct btrfs_device *tgtdev)
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 75af2334b2e3..83862e27f566 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -573,6 +573,9 @@ void btrfs_set_fs_info_ptr(struct btrfs_fs_info *fs_info);
void btrfs_reset_fs_info_ptr(struct btrfs_fs_info *fs_info);
bool btrfs_check_rw_degradable(struct btrfs_fs_info *fs_info,
struct btrfs_device *failing_dev);
+void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
+ struct block_device *bdev,
+ const char *device_path);

int btrfs_bg_type_to_factor(u64 flags);
const char *btrfs_bg_type_to_raid_name(u64 flags);
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 32f90dc82c84..d44df8f95bcd 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -1208,7 +1208,7 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon,
rqst[1].rq_iov = si_iov;
rqst[1].rq_nvec = 1;

- len = sizeof(ea) + ea_name_len + ea_value_len + 1;
+ len = sizeof(*ea) + ea_name_len + ea_value_len + 1;
ea = kzalloc(len, GFP_KERNEL);
if (ea == NULL) {
rc = -ENOMEM;
diff --git a/fs/exfat/cache.c b/fs/exfat/cache.c
index 03d0824fc368..5a2f119b7e8c 100644
--- a/fs/exfat/cache.c
+++ b/fs/exfat/cache.c
@@ -17,7 +17,6 @@
#include "exfat_raw.h"
#include "exfat_fs.h"

-#define EXFAT_CACHE_VALID 0
#define EXFAT_MAX_CACHE 16

struct exfat_cache {
@@ -61,16 +60,6 @@ void exfat_cache_shutdown(void)
kmem_cache_destroy(exfat_cachep);
}

-void exfat_cache_init_inode(struct inode *inode)
-{
- struct exfat_inode_info *ei = EXFAT_I(inode);
-
- spin_lock_init(&ei->cache_lru_lock);
- ei->nr_caches = 0;
- ei->cache_valid_id = EXFAT_CACHE_VALID + 1;
- INIT_LIST_HEAD(&ei->cache_lru);
-}
-
static inline struct exfat_cache *exfat_cache_alloc(void)
{
return kmem_cache_alloc(exfat_cachep, GFP_NOFS);
diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h
index 75c7bdbeba6d..fb49928687bb 100644
--- a/fs/exfat/exfat_fs.h
+++ b/fs/exfat/exfat_fs.h
@@ -250,6 +250,8 @@ struct exfat_sb_info {
struct rcu_head rcu;
};

+#define EXFAT_CACHE_VALID 0
+
/*
* EXFAT file system inode in-memory data
*/
@@ -429,7 +431,6 @@ extern const struct dentry_operations exfat_utf8_dentry_ops;
/* cache.c */
int exfat_cache_init(void);
void exfat_cache_shutdown(void);
-void exfat_cache_init_inode(struct inode *inode);
void exfat_cache_inval_inode(struct inode *inode);
int exfat_get_cluster(struct inode *inode, unsigned int cluster,
unsigned int *fclus, unsigned int *dclus,
diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c
index cf9ca6c4d046..1952b88e14db 100644
--- a/fs/exfat/inode.c
+++ b/fs/exfat/inode.c
@@ -610,8 +610,6 @@ static int exfat_fill_inode(struct inode *inode, struct exfat_dir_entry *info)
ei->i_crtime = info->crtime;
inode->i_atime = info->atime;

- exfat_cache_init_inode(inode);
-
return 0;
}

diff --git a/fs/exfat/super.c b/fs/exfat/super.c
index 253a92460d52..142f3459c7ca 100644
--- a/fs/exfat/super.c
+++ b/fs/exfat/super.c
@@ -361,7 +361,6 @@ static int exfat_read_root(struct inode *inode)
inode->i_mtime = inode->i_atime = inode->i_ctime = ei->i_crtime =
current_time(inode);
exfat_truncate_atime(&inode->i_atime);
- exfat_cache_init_inode(inode);
return 0;
}

@@ -747,6 +746,10 @@ static void exfat_inode_init_once(void *foo)
{
struct exfat_inode_info *ei = (struct exfat_inode_info *)foo;

+ spin_lock_init(&ei->cache_lru_lock);
+ ei->nr_caches = 0;
+ ei->cache_valid_id = EXFAT_CACHE_VALID + 1;
+ INIT_LIST_HEAD(&ei->cache_lru);
INIT_HLIST_NODE(&ei->i_hash_fat);
inode_init_once(&ei->vfs_inode);
}
diff --git a/fs/io_uring.c b/fs/io_uring.c
index ebc3586b1879..d2bb2ae9551f 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -7998,11 +7998,19 @@ static int io_uring_show_cred(int id, void *p, void *data)

static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
{
+ bool has_lock;
int i;

- mutex_lock(&ctx->uring_lock);
+ /*
+ * Avoid ABBA deadlock between the seq lock and the io_uring mutex,
+ * since fdinfo case grabs it in the opposite direction of normal use
+ * cases. If we fail to get the lock, we just don't iterate any
+ * structures that could be going away outside the io_uring mutex.
+ */
+ has_lock = mutex_trylock(&ctx->uring_lock);
+
seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files);
- for (i = 0; i < ctx->nr_user_files; i++) {
+ for (i = 0; has_lock && i < ctx->nr_user_files; i++) {
struct fixed_file_table *table;
struct file *f;

@@ -8014,13 +8022,13 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
seq_printf(m, "%5u: <none>\n", i);
}
seq_printf(m, "UserBufs:\t%u\n", ctx->nr_user_bufs);
- for (i = 0; i < ctx->nr_user_bufs; i++) {
+ for (i = 0; has_lock && i < ctx->nr_user_bufs; i++) {
struct io_mapped_ubuf *buf = &ctx->user_bufs[i];

seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf,
(unsigned int) buf->len);
}
- if (!idr_is_empty(&ctx->personality_idr)) {
+ if (has_lock && !idr_is_empty(&ctx->personality_idr)) {
seq_printf(m, "Personalities:\n");
idr_for_each(&ctx->personality_idr, io_uring_show_cred, m);
}
@@ -8035,7 +8043,8 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
req->task->task_works != NULL);
}
spin_unlock_irq(&ctx->completion_lock);
- mutex_unlock(&ctx->uring_lock);
+ if (has_lock)
+ mutex_unlock(&ctx->uring_lock);
}

static void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
diff --git a/fs/pipe.c b/fs/pipe.c
index 117db82b10af..0ac197658a2d 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -894,19 +894,18 @@ int create_pipe_files(struct file **res, int flags)
{
struct inode *inode = get_pipe_inode();
struct file *f;
+ int error;

if (!inode)
return -ENFILE;

if (flags & O_NOTIFICATION_PIPE) {
-#ifdef CONFIG_WATCH_QUEUE
- if (watch_queue_init(inode->i_pipe) < 0) {
+ error = watch_queue_init(inode->i_pipe);
+ if (error) {
+ free_pipe_info(inode->i_pipe);
iput(inode);
- return -ENOMEM;
+ return error;
}
-#else
- return -ENOPKG;
-#endif
}

f = alloc_file_pseudo(inode, pipe_mnt, "",
diff --git a/fs/splice.c b/fs/splice.c
index c3d00dfc7344..ce75aec52274 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -526,6 +526,22 @@ static int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_des
return 1;
}

+/* We know we have a pipe buffer, but maybe it's empty? */
+static inline bool eat_empty_buffer(struct pipe_inode_info *pipe)
+{
+ unsigned int tail = pipe->tail;
+ unsigned int mask = pipe->ring_size - 1;
+ struct pipe_buffer *buf = &pipe->bufs[tail & mask];
+
+ if (unlikely(!buf->len)) {
+ pipe_buf_release(pipe, buf);
+ pipe->tail = tail+1;
+ return true;
+ }
+
+ return false;
+}
+
/**
* splice_from_pipe_next - wait for some data to splice from
* @pipe: pipe to splice from
@@ -545,6 +561,7 @@ static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_des
if (signal_pending(current))
return -ERESTARTSYS;

+repeat:
while (pipe_empty(pipe->head, pipe->tail)) {
if (!pipe->writers)
return 0;
@@ -566,6 +583,9 @@ static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_des
pipe_wait_readable(pipe);
}

+ if (eat_empty_buffer(pipe))
+ goto repeat;
+
return 1;
}

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 9e9b1ec30b90..d7eb9e7689b4 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -641,7 +641,7 @@
#define BTF \
.BTF : AT(ADDR(.BTF) - LOAD_OFFSET) { \
__start_BTF = .; \
- *(.BTF) \
+ KEEP(*(.BTF)) \
__stop_BTF = .; \
}
#else
diff --git a/include/linux/font.h b/include/linux/font.h
index 51b91c8b69d5..59faa80f586d 100644
--- a/include/linux/font.h
+++ b/include/linux/font.h
@@ -59,4 +59,17 @@ extern const struct font_desc *get_default_font(int xres, int yres,
/* Max. length for the name of a predefined font */
#define MAX_FONT_NAME 32

+/* Extra word getters */
+#define REFCOUNT(fd) (((int *)(fd))[-1])
+#define FNTSIZE(fd) (((int *)(fd))[-2])
+#define FNTCHARCNT(fd) (((int *)(fd))[-3])
+#define FNTSUM(fd) (((int *)(fd))[-4])
+
+#define FONT_EXTRA_WORDS 4
+
+struct font_data {
+ unsigned int extra[FONT_EXTRA_WORDS];
+ const unsigned char data[];
+} __packed;
+
#endif /* _VIDEO_FONT_H */
diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h
index bc45ea1efbf7..c941b7377321 100644
--- a/include/linux/khugepaged.h
+++ b/include/linux/khugepaged.h
@@ -15,6 +15,7 @@ extern int __khugepaged_enter(struct mm_struct *mm);
extern void __khugepaged_exit(struct mm_struct *mm);
extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
unsigned long vm_flags);
+extern void khugepaged_min_free_kbytes_update(void);
#ifdef CONFIG_SHMEM
extern void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr);
#else
@@ -85,6 +86,10 @@ static inline void collapse_pte_mapped_thp(struct mm_struct *mm,
unsigned long addr)
{
}
+
+static inline void khugepaged_min_free_kbytes_update(void)
+{
+}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

#endif /* _LINUX_KHUGEPAGED_H */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 1e6ca716635a..484cd8ba869c 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -764,6 +764,8 @@ struct mlx5_cmd_work_ent {
u64 ts2;
u16 op;
bool polling;
+ /* Track the max comp handlers */
+ refcount_t refcnt;
};

struct mlx5_pas {
diff --git a/include/linux/net.h b/include/linux/net.h
index 016a9c5faa34..5fab2dcd3364 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -21,6 +21,7 @@
#include <linux/rcupdate.h>
#include <linux/once.h>
#include <linux/fs.h>
+#include <linux/mm.h>

#include <uapi/linux/net.h>

@@ -290,6 +291,21 @@ do { \
#define net_get_random_once_wait(buf, nbytes) \
get_random_once_wait((buf), (nbytes))

+/*
+ * E.g. XFS meta- & log-data is in slab pages, or bcache meta
+ * data pages, or other high order pages allocated by
+ * __get_free_pages() without __GFP_COMP, which have a page_count
+ * of 0 and/or have PageSlab() set. We cannot use send_page for
+ * those, as that does get_page(); put_page(); and would cause
+ * either a VM_BUG directly, or __page_cache_release a page that
+ * would actually still be referenced by someone, leading to some
+ * obscure delayed Oops somewhere else.
+ */
+static inline bool sendpage_ok(struct page *page)
+{
+ return !PageSlab(page) && page_count(page) >= 1;
+}
+
int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec,
size_t num, size_t len);
int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg,
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index cf2468da68e9..601ad6957bb9 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -54,7 +54,8 @@ static inline void mapping_set_error(struct address_space *mapping, int error)
__filemap_set_wb_err(mapping, error);

/* Record it in superblock */
- errseq_set(&mapping->host->i_sb->s_wb_err, error);
+ if (mapping->host)
+ errseq_set(&mapping->host->i_sb->s_wb_err, error);

/* Record it in flags for now, for legacy callers */
if (error == -ENOSPC)
diff --git a/include/linux/watch_queue.h b/include/linux/watch_queue.h
index 5e08db2adc31..c994d1b2cdba 100644
--- a/include/linux/watch_queue.h
+++ b/include/linux/watch_queue.h
@@ -122,6 +122,12 @@ static inline void remove_watch_list(struct watch_list *wlist, u64 id)
*/
#define watch_sizeof(STRUCT) (sizeof(STRUCT) << WATCH_INFO_LENGTH__SHIFT)

+#else
+static inline int watch_queue_init(struct pipe_inode_info *pipe)
+{
+ return -ENOPKG;
+}
+
#endif

#endif /* _LINUX_WATCH_QUEUE_H */
diff --git a/include/net/act_api.h b/include/net/act_api.h
index 8c3934880670..7dc88ebb6e3e 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -166,8 +166,6 @@ int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index,
struct nlattr *est, struct tc_action **a,
const struct tc_action_ops *ops, int bind,
u32 flags);
-void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a);
-
void tcf_idr_cleanup(struct tc_action_net *tn, u32 index);
int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
struct tc_action **a, int bind);
diff --git a/include/net/netlink.h b/include/net/netlink.h
index c0411f14fb53..6df0c91870a3 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -1936,7 +1936,8 @@ void nla_get_range_signed(const struct nla_policy *pt,
int netlink_policy_dump_start(const struct nla_policy *policy,
unsigned int maxtype,
unsigned long *state);
-bool netlink_policy_dump_loop(unsigned long *state);
+bool netlink_policy_dump_loop(unsigned long state);
int netlink_policy_dump_write(struct sk_buff *skb, unsigned long state);
+void netlink_policy_dump_free(unsigned long state);

#endif
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 51f65d23ebaf..2e32cb10ac16 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1767,21 +1767,17 @@ static inline unsigned int xfrm_replay_state_esn_len(struct xfrm_replay_state_es
static inline int xfrm_replay_clone(struct xfrm_state *x,
struct xfrm_state *orig)
{
- x->replay_esn = kzalloc(xfrm_replay_state_esn_len(orig->replay_esn),
+
+ x->replay_esn = kmemdup(orig->replay_esn,
+ xfrm_replay_state_esn_len(orig->replay_esn),
GFP_KERNEL);
if (!x->replay_esn)
return -ENOMEM;
-
- x->replay_esn->bmp_len = orig->replay_esn->bmp_len;
- x->replay_esn->replay_window = orig->replay_esn->replay_window;
-
- x->preplay_esn = kmemdup(x->replay_esn,
- xfrm_replay_state_esn_len(x->replay_esn),
+ x->preplay_esn = kmemdup(orig->preplay_esn,
+ xfrm_replay_state_esn_len(orig->preplay_esn),
GFP_KERNEL);
- if (!x->preplay_esn) {
- kfree(x->replay_esn);
+ if (!x->preplay_esn)
return -ENOMEM;
- }

return 0;
}
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 4953e9994df3..8e174a24c575 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -468,6 +468,7 @@ struct ocelot;

struct ocelot_ops {
int (*reset)(struct ocelot *ocelot);
+ u16 (*wm_enc)(u16 value);
};

struct ocelot_acl_block {
diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c
index 3b495773de5a..11b3380887fa 100644
--- a/kernel/bpf/sysfs_btf.c
+++ b/kernel/bpf/sysfs_btf.c
@@ -30,15 +30,15 @@ static struct kobject *btf_kobj;

static int __init btf_vmlinux_init(void)
{
- if (!__start_BTF)
+ bin_attr_btf_vmlinux.size = __stop_BTF - __start_BTF;
+
+ if (!__start_BTF || bin_attr_btf_vmlinux.size == 0)
return 0;

btf_kobj = kobject_create_and_add("btf", kernel_kobj);
if (!btf_kobj)
return -ENOMEM;

- bin_attr_btf_vmlinux.size = __stop_BTF - __start_BTF;
-
return sysfs_create_bin_file(btf_kobj, &bin_attr_btf_vmlinux);
}

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 94cead5a43e5..89b07db14676 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5490,8 +5490,8 @@ static void scalar32_min_max_or(struct bpf_reg_state *dst_reg,
bool src_known = tnum_subreg_is_const(src_reg->var_off);
bool dst_known = tnum_subreg_is_const(dst_reg->var_off);
struct tnum var32_off = tnum_subreg(dst_reg->var_off);
- s32 smin_val = src_reg->smin_value;
- u32 umin_val = src_reg->umin_value;
+ s32 smin_val = src_reg->s32_min_value;
+ u32 umin_val = src_reg->u32_min_value;

/* Assuming scalar64_min_max_or will be called so it is safe
* to skip updating register for known case.
@@ -5514,8 +5514,8 @@ static void scalar32_min_max_or(struct bpf_reg_state *dst_reg,
/* ORing two positives gives a positive, so safe to
* cast result into s64.
*/
- dst_reg->s32_min_value = dst_reg->umin_value;
- dst_reg->s32_max_value = dst_reg->umax_value;
+ dst_reg->s32_min_value = dst_reg->u32_min_value;
+ dst_reg->s32_max_value = dst_reg->u32_max_value;
}
}

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 856d98c36f56..fd8cd00099da 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -99,7 +99,7 @@ static void remote_function(void *data)
* retry due to any failures in smp_call_function_single(), such as if the
* task_cpu() goes offline concurrently.
*
- * returns @func return value or -ESRCH when the process isn't running
+ * returns @func return value or -ESRCH or -ENXIO when the process isn't running
*/
static int
task_function_call(struct task_struct *p, remote_function_f func, void *info)
@@ -115,7 +115,8 @@ task_function_call(struct task_struct *p, remote_function_f func, void *info)
for (;;) {
ret = smp_call_function_single(task_cpu(p), remote_function,
&data, 1);
- ret = !ret ? data.ret : -EAGAIN;
+ if (!ret)
+ ret = data.ret;

if (ret != -EAGAIN)
break;
diff --git a/kernel/umh.c b/kernel/umh.c
index 79f139a7ca03..6aaf456d402d 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -14,6 +14,7 @@
#include <linux/cred.h>
#include <linux/file.h>
#include <linux/fdtable.h>
+#include <linux/fs_struct.h>
#include <linux/workqueue.h>
#include <linux/security.h>
#include <linux/mount.h>
@@ -75,6 +76,14 @@ static int call_usermodehelper_exec_async(void *data)
flush_signal_handlers(current, 1);
spin_unlock_irq(&current->sighand->siglock);

+ /*
+ * Initial kernel threads share ther FS with init, in order to
+ * get the init root directory. But we've now created a new
+ * thread that is going to execve a user process and has its own
+ * 'struct fs_struct'. Reset umask to the default.
+ */
+ current->fs->umask = 0022;
+
/*
* Our parent (unbound workqueue) runs with elevated scheduling
* priority. Avoid propagating that into the userspace child.
diff --git a/lib/fonts/font_10x18.c b/lib/fonts/font_10x18.c
index 532f0ff89a96..0e2deac97da0 100644
--- a/lib/fonts/font_10x18.c
+++ b/lib/fonts/font_10x18.c
@@ -8,8 +8,8 @@

#define FONTDATAMAX 9216

-static const unsigned char fontdata_10x18[FONTDATAMAX] = {
-
+static struct font_data fontdata_10x18 = {
+ { 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, 0x00, /* 0000000000 */
0x00, 0x00, /* 0000000000 */
@@ -5129,8 +5129,7 @@ static const unsigned char fontdata_10x18[FONTDATAMAX] = {
0x00, 0x00, /* 0000000000 */
0x00, 0x00, /* 0000000000 */
0x00, 0x00, /* 0000000000 */
-
-};
+} };


const struct font_desc font_10x18 = {
@@ -5138,7 +5137,7 @@ const struct font_desc font_10x18 = {
.name = "10x18",
.width = 10,
.height = 18,
- .data = fontdata_10x18,
+ .data = fontdata_10x18.data,
#ifdef __sparc__
.pref = 5,
#else
diff --git a/lib/fonts/font_6x10.c b/lib/fonts/font_6x10.c
index 09b2cc03435b..87da8acd07db 100644
--- a/lib/fonts/font_6x10.c
+++ b/lib/fonts/font_6x10.c
@@ -1,8 +1,10 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/font.h>

-static const unsigned char fontdata_6x10[] = {
+#define FONTDATAMAX 2560

+static struct font_data fontdata_6x10 = {
+ { 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, /* 00000000 */
0x00, /* 00000000 */
@@ -3074,14 +3076,13 @@ static const unsigned char fontdata_6x10[] = {
0x00, /* 00000000 */
0x00, /* 00000000 */
0x00, /* 00000000 */
-
-};
+} };

const struct font_desc font_6x10 = {
.idx = FONT6x10_IDX,
.name = "6x10",
.width = 6,
.height = 10,
- .data = fontdata_6x10,
+ .data = fontdata_6x10.data,
.pref = 0,
};
diff --git a/lib/fonts/font_6x11.c b/lib/fonts/font_6x11.c
index d7136c33f1f0..5e975dfa10a5 100644
--- a/lib/fonts/font_6x11.c
+++ b/lib/fonts/font_6x11.c
@@ -9,8 +9,8 @@

#define FONTDATAMAX (11*256)

-static const unsigned char fontdata_6x11[FONTDATAMAX] = {
-
+static struct font_data fontdata_6x11 = {
+ { 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, /* 00000000 */
0x00, /* 00000000 */
@@ -3338,8 +3338,7 @@ static const unsigned char fontdata_6x11[FONTDATAMAX] = {
0x00, /* 00000000 */
0x00, /* 00000000 */
0x00, /* 00000000 */
-
-};
+} };


const struct font_desc font_vga_6x11 = {
@@ -3347,7 +3346,7 @@ const struct font_desc font_vga_6x11 = {
.name = "ProFont6x11",
.width = 6,
.height = 11,
- .data = fontdata_6x11,
+ .data = fontdata_6x11.data,
/* Try avoiding this font if possible unless on MAC */
.pref = -2000,
};
diff --git a/lib/fonts/font_7x14.c b/lib/fonts/font_7x14.c
index 89752d0b23e8..86d298f38505 100644
--- a/lib/fonts/font_7x14.c
+++ b/lib/fonts/font_7x14.c
@@ -8,8 +8,8 @@

#define FONTDATAMAX 3584

-static const unsigned char fontdata_7x14[FONTDATAMAX] = {
-
+static struct font_data fontdata_7x14 = {
+ { 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, /* 0000000 */
0x00, /* 0000000 */
@@ -4105,8 +4105,7 @@ static const unsigned char fontdata_7x14[FONTDATAMAX] = {
0x00, /* 0000000 */
0x00, /* 0000000 */
0x00, /* 0000000 */
-
-};
+} };


const struct font_desc font_7x14 = {
@@ -4114,6 +4113,6 @@ const struct font_desc font_7x14 = {
.name = "7x14",
.width = 7,
.height = 14,
- .data = fontdata_7x14,
+ .data = fontdata_7x14.data,
.pref = 0,
};
diff --git a/lib/fonts/font_8x16.c b/lib/fonts/font_8x16.c
index b7ab1f5fbdb8..37cedd36ca5e 100644
--- a/lib/fonts/font_8x16.c
+++ b/lib/fonts/font_8x16.c
@@ -10,8 +10,8 @@

#define FONTDATAMAX 4096

-static const unsigned char fontdata_8x16[FONTDATAMAX] = {
-
+static struct font_data fontdata_8x16 = {
+ { 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, /* 00000000 */
0x00, /* 00000000 */
@@ -4619,8 +4619,7 @@ static const unsigned char fontdata_8x16[FONTDATAMAX] = {
0x00, /* 00000000 */
0x00, /* 00000000 */
0x00, /* 00000000 */
-
-};
+} };


const struct font_desc font_vga_8x16 = {
@@ -4628,7 +4627,7 @@ const struct font_desc font_vga_8x16 = {
.name = "VGA8x16",
.width = 8,
.height = 16,
- .data = fontdata_8x16,
+ .data = fontdata_8x16.data,
.pref = 0,
};
EXPORT_SYMBOL(font_vga_8x16);
diff --git a/lib/fonts/font_8x8.c b/lib/fonts/font_8x8.c
index 2328ebc8bab5..8ab695538395 100644
--- a/lib/fonts/font_8x8.c
+++ b/lib/fonts/font_8x8.c
@@ -9,8 +9,8 @@

#define FONTDATAMAX 2048

-static const unsigned char fontdata_8x8[FONTDATAMAX] = {
-
+static struct font_data fontdata_8x8 = {
+ { 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, /* 00000000 */
0x00, /* 00000000 */
@@ -2570,8 +2570,7 @@ static const unsigned char fontdata_8x8[FONTDATAMAX] = {
0x00, /* 00000000 */
0x00, /* 00000000 */
0x00, /* 00000000 */
-
-};
+} };


const struct font_desc font_vga_8x8 = {
@@ -2579,6 +2578,6 @@ const struct font_desc font_vga_8x8 = {
.name = "VGA8x8",
.width = 8,
.height = 8,
- .data = fontdata_8x8,
+ .data = fontdata_8x8.data,
.pref = 0,
};
diff --git a/lib/fonts/font_acorn_8x8.c b/lib/fonts/font_acorn_8x8.c
index 0ff0e85d4481..069b3e80c434 100644
--- a/lib/fonts/font_acorn_8x8.c
+++ b/lib/fonts/font_acorn_8x8.c
@@ -3,7 +3,10 @@

#include <linux/font.h>

-static const unsigned char acorndata_8x8[] = {
+#define FONTDATAMAX 2048
+
+static struct font_data acorndata_8x8 = {
+{ 0, 0, FONTDATAMAX, 0 }, {
/* 00 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* ^@ */
/* 01 */ 0x7e, 0x81, 0xa5, 0x81, 0xbd, 0x99, 0x81, 0x7e, /* ^A */
/* 02 */ 0x7e, 0xff, 0xbd, 0xff, 0xc3, 0xe7, 0xff, 0x7e, /* ^B */
@@ -260,14 +263,14 @@ static const unsigned char acorndata_8x8[] = {
/* FD */ 0x38, 0x04, 0x18, 0x20, 0x3c, 0x00, 0x00, 0x00,
/* FE */ 0x00, 0x00, 0x3c, 0x3c, 0x3c, 0x3c, 0x00, 0x00,
/* FF */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
-};
+} };

const struct font_desc font_acorn_8x8 = {
.idx = ACORN8x8_IDX,
.name = "Acorn8x8",
.width = 8,
.height = 8,
- .data = acorndata_8x8,
+ .data = acorndata_8x8.data,
#ifdef CONFIG_ARCH_ACORN
.pref = 20,
#else
diff --git a/lib/fonts/font_mini_4x6.c b/lib/fonts/font_mini_4x6.c
index 838caa1cfef7..1449876c6a27 100644
--- a/lib/fonts/font_mini_4x6.c
+++ b/lib/fonts/font_mini_4x6.c
@@ -43,8 +43,8 @@ __END__;

#define FONTDATAMAX 1536

-static const unsigned char fontdata_mini_4x6[FONTDATAMAX] = {
-
+static struct font_data fontdata_mini_4x6 = {
+ { 0, 0, FONTDATAMAX, 0 }, {
/*{*/
/* Char 0: ' ' */
0xee, /*= [*** ] */
@@ -2145,14 +2145,14 @@ static const unsigned char fontdata_mini_4x6[FONTDATAMAX] = {
0xee, /*= [*** ] */
0x00, /*= [ ] */
/*}*/
-};
+} };

const struct font_desc font_mini_4x6 = {
.idx = MINI4x6_IDX,
.name = "MINI4x6",
.width = 4,
.height = 6,
- .data = fontdata_mini_4x6,
+ .data = fontdata_mini_4x6.data,
.pref = 3,
};

diff --git a/lib/fonts/font_pearl_8x8.c b/lib/fonts/font_pearl_8x8.c
index b15d3c342c5b..32d65551e7ed 100644
--- a/lib/fonts/font_pearl_8x8.c
+++ b/lib/fonts/font_pearl_8x8.c
@@ -14,8 +14,8 @@

#define FONTDATAMAX 2048

-static const unsigned char fontdata_pearl8x8[FONTDATAMAX] = {
-
+static struct font_data fontdata_pearl8x8 = {
+ { 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, /* 00000000 */
0x00, /* 00000000 */
@@ -2575,14 +2575,13 @@ static const unsigned char fontdata_pearl8x8[FONTDATAMAX] = {
0x00, /* 00000000 */
0x00, /* 00000000 */
0x00, /* 00000000 */
-
-};
+} };

const struct font_desc font_pearl_8x8 = {
.idx = PEARL8x8_IDX,
.name = "PEARL8x8",
.width = 8,
.height = 8,
- .data = fontdata_pearl8x8,
+ .data = fontdata_pearl8x8.data,
.pref = 2,
};
diff --git a/lib/fonts/font_sun12x22.c b/lib/fonts/font_sun12x22.c
index 955d6eee3959..641a6b4dca42 100644
--- a/lib/fonts/font_sun12x22.c
+++ b/lib/fonts/font_sun12x22.c
@@ -3,8 +3,8 @@

#define FONTDATAMAX 11264

-static const unsigned char fontdata_sun12x22[FONTDATAMAX] = {
-
+static struct font_data fontdata_sun12x22 = {
+ { 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, 0x00, /* 000000000000 */
0x00, 0x00, /* 000000000000 */
@@ -6148,8 +6148,7 @@ static const unsigned char fontdata_sun12x22[FONTDATAMAX] = {
0x00, 0x00, /* 000000000000 */
0x00, 0x00, /* 000000000000 */
0x00, 0x00, /* 000000000000 */
-
-};
+} };


const struct font_desc font_sun_12x22 = {
@@ -6157,7 +6156,7 @@ const struct font_desc font_sun_12x22 = {
.name = "SUN12x22",
.width = 12,
.height = 22,
- .data = fontdata_sun12x22,
+ .data = fontdata_sun12x22.data,
#ifdef __sparc__
.pref = 5,
#else
diff --git a/lib/fonts/font_sun8x16.c b/lib/fonts/font_sun8x16.c
index 03d71e53954a..193fe6d988e0 100644
--- a/lib/fonts/font_sun8x16.c
+++ b/lib/fonts/font_sun8x16.c
@@ -3,7 +3,8 @@

#define FONTDATAMAX 4096

-static const unsigned char fontdata_sun8x16[FONTDATAMAX] = {
+static struct font_data fontdata_sun8x16 = {
+{ 0, 0, FONTDATAMAX, 0 }, {
/* */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
/* */ 0x00,0x00,0x7e,0x81,0xa5,0x81,0x81,0xbd,0x99,0x81,0x81,0x7e,0x00,0x00,0x00,0x00,
/* */ 0x00,0x00,0x7e,0xff,0xdb,0xff,0xff,0xc3,0xe7,0xff,0xff,0x7e,0x00,0x00,0x00,0x00,
@@ -260,14 +261,14 @@ static const unsigned char fontdata_sun8x16[FONTDATAMAX] = {
/* */ 0x00,0x70,0xd8,0x30,0x60,0xc8,0xf8,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
/* */ 0x00,0x00,0x00,0x00,0x7c,0x7c,0x7c,0x7c,0x7c,0x7c,0x7c,0x00,0x00,0x00,0x00,0x00,
/* */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
-};
+} };

const struct font_desc font_sun_8x16 = {
.idx = SUN8x16_IDX,
.name = "SUN8x16",
.width = 8,
.height = 16,
- .data = fontdata_sun8x16,
+ .data = fontdata_sun8x16.data,
#ifdef __sparc__
.pref = 10,
#else
diff --git a/lib/fonts/font_ter16x32.c b/lib/fonts/font_ter16x32.c
index 3f0cf1ccdf3a..91b9c283bd9c 100644
--- a/lib/fonts/font_ter16x32.c
+++ b/lib/fonts/font_ter16x32.c
@@ -4,8 +4,8 @@

#define FONTDATAMAX 16384

-static const unsigned char fontdata_ter16x32[FONTDATAMAX] = {
-
+static struct font_data fontdata_ter16x32 = {
+ { 0, 0, FONTDATAMAX, 0 }, {
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x7f, 0xfc, 0x7f, 0xfc,
0x70, 0x1c, 0x70, 0x1c, 0x70, 0x1c, 0x70, 0x1c,
@@ -2054,8 +2054,7 @@ static const unsigned char fontdata_ter16x32[FONTDATAMAX] = {
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 255 */
-
-};
+} };


const struct font_desc font_ter_16x32 = {
@@ -2063,7 +2062,7 @@ const struct font_desc font_ter_16x32 = {
.name = "TER16x32",
.width = 16,
.height = 32,
- .data = fontdata_ter16x32,
+ .data = fontdata_ter16x32.data,
#ifdef __sparc__
.pref = 5,
#else
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index e6fc7c3e7dc9..bc2812bb1a01 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -56,6 +56,9 @@ enum scan_result {
#define CREATE_TRACE_POINTS
#include <trace/events/huge_memory.h>

+static struct task_struct *khugepaged_thread __read_mostly;
+static DEFINE_MUTEX(khugepaged_mutex);
+
/* default scan 8*512 pte (or vmas) every 30 second */
static unsigned int khugepaged_pages_to_scan __read_mostly;
static unsigned int khugepaged_pages_collapsed;
@@ -914,6 +917,18 @@ static struct page *khugepaged_alloc_hugepage(bool *wait)

static bool khugepaged_prealloc_page(struct page **hpage, bool *wait)
{
+ /*
+ * If the hpage allocated earlier was briefly exposed in page cache
+ * before collapse_file() failed, it is possible that racing lookups
+ * have not yet completed, and would then be unpleasantly surprised by
+ * finding the hpage reused for the same mapping at a different offset.
+ * Just release the previous allocation if there is any danger of that.
+ */
+ if (*hpage && page_count(*hpage) > 1) {
+ put_page(*hpage);
+ *hpage = NULL;
+ }
+
if (!*hpage)
*hpage = khugepaged_alloc_hugepage(wait);

@@ -2292,8 +2307,6 @@ static void set_recommended_min_free_kbytes(void)

int start_stop_khugepaged(void)
{
- static struct task_struct *khugepaged_thread __read_mostly;
- static DEFINE_MUTEX(khugepaged_mutex);
int err = 0;

mutex_lock(&khugepaged_mutex);
@@ -2320,3 +2333,11 @@ int start_stop_khugepaged(void)
mutex_unlock(&khugepaged_mutex);
return err;
}
+
+void khugepaged_min_free_kbytes_update(void)
+{
+ mutex_lock(&khugepaged_mutex);
+ if (khugepaged_enabled() && khugepaged_thread)
+ set_recommended_min_free_kbytes();
+ mutex_unlock(&khugepaged_mutex);
+}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 898ff44f2c7b..43f6d91f5715 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -69,6 +69,7 @@
#include <linux/nmi.h>
#include <linux/psi.h>
#include <linux/padata.h>
+#include <linux/khugepaged.h>

#include <asm/sections.h>
#include <asm/tlbflush.h>
@@ -7884,6 +7885,8 @@ int __meminit init_per_zone_wmark_min(void)
setup_min_slab_ratio();
#endif

+ khugepaged_min_free_kbytes_update();
+
return 0;
}
postcore_initcall(init_per_zone_wmark_min)
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 4877a0db16c6..a8fa622e2d9b 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -404,6 +404,8 @@ void br_fdb_delete_by_port(struct net_bridge *br,

if (!do_all)
if (test_bit(BR_FDB_STATIC, &f->flags) ||
+ (test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &f->flags) &&
+ !test_bit(BR_FDB_OFFLOADED, &f->flags)) ||
(vid && f->key.vlan_id != vid))
continue;

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c50bd7a7943a..72f4a3730ecf 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5621,7 +5621,7 @@ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto,
lse->label_stack_entry = mpls_lse;
skb_postpush_rcsum(skb, lse, MPLS_HLEN);

- if (ethernet)
+ if (ethernet && mac_len >= ETH_HLEN)
skb_mod_eth_type(skb, eth_hdr(skb), mpls_proto);
skb->protocol = mpls_proto;

@@ -5661,7 +5661,7 @@ int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len,
skb_reset_mac_header(skb);
skb_set_network_header(skb, mac_len);

- if (ethernet) {
+ if (ethernet && mac_len >= ETH_HLEN) {
struct ethhdr *hdr;

/* use mpls_hdr() to get ethertype to account for VLANs. */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 30c1142584b1..06a8242aa698 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -970,7 +970,8 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);

if (IS_ENABLED(CONFIG_DEBUG_VM) &&
- WARN_ONCE(PageSlab(page), "page must not be a Slab one"))
+ WARN_ONCE(!sendpage_ok(page),
+ "page must not be a Slab one and have page_count > 0"))
return -EINVAL;

/* Wait for a connection to finish. One exception is TCP Fast Open
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 04bfcbbfee83..ab4576ac1fe6 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1787,12 +1787,12 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)

__skb_pull(skb, hdrlen);
if (skb_try_coalesce(tail, skb, &fragstolen, &delta)) {
- thtail->window = th->window;
-
TCP_SKB_CB(tail)->end_seq = TCP_SKB_CB(skb)->end_seq;

- if (after(TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(tail)->ack_seq))
+ if (likely(!before(TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(tail)->ack_seq))) {
TCP_SKB_CB(tail)->ack_seq = TCP_SKB_CB(skb)->ack_seq;
+ thtail->window = th->window;
+ }

/* We have to update both TCP_SKB_CB(tail)->tcp_flags and
* thtail->fin, so that the fast path in tcp_rcv_established()
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 9395ee8a868d..a4148ef314ea 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1079,7 +1079,7 @@ static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb)
if (err)
return err;

- while (netlink_policy_dump_loop(&cb->args[1])) {
+ while (netlink_policy_dump_loop(cb->args[1])) {
void *hdr;
struct nlattr *nest;

@@ -1113,6 +1113,12 @@ static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb)
return skb->len;
}

+static int ctrl_dumppolicy_done(struct netlink_callback *cb)
+{
+ netlink_policy_dump_free(cb->args[1]);
+ return 0;
+}
+
static const struct genl_ops genl_ctrl_ops[] = {
{
.cmd = CTRL_CMD_GETFAMILY,
@@ -1123,6 +1129,7 @@ static const struct genl_ops genl_ctrl_ops[] = {
{
.cmd = CTRL_CMD_GETPOLICY,
.dumpit = ctrl_dumppolicy,
+ .done = ctrl_dumppolicy_done,
},
};

diff --git a/net/netlink/policy.c b/net/netlink/policy.c
index 2b3e26f7496f..ceeaee157b2f 100644
--- a/net/netlink/policy.c
+++ b/net/netlink/policy.c
@@ -84,7 +84,6 @@ int netlink_policy_dump_start(const struct nla_policy *policy,
unsigned int policy_idx;
int err;

- /* also returns 0 if "*_state" is our ERR_PTR() end marker */
if (*_state)
return 0;

@@ -140,21 +139,11 @@ static bool netlink_policy_dump_finished(struct nl_policy_dump *state)
!state->policies[state->policy_idx].policy;
}

-bool netlink_policy_dump_loop(unsigned long *_state)
+bool netlink_policy_dump_loop(unsigned long _state)
{
- struct nl_policy_dump *state = (void *)*_state;
-
- if (IS_ERR(state))
- return false;
-
- if (netlink_policy_dump_finished(state)) {
- kfree(state);
- /* store end marker instead of freed state */
- *_state = (unsigned long)ERR_PTR(-ENOENT);
- return false;
- }
+ struct nl_policy_dump *state = (void *)_state;

- return true;
+ return !netlink_policy_dump_finished(state);
}

int netlink_policy_dump_write(struct sk_buff *skb, unsigned long _state)
@@ -309,3 +298,10 @@ int netlink_policy_dump_write(struct sk_buff *skb, unsigned long _state)
nla_nest_cancel(skb, policy);
return -ENOBUFS;
}
+
+void netlink_policy_dump_free(unsigned long _state)
+{
+ struct nl_policy_dump *state = (void *)_state;
+
+ kfree(state);
+}
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 4340f25fe390..67dacc7152f7 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -903,15 +903,19 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
}
err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype);

- if (err == NF_ACCEPT &&
- ct->status & IPS_SRC_NAT && ct->status & IPS_DST_NAT) {
- if (maniptype == NF_NAT_MANIP_SRC)
- maniptype = NF_NAT_MANIP_DST;
- else
- maniptype = NF_NAT_MANIP_SRC;
-
- err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range,
- maniptype);
+ if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) {
+ if (ct->status & IPS_SRC_NAT) {
+ if (maniptype == NF_NAT_MANIP_SRC)
+ maniptype = NF_NAT_MANIP_DST;
+ else
+ maniptype = NF_NAT_MANIP_SRC;
+
+ err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range,
+ maniptype);
+ } else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
+ err = ovs_ct_nat_execute(skb, ct, ctinfo, NULL,
+ NF_NAT_MANIP_SRC);
+ }
}

/* Mark NAT done if successful and update the flow key. */
diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c
index d8252fdab851..934999b56d60 100644
--- a/net/qrtr/ns.c
+++ b/net/qrtr/ns.c
@@ -193,12 +193,13 @@ static int announce_servers(struct sockaddr_qrtr *sq)
struct qrtr_server *srv;
struct qrtr_node *node;
void __rcu **slot;
- int ret;
+ int ret = 0;

node = node_get(qrtr_ns.local_node);
if (!node)
return 0;

+ rcu_read_lock();
/* Announce the list of servers registered in this node */
radix_tree_for_each_slot(slot, &node->servers, &iter, 0) {
srv = radix_tree_deref_slot(slot);
@@ -206,11 +207,14 @@ static int announce_servers(struct sockaddr_qrtr *sq)
ret = service_announce_new(sq, srv);
if (ret < 0) {
pr_err("failed to announce new service\n");
- return ret;
+ goto err_out;
}
}

- return 0;
+err_out:
+ rcu_read_unlock();
+
+ return ret;
}

static struct qrtr_server *server_add(unsigned int service,
@@ -335,7 +339,7 @@ static int ctrl_cmd_bye(struct sockaddr_qrtr *from)
struct qrtr_node *node;
void __rcu **slot;
struct kvec iv;
- int ret;
+ int ret = 0;

iv.iov_base = &pkt;
iv.iov_len = sizeof(pkt);
@@ -344,11 +348,13 @@ static int ctrl_cmd_bye(struct sockaddr_qrtr *from)
if (!node)
return 0;

+ rcu_read_lock();
/* Advertise removal of this client to all servers of remote node */
radix_tree_for_each_slot(slot, &node->servers, &iter, 0) {
srv = radix_tree_deref_slot(slot);
server_del(node, srv->port);
}
+ rcu_read_unlock();

/* Advertise the removal of this client to all local servers */
local_node = node_get(qrtr_ns.local_node);
@@ -359,6 +365,7 @@ static int ctrl_cmd_bye(struct sockaddr_qrtr *from)
pkt.cmd = cpu_to_le32(QRTR_TYPE_BYE);
pkt.client.node = cpu_to_le32(from->sq_node);

+ rcu_read_lock();
radix_tree_for_each_slot(slot, &local_node->servers, &iter, 0) {
srv = radix_tree_deref_slot(slot);

@@ -372,11 +379,14 @@ static int ctrl_cmd_bye(struct sockaddr_qrtr *from)
ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt));
if (ret < 0) {
pr_err("failed to send bye cmd\n");
- return ret;
+ goto err_out;
}
}

- return 0;
+err_out:
+ rcu_read_unlock();
+
+ return ret;
}

static int ctrl_cmd_del_client(struct sockaddr_qrtr *from,
@@ -394,7 +404,7 @@ static int ctrl_cmd_del_client(struct sockaddr_qrtr *from,
struct list_head *li;
void __rcu **slot;
struct kvec iv;
- int ret;
+ int ret = 0;

iv.iov_base = &pkt;
iv.iov_len = sizeof(pkt);
@@ -434,6 +444,7 @@ static int ctrl_cmd_del_client(struct sockaddr_qrtr *from,
pkt.client.node = cpu_to_le32(node_id);
pkt.client.port = cpu_to_le32(port);

+ rcu_read_lock();
radix_tree_for_each_slot(slot, &local_node->servers, &iter, 0) {
srv = radix_tree_deref_slot(slot);

@@ -447,11 +458,14 @@ static int ctrl_cmd_del_client(struct sockaddr_qrtr *from,
ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt));
if (ret < 0) {
pr_err("failed to send del client cmd\n");
- return ret;
+ goto err_out;
}
}

- return 0;
+err_out:
+ rcu_read_unlock();
+
+ return ret;
}

static int ctrl_cmd_new_server(struct sockaddr_qrtr *from,
@@ -554,6 +568,7 @@ static int ctrl_cmd_new_lookup(struct sockaddr_qrtr *from,
filter.service = service;
filter.instance = instance;

+ rcu_read_lock();
radix_tree_for_each_slot(node_slot, &nodes, &node_iter, 0) {
node = radix_tree_deref_slot(node_slot);

@@ -568,6 +583,7 @@ static int ctrl_cmd_new_lookup(struct sockaddr_qrtr *from,
lookup_notify(from, srv, true);
}
}
+ rcu_read_unlock();

/* Empty notification, to indicate end of listing */
lookup_notify(from, NULL, true);
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 447f55ca6886..6e972b4823ef 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -340,18 +340,18 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
return ret;

spin_lock(&conn->channel_lock);
- spin_lock(&conn->state_lock);
+ spin_lock_bh(&conn->state_lock);

if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) {
conn->state = RXRPC_CONN_SERVICE;
- spin_unlock(&conn->state_lock);
+ spin_unlock_bh(&conn->state_lock);
for (loop = 0; loop < RXRPC_MAXCALLS; loop++)
rxrpc_call_is_secure(
rcu_dereference_protected(
conn->channels[loop].call,
lockdep_is_held(&conn->channel_lock)));
} else {
- spin_unlock(&conn->state_lock);
+ spin_unlock_bh(&conn->state_lock);
}

spin_unlock(&conn->channel_lock);
diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c
index 0c98313dd7a8..85a9ff8cd236 100644
--- a/net/rxrpc/key.c
+++ b/net/rxrpc/key.c
@@ -903,7 +903,7 @@ int rxrpc_request_key(struct rxrpc_sock *rx, char __user *optval, int optlen)

_enter("");

- if (optlen <= 0 || optlen > PAGE_SIZE - 1)
+ if (optlen <= 0 || optlen > PAGE_SIZE - 1 || rx->securities)
return -EINVAL;

description = memdup_user_nul(optval, optlen);
@@ -941,7 +941,7 @@ int rxrpc_server_keyring(struct rxrpc_sock *rx, char __user *optval,
if (IS_ERR(description))
return PTR_ERR(description);

- key = request_key_net(&key_type_keyring, description, sock_net(&rx->sk), NULL);
+ key = request_key(&key_type_keyring, description, NULL);
if (IS_ERR(key)) {
kfree(description);
_leave(" = %ld", PTR_ERR(key));
@@ -1073,7 +1073,7 @@ static long rxrpc_read(const struct key *key,

switch (token->security_index) {
case RXRPC_SECURITY_RXKAD:
- toksize += 9 * 4; /* viceid, kvno, key*2 + len, begin,
+ toksize += 8 * 4; /* viceid, kvno, key*2, begin,
* end, primary, tktlen */
toksize += RND(token->kad->ticket_len);
break;
@@ -1108,7 +1108,8 @@ static long rxrpc_read(const struct key *key,
break;

default: /* we have a ticket we can't encode */
- BUG();
+ pr_err("Unsupported key token type (%u)\n",
+ token->security_index);
continue;
}

@@ -1139,6 +1140,14 @@ static long rxrpc_read(const struct key *key,
memcpy((u8 *)xdr + _l, &zero, 4 - (_l & 3)); \
xdr += (_l + 3) >> 2; \
} while(0)
+#define ENCODE_BYTES(l, s) \
+ do { \
+ u32 _l = (l); \
+ memcpy(xdr, (s), _l); \
+ if (_l & 3) \
+ memcpy((u8 *)xdr + _l, &zero, 4 - (_l & 3)); \
+ xdr += (_l + 3) >> 2; \
+ } while(0)
#define ENCODE64(x) \
do { \
__be64 y = cpu_to_be64(x); \
@@ -1166,7 +1175,7 @@ static long rxrpc_read(const struct key *key,
case RXRPC_SECURITY_RXKAD:
ENCODE(token->kad->vice_id);
ENCODE(token->kad->kvno);
- ENCODE_DATA(8, token->kad->session_key);
+ ENCODE_BYTES(8, token->kad->session_key);
ENCODE(token->kad->start);
ENCODE(token->kad->expiry);
ENCODE(token->kad->primary_flag);
@@ -1216,7 +1225,6 @@ static long rxrpc_read(const struct key *key,
break;

default:
- BUG();
break;
}

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 8ac7eb0a8309..aa69fc4ce39d 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -307,6 +307,8 @@ static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,

mutex_lock(&idrinfo->lock);
idr_for_each_entry_ul(idr, p, tmp, id) {
+ if (IS_ERR(p))
+ continue;
ret = tcf_idr_release_unsafe(p);
if (ret == ACT_P_DELETED) {
module_put(ops->owner);
@@ -467,17 +469,6 @@ int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index,
}
EXPORT_SYMBOL(tcf_idr_create_from_flags);

-void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a)
-{
- struct tcf_idrinfo *idrinfo = tn->idrinfo;
-
- mutex_lock(&idrinfo->lock);
- /* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */
- WARN_ON(!IS_ERR(idr_replace(&idrinfo->action_idr, a, a->tcfa_index)));
- mutex_unlock(&idrinfo->lock);
-}
-EXPORT_SYMBOL(tcf_idr_insert);
-
/* Cleanup idr index that was allocated but not initialized. */

void tcf_idr_cleanup(struct tc_action_net *tn, u32 index)
@@ -902,6 +893,26 @@ static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = {
[TCA_ACT_HW_STATS] = NLA_POLICY_BITFIELD32(TCA_ACT_HW_STATS_ANY),
};

+static void tcf_idr_insert_many(struct tc_action *actions[])
+{
+ int i;
+
+ for (i = 0; i < TCA_ACT_MAX_PRIO; i++) {
+ struct tc_action *a = actions[i];
+ struct tcf_idrinfo *idrinfo;
+
+ if (!a)
+ continue;
+ idrinfo = a->idrinfo;
+ mutex_lock(&idrinfo->lock);
+ /* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc if
+ * it is just created, otherwise this is just a nop.
+ */
+ idr_replace(&idrinfo->action_idr, a, a->tcfa_index);
+ mutex_unlock(&idrinfo->lock);
+ }
+}
+
struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
struct nlattr *nla, struct nlattr *est,
char *name, int ovr, int bind,
@@ -989,6 +1000,13 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
if (err < 0)
goto err_mod;

+ if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN) &&
+ !rcu_access_pointer(a->goto_chain)) {
+ tcf_action_destroy_1(a, bind);
+ NL_SET_ERR_MSG(extack, "can't use goto chain with NULL chain");
+ return ERR_PTR(-EINVAL);
+ }
+
if (!name && tb[TCA_ACT_COOKIE])
tcf_set_action_cookie(&a->act_cookie, cookie);

@@ -1002,13 +1020,6 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
if (err != ACT_P_CREATED)
module_put(a_o->owner);

- if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN) &&
- !rcu_access_pointer(a->goto_chain)) {
- tcf_action_destroy_1(a, bind);
- NL_SET_ERR_MSG(extack, "can't use goto chain with NULL chain");
- return ERR_PTR(-EINVAL);
- }
-
return a;

err_mod:
@@ -1051,6 +1062,11 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
actions[i - 1] = act;
}

+ /* We have to commit them all together, because if any error happened in
+ * between, we could not handle the failure gracefully.
+ */
+ tcf_idr_insert_many(actions);
+
*attr_size = tcf_action_full_attrs_size(sz);
return i - 1;

diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 54d5652cfe6c..a4c7ba35a343 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -365,9 +365,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
if (goto_ch)
tcf_chain_put_by_act(goto_ch);

- if (res == ACT_P_CREATED) {
- tcf_idr_insert(tn, *act);
- } else {
+ if (res != ACT_P_CREATED) {
/* make sure the program being replaced is no longer executing */
synchronize_rcu();
tcf_bpf_cfg_cleanup(&old);
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index f901421b0634..e19885d7fe2c 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -139,7 +139,6 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
ci->net = net;
ci->zone = parm->zone;

- tcf_idr_insert(tn, *a);
ret = ACT_P_CREATED;
} else if (ret > 0) {
ci = to_connmark(*a);
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index c60674cf25c4..8b3f45cdc319 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -110,9 +110,6 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
if (params_new)
kfree_rcu(params_new, rcu);

- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
-
return ret;
put_chain:
if (goto_ch)
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 41d8440deaf1..0eb4722cf7cd 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -1293,8 +1293,6 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla,
tcf_chain_put_by_act(goto_ch);
if (params)
call_rcu(&params->rcu, tcf_ct_params_free);
- if (res == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);

return res;

diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c
index b5042f3ea079..6084300e51ad 100644
--- a/net/sched/act_ctinfo.c
+++ b/net/sched/act_ctinfo.c
@@ -269,9 +269,6 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla,
if (cp_new)
kfree_rcu(cp_new, rcu);

- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
-
return ret;

put_chain:
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 416065772719..1a29751ae63b 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -140,8 +140,6 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
if (goto_ch)
tcf_chain_put_by_act(goto_ch);

- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
return ret;
release_idr:
tcf_idr_release(*a, bind);
diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c
index 323ae7f6315d..c86e7fa7b220 100644
--- a/net/sched/act_gate.c
+++ b/net/sched/act_gate.c
@@ -437,9 +437,6 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla,
if (goto_ch)
tcf_chain_put_by_act(goto_ch);

- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
-
return ret;

chain_put:
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 5c568757643b..a2ddea04183a 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -627,9 +627,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
if (p)
kfree_rcu(p, rcu);

- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
-
return ret;
metadata_parse_err:
if (goto_ch)
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 400a2cfe8452..8dc3bec0d325 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -189,8 +189,6 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
ipt->tcfi_t = t;
ipt->tcfi_hook = hook;
spin_unlock_bh(&ipt->tcf_lock);
- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
return ret;

err3:
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 83dd82fc9f40..cd3a7f814fc8 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -194,8 +194,6 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
spin_lock(&mirred_list_lock);
list_add(&m->tcfm_list, &mirred_list);
spin_unlock(&mirred_list_lock);
-
- tcf_idr_insert(tn, *a);
}

return ret;
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
index 8118e2640979..e298ec3b3c9e 100644
--- a/net/sched/act_mpls.c
+++ b/net/sched/act_mpls.c
@@ -273,8 +273,6 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla,
if (p)
kfree_rcu(p, rcu);

- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
return ret;
put_chain:
if (goto_ch)
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 855a6fa16a62..1ebd2a86d980 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -93,9 +93,6 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
if (goto_ch)
tcf_chain_put_by_act(goto_ch);

- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
-
return ret;
release_idr:
tcf_idr_release(*a, bind);
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index d41d6200d9de..ed1700fe662e 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -238,8 +238,6 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
spin_unlock_bh(&p->tcf_lock);
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
return ret;

put_chain:
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 8b7a0ac96c51..2d236b9a411f 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -201,8 +201,6 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
if (new)
kfree_rcu(new, rcu);

- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
return ret;

failure:
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 5e2df590bb58..3ebf9ede3cf1 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -116,8 +116,6 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
if (goto_ch)
tcf_chain_put_by_act(goto_ch);

- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
return ret;
put_chain:
if (goto_ch)
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 9813ca4006dd..a4f3d0f0daa9 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -157,8 +157,6 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
goto release_idr;
}

- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
return ret;
put_chain:
if (goto_ch)
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index b2b3faa57294..8012ae84847b 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -224,8 +224,6 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
if (goto_ch)
tcf_chain_put_by_act(goto_ch);

- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
return ret;
put_chain:
if (goto_ch)
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 39e6d94cfafb..81a1c67335be 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -190,8 +190,6 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
if (goto_ch)
tcf_chain_put_by_act(goto_ch);

- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
return ret;
put_chain:
if (goto_ch)
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 536c4bc31be6..23cf8469a2e7 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -536,9 +536,6 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
if (goto_ch)
tcf_chain_put_by_act(goto_ch);

- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
-
return ret;

put_chain:
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index c91d3958fcbb..68137d7519d0 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -229,8 +229,6 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
if (p)
kfree_rcu(p, rcu);

- if (ret == ACT_P_CREATED)
- tcf_idr_insert(tn, *a);
return ret;
put_chain:
if (goto_ch)
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index 83e97e8892e0..155aac6943d1 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -494,6 +494,7 @@ int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp)
out_err:
/* Clean up any successful allocations */
sctp_auth_destroy_hmacs(ep->auth_hmacs);
+ ep->auth_hmacs = NULL;
return -ENOMEM;
}

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 24f64bc0de18..d8bc02b185f3 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2142,10 +2142,15 @@ void tls_sw_release_resources_tx(struct sock *sk)
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
struct tls_rec *rec, *tmp;
+ int pending;

/* Wait for any pending async encryptions to complete */
- smp_store_mb(ctx->async_notify, true);
- if (atomic_read(&ctx->encrypt_pending))
+ spin_lock_bh(&ctx->encrypt_compl_lock);
+ ctx->async_notify = true;
+ pending = atomic_read(&ctx->encrypt_pending);
+ spin_unlock_bh(&ctx->encrypt_compl_lock);
+
+ if (pending)
crypto_wait_req(-EINPROGRESS, &ctx->async_wait);

tls_tx_records(sk, -1);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 279c87a2a523..4d7b25506722 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4172,6 +4172,9 @@ static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info)
if (err)
return err;

+ if (key.idx < 0)
+ return -EINVAL;
+
if (info->attrs[NL80211_ATTR_MAC])
mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]);

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 3700266229f6..dcce888b8ef5 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -375,15 +375,30 @@ static int xsk_generic_xmit(struct sock *sk)
skb_shinfo(skb)->destructor_arg = (void *)(long)desc.addr;
skb->destructor = xsk_destruct_skb;

+ /* Hinder dev_direct_xmit from freeing the packet and
+ * therefore completing it in the destructor
+ */
+ refcount_inc(&skb->users);
err = dev_direct_xmit(skb, xs->queue_id);
+ if (err == NETDEV_TX_BUSY) {
+ /* Tell user-space to retry the send */
+ skb->destructor = sock_wfree;
+ /* Free skb without triggering the perf drop trace */
+ consume_skb(skb);
+ err = -EAGAIN;
+ goto out;
+ }
+
xskq_cons_release(xs->tx);
/* Ignore NET_XMIT_CN as packet might have been sent */
- if (err == NET_XMIT_DROP || err == NETDEV_TX_BUSY) {
+ if (err == NET_XMIT_DROP) {
/* SKB completed but not sent */
+ kfree_skb(skb);
err = -EBUSY;
goto out;
}

+ consume_skb(skb);
sent_frame = true;
}

diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c
index 827ccdf2db57..1f08ebf7d80c 100644
--- a/net/xfrm/espintcp.c
+++ b/net/xfrm/espintcp.c
@@ -29,8 +29,12 @@ static void handle_nonesp(struct espintcp_ctx *ctx, struct sk_buff *skb,

static void handle_esp(struct sk_buff *skb, struct sock *sk)
{
+ struct tcp_skb_cb *tcp_cb = (struct tcp_skb_cb *)skb->cb;
+
skb_reset_transport_header(skb);
- memset(skb->cb, 0, sizeof(skb->cb));
+
+ /* restore IP CB, we need at least IP6CB->nhoff */
+ memmove(skb->cb, &tcp_cb->header, sizeof(tcp_cb->header));

rcu_read_lock();
skb->dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif);
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index b615729812e5..ade2eba863b3 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -292,7 +292,7 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
}

mtu = dst_mtu(dst);
- if (!skb->ignore_df && skb->len > mtu) {
+ if (skb->len > mtu) {
skb_dst_update_pmtu_no_confirm(skb, mtu);

if (skb->protocol == htons(ETH_P_IPV6)) {
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 8be2d926acc2..158510cd34ae 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1019,7 +1019,8 @@ static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x,
*/
if (x->km.state == XFRM_STATE_VALID) {
if ((x->sel.family &&
- !xfrm_selector_match(&x->sel, fl, x->sel.family)) ||
+ (x->sel.family != family ||
+ !xfrm_selector_match(&x->sel, fl, family))) ||
!security_xfrm_state_pol_flow_match(x, pol, fl))
return;

@@ -1032,7 +1033,9 @@ static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x,
*acq_in_progress = 1;
} else if (x->km.state == XFRM_STATE_ERROR ||
x->km.state == XFRM_STATE_EXPIRED) {
- if (xfrm_selector_match(&x->sel, fl, x->sel.family) &&
+ if ((!x->sel.family ||
+ (x->sel.family == family &&
+ xfrm_selector_match(&x->sel, fl, family))) &&
security_xfrm_state_pol_flow_match(x, pol, fl))
*error = -ESRCH;
}
@@ -1072,7 +1075,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
tmpl->mode == x->props.mode &&
tmpl->id.proto == x->id.proto &&
(tmpl->id.spi == x->id.spi || !tmpl->id.spi))
- xfrm_state_look_at(pol, x, fl, encap_family,
+ xfrm_state_look_at(pol, x, fl, family,
&best, &acquire_in_progress, &error);
}
if (best || acquire_in_progress)
@@ -1089,7 +1092,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
tmpl->mode == x->props.mode &&
tmpl->id.proto == x->id.proto &&
(tmpl->id.spi == x->id.spi || !tmpl->id.spi))
- xfrm_state_look_at(pol, x, fl, encap_family,
+ xfrm_state_look_at(pol, x, fl, family,
&best, &acquire_in_progress, &error);
}

@@ -1441,6 +1444,30 @@ int xfrm_state_add(struct xfrm_state *x)
EXPORT_SYMBOL(xfrm_state_add);

#ifdef CONFIG_XFRM_MIGRATE
+static inline int clone_security(struct xfrm_state *x, struct xfrm_sec_ctx *security)
+{
+ struct xfrm_user_sec_ctx *uctx;
+ int size = sizeof(*uctx) + security->ctx_len;
+ int err;
+
+ uctx = kmalloc(size, GFP_KERNEL);
+ if (!uctx)
+ return -ENOMEM;
+
+ uctx->exttype = XFRMA_SEC_CTX;
+ uctx->len = size;
+ uctx->ctx_doi = security->ctx_doi;
+ uctx->ctx_alg = security->ctx_alg;
+ uctx->ctx_len = security->ctx_len;
+ memcpy(uctx + 1, security->ctx_str, security->ctx_len);
+ err = security_xfrm_state_alloc(x, uctx);
+ kfree(uctx);
+ if (err)
+ return err;
+
+ return 0;
+}
+
static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
struct xfrm_encap_tmpl *encap)
{
@@ -1497,6 +1524,10 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
goto error;
}

+ if (orig->security)
+ if (clone_security(x, orig->security))
+ goto error;
+
if (orig->coaddr) {
x->coaddr = kmemdup(orig->coaddr, sizeof(*x->coaddr),
GFP_KERNEL);
@@ -1510,6 +1541,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
}

memcpy(&x->mark, &orig->mark, sizeof(x->mark));
+ memcpy(&x->props.smark, &orig->props.smark, sizeof(x->props.smark));

if (xfrm_init_state(x) < 0)
goto error;
@@ -1521,7 +1553,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
x->tfcpad = orig->tfcpad;
x->replay_maxdiff = orig->replay_maxdiff;
x->replay_maxage = orig->replay_maxage;
- x->curlft.add_time = orig->curlft.add_time;
+ memcpy(&x->curlft, &orig->curlft, sizeof(x->curlft));
x->km.state = orig->km.state;
x->km.seq = orig->km.seq;
x->replay = orig->replay;