From 0a8a29be499cbb67df79370aaf5109085509feb8 Mon Sep 17 00:00:00 2001 From: Leonard Pollak Date: Wed, 13 Feb 2019 11:19:52 +0100 Subject: Staging: iio: meter: fixed typo This patch fixes an obvious typo, which will cause erroneously returning the Peak Voltage instead of the Peak Current. Signed-off-by: Leonard Pollak Cc: Acked-by: Michael Hennerich Signed-off-by: Jonathan Cameron --- drivers/staging/iio/meter/ade7854.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/iio/meter/ade7854.c b/drivers/staging/iio/meter/ade7854.c index 029c3bf42d4d..07774c000c5a 100644 --- a/drivers/staging/iio/meter/ade7854.c +++ b/drivers/staging/iio/meter/ade7854.c @@ -269,7 +269,7 @@ static IIO_DEV_ATTR_VPEAK(0644, static IIO_DEV_ATTR_IPEAK(0644, ade7854_read_32bit, ade7854_write_32bit, - ADE7854_VPEAK); + ADE7854_IPEAK); static IIO_DEV_ATTR_APHCAL(0644, ade7854_read_16bit, ade7854_write_16bit, -- cgit v1.2.3-55-g7522 From 40a7198a4a01037003c7ca714f0d048a61e729ac Mon Sep 17 00:00:00 2001 From: Mike Looijmans Date: Wed, 13 Feb 2019 08:41:47 +0100 Subject: iio/gyro/bmg160: Use millidegrees for temperature scale Standard unit for temperature is millidegrees Celcius, whereas this driver was reporting in degrees. Fix the scale factor in the driver. Signed-off-by: Mike Looijmans Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/gyro/bmg160_core.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/iio/gyro/bmg160_core.c b/drivers/iio/gyro/bmg160_core.c index 63ca31628a93..92c07ab826eb 100644 --- a/drivers/iio/gyro/bmg160_core.c +++ b/drivers/iio/gyro/bmg160_core.c @@ -582,11 +582,10 @@ static int bmg160_read_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY: return bmg160_get_filter(data, val); case IIO_CHAN_INFO_SCALE: - *val = 0; switch (chan->type) { case IIO_TEMP: - *val2 = 500000; - return IIO_VAL_INT_PLUS_MICRO; + *val = 500; + return IIO_VAL_INT; case IIO_ANGL_VEL: { int i; @@ -594,6 +593,7 @@ static int bmg160_read_raw(struct iio_dev *indio_dev, for (i = 0; i < ARRAY_SIZE(bmg160_scale_table); ++i) { if (bmg160_scale_table[i].dps_range == data->dps_range) { + *val = 0; *val2 = bmg160_scale_table[i].scale; return IIO_VAL_INT_PLUS_MICRO; } -- cgit v1.2.3-55-g7522 From 7ce0f216221856a17fc4934b39284678a5fef2e9 Mon Sep 17 00:00:00 2001 From: Mircea Caprioru Date: Wed, 20 Feb 2019 13:08:20 +0200 Subject: staging: iio: ad7192: Fix ad7193 channel address This patch fixes the differential channels addresses for the ad7193. Signed-off-by: Mircea Caprioru Cc: Signed-off-by: Jonathan Cameron --- drivers/staging/iio/adc/ad7192.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/staging/iio/adc/ad7192.c b/drivers/staging/iio/adc/ad7192.c index acdbc07fd259..2fc8bc22b57b 100644 --- a/drivers/staging/iio/adc/ad7192.c +++ b/drivers/staging/iio/adc/ad7192.c @@ -109,10 +109,10 @@ #define AD7192_CH_AIN3 BIT(6) /* AIN3 - AINCOM */ #define AD7192_CH_AIN4 BIT(7) /* AIN4 - AINCOM */ -#define AD7193_CH_AIN1P_AIN2M 0x000 /* AIN1(+) - AIN2(-) */ -#define AD7193_CH_AIN3P_AIN4M 0x001 /* AIN3(+) - AIN4(-) */ -#define AD7193_CH_AIN5P_AIN6M 0x002 /* AIN5(+) - AIN6(-) */ -#define AD7193_CH_AIN7P_AIN8M 0x004 /* AIN7(+) - AIN8(-) */ +#define AD7193_CH_AIN1P_AIN2M 0x001 /* AIN1(+) - AIN2(-) */ +#define AD7193_CH_AIN3P_AIN4M 0x002 /* AIN3(+) - AIN4(-) */ +#define AD7193_CH_AIN5P_AIN6M 0x004 /* AIN5(+) - AIN6(-) */ +#define AD7193_CH_AIN7P_AIN8M 0x008 /* AIN7(+) - AIN8(-) */ #define AD7193_CH_TEMP 0x100 /* Temp senseor */ #define AD7193_CH_AIN2P_AIN2M 0x200 /* AIN2(+) - AIN2(-) */ #define AD7193_CH_AIN1 0x401 /* AIN1 - AINCOM */ -- cgit v1.2.3-55-g7522 From 20ea39ef9f2f911bd01c69519e7d69cfec79fde3 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Wed, 20 Feb 2019 17:11:32 +0200 Subject: iio: Fix scan mask selection The trialmask is expected to have all bits set to 0 after allocation. Currently kmalloc_array() is used which does not zero the memory and so random bits are set. This results in random channels being enabled when they shouldn't. Replace kmalloc_array() with kcalloc() which has the same interface but zeros the memory. Note the fix is actually required earlier than the below fixes tag, but will require a manual backport due to move from kmalloc to kmalloc_array. Signed-off-by: Lars-Peter Clausen Signed-off-by: Alexandru Ardelean Fixes commit 057ac1acdfc4 ("iio: Use kmalloc_array() in iio_scan_mask_set()"). Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/industrialio-buffer.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index cd5bfe39591b..dadd921a4a30 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -320,9 +320,8 @@ static int iio_scan_mask_set(struct iio_dev *indio_dev, const unsigned long *mask; unsigned long *trialmask; - trialmask = kmalloc_array(BITS_TO_LONGS(indio_dev->masklength), - sizeof(*trialmask), - GFP_KERNEL); + trialmask = kcalloc(BITS_TO_LONGS(indio_dev->masklength), + sizeof(*trialmask), GFP_KERNEL); if (trialmask == NULL) return -ENOMEM; if (!indio_dev->masklength) { -- cgit v1.2.3-55-g7522 From 409a51e0a4a5f908763191fae2c29008632eb712 Mon Sep 17 00:00:00 2001 From: Sergey Larin Date: Sat, 2 Mar 2019 19:54:55 +0300 Subject: iio: gyro: mpu3050: fix chip ID reading According to the datasheet, the last bit of CHIP_ID register controls I2C bus, and the first one is unused. Handle this correctly. Note that there are chips out there that have a value such that the id check currently fails. Signed-off-by: Sergey Larin Reviewed-by: Linus Walleij Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/gyro/mpu3050-core.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/iio/gyro/mpu3050-core.c b/drivers/iio/gyro/mpu3050-core.c index 77fac81a3adc..5ddebede31a6 100644 --- a/drivers/iio/gyro/mpu3050-core.c +++ b/drivers/iio/gyro/mpu3050-core.c @@ -29,7 +29,8 @@ #include "mpu3050.h" -#define MPU3050_CHIP_ID 0x69 +#define MPU3050_CHIP_ID 0x68 +#define MPU3050_CHIP_ID_MASK 0x7E /* * Register map: anything suffixed *_H is a big-endian high byte and always @@ -1176,8 +1177,9 @@ int mpu3050_common_probe(struct device *dev, goto err_power_down; } - if (val != MPU3050_CHIP_ID) { - dev_err(dev, "unsupported chip id %02x\n", (u8)val); + if ((val & MPU3050_CHIP_ID_MASK) != MPU3050_CHIP_ID) { + dev_err(dev, "unsupported chip id %02x\n", + (u8)(val & MPU3050_CHIP_ID_MASK)); ret = -ENODEV; goto err_power_down; } -- cgit v1.2.3-55-g7522 From 09c6bdee51183a575bf7546890c8c137a75a2b44 Mon Sep 17 00:00:00 2001 From: Georg Ottinger Date: Wed, 30 Jan 2019 14:42:02 +0100 Subject: iio: adc: at91: disable adc channel interrupt in timeout case Having a brief look at at91_adc_read_raw() it is obvious that in the case of a timeout the setting of AT91_ADC_CHDR and AT91_ADC_IDR registers is omitted. If 2 different channels are queried we can end up with a situation where two interrupts are enabled, but only one interrupt is cleared in the interrupt handler. Resulting in a interrupt loop and a system hang. Signed-off-by: Georg Ottinger Acked-by: Ludovic Desroches Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/at91_adc.c | 28 +++++++++++++++++----------- 1 file changed, 17 insertions(+), 11 deletions(-) diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c index 75d2f73582a3..596841a3c4db 100644 --- a/drivers/iio/adc/at91_adc.c +++ b/drivers/iio/adc/at91_adc.c @@ -704,23 +704,29 @@ static int at91_adc_read_raw(struct iio_dev *idev, ret = wait_event_interruptible_timeout(st->wq_data_avail, st->done, msecs_to_jiffies(1000)); - if (ret == 0) - ret = -ETIMEDOUT; - if (ret < 0) { - mutex_unlock(&st->lock); - return ret; - } - - *val = st->last_value; + /* Disable interrupts, regardless if adc conversion was + * successful or not + */ at91_adc_writel(st, AT91_ADC_CHDR, AT91_ADC_CH(chan->channel)); at91_adc_writel(st, AT91_ADC_IDR, BIT(chan->channel)); - st->last_value = 0; - st->done = false; + if (ret > 0) { + /* a valid conversion took place */ + *val = st->last_value; + st->last_value = 0; + st->done = false; + ret = IIO_VAL_INT; + } else if (ret == 0) { + /* conversion timeout */ + dev_err(&idev->dev, "ADC Channel %d timeout.\n", + chan->channel); + ret = -ETIMEDOUT; + } + mutex_unlock(&st->lock); - return IIO_VAL_INT; + return ret; case IIO_CHAN_INFO_SCALE: *val = st->vref_mv; -- cgit v1.2.3-55-g7522 From 831d2fefdfce757fcea86742220f8cbe7ca51ddd Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Sat, 9 Mar 2019 16:59:03 +0000 Subject: iio: chemical: fix missing Kconfig block for sgp30 I clearly messed up applying this patch. Not sure how but the entire Kconfig block is missing. This patch puts it back as it was in the original patch. Reported-by: Andreas Brauchli Fixes: ce514124161a ("iio: chemical: sgp30: Support Sensirion SGP30/SGPC3 sensors") Signed-off-by: Jonathan Cameron --- drivers/iio/chemical/Kconfig | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/iio/chemical/Kconfig b/drivers/iio/chemical/Kconfig index d5d146e9e372..5248e180b442 100644 --- a/drivers/iio/chemical/Kconfig +++ b/drivers/iio/chemical/Kconfig @@ -71,6 +71,19 @@ config PMS7003 To compile this driver as a module, choose M here: the module will be called pms7003. +config SENSIRION_SGP30 + tristate "Sensirion SGPxx gas sensors" + depends on I2C + select CRC8 + help + Say Y here to build I2C interface support for the following + Sensirion SGP gas sensors: + * SGP30 gas sensor + * SGPC3 low power gas sensor + + To compile this driver as module, choose M here: the + module will be called sgp30. + config SPS30 tristate "SPS30 particulate matter sensor" depends on I2C -- cgit v1.2.3-55-g7522 From 9436f45dd53595e21566a8c6627411077dfdb776 Mon Sep 17 00:00:00 2001 From: Mike Looijmans Date: Wed, 6 Mar 2019 08:31:47 +0100 Subject: iio:chemical:bme680: Fix, report temperature in millidegrees The standard unit for temperature is millidegrees Celcius. Adapt the driver to report in millidegrees instead of degrees. Signed-off-by: Mike Looijmans Fixes: 1b3bd8592780 ("iio: chemical: Add support for Bosch BME680 sensor"); Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/chemical/bme680_core.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/drivers/iio/chemical/bme680_core.c b/drivers/iio/chemical/bme680_core.c index 70c1fe4366f4..fefe32b5b69d 100644 --- a/drivers/iio/chemical/bme680_core.c +++ b/drivers/iio/chemical/bme680_core.c @@ -583,8 +583,7 @@ static int bme680_gas_config(struct bme680_data *data) return ret; } -static int bme680_read_temp(struct bme680_data *data, - int *val, int *val2) +static int bme680_read_temp(struct bme680_data *data, int *val) { struct device *dev = regmap_get_device(data->regmap); int ret; @@ -617,10 +616,9 @@ static int bme680_read_temp(struct bme680_data *data, * compensate_press/compensate_humid to get compensated * pressure/humidity readings. */ - if (val && val2) { - *val = comp_temp; - *val2 = 100; - return IIO_VAL_FRACTIONAL; + if (val) { + *val = comp_temp * 10; /* Centidegrees to millidegrees */ + return IIO_VAL_INT; } return ret; @@ -635,7 +633,7 @@ static int bme680_read_press(struct bme680_data *data, s32 adc_press; /* Read and compensate temperature to get a reading of t_fine */ - ret = bme680_read_temp(data, NULL, NULL); + ret = bme680_read_temp(data, NULL); if (ret < 0) return ret; @@ -668,7 +666,7 @@ static int bme680_read_humid(struct bme680_data *data, u32 comp_humidity; /* Read and compensate temperature to get a reading of t_fine */ - ret = bme680_read_temp(data, NULL, NULL); + ret = bme680_read_temp(data, NULL); if (ret < 0) return ret; @@ -761,7 +759,7 @@ static int bme680_read_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_PROCESSED: switch (chan->type) { case IIO_TEMP: - return bme680_read_temp(data, val, val2); + return bme680_read_temp(data, val); case IIO_PRESSURE: return bme680_read_press(data, val, val2); case IIO_HUMIDITYRELATIVE: -- cgit v1.2.3-55-g7522 From 73f3bc6da506711302bb67572440eb84b1ec4a2c Mon Sep 17 00:00:00 2001 From: Mike Looijmans Date: Wed, 6 Mar 2019 08:31:48 +0100 Subject: iio:chemical:bme680: Fix SPI read interface The SPI interface implementation was completely broken. When using the SPI interface, there are only 7 address bits, the upper bit is controlled by a page select register. The core needs access to both ranges, so implement register read/write for both regions. The regmap paging functionality didn't agree with a register that needs to be read and modified, so I implemented a custom paging algorithm. This fixes that the device wouldn't even probe in SPI mode. The SPI interface then isn't different from I2C, merged them into the core, and the I2C/SPI named registers are no longer needed. Implemented register value caching for the registers to reduce the I2C/SPI data transfers considerably. The calibration set reads as all zeroes until some undefined point in time, and I couldn't determine what makes it valid. The datasheet mentions these registers but does not provide any hints on when they become valid, and they aren't even enumerated in the memory map. So check the calibration and retry reading it from the device after each measurement until it provides something valid. Despite the size this is suitable for a stable backport given that it seems the SPI support never worked. Signed-off-by: Mike Looijmans Fixes: 1b3bd8592780 ("iio: chemical: Add support for Bosch BME680 sensor"); Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/chemical/bme680.h | 6 +- drivers/iio/chemical/bme680_core.c | 38 ++++++++++++ drivers/iio/chemical/bme680_i2c.c | 21 ------- drivers/iio/chemical/bme680_spi.c | 115 +++++++++++++++++++++++++------------ 4 files changed, 118 insertions(+), 62 deletions(-) diff --git a/drivers/iio/chemical/bme680.h b/drivers/iio/chemical/bme680.h index 0ae89b87e2d6..4edc5d21cb9f 100644 --- a/drivers/iio/chemical/bme680.h +++ b/drivers/iio/chemical/bme680.h @@ -2,11 +2,9 @@ #ifndef BME680_H_ #define BME680_H_ -#define BME680_REG_CHIP_I2C_ID 0xD0 -#define BME680_REG_CHIP_SPI_ID 0x50 +#define BME680_REG_CHIP_ID 0xD0 #define BME680_CHIP_ID_VAL 0x61 -#define BME680_REG_SOFT_RESET_I2C 0xE0 -#define BME680_REG_SOFT_RESET_SPI 0x60 +#define BME680_REG_SOFT_RESET 0xE0 #define BME680_CMD_SOFTRESET 0xB6 #define BME680_REG_STATUS 0x73 #define BME680_SPI_MEM_PAGE_BIT BIT(4) diff --git a/drivers/iio/chemical/bme680_core.c b/drivers/iio/chemical/bme680_core.c index fefe32b5b69d..ccde4c65ff93 100644 --- a/drivers/iio/chemical/bme680_core.c +++ b/drivers/iio/chemical/bme680_core.c @@ -63,9 +63,23 @@ struct bme680_data { s32 t_fine; }; +static const struct regmap_range bme680_volatile_ranges[] = { + regmap_reg_range(BME680_REG_MEAS_STAT_0, BME680_REG_GAS_R_LSB), + regmap_reg_range(BME680_REG_STATUS, BME680_REG_STATUS), + regmap_reg_range(BME680_T2_LSB_REG, BME680_GH3_REG), +}; + +static const struct regmap_access_table bme680_volatile_table = { + .yes_ranges = bme680_volatile_ranges, + .n_yes_ranges = ARRAY_SIZE(bme680_volatile_ranges), +}; + const struct regmap_config bme680_regmap_config = { .reg_bits = 8, .val_bits = 8, + .max_register = 0xef, + .volatile_table = &bme680_volatile_table, + .cache_type = REGCACHE_RBTREE, }; EXPORT_SYMBOL(bme680_regmap_config); @@ -316,6 +330,10 @@ static s16 bme680_compensate_temp(struct bme680_data *data, s64 var1, var2, var3; s16 calc_temp; + /* If the calibration is invalid, attempt to reload it */ + if (!calib->par_t2) + bme680_read_calib(data, calib); + var1 = (adc_temp >> 3) - (calib->par_t1 << 1); var2 = (var1 * calib->par_t2) >> 11; var3 = ((var1 >> 1) * (var1 >> 1)) >> 12; @@ -865,8 +883,28 @@ int bme680_core_probe(struct device *dev, struct regmap *regmap, { struct iio_dev *indio_dev; struct bme680_data *data; + unsigned int val; int ret; + ret = regmap_write(regmap, BME680_REG_SOFT_RESET, + BME680_CMD_SOFTRESET); + if (ret < 0) { + dev_err(dev, "Failed to reset chip\n"); + return ret; + } + + ret = regmap_read(regmap, BME680_REG_CHIP_ID, &val); + if (ret < 0) { + dev_err(dev, "Error reading chip ID\n"); + return ret; + } + + if (val != BME680_CHIP_ID_VAL) { + dev_err(dev, "Wrong chip ID, got %x expected %x\n", + val, BME680_CHIP_ID_VAL); + return -ENODEV; + } + indio_dev = devm_iio_device_alloc(dev, sizeof(*data)); if (!indio_dev) return -ENOMEM; diff --git a/drivers/iio/chemical/bme680_i2c.c b/drivers/iio/chemical/bme680_i2c.c index b2f805b6b36a..de9c9e3d23ea 100644 --- a/drivers/iio/chemical/bme680_i2c.c +++ b/drivers/iio/chemical/bme680_i2c.c @@ -23,8 +23,6 @@ static int bme680_i2c_probe(struct i2c_client *client, { struct regmap *regmap; const char *name = NULL; - unsigned int val; - int ret; regmap = devm_regmap_init_i2c(client, &bme680_regmap_config); if (IS_ERR(regmap)) { @@ -33,25 +31,6 @@ static int bme680_i2c_probe(struct i2c_client *client, return PTR_ERR(regmap); } - ret = regmap_write(regmap, BME680_REG_SOFT_RESET_I2C, - BME680_CMD_SOFTRESET); - if (ret < 0) { - dev_err(&client->dev, "Failed to reset chip\n"); - return ret; - } - - ret = regmap_read(regmap, BME680_REG_CHIP_I2C_ID, &val); - if (ret < 0) { - dev_err(&client->dev, "Error reading I2C chip ID\n"); - return ret; - } - - if (val != BME680_CHIP_ID_VAL) { - dev_err(&client->dev, "Wrong chip ID, got %x expected %x\n", - val, BME680_CHIP_ID_VAL); - return -ENODEV; - } - if (id) name = id->name; diff --git a/drivers/iio/chemical/bme680_spi.c b/drivers/iio/chemical/bme680_spi.c index d0b7bdd3f066..3b838068a7e4 100644 --- a/drivers/iio/chemical/bme680_spi.c +++ b/drivers/iio/chemical/bme680_spi.c @@ -12,28 +12,93 @@ #include "bme680.h" +struct bme680_spi_bus_context { + struct spi_device *spi; + u8 current_page; +}; + +/* + * In SPI mode there are only 7 address bits, a "page" register determines + * which part of the 8-bit range is active. This function looks at the address + * and writes the page selection bit if needed + */ +static int bme680_regmap_spi_select_page( + struct bme680_spi_bus_context *ctx, u8 reg) +{ + struct spi_device *spi = ctx->spi; + int ret; + u8 buf[2]; + u8 page = (reg & 0x80) ? 0 : 1; /* Page "1" is low range */ + + if (page == ctx->current_page) + return 0; + + /* + * Data sheet claims we're only allowed to change bit 4, so we must do + * a read-modify-write on each and every page select + */ + buf[0] = BME680_REG_STATUS; + ret = spi_write_then_read(spi, buf, 1, buf + 1, 1); + if (ret < 0) { + dev_err(&spi->dev, "failed to set page %u\n", page); + return ret; + } + + buf[0] = BME680_REG_STATUS; + if (page) + buf[1] |= BME680_SPI_MEM_PAGE_BIT; + else + buf[1] &= ~BME680_SPI_MEM_PAGE_BIT; + + ret = spi_write(spi, buf, 2); + if (ret < 0) { + dev_err(&spi->dev, "failed to set page %u\n", page); + return ret; + } + + ctx->current_page = page; + + return 0; +} + static int bme680_regmap_spi_write(void *context, const void *data, size_t count) { - struct spi_device *spi = context; + struct bme680_spi_bus_context *ctx = context; + struct spi_device *spi = ctx->spi; + int ret; u8 buf[2]; memcpy(buf, data, 2); + + ret = bme680_regmap_spi_select_page(ctx, buf[0]); + if (ret) + return ret; + /* * The SPI register address (= full register address without bit 7) * and the write command (bit7 = RW = '0') */ buf[0] &= ~0x80; - return spi_write_then_read(spi, buf, 2, NULL, 0); + return spi_write(spi, buf, 2); } static int bme680_regmap_spi_read(void *context, const void *reg, size_t reg_size, void *val, size_t val_size) { - struct spi_device *spi = context; + struct bme680_spi_bus_context *ctx = context; + struct spi_device *spi = ctx->spi; + int ret; + u8 addr = *(const u8 *)reg; + + ret = bme680_regmap_spi_select_page(ctx, addr); + if (ret) + return ret; - return spi_write_then_read(spi, reg, reg_size, val, val_size); + addr |= 0x80; /* bit7 = RW = '1' */ + + return spi_write_then_read(spi, &addr, 1, val, val_size); } static struct regmap_bus bme680_regmap_bus = { @@ -46,8 +111,8 @@ static struct regmap_bus bme680_regmap_bus = { static int bme680_spi_probe(struct spi_device *spi) { const struct spi_device_id *id = spi_get_device_id(spi); + struct bme680_spi_bus_context *bus_context; struct regmap *regmap; - unsigned int val; int ret; spi->bits_per_word = 8; @@ -57,45 +122,21 @@ static int bme680_spi_probe(struct spi_device *spi) return ret; } + bus_context = devm_kzalloc(&spi->dev, sizeof(*bus_context), GFP_KERNEL); + if (!bus_context) + return -ENOMEM; + + bus_context->spi = spi; + bus_context->current_page = 0xff; /* Undefined on warm boot */ + regmap = devm_regmap_init(&spi->dev, &bme680_regmap_bus, - &spi->dev, &bme680_regmap_config); + bus_context, &bme680_regmap_config); if (IS_ERR(regmap)) { dev_err(&spi->dev, "Failed to register spi regmap %d\n", (int)PTR_ERR(regmap)); return PTR_ERR(regmap); } - ret = regmap_write(regmap, BME680_REG_SOFT_RESET_SPI, - BME680_CMD_SOFTRESET); - if (ret < 0) { - dev_err(&spi->dev, "Failed to reset chip\n"); - return ret; - } - - /* after power-on reset, Page 0(0x80-0xFF) of spi_mem_page is active */ - ret = regmap_read(regmap, BME680_REG_CHIP_SPI_ID, &val); - if (ret < 0) { - dev_err(&spi->dev, "Error reading SPI chip ID\n"); - return ret; - } - - if (val != BME680_CHIP_ID_VAL) { - dev_err(&spi->dev, "Wrong chip ID, got %x expected %x\n", - val, BME680_CHIP_ID_VAL); - return -ENODEV; - } - /* - * select Page 1 of spi_mem_page to enable access to - * to registers from address 0x00 to 0x7F. - */ - ret = regmap_write_bits(regmap, BME680_REG_STATUS, - BME680_SPI_MEM_PAGE_BIT, - BME680_SPI_MEM_PAGE_1_VAL); - if (ret < 0) { - dev_err(&spi->dev, "failed to set page 1 of spi_mem_page\n"); - return ret; - } - return bme680_core_probe(&spi->dev, regmap, id->name); } -- cgit v1.2.3-55-g7522 From fe2d3df639a7940a125a33d6460529b9689c5406 Mon Sep 17 00:00:00 2001 From: he, bo Date: Wed, 6 Mar 2019 10:32:20 +0800 Subject: io: accel: kxcjk1013: restore the range after resume. On some laptops, kxcjk1013 is powered off when system enters S3. We need restore the range regiter during resume. Otherwise, the sensor doesn't work properly after S3. Signed-off-by: he, bo Signed-off-by: Chen, Hu Reviewed-by: Hans de Goede Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/accel/kxcjk-1013.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/iio/accel/kxcjk-1013.c b/drivers/iio/accel/kxcjk-1013.c index 7096e577b23f..50f3ff386bea 100644 --- a/drivers/iio/accel/kxcjk-1013.c +++ b/drivers/iio/accel/kxcjk-1013.c @@ -1437,6 +1437,8 @@ static int kxcjk1013_resume(struct device *dev) mutex_lock(&data->mutex); ret = kxcjk1013_set_mode(data, OPERATION); + if (ret == 0) + ret = kxcjk1013_set_range(data, data->range); mutex_unlock(&data->mutex); return ret; -- cgit v1.2.3-55-g7522 From 06003531502d06bc89d32528f6ec96bf978790f9 Mon Sep 17 00:00:00 2001 From: Jean-Francois Dagenais Date: Wed, 6 Mar 2019 15:56:06 -0500 Subject: iio: dac: mcp4725: add missing powerdown bits in store eeprom When issuing the write DAC register and write eeprom command, the two powerdown bits (PD0 and PD1) are assumed by the chip to be present in the bytes sent. Leaving them at 0 implies "powerdown disabled" which is a different state that the current one. By adding the current state of the powerdown in the i2c write, the chip will correctly power-on exactly like as it is at the moment of store_eeprom call. This is documented in MCP4725's datasheet, FIGURE 6-2: "Write Commands for DAC Input Register and EEPROM" and MCP4726's datasheet, FIGURE 6-3: "Write All Memory Command". Signed-off-by: Jean-Francois Dagenais Acked-by: Peter Meerwald-Stadler Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/dac/mcp4725.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iio/dac/mcp4725.c b/drivers/iio/dac/mcp4725.c index 6d71fd905e29..c701a45469f6 100644 --- a/drivers/iio/dac/mcp4725.c +++ b/drivers/iio/dac/mcp4725.c @@ -92,6 +92,7 @@ static ssize_t mcp4725_store_eeprom(struct device *dev, inoutbuf[0] = 0x60; /* write EEPROM */ inoutbuf[0] |= data->ref_mode << 3; + inoutbuf[0] |= data->powerdown ? ((data->powerdown_mode + 1) << 1) : 0; inoutbuf[1] = data->dac_value >> 4; inoutbuf[2] = (data->dac_value & 0xf) << 4; -- cgit v1.2.3-55-g7522 From 62039b6aef63380ba7a37c113bbaeee8a55c5342 Mon Sep 17 00:00:00 2001 From: Sven Van Asbroeck Date: Sun, 10 Mar 2019 14:58:24 -0400 Subject: iio: adc: xilinx: fix potential use-after-free on remove When cancel_delayed_work() returns, the delayed work may still be running. This means that the core could potentially free the private structure (struct xadc) while the delayed work is still using it. This is a potential use-after-free. Fix by calling cancel_delayed_work_sync(), which waits for any residual work to finish before returning. Signed-off-by: Sven Van Asbroeck Signed-off-by: Jonathan Cameron --- drivers/iio/adc/xilinx-xadc-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/adc/xilinx-xadc-core.c b/drivers/iio/adc/xilinx-xadc-core.c index b13c61539d46..ef3afaeed194 100644 --- a/drivers/iio/adc/xilinx-xadc-core.c +++ b/drivers/iio/adc/xilinx-xadc-core.c @@ -1322,7 +1322,7 @@ static int xadc_remove(struct platform_device *pdev) } free_irq(xadc->irq, indio_dev); clk_disable_unprepare(xadc->clk); - cancel_delayed_work(&xadc->zynq_unmask_work); + cancel_delayed_work_sync(&xadc->zynq_unmask_work); kfree(xadc->data); kfree(indio_dev->channels); -- cgit v1.2.3-55-g7522 From 862e4644fd2d7df8998edc65e0963ea2f567bde9 Mon Sep 17 00:00:00 2001 From: Sven Van Asbroeck Date: Sun, 10 Mar 2019 14:58:25 -0400 Subject: iio: adc: xilinx: fix potential use-after-free on probe If probe errors out after request_irq(), its error path does not explicitly cancel the delayed work, which may have been scheduled by the interrupt handler. This means the delayed work may still be running when the core frees the private structure (struct xadc). This is a potential use-after-free. Fix by inserting cancel_delayed_work_sync() in the probe error path. Signed-off-by: Sven Van Asbroeck Signed-off-by: Jonathan Cameron --- drivers/iio/adc/xilinx-xadc-core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iio/adc/xilinx-xadc-core.c b/drivers/iio/adc/xilinx-xadc-core.c index ef3afaeed194..5a1b63f9d041 100644 --- a/drivers/iio/adc/xilinx-xadc-core.c +++ b/drivers/iio/adc/xilinx-xadc-core.c @@ -1292,6 +1292,7 @@ static int xadc_probe(struct platform_device *pdev) err_free_irq: free_irq(xadc->irq, indio_dev); + cancel_delayed_work_sync(&xadc->zynq_unmask_work); err_clk_disable_unprepare: clk_disable_unprepare(xadc->clk); err_free_samplerate_trigger: -- cgit v1.2.3-55-g7522 From 2e4b88f73966adead360e47621df0183586fac32 Mon Sep 17 00:00:00 2001 From: Sven Van Asbroeck Date: Sun, 10 Mar 2019 14:58:26 -0400 Subject: iio: adc: xilinx: prevent touching unclocked h/w on remove In remove, the clock is disabled before canceling the delayed work. This means that the delayed work may be touching unclocked hardware. Fix by disabling the clock after the delayed work is fully canceled. This is consistent with the probe error path order. Signed-off-by: Sven Van Asbroeck Signed-off-by: Jonathan Cameron --- drivers/iio/adc/xilinx-xadc-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/adc/xilinx-xadc-core.c b/drivers/iio/adc/xilinx-xadc-core.c index 5a1b63f9d041..6401ca7a9a20 100644 --- a/drivers/iio/adc/xilinx-xadc-core.c +++ b/drivers/iio/adc/xilinx-xadc-core.c @@ -1322,8 +1322,8 @@ static int xadc_remove(struct platform_device *pdev) iio_triggered_buffer_cleanup(indio_dev); } free_irq(xadc->irq, indio_dev); - clk_disable_unprepare(xadc->clk); cancel_delayed_work_sync(&xadc->zynq_unmask_work); + clk_disable_unprepare(xadc->clk); kfree(xadc->data); kfree(indio_dev->channels); -- cgit v1.2.3-55-g7522 From 3d02d7082e5823598090530c3988a35f69689943 Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Wed, 13 Mar 2019 12:40:02 +0100 Subject: iio: cros_ec: Fix the maths for gyro scale calculation Calculation did not use IIO_DEGREE_TO_RAD and implemented a variant to avoid precision loss as we aim a nano value. The offset added to avoid rounding error, though, doesn't give us a close result to the expected value. E.g. For 1000dps, the result should be: (1000 * pi ) / 180 >> 15 ~= 0.000532632218 But with current calculation we get $ cat scale 0.000547890 Fix the calculation by just doing the maths involved for a nano value val * pi * 10e12 / (180 * 2^15) so we get a closer result. $ cat scale 0.000532632 Fixes: c14dca07a31d ("iio: cros_ec_sensors: add ChromeOS EC Contiguous Sensors driver") Signed-off-by: Gwendal Grignou Signed-off-by: Enric Balletbo i Serra Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c index 89cb0066a6e0..8d76afb87d87 100644 --- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c +++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c @@ -103,9 +103,10 @@ static int cros_ec_sensors_read(struct iio_dev *indio_dev, * Do not use IIO_DEGREE_TO_RAD to avoid precision * loss. Round to the nearest integer. */ - *val = div_s64(val64 * 314159 + 9000000ULL, 1000); - *val2 = 18000 << (CROS_EC_SENSOR_BITS - 1); - ret = IIO_VAL_FRACTIONAL; + *val = 0; + *val2 = div_s64(val64 * 3141592653ULL, + 180 << (CROS_EC_SENSOR_BITS - 1)); + ret = IIO_VAL_INT_PLUS_NANO; break; case MOTIONSENSE_TYPE_MAG: /* -- cgit v1.2.3-55-g7522 From f6a7bf2ccf22db3e1b936ebc03898f9c025c051e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 14 Mar 2019 10:00:52 +0100 Subject: iio: pms7003: select IIO_TRIGGERED_BUFFER Without IIO_TRIGGERED_BUFFER, this driver fails to link: drivers/iio/chemical/pms7003.o: In function `pms7003_probe': pms7003.c:(.text+0x21c): undefined reference to `devm_iio_triggered_buffer_setup' pms7003.c:(.text+0x21c): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `devm_iio_triggered_buffer_setup' Fixes: a1d642266c14 ("iio: chemical: add support for Plantower PMS7003 sensor") Signed-off-by: Arnd Bergmann Acked-by: Tomasz Duszynski Signed-off-by: Jonathan Cameron --- drivers/iio/chemical/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iio/chemical/Kconfig b/drivers/iio/chemical/Kconfig index 5248e180b442..92c684d2b67e 100644 --- a/drivers/iio/chemical/Kconfig +++ b/drivers/iio/chemical/Kconfig @@ -64,6 +64,7 @@ config IAQCORE config PMS7003 tristate "Plantower PMS7003 particulate matter sensor" depends on SERIAL_DEV_BUS + select IIO_TRIGGERED_BUFFER help Say Y here to build support for the Plantower PMS7003 particulate matter sensor. -- cgit v1.2.3-55-g7522 From 00206a69ee32f03e6f40837684dcbe475ea02266 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Mon, 18 Mar 2019 02:32:36 +0100 Subject: percpu: stop printing kernel addresses Since commit ad67b74d2469d9b8 ("printk: hash addresses printed with %p"), at boot "____ptrval____" is printed instead of actual addresses: percpu: Embedded 38 pages/cpu @(____ptrval____) s124376 r0 d31272 u524288 Instead of changing the print to "%px", and leaking kernel addresses, just remove the print completely, cfr. e.g. commit 071929dbdd865f77 ("arm64: Stop printing the virtual memory layout"). Signed-off-by: Matteo Croce Signed-off-by: Dennis Zhou --- mm/percpu.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/mm/percpu.c b/mm/percpu.c index 2e6fc8d552c9..68dd2e7e73b5 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -2567,8 +2567,8 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, ai->groups[group].base_offset = areas[group] - base; } - pr_info("Embedded %zu pages/cpu @%p s%zu r%zu d%zu u%zu\n", - PFN_DOWN(size_sum), base, ai->static_size, ai->reserved_size, + pr_info("Embedded %zu pages/cpu s%zu r%zu d%zu u%zu\n", + PFN_DOWN(size_sum), ai->static_size, ai->reserved_size, ai->dyn_size, ai->unit_size); rc = pcpu_setup_first_chunk(ai, base); @@ -2692,8 +2692,8 @@ int __init pcpu_page_first_chunk(size_t reserved_size, } /* we're ready, commit */ - pr_info("%d %s pages/cpu @%p s%zu r%zu d%zu\n", - unit_pages, psize_str, vm.addr, ai->static_size, + pr_info("%d %s pages/cpu s%zu r%zu d%zu\n", + unit_pages, psize_str, ai->static_size, ai->reserved_size, ai->dyn_size); rc = pcpu_setup_first_chunk(ai, vm.addr); -- cgit v1.2.3-55-g7522 From 0fcc4c8c044e117ac126ab6df4138ea9a67fa2a9 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Tue, 19 Mar 2019 02:36:59 +0100 Subject: device_cgroup: fix RCU imbalance in error case When dev_exception_add() returns an error (due to a failed memory allocation), make sure that we move the RCU preemption count back to where it was before we were called. We dropped the RCU read lock inside the loop body, so we can't just "break". sparse complains about this, too: $ make -s C=2 security/device_cgroup.o ./include/linux/rcupdate.h:647:9: warning: context imbalance in 'propagate_exception' - unexpected unlock Fixes: d591fb56618f ("device_cgroup: simplify cgroup tree walk in propagate_exception()") Cc: stable@vger.kernel.org Signed-off-by: Jann Horn Acked-by: Michal Hocko Signed-off-by: Tejun Heo --- security/device_cgroup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/security/device_cgroup.c b/security/device_cgroup.c index cd97929fac66..dc28914fa72e 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -560,7 +560,7 @@ static int propagate_exception(struct dev_cgroup *devcg_root, devcg->behavior == DEVCG_DEFAULT_ALLOW) { rc = dev_exception_add(devcg, ex); if (rc) - break; + return rc; } else { /* * in the other possible cases: -- cgit v1.2.3-55-g7522 From bfb57a91c2cb497c3780ed2e08f85d038efd0b7b Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Sun, 24 Mar 2019 18:07:02 +0200 Subject: habanalabs: remove low credit limit of DMA #0 Because DMA #0 is now used by the user, remove the limitation of credits from this channel. Without this patch, this channel is pretty much unusable due to its very low bandwidth configuration. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index ea979ebd62fb..3c509e19d69d 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -1688,12 +1688,11 @@ static void goya_init_golden_registers(struct hl_device *hdev) /* * Workaround for H2 #HW-23 bug - * Set DMA max outstanding read requests to 240 on DMA CH 1. Set it - * to 16 on KMD DMA - * We need to limit only these DMAs because the user can only read + * Set DMA max outstanding read requests to 240 on DMA CH 1. + * This limitation is still large enough to not affect Gen4 bandwidth. + * We need to only limit that DMA channel because the user can only read * from Host using DMA CH 1 */ - WREG32(mmDMA_CH_0_CFG0, 0x0fff0010); WREG32(mmDMA_CH_1_CFG0, 0x0fff00F0); goya->hw_cap_initialized |= HW_CAP_GOLDEN; @@ -3693,7 +3692,7 @@ static int goya_validate_dma_pkt_mmu(struct hl_device *hdev, * WA for HW-23. * We can't allow user to read from Host using QMANs other than 1. */ - if (parser->hw_queue_id > GOYA_QUEUE_ID_DMA_1 && + if (parser->hw_queue_id != GOYA_QUEUE_ID_DMA_1 && hl_mem_area_inside_range(le64_to_cpu(user_dma_pkt->src_addr), le32_to_cpu(user_dma_pkt->tsize), hdev->asic_prop.va_space_host_start_address, -- cgit v1.2.3-55-g7522 From fccfb9ce70ed4ea7a145f77b86de62e38178517f Mon Sep 17 00:00:00 2001 From: Dragos Bogdan Date: Tue, 19 Mar 2019 12:47:00 +0200 Subject: iio: ad_sigma_delta: select channel when reading register The desired channel has to be selected in order to correctly fill the buffer with the corresponding data. The `ad_sd_write_reg()` already does this, but for the `ad_sd_read_reg_raw()` this was omitted. Fixes: af3008485ea03 ("iio:adc: Add common code for ADI Sigma Delta devices") Signed-off-by: Dragos Bogdan Signed-off-by: Alexandru Ardelean Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/ad_sigma_delta.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c index ff5f2da2e1b1..54d9978b2740 100644 --- a/drivers/iio/adc/ad_sigma_delta.c +++ b/drivers/iio/adc/ad_sigma_delta.c @@ -121,6 +121,7 @@ static int ad_sd_read_reg_raw(struct ad_sigma_delta *sigma_delta, if (sigma_delta->info->has_registers) { data[0] = reg << sigma_delta->info->addr_shift; data[0] |= sigma_delta->info->read_mask; + data[0] |= sigma_delta->comm; spi_message_add_tail(&t[0], &m); } spi_message_add_tail(&t[1], &m); -- cgit v1.2.3-55-g7522 From 738c06d0e4562e0acf9f2c7438a22b2d5afc67aa Mon Sep 17 00:00:00 2001 From: KT Liao Date: Tue, 26 Mar 2019 17:28:32 -0700 Subject: Input: elan_i2c - add hardware ID for multiple Lenovo laptops There are many Lenovo laptops which need elan_i2c support, this patch adds relevant IDs to the Elan driver so that touchpads are recognized. Signed-off-by: KT Liao Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov --- drivers/input/mouse/elan_i2c_core.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index 628ef617bb2f..f9525d6f0bfe 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -1339,21 +1339,46 @@ static const struct acpi_device_id elan_acpi_id[] = { { "ELAN0600", 0 }, { "ELAN0601", 0 }, { "ELAN0602", 0 }, + { "ELAN0603", 0 }, + { "ELAN0604", 0 }, { "ELAN0605", 0 }, + { "ELAN0606", 0 }, + { "ELAN0607", 0 }, { "ELAN0608", 0 }, { "ELAN0609", 0 }, { "ELAN060B", 0 }, { "ELAN060C", 0 }, + { "ELAN060F", 0 }, + { "ELAN0610", 0 }, { "ELAN0611", 0 }, { "ELAN0612", 0 }, + { "ELAN0615", 0 }, + { "ELAN0616", 0 }, { "ELAN0617", 0 }, { "ELAN0618", 0 }, + { "ELAN0619", 0 }, + { "ELAN061A", 0 }, + { "ELAN061B", 0 }, { "ELAN061C", 0 }, { "ELAN061D", 0 }, { "ELAN061E", 0 }, + { "ELAN061F", 0 }, { "ELAN0620", 0 }, { "ELAN0621", 0 }, { "ELAN0622", 0 }, + { "ELAN0623", 0 }, + { "ELAN0624", 0 }, + { "ELAN0625", 0 }, + { "ELAN0626", 0 }, + { "ELAN0627", 0 }, + { "ELAN0628", 0 }, + { "ELAN0629", 0 }, + { "ELAN062A", 0 }, + { "ELAN062B", 0 }, + { "ELAN062C", 0 }, + { "ELAN062D", 0 }, + { "ELAN0631", 0 }, + { "ELAN0632", 0 }, { "ELAN1000", 0 }, { } }; -- cgit v1.2.3-55-g7522 From 07ba9e7be423423043c5090a2f395c0da26e1b3d Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 18 Jan 2019 11:18:17 -0800 Subject: Input: document meanings of KEY_SCREEN and KEY_ZOOM It is hard to say what KEY_SCREEN and KEY_ZOOM mean, but historically DVB folks have used them to indicate switch to full screen mode. Later, they converged on using KEY_ZOOM to switch into full screen mode and KEY)SCREEN to control aspect ratio (see Documentation/media/uapi/rc/rc-tables.rst). Let's commit to these uses, and define: - KEY_FULL_SCREEN (and make KEY_ZOOM its alias) - KEY_ASPECT_RATIO (and make KEY_SCREEN its alias) Signed-off-by: Dmitry Torokhov --- include/uapi/linux/input-event-codes.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index ae366b87426a..bc5054e51bef 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -439,10 +439,12 @@ #define KEY_TITLE 0x171 #define KEY_SUBTITLE 0x172 #define KEY_ANGLE 0x173 -#define KEY_ZOOM 0x174 +#define KEY_FULL_SCREEN 0x174 /* AC View Toggle */ +#define KEY_ZOOM KEY_FULL_SCREEN #define KEY_MODE 0x175 #define KEY_KEYBOARD 0x176 -#define KEY_SCREEN 0x177 +#define KEY_ASPECT_RATIO 0x177 /* HUTRR37: Aspect */ +#define KEY_SCREEN KEY_ASPECT_RATIO #define KEY_PC 0x178 /* Media Select Computer */ #define KEY_TV 0x179 /* Media Select TV */ #define KEY_TV2 0x17a /* Media Select Cable */ -- cgit v1.2.3-55-g7522 From 2291da5b4d305a6506d915d5bef85dedd7c94882 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 18 Jan 2019 13:37:40 -0800 Subject: [media] doc-rst: switch to new names for Full Screen/Aspect keys We defined better names for keys to activate full screen mode or change aspect ratio (while keeping the existing keycodes to avoid breaking userspace), so let's use them in the document. Signed-off-by: Dmitry Torokhov --- Documentation/media/uapi/rc/rc-tables.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/media/uapi/rc/rc-tables.rst b/Documentation/media/uapi/rc/rc-tables.rst index c8ae9479f842..57797e56f45e 100644 --- a/Documentation/media/uapi/rc/rc-tables.rst +++ b/Documentation/media/uapi/rc/rc-tables.rst @@ -616,7 +616,7 @@ the remote via /dev/input/event devices. - .. row 78 - - ``KEY_SCREEN`` + - ``KEY_ASPECT_RATIO`` - Select screen aspect ratio @@ -624,7 +624,7 @@ the remote via /dev/input/event devices. - .. row 79 - - ``KEY_ZOOM`` + - ``KEY_FULL_SCREEN`` - Put device into zoom/full screen mode -- cgit v1.2.3-55-g7522 From f7b3d85aa7a31a90c3ef5b0992604db339a615ab Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 18 Jan 2019 13:44:23 -0800 Subject: HID: input: fix mapping of aspect ratio key According to HUTRR37 usage 0x6d from the consumer usage page corresponds to action that selects the next available supported aspect ratio option on a device which outputs or displays video. However KEY_ZOOM means activate "Full Screen" mode, KEY_ASPECT_RATIO should be used instead. Signed-off-by: Dmitry Torokhov --- drivers/hid/hid-input.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index d6fab5798487..def58c6aa835 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -891,7 +891,7 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel case 0x06a: map_key_clear(KEY_GREEN); break; case 0x06b: map_key_clear(KEY_BLUE); break; case 0x06c: map_key_clear(KEY_YELLOW); break; - case 0x06d: map_key_clear(KEY_ZOOM); break; + case 0x06d: map_key_clear(KEY_ASPECT_RATIO); break; case 0x06f: map_key_clear(KEY_BRIGHTNESSUP); break; case 0x070: map_key_clear(KEY_BRIGHTNESSDOWN); break; -- cgit v1.2.3-55-g7522 From 96dd86871e1fffbc39e4fa61c9c75ec54ee9af0f Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 18 Jan 2019 13:59:08 -0800 Subject: HID: input: add mapping for Expose/Overview key According to HUTRR77 usage 0x29f from the consumer page is reserved for the Desktop application to present all running user’s application windows. Linux defines KEY_SCALE to request Compiz Scale (Expose) mode, so let's add the mapping. Signed-off-by: Dmitry Torokhov --- drivers/hid/hid-input.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index def58c6aa835..5f800e7b04f2 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -1030,6 +1030,8 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel case 0x2cb: map_key_clear(KEY_KBDINPUTASSIST_ACCEPT); break; case 0x2cc: map_key_clear(KEY_KBDINPUTASSIST_CANCEL); break; + case 0x29f: map_key_clear(KEY_SCALE); break; + default: map_key_clear(KEY_UNKNOWN); } break; -- cgit v1.2.3-55-g7522 From 7975a1d6a7afeb3eb61c971a153d24dd8fa032f3 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 18 Jan 2019 14:05:52 -0800 Subject: HID: input: add mapping for keyboard Brightness Up/Down/Toggle keys According to HUTRR73 usages 0x79, 0x7a and 0x7c from the consumer page correspond to Brightness Up/Down/Toggle keys, so let's add the mappings. Signed-off-by: Dmitry Torokhov --- drivers/hid/hid-input.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 5f800e7b04f2..cebe8a8cce2e 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -900,6 +900,10 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel case 0x074: map_key_clear(KEY_BRIGHTNESS_MAX); break; case 0x075: map_key_clear(KEY_BRIGHTNESS_AUTO); break; + case 0x079: map_key_clear(KEY_KBDILLUMUP); break; + case 0x07a: map_key_clear(KEY_KBDILLUMDOWN); break; + case 0x07c: map_key_clear(KEY_KBDILLUMTOGGLE); break; + case 0x082: map_key_clear(KEY_VIDEO_NEXT); break; case 0x083: map_key_clear(KEY_LAST); break; case 0x084: map_key_clear(KEY_ENTER); break; -- cgit v1.2.3-55-g7522 From afbbaa1bc0011d28f7604f9a7f0532f997c6f45e Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 18 Jan 2019 14:20:27 -0800 Subject: HID: input: add mapping for "Full Screen" key According to HUT 1.12 usage 0x232 from the consumer page is reserved for switching application between full screen and windowed mode, so let's add the mapping. Signed-off-by: Dmitry Torokhov --- drivers/hid/hid-input.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index cebe8a8cce2e..ecb1b6f26853 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -1014,6 +1014,7 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel case 0x22d: map_key_clear(KEY_ZOOMIN); break; case 0x22e: map_key_clear(KEY_ZOOMOUT); break; case 0x22f: map_key_clear(KEY_ZOOMRESET); break; + case 0x232: map_key_clear(KEY_FULL_SCREEN); break; case 0x233: map_key_clear(KEY_SCROLLUP); break; case 0x234: map_key_clear(KEY_SCROLLDOWN); break; case 0x238: map_rel(REL_HWHEEL); break; -- cgit v1.2.3-55-g7522 From c01908a14bf735b871170092807c618bb9dae654 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 18 Jan 2019 14:35:45 -0800 Subject: HID: input: add mapping for "Toggle Display" key According to HUT 1.12 usage 0xb5 from the generic desktop page is reserved for switching between external and internal display, so let's add the mapping. Signed-off-by: Dmitry Torokhov --- drivers/hid/hid-input.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index ecb1b6f26853..da76358cde06 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -677,6 +677,14 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel break; } + if ((usage->hid & 0xf0) == 0xb0) { /* SC - Display */ + switch (usage->hid & 0xf) { + case 0x05: map_key_clear(KEY_SWITCHVIDEOMODE); break; + default: goto ignore; + } + break; + } + /* * Some lazy vendors declare 255 usages for System Control, * leading to the creation of ABS_X|Y axis and too many others. -- cgit v1.2.3-55-g7522 From 2d4ea4b95cae3133de6b18ec5d5a42ee824fa0ef Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 7 Mar 2019 15:51:45 -0800 Subject: s390/mem_detect: Use IS_ENABLED(CONFIG_BLK_DEV_INITRD) IS_ENABLED should generally use CONFIG_ prefaced symbols and it doesn't appear as if there is a BLK_DEV_INITRD define. Cc: # 4.20 Signed-off-by: Joe Perches Signed-off-by: Martin Schwidefsky --- arch/s390/boot/mem_detect.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/boot/mem_detect.c b/arch/s390/boot/mem_detect.c index 4cb771ba13fa..5d316fe40480 100644 --- a/arch/s390/boot/mem_detect.c +++ b/arch/s390/boot/mem_detect.c @@ -25,7 +25,7 @@ static void *mem_detect_alloc_extended(void) { unsigned long offset = ALIGN(mem_safe_offset(), sizeof(u64)); - if (IS_ENABLED(BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE && + if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE && INITRD_START < offset + ENTRIES_EXTENDED_MAX) offset = ALIGN(INITRD_START + INITRD_SIZE, sizeof(u64)); -- cgit v1.2.3-55-g7522 From 2cc9637ce825f3a9f51f8f78af7474e9e85bfa5f Mon Sep 17 00:00:00 2001 From: Peter Oberparleiter Date: Fri, 22 Mar 2019 16:01:17 +0100 Subject: s390/dasd: Fix capacity calculation for large volumes The DASD driver incorrectly limits the maximum number of blocks of ECKD DASD volumes to 32 bit numbers. Volumes with a capacity greater than 2^32-1 blocks are incorrectly recognized as smaller volumes. This results in the following volume capacity limits depending on the formatted block size: BLKSIZE MAX_GB MAX_CYL 512 2047 5843492 1024 4095 8676701 2048 8191 13634816 4096 16383 23860929 The same problem occurs when a volume with more than 17895697 cylinders is accessed in raw-track-access mode. Fix this problem by adding an explicit type cast when calculating the maximum number of blocks. Signed-off-by: Peter Oberparleiter Reviewed-by: Stefan Haberland Signed-off-by: Martin Schwidefsky --- drivers/s390/block/dasd_eckd.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 6e294b4d3635..f89f9d02e788 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -2004,14 +2004,14 @@ static int dasd_eckd_end_analysis(struct dasd_block *block) blk_per_trk = recs_per_track(&private->rdc_data, 0, block->bp_block); raw: - block->blocks = (private->real_cyl * + block->blocks = ((unsigned long) private->real_cyl * private->rdc_data.trk_per_cyl * blk_per_trk); dev_info(&device->cdev->dev, - "DASD with %d KB/block, %d KB total size, %d KB/track, " + "DASD with %u KB/block, %lu KB total size, %u KB/track, " "%s\n", (block->bp_block >> 10), - ((private->real_cyl * + (((unsigned long) private->real_cyl * private->rdc_data.trk_per_cyl * blk_per_trk * (block->bp_block >> 9)) >> 1), ((blk_per_trk * block->bp_block) >> 10), -- cgit v1.2.3-55-g7522 From 7f75591fc5a123929a29636834d1bcb8b5c9fee3 Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Mon, 25 Mar 2019 14:01:23 +0100 Subject: iio: core: fix a possible circular locking dependency This fixes a possible circular locking dependency detected warning seen with: - CONFIG_PROVE_LOCKING=y - consumer/provider IIO devices (ex: "voltage-divider" consumer of "adc") When using the IIO consumer interface, e.g. iio_channel_get(), the consumer device will likely call iio_read_channel_raw() or similar that rely on 'info_exist_lock' mutex. typically: ... mutex_lock(&chan->indio_dev->info_exist_lock); if (chan->indio_dev->info == NULL) { ret = -ENODEV; goto err_unlock; } ret = do_some_ops() err_unlock: mutex_unlock(&chan->indio_dev->info_exist_lock); return ret; ... Same mutex is also hold in iio_device_unregister(). The following deadlock warning happens when: - the consumer device has called an API like iio_read_channel_raw() at least once. - the consumer driver is unregistered, removed (unbind from sysfs) ====================================================== WARNING: possible circular locking dependency detected 4.19.24 #577 Not tainted ------------------------------------------------------ sh/372 is trying to acquire lock: (kn->count#30){++++}, at: kernfs_remove_by_name_ns+0x3c/0x84 but task is already holding lock: (&dev->info_exist_lock){+.+.}, at: iio_device_unregister+0x18/0x60 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&dev->info_exist_lock){+.+.}: __mutex_lock+0x70/0xa3c mutex_lock_nested+0x1c/0x24 iio_read_channel_raw+0x1c/0x60 iio_read_channel_info+0xa8/0xb0 dev_attr_show+0x1c/0x48 sysfs_kf_seq_show+0x84/0xec seq_read+0x154/0x528 __vfs_read+0x2c/0x15c vfs_read+0x8c/0x110 ksys_read+0x4c/0xac ret_fast_syscall+0x0/0x28 0xbedefb60 -> #0 (kn->count#30){++++}: lock_acquire+0xd8/0x268 __kernfs_remove+0x288/0x374 kernfs_remove_by_name_ns+0x3c/0x84 remove_files+0x34/0x78 sysfs_remove_group+0x40/0x9c sysfs_remove_groups+0x24/0x34 device_remove_attrs+0x38/0x64 device_del+0x11c/0x360 cdev_device_del+0x14/0x2c iio_device_unregister+0x24/0x60 release_nodes+0x1bc/0x200 device_release_driver_internal+0x1a0/0x230 unbind_store+0x80/0x130 kernfs_fop_write+0x100/0x1e4 __vfs_write+0x2c/0x160 vfs_write+0xa4/0x17c ksys_write+0x4c/0xac ret_fast_syscall+0x0/0x28 0xbe906840 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&dev->info_exist_lock); lock(kn->count#30); lock(&dev->info_exist_lock); lock(kn->count#30); *** DEADLOCK *** ... cdev_device_del() can be called without holding the lock. It should be safe as info_exist_lock prevents kernelspace consumers to use the exported routines during/after provider removal. cdev_device_del() is for userspace. Help to reproduce: See example: Documentation/devicetree/bindings/iio/afe/voltage-divider.txt sysv { compatible = "voltage-divider"; io-channels = <&adc 0>; output-ohms = <22>; full-ohms = <222>; }; First, go to iio:deviceX for the "voltage-divider", do one read: $ cd /sys/bus/iio/devices/iio:deviceX $ cat in_voltage0_raw Then, unbind the consumer driver. It triggers above deadlock warning. $ cd /sys/bus/platform/drivers/iio-rescale/ $ echo sysv > unbind Note I don't actually expect stable will pick this up all the way back into IIO being in staging, but if's probably valid that far back. Signed-off-by: Fabrice Gasnier Fixes: ac917a81117c ("staging:iio:core set the iio_dev.info pointer to null on unregister") Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/industrialio-core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 4700fd5d8c90..9c4d92115504 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -1743,10 +1743,10 @@ EXPORT_SYMBOL(__iio_device_register); **/ void iio_device_unregister(struct iio_dev *indio_dev) { - mutex_lock(&indio_dev->info_exist_lock); - cdev_device_del(&indio_dev->chrdev, &indio_dev->dev); + mutex_lock(&indio_dev->info_exist_lock); + iio_device_unregister_debugfs(indio_dev); iio_disable_all_buffers(indio_dev); -- cgit v1.2.3-55-g7522 From 01b76c32e3f30d54ab8ec1efeed3c6ecef7f6027 Mon Sep 17 00:00:00 2001 From: Bo YU Date: Thu, 28 Mar 2019 03:47:37 -0400 Subject: misc: fastrpc: add checked value for dma_set_mask There be should check return value from dma_set_mask to throw some info if fail to set dma mask. Detected by CoverityScan, CID# 1443983: Error handling issues (CHECKED_RETURN) Fixes: f6f9279f2bf0 ("misc: fastrpc: Add Qualcomm fastrpc basic driver model") Signed-off-by: Bo YU Signed-off-by: Greg Kroah-Hartman --- drivers/misc/fastrpc.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 39f832d27288..36d0d5c9cfba 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -1184,6 +1184,7 @@ static int fastrpc_cb_probe(struct platform_device *pdev) struct fastrpc_session_ctx *sess; struct device *dev = &pdev->dev; int i, sessions = 0; + int rc; cctx = dev_get_drvdata(dev->parent); if (!cctx) @@ -1213,7 +1214,11 @@ static int fastrpc_cb_probe(struct platform_device *pdev) } cctx->sesscount++; spin_unlock(&cctx->lock); - dma_set_mask(dev, DMA_BIT_MASK(32)); + rc = dma_set_mask(dev, DMA_BIT_MASK(32)); + if (rc) { + dev_err(dev, "32-bit DMA enable failed\n"); + return rc; + } return 0; } -- cgit v1.2.3-55-g7522 From 131ac62253dba79daf4a6d83ab12293d2b9863d3 Mon Sep 17 00:00:00 2001 From: Christian Gromm Date: Tue, 2 Apr 2019 13:39:57 +0200 Subject: staging: most: core: use device description as name This patch uses the device description to clearly identity a device attached to the bus. It is needed as the currently useed mdevX notation is not sufficiant in case more than one network interface controller is being used at the same time. Cc: stable@vger.kernel.org Signed-off-by: Christian Gromm Signed-off-by: Greg Kroah-Hartman --- drivers/staging/most/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/most/core.c b/drivers/staging/most/core.c index 18936cdb1083..956daf8c3bd2 100644 --- a/drivers/staging/most/core.c +++ b/drivers/staging/most/core.c @@ -1431,7 +1431,7 @@ int most_register_interface(struct most_interface *iface) INIT_LIST_HEAD(&iface->p->channel_list); iface->p->dev_id = id; - snprintf(iface->p->name, STRING_SIZE, "mdev%d", id); + strcpy(iface->p->name, iface->description); iface->dev.init_name = iface->p->name; iface->dev.bus = &mc.bus; iface->dev.parent = &mc.dev; -- cgit v1.2.3-55-g7522 From bf2a7ca39fd3ab47ef71c621a7ee69d1813b1f97 Mon Sep 17 00:00:00 2001 From: Anson Huang Date: Wed, 3 Apr 2019 15:14:44 -0700 Subject: Input: snvs_pwrkey - initialize necessary driver data before enabling IRQ SNVS IRQ is requested before necessary driver data initialized, if there is a pending IRQ during driver probe phase, kernel NULL pointer panic will occur in IRQ handler. To avoid such scenario, just initialize necessary driver data before enabling IRQ. This patch is inspired by NXP's internal kernel tree. Fixes: d3dc6e232215 ("input: keyboard: imx: add snvs power key driver") Signed-off-by: Anson Huang Signed-off-by: Dmitry Torokhov --- drivers/input/keyboard/snvs_pwrkey.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/input/keyboard/snvs_pwrkey.c b/drivers/input/keyboard/snvs_pwrkey.c index effb63205d3d..4c67cf30a5d9 100644 --- a/drivers/input/keyboard/snvs_pwrkey.c +++ b/drivers/input/keyboard/snvs_pwrkey.c @@ -148,6 +148,9 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev) return error; } + pdata->input = input; + platform_set_drvdata(pdev, pdata); + error = devm_request_irq(&pdev->dev, pdata->irq, imx_snvs_pwrkey_interrupt, 0, pdev->name, pdev); @@ -163,9 +166,6 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev) return error; } - pdata->input = input; - platform_set_drvdata(pdev, pdata); - device_init_wakeup(&pdev->dev, pdata->wakeup); return 0; -- cgit v1.2.3-55-g7522 From 86baf800de84eb89615c138d368b14bff5ee7d8a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 6 Mar 2019 12:08:57 +0100 Subject: extcon: ptn5150: fix COMPILE_TEST dependencies The PTN5150 dependencies look like they were meant to do the right thing, but they actually should not allow building without I2C for compile testing, as that results in a Kconfig warning and subsequent build failure: WARNING: unmet direct dependencies detected for REGMAP_I2C Depends on [m]: I2C [=m] Selected by [y]: - EXTCON_PTN5150 [=y] && EXTCON [=y] && (I2C [=m] && GPIOLIB [=y] || COMPILE_TEST [=y]) Selected by [m]: - EEPROM_AT24 [=m] && I2C [=m] && SYSFS [=y] - KEYBOARD_CAP11XX [=m] && !UML && INPUT [=y] && INPUT_KEYBOARD [=y] && OF [=y] && I2C [=m] - INPUT_DRV260X_HAPTICS [=m] && !UML && INPUT_MISC [=y] && INPUT [=y] && I2C [=m] && (GPIOLIB [=y] || COMPILE_TEST [=y]) - ... [many others] Add parentheses around the expression so we can compile-test without GPIOLIB but not without I2C. Fixes: 4ed754de2d66 ("extcon: Add support for ptn5150 extcon driver") Signed-off-by: Arnd Bergmann Signed-off-by: Chanwoo Choi --- drivers/extcon/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/extcon/Kconfig b/drivers/extcon/Kconfig index 8e17149655f0..540e8cd16ee6 100644 --- a/drivers/extcon/Kconfig +++ b/drivers/extcon/Kconfig @@ -116,7 +116,7 @@ config EXTCON_PALMAS config EXTCON_PTN5150 tristate "NXP PTN5150 CC LOGIC USB EXTCON support" - depends on I2C && GPIOLIB || COMPILE_TEST + depends on I2C && (GPIOLIB || COMPILE_TEST) select REGMAP_I2C help Say Y here to enable support for USB peripheral and USB host -- cgit v1.2.3-55-g7522 From d58431eacb226222430940134d97bfd72f292fcd Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 5 Apr 2019 11:34:40 +1100 Subject: sunrpc: don't mark uninitialised items as VALID. A recent commit added a call to cache_fresh_locked() when an expired item was found. The call sets the CACHE_VALID flag, so it is important that the item actually is valid. There are two ways it could be valid: 1/ If ->update has been called to fill in relevant content 2/ if CACHE_NEGATIVE is set, to say that content doesn't exist. An expired item that is waiting for an update will be neither. Setting CACHE_VALID will mean that a subsequent call to cache_put() will be likely to dereference uninitialised pointers. So we must make sure the item is valid, and we already have code to do that in try_to_negate_entry(). This takes the hash lock and so cannot be used directly, so take out the two lines that we need and use them. Now cache_fresh_locked() is certain to be called only on a valid item. Cc: stable@kernel.org # 2.6.35 Fixes: 4ecd55ea0742 ("sunrpc: fix cache_head leak due to queued request") Signed-off-by: NeilBrown Signed-off-by: J. Bruce Fields --- net/sunrpc/cache.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 12bb23b8e0c5..261131dfa1f1 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -54,6 +54,7 @@ static void cache_init(struct cache_head *h, struct cache_detail *detail) h->last_refresh = now; } +static inline int cache_is_valid(struct cache_head *h); static void cache_fresh_locked(struct cache_head *head, time_t expiry, struct cache_detail *detail); static void cache_fresh_unlocked(struct cache_head *head, @@ -105,6 +106,8 @@ static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail, if (cache_is_expired(detail, tmp)) { hlist_del_init_rcu(&tmp->cache_list); detail->entries --; + if (cache_is_valid(tmp) == -EAGAIN) + set_bit(CACHE_NEGATIVE, &tmp->flags); cache_fresh_locked(tmp, 0, detail); freeme = tmp; break; -- cgit v1.2.3-55-g7522 From 3c86794ac0e6582eea7733619d58ea150198502f Mon Sep 17 00:00:00 2001 From: Murphy Zhou Date: Thu, 4 Apr 2019 14:57:11 +0800 Subject: nfsd/nfsd3_proc_readdir: fix buffer count and page pointers After this commit f875a79 nfsd: allow nfsv3 readdir request to be larger. nfsv3 readdir request size can be larger than PAGE_SIZE. So if the directory been read is large enough, we can use multiple pages in rq_respages. Update buffer count and page pointers like we do in readdirplus to make this happen. Now listing a directory within 3000 files will panic because we are counting in a wrong way and would write on random page. Fixes: f875a79 "nfsd: allow nfsv3 readdir request to be larger" Signed-off-by: Murphy Zhou Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs3proc.c | 17 +++++++++++++++-- fs/nfsd/nfs3xdr.c | 11 +++++++++-- 2 files changed, 24 insertions(+), 4 deletions(-) diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 8f933e84cec1..9bc32af4e2da 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -442,7 +442,9 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp) struct nfsd3_readdirargs *argp = rqstp->rq_argp; struct nfsd3_readdirres *resp = rqstp->rq_resp; __be32 nfserr; - int count; + int count = 0; + struct page **p; + caddr_t page_addr = NULL; dprintk("nfsd: READDIR(3) %s %d bytes at %d\n", SVCFH_fmt(&argp->fh), @@ -462,7 +464,18 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp) nfserr = nfsd_readdir(rqstp, &resp->fh, (loff_t*) &argp->cookie, &resp->common, nfs3svc_encode_entry); memcpy(resp->verf, argp->verf, 8); - resp->count = resp->buffer - argp->buffer; + count = 0; + for (p = rqstp->rq_respages + 1; p < rqstp->rq_next_page; p++) { + page_addr = page_address(*p); + + if (((caddr_t)resp->buffer >= page_addr) && + ((caddr_t)resp->buffer < page_addr + PAGE_SIZE)) { + count += (caddr_t)resp->buffer - page_addr; + break; + } + count += PAGE_SIZE; + } + resp->count = count >> 2; if (resp->offset) { loff_t offset = argp->cookie; diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 93fea246f676..8d789124ed3c 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -573,6 +573,7 @@ int nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) { struct nfsd3_readdirargs *args = rqstp->rq_argp; + int len; u32 max_blocksize = svc_max_payload(rqstp); p = decode_fh(p, &args->fh); @@ -582,8 +583,14 @@ nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) args->verf = p; p += 2; args->dircount = ~0; args->count = ntohl(*p++); - args->count = min_t(u32, args->count, max_blocksize); - args->buffer = page_address(*(rqstp->rq_next_page++)); + len = args->count = min_t(u32, args->count, max_blocksize); + + while (len > 0) { + struct page *p = *(rqstp->rq_next_page++); + if (!args->buffer) + args->buffer = page_address(p); + len -= PAGE_SIZE; + } return xdr_argsize_check(rqstp, p); } -- cgit v1.2.3-55-g7522 From 678cce4019d746da6c680c48ba9e6d417803e127 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 31 Mar 2019 13:04:11 -0700 Subject: crypto: x86/poly1305 - fix overflow during partial reduction The x86_64 implementation of Poly1305 produces the wrong result on some inputs because poly1305_4block_avx2() incorrectly assumes that when partially reducing the accumulator, the bits carried from limb 'd4' to limb 'h0' fit in a 32-bit integer. This is true for poly1305-generic which processes only one block at a time. However, it's not true for the AVX2 implementation, which processes 4 blocks at a time and therefore can produce intermediate limbs about 4x larger. Fix it by making the relevant calculations use 64-bit arithmetic rather than 32-bit. Note that most of the carries already used 64-bit arithmetic, but the d4 -> h0 carry was different for some reason. To be safe I also made the same change to the corresponding SSE2 code, though that only operates on 1 or 2 blocks at a time. I don't think it's really needed for poly1305_block_sse2(), but it doesn't hurt because it's already x86_64 code. It *might* be needed for poly1305_2block_sse2(), but overflows aren't easy to reproduce there. This bug was originally detected by my patches that improve testmgr to fuzz algorithms against their generic implementation. But also add a test vector which reproduces it directly (in the AVX2 case). Fixes: b1ccc8f4b631 ("crypto: poly1305 - Add a four block AVX2 variant for x86_64") Fixes: c70f4abef07a ("crypto: poly1305 - Add a SSE2 SIMD variant for x86_64") Cc: # v4.3+ Cc: Martin Willi Cc: Jason A. Donenfeld Signed-off-by: Eric Biggers Reviewed-by: Martin Willi Signed-off-by: Herbert Xu --- arch/x86/crypto/poly1305-avx2-x86_64.S | 14 +++++++---- arch/x86/crypto/poly1305-sse2-x86_64.S | 22 ++++++++++------- crypto/testmgr.h | 44 +++++++++++++++++++++++++++++++++- 3 files changed, 67 insertions(+), 13 deletions(-) diff --git a/arch/x86/crypto/poly1305-avx2-x86_64.S b/arch/x86/crypto/poly1305-avx2-x86_64.S index 3b6e70d085da..8457cdd47f75 100644 --- a/arch/x86/crypto/poly1305-avx2-x86_64.S +++ b/arch/x86/crypto/poly1305-avx2-x86_64.S @@ -323,6 +323,12 @@ ENTRY(poly1305_4block_avx2) vpaddq t2,t1,t1 vmovq t1x,d4 + # Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 -> + # h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small + # amount. Careful: we must not assume the carry bits 'd0 >> 26', + # 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit + # integers. It's true in a single-block implementation, but not here. + # d1 += d0 >> 26 mov d0,%rax shr $26,%rax @@ -361,16 +367,16 @@ ENTRY(poly1305_4block_avx2) # h0 += (d4 >> 26) * 5 mov d4,%rax shr $26,%rax - lea (%eax,%eax,4),%eax - add %eax,%ebx + lea (%rax,%rax,4),%rax + add %rax,%rbx # h4 = d4 & 0x3ffffff mov d4,%rax and $0x3ffffff,%eax mov %eax,h4 # h1 += h0 >> 26 - mov %ebx,%eax - shr $26,%eax + mov %rbx,%rax + shr $26,%rax add %eax,h1 # h0 = h0 & 0x3ffffff andl $0x3ffffff,%ebx diff --git a/arch/x86/crypto/poly1305-sse2-x86_64.S b/arch/x86/crypto/poly1305-sse2-x86_64.S index e6add74d78a5..6f0be7a86964 100644 --- a/arch/x86/crypto/poly1305-sse2-x86_64.S +++ b/arch/x86/crypto/poly1305-sse2-x86_64.S @@ -253,16 +253,16 @@ ENTRY(poly1305_block_sse2) # h0 += (d4 >> 26) * 5 mov d4,%rax shr $26,%rax - lea (%eax,%eax,4),%eax - add %eax,%ebx + lea (%rax,%rax,4),%rax + add %rax,%rbx # h4 = d4 & 0x3ffffff mov d4,%rax and $0x3ffffff,%eax mov %eax,h4 # h1 += h0 >> 26 - mov %ebx,%eax - shr $26,%eax + mov %rbx,%rax + shr $26,%rax add %eax,h1 # h0 = h0 & 0x3ffffff andl $0x3ffffff,%ebx @@ -524,6 +524,12 @@ ENTRY(poly1305_2block_sse2) paddq t2,t1 movq t1,d4 + # Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 -> + # h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small + # amount. Careful: we must not assume the carry bits 'd0 >> 26', + # 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit + # integers. It's true in a single-block implementation, but not here. + # d1 += d0 >> 26 mov d0,%rax shr $26,%rax @@ -562,16 +568,16 @@ ENTRY(poly1305_2block_sse2) # h0 += (d4 >> 26) * 5 mov d4,%rax shr $26,%rax - lea (%eax,%eax,4),%eax - add %eax,%ebx + lea (%rax,%rax,4),%rax + add %rax,%rbx # h4 = d4 & 0x3ffffff mov d4,%rax and $0x3ffffff,%eax mov %eax,h4 # h1 += h0 >> 26 - mov %ebx,%eax - shr $26,%eax + mov %rbx,%rax + shr $26,%rax add %eax,h1 # h0 = h0 & 0x3ffffff andl $0x3ffffff,%ebx diff --git a/crypto/testmgr.h b/crypto/testmgr.h index f267633cf13a..d18a37629f05 100644 --- a/crypto/testmgr.h +++ b/crypto/testmgr.h @@ -5634,7 +5634,49 @@ static const struct hash_testvec poly1305_tv_template[] = { .psize = 80, .digest = "\x13\x00\x00\x00\x00\x00\x00\x00" "\x00\x00\x00\x00\x00\x00\x00\x00", - }, + }, { /* Regression test for overflow in AVX2 implementation */ + .plaintext = "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff", + .psize = 300, + .digest = "\xfb\x5e\x96\xd8\x61\xd5\xc7\xc8" + "\x78\xe5\x87\xcc\x2d\x5a\x22\xe1", + } }; /* NHPoly1305 test vectors from https://github.com/google/adiantum */ -- cgit v1.2.3-55-g7522 From e6abc8caa6deb14be2a206253f7e1c5e37e9515b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 5 Apr 2019 08:54:37 -0700 Subject: nfsd: Don't release the callback slot unless it was actually held If there are multiple callbacks queued, waiting for the callback slot when the callback gets shut down, then they all currently end up acting as if they hold the slot, and call nfsd4_cb_sequence_done() resulting in interesting side-effects. In addition, the 'retry_nowait' path in nfsd4_cb_sequence_done() causes a loop back to nfsd4_cb_prepare() without first freeing the slot, which causes a deadlock when nfsd41_cb_get_slot() gets called a second time. This patch therefore adds a boolean to track whether or not the callback did pick up the slot, so that it can do the right thing in these 2 cases. Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4callback.c | 8 +++++++- fs/nfsd/state.h | 1 + 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index d219159b98af..7caa3801ce72 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -1010,8 +1010,9 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata) cb->cb_seq_status = 1; cb->cb_status = 0; if (minorversion) { - if (!nfsd41_cb_get_slot(clp, task)) + if (!cb->cb_holds_slot && !nfsd41_cb_get_slot(clp, task)) return; + cb->cb_holds_slot = true; } rpc_call_start(task); } @@ -1038,6 +1039,9 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback return true; } + if (!cb->cb_holds_slot) + goto need_restart; + switch (cb->cb_seq_status) { case 0: /* @@ -1076,6 +1080,7 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback cb->cb_seq_status); } + cb->cb_holds_slot = false; clear_bit(0, &clp->cl_cb_slot_busy); rpc_wake_up_next(&clp->cl_cb_waitq); dprintk("%s: freed slot, new seqid=%d\n", __func__, @@ -1283,6 +1288,7 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp, cb->cb_seq_status = 1; cb->cb_status = 0; cb->cb_need_restart = false; + cb->cb_holds_slot = false; } void nfsd4_run_cb(struct nfsd4_callback *cb) diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 396c76755b03..9d6cb246c6c5 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -70,6 +70,7 @@ struct nfsd4_callback { int cb_seq_status; int cb_status; bool cb_need_restart; + bool cb_holds_slot; }; struct nfsd4_callback_ops { -- cgit v1.2.3-55-g7522 From 9752c37cc89f43675e70cf9acff23519fa84b48c Mon Sep 17 00:00:00 2001 From: Vitor Soares Date: Tue, 9 Apr 2019 18:59:59 +0200 Subject: i3c: Fix the verification of random PID The validation of random PID should be done by checking the boardinfo->pid instead of info.pid which is empty. Doing the change the info struture declaration is no longer necessary. Cc: Boris Brezillon Cc: Fixes: 3a379bbcea0a ("i3c: Add core I3C infrastructure") Signed-off-by: Vitor Soares Signed-off-by: Boris Brezillon --- drivers/i3c/master.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c index 2dc628d4f1ae..1412abcff010 100644 --- a/drivers/i3c/master.c +++ b/drivers/i3c/master.c @@ -1980,7 +1980,6 @@ of_i3c_master_add_i3c_boardinfo(struct i3c_master_controller *master, { struct i3c_dev_boardinfo *boardinfo; struct device *dev = &master->dev; - struct i3c_device_info info = { }; enum i3c_addr_slot_status addrstatus; u32 init_dyn_addr = 0; @@ -2012,8 +2011,8 @@ of_i3c_master_add_i3c_boardinfo(struct i3c_master_controller *master, boardinfo->pid = ((u64)reg[1] << 32) | reg[2]; - if ((info.pid & GENMASK_ULL(63, 48)) || - I3C_PID_RND_LOWER_32BITS(info.pid)) + if ((boardinfo->pid & GENMASK_ULL(63, 48)) || + I3C_PID_RND_LOWER_32BITS(boardinfo->pid)) return -EINVAL; boardinfo->init_dyn_addr = init_dyn_addr; -- cgit v1.2.3-55-g7522 From 907621e94d49b85cd76f13110eceb940a182c69e Mon Sep 17 00:00:00 2001 From: Vitor Soares Date: Mon, 8 Apr 2019 13:13:34 +0200 Subject: i3c: dw: Fix dw_i3c_master_disable controller by using correct mask The controller was being disabled incorrectly. The correct way is to clear the DEV_CTRL_ENABLE bit. Fix this by clearing this bit. Cc: Boris Brezillon Cc: Fixes: 1dd728f5d4d4 ("i3c: master: Add driver for Synopsys DesignWare IP") Signed-off-by: Vitor Soares Signed-off-by: Boris Brezillon --- drivers/i3c/master/dw-i3c-master.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index 59279224e07f..10c26ffaa8ef 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -300,7 +300,7 @@ to_dw_i3c_master(struct i3c_master_controller *master) static void dw_i3c_master_disable(struct dw_i3c_master *master) { - writel(readl(master->regs + DEVICE_CTRL) & DEV_CTRL_ENABLE, + writel(readl(master->regs + DEVICE_CTRL) & ~DEV_CTRL_ENABLE, master->regs + DEVICE_CTRL); } -- cgit v1.2.3-55-g7522 From 709a53e1948494cc4f6c4636c6f84a4d36a8117e Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sat, 30 Mar 2019 09:02:14 +0100 Subject: MAINTAINERS: Fix the I3C entry There's no include/dt-bindings/i3c/ directory, remove this F: entry from the I3C file patterns. Cc: Greg Kroah-Hartman Cc: Joe Perches Reported-by: Joe Perches Fixes: 4f26d0666961 ("MAINTAINERS: Add myself as the I3C subsystem maintainer") Signed-off-by: Boris Brezillon --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 2359e12e4c41..30d3010c8825 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7333,7 +7333,6 @@ F: Documentation/devicetree/bindings/i3c/ F: Documentation/driver-api/i3c F: drivers/i3c/ F: include/linux/i3c/ -F: include/dt-bindings/i3c/ I3C DRIVER FOR SYNOPSYS DESIGNWARE M: Vitor Soares -- cgit v1.2.3-55-g7522 From 5712f3301a12c0c3de9cc423484496b0464f2faf Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Wed, 3 Apr 2019 09:13:34 +0200 Subject: s390/3270: fix lockdep false positive on view->lock The spinlock in the raw3270_view structure is used by con3270, tty3270 and fs3270 in different ways. For con3270 the lock can be acquired in irq context, for tty3270 and fs3270 the highest context is bh. Lockdep sees the view->lock as a single class and if the 3270 driver is used for the console the following message is generated: WARNING: inconsistent lock state 5.1.0-rc3-05157-g5c168033979d #12 Not tainted -------------------------------- inconsistent {IN-HARDIRQ-W} -> {HARDIRQ-ON-W} usage. swapper/0/1 [HC0[0]:SC1[1]:HE1:SE0] takes: (____ptrval____) (&(&view->lock)->rlock){?.-.}, at: tty3270_update+0x7c/0x330 Introduce a lockdep subclass for the view lock to distinguish bh from irq locks. Signed-off-by: Martin Schwidefsky --- drivers/s390/char/con3270.c | 2 +- drivers/s390/char/fs3270.c | 3 ++- drivers/s390/char/raw3270.c | 3 ++- drivers/s390/char/raw3270.h | 4 +++- drivers/s390/char/tty3270.c | 3 ++- 5 files changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/s390/char/con3270.c b/drivers/s390/char/con3270.c index fd2146bcc0ad..e17364e13d2f 100644 --- a/drivers/s390/char/con3270.c +++ b/drivers/s390/char/con3270.c @@ -629,7 +629,7 @@ con3270_init(void) (void (*)(unsigned long)) con3270_read_tasklet, (unsigned long) condev->read); - raw3270_add_view(&condev->view, &con3270_fn, 1); + raw3270_add_view(&condev->view, &con3270_fn, 1, RAW3270_VIEW_LOCK_IRQ); INIT_LIST_HEAD(&condev->freemem); for (i = 0; i < CON3270_STRING_PAGES; i++) { diff --git a/drivers/s390/char/fs3270.c b/drivers/s390/char/fs3270.c index 8f3a2eeb28dc..8b48ba9c598e 100644 --- a/drivers/s390/char/fs3270.c +++ b/drivers/s390/char/fs3270.c @@ -463,7 +463,8 @@ fs3270_open(struct inode *inode, struct file *filp) init_waitqueue_head(&fp->wait); fp->fs_pid = get_pid(task_pid(current)); - rc = raw3270_add_view(&fp->view, &fs3270_fn, minor); + rc = raw3270_add_view(&fp->view, &fs3270_fn, minor, + RAW3270_VIEW_LOCK_BH); if (rc) { fs3270_free_view(&fp->view); goto out; diff --git a/drivers/s390/char/raw3270.c b/drivers/s390/char/raw3270.c index f8cd2935fbfd..63a41b168761 100644 --- a/drivers/s390/char/raw3270.c +++ b/drivers/s390/char/raw3270.c @@ -920,7 +920,7 @@ raw3270_deactivate_view(struct raw3270_view *view) * Add view to device with minor "minor". */ int -raw3270_add_view(struct raw3270_view *view, struct raw3270_fn *fn, int minor) +raw3270_add_view(struct raw3270_view *view, struct raw3270_fn *fn, int minor, int subclass) { unsigned long flags; struct raw3270 *rp; @@ -942,6 +942,7 @@ raw3270_add_view(struct raw3270_view *view, struct raw3270_fn *fn, int minor) view->cols = rp->cols; view->ascebc = rp->ascebc; spin_lock_init(&view->lock); + lockdep_set_subclass(&view->lock, subclass); list_add(&view->list, &rp->view_list); rc = 0; spin_unlock_irqrestore(get_ccwdev_lock(rp->cdev), flags); diff --git a/drivers/s390/char/raw3270.h b/drivers/s390/char/raw3270.h index 114ca7cbf889..3afaa35f7351 100644 --- a/drivers/s390/char/raw3270.h +++ b/drivers/s390/char/raw3270.h @@ -150,6 +150,8 @@ struct raw3270_fn { struct raw3270_view { struct list_head list; spinlock_t lock; +#define RAW3270_VIEW_LOCK_IRQ 0 +#define RAW3270_VIEW_LOCK_BH 1 atomic_t ref_count; struct raw3270 *dev; struct raw3270_fn *fn; @@ -158,7 +160,7 @@ struct raw3270_view { unsigned char *ascebc; /* ascii -> ebcdic table */ }; -int raw3270_add_view(struct raw3270_view *, struct raw3270_fn *, int); +int raw3270_add_view(struct raw3270_view *, struct raw3270_fn *, int, int); int raw3270_activate_view(struct raw3270_view *); void raw3270_del_view(struct raw3270_view *); void raw3270_deactivate_view(struct raw3270_view *); diff --git a/drivers/s390/char/tty3270.c b/drivers/s390/char/tty3270.c index 2b0c36c2c568..98d7fc152e32 100644 --- a/drivers/s390/char/tty3270.c +++ b/drivers/s390/char/tty3270.c @@ -980,7 +980,8 @@ static int tty3270_install(struct tty_driver *driver, struct tty_struct *tty) return PTR_ERR(tp); rc = raw3270_add_view(&tp->view, &tty3270_fn, - tty->index + RAW3270_FIRSTMINOR); + tty->index + RAW3270_FIRSTMINOR, + RAW3270_VIEW_LOCK_BH); if (rc) { tty3270_free_view(tp); return rc; -- cgit v1.2.3-55-g7522 From 16222cfb96b02a4a3e38e52012f2a6304850c3c9 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Wed, 3 Apr 2019 13:18:22 +0200 Subject: s390/zcrypt: fix possible deadlock situation on ap queue remove With commit 01396a374c3d ("s390/zcrypt: revisit ap device remove procedure") the ap queue remove is now a two stage process. However, a del_timer_sync() call may trigger the timer function which may try to lock the very same spinlock as is held by the function just initiating the del_timer_sync() call. This could end up in a deadlock situation. Very unlikely but possible as you need to remove an ap queue at the exact sime time when a timeout of a request occurs. Signed-off-by: Harald Freudenberger Reported-by: Pierre Morel Fixes: commit 01396a374c3d ("s390/zcrypt: revisit ap device remove procedure") Signed-off-by: Martin Schwidefsky --- drivers/s390/crypto/ap_queue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index 6a340f2c3556..5ea83dc4f1d7 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -751,8 +751,8 @@ void ap_queue_prepare_remove(struct ap_queue *aq) __ap_flush_queue(aq); /* set REMOVE state to prevent new messages are queued in */ aq->state = AP_STATE_REMOVE; - del_timer_sync(&aq->timeout); spin_unlock_bh(&aq->lock); + del_timer_sync(&aq->timeout); } void ap_queue_remove(struct ap_queue *aq) -- cgit v1.2.3-55-g7522 From 1bfb97b9a51901103677a4d1a2386d223c15bc71 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 12 Mar 2019 10:50:05 -0700 Subject: MAINTAINERS: BMIPS: Add internal Broadcom mailing list There is a patchwork instance behind bcm-kernel-feedback-list that is helpful to track submissions, add this list for the MIPS BMIPS entry. Signed-off-by: Florian Fainelli Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 2359e12e4c41..92df0eb1aa6c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3121,6 +3121,7 @@ F: drivers/cpufreq/bmips-cpufreq.c BROADCOM BMIPS MIPS ARCHITECTURE M: Kevin Cernekee M: Florian Fainelli +L: bcm-kernel-feedback-list@broadcom.com L: linux-mips@vger.kernel.org T: git git://github.com/broadcom/stblinux.git S: Maintained -- cgit v1.2.3-55-g7522 From a66477b0efe511d98dde3e4aaeb189790e6f0a39 Mon Sep 17 00:00:00 2001 From: Christian König Date: Tue, 2 Apr 2019 09:26:52 +0200 Subject: drm/ttm: fix out-of-bounds read in ttm_put_pages() v2 When ttm_put_pages() tries to figure out whether it's dealing with transparent hugepages, it just reads past the bounds of the pages array without a check. v2: simplify the test if enough pages are left in the array (Christian). Signed-off-by: Jann Horn Signed-off-by: Christian König Fixes: 5c42c64f7d54 ("drm/ttm: fix the fix for huge compound pages") Cc: stable@vger.kernel.org Reviewed-by: Michel Dänzer Reviewed-by: Junwei Zhang Reviewed-by: Huang Rui Signed-off-by: Alex Deucher --- drivers/gpu/drm/ttm/ttm_page_alloc.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c index f841accc2c00..f77c81db161b 100644 --- a/drivers/gpu/drm/ttm/ttm_page_alloc.c +++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c @@ -730,7 +730,8 @@ static void ttm_put_pages(struct page **pages, unsigned npages, int flags, } #ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (!(flags & TTM_PAGE_FLAG_DMA32)) { + if (!(flags & TTM_PAGE_FLAG_DMA32) && + (npages - i) >= HPAGE_PMD_NR) { for (j = 0; j < HPAGE_PMD_NR; ++j) if (p++ != pages[i + j]) break; @@ -759,7 +760,7 @@ static void ttm_put_pages(struct page **pages, unsigned npages, int flags, unsigned max_size, n2free; spin_lock_irqsave(&huge->lock, irq_flags); - while (i < npages) { + while ((npages - i) >= HPAGE_PMD_NR) { struct page *p = pages[i]; unsigned j; -- cgit v1.2.3-55-g7522 From ac1e516d5a4c56bf0cb4a3dfc0672f689131cfd4 Mon Sep 17 00:00:00 2001 From: Christian König Date: Tue, 2 Apr 2019 09:29:35 +0200 Subject: drm/ttm: fix start page for huge page check in ttm_put_pages() The first page entry is always the same with itself. Signed-off-by: Christian König Reviewed-by: Michel Dänzer Reviewed-by: Junwei Zhang Reviewed-by: Huang Rui Signed-off-by: Alex Deucher --- drivers/gpu/drm/ttm/ttm_page_alloc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c index f77c81db161b..c74147f0cbe3 100644 --- a/drivers/gpu/drm/ttm/ttm_page_alloc.c +++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c @@ -732,7 +732,7 @@ static void ttm_put_pages(struct page **pages, unsigned npages, int flags, #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (!(flags & TTM_PAGE_FLAG_DMA32) && (npages - i) >= HPAGE_PMD_NR) { - for (j = 0; j < HPAGE_PMD_NR; ++j) + for (j = 1; j < HPAGE_PMD_NR; ++j) if (p++ != pages[i + j]) break; @@ -767,7 +767,7 @@ static void ttm_put_pages(struct page **pages, unsigned npages, int flags, if (!p) break; - for (j = 0; j < HPAGE_PMD_NR; ++j) + for (j = 1; j < HPAGE_PMD_NR; ++j) if (p++ != pages[i + j]) break; -- cgit v1.2.3-55-g7522 From 453393369dc9806d2455151e329c599684762428 Mon Sep 17 00:00:00 2001 From: Christian König Date: Wed, 10 Apr 2019 11:43:43 +0200 Subject: drm/ttm: fix incrementing the page pointer for huge pages When we increment the counter we need to increment the pointer as well. Signed-off-by: Christian König Fixes: e16858a7e6e7 drm/ttm: fix start page for huge page check in ttm_put_pages() Reviewed-by: Michel Dänzer Acked-by: Huang Rui Signed-off-by: Alex Deucher --- drivers/gpu/drm/ttm/ttm_page_alloc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c index c74147f0cbe3..627f8dc91d0e 100644 --- a/drivers/gpu/drm/ttm/ttm_page_alloc.c +++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c @@ -733,7 +733,7 @@ static void ttm_put_pages(struct page **pages, unsigned npages, int flags, if (!(flags & TTM_PAGE_FLAG_DMA32) && (npages - i) >= HPAGE_PMD_NR) { for (j = 1; j < HPAGE_PMD_NR; ++j) - if (p++ != pages[i + j]) + if (++p != pages[i + j]) break; if (j == HPAGE_PMD_NR) @@ -768,7 +768,7 @@ static void ttm_put_pages(struct page **pages, unsigned npages, int flags, break; for (j = 1; j < HPAGE_PMD_NR; ++j) - if (p++ != pages[i + j]) + if (++p != pages[i + j]) break; if (j != HPAGE_PMD_NR) -- cgit v1.2.3-55-g7522 From 543c364d8eeeb42c0edfaac9764f4e9f3d777ec1 Mon Sep 17 00:00:00 2001 From: Lin Yi Date: Wed, 10 Apr 2019 10:23:34 +0800 Subject: drm/ttm: fix dma_fence refcount imbalance on error path the ttm_bo_add_move_fence takes a reference to the struct dma_fence, but failed to release it on the error path, leading to a memory leak. add dma_fence_put before return when error occur. Signed-off-by: Lin Yi Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/ttm/ttm_bo.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 3f56647cdb35..0fa5034b9f9e 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -876,8 +876,10 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo, reservation_object_add_shared_fence(bo->resv, fence); ret = reservation_object_reserve_shared(bo->resv, 1); - if (unlikely(ret)) + if (unlikely(ret)) { + dma_fence_put(fence); return ret; + } dma_fence_put(bo->moving); bo->moving = fence; -- cgit v1.2.3-55-g7522 From f4bbebf8e7eb4d294b040ab2d2ba71e70e69b930 Mon Sep 17 00:00:00 2001 From: Martin Leung Date: Tue, 26 Mar 2019 13:14:11 -0400 Subject: drm/amd/display: extending AUX SW Timeout [Why] AUX takes longer to reply when using active DP-DVI dongle on some asics resulting in up to 2000+ us edid read (timeout). [How] 1. Adjust AUX poll to match spec 2. Extend the SW timeout. This does not affect normal operation since we exit the loop as soon as AUX acks. Signed-off-by: Martin Leung Reviewed-by: Jun Lei Acked-by: Joshua Aberback Acked-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dce/dce_aux.c | 9 ++++++--- drivers/gpu/drm/amd/display/dc/dce/dce_aux.h | 6 +++--- 2 files changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c index 4febf4ef7240..4fe3664fb495 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c @@ -190,6 +190,12 @@ static void submit_channel_request( 1, 0); } + + REG_UPDATE(AUX_INTERRUPT_CONTROL, AUX_SW_DONE_ACK, 1); + + REG_WAIT(AUX_SW_STATUS, AUX_SW_DONE, 0, + 10, aux110->timeout_period/10); + /* set the delay and the number of bytes to write */ /* The length include @@ -242,9 +248,6 @@ static void submit_channel_request( } } - REG_UPDATE(AUX_INTERRUPT_CONTROL, AUX_SW_DONE_ACK, 1); - REG_WAIT(AUX_SW_STATUS, AUX_SW_DONE, 0, - 10, aux110->timeout_period/10); REG_UPDATE(AUX_SW_CONTROL, AUX_SW_GO, 1); } diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h index d27f22c05e4b..e28ed6a00ff4 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h @@ -71,11 +71,11 @@ enum { /* This is the timeout as defined in DP 1.2a, * at most within ~240usec. That means, * increasing this timeout will not affect normal operation, * and we'll timeout after - * SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD = 1600usec. + * SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD = 2400usec. * This timeout is especially important for - * resume from S3 and CTS. + * converters, resume from S3, and CTS. */ - SW_AUX_TIMEOUT_PERIOD_MULTIPLIER = 4 + SW_AUX_TIMEOUT_PERIOD_MULTIPLIER = 6 }; struct dce_aux { -- cgit v1.2.3-55-g7522 From 8bbad1ba3196814487438d1299cec75de5c74615 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 6 Mar 2019 14:57:43 +0100 Subject: gpu: host1x: Program stream ID to bypass without SMMU If SMMU support is not available, fall back to programming the bypass stream ID (0x7f). Fixes: de5469c21ff9 ("gpu: host1x: Program the channel stream ID") Suggested-by: Mikko Perttunen Signed-off-by: Arnd Bergmann Reviewed-by: Mikko Perttunen [treding@nvidia.com: rebase this on top of a later build fix] Signed-off-by: Thierry Reding --- drivers/gpu/host1x/hw/channel_hw.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c index 4030d64916f0..0c0eb43abf65 100644 --- a/drivers/gpu/host1x/hw/channel_hw.c +++ b/drivers/gpu/host1x/hw/channel_hw.c @@ -114,9 +114,13 @@ static inline void synchronize_syncpt_base(struct host1x_job *job) static void host1x_channel_set_streamid(struct host1x_channel *channel) { -#if IS_ENABLED(CONFIG_IOMMU_API) && HOST1X_HW >= 6 +#if HOST1X_HW >= 6 + u32 sid = 0x7f; +#ifdef CONFIG_IOMMU_API struct iommu_fwspec *spec = dev_iommu_fwspec_get(channel->dev->parent); - u32 sid = spec ? spec->ids[0] & 0xffff : 0x7f; + if (spec) + sid = spec->ids[0] & 0xffff; +#endif host1x_ch_writel(channel, sid, HOST1X_CHANNEL_SMMU_STREAMID); #endif -- cgit v1.2.3-55-g7522 From 99834eead2a04e93a120abb112542b87c42ff5e1 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 5 Mar 2019 14:24:48 +0100 Subject: clocksource/drivers/npcm: select TIMER_OF When this is disabled, we get a link failure: drivers/clocksource/timer-npcm7xx.o: In function `npcm7xx_timer_init': timer-npcm7xx.c:(.init.text+0xf): undefined reference to `timer_of_init' Fixes: 1c00289ecd12 ("clocksource/drivers/npcm: Add NPCM7xx timer driver") Signed-off-by: Arnd Bergmann Signed-off-by: Daniel Lezcano --- drivers/clocksource/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index 171502a356aa..4b3d143f0f8a 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -145,6 +145,7 @@ config VT8500_TIMER config NPCM7XX_TIMER bool "NPCM7xx timer driver" if COMPILE_TEST depends on HAS_IOMEM + select TIMER_OF select CLKSRC_MMIO help Enable 24-bit TIMER0 and TIMER1 counters in the NPCM7xx architecture, -- cgit v1.2.3-55-g7522 From 9155697e20040658438b89e4ceec415ec125f478 Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Tue, 5 Mar 2019 12:08:51 -0500 Subject: clocksource/drivers/arm_arch_timer: Remove unneeded pr_fmt macro After this commit ded24019b6b6f(clocksource: arm_arch_timer: clean up printk usage), the previous macro is redundant, so delete it. And move the new macro to the previous position. Signed-off-by: Yangtao Li Signed-off-by: Daniel Lezcano --- drivers/clocksource/arm_arch_timer.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index aa4ec53281ce..ea373cfbcecb 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -9,7 +9,7 @@ * published by the Free Software Foundation. */ -#define pr_fmt(fmt) "arm_arch_timer: " fmt +#define pr_fmt(fmt) "arch_timer: " fmt #include #include @@ -33,9 +33,6 @@ #include -#undef pr_fmt -#define pr_fmt(fmt) "arch_timer: " fmt - #define CNTTIDR 0x08 #define CNTTIDR_VIRT(n) (BIT(1) << ((n) * 4)) -- cgit v1.2.3-55-g7522 From fbc87aa0f7c429999dc31f1bac3b2615008cac32 Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Tue, 12 Mar 2019 11:32:56 +0100 Subject: clocksource/drivers/oxnas: Fix OX820 compatible The OX820 compatible is wrong is the driver, fix it. Fixes: 2ea3401e2a84 ("clocksource/drivers/oxnas: Add OX820 compatible") Reported-by: Daniel Golle Signed-off-by: Neil Armstrong Signed-off-by: Daniel Lezcano --- drivers/clocksource/timer-oxnas-rps.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clocksource/timer-oxnas-rps.c b/drivers/clocksource/timer-oxnas-rps.c index eed6feff8b5f..30c6f4ce672b 100644 --- a/drivers/clocksource/timer-oxnas-rps.c +++ b/drivers/clocksource/timer-oxnas-rps.c @@ -296,4 +296,4 @@ err_alloc: TIMER_OF_DECLARE(ox810se_rps, "oxsemi,ox810se-rps-timer", oxnas_rps_timer_init); TIMER_OF_DECLARE(ox820_rps, - "oxsemi,ox820se-rps-timer", oxnas_rps_timer_init); + "oxsemi,ox820-rps-timer", oxnas_rps_timer_init); -- cgit v1.2.3-55-g7522 From b575f10dbd6f84c2c8744ff1f486bfae1e4f6f38 Mon Sep 17 00:00:00 2001 From: wentalou Date: Fri, 12 Apr 2019 15:01:14 +0800 Subject: drm/amdgpu: shadow in shadow_list without tbo.mem.start cause page fault in sriov TDR shadow was added into shadow_list by amdgpu_bo_create_shadow. meanwhile, shadow->tbo.mem was not fully configured. tbo.mem would be fully configured by amdgpu_vm_sdma_map_table until calling amdgpu_vm_clear_bo. If sriov TDR occurred between amdgpu_bo_create_shadow and amdgpu_vm_sdma_map_table, amdgpu_device_recover_vram would deal with shadow without tbo.mem.start. Signed-off-by: Wentao Lou Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 5d8b30fd4534..79fb302fb954 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3165,6 +3165,7 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev) /* No need to recover an evicted BO */ if (shadow->tbo.mem.mem_type != TTM_PL_TT || + shadow->tbo.mem.start == AMDGPU_BO_INVALID_OFFSET || shadow->parent->tbo.mem.mem_type != TTM_PL_VRAM) continue; -- cgit v1.2.3-55-g7522 From 1925e7d3d4677e681cc2e878c2bdbeaee988c8e2 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 11 Apr 2019 14:54:40 -0500 Subject: drm/amdgpu/gmc9: fix VM_L2_CNTL3 programming Got accidently dropped when 2+1 level support was added. Fixes: 6a42fd6fbf534096 ("drm/amdgpu: implement 2+1 PD support for Raven v3") Reviewed-by: Christian König Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c index d0d966d6080a..1696644ec022 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c @@ -182,6 +182,7 @@ static void mmhub_v1_0_init_cache_regs(struct amdgpu_device *adev) tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, L2_CACHE_BIGK_FRAGMENT_SIZE, 6); } + WREG32_SOC15(MMHUB, 0, mmVM_L2_CNTL3, tmp); tmp = mmVM_L2_CNTL4_DEFAULT; tmp = REG_SET_FIELD(tmp, VM_L2_CNTL4, VMC_TAP_PDE_REQUEST_PHYSICAL, 0); -- cgit v1.2.3-55-g7522 From ba25b81e3a420f8345585029d49ee32e73de9d5f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 13 Apr 2019 08:37:36 +0100 Subject: afs: avoid deprecated get_seconds() get_seconds() has a limited range on 32-bit architectures and is deprecated because of that. While AFS uses the same limits for its inode timestamps on the wire protocol, let's just use the simpler current_time() as we do for other file systems. This will still zero out the 'tv_nsec' field of the timestamps internally. Signed-off-by: Arnd Bergmann Signed-off-by: David Howells --- fs/afs/inode.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 1a4ce07fb406..9cedc3fc1b77 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -216,9 +216,7 @@ struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root) set_nlink(inode, 2); inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; - inode->i_ctime.tv_sec = get_seconds(); - inode->i_ctime.tv_nsec = 0; - inode->i_atime = inode->i_mtime = inode->i_ctime; + inode->i_ctime = inode->i_atime = inode->i_mtime = current_time(inode); inode->i_blocks = 0; inode_set_iversion_raw(inode, 0); inode->i_generation = 0; -- cgit v1.2.3-55-g7522 From d2abfa86ff373bd00634a656c7ad5531747f2bf8 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Sat, 13 Apr 2019 08:37:36 +0100 Subject: afs: Avoid section confusion in CM_NAME __tracepoint_str cannot be const because the tracepoint_str section is not read-only. Remove the stray const. Cc: dhowells@redhat.com Cc: viro@zeniv.linux.org.uk Signed-off-by: Andi Kleen --- fs/afs/cmservice.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index 8ee5972893ed..2f8acb4c556d 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -34,7 +34,7 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *); static int afs_deliver_yfs_cb_callback(struct afs_call *); #define CM_NAME(name) \ - const char afs_SRXCB##name##_name[] __tracepoint_string = \ + char afs_SRXCB##name##_name[] __tracepoint_string = \ "CB." #name /* -- cgit v1.2.3-55-g7522 From 8022c4b95c3793d7ba28ab0701ea15b5deb46e02 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 13 Apr 2019 08:37:37 +0100 Subject: afs: Differentiate abort due to unmarshalling from other errors Differentiate an abort due to an unmarshalling error from an abort due to other errors, such as ENETUNREACH. It doesn't make sense to set abort code RXGEN_*_UNMARSHAL in such a case, so use RX_USER_ABORT instead. Signed-off-by: David Howells --- fs/afs/rxrpc.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index c14001b42d20..15c7e82d80cb 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -572,13 +572,17 @@ static void afs_deliver_to_call(struct afs_call *call) case -ENODATA: case -EBADMSG: case -EMSGSIZE: - default: abort_code = RXGEN_CC_UNMARSHAL; if (state != AFS_CALL_CL_AWAIT_REPLY) abort_code = RXGEN_SS_UNMARSHAL; rxrpc_kernel_abort_call(call->net->socket, call->rxcall, abort_code, ret, "KUM"); goto local_abort; + default: + abort_code = RX_USER_ABORT; + rxrpc_kernel_abort_call(call->net->socket, call->rxcall, + abort_code, ret, "KER"); + goto local_abort; } } -- cgit v1.2.3-55-g7522 From 21bd68f196ca91fc0f3d9bd1b32f6e530e8c1c88 Mon Sep 17 00:00:00 2001 From: Marc Dionne Date: Sat, 13 Apr 2019 08:37:37 +0100 Subject: afs: Unlock pages for __pagevec_release() __pagevec_release() complains loudly if any page in the vector is still locked. The pages need to be locked for generic_error_remove_page(), but that function doesn't actually unlock them. Unlock the pages afterwards. Signed-off-by: Marc Dionne Signed-off-by: David Howells Tested-by: Jonathan Billings --- fs/afs/write.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/afs/write.c b/fs/afs/write.c index 72efcfcf9f95..0122d7445fba 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -264,6 +264,7 @@ static void afs_kill_pages(struct address_space *mapping, first = page->index + 1; lock_page(page); generic_error_remove_page(mapping, page); + unlock_page(page); } __pagevec_release(&pv); -- cgit v1.2.3-55-g7522 From eeba1e9cf31d064284dd1fa7bd6cfe01395bd03d Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 13 Apr 2019 08:37:37 +0100 Subject: afs: Fix in-progess ops to ignore server-level callback invalidation The in-kernel afs filesystem client counts the number of server-level callback invalidation events (CB.InitCallBackState* RPC operations) that it receives from the server. This is stored in cb_s_break in various structures, including afs_server and afs_vnode. If an inode is examined by afs_validate(), say, the afs_server copy is compared, along with other break counters, to those in afs_vnode, and if one or more of the counters do not match, it is considered that the server's callback promise is broken. At points where this happens, AFS_VNODE_CB_PROMISED is cleared to indicate that the status must be refetched from the server. afs_validate() issues an FS.FetchStatus operation to get updated metadata - and based on the updated data_version may invalidate the pagecache too. However, the break counters are also used to determine whether to note a new callback in the vnode (which would set the AFS_VNODE_CB_PROMISED flag) and whether to cache the permit data included in the YFSFetchStatus record by the server. The problem comes when the server sends us a CB.InitCallBackState op. The first such instance doesn't cause cb_s_break to be incremented, but rather causes AFS_SERVER_FL_NEW to be cleared - but thereafter, say some hours after last use and all the volumes have been automatically unmounted and the server has forgotten about the client[*], this *will* likely cause an increment. [*] There are other circumstances too, such as the server restarting or needing to make space in its callback table. Note that the server won't send us a CB.InitCallBackState op until we talk to it again. So what happens is: (1) A mount for a new volume is attempted, a inode is created for the root vnode and vnode->cb_s_break and AFS_VNODE_CB_PROMISED aren't set immediately, as we don't have a nominated server to talk to yet - and we may iterate through a few to find one. (2) Before the operation happens, afs_fetch_status(), say, notes in the cursor (fc.cb_break) the break counter sum from the vnode, volume and server counters, but the server->cb_s_break is currently 0. (3) We send FS.FetchStatus to the server. The server sends us back CB.InitCallBackState. We increment server->cb_s_break. (4) Our FS.FetchStatus completes. The reply includes a callback record. (5) xdr_decode_AFSCallBack()/xdr_decode_YFSCallBack() check to see whether the callback promise was broken by checking the break counter sum from step (2) against the current sum. This fails because of step (3), so we don't set the callback record and, importantly, don't set AFS_VNODE_CB_PROMISED on the vnode. This does not preclude the syscall from progressing, and we don't loop here rechecking the status, but rather assume it's good enough for one round only and will need to be rechecked next time. (6) afs_validate() it triggered on the vnode, probably called from d_revalidate() checking the parent directory. (7) afs_validate() notes that AFS_VNODE_CB_PROMISED isn't set, so doesn't update vnode->cb_s_break and assumes the vnode to be invalid. (8) afs_validate() needs to calls afs_fetch_status(). Go back to step (2) and repeat, every time the vnode is validated. This primarily affects volume root dir vnodes. Everything subsequent to those inherit an already incremented cb_s_break upon mounting. The issue is that we assume that the callback record and the cached permit information in a reply from the server can't be trusted after getting a server break - but this is wrong since the server makes sure things are done in the right order, holding up our ops if necessary[*]. [*] There is an extremely unlikely scenario where a reply from before the CB.InitCallBackState could get its delivery deferred till after - at which point we think we have a promise when we don't. This, however, requires unlucky mass packet loss to one call. AFS_SERVER_FL_NEW tries to paper over the cracks for the initial mount from a server we've never contacted before, but this should be unnecessary. It's also further insulated from the problem on an initial mount by querying the server first with FS.GetCapabilities, which triggers the CB.InitCallBackState. Fix this by (1) Remove AFS_SERVER_FL_NEW. (2) In afs_calc_vnode_cb_break(), don't include cb_s_break in the calculation. (3) In afs_cb_is_broken(), don't include cb_s_break in the check. Signed-off-by: David Howells --- fs/afs/callback.c | 3 +-- fs/afs/internal.h | 4 +--- fs/afs/server.c | 1 - 3 files changed, 2 insertions(+), 6 deletions(-) diff --git a/fs/afs/callback.c b/fs/afs/callback.c index 1c7955f5cdaf..128f2dbe256a 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -203,8 +203,7 @@ void afs_put_cb_interest(struct afs_net *net, struct afs_cb_interest *cbi) */ void afs_init_callback_state(struct afs_server *server) { - if (!test_and_clear_bit(AFS_SERVER_FL_NEW, &server->flags)) - server->cb_s_break++; + server->cb_s_break++; } /* diff --git a/fs/afs/internal.h b/fs/afs/internal.h index bb1f244b2b3a..3904ab0b9563 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -474,7 +474,6 @@ struct afs_server { time64_t put_time; /* Time at which last put */ time64_t update_at; /* Time at which to next update the record */ unsigned long flags; -#define AFS_SERVER_FL_NEW 0 /* New server, don't inc cb_s_break */ #define AFS_SERVER_FL_NOT_READY 1 /* The record is not ready for use */ #define AFS_SERVER_FL_NOT_FOUND 2 /* VL server says no such server */ #define AFS_SERVER_FL_VL_FAIL 3 /* Failed to access VL server */ @@ -827,7 +826,7 @@ static inline struct afs_cb_interest *afs_get_cb_interest(struct afs_cb_interest static inline unsigned int afs_calc_vnode_cb_break(struct afs_vnode *vnode) { - return vnode->cb_break + vnode->cb_s_break + vnode->cb_v_break; + return vnode->cb_break + vnode->cb_v_break; } static inline bool afs_cb_is_broken(unsigned int cb_break, @@ -835,7 +834,6 @@ static inline bool afs_cb_is_broken(unsigned int cb_break, const struct afs_cb_interest *cbi) { return !cbi || cb_break != (vnode->cb_break + - cbi->server->cb_s_break + vnode->volume->cb_v_break); } diff --git a/fs/afs/server.c b/fs/afs/server.c index 642afa2e9783..65b33b6da48b 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -226,7 +226,6 @@ static struct afs_server *afs_alloc_server(struct afs_net *net, RCU_INIT_POINTER(server->addresses, alist); server->addr_version = alist->version; server->uuid = *uuid; - server->flags = (1UL << AFS_SERVER_FL_NEW); server->update_at = ktime_get_real_seconds() + afs_server_update_delay; rwlock_init(&server->fs_lock); INIT_HLIST_HEAD(&server->cb_volumes); -- cgit v1.2.3-55-g7522 From 183ab39eb0ea9879bb68422a83e65f750f3192f0 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sat, 13 Apr 2019 10:04:49 +0200 Subject: ALSA: hda: Initialize power_state field properly The recent commit 98081ca62cba ("ALSA: hda - Record the current power state before suspend/resume calls") made the HD-audio driver to store the PM state in power_state field. This forgot, however, the initialization at power up. Although the codec drivers usually don't need to refer to this field in the normal operation, let's initialize it properly for consistency. Fixes: 98081ca62cba ("ALSA: hda - Record the current power state before suspend/resume calls") Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_codec.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index ec0b8595eb4d..701a69d856f5 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -969,6 +969,7 @@ int snd_hda_codec_device_new(struct hda_bus *bus, struct snd_card *card, /* power-up all before initialization */ hda_set_power_state(codec, AC_PWRST_D0); + codec->core.dev.power.power_state = PMSG_ON; snd_hda_codec_proc_new(codec); -- cgit v1.2.3-55-g7522 From becf2319f320cae43e20cf179cc51a355a0deb5f Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 25 Mar 2019 23:11:53 +0100 Subject: selftests: netfilter: check icmp pkttoobig errors are set as related When an icmp error such as pkttoobig is received, conntrack checks if the "inner" header (header of packet that did not fit link mtu) is matches an existing connection, and, if so, sets that packet as being related to the conntrack entry it found. It was recently reported that this "related" setting also works if the inner header is from another, different connection (i.e., artificial/forged icmp error). Add a test, followup patch will add additional "inner dst matches outer dst in reverse direction" check before setting related state. Link: https://www.synacktiv.com/posts/systems/icmp-reachable.html Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/netfilter/Makefile | 2 +- .../selftests/netfilter/conntrack_icmp_related.sh | 283 +++++++++++++++++++++ 2 files changed, 284 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/netfilter/conntrack_icmp_related.sh diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index c9ff2b47bd1c..a37cb1192c6a 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for netfilter selftests -TEST_PROGS := nft_trans_stress.sh nft_nat.sh +TEST_PROGS := nft_trans_stress.sh nft_nat.sh conntrack_icmp_related.sh include ../lib.mk diff --git a/tools/testing/selftests/netfilter/conntrack_icmp_related.sh b/tools/testing/selftests/netfilter/conntrack_icmp_related.sh new file mode 100755 index 000000000000..b48e1833bc89 --- /dev/null +++ b/tools/testing/selftests/netfilter/conntrack_icmp_related.sh @@ -0,0 +1,283 @@ +#!/bin/bash +# +# check that ICMP df-needed/pkttoobig icmp are set are set as related +# state +# +# Setup is: +# +# nsclient1 -> nsrouter1 -> nsrouter2 -> nsclient2 +# MTU 1500, except for nsrouter2 <-> nsclient2 link (1280). +# ping nsclient2 from nsclient1, checking that conntrack did set RELATED +# 'fragmentation needed' icmp packet. +# +# In addition, nsrouter1 will perform IP masquerading, i.e. also +# check the icmp errors are propagated to the correct host as per +# nat of "established" icmp-echo "connection". + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +ret=0 + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +cleanup() { + for i in 1 2;do ip netns del nsclient$i;done + for i in 1 2;do ip netns del nsrouter$i;done +} + +ipv4() { + echo -n 192.168.$1.2 +} + +ipv6 () { + echo -n dead:$1::2 +} + +check_counter() +{ + ns=$1 + name=$2 + expect=$3 + local lret=0 + + cnt=$(ip netns exec $ns nft list counter inet filter "$name" | grep -q "$expect") + if [ $? -ne 0 ]; then + echo "ERROR: counter $name in $ns has unexpected value (expected $expect)" 1>&2 + ip netns exec $ns nft list counter inet filter "$name" 1>&2 + lret=1 + fi + + return $lret +} + +check_unknown() +{ + expect="packets 0 bytes 0" + for n in nsclient1 nsclient2 nsrouter1 nsrouter2; do + check_counter $n "unknown" "$expect" + if [ $? -ne 0 ] ;then + return 1 + fi + done + + return 0 +} + +for n in nsclient1 nsclient2 nsrouter1 nsrouter2; do + ip netns add $n + ip -net $n link set lo up +done + +DEV=veth0 +ip link add $DEV netns nsclient1 type veth peer name eth1 netns nsrouter1 +DEV=veth0 +ip link add $DEV netns nsclient2 type veth peer name eth1 netns nsrouter2 + +DEV=veth0 +ip link add $DEV netns nsrouter1 type veth peer name eth2 netns nsrouter2 + +DEV=veth0 +for i in 1 2; do + ip -net nsclient$i link set $DEV up + ip -net nsclient$i addr add $(ipv4 $i)/24 dev $DEV + ip -net nsclient$i addr add $(ipv6 $i)/64 dev $DEV +done + +ip -net nsrouter1 link set eth1 up +ip -net nsrouter1 link set veth0 up + +ip -net nsrouter2 link set eth1 up +ip -net nsrouter2 link set eth2 up + +ip -net nsclient1 route add default via 192.168.1.1 +ip -net nsclient1 -6 route add default via dead:1::1 + +ip -net nsclient2 route add default via 192.168.2.1 +ip -net nsclient2 route add default via dead:2::1 + +i=3 +ip -net nsrouter1 addr add 192.168.1.1/24 dev eth1 +ip -net nsrouter1 addr add 192.168.3.1/24 dev veth0 +ip -net nsrouter1 addr add dead:1::1/64 dev eth1 +ip -net nsrouter1 addr add dead:3::1/64 dev veth0 +ip -net nsrouter1 route add default via 192.168.3.10 +ip -net nsrouter1 -6 route add default via dead:3::10 + +ip -net nsrouter2 addr add 192.168.2.1/24 dev eth1 +ip -net nsrouter2 addr add 192.168.3.10/24 dev eth2 +ip -net nsrouter2 addr add dead:2::1/64 dev eth1 +ip -net nsrouter2 addr add dead:3::10/64 dev eth2 +ip -net nsrouter2 route add default via 192.168.3.1 +ip -net nsrouter2 route add default via dead:3::1 + +sleep 2 +for i in 4 6; do + ip netns exec nsrouter1 sysctl -q net.ipv$i.conf.all.forwarding=1 + ip netns exec nsrouter2 sysctl -q net.ipv$i.conf.all.forwarding=1 +done + +for netns in nsrouter1 nsrouter2; do +ip netns exec $netns nft -f - </dev/null +if [ $? -ne 0 ]; then + echo "ERROR: netns ip routing/connectivity broken" 1>&2 + cleanup + exit 1 +fi +ip netns exec nsclient1 ping6 -q -c 1 -s 1000 dead:2::2 >/dev/null +if [ $? -ne 0 ]; then + echo "ERROR: netns ipv6 routing/connectivity broken" 1>&2 + cleanup + exit 1 +fi + +check_unknown +if [ $? -ne 0 ]; then + ret=1 +fi + +expect="packets 0 bytes 0" +for netns in nsrouter1 nsrouter2 nsclient1;do + check_counter "$netns" "related" "$expect" + if [ $? -ne 0 ]; then + ret=1 + fi +done + +expect="packets 2 bytes 2076" +check_counter nsclient2 "new" "$expect" +if [ $? -ne 0 ]; then + ret=1 +fi + +ip netns exec nsclient1 ping -q -c 1 -s 1300 -M do 192.168.2.2 > /dev/null +if [ $? -eq 0 ]; then + echo "ERROR: ping should have failed with PMTU too big error" 1>&2 + ret=1 +fi + +# nsrouter2 should have generated the icmp error, so +# related counter should be 0 (its in forward). +expect="packets 0 bytes 0" +check_counter "nsrouter2" "related" "$expect" +if [ $? -ne 0 ]; then + ret=1 +fi + +# but nsrouter1 should have seen it, same for nsclient1. +expect="packets 1 bytes 576" +for netns in nsrouter1 nsclient1;do + check_counter "$netns" "related" "$expect" + if [ $? -ne 0 ]; then + ret=1 + fi +done + +ip netns exec nsclient1 ping6 -c 1 -s 1300 dead:2::2 > /dev/null +if [ $? -eq 0 ]; then + echo "ERROR: ping6 should have failed with PMTU too big error" 1>&2 + ret=1 +fi + +expect="packets 2 bytes 1856" +for netns in nsrouter1 nsclient1;do + check_counter "$netns" "related" "$expect" + if [ $? -ne 0 ]; then + ret=1 + fi +done + +if [ $ret -eq 0 ];then + echo "PASS: icmp mtu error had RELATED state" +else + echo "ERROR: icmp error RELATED state test has failed" +fi + +cleanup +exit $ret -- cgit v1.2.3-55-g7522 From 1025ce75212bf06d93910297a03ed6a4d41d8213 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 25 Mar 2019 23:11:54 +0100 Subject: netfilter: conntrack: don't set related state for different outer address Luca Moro says: ------ The issue lies in the filtering of ICMP and ICMPv6 errors that include an inner IP datagram. For these packets, icmp_error_message() extract the ICMP error and inner layer to search of a known state. If a state is found the packet is tagged as related (IP_CT_RELATED). The problem is that there is no correlation check between the inner and outer layer of the packet. So one can encapsulate an error with an inner layer matching a known state, while its outer layer is directed to a filtered host. In this case the whole packet will be tagged as related. This has various implications from a rule bypass (if a rule to related trafic is allow), to a known state oracle. Unfortunately, we could not find a real statement in a RFC on how this case should be filtered. The closest we found is RFC5927 (Section 4.3) but it is not very clear. A possible fix would be to check that the inner IP source is the same than the outer destination. We believed this kind of attack was not documented yet, so we started to write a blog post about it. You can find it attached to this mail (sorry for the extract quality). It contains more technical details, PoC and discussion about the identified behavior. We discovered later that https://www.gont.com.ar/papers/filtering-of-icmp-error-messages.pdf described a similar attack concept in 2004 but without the stateful filtering in mind. ----- This implements above suggested fix: In icmp(v6) error handler, take outer destination address, then pass that into the common function that does the "related" association. After obtaining the nf_conn of the matching inner-headers connection, check that the destination address of the opposite direction tuple is the same as the outer address and only set RELATED if thats the case. Reported-by: Luca Moro Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 6 ++ net/netfilter/nf_conntrack_proto_icmp.c | 93 +++++++++++++++++++++------- net/netfilter/nf_conntrack_proto_icmpv6.c | 52 ++-------------- 3 files changed, 84 insertions(+), 67 deletions(-) diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 778087591983..a49edfdf47e8 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -75,6 +75,12 @@ bool nf_conntrack_invert_icmp_tuple(struct nf_conntrack_tuple *tuple, bool nf_conntrack_invert_icmpv6_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig); +int nf_conntrack_inet_error(struct nf_conn *tmpl, struct sk_buff *skb, + unsigned int dataoff, + const struct nf_hook_state *state, + u8 l4proto, + union nf_inet_addr *outer_daddr); + int nf_conntrack_icmpv4_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index 7df477996b16..9becac953587 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -103,49 +103,94 @@ int nf_conntrack_icmp_packet(struct nf_conn *ct, return NF_ACCEPT; } -/* Returns conntrack if it dealt with ICMP, and filled in skb fields */ -static int -icmp_error_message(struct nf_conn *tmpl, struct sk_buff *skb, - const struct nf_hook_state *state) +/* Check inner header is related to any of the existing connections */ +int nf_conntrack_inet_error(struct nf_conn *tmpl, struct sk_buff *skb, + unsigned int dataoff, + const struct nf_hook_state *state, + u8 l4proto, union nf_inet_addr *outer_daddr) { struct nf_conntrack_tuple innertuple, origtuple; const struct nf_conntrack_tuple_hash *h; const struct nf_conntrack_zone *zone; enum ip_conntrack_info ctinfo; struct nf_conntrack_zone tmp; + union nf_inet_addr *ct_daddr; + enum ip_conntrack_dir dir; + struct nf_conn *ct; WARN_ON(skb_nfct(skb)); zone = nf_ct_zone_tmpl(tmpl, skb, &tmp); /* Are they talking about one of our connections? */ - if (!nf_ct_get_tuplepr(skb, - skb_network_offset(skb) + ip_hdrlen(skb) - + sizeof(struct icmphdr), - PF_INET, state->net, &origtuple)) { - pr_debug("icmp_error_message: failed to get tuple\n"); + if (!nf_ct_get_tuplepr(skb, dataoff, + state->pf, state->net, &origtuple)) return -NF_ACCEPT; - } /* Ordinarily, we'd expect the inverted tupleproto, but it's been preserved inside the ICMP. */ - if (!nf_ct_invert_tuple(&innertuple, &origtuple)) { - pr_debug("icmp_error_message: no match\n"); + if (!nf_ct_invert_tuple(&innertuple, &origtuple)) return -NF_ACCEPT; - } - - ctinfo = IP_CT_RELATED; h = nf_conntrack_find_get(state->net, zone, &innertuple); - if (!h) { - pr_debug("icmp_error_message: no match\n"); + if (!h) + return -NF_ACCEPT; + + /* Consider: A -> T (=This machine) -> B + * Conntrack entry will look like this: + * Original: A->B + * Reply: B->T (SNAT case) OR A + * + * When this function runs, we got packet that looks like this: + * iphdr|icmphdr|inner_iphdr|l4header (tcp, udp, ..). + * + * Above nf_conntrack_find_get() makes lookup based on inner_hdr, + * so we should expect that destination of the found connection + * matches outer header destination address. + * + * In above example, we can consider these two cases: + * 1. Error coming in reply direction from B or M (middle box) to + * T (SNAT case) or A. + * Inner saddr will be B, dst will be T or A. + * The found conntrack will be reply tuple (B->T/A). + * 2. Error coming in original direction from A or M to B. + * Inner saddr will be A, inner daddr will be B. + * The found conntrack will be original tuple (A->B). + * + * In both cases, conntrack[dir].dst == inner.dst. + * + * A bogus packet could look like this: + * Inner: B->T + * Outer: B->X (other machine reachable by T). + * + * In this case, lookup yields connection A->B and will + * set packet from B->X as *RELATED*, even though no connection + * from X was ever seen. + */ + ct = nf_ct_tuplehash_to_ctrack(h); + dir = NF_CT_DIRECTION(h); + ct_daddr = &ct->tuplehash[dir].tuple.dst.u3; + if (!nf_inet_addr_cmp(outer_daddr, ct_daddr)) { + if (state->pf == AF_INET) { + nf_l4proto_log_invalid(skb, state->net, state->pf, + l4proto, + "outer daddr %pI4 != inner %pI4", + &outer_daddr->ip, &ct_daddr->ip); + } else if (state->pf == AF_INET6) { + nf_l4proto_log_invalid(skb, state->net, state->pf, + l4proto, + "outer daddr %pI6 != inner %pI6", + &outer_daddr->ip6, &ct_daddr->ip6); + } + nf_ct_put(ct); return -NF_ACCEPT; } - if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) + ctinfo = IP_CT_RELATED; + if (dir == IP_CT_DIR_REPLY) ctinfo += IP_CT_IS_REPLY; /* Update skb to refer to this connection */ - nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo); + nf_ct_set(skb, ct, ctinfo); return NF_ACCEPT; } @@ -162,11 +207,12 @@ int nf_conntrack_icmpv4_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state) { + union nf_inet_addr outer_daddr; const struct icmphdr *icmph; struct icmphdr _ih; /* Not enough header? */ - icmph = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_ih), &_ih); + icmph = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih); if (icmph == NULL) { icmp_error_log(skb, state, "short packet"); return -NF_ACCEPT; @@ -199,7 +245,12 @@ int nf_conntrack_icmpv4_error(struct nf_conn *tmpl, icmph->type != ICMP_REDIRECT) return NF_ACCEPT; - return icmp_error_message(tmpl, skb, state); + memset(&outer_daddr, 0, sizeof(outer_daddr)); + outer_daddr.ip = ip_hdr(skb)->daddr; + + dataoff += sizeof(*icmph); + return nf_conntrack_inet_error(tmpl, skb, dataoff, state, + IPPROTO_ICMP, &outer_daddr); } #if IS_ENABLED(CONFIG_NF_CT_NETLINK) diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index bec4a3211658..c63ee3612855 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -123,51 +123,6 @@ int nf_conntrack_icmpv6_packet(struct nf_conn *ct, return NF_ACCEPT; } -static int -icmpv6_error_message(struct net *net, struct nf_conn *tmpl, - struct sk_buff *skb, - unsigned int icmp6off) -{ - struct nf_conntrack_tuple intuple, origtuple; - const struct nf_conntrack_tuple_hash *h; - enum ip_conntrack_info ctinfo; - struct nf_conntrack_zone tmp; - - WARN_ON(skb_nfct(skb)); - - /* Are they talking about one of our connections? */ - if (!nf_ct_get_tuplepr(skb, - skb_network_offset(skb) - + sizeof(struct ipv6hdr) - + sizeof(struct icmp6hdr), - PF_INET6, net, &origtuple)) { - pr_debug("icmpv6_error: Can't get tuple\n"); - return -NF_ACCEPT; - } - - /* Ordinarily, we'd expect the inverted tupleproto, but it's - been preserved inside the ICMP. */ - if (!nf_ct_invert_tuple(&intuple, &origtuple)) { - pr_debug("icmpv6_error: Can't invert tuple\n"); - return -NF_ACCEPT; - } - - ctinfo = IP_CT_RELATED; - - h = nf_conntrack_find_get(net, nf_ct_zone_tmpl(tmpl, skb, &tmp), - &intuple); - if (!h) { - pr_debug("icmpv6_error: no match\n"); - return -NF_ACCEPT; - } else { - if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) - ctinfo += IP_CT_IS_REPLY; - } - - /* Update skb to refer to this connection */ - nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo); - return NF_ACCEPT; -} static void icmpv6_error_log(const struct sk_buff *skb, const struct nf_hook_state *state, @@ -182,6 +137,7 @@ int nf_conntrack_icmpv6_error(struct nf_conn *tmpl, unsigned int dataoff, const struct nf_hook_state *state) { + union nf_inet_addr outer_daddr; const struct icmp6hdr *icmp6h; struct icmp6hdr _ih; int type; @@ -210,7 +166,11 @@ int nf_conntrack_icmpv6_error(struct nf_conn *tmpl, if (icmp6h->icmp6_type >= 128) return NF_ACCEPT; - return icmpv6_error_message(state->net, tmpl, skb, dataoff); + memcpy(&outer_daddr.ip6, &ipv6_hdr(skb)->daddr, + sizeof(outer_daddr.ip6)); + dataoff += sizeof(*icmp6h); + return nf_conntrack_inet_error(tmpl, skb, dataoff, state, + IPPROTO_ICMPV6, &outer_daddr); } #if IS_ENABLED(CONFIG_NF_CT_NETLINK) -- cgit v1.2.3-55-g7522 From 8176c8332751bf27597488d6e45c9b8f530593bf Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 28 Mar 2019 10:47:20 +0100 Subject: netfilter: conntrack: initialize ct->timeout KMSAN started reporting an error when accessing ct->timeout for the first time without initialization: BUG: KMSAN: uninit-value in __nf_ct_refresh_acct+0x1ae/0x470 net/netfilter/nf_conntrack_core.c:1765 ... dump_stack+0x173/0x1d0 lib/dump_stack.c:113 kmsan_report+0x131/0x2a0 mm/kmsan/kmsan.c:624 __msan_warning+0x7a/0xf0 mm/kmsan/kmsan_instr.c:310 __nf_ct_refresh_acct+0x1ae/0x470 net/netfilter/nf_conntrack_core.c:1765 nf_ct_refresh_acct ./include/net/netfilter/nf_conntrack.h:201 nf_conntrack_udp_packet+0xb44/0x1040 net/netfilter/nf_conntrack_proto_udp.c:122 nf_conntrack_handle_packet net/netfilter/nf_conntrack_core.c:1605 nf_conntrack_in+0x1250/0x26c9 net/netfilter/nf_conntrack_core.c:1696 ... Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:205 kmsan_internal_poison_shadow+0x92/0x150 mm/kmsan/kmsan.c:159 kmsan_kmalloc+0xa9/0x130 mm/kmsan/kmsan_hooks.c:173 kmem_cache_alloc+0x554/0xb10 mm/slub.c:2789 __nf_conntrack_alloc+0x16f/0x690 net/netfilter/nf_conntrack_core.c:1342 init_conntrack+0x6cb/0x2490 net/netfilter/nf_conntrack_core.c:1421 Signed-off-by: Alexander Potapenko Fixes: cc16921351d8ba1 ("netfilter: conntrack: avoid same-timeout update") Cc: Florian Westphal Acked-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 82bfbeef46af..a137d4e7f218 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1350,6 +1350,7 @@ __nf_conntrack_alloc(struct net *net, /* save hash for reusing when confirming */ *(unsigned long *)(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev) = hash; ct->status = 0; + ct->timeout = 0; write_pnet(&ct->ct_net, net); memset(&ct->__nfct_init_offset[0], 0, offsetof(struct nf_conn, proto) - -- cgit v1.2.3-55-g7522 From 0261ea1bd1eb0da5c0792a9119b8655cf33c80a3 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sun, 31 Mar 2019 13:24:52 +0300 Subject: ipvs: do not schedule icmp errors from tunnels We can receive ICMP errors from client or from tunneling real server. While the former can be scheduled to real server, the latter should not be scheduled, they are decapsulated only when existing connection is found. Fixes: 6044eeffafbe ("ipvs: attempt to schedule icmp packets") Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipvs/ip_vs_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 43bbaa32b1d6..14457551bcb4 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1678,7 +1678,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, if (!cp) { int v; - if (!sysctl_schedule_icmp(ipvs)) + if (ipip || !sysctl_schedule_icmp(ipvs)) return NF_ACCEPT; if (!ip_vs_try_to_schedule(ipvs, AF_INET, skb, pd, &v, &cp, &ciph)) -- cgit v1.2.3-55-g7522 From 06058632464845abb1af91521122fd04dd3daaec Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 13 Apr 2019 09:26:03 -0600 Subject: io_uring: park SQPOLL thread if it's percpu kthread expects this, or we can throw a warning on exit: WARNING: CPU: 0 PID: 7822 at kernel/kthread.c:399 __kthread_bind_mask+0x3b/0xc0 kernel/kthread.c:399 Kernel panic - not syncing: panic_on_warn set ... CPU: 0 PID: 7822 Comm: syz-executor030 Not tainted 5.1.0-rc4-next-20190412 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 panic+0x2cb/0x72b kernel/panic.c:214 __warn.cold+0x20/0x46 kernel/panic.c:576 report_bug+0x263/0x2b0 lib/bug.c:186 fixup_bug arch/x86/kernel/traps.c:179 [inline] fixup_bug arch/x86/kernel/traps.c:174 [inline] do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:272 do_invalid_op+0x37/0x50 arch/x86/kernel/traps.c:291 invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:973 RIP: 0010:__kthread_bind_mask+0x3b/0xc0 kernel/kthread.c:399 Code: 48 89 fb e8 f7 ab 24 00 4c 89 e6 48 89 df e8 ac e1 02 00 31 ff 49 89 c4 48 89 c6 e8 7f ad 24 00 4d 85 e4 75 15 e8 d5 ab 24 00 <0f> 0b e8 ce ab 24 00 5b 41 5c 41 5d 41 5e 5d c3 e8 c0 ab 24 00 4c RSP: 0018:ffff8880a89bfbb8 EFLAGS: 00010293 RAX: ffff88808ca7a280 RBX: ffff8880a98e4380 RCX: ffffffff814bdd11 RDX: 0000000000000000 RSI: ffffffff814bdd1b RDI: 0000000000000007 RBP: ffff8880a89bfbd8 R08: ffff88808ca7a280 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 R13: ffffffff87691148 R14: ffff8880a98e43a0 R15: ffffffff81c91e10 __kthread_bind kernel/kthread.c:412 [inline] kthread_unpark+0x123/0x160 kernel/kthread.c:480 kthread_stop+0xfa/0x6c0 kernel/kthread.c:556 io_sq_thread_stop fs/io_uring.c:2057 [inline] io_sq_thread_stop fs/io_uring.c:2052 [inline] io_finish_async+0xab/0x180 fs/io_uring.c:2064 io_ring_ctx_free fs/io_uring.c:2534 [inline] io_ring_ctx_wait_and_kill+0x133/0x510 fs/io_uring.c:2591 io_uring_release+0x42/0x50 fs/io_uring.c:2599 __fput+0x2e5/0x8d0 fs/file_table.c:278 ____fput+0x16/0x20 fs/file_table.c:309 task_work_run+0x14a/0x1c0 kernel/task_work.c:113 exit_task_work include/linux/task_work.h:22 [inline] do_exit+0x90a/0x2fa0 kernel/exit.c:876 do_group_exit+0x135/0x370 kernel/exit.c:980 __do_sys_exit_group kernel/exit.c:991 [inline] __se_sys_exit_group kernel/exit.c:989 [inline] __x64_sys_exit_group+0x44/0x50 kernel/exit.c:989 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe Reported-by: syzbot+6d4a92619eb0ad08602b@syzkaller.appspotmail.com Fixes: 6c271ce2f1d5 ("io_uring: add submission polling") Signed-off-by: Jens Axboe --- fs/io_uring.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/io_uring.c b/fs/io_uring.c index 89aa8412b5f5..e5008c1b82be 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1920,6 +1920,10 @@ static int io_sq_thread(void *data) unuse_mm(cur_mm); mmput(cur_mm); } + + if (kthread_should_park()) + kthread_parkme(); + return 0; } @@ -2054,6 +2058,7 @@ static void io_sq_thread_stop(struct io_ring_ctx *ctx) if (ctx->sqo_thread) { ctx->sqo_stop = 1; mb(); + kthread_park(ctx->sqo_thread); kthread_stop(ctx->sqo_thread); ctx->sqo_thread = NULL; } -- cgit v1.2.3-55-g7522 From 917257daa0fea7a007102691c0e27d9216a96768 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 13 Apr 2019 09:28:55 -0600 Subject: io_uring: only test SQPOLL cpu after we've verified it We currently call cpu_possible() even if we don't use the CPU. Move the test under the SQ_AFF branch, which is the only place where we'll use the value. Do the cpu_possible() test AFTER we've limited it to a max of NR_CPUS. This avoids triggering the following warning: WARNING: CPU: 1 PID: 7600 at include/linux/cpumask.h:121 cpu_max_bits_warn if CONFIG_DEBUG_PER_CPU_MAPS is enabled. While in there, also move the SQ thread idle period assignment inside SETUP_SQPOLL, as we don't use it otherwise either. Reported-by: syzbot+cd714a07c6de2bc34293@syzkaller.appspotmail.com Fixes: 6c271ce2f1d5 ("io_uring: add submission polling") Signed-off-by: Jens Axboe --- fs/io_uring.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index e5008c1b82be..24355e0c47f0 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2241,10 +2241,6 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx, mmgrab(current->mm); ctx->sqo_mm = current->mm; - ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle); - if (!ctx->sq_thread_idle) - ctx->sq_thread_idle = HZ; - ret = -EINVAL; if (!cpu_possible(p->sq_thread_cpu)) goto err; @@ -2254,10 +2250,18 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx, if (!capable(CAP_SYS_ADMIN)) goto err; + ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle); + if (!ctx->sq_thread_idle) + ctx->sq_thread_idle = HZ; + if (p->flags & IORING_SETUP_SQ_AFF) { int cpu; cpu = array_index_nospec(p->sq_thread_cpu, NR_CPUS); + ret = -EINVAL; + if (!cpu_possible(p->sq_thread_cpu)) + goto err; + ctx->sqo_thread = kthread_create_on_cpu(io_sq_thread, ctx, cpu, "io_uring-sq"); -- cgit v1.2.3-55-g7522 From 77f1e0a52d26242b6c2dba019f6ebebfb9ff701e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 18 Jan 2019 10:34:16 -0700 Subject: bfq: update internal depth state when queue depth changes A previous commit moved the shallow depth and BFQ depth map calculations to be done at init time, moving it outside of the hotter IO path. This potentially causes hangs if the users changes the depth of the scheduler map, by writing to the 'nr_requests' sysfs file for that device. Add a blk-mq-sched hook that allows blk-mq to inform the scheduler if the depth changes, so that the scheduler can update its internal state. Tested-by: Kai Krakow Reported-by: Paolo Valente Fixes: f0635b8a416e ("bfq: calculate shallow depths at init time") Signed-off-by: Jens Axboe --- block/bfq-iosched.c | 8 +++++++- block/blk-mq.c | 2 ++ include/linux/elevator.h | 1 + 3 files changed, 10 insertions(+), 1 deletion(-) diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index dfb8cb0af13a..5ba1e0d841b4 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -5396,7 +5396,7 @@ static unsigned int bfq_update_depths(struct bfq_data *bfqd, return min_shallow; } -static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index) +static void bfq_depth_updated(struct blk_mq_hw_ctx *hctx) { struct bfq_data *bfqd = hctx->queue->elevator->elevator_data; struct blk_mq_tags *tags = hctx->sched_tags; @@ -5404,6 +5404,11 @@ static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index) min_shallow = bfq_update_depths(bfqd, &tags->bitmap_tags); sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, min_shallow); +} + +static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index) +{ + bfq_depth_updated(hctx); return 0; } @@ -5826,6 +5831,7 @@ static struct elevator_type iosched_bfq_mq = { .requests_merged = bfq_requests_merged, .request_merged = bfq_request_merged, .has_work = bfq_has_work, + .depth_updated = bfq_depth_updated, .init_hctx = bfq_init_hctx, .init_sched = bfq_init_queue, .exit_sched = bfq_exit_queue, diff --git a/block/blk-mq.c b/block/blk-mq.c index 9516304a38ee..fc60ed7e940e 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -3135,6 +3135,8 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr) } if (ret) break; + if (q->elevator && q->elevator->type->ops.depth_updated) + q->elevator->type->ops.depth_updated(hctx); } if (!ret) diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 2e9e2763bf47..6e8bc53740f0 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -31,6 +31,7 @@ struct elevator_mq_ops { void (*exit_sched)(struct elevator_queue *); int (*init_hctx)(struct blk_mq_hw_ctx *, unsigned int); void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int); + void (*depth_updated)(struct blk_mq_hw_ctx *); bool (*allow_merge)(struct request_queue *, struct request *, struct bio *); bool (*bio_merge)(struct blk_mq_hw_ctx *, struct bio *); -- cgit v1.2.3-55-g7522 From 3d6770fbd9353988839611bab107e4e891506aad Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 13 Apr 2019 11:50:54 -0600 Subject: io_uring: drop io_file_put() 'file' argument Since the fget/fput handling was reworked in commit 09bb839434bd, we never call io_file_put() with state == NULL (and hence file != NULL) anymore. Remove that case. Reported-by: Al Viro Signed-off-by: Jens Axboe --- fs/io_uring.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 24355e0c47f0..f4ddb9d23241 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -682,11 +682,9 @@ static void io_iopoll_req_issued(struct io_kiocb *req) list_add_tail(&req->list, &ctx->poll_list); } -static void io_file_put(struct io_submit_state *state, struct file *file) +static void io_file_put(struct io_submit_state *state) { - if (!state) { - fput(file); - } else if (state->file) { + if (state->file) { int diff = state->has_refs - state->used_refs; if (diff) @@ -711,7 +709,7 @@ static struct file *io_file_get(struct io_submit_state *state, int fd) state->ios_left--; return state->file; } - io_file_put(state, NULL); + io_file_put(state); } state->file = fget_many(fd, state->ios_left); if (!state->file) @@ -1671,7 +1669,7 @@ out: static void io_submit_state_end(struct io_submit_state *state) { blk_finish_plug(&state->plug); - io_file_put(state, NULL); + io_file_put(state); if (state->free_reqs) kmem_cache_free_bulk(req_cachep, state->free_reqs, &state->reqs[state->cur_req]); -- cgit v1.2.3-55-g7522 From 40fba00ffa431c8597ca785ea1cfa4d9f6503390 Mon Sep 17 00:00:00 2001 From: Xiaochen Shen Date: Wed, 10 Apr 2019 03:53:49 +0800 Subject: x86/resctrl: Do not repeat rdtgroup mode initialization When cache allocation is supported and the user creates a new resctrl resource group, the allocations of the new resource group are initialized to all regions that it can possibly use. At this time these regions are all that are shareable by other resource groups as well as regions that are not currently used. The new resource group's mode is also initialized to reflect this initialization and set to "shareable". The new resource group's mode is currently repeatedly initialized within the loop that configures the hardware with the resource group's default allocations. Move the initialization of the resource group's mode outside the hardware configuration loop. The resource group's mode is now initialized only once as the final step to reflect that its configured allocations are "shareable". Fixes: 95f0b77efa57 ("x86/intel_rdt: Initialize new resource group with sane defaults") Signed-off-by: Xiaochen Shen Signed-off-by: Borislav Petkov Reviewed-by: Fenghua Yu Acked-by: Reinette Chatre Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: pei.p.jia@intel.com Cc: Thomas Gleixner Cc: Tony Luck Cc: x86-ml Link: https://lkml.kernel.org/r/1554839629-5448-1-git-send-email-xiaochen.shen@intel.com --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 54b9eef3eea9..85212a32b54d 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -2610,9 +2610,10 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) rdt_last_cmd_puts("Failed to initialize allocations\n"); return ret; } - rdtgrp->mode = RDT_MODE_SHAREABLE; } + rdtgrp->mode = RDT_MODE_SHAREABLE; + return 0; } -- cgit v1.2.3-55-g7522 From 2f5fb19341883bb6e37da351bc3700489d8506a7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 14 Apr 2019 19:51:06 +0200 Subject: x86/speculation: Prevent deadlock on ssb_state::lock Mikhail reported a lockdep splat related to the AMD specific ssb_state lock: CPU0 CPU1 lock(&st->lock); local_irq_disable(); lock(&(&sighand->siglock)->rlock); lock(&st->lock); lock(&(&sighand->siglock)->rlock); *** DEADLOCK *** The connection between sighand->siglock and st->lock comes through seccomp, which takes st->lock while holding sighand->siglock. Make sure interrupts are disabled when __speculation_ctrl_update() is invoked via prctl() -> speculation_ctrl_update(). Add a lockdep assert to catch future offenders. Fixes: 1f50ddb4f418 ("x86/speculation: Handle HT correctly on AMD") Reported-by: Mikhail Gavrilov Signed-off-by: Thomas Gleixner Tested-by: Mikhail Gavrilov Cc: Thomas Lendacky Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1904141948200.4917@nanos.tec.linutronix.de --- arch/x86/kernel/process.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 58ac7be52c7a..957eae13b370 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -426,6 +426,8 @@ static __always_inline void __speculation_ctrl_update(unsigned long tifp, u64 msr = x86_spec_ctrl_base; bool updmsr = false; + lockdep_assert_irqs_disabled(); + /* * If TIF_SSBD is different, select the proper mitigation * method. Note that if SSBD mitigation is disabled or permanentely @@ -477,10 +479,12 @@ static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk) void speculation_ctrl_update(unsigned long tif) { + unsigned long flags; + /* Forced update. Make sure all relevant TIF flags are different */ - preempt_disable(); + local_irq_save(flags); __speculation_ctrl_update(~tif, tif); - preempt_enable(); + local_irq_restore(flags); } /* Called from seccomp/prctl update */ -- cgit v1.2.3-55-g7522 From c238bfe0be9ef7420f7669a69e27c8c8f4d8a568 Mon Sep 17 00:00:00 2001 From: David Francis Date: Fri, 29 Mar 2019 13:23:15 -0400 Subject: drm/amd/display: If one stream full updates, full update all planes [Why] On some compositors, with two monitors attached, VT terminal switch can cause a graphical issue by the following means: There are two streams, one for each monitor. Each stream has one plane current state: M1:S1->P1 M2:S2->P2 The user calls for a terminal switch and a commit is made to change both planes to linear swizzle mode. In atomic check, a new dc_state is constructed with new planes on each stream new state: M1:S1->P3 M2:S2->P4 In commit tail, each stream is committed, one at a time. The first stream (S1) updates properly, triggerring a full update and replacing the state current state: M1:S1->P3 M2:S2->P4 The update for S2 comes in, but dc detects that there is no difference between the stream and plane in the new and current states, and so triggers a fast update. The fast update does not program swizzle, so the second monitor is corrupted [How] Add a flag to dc_plane_state that forces full updates When a stream undergoes a full update, set this flag on all changed planes, then clear it on the current stream Subsequent streams will get full updates as a result Signed-off-by: David Francis Signed-off-by: Nicholas Kazlauskas Reviewed-by: Roman Li Acked-by: Bhawanpreet Lakha Acked-by: Nicholas Kazlauskas Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc.c | 19 +++++++++++++++++++ drivers/gpu/drm/amd/display/dc/dc.h | 3 +++ 2 files changed, 22 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index c68fbd55db3c..a6cda201c964 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1377,6 +1377,11 @@ static enum surface_update_type det_surface_update(const struct dc *dc, return UPDATE_TYPE_FULL; } + if (u->surface->force_full_update) { + update_flags->bits.full_update = 1; + return UPDATE_TYPE_FULL; + } + type = get_plane_info_update_type(u); elevate_update_type(&overall_type, type); @@ -1802,6 +1807,14 @@ void dc_commit_updates_for_stream(struct dc *dc, } dc_resource_state_copy_construct(state, context); + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i]; + struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i]; + + if (new_pipe->plane_state && new_pipe->plane_state != old_pipe->plane_state) + new_pipe->plane_state->force_full_update = true; + } } @@ -1838,6 +1851,12 @@ void dc_commit_updates_for_stream(struct dc *dc, dc->current_state = context; dc_release_state(old); + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; + + if (pipe_ctx->plane_state && pipe_ctx->stream == stream) + pipe_ctx->plane_state->force_full_update = false; + } } /*let's use current_state to update watermark etc*/ if (update_type >= UPDATE_TYPE_FULL) diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 1a7fd6aa77eb..0515095574e7 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -503,6 +503,9 @@ struct dc_plane_state { struct dc_plane_status status; struct dc_context *ctx; + /* HACK: Workaround for forcing full reprogramming under some conditions */ + bool force_full_update; + /* private to dc_surface.c */ enum dc_irq_source irq_source; struct kref refcount; -- cgit v1.2.3-55-g7522 From 3c79107631db1f7fd32cf3f7368e4672004a3010 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 1 Apr 2019 13:08:54 +0200 Subject: netfilter: ctnetlink: don't use conntrack/expect object addresses as id else, we leak the addresses to userspace via ctnetlink events and dumps. Compute an ID on demand based on the immutable parts of nf_conn struct. Another advantage compared to using an address is that there is no immediate re-use of the same ID in case the conntrack entry is freed and reallocated again immediately. Fixes: 3583240249ef ("[NETFILTER]: nf_conntrack_expect: kill unique ID") Fixes: 7f85f914721f ("[NETFILTER]: nf_conntrack: kill unique ID") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 2 ++ net/netfilter/nf_conntrack_core.c | 35 +++++++++++++++++++++++++++++++++++ net/netfilter/nf_conntrack_netlink.c | 34 +++++++++++++++++++++++++++++----- 3 files changed, 66 insertions(+), 5 deletions(-) diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 5ee7b30b4917..d2bc733a2ef1 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -316,6 +316,8 @@ struct nf_conn *nf_ct_tmpl_alloc(struct net *net, gfp_t flags); void nf_ct_tmpl_free(struct nf_conn *tmpl); +u32 nf_ct_get_id(const struct nf_conn *ct); + static inline void nf_ct_set(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info info) { diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index a137d4e7f218..3c48d44d6fff 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -449,6 +450,40 @@ nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, } EXPORT_SYMBOL_GPL(nf_ct_invert_tuple); +/* Generate a almost-unique pseudo-id for a given conntrack. + * + * intentionally doesn't re-use any of the seeds used for hash + * table location, we assume id gets exposed to userspace. + * + * Following nf_conn items do not change throughout lifetime + * of the nf_conn after it has been committed to main hash table: + * + * 1. nf_conn address + * 2. nf_conn->ext address + * 3. nf_conn->master address (normally NULL) + * 4. tuple + * 5. the associated net namespace + */ +u32 nf_ct_get_id(const struct nf_conn *ct) +{ + static __read_mostly siphash_key_t ct_id_seed; + unsigned long a, b, c, d; + + net_get_random_once(&ct_id_seed, sizeof(ct_id_seed)); + + a = (unsigned long)ct; + b = (unsigned long)ct->master ^ net_hash_mix(nf_ct_net(ct)); + c = (unsigned long)ct->ext; + d = (unsigned long)siphash(&ct->tuplehash, sizeof(ct->tuplehash), + &ct_id_seed); +#ifdef CONFIG_64BIT + return siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &ct_id_seed); +#else + return siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &ct_id_seed); +#endif +} +EXPORT_SYMBOL_GPL(nf_ct_get_id); + static void clean_from_lists(struct nf_conn *ct) { diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 66c596d287a5..d7f61b0547c6 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include @@ -485,7 +486,9 @@ nla_put_failure: static int ctnetlink_dump_id(struct sk_buff *skb, const struct nf_conn *ct) { - if (nla_put_be32(skb, CTA_ID, htonl((unsigned long)ct))) + __be32 id = (__force __be32)nf_ct_get_id(ct); + + if (nla_put_be32(skb, CTA_ID, id)) goto nla_put_failure; return 0; @@ -1286,8 +1289,9 @@ static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl, } if (cda[CTA_ID]) { - u_int32_t id = ntohl(nla_get_be32(cda[CTA_ID])); - if (id != (u32)(unsigned long)ct) { + __be32 id = nla_get_be32(cda[CTA_ID]); + + if (id != (__force __be32)nf_ct_get_id(ct)) { nf_ct_put(ct); return -ENOENT; } @@ -2692,6 +2696,25 @@ nla_put_failure: static const union nf_inet_addr any_addr; +static __be32 nf_expect_get_id(const struct nf_conntrack_expect *exp) +{ + static __read_mostly siphash_key_t exp_id_seed; + unsigned long a, b, c, d; + + net_get_random_once(&exp_id_seed, sizeof(exp_id_seed)); + + a = (unsigned long)exp; + b = (unsigned long)exp->helper; + c = (unsigned long)exp->master; + d = (unsigned long)siphash(&exp->tuple, sizeof(exp->tuple), &exp_id_seed); + +#ifdef CONFIG_64BIT + return (__force __be32)siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &exp_id_seed); +#else + return (__force __be32)siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &exp_id_seed); +#endif +} + static int ctnetlink_exp_dump_expect(struct sk_buff *skb, const struct nf_conntrack_expect *exp) @@ -2739,7 +2762,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, } #endif if (nla_put_be32(skb, CTA_EXPECT_TIMEOUT, htonl(timeout)) || - nla_put_be32(skb, CTA_EXPECT_ID, htonl((unsigned long)exp)) || + nla_put_be32(skb, CTA_EXPECT_ID, nf_expect_get_id(exp)) || nla_put_be32(skb, CTA_EXPECT_FLAGS, htonl(exp->flags)) || nla_put_be32(skb, CTA_EXPECT_CLASS, htonl(exp->class))) goto nla_put_failure; @@ -3044,7 +3067,8 @@ static int ctnetlink_get_expect(struct net *net, struct sock *ctnl, if (cda[CTA_EXPECT_ID]) { __be32 id = nla_get_be32(cda[CTA_EXPECT_ID]); - if (ntohl(id) != (u32)(unsigned long)exp) { + + if (id != nf_expect_get_id(exp)) { nf_ct_expect_put(exp); return -ENOENT; } -- cgit v1.2.3-55-g7522 From 33d1c018179d0a30c39cc5f1682b77867282694b Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Sat, 6 Apr 2019 08:26:52 +0300 Subject: netfilter: nf_tables: prevent shift wrap in nft_chain_parse_hook() I believe that "hook->num" can be up to UINT_MAX. Shifting more than 31 bits would is undefined in C but in practice it would lead to shift wrapping. That would lead to an array overflow in nf_tables_addchain(): ops->hook = hook.type->hooks[ops->hooknum]; Fixes: fe19c04ca137 ("netfilter: nf_tables: remove nhooks field from struct nft_af_info") Signed-off-by: Dan Carpenter Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index ef7772e976cc..1606eaa5ae0d 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1545,7 +1545,7 @@ static int nft_chain_parse_hook(struct net *net, if (IS_ERR(type)) return PTR_ERR(type); } - if (!(type->hook_mask & (1 << hook->num))) + if (hook->num > NF_MAX_HOOKS || !(type->hook_mask & (1 << hook->num))) return -EOPNOTSUPP; if (type->type == NFT_CHAIN_T_NAT && -- cgit v1.2.3-55-g7522 From 5bdac418f33f60b07a34e01e722889140ee8fac9 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 9 Apr 2019 14:45:20 +0200 Subject: netfilter: nat: fix icmp id randomization Sven Auhagen reported that a 2nd ping request will fail if 'fully-random' mode is used. Reason is that if no proto information is given, min/max are both 0, so we set the icmp id to 0 instead of chosing a random value between 0 and 65535. Update test case as well to catch this, without fix this yields: [..] ERROR: cannot ping ns1 from ns2 with ip masquerade fully-random (attempt 2) ERROR: cannot ping ns1 from ns2 with ipv6 masquerade fully-random (attempt 2) ... becaus 2nd ping clashes with existing 'id 0' icmp conntrack and gets dropped. Fixes: 203f2e78200c27e ("netfilter: nat: remove l4proto->unique_tuple") Reported-by: Sven Auhagen Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_nat_core.c | 11 ++++++--- tools/testing/selftests/netfilter/nft_nat.sh | 36 +++++++++++++++++++++------- 2 files changed, 35 insertions(+), 12 deletions(-) diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index af7dc6537758..000952719adf 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -415,9 +415,14 @@ static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple, case IPPROTO_ICMPV6: /* id is same for either direction... */ keyptr = &tuple->src.u.icmp.id; - min = range->min_proto.icmp.id; - range_size = ntohs(range->max_proto.icmp.id) - - ntohs(range->min_proto.icmp.id) + 1; + if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) { + min = 0; + range_size = 65536; + } else { + min = ntohs(range->min_proto.icmp.id); + range_size = ntohs(range->max_proto.icmp.id) - + ntohs(range->min_proto.icmp.id) + 1; + } goto find_free_id; #if IS_ENABLED(CONFIG_NF_CT_PROTO_GRE) case IPPROTO_GRE: diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index 8ec76681605c..3194007cf8d1 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -321,6 +321,7 @@ EOF test_masquerade6() { + local natflags=$1 local lret=0 ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null @@ -354,13 +355,13 @@ ip netns exec ns0 nft -f - < /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerading" + echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerade $natflags" lret=1 fi @@ -397,19 +398,26 @@ EOF fi done + ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerade $natflags (attempt 2)" + lret=1 + fi + ip netns exec ns0 nft flush chain ip6 nat postrouting if [ $? -ne 0 ]; then echo "ERROR: Could not flush ip6 nat postrouting" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: IPv6 masquerade for ns2" + test $lret -eq 0 && echo "PASS: IPv6 masquerade $natflags for ns2" return $lret } test_masquerade() { + local natflags=$1 local lret=0 ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null @@ -417,7 +425,7 @@ test_masquerade() ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: canot ping ns1 from ns2" + echo "ERROR: cannot ping ns1 from ns2 $natflags" lret=1 fi @@ -443,13 +451,13 @@ ip netns exec ns0 nft -f - < /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active ip masquerading" + echo "ERROR: cannot ping ns1 from ns2 with active ip masquere $natflags" lret=1 fi @@ -485,13 +493,19 @@ EOF fi done + ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ip masquerade $natflags (attempt 2)" + lret=1 + fi + ip netns exec ns0 nft flush chain ip nat postrouting if [ $? -ne 0 ]; then echo "ERROR: Could not flush nat postrouting" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: IP masquerade for ns2" + test $lret -eq 0 && echo "PASS: IP masquerade $natflags for ns2" return $lret } @@ -750,8 +764,12 @@ test_local_dnat test_local_dnat6 reset_counters -test_masquerade -test_masquerade6 +test_masquerade "" +test_masquerade6 "" + +reset_counters +test_masquerade "fully-random" +test_masquerade6 "fully-random" reset_counters test_redirect -- cgit v1.2.3-55-g7522 From 6b1f16ba730d4c0cda1247568c3a1bf4fa3a2f2f Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Fri, 12 Apr 2019 11:04:50 +0200 Subject: s390/pkey: add one more argument space for debug feature entry The debug feature entries have been used with up to 5 arguents (including the pointer to the format string) but there was only space reserved for 4 arguemnts. So now the registration does reserve space for 5 times a long value. This fixes a sometime appearing weired value as the last value of an debug feature entry like this: ... pkey_sec2protkey zcrypt_send_cprb (cardnr=10 domain=12) failed with errno -2143346254 Signed-off-by: Harald Freudenberger Reported-by: Christian Rund Signed-off-by: Martin Schwidefsky --- drivers/s390/crypto/pkey_api.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index 3e85d665c572..45eb0c14b880 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -51,7 +51,8 @@ static debug_info_t *debug_info; static void __init pkey_debug_init(void) { - debug_info = debug_register("pkey", 1, 1, 4 * sizeof(long)); + /* 5 arguments per dbf entry (including the format string ptr) */ + debug_info = debug_register("pkey", 1, 1, 5 * sizeof(long)); debug_register_view(debug_info, &debug_sprintf_view); debug_set_level(debug_info, 3); } -- cgit v1.2.3-55-g7522 From 2aae471d66c108b78493be1147e707bca6331e50 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 19 Mar 2019 15:51:56 +0100 Subject: drivers: power: supply: goldfish_battery: Fix bogus SPDX identifier spdxcheck.py complains: drivers/power/supply/goldfish_battery.c: 1:28 Invalid License ID: GPL which is correct because GPL is not a valid identifier. Of course this could have been caught by checkpatch.pl _before_ submitting or merging the patch. WARNING: 'SPDX-License-Identifier: GPL' is not supported in LICENSES/... #19: FILE: drivers/power/supply/goldfish_battery.c:1: +// SPDX-License-Identifier: GPL Which is absolutely hillarious as the commit introducing this wreckage says in the changelog: There was a checkpatch complain: "Missing or malformed SPDX-License-Identifier tag". Oh well. Replacing a checkpatch warning by a different checkpatch warning is a really useful exercise. Use the proper GPL-2.0 identifier which is what the boiler plate in the file had originally. Fixes: e75e3a125b40 ("drivers: power: supply: goldfish_battery: Put an SPDX tag") Signed-off-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- drivers/power/supply/goldfish_battery.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/power/supply/goldfish_battery.c b/drivers/power/supply/goldfish_battery.c index ad969d9fc981..c2644a9fe80f 100644 --- a/drivers/power/supply/goldfish_battery.c +++ b/drivers/power/supply/goldfish_battery.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL +// SPDX-License-Identifier: GPL-2.0 /* * Power supply driver for the goldfish emulator * -- cgit v1.2.3-55-g7522 From 39036cd2727395c3369b1051005da74059a85317 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 28 Feb 2019 13:59:19 +0100 Subject: arch: add pidfd and io_uring syscalls everywhere Add the io_uring and pidfd_send_signal system calls to all architectures. These system calls are designed to handle both native and compat tasks, so all entries are the same across architectures, only arm-compat and the generic tale still use an old format. Acked-by: Michael Ellerman (powerpc) Acked-by: Heiko Carstens (s390) Acked-by: Geert Uytterhoeven Signed-off-by: Arnd Bergmann --- arch/alpha/kernel/syscalls/syscall.tbl | 4 ++++ arch/arm/tools/syscall.tbl | 4 ++++ arch/arm64/include/asm/unistd.h | 2 +- arch/arm64/include/asm/unistd32.h | 8 ++++++++ arch/ia64/kernel/syscalls/syscall.tbl | 4 ++++ arch/m68k/kernel/syscalls/syscall.tbl | 4 ++++ arch/microblaze/kernel/syscalls/syscall.tbl | 4 ++++ arch/mips/kernel/syscalls/syscall_n32.tbl | 4 ++++ arch/mips/kernel/syscalls/syscall_n64.tbl | 4 ++++ arch/mips/kernel/syscalls/syscall_o32.tbl | 4 ++++ arch/parisc/kernel/syscalls/syscall.tbl | 4 ++++ arch/powerpc/kernel/syscalls/syscall.tbl | 4 ++++ arch/s390/kernel/syscalls/syscall.tbl | 4 ++++ arch/sh/kernel/syscalls/syscall.tbl | 4 ++++ arch/sparc/kernel/syscalls/syscall.tbl | 4 ++++ arch/xtensa/kernel/syscalls/syscall.tbl | 4 ++++ 16 files changed, 65 insertions(+), 1 deletion(-) diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index 63ed39cbd3bd..165f268beafc 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -463,3 +463,7 @@ 532 common getppid sys_getppid # all other architectures have common numbers for new syscall, alpha # is the exception. +534 common pidfd_send_signal sys_pidfd_send_signal +535 common io_uring_setup sys_io_uring_setup +536 common io_uring_enter sys_io_uring_enter +537 common io_uring_register sys_io_uring_register diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index 9016f4081bb9..0393917eaa57 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -437,3 +437,7 @@ 421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait 422 common futex_time64 sys_futex 423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index d1dd93436e1e..f2a83ff6b73c 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -44,7 +44,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) -#define __NR_compat_syscalls 424 +#define __NR_compat_syscalls 428 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 5590f2623690..23f1a44acada 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -866,6 +866,14 @@ __SYSCALL(__NR_rt_sigtimedwait_time64, compat_sys_rt_sigtimedwait_time64) __SYSCALL(__NR_futex_time64, sys_futex) #define __NR_sched_rr_get_interval_time64 423 __SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval) +#define __NR_pidfd_send_signal 424 +__SYSCALL(__NR_pidfd_send_signal, sys_pidfd_send_signal) +#define __NR_io_uring_setup 425 +__SYSCALL(__NR_io_uring_setup, sys_io_uring_setup) +#define __NR_io_uring_enter 426 +__SYSCALL(__NR_io_uring_enter, sys_io_uring_enter) +#define __NR_io_uring_register 427 +__SYSCALL(__NR_io_uring_register, sys_io_uring_register) /* * Please add new compat syscalls above this comment and update diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index ab9cda5f6136..56e3d0b685e1 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -344,3 +344,7 @@ 332 common pkey_free sys_pkey_free 333 common rseq sys_rseq # 334 through 423 are reserved to sync up with other architectures +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 125c14178979..df4ec3ec71d1 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -423,3 +423,7 @@ 421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait 422 common futex_time64 sys_futex 423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index 8ee3a8c18498..4964947732af 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -429,3 +429,7 @@ 421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait 422 common futex_time64 sys_futex 423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 15f4117900ee..9392dfe33f97 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -362,3 +362,7 @@ 421 n32 rt_sigtimedwait_time64 compat_sys_rt_sigtimedwait_time64 422 n32 futex_time64 sys_futex 423 n32 sched_rr_get_interval_time64 sys_sched_rr_get_interval +424 n32 pidfd_send_signal sys_pidfd_send_signal +425 n32 io_uring_setup sys_io_uring_setup +426 n32 io_uring_enter sys_io_uring_enter +427 n32 io_uring_register sys_io_uring_register diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index c85502e67b44..cd0c8aa21fba 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -338,3 +338,7 @@ 327 n64 rseq sys_rseq 328 n64 io_pgetevents sys_io_pgetevents # 329 through 423 are reserved to sync up with other architectures +424 n64 pidfd_send_signal sys_pidfd_send_signal +425 n64 io_uring_setup sys_io_uring_setup +426 n64 io_uring_enter sys_io_uring_enter +427 n64 io_uring_register sys_io_uring_register diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 2e063d0f837e..e849e8ffe4a2 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -411,3 +411,7 @@ 421 o32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 422 o32 futex_time64 sys_futex sys_futex 423 o32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval +424 o32 pidfd_send_signal sys_pidfd_send_signal +425 o32 io_uring_setup sys_io_uring_setup +426 o32 io_uring_enter sys_io_uring_enter +427 o32 io_uring_register sys_io_uring_register diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index b26766c6647d..fe8ca623add8 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -420,3 +420,7 @@ 421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 422 32 futex_time64 sys_futex sys_futex 423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index b18abb0c3dae..00f5a63c8d9a 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -505,3 +505,7 @@ 421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 422 32 futex_time64 sys_futex sys_futex 423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index 02579f95f391..061418f787c3 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -426,3 +426,7 @@ 421 32 rt_sigtimedwait_time64 - compat_sys_rt_sigtimedwait_time64 422 32 futex_time64 - sys_futex 423 32 sched_rr_get_interval_time64 - sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register sys_io_uring_register diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index bfda678576e4..480b057556ee 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -426,3 +426,7 @@ 421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait 422 common futex_time64 sys_futex 423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index b9a5a04b2d2c..a1dd24307b00 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -469,3 +469,7 @@ 421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 422 32 futex_time64 sys_futex sys_futex 423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 6af49929de85..30084eaf8422 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -394,3 +394,7 @@ 421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait 422 common futex_time64 sys_futex 423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register -- cgit v1.2.3-55-g7522 From b19062a567266ee1f10f6709325f766bbcc07d1c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 15 Apr 2019 10:49:38 -0600 Subject: io_uring: fix possible deadlock between io_uring_{enter,register} If we have multiple threads, one doing io_uring_enter() while the other is doing io_uring_register(), we can run into a deadlock between the two. io_uring_register() must wait for existing users of the io_uring instance to exit. But it does so while holding the io_uring mutex. Callers of io_uring_enter() may need this mutex to make progress (and eventually exit). If we wait for users to exit in io_uring_register(), we can't do so with the io_uring mutex held without potentially risking a deadlock. Drop the io_uring mutex while waiting for existing callers to exit. This is safe and guaranteed to make forward progress, since we already killed the percpu ref before doing so. Hence later callers of io_uring_enter() will be rejected. Reported-by: syzbot+16dc03452dee970a0c3e@syzkaller.appspotmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/fs/io_uring.c b/fs/io_uring.c index f4ddb9d23241..b35300e4c9a7 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2929,11 +2929,23 @@ SYSCALL_DEFINE2(io_uring_setup, u32, entries, static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, void __user *arg, unsigned nr_args) + __releases(ctx->uring_lock) + __acquires(ctx->uring_lock) { int ret; percpu_ref_kill(&ctx->refs); + + /* + * Drop uring mutex before waiting for references to exit. If another + * thread is currently inside io_uring_enter() it might need to grab + * the uring_lock to make progress. If we hold it here across the drain + * wait, then we can deadlock. It's safe to drop the mutex here, since + * no new references will come in after we've killed the percpu ref. + */ + mutex_unlock(&ctx->uring_lock); wait_for_completion(&ctx->ctx_done); + mutex_lock(&ctx->uring_lock); switch (opcode) { case IORING_REGISTER_BUFFERS: -- cgit v1.2.3-55-g7522 From 79b4a9cf0e2ea8203ce777c8d5cfa86c71eae86e Mon Sep 17 00:00:00 2001 From: Aurelien Jarno Date: Tue, 9 Apr 2019 16:53:55 +0200 Subject: MIPS: scall64-o32: Fix indirect syscall number load Commit 4c21b8fd8f14 (MIPS: seccomp: Handle indirect system calls (o32)) added indirect syscall detection for O32 processes running on MIPS64, but it did not work correctly for big endian kernel/processes. The reason is that the syscall number is loaded from ARG1 using the lw instruction while this is a 64-bit value, so zero is loaded instead of the syscall number. Fix the code by using the ld instruction instead. When running a 32-bit processes on a 64 bit CPU, the values are properly sign-extended, so it ensures the value passed to syscall_trace_enter is correct. Recent systemd versions with seccomp enabled whitelist the getpid syscall for their internal processes (e.g. systemd-journald), but call it through syscall(SYS_getpid). This fix therefore allows O32 big endian systems with a 64-bit kernel to run recent systemd versions. Signed-off-by: Aurelien Jarno Cc: # v3.15+ Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Paul Burton Cc: Ralf Baechle Cc: James Hogan Cc: linux-mips@vger.kernel.org Cc: linux-kernel@vger.kernel.org --- arch/mips/kernel/scall64-o32.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index f158c5894a9a..feb2653490df 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -125,7 +125,7 @@ trace_a_syscall: subu t1, v0, __NR_O32_Linux move a1, v0 bnez t1, 1f /* __NR_syscall at offset 0 */ - lw a1, PT_R4(sp) /* Arg1 for __NR_syscall case */ + ld a1, PT_R4(sp) /* Arg1 for __NR_syscall case */ .set pop 1: jal syscall_trace_enter -- cgit v1.2.3-55-g7522 From be549d49115422f846b6d96ee8fd7173a5f7ceb0 Mon Sep 17 00:00:00 2001 From: Jaesoo Lee Date: Tue, 9 Apr 2019 17:02:22 -0700 Subject: scsi: core: set result when the command cannot be dispatched When SCSI blk-mq is enabled, there is a bug in handling errors in scsi_queue_rq. Specifically, the bug is not setting result field of scsi_request correctly when the dispatch of the command has been failed. Since the upper layer code including the sg_io ioctl expects to receive any error status from result field of scsi_request, the error is silently ignored and this could cause data corruptions for some applications. Fixes: d285203cf647 ("scsi: add support for a blk-mq based I/O path.") Cc: Signed-off-by: Jaesoo Lee Reviewed-by: Hannes Reinecke Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_lib.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 601b9f1de267..07dfc17d4824 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1706,8 +1706,12 @@ out_put_budget: ret = BLK_STS_DEV_RESOURCE; break; default: + if (unlikely(!scsi_device_online(sdev))) + scsi_req(req)->result = DID_NO_CONNECT << 16; + else + scsi_req(req)->result = DID_ERROR << 16; /* - * Make sure to release all allocated ressources when + * Make sure to release all allocated resources when * we hit an error, as we will never see this command * again. */ -- cgit v1.2.3-55-g7522 From 6a03469a1edc94da52b65478f1e00837add869a3 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Mon, 15 Apr 2019 09:49:56 -0700 Subject: x86/build/lto: Fix truncated .bss with -fdata-sections With CONFIG_LD_DEAD_CODE_DATA_ELIMINATION=y, we compile the kernel with -fdata-sections, which also splits the .bss section. The new section, with a new .bss.* name, which pattern gets missed by the main x86 linker script which only expects the '.bss' name. This results in the discarding of the second part and a too small, truncated .bss section and an unhappy, non-working kernel. Use the common BSS_MAIN macro in the linker script to properly capture and merge all the generated BSS sections. Signed-off-by: Sami Tolvanen Reviewed-by: Nick Desaulniers Reviewed-by: Kees Cook Cc: Borislav Petkov Cc: Kees Cook Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20190415164956.124067-1-samitolvanen@google.com [ Extended the changelog. ] Signed-off-by: Ingo Molnar --- arch/x86/kernel/vmlinux.lds.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index bad8c51fee6e..a5127b2c195f 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -362,7 +362,7 @@ SECTIONS .bss : AT(ADDR(.bss) - LOAD_OFFSET) { __bss_start = .; *(.bss..page_aligned) - *(.bss) + *(BSS_MAIN) BSS_DECRYPTED . = ALIGN(PAGE_SIZE); __bss_stop = .; -- cgit v1.2.3-55-g7522 From 8b39adbee805c539a461dbf208b125b096152b1c Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 15 Apr 2019 10:05:38 -0700 Subject: locking/lockdep: Make lockdep_unregister_key() honor 'debug_locks' again If lockdep_register_key() and lockdep_unregister_key() are called with debug_locks == false then the following warning is reported: WARNING: CPU: 2 PID: 15145 at kernel/locking/lockdep.c:4920 lockdep_unregister_key+0x1ad/0x240 That warning is reported because lockdep_unregister_key() ignores the value of 'debug_locks' and because the behavior of lockdep_register_key() depends on whether or not 'debug_locks' is set. Fix this inconsistency by making lockdep_unregister_key() take 'debug_locks' again into account. Signed-off-by: Bart Van Assche Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Waiman Long Cc: Will Deacon Cc: shenghui Fixes: 90c1cba2b3b3 ("locking/lockdep: Zap lock classes even with lock debugging disabled") Link: http://lkml.kernel.org/r/20190415170538.23491-1-bvanassche@acm.org Signed-off-by: Ingo Molnar --- kernel/locking/lockdep.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index e16766ff184b..e221be724fe8 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -4907,8 +4907,9 @@ void lockdep_unregister_key(struct lock_class_key *key) return; raw_local_irq_save(flags); - arch_spin_lock(&lockdep_lock); - current->lockdep_recursion = 1; + if (!graph_lock()) + goto out_irq; + pf = get_pending_free(); hlist_for_each_entry_rcu(k, hash_head, hash_entry) { if (k == key) { @@ -4920,8 +4921,8 @@ void lockdep_unregister_key(struct lock_class_key *key) WARN_ON_ONCE(!found); __lockdep_free_key_range(pf, key, 1); call_rcu_zapped(pf); - current->lockdep_recursion = 0; - arch_spin_unlock(&lockdep_lock); + graph_unlock(); +out_irq: raw_local_irq_restore(flags); /* Wait until is_dynamic_key() has finished accessing k->hash_entry. */ -- cgit v1.2.3-55-g7522 From 5f843ed415581cfad4ef8fefe31c138a8346ca8a Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Mon, 15 Apr 2019 15:01:25 +0900 Subject: kprobes: Fix error check when reusing optimized probes The following commit introduced a bug in one of our error paths: 819319fc9346 ("kprobes: Return error if we fail to reuse kprobe instead of BUG_ON()") it missed to handle the return value of kprobe_optready() as error-value. In reality, the kprobe_optready() returns a bool result, so "true" case must be passed instead of 0. This causes some errors on kprobe boot-time selftests on ARM: [ ] Beginning kprobe tests... [ ] Probe ARM code [ ] kprobe [ ] kretprobe [ ] ARM instruction simulation [ ] Check decoding tables [ ] Run test cases [ ] FAIL: test_case_handler not run [ ] FAIL: Test andge r10, r11, r14, asr r7 [ ] FAIL: Scenario 11 ... [ ] FAIL: Scenario 7 [ ] Total instruction simulation tests=1631, pass=1433 fail=198 [ ] kprobe tests failed This can happen if an optimized probe is unregistered and next kprobe is registered on same address until the previous probe is not reclaimed. If this happens, a hidden aggregated probe may be kept in memory, and no new kprobe can probe same address. Also, in that case register_kprobe() will return "1" instead of minus error value, which can mislead caller logic. Signed-off-by: Masami Hiramatsu Cc: Anil S Keshavamurthy Cc: David S . Miller Cc: Linus Torvalds Cc: Naveen N . Rao Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: stable@vger.kernel.org # v5.0+ Fixes: 819319fc9346 ("kprobes: Return error if we fail to reuse kprobe instead of BUG_ON()") Link: http://lkml.kernel.org/r/155530808559.32517.539898325433642204.stgit@devnote2 Signed-off-by: Ingo Molnar --- kernel/kprobes.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/kernel/kprobes.c b/kernel/kprobes.c index c83e54727131..b1ea30a5540e 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -709,7 +709,6 @@ static void unoptimize_kprobe(struct kprobe *p, bool force) static int reuse_unused_kprobe(struct kprobe *ap) { struct optimized_kprobe *op; - int ret; /* * Unused kprobe MUST be on the way of delayed unoptimizing (means @@ -720,9 +719,8 @@ static int reuse_unused_kprobe(struct kprobe *ap) /* Enable the probe again */ ap->flags &= ~KPROBE_FLAG_DISABLED; /* Optimize it again (remove from op->list) */ - ret = kprobe_optready(ap); - if (ret) - return ret; + if (!kprobe_optready(ap)) + return -EINVAL; optimize_kprobe(ap); return 0; -- cgit v1.2.3-55-g7522 From 510bb96fe5b3480b4b22d815786377e54cb701e7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 15 Apr 2019 10:46:07 +0200 Subject: x86/mm: Prevent bogus warnings with "noexec=off" Xose Vazquez Perez reported boot warnings when NX is disabled on the kernel command line. __early_set_fixmap() triggers this warning: attempted to set unsupported pgprot: 8000000000000163 bits: 8000000000000000 supported: 7fffffffffffffff WARNING: CPU: 0 PID: 0 at arch/x86/include/asm/pgtable.h:537 __early_set_fixmap+0xa2/0xff because it uses __default_kernel_pte_mask to mask out unsupported bits. Use __supported_pte_mask instead. Disabling NX on the command line also triggers the NX warning in the page table mapping check: WARNING: CPU: 1 PID: 1 at arch/x86/mm/dump_pagetables.c:262 note_page+0x2ae/0x650 .... Make the warning depend on NX set in __supported_pte_mask. Reported-by: Xose Vazquez Perez Tested-by: Xose Vazquez Perez Signed-off-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Link: http://lkml.kernel.org/r/alpine.DEB.2.21.1904151037530.1729@nanos.tec.linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/mm/dump_pagetables.c | 3 ++- arch/x86/mm/ioremap.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index ee8f8ab46941..c0309ea9abee 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -259,7 +259,8 @@ static void note_wx(struct pg_state *st) #endif /* Account the WX pages */ st->wx_pages += npages; - WARN_ONCE(1, "x86/mm: Found insecure W+X mapping at address %pS\n", + WARN_ONCE(__supported_pte_mask & _PAGE_NX, + "x86/mm: Found insecure W+X mapping at address %pS\n", (void *)st->start_address); } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 0029604af8a4..dd73d5d74393 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -825,7 +825,7 @@ void __init __early_set_fixmap(enum fixed_addresses idx, pte = early_ioremap_pte(addr); /* Sanitize 'prot' against any unsupported bits: */ - pgprot_val(flags) &= __default_kernel_pte_mask; + pgprot_val(flags) &= __supported_pte_mask; if (pgprot_val(flags)) set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags)); -- cgit v1.2.3-55-g7522 From 0082517fa4bce073e7cf542633439f26538a14cc Mon Sep 17 00:00:00 2001 From: Jian-Hong Pan Date: Fri, 12 Apr 2019 16:01:53 +0800 Subject: x86/reboot, efi: Use EFI reboot for Acer TravelMate X514-51T Upon reboot, the Acer TravelMate X514-51T laptop appears to complete the shutdown process, but then it hangs in BIOS POST with a black screen. The problem is intermittent - at some points it has appeared related to Secure Boot settings or different kernel builds, but ultimately we have not been able to identify the exact conditions that trigger the issue to come and go. Besides, the EFI mode cannot be disabled in the BIOS of this model. However, after extensive testing, we observe that using the EFI reboot method reliably avoids the issue in all cases. So add a boot time quirk to use EFI reboot on such systems. Buglink: https://bugzilla.kernel.org/show_bug.cgi?id=203119 Signed-off-by: Jian-Hong Pan Signed-off-by: Daniel Drake Cc: Ard Biesheuvel Cc: Borislav Petkov Cc: Linus Torvalds Cc: Matt Fleming Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Cc: linux@endlessm.com Link: http://lkml.kernel.org/r/20190412080152.3718-1-jian-hong@endlessm.com [ Fix !CONFIG_EFI build failure, clarify the code and the changelog a bit. ] Signed-off-by: Ingo Molnar --- arch/x86/kernel/reboot.c | 21 +++++++++++++++++++++ include/linux/efi.h | 7 ++++++- 2 files changed, 27 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 725624b6c0c0..8fd3cedd9acc 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -81,6 +81,19 @@ static int __init set_bios_reboot(const struct dmi_system_id *d) return 0; } +/* + * Some machines don't handle the default ACPI reboot method and + * require the EFI reboot method: + */ +static int __init set_efi_reboot(const struct dmi_system_id *d) +{ + if (reboot_type != BOOT_EFI && !efi_runtime_disabled()) { + reboot_type = BOOT_EFI; + pr_info("%s series board detected. Selecting EFI-method for reboot.\n", d->ident); + } + return 0; +} + void __noreturn machine_real_restart(unsigned int type) { local_irq_disable(); @@ -166,6 +179,14 @@ static const struct dmi_system_id reboot_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "AOA110"), }, }, + { /* Handle reboot issue on Acer TravelMate X514-51T */ + .callback = set_efi_reboot, + .ident = "Acer TravelMate X514-51T", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate X514-51T"), + }, + }, /* Apple */ { /* Handle problems with rebooting on Apple MacBook5 */ diff --git a/include/linux/efi.h b/include/linux/efi.h index 54357a258b35..6ebc2098cfe1 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1611,7 +1611,12 @@ efi_status_t efi_setup_gop(efi_system_table_t *sys_table_arg, struct screen_info *si, efi_guid_t *proto, unsigned long size); -bool efi_runtime_disabled(void); +#ifdef CONFIG_EFI +extern bool efi_runtime_disabled(void); +#else +static inline bool efi_runtime_disabled(void) { return true; } +#endif + extern void efi_call_virt_check_flags(unsigned long flags, const char *call); extern unsigned long efi_call_virt_save_flags(void); -- cgit v1.2.3-55-g7522 From 780e0106d468a2962b16b52fdf42898f2639e0a0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 16 Apr 2019 10:03:35 +0200 Subject: x86/mm/tlb: Revert "x86/mm: Align TLB invalidation info" Revert the following commit: 515ab7c41306: ("x86/mm: Align TLB invalidation info") I found out (the hard way) that under some .config options (notably L1_CACHE_SHIFT=7) and compiler combinations this on-stack alignment leads to a 320 byte stack usage, which then triggers a KASAN stack warning elsewhere. Using 320 bytes of stack space for a 40 byte structure is ludicrous and clearly not right. Signed-off-by: Peter Zijlstra (Intel) Acked-by: Linus Torvalds Acked-by: Nadav Amit Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: 515ab7c41306 ("x86/mm: Align TLB invalidation info") Link: http://lkml.kernel.org/r/20190416080335.GM7905@worktop.programming.kicks-ass.net [ Minor changelog edits. ] Signed-off-by: Ingo Molnar --- arch/x86/mm/tlb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index bc4bc7b2f075..487b8474c01c 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -728,7 +728,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, { int cpu; - struct flush_tlb_info info __aligned(SMP_CACHE_BYTES) = { + struct flush_tlb_info info = { .mm = mm, .stride_shift = stride_shift, .freed_tables = freed_tables, -- cgit v1.2.3-55-g7522 From 52a44f83fc2d64a5e74d5d685fad2fecc7b7a321 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 29 Mar 2019 11:12:12 +0200 Subject: perf/core: Fix the address filtering fix The following recent commit: c60f83b813e5 ("perf, pt, coresight: Fix address filters for vmas with non-zero offset") changes the address filtering logic to communicate filter ranges to the PMU driver via a single address range object, instead of having the driver do the final bit of math. That change forgets to take into account kernel filters, which are not calculated the same way as DSO based filters. Fix that by passing the kernel filters the same way as file-based filters. This doesn't require any additional changes in the drivers. Reported-by: Adrian Hunter Signed-off-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Fixes: c60f83b813e5 ("perf, pt, coresight: Fix address filters for vmas with non-zero offset") Link: https://lkml.kernel.org/r/20190329091212.29870-1-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar --- kernel/events/core.c | 37 +++++++++++++++++++++---------------- 1 file changed, 21 insertions(+), 16 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 534e01e7bc36..dc7dead2d2cc 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -9077,26 +9077,29 @@ static void perf_event_addr_filters_apply(struct perf_event *event) if (task == TASK_TOMBSTONE) return; - if (!ifh->nr_file_filters) - return; - - mm = get_task_mm(event->ctx->task); - if (!mm) - goto restart; + if (ifh->nr_file_filters) { + mm = get_task_mm(event->ctx->task); + if (!mm) + goto restart; - down_read(&mm->mmap_sem); + down_read(&mm->mmap_sem); + } raw_spin_lock_irqsave(&ifh->lock, flags); list_for_each_entry(filter, &ifh->list, entry) { - event->addr_filter_ranges[count].start = 0; - event->addr_filter_ranges[count].size = 0; + if (filter->path.dentry) { + /* + * Adjust base offset if the filter is associated to a + * binary that needs to be mapped: + */ + event->addr_filter_ranges[count].start = 0; + event->addr_filter_ranges[count].size = 0; - /* - * Adjust base offset if the filter is associated to a binary - * that needs to be mapped: - */ - if (filter->path.dentry) perf_addr_filter_apply(filter, mm, &event->addr_filter_ranges[count]); + } else { + event->addr_filter_ranges[count].start = filter->offset; + event->addr_filter_ranges[count].size = filter->size; + } count++; } @@ -9104,9 +9107,11 @@ static void perf_event_addr_filters_apply(struct perf_event *event) event->addr_filters_gen++; raw_spin_unlock_irqrestore(&ifh->lock, flags); - up_read(&mm->mmap_sem); + if (ifh->nr_file_filters) { + up_read(&mm->mmap_sem); - mmput(mm); + mmput(mm); + } restart: perf_event_stop(event, 1); -- cgit v1.2.3-55-g7522 From 339bc4183596e1f68c2c98a03b87aa124107c317 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 29 Mar 2019 11:13:38 +0200 Subject: perf/ring_buffer: Fix AUX record suppression The following commit: 1627314fb54a33e ("perf: Suppress AUX/OVERWRITE records") has an unintended side-effect of also suppressing all AUX records with no flags and non-zero size, so all the regular records in the full trace mode. This breaks some use cases for people. Fix this by restoring "regular" AUX records. Reported-by: Ben Gainey Tested-by: Ben Gainey Signed-off-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Fixes: 1627314fb54a33e ("perf: Suppress AUX/OVERWRITE records") Link: https://lkml.kernel.org/r/20190329091338.29999-1-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar --- kernel/events/ring_buffer.c | 33 +++++++++++++++------------------ 1 file changed, 15 insertions(+), 18 deletions(-) diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 2545ac08cc77..5eedb49a65ea 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -455,24 +455,21 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) rb->aux_head += size; } - if (size || handle->aux_flags) { - /* - * Only send RECORD_AUX if we have something useful to communicate - * - * Note: the OVERWRITE records by themselves are not considered - * useful, as they don't communicate any *new* information, - * aside from the short-lived offset, that becomes history at - * the next event sched-in and therefore isn't useful. - * The userspace that needs to copy out AUX data in overwrite - * mode should know to use user_page::aux_head for the actual - * offset. So, from now on we don't output AUX records that - * have *only* OVERWRITE flag set. - */ - - if (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE) - perf_event_aux_event(handle->event, aux_head, size, - handle->aux_flags); - } + /* + * Only send RECORD_AUX if we have something useful to communicate + * + * Note: the OVERWRITE records by themselves are not considered + * useful, as they don't communicate any *new* information, + * aside from the short-lived offset, that becomes history at + * the next event sched-in and therefore isn't useful. + * The userspace that needs to copy out AUX data in overwrite + * mode should know to use user_page::aux_head for the actual + * offset. So, from now on we don't output AUX records that + * have *only* OVERWRITE flag set. + */ + if (size || (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE)) + perf_event_aux_event(handle->event, aux_head, size, + handle->aux_flags); rb->user_page->aux_head = rb->aux_head; if (rb_need_aux_wakeup(rb)) -- cgit v1.2.3-55-g7522 From 9d5dcc93a6ddfc78124f006ccd3637ce070ef2fc Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Tue, 2 Apr 2019 12:44:58 -0700 Subject: perf/x86: Fix incorrect PEBS_REGS PEBS_REGS used as mask for the supported registers for large PEBS. However, the mask cannot filter the sample_regs_user/sample_regs_intr correctly. (1ULL << PERF_REG_X86_*) should be used to replace PERF_REG_X86_*, which is only the index. Rename PEBS_REGS to PEBS_GP_REGS, because the mask is only for general purpose registers. Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: acme@kernel.org Cc: jolsa@kernel.org Fixes: 2fe1bc1f501d ("perf/x86: Enable free running PEBS for REGS_USER/INTR") Link: https://lkml.kernel.org/r/20190402194509.2832-2-kan.liang@linux.intel.com [ Renamed it to PEBS_GP_REGS - as 'GPRS' is used elsewhere ;-) ] Signed-off-by: Ingo Molnar --- arch/x86/events/intel/core.c | 2 +- arch/x86/events/perf_event.h | 38 +++++++++++++++++++------------------- 2 files changed, 20 insertions(+), 20 deletions(-) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index f61dcbef20ff..f9451566cd9b 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3131,7 +3131,7 @@ static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event) flags &= ~PERF_SAMPLE_TIME; if (!event->attr.exclude_kernel) flags &= ~PERF_SAMPLE_REGS_USER; - if (event->attr.sample_regs_user & ~PEBS_REGS) + if (event->attr.sample_regs_user & ~PEBS_GP_REGS) flags &= ~(PERF_SAMPLE_REGS_USER | PERF_SAMPLE_REGS_INTR); return flags; } diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index a75955741c50..1e98a42b560a 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -96,25 +96,25 @@ struct amd_nb { PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \ PERF_SAMPLE_PERIOD) -#define PEBS_REGS \ - (PERF_REG_X86_AX | \ - PERF_REG_X86_BX | \ - PERF_REG_X86_CX | \ - PERF_REG_X86_DX | \ - PERF_REG_X86_DI | \ - PERF_REG_X86_SI | \ - PERF_REG_X86_SP | \ - PERF_REG_X86_BP | \ - PERF_REG_X86_IP | \ - PERF_REG_X86_FLAGS | \ - PERF_REG_X86_R8 | \ - PERF_REG_X86_R9 | \ - PERF_REG_X86_R10 | \ - PERF_REG_X86_R11 | \ - PERF_REG_X86_R12 | \ - PERF_REG_X86_R13 | \ - PERF_REG_X86_R14 | \ - PERF_REG_X86_R15) +#define PEBS_GP_REGS \ + ((1ULL << PERF_REG_X86_AX) | \ + (1ULL << PERF_REG_X86_BX) | \ + (1ULL << PERF_REG_X86_CX) | \ + (1ULL << PERF_REG_X86_DX) | \ + (1ULL << PERF_REG_X86_DI) | \ + (1ULL << PERF_REG_X86_SI) | \ + (1ULL << PERF_REG_X86_SP) | \ + (1ULL << PERF_REG_X86_BP) | \ + (1ULL << PERF_REG_X86_IP) | \ + (1ULL << PERF_REG_X86_FLAGS) | \ + (1ULL << PERF_REG_X86_R8) | \ + (1ULL << PERF_REG_X86_R9) | \ + (1ULL << PERF_REG_X86_R10) | \ + (1ULL << PERF_REG_X86_R11) | \ + (1ULL << PERF_REG_X86_R12) | \ + (1ULL << PERF_REG_X86_R13) | \ + (1ULL << PERF_REG_X86_R14) | \ + (1ULL << PERF_REG_X86_R15)) /* * Per register state. -- cgit v1.2.3-55-g7522 From 08b7c2f9208f0e2a32159e4e7a4831b7adb10a3e Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Mon, 15 Apr 2019 12:10:14 +0100 Subject: staging: comedi: vmk80xx: Fix use of uninitialized semaphore If `vmk80xx_auto_attach()` returns an error, the core comedi module code will call `vmk80xx_detach()` to clean up. If `vmk80xx_auto_attach()` successfully allocated the comedi device private data, `vmk80xx_detach()` assumes that a `struct semaphore limit_sem` contained in the private data has been initialized and uses it. Unfortunately, there are a couple of places where `vmk80xx_auto_attach()` can return an error after allocating the device private data but before initializing the semaphore, so this assumption is invalid. Fix it by initializing the semaphore just after allocating the private data in `vmk80xx_auto_attach()` before any other errors can be returned. I believe this was the cause of the following syzbot crash report : usb 1-1: config 0 has no interface number 0 usb 1-1: New USB device found, idVendor=10cf, idProduct=8068, bcdDevice=e6.8d usb 1-1: New USB device strings: Mfr=0, Product=0, SerialNumber=0 usb 1-1: config 0 descriptor?? vmk80xx 1-1:0.117: driver 'vmk80xx' failed to auto-configure device. INFO: trying to register non-static key. the code is fine but needs lockdep annotation. turning off the locking correctness validator. CPU: 0 PID: 12 Comm: kworker/0:1 Not tainted 5.1.0-rc4-319354-g9a33b36 #3 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: usb_hub_wq hub_event Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0xe8/0x16e lib/dump_stack.c:113 assign_lock_key kernel/locking/lockdep.c:786 [inline] register_lock_class+0x11b8/0x1250 kernel/locking/lockdep.c:1095 __lock_acquire+0xfb/0x37c0 kernel/locking/lockdep.c:3582 lock_acquire+0x10d/0x2f0 kernel/locking/lockdep.c:4211 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline] _raw_spin_lock_irqsave+0x44/0x60 kernel/locking/spinlock.c:152 down+0x12/0x80 kernel/locking/semaphore.c:58 vmk80xx_detach+0x59/0x100 drivers/staging/comedi/drivers/vmk80xx.c:829 comedi_device_detach+0xed/0x800 drivers/staging/comedi/drivers.c:204 comedi_device_cleanup.part.0+0x68/0x140 drivers/staging/comedi/comedi_fops.c:156 comedi_device_cleanup drivers/staging/comedi/comedi_fops.c:187 [inline] comedi_free_board_dev.part.0+0x16/0x90 drivers/staging/comedi/comedi_fops.c:190 comedi_free_board_dev drivers/staging/comedi/comedi_fops.c:189 [inline] comedi_release_hardware_device+0x111/0x140 drivers/staging/comedi/comedi_fops.c:2880 comedi_auto_config.cold+0x124/0x1b0 drivers/staging/comedi/drivers.c:1068 usb_probe_interface+0x31d/0x820 drivers/usb/core/driver.c:361 really_probe+0x2da/0xb10 drivers/base/dd.c:509 driver_probe_device+0x21d/0x350 drivers/base/dd.c:671 __device_attach_driver+0x1d8/0x290 drivers/base/dd.c:778 bus_for_each_drv+0x163/0x1e0 drivers/base/bus.c:454 __device_attach+0x223/0x3a0 drivers/base/dd.c:844 bus_probe_device+0x1f1/0x2a0 drivers/base/bus.c:514 device_add+0xad2/0x16e0 drivers/base/core.c:2106 usb_set_configuration+0xdf7/0x1740 drivers/usb/core/message.c:2021 generic_probe+0xa2/0xda drivers/usb/core/generic.c:210 usb_probe_device+0xc0/0x150 drivers/usb/core/driver.c:266 really_probe+0x2da/0xb10 drivers/base/dd.c:509 driver_probe_device+0x21d/0x350 drivers/base/dd.c:671 __device_attach_driver+0x1d8/0x290 drivers/base/dd.c:778 bus_for_each_drv+0x163/0x1e0 drivers/base/bus.c:454 __device_attach+0x223/0x3a0 drivers/base/dd.c:844 bus_probe_device+0x1f1/0x2a0 drivers/base/bus.c:514 device_add+0xad2/0x16e0 drivers/base/core.c:2106 usb_new_device.cold+0x537/0xccf drivers/usb/core/hub.c:2534 hub_port_connect drivers/usb/core/hub.c:5089 [inline] hub_port_connect_change drivers/usb/core/hub.c:5204 [inline] port_event drivers/usb/core/hub.c:5350 [inline] hub_event+0x138e/0x3b00 drivers/usb/core/hub.c:5432 process_one_work+0x90f/0x1580 kernel/workqueue.c:2269 worker_thread+0x9b/0xe20 kernel/workqueue.c:2415 kthread+0x313/0x420 kernel/kthread.c:253 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:352 Reported-by: syzbot+54c2f58f15fe6876b6ad@syzkaller.appspotmail.com Signed-off-by: Ian Abbott Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/staging/comedi/drivers/vmk80xx.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/staging/comedi/drivers/vmk80xx.c b/drivers/staging/comedi/drivers/vmk80xx.c index 6234b649d887..b035d662390b 100644 --- a/drivers/staging/comedi/drivers/vmk80xx.c +++ b/drivers/staging/comedi/drivers/vmk80xx.c @@ -800,6 +800,8 @@ static int vmk80xx_auto_attach(struct comedi_device *dev, devpriv->model = board->model; + sema_init(&devpriv->limit_sem, 8); + ret = vmk80xx_find_usb_endpoints(dev); if (ret) return ret; @@ -808,8 +810,6 @@ static int vmk80xx_auto_attach(struct comedi_device *dev, if (ret) return ret; - sema_init(&devpriv->limit_sem, 8); - usb_set_intfdata(intf, devpriv); if (devpriv->model == VMK8055_MODEL) -- cgit v1.2.3-55-g7522 From 663d294b4768bfd89e529e069bffa544a830b5bf Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Mon, 15 Apr 2019 12:52:30 +0100 Subject: staging: comedi: vmk80xx: Fix possible double-free of ->usb_rx_buf `vmk80xx_alloc_usb_buffers()` is called from `vmk80xx_auto_attach()` to allocate RX and TX buffers for USB transfers. It allocates `devpriv->usb_rx_buf` followed by `devpriv->usb_tx_buf`. If the allocation of `devpriv->usb_tx_buf` fails, it frees `devpriv->usb_rx_buf`, leaving the pointer set dangling, and returns an error. Later, `vmk80xx_detach()` will be called from the core comedi module code to clean up. `vmk80xx_detach()` also frees both `devpriv->usb_rx_buf` and `devpriv->usb_tx_buf`, but `devpriv->usb_rx_buf` may have already been freed, leading to a double-free error. Fix it by removing the call to `kfree(devpriv->usb_rx_buf)` from `vmk80xx_alloc_usb_buffers()`, relying on `vmk80xx_detach()` to free the memory. Signed-off-by: Ian Abbott Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/staging/comedi/drivers/vmk80xx.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/staging/comedi/drivers/vmk80xx.c b/drivers/staging/comedi/drivers/vmk80xx.c index b035d662390b..65dc6c51037e 100644 --- a/drivers/staging/comedi/drivers/vmk80xx.c +++ b/drivers/staging/comedi/drivers/vmk80xx.c @@ -682,10 +682,8 @@ static int vmk80xx_alloc_usb_buffers(struct comedi_device *dev) size = usb_endpoint_maxp(devpriv->ep_tx); devpriv->usb_tx_buf = kzalloc(size, GFP_KERNEL); - if (!devpriv->usb_tx_buf) { - kfree(devpriv->usb_rx_buf); + if (!devpriv->usb_tx_buf) return -ENOMEM; - } return 0; } -- cgit v1.2.3-55-g7522 From a943245adc9ae31942af752e879fbbc182166573 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 16 Apr 2019 11:57:51 +0100 Subject: x86/Kconfig: Fix spelling mistake "effectivness" -> "effectiveness" The Kconfig text contains a spelling mistake, fix it. Signed-off-by: Colin Ian King Cc: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: kernel-janitors@vger.kernel.org Link: http://lkml.kernel.org/r/20190416105751.18899-1-colin.king@canonical.com Signed-off-by: Ingo Molnar --- arch/x86/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c1f9b3cf437c..01dbb05bc498 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1499,7 +1499,7 @@ config X86_CPA_STATISTICS depends on DEBUG_FS ---help--- Expose statistics about the Change Page Attribute mechanims, which - helps to determine the effectivness of preserving large and huge + helps to determine the effectiveness of preserving large and huge page mappings when mapping protections are changed. config ARCH_HAS_MEM_ENCRYPT -- cgit v1.2.3-55-g7522 From f4e97f5d4c9ece362b9379d3158cf5e4c02404dc Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Fri, 12 Apr 2019 17:53:14 +0800 Subject: staging: erofs: fix unexpected out-of-bound data access Unexpected out-of-bound data will be read in erofs_read_raw_page after commit 07173c3ec276 ("block: enable multipage bvecs") since one iovec could have multiple pages. Let's fix as what Ming's pointed out in the previous email [1]. [1] https://lore.kernel.org/lkml/20190411080953.GE421@ming.t460p/ Suggested-by: Ming Lei Reviewed-by: Chao Yu Signed-off-by: Gao Xiang Fixes: 07173c3ec276 ("block: enable multipage bvecs") Signed-off-by: Greg Kroah-Hartman --- drivers/staging/erofs/data.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/erofs/data.c b/drivers/staging/erofs/data.c index 526e0dbea5b5..81af768e7248 100644 --- a/drivers/staging/erofs/data.c +++ b/drivers/staging/erofs/data.c @@ -298,7 +298,7 @@ submit_bio_retry: *last_block = current_block; /* shift in advance in case of it followed by too many gaps */ - if (unlikely(bio->bi_vcnt >= bio->bi_max_vecs)) { + if (bio->bi_iter.bi_size >= bio->bi_max_vecs * PAGE_SIZE) { /* err should reassign to 0 after submitting */ err = 0; goto submit_bio_out; -- cgit v1.2.3-55-g7522 From 4d86c9f73c5a9a7c3c0661e922509c2c51801671 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Tue, 26 Mar 2019 22:01:27 -0700 Subject: clocksource/drivers/timer-ti-dm: Remove omap_dm_timer_set_load_start Commit 008258d995a6 ("clocksource/drivers/timer-ti-dm: Make omap_dm_timer_set_load_start() static") made omap_dm_time_set_load_start static because its prototype was not defined in a header. Unfortunately, this causes a build warning on multi_v7_defconfig because this function is not used anywhere in this translation unit: drivers/clocksource/timer-ti-dm.c:589:12: error: unused function 'omap_dm_timer_set_load_start' [-Werror,-Wunused-function] In fact, omap_dm_timer_set_load_start hasn't been used anywhere since commit f190be7f39a5 ("staging: tidspbridge: remove driver") and the prototype was removed in commit 592ea6bd1fad ("clocksource: timer-ti-dm: Make unexported functions static"), which is probably where this should have happened. Fixes: 592ea6bd1fad ("clocksource: timer-ti-dm: Make unexported functions static") Fixes: 008258d995a6 ("clocksource/drivers/timer-ti-dm: Make omap_dm_timer_set_load_start() static") Signed-off-by: Nathan Chancellor Acked-by: Tony Lindgren Signed-off-by: Daniel Lezcano --- drivers/clocksource/timer-ti-dm.c | 28 ---------------------------- 1 file changed, 28 deletions(-) diff --git a/drivers/clocksource/timer-ti-dm.c b/drivers/clocksource/timer-ti-dm.c index 3352da6ed61f..ee8ec5a8cb16 100644 --- a/drivers/clocksource/timer-ti-dm.c +++ b/drivers/clocksource/timer-ti-dm.c @@ -585,34 +585,6 @@ static int omap_dm_timer_set_load(struct omap_dm_timer *timer, int autoreload, return 0; } -/* Optimized set_load which removes costly spin wait in timer_start */ -static int omap_dm_timer_set_load_start(struct omap_dm_timer *timer, - int autoreload, unsigned int load) -{ - u32 l; - - if (unlikely(!timer)) - return -EINVAL; - - omap_dm_timer_enable(timer); - - l = omap_dm_timer_read_reg(timer, OMAP_TIMER_CTRL_REG); - if (autoreload) { - l |= OMAP_TIMER_CTRL_AR; - omap_dm_timer_write_reg(timer, OMAP_TIMER_LOAD_REG, load); - } else { - l &= ~OMAP_TIMER_CTRL_AR; - } - l |= OMAP_TIMER_CTRL_ST; - - __omap_dm_timer_load_start(timer, l, load, timer->posted); - - /* Save the context */ - timer->context.tclr = l; - timer->context.tldr = load; - timer->context.tcrr = load; - return 0; -} static int omap_dm_timer_set_match(struct omap_dm_timer *timer, int enable, unsigned int match) { -- cgit v1.2.3-55-g7522 From ace965696da2611af759f0284e26342b7b6cec89 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 1 Apr 2019 13:25:10 +0200 Subject: serial: sh-sci: Fix HSCIF RX sampling point calculation There are several issues with the formula used for calculating the deviation from the intended rate: 1. While min_err and last_stop are signed, srr and baud are unsigned. Hence the signed values are promoted to unsigned, which will lead to a bogus value of deviation if min_err is negative, 2. Srr is the register field value, which is one less than the actual sampling rate factor, 3. The divisions do not use rounding. Fix this by casting unsigned variables to int, adding one to srr, and using a single DIV_ROUND_CLOSEST(). Fixes: 63ba1e00f178a448 ("serial: sh-sci: Support for HSCIF RX sampling point adjustment") Signed-off-by: Geert Uytterhoeven Reviewed-by: Mukesh Ojha Cc: stable Reviewed-by: Ulrich Hecht Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/sh-sci.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 2d1c626312cd..55ef6e577f46 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -2512,7 +2512,9 @@ done: * center of the last stop bit in sampling clocks. */ int last_stop = bits * 2 - 1; - int deviation = min_err * srr * last_stop / 2 / baud; + int deviation = DIV_ROUND_CLOSEST(min_err * last_stop * + (int)(srr + 1), + 2 * (int)baud); if (abs(deviation) >= 2) { /* At least two sampling clocks off at the -- cgit v1.2.3-55-g7522 From 6b87784b53592a90d21576be8eff688b56d93cce Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 29 Mar 2019 10:10:26 +0100 Subject: serial: sh-sci: Fix HSCIF RX sampling point adjustment The calculation of the sampling point has min() and max() exchanged. Fix this by using the clamp() helper instead. Fixes: 63ba1e00f178a448 ("serial: sh-sci: Support for HSCIF RX sampling point adjustment") Signed-off-by: Geert Uytterhoeven Reviewed-by: Ulrich Hecht Reviewed-by: Wolfram Sang Acked-by: Dirk Behme Cc: stable Reviewed-by: Simon Horman Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/sh-sci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 55ef6e577f46..3cd139752d3f 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -2521,7 +2521,7 @@ done: * last stop bit; we can increase the error * margin by shifting the sampling point. */ - int shift = min(-8, max(7, deviation / 2)); + int shift = clamp(deviation / 2, -8, 7); hssrr |= (shift << HSCIF_SRHP_SHIFT) & HSCIF_SRHP_MASK; -- cgit v1.2.3-55-g7522 From e00164a0f000de893944981f41a568c981aca658 Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Tue, 9 Apr 2019 16:16:38 +0800 Subject: sc16is7xx: move label 'err_spi' to correct section err_spi is used when SERIAL_SC16IS7XX_SPI is enabled, so make the label only available under SERIAL_SC16IS7XX_SPI option. Otherwise, the below warning appears. drivers/tty/serial/sc16is7xx.c:1523:1: warning: label ‘err_spi’ defined but not used [-Wunused-label] err_spi: ^~~~~~~ Signed-off-by: Guoqing Jiang Fixes: ac0cdb3d9901 ("sc16is7xx: missing unregister/delete driver on error in sc16is7xx_init()") Signed-off-by: Arnd Bergmann Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/sc16is7xx.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index 09a183dfc526..22381a8c72e4 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -1520,10 +1520,12 @@ static int __init sc16is7xx_init(void) #endif return ret; +#ifdef CONFIG_SERIAL_SC16IS7XX_SPI err_spi: #ifdef CONFIG_SERIAL_SC16IS7XX_I2C i2c_del_driver(&sc16is7xx_i2c_uart_driver); #endif +#endif err_i2c: uart_unregister_driver(&sc16is7xx_uart); return ret; -- cgit v1.2.3-55-g7522 From 8c2f870890fd28e023b0fcf49dcee333f2c8bad7 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 16 Apr 2019 15:25:00 +0200 Subject: ALSA: info: Fix racy addition/deletion of nodes The ALSA proc helper manages the child nodes in a linked list, but its addition and deletion is done without any lock. This leads to a corruption if they are operated concurrently. Usually this isn't a problem because the proc entries are added sequentially in the driver probe procedure itself. But the card registrations are done often asynchronously, and the crash could be actually reproduced with syzkaller. This patch papers over it by protecting the link addition and deletion with the parent's mutex. There is "access" mutex that is used for the file access, and this can be reused for this purpose as well. Reported-by: syzbot+48df349490c36f9f54ab@syzkaller.appspotmail.com Cc: Signed-off-by: Takashi Iwai --- sound/core/info.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/sound/core/info.c b/sound/core/info.c index 96a074019c33..0eb169acc850 100644 --- a/sound/core/info.c +++ b/sound/core/info.c @@ -713,8 +713,11 @@ snd_info_create_entry(const char *name, struct snd_info_entry *parent, INIT_LIST_HEAD(&entry->list); entry->parent = parent; entry->module = module; - if (parent) + if (parent) { + mutex_lock(&parent->access); list_add_tail(&entry->list, &parent->children); + mutex_unlock(&parent->access); + } return entry; } @@ -792,7 +795,12 @@ void snd_info_free_entry(struct snd_info_entry * entry) list_for_each_entry_safe(p, n, &entry->children, list) snd_info_free_entry(p); - list_del(&entry->list); + p = entry->parent; + if (p) { + mutex_lock(&p->access); + list_del(&entry->list); + mutex_unlock(&p->access); + } kfree(entry->name); if (entry->private_free) entry->private_free(entry); -- cgit v1.2.3-55-g7522 From 14c9b31a925a9f5c647523a12e2b575b97c0aa47 Mon Sep 17 00:00:00 2001 From: Gustavo A. R. Silva Date: Mon, 8 Apr 2019 12:33:55 -0500 Subject: perf header: Fix lock/unlock imbalances when processing BPF/BTF info Fix lock/unlock imbalances by refactoring the code a bit and adding calls to up_write() before return. Signed-off-by: Gustavo A. R. Silva Acked-by: Song Liu Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Addresses-Coverity-ID: 1444315 ("Missing unlock") Addresses-Coverity-ID: 1444316 ("Missing unlock") Fixes: a70a1123174a ("perf bpf: Save BTF information as headers to perf.data") Fixes: 606f972b1361 ("perf bpf: Save bpf_prog_info information as headers to perf.data") Link: http://lkml.kernel.org/r/20190408173355.GA10501@embeddedor [ Simplified the exit path to have just one up_write() + return ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/header.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index b9e693825873..2d2af2ac2b1e 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -2606,6 +2606,7 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused) perf_env__insert_bpf_prog_info(env, info_node); } + up_write(&env->bpf_progs.lock); return 0; out: free(info_linear); @@ -2623,7 +2624,9 @@ static int process_bpf_prog_info(struct feat_fd *ff __maybe_unused, void *data _ static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused) { struct perf_env *env = &ff->ph->env; + struct btf_node *node = NULL; u32 count, i; + int err = -1; if (ff->ph->needs_swap) { pr_warning("interpreting btf from systems with endianity is not yet supported\n"); @@ -2636,31 +2639,32 @@ static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused) down_write(&env->bpf_progs.lock); for (i = 0; i < count; ++i) { - struct btf_node *node; u32 id, data_size; if (do_read_u32(ff, &id)) - return -1; + goto out; if (do_read_u32(ff, &data_size)) - return -1; + goto out; node = malloc(sizeof(struct btf_node) + data_size); if (!node) - return -1; + goto out; node->id = id; node->data_size = data_size; - if (__do_read(ff, node->data, data_size)) { - free(node); - return -1; - } + if (__do_read(ff, node->data, data_size)) + goto out; perf_env__insert_btf(env, node); + node = NULL; } + err = 0; +out: up_write(&env->bpf_progs.lock); - return 0; + free(node); + return err; } struct feature_ops { -- cgit v1.2.3-55-g7522 From 6e4b1cac30d297718218dc268199ed20df074b98 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 9 Apr 2019 09:25:57 +0300 Subject: perf scripts python: export-to-sqlite.py: Fix use of parent_id in calls_view Fix following error using calls_view: Query failed: ambiguous column name: parent_id Unable to execute statement Signed-off-by: Adrian Hunter Cc: Jiri Olsa Fixes: 8ce9a7251d11 ("perf scripts python: export-to-sqlite.py: Export calls parent_id") Link: http://lkml.kernel.org/r/20190409062557.26138-1-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/scripts/python/export-to-sqlite.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py index 3b71902a5a21..bf271fbc3a88 100644 --- a/tools/perf/scripts/python/export-to-sqlite.py +++ b/tools/perf/scripts/python/export-to-sqlite.py @@ -331,7 +331,7 @@ if perf_db_export_calls: 'return_id,' 'CASE WHEN flags=0 THEN \'\' WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' WHEN flags=6 THEN \'jump\' ELSE flags END AS flags,' 'parent_call_path_id,' - 'parent_id' + 'calls.parent_id' ' FROM calls INNER JOIN call_paths ON call_paths.id = call_path_id') do_query(query, 'CREATE VIEW samples_view AS ' -- cgit v1.2.3-55-g7522 From 8002a63f9ace7e9c958408f77f0a4dd4a8414511 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 9 Apr 2019 12:01:56 +0200 Subject: perf stat: Disable DIR_FORMAT feature for 'perf stat record' Arnaldo reported assertion in perf stat record: assertion failed at util/header.c:875 There's no support for this in the 'perf state record' command, disable the feature for that case. Reported-by: Arnaldo Carvalho de Melo Signed-off-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Peter Zijlstra Fixes: 258031c017c3 ("perf header: Add DIR_FORMAT feature to describe directory data") Link: http://lkml.kernel.org/r/20190409100156.20303-1-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 49ee3c2033ec..c3625ec374e0 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1308,6 +1308,7 @@ static void init_features(struct perf_session *session) for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++) perf_header__set_feat(&session->header, feat); + perf_header__clear_feat(&session->header, HEADER_DIR_FORMAT); perf_header__clear_feat(&session->header, HEADER_BUILD_ID); perf_header__clear_feat(&session->header, HEADER_TRACING_DATA); perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK); -- cgit v1.2.3-55-g7522 From f32c2877bcb068a718bb70094cd59ccc29d4d082 Mon Sep 17 00:00:00 2001 From: Rikard Falkeborn Date: Tue, 9 Apr 2019 11:15:29 +0200 Subject: tools lib traceevent: Fix missing equality check for strcmp There was a missing comparison with 0 when checking if type is "s64" or "u64". Therefore, the body of the if-statement was entered if "type" was "u64" or not "s64", which made the first strcmp() redundant since if type is "u64", it's not "s64". If type is "s64", the body of the if-statement is not entered but since the remainder of the function consists of if-statements which will not be entered if type is "s64", we will just return "val", which is correct, albeit at the cost of a few more calls to strcmp(), i.e., it will behave just as if the if-statement was entered. If type is neither "s64" or "u64", the body of the if-statement will be entered incorrectly and "val" returned. This means that any type that is checked after "s64" and "u64" is handled the same way as "s64" and "u64", i.e., the limiting of "val" to fit in for example "s8" is never reached. This was introduced in the kernel tree when the sources were copied from trace-cmd in commit f7d82350e597 ("tools/events: Add files to create libtraceevent.a"), and in the trace-cmd repo in 1cdbae6035cei ("Implement typecasting in parser") when the function was introduced, i.e., it has always behaved the wrong way. Detected by cppcheck. Signed-off-by: Rikard Falkeborn Reviewed-by: Steven Rostedt (VMware) Cc: Tzvetomir Stoyanov Fixes: f7d82350e597 ("tools/events: Add files to create libtraceevent.a") Link: http://lkml.kernel.org/r/20190409091529.2686-1-rikard.falkeborn@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/traceevent/event-parse.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 87494c7c619d..981c6ce2da2c 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -2233,7 +2233,7 @@ eval_type_str(unsigned long long val, const char *type, int pointer) return val & 0xffffffff; if (strcmp(type, "u64") == 0 || - strcmp(type, "s64")) + strcmp(type, "s64") == 0) return val; if (strcmp(type, "s8") == 0) -- cgit v1.2.3-55-g7522 From 3a5b64f05d7fe36dea0dde26423e3044fbacd482 Mon Sep 17 00:00:00 2001 From: Mao Han Date: Wed, 10 Apr 2019 16:16:43 +0800 Subject: perf evsel: Use hweight64() instead of hweight_long(attr.sample_regs_user) On 32-bits platform with more than 32 registers, the 64 bits mask is truncate to the lower 32 bits and the return value of hweight_long will always smaller than 32. When kernel outputs more than 32 registers, but the user perf program only counts 32, there will be a data mismatch result to overflow check fail. Signed-off-by: Mao Han Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Fixes: 6a21c0b5c2ab ("perf tools: Add core support for sampling intr machine state regs") Fixes: d03f2170546d ("perf tools: Expand perf_event__synthesize_sample()") Fixes: 0f6a30150ca2 ("perf tools: Support user regs and stack in sample parsing") Link: http://lkml.kernel.org/r/29ad7947dc8fd1ff0abd2093a72cc27a2446be9f.1554883878.git.han_mao@c-sky.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 66d066f18b5b..966360844fff 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -2368,7 +2368,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, if (data->user_regs.abi) { u64 mask = evsel->attr.sample_regs_user; - sz = hweight_long(mask) * sizeof(u64); + sz = hweight64(mask) * sizeof(u64); OVERFLOW_CHECK(array, sz, max_size); data->user_regs.mask = mask; data->user_regs.regs = (u64 *)array; @@ -2424,7 +2424,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) { u64 mask = evsel->attr.sample_regs_intr; - sz = hweight_long(mask) * sizeof(u64); + sz = hweight64(mask) * sizeof(u64); OVERFLOW_CHECK(array, sz, max_size); data->intr_regs.mask = mask; data->intr_regs.regs = (u64 *)array; @@ -2552,7 +2552,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, if (type & PERF_SAMPLE_REGS_USER) { if (sample->user_regs.abi) { result += sizeof(u64); - sz = hweight_long(sample->user_regs.mask) * sizeof(u64); + sz = hweight64(sample->user_regs.mask) * sizeof(u64); result += sz; } else { result += sizeof(u64); @@ -2580,7 +2580,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, if (type & PERF_SAMPLE_REGS_INTR) { if (sample->intr_regs.abi) { result += sizeof(u64); - sz = hweight_long(sample->intr_regs.mask) * sizeof(u64); + sz = hweight64(sample->intr_regs.mask) * sizeof(u64); result += sz; } else { result += sizeof(u64); @@ -2710,7 +2710,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, if (type & PERF_SAMPLE_REGS_USER) { if (sample->user_regs.abi) { *array++ = sample->user_regs.abi; - sz = hweight_long(sample->user_regs.mask) * sizeof(u64); + sz = hweight64(sample->user_regs.mask) * sizeof(u64); memcpy(array, sample->user_regs.regs, sz); array = (void *)array + sz; } else { @@ -2746,7 +2746,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, if (type & PERF_SAMPLE_REGS_INTR) { if (sample->intr_regs.abi) { *array++ = sample->intr_regs.abi; - sz = hweight_long(sample->intr_regs.mask) * sizeof(u64); + sz = hweight64(sample->intr_regs.mask) * sizeof(u64); memcpy(array, sample->intr_regs.regs, sz); array = (void *)array + sz; } else { -- cgit v1.2.3-55-g7522 From 6a3eb3360667170988f8a6477f6686242061488a Mon Sep 17 00:00:00 2001 From: ZhangXiaoxu Date: Sat, 6 Apr 2019 15:47:38 +0800 Subject: cifs: Fix use-after-free in SMB2_write There is a KASAN use-after-free: BUG: KASAN: use-after-free in SMB2_write+0x1342/0x1580 Read of size 8 at addr ffff8880b6a8e450 by task ln/4196 Should not release the 'req' because it will use in the trace. Fixes: eccb4422cf97 ("smb3: Add ftrace tracepoints for improved SMB3 debugging") Signed-off-by: ZhangXiaoxu Signed-off-by: Steve French CC: Stable 4.18+ Reviewed-by: Pavel Shilovsky --- fs/cifs/smb2pdu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 21ad01d55ab2..5d1f8d2d44e4 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -3769,7 +3769,6 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms, rc = cifs_send_recv(xid, io_parms->tcon->ses, &rqst, &resp_buftype, flags, &rsp_iov); - cifs_small_buf_release(req); rsp = (struct smb2_write_rsp *)rsp_iov.iov_base; if (rc) { @@ -3787,6 +3786,7 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms, io_parms->offset, *nbytes); } + cifs_small_buf_release(req); free_rsp_buf(resp_buftype, rsp); return rc; } -- cgit v1.2.3-55-g7522 From 088aaf17aa79300cab14dbee2569c58cfafd7d6e Mon Sep 17 00:00:00 2001 From: ZhangXiaoxu Date: Sat, 6 Apr 2019 15:47:39 +0800 Subject: cifs: Fix use-after-free in SMB2_read There is a KASAN use-after-free: BUG: KASAN: use-after-free in SMB2_read+0x1136/0x1190 Read of size 8 at addr ffff8880b4e45e50 by task ln/1009 Should not release the 'req' because it will use in the trace. Fixes: eccb4422cf97 ("smb3: Add ftrace tracepoints for improved SMB3 debugging") Signed-off-by: ZhangXiaoxu Signed-off-by: Steve French CC: Stable 4.18+ Reviewed-by: Pavel Shilovsky --- fs/cifs/smb2pdu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 5d1f8d2d44e4..5d6adc63ad62 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -3448,8 +3448,6 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, rqst.rq_nvec = 1; rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); - cifs_small_buf_release(req); - rsp = (struct smb2_read_rsp *)rsp_iov.iov_base; if (rc) { @@ -3471,6 +3469,8 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, io_parms->tcon->tid, ses->Suid, io_parms->offset, io_parms->length); + cifs_small_buf_release(req); + *nbytes = le32_to_cpu(rsp->DataLength); if ((*nbytes > CIFS_MAX_MSGSIZE) || (*nbytes > io_parms->length)) { -- cgit v1.2.3-55-g7522 From b57a55e2200ede754e4dc9cce4ba9402544b9365 Mon Sep 17 00:00:00 2001 From: ZhangXiaoxu Date: Sat, 6 Apr 2019 15:30:38 +0800 Subject: cifs: Fix lease buffer length error There is a KASAN slab-out-of-bounds: BUG: KASAN: slab-out-of-bounds in _copy_from_iter_full+0x783/0xaa0 Read of size 80 at addr ffff88810c35e180 by task mount.cifs/539 CPU: 1 PID: 539 Comm: mount.cifs Not tainted 4.19 #10 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-0-ga698c8995f-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack+0xdd/0x12a print_address_description+0xa7/0x540 kasan_report+0x1ff/0x550 check_memory_region+0x2f1/0x310 memcpy+0x2f/0x80 _copy_from_iter_full+0x783/0xaa0 tcp_sendmsg_locked+0x1840/0x4140 tcp_sendmsg+0x37/0x60 inet_sendmsg+0x18c/0x490 sock_sendmsg+0xae/0x130 smb_send_kvec+0x29c/0x520 __smb_send_rqst+0x3ef/0xc60 smb_send_rqst+0x25a/0x2e0 compound_send_recv+0x9e8/0x2af0 cifs_send_recv+0x24/0x30 SMB2_open+0x35e/0x1620 open_shroot+0x27b/0x490 smb2_open_op_close+0x4e1/0x590 smb2_query_path_info+0x2ac/0x650 cifs_get_inode_info+0x1058/0x28f0 cifs_root_iget+0x3bb/0xf80 cifs_smb3_do_mount+0xe00/0x14c0 cifs_do_mount+0x15/0x20 mount_fs+0x5e/0x290 vfs_kern_mount+0x88/0x460 do_mount+0x398/0x31e0 ksys_mount+0xc6/0x150 __x64_sys_mount+0xea/0x190 do_syscall_64+0x122/0x590 entry_SYSCALL_64_after_hwframe+0x44/0xa9 It can be reproduced by the following step: 1. samba configured with: server max protocol = SMB2_10 2. mount -o vers=default When parse the mount version parameter, the 'ops' and 'vals' was setted to smb30, if negotiate result is smb21, just update the 'ops' to smb21, but the 'vals' is still smb30. When add lease context, the iov_base is allocated with smb21 ops, but the iov_len is initiallited with the smb30. Because the iov_len is longer than iov_base, when send the message, copy array out of bounds. we need to keep the 'ops' and 'vals' consistent. Fixes: 9764c02fcbad ("SMB3: Add support for multidialect negotiate (SMB2.1 and later)") Fixes: d5c7076b772a ("smb3: add smb3.1.1 to default dialect list") Signed-off-by: ZhangXiaoxu Signed-off-by: Steve French CC: Stable Reviewed-by: Pavel Shilovsky --- fs/cifs/smb2pdu.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 5d6adc63ad62..b8f7262ac354 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -832,8 +832,11 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) } else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) { /* ops set to 3.0 by default for default so update */ ses->server->ops = &smb21_operations; - } else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) + ses->server->vals = &smb21_values; + } else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) { ses->server->ops = &smb311_operations; + ses->server->vals = &smb311_values; + } } else if (le16_to_cpu(rsp->DialectRevision) != ses->server->vals->protocol_id) { /* if requested single dialect ensure returned dialect matched */ -- cgit v1.2.3-55-g7522 From e6d0fb7b34f264f72c33053558a360a6a734905e Mon Sep 17 00:00:00 2001 From: Ronnie Sahlberg Date: Wed, 10 Apr 2019 07:47:22 +1000 Subject: cifs: fix handle leak in smb2_query_symlink() If we enter smb2_query_symlink() for something that is not a symlink and where the SMB2_open() would succeed we would never end up closing this handle and would thus leak a handle on the server. Fix this by immediately calling SMB2_close() on successfull open. Signed-off-by: Ronnie Sahlberg CC: Stable Signed-off-by: Steve French Reviewed-by: Pavel Shilovsky --- fs/cifs/smb2ops.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 00225e699d03..c36ff0d1fe2a 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -2389,6 +2389,8 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, &err_iov, &resp_buftype); + if (!rc) + SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); if (!rc || !err_iov.iov_base) { rc = -ENOENT; goto free_path; -- cgit v1.2.3-55-g7522 From b98749cac4a695f084a5ff076f4510b23e353ecd Mon Sep 17 00:00:00 2001 From: Aurelien Aptel Date: Fri, 29 Mar 2019 10:49:12 +0100 Subject: CIFS: keep FileInfo handle live during oplock break In the oplock break handler, writing pending changes from pages puts the FileInfo handle. If the refcount reaches zero it closes the handle and waits for any oplock break handler to return, thus causing a deadlock. To prevent this situation: * We add a wait flag to cifsFileInfo_put() to decide whether we should wait for running/pending oplock break handlers * We keep an additionnal reference of the SMB FileInfo handle so that for the rest of the handler putting the handle won't close it. - The ref is bumped everytime we queue the handler via the cifs_queue_oplock_break() helper. - The ref is decremented at the end of the handler This bug was triggered by xfstest 464. Also important fix to address the various reports of oops in smb2_push_mandatory_locks Signed-off-by: Aurelien Aptel Signed-off-by: Steve French Reviewed-by: Pavel Shilovsky CC: Stable --- fs/cifs/cifsglob.h | 2 ++ fs/cifs/file.c | 30 +++++++++++++++++++++++++----- fs/cifs/misc.c | 25 +++++++++++++++++++++++-- fs/cifs/smb2misc.c | 6 +++--- 4 files changed, 53 insertions(+), 10 deletions(-) diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 5b18d4585740..585ad3207cb1 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1333,6 +1333,7 @@ cifsFileInfo_get_locked(struct cifsFileInfo *cifs_file) } struct cifsFileInfo *cifsFileInfo_get(struct cifsFileInfo *cifs_file); +void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_hdlr); void cifsFileInfo_put(struct cifsFileInfo *cifs_file); #define CIFS_CACHE_READ_FLG 1 @@ -1855,6 +1856,7 @@ GLOBAL_EXTERN spinlock_t gidsidlock; #endif /* CONFIG_CIFS_ACL */ void cifs_oplock_break(struct work_struct *work); +void cifs_queue_oplock_break(struct cifsFileInfo *cfile); extern const struct slow_work_ops cifs_oplock_break_ops; extern struct workqueue_struct *cifsiod_wq; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 89006e044973..9c0ccc06d172 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -360,12 +360,30 @@ cifsFileInfo_get(struct cifsFileInfo *cifs_file) return cifs_file; } -/* - * Release a reference on the file private data. This may involve closing - * the filehandle out on the server. Must be called without holding - * tcon->open_file_lock and cifs_file->file_info_lock. +/** + * cifsFileInfo_put - release a reference of file priv data + * + * Always potentially wait for oplock handler. See _cifsFileInfo_put(). */ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) +{ + _cifsFileInfo_put(cifs_file, true); +} + +/** + * _cifsFileInfo_put - release a reference of file priv data + * + * This may involve closing the filehandle @cifs_file out on the + * server. Must be called without holding tcon->open_file_lock and + * cifs_file->file_info_lock. + * + * If @wait_for_oplock_handler is true and we are releasing the last + * reference, wait for any running oplock break handler of the file + * and cancel any pending one. If calling this function from the + * oplock break handler, you need to pass false. + * + */ +void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler) { struct inode *inode = d_inode(cifs_file->dentry); struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink); @@ -414,7 +432,8 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) spin_unlock(&tcon->open_file_lock); - oplock_break_cancelled = cancel_work_sync(&cifs_file->oplock_break); + oplock_break_cancelled = wait_oplock_handler ? + cancel_work_sync(&cifs_file->oplock_break) : false; if (!tcon->need_reconnect && !cifs_file->invalidHandle) { struct TCP_Server_Info *server = tcon->ses->server; @@ -4603,6 +4622,7 @@ void cifs_oplock_break(struct work_struct *work) cinode); cifs_dbg(FYI, "Oplock release rc = %d\n", rc); } + _cifsFileInfo_put(cfile, false /* do not wait for ourself */); cifs_done_oplock_break(cinode); } diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index bee203055b30..1e1626a2cfc3 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -501,8 +501,7 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &pCifsInode->flags); - queue_work(cifsoplockd_wq, - &netfile->oplock_break); + cifs_queue_oplock_break(netfile); netfile->oplock_break_cancelled = false; spin_unlock(&tcon->open_file_lock); @@ -607,6 +606,28 @@ void cifs_put_writer(struct cifsInodeInfo *cinode) spin_unlock(&cinode->writers_lock); } +/** + * cifs_queue_oplock_break - queue the oplock break handler for cfile + * + * This function is called from the demultiplex thread when it + * receives an oplock break for @cfile. + * + * Assumes the tcon->open_file_lock is held. + * Assumes cfile->file_info_lock is NOT held. + */ +void cifs_queue_oplock_break(struct cifsFileInfo *cfile) +{ + /* + * Bump the handle refcount now while we hold the + * open_file_lock to enforce the validity of it for the oplock + * break handler. The matching put is done at the end of the + * handler. + */ + cifsFileInfo_get(cfile); + + queue_work(cifsoplockd_wq, &cfile->oplock_break); +} + void cifs_done_oplock_break(struct cifsInodeInfo *cinode) { clear_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags); diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 0e3570e40ff8..e311f58dc1c8 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -555,7 +555,7 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp, clear_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags); - queue_work(cifsoplockd_wq, &cfile->oplock_break); + cifs_queue_oplock_break(cfile); kfree(lw); return true; } @@ -712,8 +712,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags); spin_unlock(&cfile->file_info_lock); - queue_work(cifsoplockd_wq, - &cfile->oplock_break); + + cifs_queue_oplock_break(cfile); spin_unlock(&tcon->open_file_lock); spin_unlock(&cifs_tcp_ses_lock); -- cgit v1.2.3-55-g7522 From 2e8e19226398db8265a8e675fcc0118b9e80c9e8 Mon Sep 17 00:00:00 2001 From: Phil Auld Date: Tue, 19 Mar 2019 09:00:05 -0400 Subject: sched/fair: Limit sched_cfs_period_timer() loop to avoid hard lockup With extremely short cfs_period_us setting on a parent task group with a large number of children the for loop in sched_cfs_period_timer() can run until the watchdog fires. There is no guarantee that the call to hrtimer_forward_now() will ever return 0. The large number of children can make do_sched_cfs_period_timer() take longer than the period. NMI watchdog: Watchdog detected hard LOCKUP on cpu 24 RIP: 0010:tg_nop+0x0/0x10 walk_tg_tree_from+0x29/0xb0 unthrottle_cfs_rq+0xe0/0x1a0 distribute_cfs_runtime+0xd3/0xf0 sched_cfs_period_timer+0xcb/0x160 ? sched_cfs_slack_timer+0xd0/0xd0 __hrtimer_run_queues+0xfb/0x270 hrtimer_interrupt+0x122/0x270 smp_apic_timer_interrupt+0x6a/0x140 apic_timer_interrupt+0xf/0x20 To prevent this we add protection to the loop that detects when the loop has run too many times and scales the period and quota up, proportionally, so that the timer can complete before then next period expires. This preserves the relative runtime quota while preventing the hard lockup. A warning is issued reporting this state and the new values. Signed-off-by: Phil Auld Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Anton Blanchard Cc: Ben Segall Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20190319130005.25492-1-pauld@redhat.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 40bd1e27b1b7..a4d9e14bf138 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4885,6 +4885,8 @@ static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer) return HRTIMER_NORESTART; } +extern const u64 max_cfs_quota_period; + static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) { struct cfs_bandwidth *cfs_b = @@ -4892,6 +4894,7 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) unsigned long flags; int overrun; int idle = 0; + int count = 0; raw_spin_lock_irqsave(&cfs_b->lock, flags); for (;;) { @@ -4899,6 +4902,28 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) if (!overrun) break; + if (++count > 3) { + u64 new, old = ktime_to_ns(cfs_b->period); + + new = (old * 147) / 128; /* ~115% */ + new = min(new, max_cfs_quota_period); + + cfs_b->period = ns_to_ktime(new); + + /* since max is 1s, this is limited to 1e9^2, which fits in u64 */ + cfs_b->quota *= new; + cfs_b->quota = div64_u64(cfs_b->quota, old); + + pr_warn_ratelimited( + "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us %lld, cfs_quota_us = %lld)\n", + smp_processor_id(), + div_u64(new, NSEC_PER_USEC), + div_u64(cfs_b->quota, NSEC_PER_USEC)); + + /* reset count so we don't come right back in here */ + count = 0; + } + idle = do_sched_cfs_period_timer(cfs_b, overrun, flags); } if (idle) -- cgit v1.2.3-55-g7522 From 1b02cd6a2d7f3e2a6a5262887d2cb2912083e42f Mon Sep 17 00:00:00 2001 From: luca abeni Date: Mon, 25 Mar 2019 14:15:30 +0100 Subject: sched/deadline: Correctly handle active 0-lag timers syzbot reported the following warning: [ ] WARNING: CPU: 4 PID: 17089 at kernel/sched/deadline.c:255 task_non_contending+0xae0/0x1950 line 255 of deadline.c is: WARN_ON(hrtimer_active(&dl_se->inactive_timer)); in task_non_contending(). Unfortunately, in some cases (for example, a deadline task continuosly blocking and waking immediately) it can happen that a task blocks (and task_non_contending() is called) while the 0-lag timer is still active. In this case, the safest thing to do is to immediately decrease the running bandwidth of the task, without trying to re-arm the 0-lag timer. Signed-off-by: luca abeni Signed-off-by: Peter Zijlstra (Intel) Acked-by: Juri Lelli Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: chengjian (D) Link: https://lkml.kernel.org/r/20190325131530.34706-1-luca.abeni@santannapisa.it Signed-off-by: Ingo Molnar --- kernel/sched/deadline.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 6a73e41a2016..43901fa3f269 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -252,7 +252,6 @@ static void task_non_contending(struct task_struct *p) if (dl_entity_is_special(dl_se)) return; - WARN_ON(hrtimer_active(&dl_se->inactive_timer)); WARN_ON(dl_se->dl_non_contending); zerolag_time = dl_se->deadline - @@ -269,7 +268,7 @@ static void task_non_contending(struct task_struct *p) * If the "0-lag time" already passed, decrease the active * utilization now, instead of starting a timer */ - if (zerolag_time < 0) { + if ((zerolag_time < 0) || hrtimer_active(&dl_se->inactive_timer)) { if (dl_task(p)) sub_running_bw(dl_se, dl_rq); if (!dl_task(p) || p->state == TASK_DEAD) { -- cgit v1.2.3-55-g7522 From 2a3f7221acddfe1caa9ff09b3a8158c39b2fdeac Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 16 Apr 2019 17:06:33 +0200 Subject: ALSA: core: Fix card races between register and disconnect There is a small race window in the card disconnection code that allows the registration of another card with the very same card id. This leads to a warning in procfs creation as caught by syzkaller. The problem is that we delete snd_cards and snd_cards_lock entries at the very beginning of the disconnection procedure. This makes the slot available to be assigned for another card object while the disconnection procedure is being processed. Then it becomes possible to issue a procfs registration with the existing file name although we check the conflict beforehand. The fix is simply to move the snd_cards and snd_cards_lock clearances at the end of the disconnection procedure. The references to these entries are merely either from the global proc files like /proc/asound/cards or from the card registration / disconnection, so it should be fine to shift at the very end. Reported-by: syzbot+48df349490c36f9f54ab@syzkaller.appspotmail.com Cc: Signed-off-by: Takashi Iwai --- sound/core/init.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/sound/core/init.c b/sound/core/init.c index 0c4dc40376a7..079c12d64b0e 100644 --- a/sound/core/init.c +++ b/sound/core/init.c @@ -382,14 +382,7 @@ int snd_card_disconnect(struct snd_card *card) card->shutdown = 1; spin_unlock(&card->files_lock); - /* phase 1: disable fops (user space) operations for ALSA API */ - mutex_lock(&snd_card_mutex); - snd_cards[card->number] = NULL; - clear_bit(card->number, snd_cards_lock); - mutex_unlock(&snd_card_mutex); - - /* phase 2: replace file->f_op with special dummy operations */ - + /* replace file->f_op with special dummy operations */ spin_lock(&card->files_lock); list_for_each_entry(mfile, &card->files_list, list) { /* it's critical part, use endless loop */ @@ -405,7 +398,7 @@ int snd_card_disconnect(struct snd_card *card) } spin_unlock(&card->files_lock); - /* phase 3: notify all connected devices about disconnection */ + /* notify all connected devices about disconnection */ /* at this point, they cannot respond to any calls except release() */ #if IS_ENABLED(CONFIG_SND_MIXER_OSS) @@ -421,6 +414,13 @@ int snd_card_disconnect(struct snd_card *card) device_del(&card->card_dev); card->registered = false; } + + /* disable fops (user space) operations for ALSA API */ + mutex_lock(&snd_card_mutex); + snd_cards[card->number] = NULL; + clear_bit(card->number, snd_cards_lock); + mutex_unlock(&snd_card_mutex); + #ifdef CONFIG_PM wake_up(&card->power_sleep); #endif -- cgit v1.2.3-55-g7522 From 1e6db2ee86e6a4399fc0ae5689e55e0fd1c43caf Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 15 Apr 2019 14:53:33 +0200 Subject: perf top: Always sample time to satisfy needs of use of ordered queuing Bastian reported broken 'perf top -p PID' command, it won't display any data. The problem is that for -p option we monitor single thread, so we don't enable time in samples, because it's not needed. However since commit 16c66bc167cc we use ordered queues to stash data plus later commits added logic for dropping samples in case there's big load and we don't keep up. All this needs timestamp for sample. Enabling it unconditionally for perf top. Reported-by: Bastian Beischer Signed-off-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: bastian beischer Fixes: 16c66bc167cc ("perf top: Add processing thread") Link: http://lkml.kernel.org/r/20190415125333.27160-1-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 1999d6533d12..fbbb0da43abb 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1377,6 +1377,7 @@ int cmd_top(int argc, const char **argv) * */ .overwrite = 0, .sample_time = true, + .sample_time_set = true, }, .max_stack = sysctl__max_stack(), .annotation_opts = annotation__default_options, -- cgit v1.2.3-55-g7522 From 30e4c574969ccb624940f1f2f7886596f8fc60ad Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 16 Apr 2019 11:30:15 -0300 Subject: tools include uapi: Sync sound/asound.h copy Picking the changes from: Fixes: b5bdbb6ccd11 ("ALSA: uapi: #include in asound.h") Which entails no changes in the tooling side. To silence this perf tools build warning: Warning: Kernel ABI header at 'tools/include/uapi/sound/asound.h' differs from latest version at 'include/uapi/sound/asound.h' diff -u tools/include/uapi/sound/asound.h include/uapi/sound/asound.h Cc: Adrian Hunter Cc: Daniel Mentz Cc: Jiri Olsa Cc: Namhyung Kim Cc: Takashi Iwai Link: https://lkml.kernel.org/n/tip-15o4twfkbn6nny9aus90dyzx@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/sound/asound.h | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index 404d4b9ffe76..df1153cea0b7 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -32,6 +32,7 @@ #ifndef __KERNEL__ #include +#include #endif /* -- cgit v1.2.3-55-g7522 From a1e8783db8e0d58891681bc1e6d9ada66eae8e20 Mon Sep 17 00:00:00 2001 From: Petr Štetiar Date: Fri, 12 Apr 2019 23:08:32 +0200 Subject: MIPS: perf: ath79: Fix perfcount IRQ assignment Currently it's not possible to use perf on ath79 due to genirq flags mismatch happening on static virtual IRQ 13 which is used for performance counters hardware IRQ 5. On TP-Link Archer C7v5: CPU0 2: 0 MIPS 2 ath9k 4: 318 MIPS 4 19000000.eth 7: 55034 MIPS 7 timer 8: 1236 MISC 3 ttyS0 12: 0 INTC 1 ehci_hcd:usb1 13: 0 gpio-ath79 2 keys 14: 0 gpio-ath79 5 keys 15: 31 AR724X PCI 1 ath10k_pci $ perf top genirq: Flags mismatch irq 13. 00014c83 (mips_perf_pmu) vs. 00002003 (keys) On TP-Link Archer C7v4: CPU0 4: 0 MIPS 4 19000000.eth 5: 7135 MIPS 5 1a000000.eth 7: 98379 MIPS 7 timer 8: 30 MISC 3 ttyS0 12: 90028 INTC 0 ath9k 13: 5520 INTC 1 ehci_hcd:usb1 14: 4623 INTC 2 ehci_hcd:usb2 15: 32844 AR724X PCI 1 ath10k_pci 16: 0 gpio-ath79 16 keys 23: 0 gpio-ath79 23 keys $ perf top genirq: Flags mismatch irq 13. 00014c80 (mips_perf_pmu) vs. 00000080 (ehci_hcd:usb1) This problem is happening, because currently statically assigned virtual IRQ 13 for performance counters is not claimed during the initialization of MIPS PMU during the bootup, so the IRQ subsystem doesn't know, that this interrupt isn't available for further use. So this patch fixes the issue by simply booking hardware IRQ 5 for MIPS PMU. Tested-by: Kevin 'ldir' Darbyshire-Bryant Signed-off-by: Petr Štetiar Acked-by: John Crispin Acked-by: Marc Zyngier Signed-off-by: Paul Burton Cc: linux-mips@vger.kernel.org Cc: Ralf Baechle Cc: James Hogan Cc: Thomas Gleixner Cc: Jason Cooper --- arch/mips/ath79/setup.c | 6 ------ drivers/irqchip/irq-ath79-misc.c | 11 +++++++++++ 2 files changed, 11 insertions(+), 6 deletions(-) diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c index 4a70c5de8c92..25a57895a3a3 100644 --- a/arch/mips/ath79/setup.c +++ b/arch/mips/ath79/setup.c @@ -210,12 +210,6 @@ const char *get_system_type(void) return ath79_sys_type; } -int get_c0_perfcount_int(void) -{ - return ATH79_MISC_IRQ(5); -} -EXPORT_SYMBOL_GPL(get_c0_perfcount_int); - unsigned int get_c0_compare_int(void) { return CP0_LEGACY_COMPARE_IRQ; diff --git a/drivers/irqchip/irq-ath79-misc.c b/drivers/irqchip/irq-ath79-misc.c index aa7290784636..0390603170b4 100644 --- a/drivers/irqchip/irq-ath79-misc.c +++ b/drivers/irqchip/irq-ath79-misc.c @@ -22,6 +22,15 @@ #define AR71XX_RESET_REG_MISC_INT_ENABLE 4 #define ATH79_MISC_IRQ_COUNT 32 +#define ATH79_MISC_PERF_IRQ 5 + +static int ath79_perfcount_irq; + +int get_c0_perfcount_int(void) +{ + return ath79_perfcount_irq; +} +EXPORT_SYMBOL_GPL(get_c0_perfcount_int); static void ath79_misc_irq_handler(struct irq_desc *desc) { @@ -113,6 +122,8 @@ static void __init ath79_misc_intc_domain_init( { void __iomem *base = domain->host_data; + ath79_perfcount_irq = irq_create_mapping(domain, ATH79_MISC_PERF_IRQ); + /* Disable and clear all interrupts */ __raw_writel(0, base + AR71XX_RESET_REG_MISC_INT_ENABLE); __raw_writel(0, base + AR71XX_RESET_REG_MISC_INT_STATUS); -- cgit v1.2.3-55-g7522 From 83f8bf4b837b0e3417f0e5c717a43fcf71ecc992 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Tue, 16 Apr 2019 14:43:26 +0200 Subject: drm/tegra: hdmi: Setup audio only if configured The audio configuration is only valid if the HDMI codec has been properly set up. Do not attempt to set up audio before that happens because it causes a division by zero. Note that this is only problematic on Tegra20 and Tegra30. Later chips implement the division instructions which return zero when dividing by zero and don't throw an exception. Fixes: db5adf4d6dce ("drm/tegra: hdmi: Fix audio to work with any pixel clock rate") Reported-by: Marcel Ziswiler Tested-by: Dmitry Osipenko Signed-off-by: Thierry Reding --- drivers/gpu/drm/tegra/hdmi.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/tegra/hdmi.c b/drivers/gpu/drm/tegra/hdmi.c index 47c55974756d..d23c4bfde790 100644 --- a/drivers/gpu/drm/tegra/hdmi.c +++ b/drivers/gpu/drm/tegra/hdmi.c @@ -1260,9 +1260,15 @@ static void tegra_hdmi_encoder_enable(struct drm_encoder *encoder) hdmi->dvi = !tegra_output_is_hdmi(output); if (!hdmi->dvi) { - err = tegra_hdmi_setup_audio(hdmi); - if (err < 0) - hdmi->dvi = true; + /* + * Make sure that the audio format has been configured before + * enabling audio, otherwise we may try to divide by zero. + */ + if (hdmi->format.sample_rate > 0) { + err = tegra_hdmi_setup_audio(hdmi); + if (err < 0) + hdmi->dvi = true; + } } if (hdmi->config->has_hda) -- cgit v1.2.3-55-g7522 From 35af0d469c6694c05f06e75c5d75caee9be66122 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Mon, 15 Apr 2019 12:41:08 +0200 Subject: s390: correct some inline assembly constraints Inline assembly code changed in this patch should really use "Q" constraint "Memory reference without index register and with short displacement". The kernel build with kasan instrumentation enabled might occasionally break otherwise (due to stack instrumentation). Signed-off-by: Vasily Gorbik Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/fpu.c | 2 +- arch/s390/kernel/vtime.c | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/s390/kernel/fpu.c b/arch/s390/kernel/fpu.c index 594464f2129d..0da378e2eb25 100644 --- a/arch/s390/kernel/fpu.c +++ b/arch/s390/kernel/fpu.c @@ -23,7 +23,7 @@ void __kernel_fpu_begin(struct kernel_fpu *state, u32 flags) if (flags & KERNEL_FPC) /* Save floating point control */ - asm volatile("stfpc %0" : "=m" (state->fpc)); + asm volatile("stfpc %0" : "=Q" (state->fpc)); if (!MACHINE_HAS_VX) { if (flags & KERNEL_VXR_V0V7) { diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index a69a0911ed0e..c475ca49cfc6 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -37,7 +37,7 @@ static inline u64 get_vtimer(void) { u64 timer; - asm volatile("stpt %0" : "=m" (timer)); + asm volatile("stpt %0" : "=Q" (timer)); return timer; } @@ -48,7 +48,7 @@ static inline void set_vtimer(u64 expires) asm volatile( " stpt %0\n" /* Store current cpu timer value */ " spt %1" /* Set new value imm. afterwards */ - : "=m" (timer) : "m" (expires)); + : "=Q" (timer) : "Q" (expires)); S390_lowcore.system_timer += S390_lowcore.last_update_timer - timer; S390_lowcore.last_update_timer = expires; } @@ -135,8 +135,8 @@ static int do_account_vtime(struct task_struct *tsk) #else " stck %1" /* Store current tod clock value */ #endif - : "=m" (S390_lowcore.last_update_timer), - "=m" (S390_lowcore.last_update_clock)); + : "=Q" (S390_lowcore.last_update_timer), + "=Q" (S390_lowcore.last_update_clock)); clock = S390_lowcore.last_update_clock - clock; timer -= S390_lowcore.last_update_timer; -- cgit v1.2.3-55-g7522 From b26e36b7ef36a8a3a147b1609b2505f8a4ecf511 Mon Sep 17 00:00:00 2001 From: Hui Wang Date: Wed, 17 Apr 2019 16:10:32 +0800 Subject: ALSA: hda/realtek - add two more pin configuration sets to quirk table We have two Dell laptops which have the codec 10ec0236 and 10ec0256 respectively, the headset mic on them can't work, need to apply the quirk of ALC255_FIXUP_DELL1_MIC_NO_PRESENCE. So adding their pin configurations in the pin quirk table. Cc: Signed-off-by: Hui Wang Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 810479766090..f5b510f119ed 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7266,6 +7266,8 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x12, 0x90a60140}, {0x14, 0x90170150}, {0x21, 0x02211020}), + SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, + {0x21, 0x02211020}), SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE, {0x14, 0x90170110}, {0x21, 0x02211020}), @@ -7376,6 +7378,10 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x21, 0x0221101f}), SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, ALC256_STANDARD_PINS), + SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, + {0x14, 0x90170110}, + {0x1b, 0x01011020}, + {0x21, 0x0221101f}), SND_HDA_PIN_QUIRK(0x10ec0256, 0x1043, "ASUS", ALC256_FIXUP_ASUS_MIC, {0x14, 0x90170110}, {0x1b, 0x90a70130}, -- cgit v1.2.3-55-g7522 From 660cf4ce9d0f3497cc7456eaa6d74c8b71d6282c Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Mon, 15 Apr 2019 12:43:01 +0100 Subject: staging: comedi: ni_usb6501: Fix use of uninitialized mutex If `ni6501_auto_attach()` returns an error, the core comedi module code will call `ni6501_detach()` to clean up. If `ni6501_auto_attach()` successfully allocated the comedi device private data, `ni6501_detach()` assumes that a `struct mutex mut` contained in the private data has been initialized and uses it. Unfortunately, there are a couple of places where `ni6501_auto_attach()` can return an error after allocating the device private data but before initializing the mutex, so this assumption is invalid. Fix it by initializing the mutex just after allocating the private data in `ni6501_auto_attach()` before any other errors can be retturned. Also move the call to `usb_set_intfdata()` just to keep the code a bit neater (either position for the call is fine). I believe this was the cause of the following syzbot crash report : usb 1-1: New USB device strings: Mfr=0, Product=0, SerialNumber=0 usb 1-1: config 0 descriptor?? usb 1-1: string descriptor 0 read error: -71 comedi comedi0: Wrong number of endpoints ni6501 1-1:0.233: driver 'ni6501' failed to auto-configure device. INFO: trying to register non-static key. the code is fine but needs lockdep annotation. turning off the locking correctness validator. CPU: 0 PID: 585 Comm: kworker/0:3 Not tainted 5.1.0-rc4-319354-g9a33b36 #3 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: usb_hub_wq hub_event Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0xe8/0x16e lib/dump_stack.c:113 assign_lock_key kernel/locking/lockdep.c:786 [inline] register_lock_class+0x11b8/0x1250 kernel/locking/lockdep.c:1095 __lock_acquire+0xfb/0x37c0 kernel/locking/lockdep.c:3582 lock_acquire+0x10d/0x2f0 kernel/locking/lockdep.c:4211 __mutex_lock_common kernel/locking/mutex.c:925 [inline] __mutex_lock+0xfe/0x12b0 kernel/locking/mutex.c:1072 ni6501_detach+0x5b/0x110 drivers/staging/comedi/drivers/ni_usb6501.c:567 comedi_device_detach+0xed/0x800 drivers/staging/comedi/drivers.c:204 comedi_device_cleanup.part.0+0x68/0x140 drivers/staging/comedi/comedi_fops.c:156 comedi_device_cleanup drivers/staging/comedi/comedi_fops.c:187 [inline] comedi_free_board_dev.part.0+0x16/0x90 drivers/staging/comedi/comedi_fops.c:190 comedi_free_board_dev drivers/staging/comedi/comedi_fops.c:189 [inline] comedi_release_hardware_device+0x111/0x140 drivers/staging/comedi/comedi_fops.c:2880 comedi_auto_config.cold+0x124/0x1b0 drivers/staging/comedi/drivers.c:1068 usb_probe_interface+0x31d/0x820 drivers/usb/core/driver.c:361 really_probe+0x2da/0xb10 drivers/base/dd.c:509 driver_probe_device+0x21d/0x350 drivers/base/dd.c:671 __device_attach_driver+0x1d8/0x290 drivers/base/dd.c:778 bus_for_each_drv+0x163/0x1e0 drivers/base/bus.c:454 __device_attach+0x223/0x3a0 drivers/base/dd.c:844 bus_probe_device+0x1f1/0x2a0 drivers/base/bus.c:514 device_add+0xad2/0x16e0 drivers/base/core.c:2106 usb_set_configuration+0xdf7/0x1740 drivers/usb/core/message.c:2021 generic_probe+0xa2/0xda drivers/usb/core/generic.c:210 usb_probe_device+0xc0/0x150 drivers/usb/core/driver.c:266 really_probe+0x2da/0xb10 drivers/base/dd.c:509 driver_probe_device+0x21d/0x350 drivers/base/dd.c:671 __device_attach_driver+0x1d8/0x290 drivers/base/dd.c:778 bus_for_each_drv+0x163/0x1e0 drivers/base/bus.c:454 __device_attach+0x223/0x3a0 drivers/base/dd.c:844 bus_probe_device+0x1f1/0x2a0 drivers/base/bus.c:514 device_add+0xad2/0x16e0 drivers/base/core.c:2106 usb_new_device.cold+0x537/0xccf drivers/usb/core/hub.c:2534 hub_port_connect drivers/usb/core/hub.c:5089 [inline] hub_port_connect_change drivers/usb/core/hub.c:5204 [inline] port_event drivers/usb/core/hub.c:5350 [inline] hub_event+0x138e/0x3b00 drivers/usb/core/hub.c:5432 process_one_work+0x90f/0x1580 kernel/workqueue.c:2269 worker_thread+0x9b/0xe20 kernel/workqueue.c:2415 kthread+0x313/0x420 kernel/kthread.c:253 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:352 Reported-by: syzbot+cf4f2b6c24aff0a3edf6@syzkaller.appspotmail.com Signed-off-by: Ian Abbott Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/staging/comedi/drivers/ni_usb6501.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/staging/comedi/drivers/ni_usb6501.c b/drivers/staging/comedi/drivers/ni_usb6501.c index 808ed92ed66f..ed5e42655821 100644 --- a/drivers/staging/comedi/drivers/ni_usb6501.c +++ b/drivers/staging/comedi/drivers/ni_usb6501.c @@ -518,6 +518,9 @@ static int ni6501_auto_attach(struct comedi_device *dev, if (!devpriv) return -ENOMEM; + mutex_init(&devpriv->mut); + usb_set_intfdata(intf, devpriv); + ret = ni6501_find_endpoints(dev); if (ret) return ret; @@ -526,9 +529,6 @@ static int ni6501_auto_attach(struct comedi_device *dev, if (ret) return ret; - mutex_init(&devpriv->mut); - usb_set_intfdata(intf, devpriv); - ret = comedi_alloc_subdevices(dev, 2); if (ret) return ret; -- cgit v1.2.3-55-g7522 From af4b54a2e5ba18259ff9aac445bf546dd60d037e Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Mon, 15 Apr 2019 12:43:02 +0100 Subject: staging: comedi: ni_usb6501: Fix possible double-free of ->usb_rx_buf `ni6501_alloc_usb_buffers()` is called from `ni6501_auto_attach()` to allocate RX and TX buffers for USB transfers. It allocates `devpriv->usb_rx_buf` followed by `devpriv->usb_tx_buf`. If the allocation of `devpriv->usb_tx_buf` fails, it frees `devpriv->usb_rx_buf`, leaving the pointer set dangling, and returns an error. Later, `ni6501_detach()` will be called from the core comedi module code to clean up. `ni6501_detach()` also frees both `devpriv->usb_rx_buf` and `devpriv->usb_tx_buf`, but `devpriv->usb_rx_buf` may have already beed freed, leading to a double-free error. Fix it bu removing the call to `kfree(devpriv->usb_rx_buf)` from `ni6501_alloc_usb_buffers()`, relying on `ni6501_detach()` to free the memory. Signed-off-by: Ian Abbott Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/staging/comedi/drivers/ni_usb6501.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/staging/comedi/drivers/ni_usb6501.c b/drivers/staging/comedi/drivers/ni_usb6501.c index ed5e42655821..1bb1cb651349 100644 --- a/drivers/staging/comedi/drivers/ni_usb6501.c +++ b/drivers/staging/comedi/drivers/ni_usb6501.c @@ -463,10 +463,8 @@ static int ni6501_alloc_usb_buffers(struct comedi_device *dev) size = usb_endpoint_maxp(devpriv->ep_tx); devpriv->usb_tx_buf = kzalloc(size, GFP_KERNEL); - if (!devpriv->usb_tx_buf) { - kfree(devpriv->usb_rx_buf); + if (!devpriv->usb_tx_buf) return -ENOMEM; - } return 0; } -- cgit v1.2.3-55-g7522 From b2ecf00631362a83744e5ec249947620db5e240c Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Thu, 4 Apr 2019 20:53:28 -0400 Subject: vt: fix cursor when clearing the screen The patch a6dbe4427559 ("vt: perform safe console erase in the right order") introduced a bug. The conditional do_update_region() was replaced by a call to update_region() that does contain the conditional already, but with unwanted extra side effects such as restoring the cursor drawing. In order to reproduce the bug: - use framebuffer console with the AMDGPU driver - type "links" to start the console www browser - press 'q' and space to exit links Now the cursor will be permanently visible in the center of the screen. It will stay there until something overwrites it. The bug goes away if we change update_region() back to the conditional do_update_region(). [ nico: reworded changelog ] Signed-off-by: Mikulas Patocka Reviewed-by: Nicolas Pitre Cc: stable@vger.kernel.org Fixes: a6dbe4427559 ("vt: perform safe console erase in the right order") Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/vt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index d34984aa646d..650c66886c80 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -1520,7 +1520,8 @@ static void csi_J(struct vc_data *vc, int vpar) return; } scr_memsetw(start, vc->vc_video_erase_char, 2 * count); - update_region(vc, (unsigned long) start, count); + if (con_should_update(vc)) + do_update_region(vc, (unsigned long) start, count); vc->vc_need_wrap = 0; } -- cgit v1.2.3-55-g7522 From aa52660231410b13d237299e691c43e346e3a73f Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 16 Apr 2019 15:41:51 +0200 Subject: perf bpf: Return NULL when RB tree lookup fails in perf_env__find_bpf_prog_info() We currently don't return NULL in case we don't find the bpf_prog_info_node, fixing that. Signed-off-by: Jiri Olsa Acked-by: Song Liu Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Peter Zijlstra Fixes: e4378f0cb90b ("perf bpf: Save bpf_prog_info in a rbtree in perf_env") Link: http://lkml.kernel.org/r/20190416134151.15282-1-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/env.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index c6351b557bb0..34a363f2e71b 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -57,9 +57,11 @@ struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env, else if (prog_id > node->info_linear->info.id) n = n->rb_right; else - break; + goto out; } + node = NULL; +out: up_read(&env->bpf_progs.lock); return node; } -- cgit v1.2.3-55-g7522 From a93e0b2365e81e5a5b61f25e269b5dc73d242cba Mon Sep 17 00:00:00 2001 From: Song Liu Date: Tue, 16 Apr 2019 18:01:22 +0200 Subject: perf tools: Check maps for bpf programs As reported by Jiri Olsa in: "[BUG] perf: intel_pt won't display kernel function" https://lore.kernel.org/lkml/20190403143738.GB32001@krava Recent changes to support PERF_RECORD_KSYMBOL and PERF_RECORD_BPF_EVENT broke --kallsyms option. This is because it broke test __map__is_kmodule. This patch fixes this by adding check for bpf program, so that these maps are not mistaken as kernel modules. Signed-off-by: Song Liu Reported-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexei Starovoitov Cc: Andi Kleen Cc: Andrii Nakryiko Cc: Daniel Borkmann Cc: Martin KaFai Lau Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Yonghong Song Link: http://lkml.kernel.org/r/20190416160127.30203-8-jolsa@kernel.org Fixes: 76193a94522f ("perf, bpf: Introduce PERF_RECORD_KSYMBOL") Signed-off-by: Jiri Olsa Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/map.c | 16 ++++++++++++++++ tools/perf/util/map.h | 4 +++- 2 files changed, 19 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index e32628cd20a7..28d484ef74ae 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -261,6 +261,22 @@ bool __map__is_extra_kernel_map(const struct map *map) return kmap && kmap->name[0]; } +bool __map__is_bpf_prog(const struct map *map) +{ + const char *name; + + if (map->dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) + return true; + + /* + * If PERF_RECORD_BPF_EVENT is not included, the dso will not have + * type of DSO_BINARY_TYPE__BPF_PROG_INFO. In such cases, we can + * guess the type based on name. + */ + name = map->dso->short_name; + return name && (strstr(name, "bpf_prog_") == name); +} + bool map__has_symbols(const struct map *map) { return dso__has_symbols(map->dso); diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 0e20749f2c55..dc93787c74f0 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -159,10 +159,12 @@ int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name, bool __map__is_kernel(const struct map *map); bool __map__is_extra_kernel_map(const struct map *map); +bool __map__is_bpf_prog(const struct map *map); static inline bool __map__is_kmodule(const struct map *map) { - return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map); + return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map) && + !__map__is_bpf_prog(map); } bool map__has_symbols(const struct map *map); -- cgit v1.2.3-55-g7522 From adc6257c4a6f23ff97dca8314fcd33828e2d8db5 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 16 Apr 2019 18:01:23 +0200 Subject: perf evlist: Fix side band thread draining Current perf_evlist__poll_thread() code could finish without draining the data. Adding the logic that makes sure we won't finish before the drain. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexei Starovoitov Cc: Andi Kleen Cc: Daniel Borkmann Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Song Liu Fixes: 657ee5531903 ("perf evlist: Introduce side band thread") Link: http://lkml.kernel.org/r/20190416160127.30203-9-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 6689378ee577..51ead577533f 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1868,12 +1868,12 @@ static void *perf_evlist__poll_thread(void *arg) { struct perf_evlist *evlist = arg; bool draining = false; - int i; + int i, done = 0; + + while (!done) { + bool got_data = false; - while (draining || !(evlist->thread.done)) { - if (draining) - draining = false; - else if (evlist->thread.done) + if (evlist->thread.done) draining = true; if (!draining) @@ -1894,9 +1894,13 @@ static void *perf_evlist__poll_thread(void *arg) pr_warning("cannot locate proper evsel for the side band event\n"); perf_mmap__consume(map); + got_data = true; } perf_mmap__read_done(map); } + + if (draining && !got_data) + break; } return NULL; } -- cgit v1.2.3-55-g7522 From b9abbdfa88024d52c8084d8f46ea4f161606c692 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 16 Apr 2019 18:01:24 +0200 Subject: perf tools: Fix map reference counting By calling maps__insert() we assume to get 2 references on the map, which we relese within maps__remove call. However if there's already same map name, we currently don't bump the reference and can crash, like: Program received signal SIGABRT, Aborted. 0x00007ffff75e60f5 in raise () from /lib64/libc.so.6 (gdb) bt #0 0x00007ffff75e60f5 in raise () from /lib64/libc.so.6 #1 0x00007ffff75d0895 in abort () from /lib64/libc.so.6 #2 0x00007ffff75d0769 in __assert_fail_base.cold () from /lib64/libc.so.6 #3 0x00007ffff75de596 in __assert_fail () from /lib64/libc.so.6 #4 0x00000000004fc006 in refcount_sub_and_test (i=1, r=0x1224e88) at tools/include/linux/refcount.h:131 #5 refcount_dec_and_test (r=0x1224e88) at tools/include/linux/refcount.h:148 #6 map__put (map=0x1224df0) at util/map.c:299 #7 0x00000000004fdb95 in __maps__remove (map=0x1224df0, maps=0xb17d80) at util/map.c:953 #8 maps__remove (maps=0xb17d80, map=0x1224df0) at util/map.c:959 #9 0x00000000004f7d8a in map_groups__remove (map=, mg=) at util/map_groups.h:65 #10 machine__process_ksymbol_unregister (sample=, event=0x7ffff7279670, machine=) at util/machine.c:728 #11 machine__process_ksymbol (machine=, event=0x7ffff7279670, sample=) at util/machine.c:741 #12 0x00000000004fffbb in perf_session__deliver_event (session=0xb11390, event=0x7ffff7279670, tool=0x7fffffffc7b0, file_offset=13936) at util/session.c:1362 #13 0x00000000005039bb in do_flush (show_progress=false, oe=0xb17e80) at util/ordered-events.c:243 #14 __ordered_events__flush (oe=0xb17e80, how=OE_FLUSH__ROUND, timestamp=) at util/ordered-events.c:322 #15 0x00000000005005e4 in perf_session__process_user_event (session=session@entry=0xb11390, event=event@entry=0x7ffff72a4af8, ... Add the map to the list and getting the reference event if we find the map with same name. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexei Starovoitov Cc: Andi Kleen Cc: Daniel Borkmann Cc: Eric Saint-Etienne Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Song Liu Fixes: 1e6285699b30 ("perf symbols: Fix slowness due to -ffunction-section") Link: http://lkml.kernel.org/r/20190416160127.30203-10-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/map.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 28d484ef74ae..ee71efb9db62 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -926,10 +926,8 @@ static void __maps__insert_name(struct maps *maps, struct map *map) rc = strcmp(m->dso->short_name, map->dso->short_name); if (rc < 0) p = &(*p)->rb_left; - else if (rc > 0) - p = &(*p)->rb_right; else - return; + p = &(*p)->rb_right; } rb_link_node(&map->rb_node_name, parent, p); rb_insert_color(&map->rb_node_name, &maps->names); -- cgit v1.2.3-55-g7522 From 2db7b1e0bd49d2b0e7d16949e167b1cfaf5c07cf Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 17 Apr 2019 16:55:39 +0200 Subject: perf bpf: Return NULL when RB tree lookup fails in perf_env__find_btf() We don't return NULL when we don't find the bpf_prog_info_node, fix that. Signed-off-by: Jiri Olsa Reported-by: Song Liu Acked-by: Song Liu Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Peter Zijlstra Fixes: 3792cb2ff43b ("perf bpf: Save BTF in a rbtree in perf_env") Link: http://lkml.kernel.org/r/20190417145539.11669-1-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/env.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 34a363f2e71b..9494f9dc61ec 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -111,10 +111,12 @@ struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id) else if (btf_id > node->id) n = n->rb_right; else - break; + goto out; } + node = NULL; up_read(&env->bpf_progs.lock); +out: return node; } -- cgit v1.2.3-55-g7522 From 74f464e97044da33b25aaed00213914b0edf1f2e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 17 Apr 2019 08:57:48 -0600 Subject: io_uring: fix CQ overflow condition This is a leftover from when the rings initially were not free flowing, and hence a test for tail + 1 == head would indicate full. Since we now let them wrap instead of mask them with the size, we need to check if they drift more than the ring size from each other. This fixes a case where we'd overwrite CQ ring entries, if the user failed to reap completions. Both cases would ultimately result in lost completions as the application violated the depth it asked for. The only difference is that before this fix we'd return invalid entries for the overflowed completions, instead of properly flagging it in the cq_ring->overflow variable. Reported-by: Stefan Bühler Signed-off-by: Jens Axboe --- fs/io_uring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index b35300e4c9a7..f65f85d89217 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -338,7 +338,7 @@ static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx) tail = ctx->cached_cq_tail; /* See comment at the top of the file */ smp_rmb(); - if (tail + 1 == READ_ONCE(ring->r.head)) + if (tail - READ_ONCE(ring->r.head) == ring->ring_entries) return NULL; ctx->cached_cq_tail++; -- cgit v1.2.3-55-g7522 From a7b1a4839ff979b4dd4fb6c1ccd31af11de9ca87 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 15 Apr 2019 11:54:13 -0400 Subject: SUNRPC: Ignore queue transmission errors on successful transmission If a request transmission fails due to write space or slot unavailability errors, but the queued task then gets transmitted before it has time to process the error in call_transmit_status() or call_bc_transmit_status(), we need to suppress the transmission error code to prevent it from leaking out of the RPC layer. Reported-by: Chuck Lever Signed-off-by: Trond Myklebust Tested-by: Chuck Lever --- net/sunrpc/clnt.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 1d0395ef62c9..8ff11dc98d7f 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2081,8 +2081,8 @@ call_transmit_status(struct rpc_task *task) * test first. */ if (rpc_task_transmitted(task)) { - if (task->tk_status == 0) - xprt_request_wait_receive(task); + task->tk_status = 0; + xprt_request_wait_receive(task); return; } @@ -2167,6 +2167,9 @@ call_bc_transmit_status(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; + if (rpc_task_transmitted(task)) + task->tk_status = 0; + dprint_status(task); switch (task->tk_status) { -- cgit v1.2.3-55-g7522 From 19fad20d15a6494f47f85d869f00b11343ee5c78 Mon Sep 17 00:00:00 2001 From: ZhangXiaoxu Date: Tue, 16 Apr 2019 09:47:24 +0800 Subject: ipv4: set the tcp_min_rtt_wlen range from 0 to one day There is a UBSAN report as below: UBSAN: Undefined behaviour in net/ipv4/tcp_input.c:2877:56 signed integer overflow: 2147483647 * 1000 cannot be represented in type 'int' CPU: 3 PID: 0 Comm: swapper/3 Not tainted 5.1.0-rc4-00058-g582549e #1 Call Trace: dump_stack+0x8c/0xba ubsan_epilogue+0x11/0x60 handle_overflow+0x12d/0x170 ? ttwu_do_wakeup+0x21/0x320 __ubsan_handle_mul_overflow+0x12/0x20 tcp_ack_update_rtt+0x76c/0x780 tcp_clean_rtx_queue+0x499/0x14d0 tcp_ack+0x69e/0x1240 ? __wake_up_sync_key+0x2c/0x50 ? update_group_capacity+0x50/0x680 tcp_rcv_established+0x4e2/0xe10 tcp_v4_do_rcv+0x22b/0x420 tcp_v4_rcv+0xfe8/0x1190 ip_protocol_deliver_rcu+0x36/0x180 ip_local_deliver+0x15b/0x1a0 ip_rcv+0xac/0xd0 __netif_receive_skb_one_core+0x7f/0xb0 __netif_receive_skb+0x33/0xc0 netif_receive_skb_internal+0x84/0x1c0 napi_gro_receive+0x2a0/0x300 receive_buf+0x3d4/0x2350 ? detach_buf_split+0x159/0x390 virtnet_poll+0x198/0x840 ? reweight_entity+0x243/0x4b0 net_rx_action+0x25c/0x770 __do_softirq+0x19b/0x66d irq_exit+0x1eb/0x230 do_IRQ+0x7a/0x150 common_interrupt+0xf/0xf It can be reproduced by: echo 2147483647 > /proc/sys/net/ipv4/tcp_min_rtt_wlen Fixes: f672258391b42 ("tcp: track min RTT using windowed min-filter") Signed-off-by: ZhangXiaoxu Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 1 + net/ipv4/sysctl_net_ipv4.c | 5 ++++- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index acdfb5d2bcaa..e2142fe40cda 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -422,6 +422,7 @@ tcp_min_rtt_wlen - INTEGER minimum RTT when it is moved to a longer path (e.g., due to traffic engineering). A longer window makes the filter more resistant to RTT inflations such as transient congestion. The unit is seconds. + Possible values: 0 - 86400 (1 day) Default: 300 tcp_moderate_rcvbuf - BOOLEAN diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index ba0fc4b18465..eeb4041fa5f9 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -49,6 +49,7 @@ static int ip_ping_group_range_min[] = { 0, 0 }; static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; static int comp_sack_nr_max = 255; static u32 u32_max_div_HZ = UINT_MAX / HZ; +static int one_day_secs = 24 * 3600; /* obsolete */ static int sysctl_tcp_low_latency __read_mostly; @@ -1151,7 +1152,9 @@ static struct ctl_table ipv4_net_table[] = { .data = &init_net.ipv4.sysctl_tcp_min_rtt_wlen, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one_day_secs }, { .procname = "tcp_autocorking", -- cgit v1.2.3-55-g7522 From f87db4dbd52f2f8a170a2b51cb0926221ca7c9e2 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Wed, 17 Apr 2019 09:49:39 +0800 Subject: net: stmmac: Use bfsize1 in ndesc_init_rx_desc gcc warn this: drivers/net/ethernet/stmicro/stmmac/norm_desc.c: In function ndesc_init_rx_desc: drivers/net/ethernet/stmicro/stmmac/norm_desc.c:138:6: warning: variable 'bfsize1' set but not used [-Wunused-but-set-variable] Like enh_desc_init_rx_desc, we should use bfsize1 in ndesc_init_rx_desc to calculate 'p->des1' Fixes: 583e63614149 ("net: stmmac: use correct DMA buffer size in the RX descriptor") Signed-off-by: YueHaibing Reviewed-by: Aaro Koskinen Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/norm_desc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c index b7dd4e3c760d..6d690678c20e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c +++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c @@ -140,7 +140,7 @@ static void ndesc_init_rx_desc(struct dma_desc *p, int disable_rx_ic, int mode, p->des0 |= cpu_to_le32(RDES0_OWN); bfsize1 = min(bfsize, BUF_SIZE_2KiB - 1); - p->des1 |= cpu_to_le32(bfsize & RDES1_BUFFER1_SIZE_MASK); + p->des1 |= cpu_to_le32(bfsize1 & RDES1_BUFFER1_SIZE_MASK); if (mode == STMMAC_CHAIN_MODE) ndesc_rx_set_on_chain(p, end); -- cgit v1.2.3-55-g7522 From d003d772e64df08af04ee63609d47169ee82ae0e Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Wed, 17 Apr 2019 14:15:00 +0100 Subject: nfp: abm: fix spelling mistake "offseting" -> "offsetting" There are a couple of spelling mistakes in NL_SET_ERR_MSG_MOD error messages. Fix these. Signed-off-by: Colin Ian King Acked-by: Jakub Kicinski Reviewed-by: Mukesh Ojha Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/abm/cls.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/abm/cls.c b/drivers/net/ethernet/netronome/nfp/abm/cls.c index 9852080cf454..ff3913085665 100644 --- a/drivers/net/ethernet/netronome/nfp/abm/cls.c +++ b/drivers/net/ethernet/netronome/nfp/abm/cls.c @@ -39,7 +39,7 @@ nfp_abm_u32_check_knode(struct nfp_abm *abm, struct tc_cls_u32_knode *knode, } if (knode->sel->off || knode->sel->offshift || knode->sel->offmask || knode->sel->offoff || knode->fshift) { - NL_SET_ERR_MSG_MOD(extack, "variable offseting not supported"); + NL_SET_ERR_MSG_MOD(extack, "variable offsetting not supported"); return false; } if (knode->sel->hoff || knode->sel->hmask) { @@ -78,7 +78,7 @@ nfp_abm_u32_check_knode(struct nfp_abm *abm, struct tc_cls_u32_knode *knode, k = &knode->sel->keys[0]; if (k->offmask) { - NL_SET_ERR_MSG_MOD(extack, "offset mask - variable offseting not supported"); + NL_SET_ERR_MSG_MOD(extack, "offset mask - variable offsetting not supported"); return false; } if (k->off) { -- cgit v1.2.3-55-g7522 From 27b141fc234a3670d21bd742c35d7205d03cbb3a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 17 Apr 2019 18:29:13 +0200 Subject: s390: ctcm: fix ctcm_new_device error return code clang points out that the return code from this function is undefined for one of the error paths: ../drivers/s390/net/ctcm_main.c:1595:7: warning: variable 'result' is used uninitialized whenever 'if' condition is true [-Wsometimes-uninitialized] if (priv->channel[direction] == NULL) { ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ../drivers/s390/net/ctcm_main.c:1638:9: note: uninitialized use occurs here return result; ^~~~~~ ../drivers/s390/net/ctcm_main.c:1595:3: note: remove the 'if' if its condition is always false if (priv->channel[direction] == NULL) { ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ../drivers/s390/net/ctcm_main.c:1539:12: note: initialize the variable 'result' to silence this warning int result; ^ Make it return -ENODEV here, as in the related failure cases. gcc has a known bug in underreporting some of these warnings when it has already eliminated the assignment of the return code based on some earlier optimization step. Reviewed-by: Nathan Chancellor Signed-off-by: Arnd Bergmann Signed-off-by: Julian Wiedmann Signed-off-by: David S. Miller --- drivers/s390/net/ctcm_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/s390/net/ctcm_main.c b/drivers/s390/net/ctcm_main.c index 7617d21cb296..f63c5c871d3d 100644 --- a/drivers/s390/net/ctcm_main.c +++ b/drivers/s390/net/ctcm_main.c @@ -1595,6 +1595,7 @@ static int ctcm_new_device(struct ccwgroup_device *cgdev) if (priv->channel[direction] == NULL) { if (direction == CTCM_WRITE) channel_free(priv->channel[CTCM_READ]); + result = -ENODEV; goto out_dev; } priv->channel[direction]->netdev = dev; -- cgit v1.2.3-55-g7522 From ec3937107ab43f3e8b2bc9dad95710043c462ff7 Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Thu, 4 Apr 2019 10:03:13 +0800 Subject: x86/mm/KASLR: Fix the size of the direct mapping section kernel_randomize_memory() uses __PHYSICAL_MASK_SHIFT to calculate the maximum amount of system RAM supported. The size of the direct mapping section is obtained from the smaller one of the below two values: (actual system RAM size + padding size) vs (max system RAM size supported) This calculation is wrong since commit b83ce5ee9147 ("x86/mm/64: Make __PHYSICAL_MASK_SHIFT always 52"). In it, __PHYSICAL_MASK_SHIFT was changed to be 52, regardless of whether the kernel is using 4-level or 5-level page tables. Thus, it will always use 4 PB as the maximum amount of system RAM, even in 4-level paging mode where it should actually be 64 TB. Thus, the size of the direct mapping section will always be the sum of the actual system RAM size plus the padding size. Even when the amount of system RAM is 64 TB, the following layout will still be used. Obviously KALSR will be weakened significantly. |____|_______actual RAM_______|_padding_|______the rest_______| 0 64TB ~120TB Instead, it should be like this: |____|_______actual RAM_______|_________the rest______________| 0 64TB ~120TB The size of padding region is controlled by CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING, which is 10 TB by default. The above issue only exists when CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING is set to a non-zero value, which is the case when CONFIG_MEMORY_HOTPLUG is enabled. Otherwise, using __PHYSICAL_MASK_SHIFT doesn't affect KASLR. Fix it by replacing __PHYSICAL_MASK_SHIFT with MAX_PHYSMEM_BITS. [ bp: Massage commit message. ] Fixes: b83ce5ee9147 ("x86/mm/64: Make __PHYSICAL_MASK_SHIFT always 52") Signed-off-by: Baoquan He Signed-off-by: Borislav Petkov Reviewed-by: Thomas Garnier Acked-by: Kirill A. Shutemov Cc: "H. Peter Anvin" Cc: Andy Lutomirski Cc: Dave Hansen Cc: Ingo Molnar Cc: Kees Cook Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: frank.ramsay@hpe.com Cc: herbert@gondor.apana.org.au Cc: kirill@shutemov.name Cc: mike.travis@hpe.com Cc: thgarnie@google.com Cc: x86-ml Cc: yamada.masahiro@socionext.com Link: https://lkml.kernel.org/r/20190417083536.GE7065@MiWiFi-R3L-srv --- arch/x86/mm/kaslr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 3f452ffed7e9..d669c5e797e0 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -94,7 +94,7 @@ void __init kernel_randomize_memory(void) if (!kaslr_memory_enabled()) return; - kaslr_regions[0].size_tb = 1 << (__PHYSICAL_MASK_SHIFT - TB_SHIFT); + kaslr_regions[0].size_tb = 1 << (MAX_PHYSMEM_BITS - TB_SHIFT); kaslr_regions[1].size_tb = VMALLOC_SIZE_TB; /* -- cgit v1.2.3-55-g7522 From 3fe3331bb285700ab2253dbb07f8e478fcea2f1b Mon Sep 17 00:00:00 2001 From: Kim Phillips Date: Thu, 21 Mar 2019 21:15:22 +0000 Subject: perf/x86/amd: Add event map for AMD Family 17h Family 17h differs from prior families by: - Does not support an L2 cache miss event - It has re-enumerated PMC counters for: - L2 cache references - front & back end stalled cycles So we add a new amd_f17h_perfmon_event_map[] so that the generic perf event names will resolve to the correct h/w events on family 17h and above processors. Reference sections 2.1.13.3.3 (stalls) and 2.1.13.3.6 (L2): https://www.amd.com/system/files/TechDocs/54945_PPR_Family_17h_Models_00h-0Fh.pdf Signed-off-by: Kim Phillips Cc: # v4.9+ Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: H. Peter Anvin Cc: Janakarajan Natarajan Cc: Jiri Olsa Cc: Linus Torvalds Cc: Martin Liška Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Pu Wen Cc: Suravee Suthikulpanit Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Fixes: e40ed1542dd7 ("perf/x86: Add perf support for AMD family-17h processors") [ Improved the formatting a bit. ] Signed-off-by: Ingo Molnar --- arch/x86/events/amd/core.c | 35 ++++++++++++++++++++++++++--------- 1 file changed, 26 insertions(+), 9 deletions(-) diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 0ecfac84ba91..d45f3fbd232e 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -117,22 +117,39 @@ static __initconst const u64 amd_hw_cache_event_ids }; /* - * AMD Performance Monitor K7 and later. + * AMD Performance Monitor K7 and later, up to and including Family 16h: */ static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] = { - [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, - [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, - [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d, - [PERF_COUNT_HW_CACHE_MISSES] = 0x077e, - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, - [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, - [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */ - [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x00d1, /* "Dispatch stalls" event */ + [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d, + [PERF_COUNT_HW_CACHE_MISSES] = 0x077e, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */ + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x00d1, /* "Dispatch stalls" event */ +}; + +/* + * AMD Performance Monitor Family 17h and later: + */ +static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] = +{ + [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x0287, + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x0187, }; static u64 amd_pmu_event_map(int hw_event) { + if (boot_cpu_data.x86 >= 0x17) + return amd_f17h_perfmon_event_map[hw_event]; + return amd_perfmon_event_map[hw_event]; } -- cgit v1.2.3-55-g7522 From 3f2552f7e9c5abef2775c53f7af66532f8bf65bc Mon Sep 17 00:00:00 2001 From: Chang-An Chen Date: Fri, 29 Mar 2019 10:59:09 +0800 Subject: timers/sched_clock: Prevent generic sched_clock wrap caused by tick_freeze() tick_freeze() introduced by suspend-to-idle in commit 124cf9117c5f ("PM / sleep: Make it possible to quiesce timers during suspend-to-idle") uses timekeeping_suspend() instead of syscore_suspend() during suspend-to-idle. As a consequence generic sched_clock will keep going because sched_clock_suspend() and sched_clock_resume() are not invoked during suspend-to-idle which can result in a generic sched_clock wrap. On a ARM system with suspend-to-idle enabled, sched_clock is registered as "56 bits at 13MHz, resolution 76ns, wraps every 4398046511101ns", which means the real wrapping duration is 8796093022202ns. [ 134.551779] suspend-to-idle suspend (timekeeping_suspend()) [ 1204.912239] suspend-to-idle resume (timekeeping_resume()) ...... [ 1206.912239] suspend-to-idle suspend (timekeeping_suspend()) [ 5880.502807] suspend-to-idle resume (timekeeping_resume()) ...... [ 6000.403724] suspend-to-idle suspend (timekeeping_suspend()) [ 8035.753167] suspend-to-idle resume (timekeeping_resume()) ...... [ 8795.786684] (2)[321:charger_thread]...... [ 8795.788387] (2)[321:charger_thread]...... [ 0.057226] (0)[0:swapper/0]...... [ 0.061447] (2)[0:swapper/2]...... sched_clock was not stopped during suspend-to-idle, and sched_clock_poll hrtimer was not expired because timekeeping_suspend() was invoked during suspend-to-idle. It makes sched_clock wrap at kernel time 8796s. To prevent this, invoke sched_clock_suspend() and sched_clock_resume() in tick_freeze() together with timekeeping_suspend() and timekeeping_resume(). Fixes: 124cf9117c5f (PM / sleep: Make it possible to quiesce timers during suspend-to-idle) Signed-off-by: Chang-An Chen Signed-off-by: Thomas Gleixner Cc: Frederic Weisbecker Cc: Matthias Brugger Cc: John Stultz Cc: Kees Cook Cc: Corey Minyard Cc: Cc: Cc: Stanley Chu Cc: Cc: Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1553828349-8914-1-git-send-email-chang-an.chen@mediatek.com --- kernel/time/sched_clock.c | 4 ++-- kernel/time/tick-common.c | 2 ++ kernel/time/timekeeping.h | 7 +++++++ 3 files changed, 11 insertions(+), 2 deletions(-) diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index 094b82ca95e5..930113b9799a 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -272,7 +272,7 @@ static u64 notrace suspended_sched_clock_read(void) return cd.read_data[seq & 1].epoch_cyc; } -static int sched_clock_suspend(void) +int sched_clock_suspend(void) { struct clock_read_data *rd = &cd.read_data[0]; @@ -283,7 +283,7 @@ static int sched_clock_suspend(void) return 0; } -static void sched_clock_resume(void) +void sched_clock_resume(void) { struct clock_read_data *rd = &cd.read_data[0]; diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 529143b4c8d2..df401463a191 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -487,6 +487,7 @@ void tick_freeze(void) trace_suspend_resume(TPS("timekeeping_freeze"), smp_processor_id(), true); system_state = SYSTEM_SUSPEND; + sched_clock_suspend(); timekeeping_suspend(); } else { tick_suspend_local(); @@ -510,6 +511,7 @@ void tick_unfreeze(void) if (tick_freeze_depth == num_online_cpus()) { timekeeping_resume(); + sched_clock_resume(); system_state = SYSTEM_RUNNING; trace_suspend_resume(TPS("timekeeping_freeze"), smp_processor_id(), false); diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h index 7a9b4eb7a1d5..141ab3ab0354 100644 --- a/kernel/time/timekeeping.h +++ b/kernel/time/timekeeping.h @@ -14,6 +14,13 @@ extern u64 timekeeping_max_deferment(void); extern void timekeeping_warp_clock(void); extern int timekeeping_suspend(void); extern void timekeeping_resume(void); +#ifdef CONFIG_GENERIC_SCHED_CLOCK +extern int sched_clock_suspend(void); +extern void sched_clock_resume(void); +#else +static inline int sched_clock_suspend(void) { return 0; } +static inline void sched_clock_resume(void) { } +#endif extern void do_timer(unsigned long ticks); extern void update_wall_time(void); -- cgit v1.2.3-55-g7522 From 738a7832d21e3d911fcddab98ce260b79010b461 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 18 Apr 2019 12:18:39 +0200 Subject: signal: use fdget() since we don't allow O_PATH As stated in the original commit for pidfd_send_signal() we don't allow to signal processes through O_PATH file descriptors since it is semantically equivalent to a write on the pidfd. We already correctly error out right now and return EBADF if an O_PATH fd is passed. This is because we use file->f_op to detect whether a pidfd is passed and O_PATH fds have their file->f_op set to empty_fops in do_dentry_open() and thus fail the test. Thus, there is no regression. It's just semantically correct to use fdget() and return an error right from there instead of taking a reference and returning an error later. Signed-off-by: Christian Brauner Acked-by: Oleg Nesterov Cc: Arnd Bergmann Cc: "Eric W. Biederman" Cc: Kees Cook Cc: Thomas Gleixner Cc: Jann Horn Cc: David Howells Cc: "Michael Kerrisk (man-pages)" Cc: Andy Lutomirsky Cc: Andrew Morton Cc: Oleg Nesterov Cc: Aleksa Sarai Cc: Al Viro Signed-off-by: Linus Torvalds --- kernel/signal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/signal.c b/kernel/signal.c index f98448cf2def..227ba170298e 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3581,7 +3581,7 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, if (flags) return -EINVAL; - f = fdget_raw(pidfd); + f = fdget(pidfd); if (!f.file) return -EBADF; -- cgit v1.2.3-55-g7522 From ff8acf929014b7f87315588e0daf8597c8aa9d1c Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 17 Apr 2019 00:21:21 -0700 Subject: arm64: futex: Restore oldval initialization to work around buggy compilers Commit 045afc24124d ("arm64: futex: Fix FUTEX_WAKE_OP atomic ops with non-zero result value") removed oldval's zero initialization in arch_futex_atomic_op_inuser because it is not necessary. Unfortunately, Android's arm64 GCC 4.9.4 [1] does not agree: ../kernel/futex.c: In function 'do_futex': ../kernel/futex.c:1658:17: warning: 'oldval' may be used uninitialized in this function [-Wmaybe-uninitialized] return oldval == cmparg; ^ In file included from ../kernel/futex.c:73:0: ../arch/arm64/include/asm/futex.h:53:6: note: 'oldval' was declared here int oldval, ret, tmp; ^ GCC fails to follow that when ret is non-zero, futex_atomic_op_inuser returns right away, avoiding the uninitialized use that it claims. Restoring the zero initialization works around this issue. [1]: https://android.googlesource.com/platform/prebuilts/gcc/linux-x86/aarch64/aarch64-linux-android-4.9/ Cc: stable@vger.kernel.org Fixes: 045afc24124d ("arm64: futex: Fix FUTEX_WAKE_OP atomic ops with non-zero result value") Reviewed-by: Greg Kroah-Hartman Signed-off-by: Nathan Chancellor Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/futex.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h index e1d95f08f8e1..c7e1a7837706 100644 --- a/arch/arm64/include/asm/futex.h +++ b/arch/arm64/include/asm/futex.h @@ -50,7 +50,7 @@ do { \ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr) { - int oldval, ret, tmp; + int oldval = 0, ret, tmp; u32 __user *uaddr = __uaccess_mask_ptr(_uaddr); pagefault_disable(); -- cgit v1.2.3-55-g7522 From f476b3f809fa02f47af6333ed63715058c3fc348 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Thu, 18 Apr 2019 07:14:13 +0000 Subject: mlxsw: spectrum: Put MC TCs into DWRR mode Both Spectrum-1 and Spectrum-2 chips are currently configured such that pairs of TC n (which is used for UC traffic) and TC n+8 (which is used for MC traffic) are feeding into the same subgroup. Strict prioritization is configured between the two TCs, and by enabling MC-aware mode on the switch, the lower-numbered (UC) TCs are favored over the higher-numbered (MC) TCs. On Spectrum-2 however, there is an issue in configuration of the MC-aware mode. As a result, MC traffic is prioritized over UC traffic. To work around the issue, configure the MC TCs with DWRR mode (while keeping the UC TCs in strict mode). With this patch, the multicast-unicast arbitration results in the same behavior on both Spectrum-1 and Spectrum-2 chips. Fixes: 7b8195306694 ("mlxsw: spectrum: Configure MC-aware mode on mlxsw ports") Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 9eb63300c1d3..3745ea194632 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3316,7 +3316,7 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port) err = mlxsw_sp_port_ets_set(mlxsw_sp_port, MLXSW_REG_QEEC_HIERARCY_TC, i + 8, i, - false, 0); + true, 100); if (err) return err; } -- cgit v1.2.3-55-g7522 From 1ab3030193d25878b3b1409060e1e0a879800c95 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 18 Apr 2019 07:14:14 +0000 Subject: mlxsw: pci: Reincrease PCI reset timeout During driver initialization the driver sends a reset to the device and waits for the firmware to signal that it is ready to continue. Commit d2f372ba0914 ("mlxsw: pci: Increase PCI SW reset timeout") increased the timeout to 13 seconds due to longer PHY calibration in Spectrum-2 compared to Spectrum-1. Recently it became apparent that this timeout is too short and therefore this patch increases it again to a safer limit that will be reduced in the future. Fixes: c3ab435466d5 ("mlxsw: spectrum: Extend to support Spectrum-2 ASIC") Fixes: d2f372ba0914 ("mlxsw: pci: Increase PCI SW reset timeout") Signed-off-by: Ido Schimmel Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/pci_hw.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h index ffee38e36ce8..8648ca171254 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h @@ -27,7 +27,7 @@ #define MLXSW_PCI_SW_RESET 0xF0010 #define MLXSW_PCI_SW_RESET_RST_BIT BIT(0) -#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 13000 +#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 20000 #define MLXSW_PCI_SW_RESET_WAIT_MSECS 100 #define MLXSW_PCI_FW_READY 0xA1844 #define MLXSW_PCI_FW_READY_MASK 0xFFFF -- cgit v1.2.3-55-g7522 From 151f0dddbbfe4c35c9c5b64873115aafd436af9d Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Thu, 18 Apr 2019 07:14:16 +0000 Subject: mlxsw: spectrum: Fix autoneg status in ethtool If link is down and autoneg is set to on/off, the status in ethtool does not change. The reason is when the link is down the function returns with zero before changing autoneg value. Move the checking of link state (up/down) to be performed after setting autoneg value, in order to be sure that autoneg will change in any case. Fixes: 56ade8fe3fe1 ("mlxsw: spectrum: Add initial support for Spectrum ASIC") Signed-off-by: Amit Cohen Signed-off-by: Ido Schimmel Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 3745ea194632..6b8aa3761899 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3126,11 +3126,11 @@ mlxsw_sp_port_set_link_ksettings(struct net_device *dev, if (err) return err; + mlxsw_sp_port->link.autoneg = autoneg; + if (!netif_running(dev)) return 0; - mlxsw_sp_port->link.autoneg = autoneg; - mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false); mlxsw_sp_port_admin_status_set(mlxsw_sp_port, true); -- cgit v1.2.3-55-g7522 From d5f6db353829fe3867bbf9cd73fd8d631e2346f1 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 18 Apr 2019 11:39:18 +0100 Subject: net: ipv6: addrlabel: fix spelling mistake "requewst" -> "request" There is a spelling mistake in a NL_SET_ERR_MSG_MOD error message, fix it. Signed-off-by: Colin Ian King Reviewed-by: Mukesh Ojha Signed-off-by: David S. Miller --- net/ipv6/addrlabel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index d43d076c98f5..1766325423b5 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -476,7 +476,7 @@ static int ip6addrlbl_valid_dump_req(const struct nlmsghdr *nlh, } if (nlmsg_attrlen(nlh, sizeof(*ifal))) { - NL_SET_ERR_MSG_MOD(extack, "Invalid data after header for address label dump requewst"); + NL_SET_ERR_MSG_MOD(extack, "Invalid data after header for address label dump request"); return -EINVAL; } -- cgit v1.2.3-55-g7522 From a7cf2cc3cd3622eae9d5619cdde56b4462398c7f Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 18 Apr 2019 18:03:50 +0100 Subject: firestream: fix spelling mistake "tramsitted" -> "transmitted" There is a spelling mistake in a debug message. Fix it. Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- drivers/atm/firestream.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c index 11e1663bdc4d..b2c06da4f62e 100644 --- a/drivers/atm/firestream.c +++ b/drivers/atm/firestream.c @@ -1646,7 +1646,7 @@ static irqreturn_t fs_irq (int irq, void *dev_id) } if (status & ISR_TBRQ_W) { - fs_dprintk (FS_DEBUG_IRQ, "Data tramsitted!\n"); + fs_dprintk (FS_DEBUG_IRQ, "Data transmitted!\n"); process_txdone_queue (dev, &dev->tx_relq); } -- cgit v1.2.3-55-g7522 From e0c1d14a1a3211dccf0540a6703ffbd5d2a75bdb Mon Sep 17 00:00:00 2001 From: Su Bao Cheng Date: Thu, 18 Apr 2019 11:14:56 +0200 Subject: stmmac: pci: Adjust IOT2000 matching Since there are more IOT2040 variants with identical hardware but different asset tags, the asset tag matching should be adjusted to support them. For the board name "SIMATIC IOT2000", currently there are 2 types of hardware, IOT2020 and IOT2040. The IOT2020 is identified by its unique asset tag. Match on it first. If we then match on the board name only, we will catch all IOT2040 variants. In the future there will be no other devices with the "SIMATIC IOT2000" DMI board name but different hardware. Signed-off-by: Su Bao Cheng Reviewed-by: Jan Kiszka Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index d819e8eaba12..cc1e887e47b5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -159,6 +159,12 @@ static const struct dmi_system_id quark_pci_dmi[] = { }, .driver_data = (void *)&galileo_stmmac_dmi_data, }, + /* + * There are 2 types of SIMATIC IOT2000: IOT20202 and IOT2040. + * The asset tag "6ES7647-0AA00-0YA2" is only for IOT2020 which + * has only one pci network device while other asset tags are + * for IOT2040 which has two. + */ { .matches = { DMI_EXACT_MATCH(DMI_BOARD_NAME, "SIMATIC IOT2000"), @@ -170,8 +176,6 @@ static const struct dmi_system_id quark_pci_dmi[] = { { .matches = { DMI_EXACT_MATCH(DMI_BOARD_NAME, "SIMATIC IOT2000"), - DMI_EXACT_MATCH(DMI_BOARD_ASSET_TAG, - "6ES7647-0AA00-1YA2"), }, .driver_data = (void *)&iot2040_stmmac_dmi_data, }, -- cgit v1.2.3-55-g7522 From 9188d5ca454fd665145904267e726e9e8d122f5c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 17 Apr 2019 10:51:19 -0700 Subject: net/tls: fix refcount adjustment in fallback Unlike atomic_add(), refcount_add() does not deal well with a negative argument. TLS fallback code reallocates the skb and is very likely to shrink the truesize, leading to: [ 189.513254] WARNING: CPU: 5 PID: 0 at lib/refcount.c:81 refcount_add_not_zero_checked+0x15c/0x180 Call Trace: refcount_add_checked+0x6/0x40 tls_enc_skb+0xb93/0x13e0 [tls] Once wmem_allocated count saturates the application can no longer send data on the socket. This is similar to Eric's fixes for GSO, TCP: commit 7ec318feeed1 ("tcp: gso: avoid refcount_t warning from tcp_gso_segment()") and UDP: commit 575b65bc5bff ("udp: avoid refcount_t saturation in __udp_gso_segment()"). Unlike the GSO case, for TLS fallback it's likely that the skb has shrunk, so the "likely" annotation is the other way around (likely branch being "sub"). Fixes: e8f69799810c ("net/tls: Add generic NIC offload infrastructure") Signed-off-by: Jakub Kicinski Reviewed-by: John Hurley Signed-off-by: David S. Miller --- net/tls/tls_device_fallback.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index 54c3a758f2a7..a3ebd4b02714 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -194,6 +194,9 @@ static void update_chksum(struct sk_buff *skb, int headln) static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln) { + struct sock *sk = skb->sk; + int delta; + skb_copy_header(nskb, skb); skb_put(nskb, skb->len); @@ -201,11 +204,15 @@ static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln) update_chksum(nskb, headln); nskb->destructor = skb->destructor; - nskb->sk = skb->sk; + nskb->sk = sk; skb->destructor = NULL; skb->sk = NULL; - refcount_add(nskb->truesize - skb->truesize, - &nskb->sk->sk_wmem_alloc); + + delta = nskb->truesize - skb->truesize; + if (likely(delta < 0)) + WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc)); + else if (delta) + refcount_add(delta, &sk->sk_wmem_alloc); } /* This function may be called after the user socket is already -- cgit v1.2.3-55-g7522 From 0228034d8e5915b98c33db35a98f5e909e848ae9 Mon Sep 17 00:00:00 2001 From: Saurav Kashyap Date: Thu, 18 Apr 2019 03:40:12 -0700 Subject: Revert "scsi: fcoe: clear FC_RP_STARTED flags when receiving a LOGO" This patch clears FC_RP_STARTED flag during logoff, because of this re-login(flogi) didn't happen to the switch. This reverts commit 1550ec458e0cf1a40a170ab1f4c46e3f52860f65. Fixes: 1550ec458e0c ("scsi: fcoe: clear FC_RP_STARTED flags when receiving a LOGO") Cc: # v4.18+ Signed-off-by: Saurav Kashyap Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- drivers/scsi/libfc/fc_rport.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c index dfba4921b265..5bf61431434b 100644 --- a/drivers/scsi/libfc/fc_rport.c +++ b/drivers/scsi/libfc/fc_rport.c @@ -2162,7 +2162,6 @@ static void fc_rport_recv_logo_req(struct fc_lport *lport, struct fc_frame *fp) FC_RPORT_DBG(rdata, "Received LOGO request while in state %s\n", fc_rport_state(rdata)); - rdata->flags &= ~FC_RP_STARTED; fc_rport_enter_delete(rdata, RPORT_EV_STOP); mutex_unlock(&rdata->rp_mutex); kref_put(&rdata->kref, fc_rport_destroy); -- cgit v1.2.3-55-g7522 From 144ec97493af34efdb77c5aba146e9c7de8d0a06 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 18 Apr 2019 18:13:58 +0200 Subject: scsi: aic7xxx: fix EISA support Instead of relying on the now removed NULL argument to pci_alloc_consistent, switch to the generic DMA API, and store the struct device so that we can pass it. Fixes: 4167b2ad5182 ("PCI: Remove NULL device handling from PCI DMA API") Reported-by: Matthew Whitehead Signed-off-by: Christoph Hellwig Tested-by: Matthew Whitehead Signed-off-by: Martin K. Petersen --- drivers/scsi/aic7xxx/aic7770_osm.c | 1 + drivers/scsi/aic7xxx/aic7xxx.h | 1 + drivers/scsi/aic7xxx/aic7xxx_osm.c | 10 ++++------ drivers/scsi/aic7xxx/aic7xxx_osm_pci.c | 1 + 4 files changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/scsi/aic7xxx/aic7770_osm.c b/drivers/scsi/aic7xxx/aic7770_osm.c index 3d401d02c019..bdd177e3d762 100644 --- a/drivers/scsi/aic7xxx/aic7770_osm.c +++ b/drivers/scsi/aic7xxx/aic7770_osm.c @@ -91,6 +91,7 @@ aic7770_probe(struct device *dev) ahc = ahc_alloc(&aic7xxx_driver_template, name); if (ahc == NULL) return (ENOMEM); + ahc->dev = dev; error = aic7770_config(ahc, aic7770_ident_table + edev->id.driver_data, eisaBase); if (error != 0) { diff --git a/drivers/scsi/aic7xxx/aic7xxx.h b/drivers/scsi/aic7xxx/aic7xxx.h index 5614921b4041..88b90f9806c9 100644 --- a/drivers/scsi/aic7xxx/aic7xxx.h +++ b/drivers/scsi/aic7xxx/aic7xxx.h @@ -943,6 +943,7 @@ struct ahc_softc { * Platform specific device information. */ ahc_dev_softc_t dev_softc; + struct device *dev; /* * Bus specific device information. diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.c b/drivers/scsi/aic7xxx/aic7xxx_osm.c index 3c9c17450bb3..d5c4a0d23706 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_osm.c +++ b/drivers/scsi/aic7xxx/aic7xxx_osm.c @@ -860,8 +860,8 @@ int ahc_dmamem_alloc(struct ahc_softc *ahc, bus_dma_tag_t dmat, void** vaddr, int flags, bus_dmamap_t *mapp) { - *vaddr = pci_alloc_consistent(ahc->dev_softc, - dmat->maxsize, mapp); + /* XXX: check if we really need the GFP_ATOMIC and unwind this mess! */ + *vaddr = dma_alloc_coherent(ahc->dev, dmat->maxsize, mapp, GFP_ATOMIC); if (*vaddr == NULL) return ENOMEM; return 0; @@ -871,8 +871,7 @@ void ahc_dmamem_free(struct ahc_softc *ahc, bus_dma_tag_t dmat, void* vaddr, bus_dmamap_t map) { - pci_free_consistent(ahc->dev_softc, dmat->maxsize, - vaddr, map); + dma_free_coherent(ahc->dev, dmat->maxsize, vaddr, map); } int @@ -1123,8 +1122,7 @@ ahc_linux_register_host(struct ahc_softc *ahc, struct scsi_host_template *templa host->transportt = ahc_linux_transport_template; - retval = scsi_add_host(host, - (ahc->dev_softc ? &ahc->dev_softc->dev : NULL)); + retval = scsi_add_host(host, ahc->dev); if (retval) { printk(KERN_WARNING "aic7xxx: scsi_add_host failed\n"); scsi_host_put(host); diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c b/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c index 0fc14dac7070..717d8d1082ce 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c +++ b/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c @@ -250,6 +250,7 @@ ahc_linux_pci_dev_probe(struct pci_dev *pdev, const struct pci_device_id *ent) } } ahc->dev_softc = pci; + ahc->dev = &pci->dev; error = ahc_pci_config(ahc, entry); if (error != 0) { ahc_free(ahc); -- cgit v1.2.3-55-g7522 From c53051128bb0e8754e13345d782ca69e5e1ce36d Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Thu, 18 Apr 2019 10:01:55 +0800 Subject: sc16is7xx: put err_spi and err_i2c into correct #ifdef err_spi is only called within SERIAL_SC16IS7XX_SPI while err_i2c is called inside SERIAL_SC16IS7XX_I2C. So we need to put err_spi and err_i2c into each #ifdef accordingly. This change fixes ("sc16is7xx: move label 'err_spi' to correct section"). Signed-off-by: Guoqing Jiang Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/sc16is7xx.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index 22381a8c72e4..a31db15cd7c0 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -1522,11 +1522,11 @@ static int __init sc16is7xx_init(void) #ifdef CONFIG_SERIAL_SC16IS7XX_SPI err_spi: +#endif #ifdef CONFIG_SERIAL_SC16IS7XX_I2C i2c_del_driver(&sc16is7xx_i2c_uart_driver); -#endif -#endif err_i2c: +#endif uart_unregister_driver(&sc16is7xx_uart); return ret; } -- cgit v1.2.3-55-g7522 From b50776ae011cfd26df3cc2b4af8b2dc3b683e553 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 13 Feb 2019 11:59:48 -0800 Subject: locking/atomics: Don't assume that scripts are executable patch(1) doesn't set the x bit on files. So if someone downloads and applies patch-4.21.xz, their kernel won't build. Fix that by executing /bin/sh. Signed-off-by: Andrew Morton Acked-by: Mark Rutland Cc: Boqun Feng Cc: Linus Torvalds Cc: Peter Zijlstra (Intel) Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Signed-off-by: Ingo Molnar --- scripts/atomic/gen-atomics.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/atomic/gen-atomics.sh b/scripts/atomic/gen-atomics.sh index 27400b0cd732..000dc6437893 100644 --- a/scripts/atomic/gen-atomics.sh +++ b/scripts/atomic/gen-atomics.sh @@ -13,7 +13,7 @@ gen-atomic-long.sh asm-generic/atomic-long.h gen-atomic-fallback.sh linux/atomic-fallback.h EOF while read script header; do - ${ATOMICDIR}/${script} ${ATOMICTBL} > ${LINUXDIR}/include/${header} + /bin/sh ${ATOMICDIR}/${script} ${ATOMICTBL} > ${LINUXDIR}/include/${header} HASH="$(sha1sum ${LINUXDIR}/include/${header})" HASH="${HASH%% *}" printf "// %s\n" "${HASH}" >> ${LINUXDIR}/include/${header} -- cgit v1.2.3-55-g7522 From 3ff9c075cc767b3060bdac12da72fc94dd7da1b8 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Sun, 24 Feb 2019 01:49:52 +0900 Subject: x86/kprobes: Verify stack frame on kretprobe Verify the stack frame pointer on kretprobe trampoline handler, If the stack frame pointer does not match, it skips the wrong entry and tries to find correct one. This can happen if user puts the kretprobe on the function which can be used in the path of ftrace user-function call. Such functions should not be probed, so this adds a warning message that reports which function should be blacklisted. Tested-by: Andrea Righi Signed-off-by: Masami Hiramatsu Acked-by: Steven Rostedt Cc: Linus Torvalds Cc: Mathieu Desnoyers Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/155094059185.6137.15527904013362842072.stgit@devbox Signed-off-by: Ingo Molnar --- arch/x86/kernel/kprobes/core.c | 26 ++++++++++++++++++++++++++ include/linux/kprobes.h | 1 + 2 files changed, 27 insertions(+) diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index a034cb808e7e..18fbe9be2d68 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -569,6 +569,7 @@ void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) unsigned long *sara = stack_addr(regs); ri->ret_addr = (kprobe_opcode_t *) *sara; + ri->fp = sara; /* Replace the return addr with trampoline addr */ *sara = (unsigned long) &kretprobe_trampoline; @@ -759,15 +760,21 @@ static __used void *trampoline_handler(struct pt_regs *regs) unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline; kprobe_opcode_t *correct_ret_addr = NULL; + void *frame_pointer; + bool skipped = false; INIT_HLIST_HEAD(&empty_rp); kretprobe_hash_lock(current, &head, &flags); /* fixup registers */ #ifdef CONFIG_X86_64 regs->cs = __KERNEL_CS; + /* On x86-64, we use pt_regs->sp for return address holder. */ + frame_pointer = ®s->sp; #else regs->cs = __KERNEL_CS | get_kernel_rpl(); regs->gs = 0; + /* On x86-32, we use pt_regs->flags for return address holder. */ + frame_pointer = ®s->flags; #endif regs->ip = trampoline_address; regs->orig_ax = ~0UL; @@ -789,8 +796,25 @@ static __used void *trampoline_handler(struct pt_regs *regs) if (ri->task != current) /* another task is sharing our hash bucket */ continue; + /* + * Return probes must be pushed on this hash list correct + * order (same as return order) so that it can be poped + * correctly. However, if we find it is pushed it incorrect + * order, this means we find a function which should not be + * probed, because the wrong order entry is pushed on the + * path of processing other kretprobe itself. + */ + if (ri->fp != frame_pointer) { + if (!skipped) + pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n"); + skipped = true; + continue; + } orig_ret_address = (unsigned long)ri->ret_addr; + if (skipped) + pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n", + ri->rp->kp.addr); if (orig_ret_address != trampoline_address) /* @@ -808,6 +832,8 @@ static __used void *trampoline_handler(struct pt_regs *regs) if (ri->task != current) /* another task is sharing our hash bucket */ continue; + if (ri->fp != frame_pointer) + continue; orig_ret_address = (unsigned long)ri->ret_addr; if (ri->rp && ri->rp->handler) { diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 201f0f2683f2..9a897256e481 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -173,6 +173,7 @@ struct kretprobe_instance { struct kretprobe *rp; kprobe_opcode_t *ret_addr; struct task_struct *task; + void *fp; char data[0]; }; -- cgit v1.2.3-55-g7522 From fabe38ab6b2bd9418350284c63825f13b8a6abba Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Sun, 24 Feb 2019 01:50:20 +0900 Subject: kprobes: Mark ftrace mcount handler functions nokprobe Mark ftrace mcount handler functions nokprobe since probing on these functions with kretprobe pushes return address incorrectly on kretprobe shadow stack. Reported-by: Francis Deslauriers Tested-by: Andrea Righi Signed-off-by: Masami Hiramatsu Acked-by: Steven Rostedt Acked-by: Steven Rostedt (VMware) Cc: Linus Torvalds Cc: Mathieu Desnoyers Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/155094062044.6137.6419622920568680640.stgit@devbox Signed-off-by: Ingo Molnar --- kernel/trace/ftrace.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 26c8ca9bd06b..b920358dd8f7 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -33,6 +33,7 @@ #include #include #include +#include #include @@ -6246,7 +6247,7 @@ void ftrace_reset_array_ops(struct trace_array *tr) tr->ops->func = ftrace_stub; } -static inline void +static nokprobe_inline void __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ignored, struct pt_regs *regs) { @@ -6306,11 +6307,13 @@ static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, { __ftrace_ops_list_func(ip, parent_ip, NULL, regs); } +NOKPROBE_SYMBOL(ftrace_ops_list_func); #else static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip) { __ftrace_ops_list_func(ip, parent_ip, NULL, NULL); } +NOKPROBE_SYMBOL(ftrace_ops_no_ops); #endif /* @@ -6337,6 +6340,7 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip, preempt_enable_notrace(); trace_clear_recursion(bit); } +NOKPROBE_SYMBOL(ftrace_ops_assist_func); /** * ftrace_ops_get_func - get the function a trampoline should call -- cgit v1.2.3-55-g7522 From b191fa96ea6dc00d331dcc28c1f7db5e075693a0 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Sun, 24 Feb 2019 01:50:49 +0900 Subject: x86/kprobes: Avoid kretprobe recursion bug Avoid kretprobe recursion loop bg by setting a dummy kprobes to current_kprobe per-CPU variable. This bug has been introduced with the asm-coded trampoline code, since previously it used another kprobe for hooking the function return placeholder (which only has a nop) and trampoline handler was called from that kprobe. This revives the old lost kprobe again. With this fix, we don't see deadlock anymore. And you can see that all inner-called kretprobe are skipped. event_1 235 0 event_2 19375 19612 The 1st column is recorded count and the 2nd is missed count. Above shows (event_1 rec) + (event_2 rec) ~= (event_2 missed) (some difference are here because the counter is racy) Reported-by: Andrea Righi Tested-by: Andrea Righi Signed-off-by: Masami Hiramatsu Acked-by: Steven Rostedt Cc: Linus Torvalds Cc: Mathieu Desnoyers Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: stable@vger.kernel.org Fixes: c9becf58d935 ("[PATCH] kretprobe: kretprobe-booster") Link: http://lkml.kernel.org/r/155094064889.6137.972160690963039.stgit@devbox Signed-off-by: Ingo Molnar --- arch/x86/kernel/kprobes/core.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 18fbe9be2d68..fed46ddb1eef 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -749,11 +749,16 @@ asm( NOKPROBE_SYMBOL(kretprobe_trampoline); STACK_FRAME_NON_STANDARD(kretprobe_trampoline); +static struct kprobe kretprobe_kprobe = { + .addr = (void *)kretprobe_trampoline, +}; + /* * Called from kretprobe_trampoline */ static __used void *trampoline_handler(struct pt_regs *regs) { + struct kprobe_ctlblk *kcb; struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; struct hlist_node *tmp; @@ -763,6 +768,17 @@ static __used void *trampoline_handler(struct pt_regs *regs) void *frame_pointer; bool skipped = false; + preempt_disable(); + + /* + * Set a dummy kprobe for avoiding kretprobe recursion. + * Since kretprobe never run in kprobe handler, kprobe must not + * be running at this point. + */ + kcb = get_kprobe_ctlblk(); + __this_cpu_write(current_kprobe, &kretprobe_kprobe); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + INIT_HLIST_HEAD(&empty_rp); kretprobe_hash_lock(current, &head, &flags); /* fixup registers */ @@ -838,10 +854,9 @@ static __used void *trampoline_handler(struct pt_regs *regs) orig_ret_address = (unsigned long)ri->ret_addr; if (ri->rp && ri->rp->handler) { __this_cpu_write(current_kprobe, &ri->rp->kp); - get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE; ri->ret_addr = correct_ret_addr; ri->rp->handler(ri, regs); - __this_cpu_write(current_kprobe, NULL); + __this_cpu_write(current_kprobe, &kretprobe_kprobe); } recycle_rp_inst(ri, &empty_rp); @@ -857,6 +872,9 @@ static __used void *trampoline_handler(struct pt_regs *regs) kretprobe_hash_unlock(current, &flags); + __this_cpu_write(current_kprobe, NULL); + preempt_enable(); + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); -- cgit v1.2.3-55-g7522 From 1de7edbb59c8f1b46071f66c5c97b8a59569eb51 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Fri, 29 Mar 2019 17:47:43 -0700 Subject: x86/cpu/bugs: Use __initconst for 'const' init data Some of the recently added const tables use __initdata which causes section attribute conflicts. Use __initconst instead. Fixes: fa1202ef2243 ("x86/speculation: Add command line control") Signed-off-by: Andi Kleen Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20190330004743.29541-9-andi@firstfloor.org --- arch/x86/kernel/cpu/bugs.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 2da82eff0eb4..b91b3bfa5cfb 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -275,7 +275,7 @@ static const struct { const char *option; enum spectre_v2_user_cmd cmd; bool secure; -} v2_user_options[] __initdata = { +} v2_user_options[] __initconst = { { "auto", SPECTRE_V2_USER_CMD_AUTO, false }, { "off", SPECTRE_V2_USER_CMD_NONE, false }, { "on", SPECTRE_V2_USER_CMD_FORCE, true }, @@ -419,7 +419,7 @@ static const struct { const char *option; enum spectre_v2_mitigation_cmd cmd; bool secure; -} mitigation_options[] __initdata = { +} mitigation_options[] __initconst = { { "off", SPECTRE_V2_CMD_NONE, false }, { "on", SPECTRE_V2_CMD_FORCE, true }, { "retpoline", SPECTRE_V2_CMD_RETPOLINE, false }, @@ -658,7 +658,7 @@ static const char * const ssb_strings[] = { static const struct { const char *option; enum ssb_mitigation_cmd cmd; -} ssb_mitigation_options[] __initdata = { +} ssb_mitigation_options[] __initconst = { { "auto", SPEC_STORE_BYPASS_CMD_AUTO }, /* Platform decides */ { "on", SPEC_STORE_BYPASS_CMD_ON }, /* Disable Speculative Store Bypass */ { "off", SPEC_STORE_BYPASS_CMD_NONE }, /* Don't touch Speculative Store Bypass */ -- cgit v1.2.3-55-g7522 From 1a62b18d51e5c5ecc0345c85bb9fef870ab721ed Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 18 Apr 2019 17:49:55 -0700 Subject: slab: store tagged freelist for off-slab slabmgmt Commit 51dedad06b5f ("kasan, slab: make freelist stored without tags") calls kasan_reset_tag() for off-slab slab management object leading to freelist being stored non-tagged. However, cache_grow_begin() calls alloc_slabmgmt() which calls kmem_cache_alloc_node() assigns a tag for the address and stores it in the shadow address. As the result, it causes endless errors below during boot due to drain_freelist() -> slab_destroy() -> kasan_slab_free() which compares already untagged freelist against the stored tag in the shadow address. Since off-slab slab management object freelist is such a special case, just store it tagged. Non-off-slab management object freelist is still stored untagged which has not been assigned a tag and should not cause any other troubles with this inconsistency. BUG: KASAN: double-free or invalid-free in slab_destroy+0x84/0x88 Pointer tag: [ff], memory tag: [99] CPU: 0 PID: 1376 Comm: kworker/0:4 Tainted: G W 5.1.0-rc3+ #8 Hardware name: HPE Apollo 70 /C01_APACHE_MB , BIOS L50_5.13_1.0.6 07/10/2018 Workqueue: cgroup_destroy css_killed_work_fn Call trace: print_address_description+0x74/0x2a4 kasan_report_invalid_free+0x80/0xc0 __kasan_slab_free+0x204/0x208 kasan_slab_free+0xc/0x18 kmem_cache_free+0xe4/0x254 slab_destroy+0x84/0x88 drain_freelist+0xd0/0x104 __kmem_cache_shrink+0x1ac/0x224 __kmemcg_cache_deactivate+0x1c/0x28 memcg_deactivate_kmem_caches+0xa0/0xe8 memcg_offline_kmem+0x8c/0x3d4 mem_cgroup_css_offline+0x24c/0x290 css_killed_work_fn+0x154/0x618 process_one_work+0x9cc/0x183c worker_thread+0x9b0/0xe38 kthread+0x374/0x390 ret_from_fork+0x10/0x18 Allocated by task 1625: __kasan_kmalloc+0x168/0x240 kasan_slab_alloc+0x18/0x20 kmem_cache_alloc_node+0x1f8/0x3a0 cache_grow_begin+0x4fc/0xa24 cache_alloc_refill+0x2f8/0x3e8 kmem_cache_alloc+0x1bc/0x3bc sock_alloc_inode+0x58/0x334 alloc_inode+0xb8/0x164 new_inode_pseudo+0x20/0xec sock_alloc+0x74/0x284 __sock_create+0xb0/0x58c sock_create+0x98/0xb8 __sys_socket+0x60/0x138 __arm64_sys_socket+0xa4/0x110 el0_svc_handler+0x2c0/0x47c el0_svc+0x8/0xc Freed by task 1625: __kasan_slab_free+0x114/0x208 kasan_slab_free+0xc/0x18 kfree+0x1a8/0x1e0 single_release+0x7c/0x9c close_pdeo+0x13c/0x43c proc_reg_release+0xec/0x108 __fput+0x2f8/0x784 ____fput+0x1c/0x28 task_work_run+0xc0/0x1b0 do_notify_resume+0xb44/0x1278 work_pending+0x8/0x10 The buggy address belongs to the object at ffff809681b89e00 which belongs to the cache kmalloc-128 of size 128 The buggy address is located 0 bytes inside of 128-byte region [ffff809681b89e00, ffff809681b89e80) The buggy address belongs to the page: page:ffff7fe025a06e00 count:1 mapcount:0 mapping:01ff80082000fb00 index:0xffff809681b8fe04 flags: 0x17ffffffc000200(slab) raw: 017ffffffc000200 ffff7fe025a06d08 ffff7fe022ef7b88 01ff80082000fb00 raw: ffff809681b8fe04 ffff809681b80000 00000001000000e0 0000000000000000 page dumped because: kasan: bad access detected page allocated via order 0, migratetype Unmovable, gfp_mask 0x2420c0(__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_COMP|__GFP_THISNODE) prep_new_page+0x4e0/0x5e0 get_page_from_freelist+0x4ce8/0x50d4 __alloc_pages_nodemask+0x738/0x38b8 cache_grow_begin+0xd8/0xa24 ____cache_alloc_node+0x14c/0x268 __kmalloc+0x1c8/0x3fc ftrace_free_mem+0x408/0x1284 ftrace_free_init_mem+0x20/0x28 kernel_init+0x24/0x548 ret_from_fork+0x10/0x18 Memory state around the buggy address: ffff809681b89c00: fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe ffff809681b89d00: fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe >ffff809681b89e00: 99 99 99 99 99 99 99 99 fe fe fe fe fe fe fe fe ^ ffff809681b89f00: 43 43 43 43 43 fe fe fe fe fe fe fe fe fe fe fe ffff809681b8a000: 6d fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe Link: http://lkml.kernel.org/r/20190403022858.97584-1-cai@lca.pw Fixes: 51dedad06b5f ("kasan, slab: make freelist stored without tags") Signed-off-by: Qian Cai Reviewed-by: Andrey Konovalov Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slab.c | 1 - 1 file changed, 1 deletion(-) diff --git a/mm/slab.c b/mm/slab.c index 47a380a486ee..9142ee992493 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2374,7 +2374,6 @@ static void *alloc_slabmgmt(struct kmem_cache *cachep, /* Slab management obj is off-slab. */ freelist = kmem_cache_alloc_node(cachep->freelist_cache, local_flags, nodeid); - freelist = kasan_reset_tag(freelist); if (!freelist) return NULL; } else { -- cgit v1.2.3-55-g7522 From 87039546544479d4bedb19d0ea525270c43c1c9b Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 18 Apr 2019 17:49:58 -0700 Subject: mm: swapoff: shmem_find_swap_entries() filter out other types Swapfile "type" was passed all the way down to shmem_unuse_inode(), but then forgotten from shmem_find_swap_entries(): with the result that removing one swapfile would try to free up all the swap from shmem - no problem when only one swapfile anyway, but counter-productive when more, causing swapoff to be unnecessarily OOM-killed when it should succeed. Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1904081254470.1523@eggly.anvils Fixes: b56a2d8af914 ("mm: rid swapoff of quadratic complexity") Signed-off-by: Hugh Dickins Cc: Konstantin Khlebnikov Cc: "Alex Xu (Hello71)" Cc: Vineeth Pillai Cc: Kelley Nielsen Cc: Rik van Riel Cc: Huang Ying Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/shmem.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/mm/shmem.c b/mm/shmem.c index b3db3779a30a..859e8628071f 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1099,10 +1099,11 @@ extern struct swap_info_struct *swap_info[]; static int shmem_find_swap_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices, - bool frontswap) + unsigned int type, bool frontswap) { XA_STATE(xas, &mapping->i_pages, start); struct page *page; + swp_entry_t entry; unsigned int ret = 0; if (!nr_entries) @@ -1116,13 +1117,12 @@ static int shmem_find_swap_entries(struct address_space *mapping, if (!xa_is_value(page)) continue; - if (frontswap) { - swp_entry_t entry = radix_to_swp_entry(page); - - if (!frontswap_test(swap_info[swp_type(entry)], - swp_offset(entry))) - continue; - } + entry = radix_to_swp_entry(page); + if (swp_type(entry) != type) + continue; + if (frontswap && + !frontswap_test(swap_info[type], swp_offset(entry))) + continue; indices[ret] = xas.xa_index; entries[ret] = page; @@ -1194,7 +1194,7 @@ static int shmem_unuse_inode(struct inode *inode, unsigned int type, pvec.nr = shmem_find_swap_entries(mapping, start, nr_entries, pvec.pages, indices, - frontswap); + type, frontswap); if (pvec.nr == 0) { ret = 0; break; -- cgit v1.2.3-55-g7522 From dd862deb151aad2548e72b077a82ad3aa91b715f Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 18 Apr 2019 17:50:02 -0700 Subject: mm: swapoff: remove too limiting SWAP_UNUSE_MAX_TRIES SWAP_UNUSE_MAX_TRIES 3 appeared to work well in earlier testing, but further testing has proved it to be a source of unnecessary swapoff EBUSY failures (which can then be followed by unmount EBUSY failures). When mmget_not_zero() or shmem's igrab() fails, there is an mm exiting or inode being evicted, freeing up swap independent of try_to_unuse(). Those typically completed much sooner than the old quadratic swapoff, but now it's more common that swapoff may need to wait for them. It's possible to move those cases from init_mm.mmlist and shmem_swaplist to separate "exiting" swaplists, and try_to_unuse() then wait for those lists to be emptied; but we've not bothered with that in the past, and don't want to risk missing some other forgotten case. So just revert to cycling around until the swap is gone, without any retries limit. Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1904081256170.1523@eggly.anvils Fixes: b56a2d8af914 ("mm: rid swapoff of quadratic complexity") Signed-off-by: Hugh Dickins Cc: "Alex Xu (Hello71)" Cc: Huang Ying Cc: Kelley Nielsen Cc: Konstantin Khlebnikov Cc: Rik van Riel Cc: Vineeth Pillai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swapfile.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/mm/swapfile.c b/mm/swapfile.c index 2b8d9c3fbb47..bf4ef2e40f23 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2023,7 +2023,6 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, * If the boolean frontswap is true, only unuse pages_to_unuse pages; * pages_to_unuse==0 means all pages; ignored if frontswap is false */ -#define SWAP_UNUSE_MAX_TRIES 3 int try_to_unuse(unsigned int type, bool frontswap, unsigned long pages_to_unuse) { @@ -2035,7 +2034,6 @@ int try_to_unuse(unsigned int type, bool frontswap, struct page *page; swp_entry_t entry; unsigned int i; - int retries = 0; if (!si->inuse_pages) return 0; @@ -2117,14 +2115,16 @@ retry: * If yes, we would need to do retry the unuse logic again. * Under global memory pressure, swap entries can be reinserted back * into process space after the mmlist loop above passes over them. - * Its not worth continuosuly retrying to unuse the swap in this case. - * So we try SWAP_UNUSE_MAX_TRIES times. + * + * Limit the number of retries? No: when shmem_unuse()'s igrab() fails, + * a shmem inode using swap is being evicted; and when mmget_not_zero() + * above fails, that mm is likely to be freeing swap from exit_mmap(). + * Both proceed at their own independent pace: we could move them to + * separate lists, and wait for those lists to be emptied; but it's + * easier and more robust (though cpu-intensive) just to keep retrying. */ - if (++retries >= SWAP_UNUSE_MAX_TRIES) - retval = -EBUSY; - else if (si->inuse_pages) + if (si->inuse_pages) goto retry; - out: return (retval == FRONTSWAP_PAGES_UNUSED) ? 0 : retval; } -- cgit v1.2.3-55-g7522 From 64165b1affc5bc16231ac971e66aae7d68d57f2c Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 18 Apr 2019 17:50:09 -0700 Subject: mm: swapoff: take notice of completion sooner The old try_to_unuse() implementation was driven by find_next_to_unuse(), which terminated as soon as all the swap had been freed. Add inuse_pages checks now (alongside signal_pending()) to stop scanning mms and swap_map once finished. The same ought to be done in shmem_unuse() too, but never was before, and needs a different interface: so leave it as is for now. Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1904081258200.1523@eggly.anvils Fixes: b56a2d8af914 ("mm: rid swapoff of quadratic complexity") Signed-off-by: Hugh Dickins Cc: "Alex Xu (Hello71)" Cc: Huang Ying Cc: Kelley Nielsen Cc: Konstantin Khlebnikov Cc: Rik van Riel Cc: Vineeth Pillai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swapfile.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/mm/swapfile.c b/mm/swapfile.c index bf4ef2e40f23..71383625a582 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2051,11 +2051,9 @@ retry: spin_lock(&mmlist_lock); p = &init_mm.mmlist; - while ((p = p->next) != &init_mm.mmlist) { - if (signal_pending(current)) { - retval = -EINTR; - break; - } + while (si->inuse_pages && + !signal_pending(current) && + (p = p->next) != &init_mm.mmlist) { mm = list_entry(p, struct mm_struct, mmlist); if (!mmget_not_zero(mm)) @@ -2082,7 +2080,9 @@ retry: mmput(prev_mm); i = 0; - while ((i = find_next_to_unuse(si, i, frontswap)) != 0) { + while (si->inuse_pages && + !signal_pending(current) && + (i = find_next_to_unuse(si, i, frontswap)) != 0) { entry = swp_entry(type, i); page = find_get_page(swap_address_space(entry), i); @@ -2123,8 +2123,11 @@ retry: * separate lists, and wait for those lists to be emptied; but it's * easier and more robust (though cpu-intensive) just to keep retrying. */ - if (si->inuse_pages) - goto retry; + if (si->inuse_pages) { + if (!signal_pending(current)) + goto retry; + retval = -EINTR; + } out: return (retval == FRONTSWAP_PAGES_UNUSED) ? 0 : retval; } -- cgit v1.2.3-55-g7522 From af53d3e9e04024885de5b4fda51e5fa362ae2bd8 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 18 Apr 2019 17:50:13 -0700 Subject: mm: swapoff: shmem_unuse() stop eviction without igrab() The igrab() in shmem_unuse() looks good, but we forgot that it gives no protection against concurrent unmounting: a point made by Konstantin Khlebnikov eight years ago, and then fixed in 2.6.39 by 778dd893ae78 ("tmpfs: fix race between umount and swapoff"). The current 5.1-rc swapoff is liable to hit "VFS: Busy inodes after unmount of tmpfs. Self-destruct in 5 seconds. Have a nice day..." followed by GPF. Once again, give up on using igrab(); but don't go back to making such heavy-handed use of shmem_swaplist_mutex as last time: that would spoil the new design, and I expect could deadlock inside shmem_swapin_page(). Instead, shmem_unuse() just raise a "stop_eviction" count in the shmem- specific inode, and shmem_evict_inode() wait for that to go down to 0. Call it "stop_eviction" rather than "swapoff_busy" because it can be put to use for others later (huge tmpfs patches expect to use it). That simplifies shmem_unuse(), protecting it from both unlink and unmount; and in practice lets it locate all the swap in its first try. But do not rely on that: there's still a theoretical case, when shmem_writepage() might have been preempted after its get_swap_page(), before making the swap entry visible to swapoff. [hughd@google.com: remove incorrect list_del()] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1904091133570.1898@eggly.anvils Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1904081259400.1523@eggly.anvils Fixes: b56a2d8af914 ("mm: rid swapoff of quadratic complexity") Signed-off-by: Hugh Dickins Cc: "Alex Xu (Hello71)" Cc: Huang Ying Cc: Kelley Nielsen Cc: Konstantin Khlebnikov Cc: Rik van Riel Cc: Vineeth Pillai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 1 + mm/shmem.c | 40 ++++++++++++++++++---------------------- mm/swapfile.c | 11 +++++------ 3 files changed, 24 insertions(+), 28 deletions(-) diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index f3fb1edb3526..20d815a33145 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -21,6 +21,7 @@ struct shmem_inode_info { struct list_head swaplist; /* chain of maybes on swap */ struct shared_policy policy; /* NUMA memory alloc policy */ struct simple_xattrs xattrs; /* list of xattrs */ + atomic_t stop_eviction; /* hold when working on inode */ struct inode vfs_inode; }; diff --git a/mm/shmem.c b/mm/shmem.c index 859e8628071f..2275a0ff7c30 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1081,9 +1081,14 @@ static void shmem_evict_inode(struct inode *inode) } spin_unlock(&sbinfo->shrinklist_lock); } - if (!list_empty(&info->swaplist)) { + while (!list_empty(&info->swaplist)) { + /* Wait while shmem_unuse() is scanning this inode... */ + wait_var_event(&info->stop_eviction, + !atomic_read(&info->stop_eviction)); mutex_lock(&shmem_swaplist_mutex); - list_del_init(&info->swaplist); + /* ...but beware of the race if we peeked too early */ + if (!atomic_read(&info->stop_eviction)) + list_del_init(&info->swaplist); mutex_unlock(&shmem_swaplist_mutex); } } @@ -1227,36 +1232,27 @@ int shmem_unuse(unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { struct shmem_inode_info *info, *next; - struct inode *inode; - struct inode *prev_inode = NULL; int error = 0; if (list_empty(&shmem_swaplist)) return 0; mutex_lock(&shmem_swaplist_mutex); - - /* - * The extra refcount on the inode is necessary to safely dereference - * p->next after re-acquiring the lock. New shmem inodes with swap - * get added to the end of the list and we will scan them all. - */ list_for_each_entry_safe(info, next, &shmem_swaplist, swaplist) { if (!info->swapped) { list_del_init(&info->swaplist); continue; } - - inode = igrab(&info->vfs_inode); - if (!inode) - continue; - + /* + * Drop the swaplist mutex while searching the inode for swap; + * but before doing so, make sure shmem_evict_inode() will not + * remove placeholder inode from swaplist, nor let it be freed + * (igrab() would protect from unlink, but not from unmount). + */ + atomic_inc(&info->stop_eviction); mutex_unlock(&shmem_swaplist_mutex); - if (prev_inode) - iput(prev_inode); - prev_inode = inode; - error = shmem_unuse_inode(inode, type, frontswap, + error = shmem_unuse_inode(&info->vfs_inode, type, frontswap, fs_pages_to_unuse); cond_resched(); @@ -1264,14 +1260,13 @@ int shmem_unuse(unsigned int type, bool frontswap, next = list_next_entry(info, swaplist); if (!info->swapped) list_del_init(&info->swaplist); + if (atomic_dec_and_test(&info->stop_eviction)) + wake_up_var(&info->stop_eviction); if (error) break; } mutex_unlock(&shmem_swaplist_mutex); - if (prev_inode) - iput(prev_inode); - return error; } @@ -2238,6 +2233,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode info = SHMEM_I(inode); memset(info, 0, (char *)inode - (char *)info); spin_lock_init(&info->lock); + atomic_set(&info->stop_eviction, 0); info->seals = F_SEAL_SEAL; info->flags = flags & VM_NORESERVE; INIT_LIST_HEAD(&info->shrinklist); diff --git a/mm/swapfile.c b/mm/swapfile.c index 71383625a582..cf63b5f01adf 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2116,12 +2116,11 @@ retry: * Under global memory pressure, swap entries can be reinserted back * into process space after the mmlist loop above passes over them. * - * Limit the number of retries? No: when shmem_unuse()'s igrab() fails, - * a shmem inode using swap is being evicted; and when mmget_not_zero() - * above fails, that mm is likely to be freeing swap from exit_mmap(). - * Both proceed at their own independent pace: we could move them to - * separate lists, and wait for those lists to be emptied; but it's - * easier and more robust (though cpu-intensive) just to keep retrying. + * Limit the number of retries? No: when mmget_not_zero() above fails, + * that mm is likely to be freeing swap from exit_mmap(), which proceeds + * at its own independent pace; and even shmem_writepage() could have + * been preempted after get_swap_page(), temporarily hiding that swap. + * It's easy and robust (though cpu-intensive) just to keep retrying. */ if (si->inuse_pages) { if (!signal_pending(current)) -- cgit v1.2.3-55-g7522 From 37803841c92d7b327147e0b1be3436423189e1cf Mon Sep 17 00:00:00 2001 From: zhong jiang Date: Thu, 18 Apr 2019 17:50:16 -0700 Subject: mm/memory_hotplug: do not unlock after failing to take the device_hotplug_lock When adding memory by probing a memory block in the sysfs interface, there is an obvious issue where we will unlock the device_hotplug_lock when we failed to takes it. That issue was introduced in 8df1d0e4a265 ("mm/memory_hotplug: make add_memory() take the device_hotplug_lock"). We should drop out in time when failing to take the device_hotplug_lock. Link: http://lkml.kernel.org/r/1554696437-9593-1-git-send-email-zhongjiang@huawei.com Fixes: 8df1d0e4a265 ("mm/memory_hotplug: make add_memory() take the device_hotplug_lock") Signed-off-by: zhong jiang Reported-by: Yang yingliang Acked-by: Michal Hocko Reviewed-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/memory.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/base/memory.c b/drivers/base/memory.c index cb8347500ce2..e49028a60429 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -506,7 +506,7 @@ static ssize_t probe_store(struct device *dev, struct device_attribute *attr, ret = lock_device_hotplug_sysfs(); if (ret) - goto out; + return ret; nid = memory_add_physaddr_to_nid(phys_addr); ret = __add_memory(nid, phys_addr, -- cgit v1.2.3-55-g7522 From e8277b3b52240ec1caad8e6df278863e4bf42eac Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Thu, 18 Apr 2019 17:50:20 -0700 Subject: mm/vmstat.c: fix /proc/vmstat format for CONFIG_DEBUG_TLBFLUSH=y CONFIG_SMP=n Commit 58bc4c34d249 ("mm/vmstat.c: skip NR_TLB_REMOTE_FLUSH* properly") depends on skipping vmstat entries with empty name introduced in 7aaf77272358 ("mm: don't show nr_indirectly_reclaimable in /proc/vmstat") but reverted in b29940c1abd7 ("mm: rename and change semantics of nr_indirectly_reclaimable_bytes"). So skipping no longer works and /proc/vmstat has misformatted lines " 0". This patch simply shows debug counters "nr_tlb_remote_*" for UP. Link: http://lkml.kernel.org/r/155481488468.467.4295519102880913454.stgit@buzz Fixes: 58bc4c34d249 ("mm/vmstat.c: skip NR_TLB_REMOTE_FLUSH* properly") Signed-off-by: Konstantin Khlebnikov Acked-by: Vlastimil Babka Cc: Roman Gushchin Cc: Jann Horn Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmstat.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/mm/vmstat.c b/mm/vmstat.c index 36b56f858f0f..a7d493366a65 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1274,13 +1274,8 @@ const char * const vmstat_text[] = { #endif #endif /* CONFIG_MEMORY_BALLOON */ #ifdef CONFIG_DEBUG_TLBFLUSH -#ifdef CONFIG_SMP "nr_tlb_remote_flush", "nr_tlb_remote_flush_received", -#else - "", /* nr_tlb_remote_flush */ - "", /* nr_tlb_remote_flush_received */ -#endif /* CONFIG_SMP */ "nr_tlb_local_flush_all", "nr_tlb_local_flush_one", #endif /* CONFIG_DEBUG_TLBFLUSH */ -- cgit v1.2.3-55-g7522 From 8cd40d1d41ffc305d9aed77937896e1712b2490c Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 18 Apr 2019 17:50:23 -0700 Subject: proc: fix map_files test on F29 F29 bans mapping first 64KB even for root making test fail. Iterate from address 0 until mmap() works. Gentoo (root): openat(AT_FDCWD, "/dev/zero", O_RDONLY) = 3 mmap(NULL, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = 0 Gentoo (non-root): openat(AT_FDCWD, "/dev/zero", O_RDONLY) = 3 mmap(NULL, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EPERM (Operation not permitted) mmap(0x1000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = 0x1000 F29 (root): openat(AT_FDCWD, "/dev/zero", O_RDONLY) = 3 mmap(NULL, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0x1000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0x2000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0x3000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0x4000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0x5000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0x6000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0x7000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0x8000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0x9000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0xa000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0xb000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0xc000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0xd000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0xe000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0xf000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = -1 EACCES (Permission denied) mmap(0x10000, 4096, PROT_NONE, MAP_PRIVATE|MAP_FIXED, 3, 0) = 0x10000 Now all proc tests succeed on F29 if run as root, at last! Link: http://lkml.kernel.org/r/20190414123612.GB12971@avx2 Signed-off-by: Alexey Dobriyan Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- .../testing/selftests/proc/proc-self-map-files-002.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/proc/proc-self-map-files-002.c b/tools/testing/selftests/proc/proc-self-map-files-002.c index 762cb01f2ca7..47b7473dedef 100644 --- a/tools/testing/selftests/proc/proc-self-map-files-002.c +++ b/tools/testing/selftests/proc/proc-self-map-files-002.c @@ -46,12 +46,9 @@ static void fail(const char *fmt, unsigned long a, unsigned long b) int main(void) { - const unsigned int PAGE_SIZE = sysconf(_SC_PAGESIZE); -#ifdef __arm__ - unsigned long va = 2 * PAGE_SIZE; -#else - unsigned long va = 0; -#endif + const int PAGE_SIZE = sysconf(_SC_PAGESIZE); + const unsigned long va_max = 1UL << 32; + unsigned long va; void *p; int fd; unsigned long a, b; @@ -60,10 +57,13 @@ int main(void) if (fd == -1) return 1; - p = mmap((void *)va, PAGE_SIZE, PROT_NONE, MAP_PRIVATE|MAP_FILE|MAP_FIXED, fd, 0); - if (p == MAP_FAILED) { - if (errno == EPERM) - return 4; + for (va = 0; va < va_max; va += PAGE_SIZE) { + p = mmap((void *)va, PAGE_SIZE, PROT_NONE, MAP_PRIVATE|MAP_FILE|MAP_FIXED, fd, 0); + if (p == (void *)va) + break; + } + if (va == va_max) { + fprintf(stderr, "error: mmap doesn't like you\n"); return 1; } -- cgit v1.2.3-55-g7522 From 68545aa1cda847c4fdda7e49331807f99f799838 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 18 Apr 2019 17:50:27 -0700 Subject: proc: fixup proc-pid-vm test Silly sizeof(pointer) vs sizeof(uint8_t[]) bug. Link: http://lkml.kernel.org/r/20190414123009.GA12971@avx2 Fixes: e483b0208784 ("proc: test /proc/*/maps, smaps, smaps_rollup, statm") Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/selftests/proc/proc-pid-vm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/proc/proc-pid-vm.c b/tools/testing/selftests/proc/proc-pid-vm.c index 7202bbac976e..853aa164a401 100644 --- a/tools/testing/selftests/proc/proc-pid-vm.c +++ b/tools/testing/selftests/proc/proc-pid-vm.c @@ -187,8 +187,8 @@ static int make_exe(const uint8_t *payload, size_t len) ph.p_offset = 0; ph.p_vaddr = VADDR; ph.p_paddr = 0; - ph.p_filesz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + sizeof(payload); - ph.p_memsz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + sizeof(payload); + ph.p_filesz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + len; + ph.p_memsz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + len; ph.p_align = 4096; fd = openat(AT_FDCWD, "/tmp", O_WRONLY|O_EXCL|O_TMPFILE, 0700); -- cgit v1.2.3-55-g7522 From 1a9f219157b22d0ffb340a9c5f431afd02cd2cf3 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 18 Apr 2019 17:50:30 -0700 Subject: mm/hotplug: treat CMA pages as unmovable has_unmovable_pages() is used by allocating CMA and gigantic pages as well as the memory hotplug. The later doesn't know how to offline CMA pool properly now, but if an unused (free) CMA page is encountered, then has_unmovable_pages() happily considers it as a free memory and propagates this up the call chain. Memory offlining code then frees the page without a proper CMA tear down which leads to an accounting issues. Moreover if the same memory range is onlined again then the memory never gets back to the CMA pool. State after memory offline: # grep cma /proc/vmstat nr_free_cma 205824 # cat /sys/kernel/debug/cma/cma-kvm_cma/count 209920 Also, kmemleak still think those memory address are reserved below but have already been used by the buddy allocator after onlining. This patch fixes the situation by treating CMA pageblocks as unmovable except when has_unmovable_pages() is called as part of CMA allocation. Offlined Pages 4096 kmemleak: Cannot insert 0xc000201f7d040008 into the object search tree (overlaps existing) Call Trace: dump_stack+0xb0/0xf4 (unreliable) create_object+0x344/0x380 __kmalloc_node+0x3ec/0x860 kvmalloc_node+0x58/0x110 seq_read+0x41c/0x620 __vfs_read+0x3c/0x70 vfs_read+0xbc/0x1a0 ksys_read+0x7c/0x140 system_call+0x5c/0x70 kmemleak: Kernel memory leak detector disabled kmemleak: Object 0xc000201cc8000000 (size 13757317120): kmemleak: comm "swapper/0", pid 0, jiffies 4294937297 kmemleak: min_count = -1 kmemleak: count = 0 kmemleak: flags = 0x5 kmemleak: checksum = 0 kmemleak: backtrace: cma_declare_contiguous+0x2a4/0x3b0 kvm_cma_reserve+0x11c/0x134 setup_arch+0x300/0x3f8 start_kernel+0x9c/0x6e8 start_here_common+0x1c/0x4b0 kmemleak: Automatic memory scanning thread ended [cai@lca.pw: use is_migrate_cma_page() and update commit log] Link: http://lkml.kernel.org/r/20190416170510.20048-1-cai@lca.pw Link: http://lkml.kernel.org/r/20190413002623.8967-1-cai@lca.pw Signed-off-by: Qian Cai Acked-by: Michal Hocko Acked-by: Vlastimil Babka Reviewed-by: Oscar Salvador Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 30 ++++++++++++++++++------------ 1 file changed, 18 insertions(+), 12 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d96ca5bc555b..c6ce20aaf80b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8005,7 +8005,10 @@ void *__init alloc_large_system_hash(const char *tablename, bool has_unmovable_pages(struct zone *zone, struct page *page, int count, int migratetype, int flags) { - unsigned long pfn, iter, found; + unsigned long found; + unsigned long iter = 0; + unsigned long pfn = page_to_pfn(page); + const char *reason = "unmovable page"; /* * TODO we could make this much more efficient by not checking every @@ -8015,17 +8018,20 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, * can still lead to having bootmem allocations in zone_movable. */ - /* - * CMA allocations (alloc_contig_range) really need to mark isolate - * CMA pageblocks even when they are not movable in fact so consider - * them movable here. - */ - if (is_migrate_cma(migratetype) && - is_migrate_cma(get_pageblock_migratetype(page))) - return false; + if (is_migrate_cma_page(page)) { + /* + * CMA allocations (alloc_contig_range) really need to mark + * isolate CMA pageblocks even when they are not movable in fact + * so consider them movable here. + */ + if (is_migrate_cma(migratetype)) + return false; + + reason = "CMA page"; + goto unmovable; + } - pfn = page_to_pfn(page); - for (found = 0, iter = 0; iter < pageblock_nr_pages; iter++) { + for (found = 0; iter < pageblock_nr_pages; iter++) { unsigned long check = pfn + iter; if (!pfn_valid_within(check)) @@ -8105,7 +8111,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, unmovable: WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE); if (flags & REPORT_FAILURE) - dump_page(pfn_to_page(pfn+iter), "unmovable page"); + dump_page(pfn_to_page(pfn + iter), reason); return true; } -- cgit v1.2.3-55-g7522 From 3b991208b897f52507168374033771a984b947b1 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 18 Apr 2019 17:50:34 -0700 Subject: mm: fix inactive list balancing between NUMA nodes and cgroups During !CONFIG_CGROUP reclaim, we expand the inactive list size if it's thrashing on the node that is about to be reclaimed. But when cgroups are enabled, we suddenly ignore the node scope and use the cgroup scope only. The result is that pressure bleeds between NUMA nodes depending on whether cgroups are merely compiled into Linux. This behavioral difference is unexpected and undesirable. When the refault adaptivity of the inactive list was first introduced, there were no statistics at the lruvec level - the intersection of node and memcg - so it was better than nothing. But now that we have that infrastructure, use lruvec_page_state() to make the list balancing decision always NUMA aware. [hannes@cmpxchg.org: fix bisection hole] Link: http://lkml.kernel.org/r/20190417155241.GB23013@cmpxchg.org Link: http://lkml.kernel.org/r/20190412144438.2645-1-hannes@cmpxchg.org Fixes: 2a2e48854d70 ("mm: vmscan: fix IO/refault regression in cache workingset transition") Signed-off-by: Johannes Weiner Reviewed-by: Shakeel Butt Cc: Roman Gushchin Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 29 +++++++++-------------------- 1 file changed, 9 insertions(+), 20 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index a5ad0b35ab8e..a815f73ee4d5 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2176,7 +2176,6 @@ static void shrink_active_list(unsigned long nr_to_scan, * 10TB 320 32GB */ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, - struct mem_cgroup *memcg, struct scan_control *sc, bool actual_reclaim) { enum lru_list active_lru = file * LRU_FILE + LRU_ACTIVE; @@ -2197,16 +2196,12 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, inactive = lruvec_lru_size(lruvec, inactive_lru, sc->reclaim_idx); active = lruvec_lru_size(lruvec, active_lru, sc->reclaim_idx); - if (memcg) - refaults = memcg_page_state(memcg, WORKINGSET_ACTIVATE); - else - refaults = node_page_state(pgdat, WORKINGSET_ACTIVATE); - /* * When refaults are being observed, it means a new workingset * is being established. Disable active list protection to get * rid of the stale workingset quickly. */ + refaults = lruvec_page_state(lruvec, WORKINGSET_ACTIVATE); if (file && actual_reclaim && lruvec->refaults != refaults) { inactive_ratio = 0; } else { @@ -2227,12 +2222,10 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, } static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, - struct lruvec *lruvec, struct mem_cgroup *memcg, - struct scan_control *sc) + struct lruvec *lruvec, struct scan_control *sc) { if (is_active_lru(lru)) { - if (inactive_list_is_low(lruvec, is_file_lru(lru), - memcg, sc, true)) + if (inactive_list_is_low(lruvec, is_file_lru(lru), sc, true)) shrink_active_list(nr_to_scan, lruvec, sc, lru); return 0; } @@ -2332,7 +2325,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, * anonymous pages on the LRU in eligible zones. * Otherwise, the small LRU gets thrashed. */ - if (!inactive_list_is_low(lruvec, false, memcg, sc, false) && + if (!inactive_list_is_low(lruvec, false, sc, false) && lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, sc->reclaim_idx) >> sc->priority) { scan_balance = SCAN_ANON; @@ -2350,7 +2343,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, * lruvec even if it has plenty of old anonymous pages unless the * system is under heavy pressure. */ - if (!inactive_list_is_low(lruvec, true, memcg, sc, false) && + if (!inactive_list_is_low(lruvec, true, sc, false) && lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, sc->reclaim_idx) >> sc->priority) { scan_balance = SCAN_FILE; goto out; @@ -2503,7 +2496,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc nr[lru] -= nr_to_scan; nr_reclaimed += shrink_list(lru, nr_to_scan, - lruvec, memcg, sc); + lruvec, sc); } } @@ -2570,7 +2563,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc * Even if we did not try to evict anon pages at all, we want to * rebalance the anon lru active/inactive ratio. */ - if (inactive_list_is_low(lruvec, false, memcg, sc, true)) + if (inactive_list_is_low(lruvec, false, sc, true)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); } @@ -2969,12 +2962,8 @@ static void snapshot_refaults(struct mem_cgroup *root_memcg, pg_data_t *pgdat) unsigned long refaults; struct lruvec *lruvec; - if (memcg) - refaults = memcg_page_state(memcg, WORKINGSET_ACTIVATE); - else - refaults = node_page_state(pgdat, WORKINGSET_ACTIVATE); - lruvec = mem_cgroup_lruvec(pgdat, memcg); + refaults = lruvec_page_state(lruvec, WORKINGSET_ACTIVATE); lruvec->refaults = refaults; } while ((memcg = mem_cgroup_iter(root_memcg, memcg, NULL))); } @@ -3339,7 +3328,7 @@ static void age_active_anon(struct pglist_data *pgdat, do { struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg); - if (inactive_list_is_low(lruvec, false, memcg, sc, true)) + if (inactive_list_is_low(lruvec, false, sc, true)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); -- cgit v1.2.3-55-g7522 From 40453c4f9bb6d166a56a102a8c51dd24b0801557 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 18 Apr 2019 17:50:37 -0700 Subject: kcov: improve CONFIG_ARCH_HAS_KCOV help text The help text for CONFIG_ARCH_HAS_KCOV is stale, and describes the feature as being enabled only for x86_64, when it is now enabled for several architectures, including arm, arm64, powerpc, and s390. Let's remove that stale help text, and update it along the lines of hat for ARCH_HAS_FORTIFY_SOURCE, better describing when an architecture should select CONFIG_ARCH_HAS_KCOV. Link: http://lkml.kernel.org/r/20190412102733.5154-1-mark.rutland@arm.com Signed-off-by: Mark Rutland Acked-by: Dmitry Vyukov Cc: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/Kconfig.debug | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 0d9e81779e37..00dbcdbc9a0d 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -753,9 +753,9 @@ endmenu # "Memory Debugging" config ARCH_HAS_KCOV bool help - KCOV does not have any arch-specific code, but currently it is enabled - only for x86_64. KCOV requires testing on other archs, and most likely - disabling of instrumentation for some early boot code. + An architecture should select this when it can successfully + build and run with CONFIG_KCOV. This typically requires + disabling instrumentation for some early boot code. config CC_HAS_SANCOV_TRACE_PC def_bool $(cc-option,-fsanitize-coverage=trace-pc) -- cgit v1.2.3-55-g7522 From 8f4a8c12cafe54535f334a09be7ec7f236134764 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 18 Apr 2019 17:50:41 -0700 Subject: kernel/watchdog_hld.c: hard lockup message should end with a newline Separate print_modules() and hard lockup error message. Before the patch: NMI watchdog: Watchdog detected hard LOCKUP on cpu 1Modules linked in: nls_cp437 Link: http://lkml.kernel.org/r/20190412062557.2700-1-sergey.senozhatsky@gmail.com Signed-off-by: Sergey Senozhatsky Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/watchdog_hld.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 71381168dede..247bf0b1582c 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -135,7 +135,8 @@ static void watchdog_overflow_callback(struct perf_event *event, if (__this_cpu_read(hard_watchdog_warn) == true) return; - pr_emerg("Watchdog detected hard LOCKUP on cpu %d", this_cpu); + pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n", + this_cpu); print_modules(); print_irqtrace_events(current); if (regs) -- cgit v1.2.3-55-g7522 From 6041186a32585fc7a1d0f6cfe2f138b05fdc3c82 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 18 Apr 2019 17:50:44 -0700 Subject: init: initialize jump labels before command line option parsing When a module option, or core kernel argument, toggles a static-key it requires jump labels to be initialized early. While x86, PowerPC, and ARM64 arrange for jump_label_init() to be called before parse_args(), ARM does not. Kernel command line: rdinit=/sbin/init page_alloc.shuffle=1 panic=-1 console=ttyAMA0,115200 page_alloc.shuffle=1 ------------[ cut here ]------------ WARNING: CPU: 0 PID: 0 at ./include/linux/jump_label.h:303 page_alloc_shuffle+0x12c/0x1ac static_key_enable(): static key 'page_alloc_shuffle_key+0x0/0x4' used before call to jump_label_init() Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 5.1.0-rc4-next-20190410-00003-g3367c36ce744 #1 Hardware name: ARM Integrator/CP (Device Tree) [] (unwind_backtrace) from [] (show_stack+0x10/0x18) [] (show_stack) from [] (dump_stack+0x18/0x24) [] (dump_stack) from [] (__warn+0xe0/0x108) [] (__warn) from [] (warn_slowpath_fmt+0x44/0x6c) [] (warn_slowpath_fmt) from [] (page_alloc_shuffle+0x12c/0x1ac) [] (page_alloc_shuffle) from [] (shuffle_store+0x28/0x48) [] (shuffle_store) from [] (parse_args+0x1f4/0x350) [] (parse_args) from [] (start_kernel+0x1c0/0x488) Move the fallback call to jump_label_init() to occur before parse_args(). The redundant calls to jump_label_init() in other archs are left intact in case they have static key toggling use cases that are even earlier than option parsing. Link: http://lkml.kernel.org/r/155544804466.1032396.13418949511615676665.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams Reported-by: Guenter Roeck Reviewed-by: Kees Cook Cc: Mathieu Desnoyers Cc: Thomas Gleixner Cc: Mike Rapoport Cc: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/init/main.c b/init/main.c index 598e278b46f7..7d4025d665eb 100644 --- a/init/main.c +++ b/init/main.c @@ -582,6 +582,8 @@ asmlinkage __visible void __init start_kernel(void) page_alloc_init(); pr_notice("Kernel command line: %s\n", boot_command_line); + /* parameters may set static keys */ + jump_label_init(); parse_early_param(); after_dashes = parse_args("Booting kernel", static_command_line, __start___param, @@ -591,8 +593,6 @@ asmlinkage __visible void __init start_kernel(void) parse_args("Setting init args", after_dashes, NULL, 0, -1, -1, NULL, set_init_arg); - jump_label_init(); - /* * These use large bootmem allocations and must precede * kmem_cache_init() -- cgit v1.2.3-55-g7522 From dce5b0bdeec61bdbee56121ceb1d014151d5cab1 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 18 Apr 2019 17:50:48 -0700 Subject: mm/kmemleak.c: fix unused-function warning The only references outside of the #ifdef have been removed, so now we get a warning in non-SMP configurations: mm/kmemleak.c:1404:13: error: unused function 'scan_large_block' [-Werror,-Wunused-function] Add a new #ifdef around it. Link: http://lkml.kernel.org/r/20190416123148.3502045-1-arnd@arndb.de Fixes: 298a32b13208 ("kmemleak: powerpc: skip scanning holes in the .bss section") Signed-off-by: Arnd Bergmann Acked-by: Catalin Marinas Cc: Vincent Whitchurch Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kmemleak.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 6c318f5ac234..2e435b8142e5 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1401,6 +1401,7 @@ static void scan_block(void *_start, void *_end, /* * Scan a large memory block in MAX_SCAN_SIZE chunks to reduce the latency. */ +#ifdef CONFIG_SMP static void scan_large_block(void *start, void *end) { void *next; @@ -1412,6 +1413,7 @@ static void scan_large_block(void *start, void *end) cond_resched(); } } +#endif /* * Scan a memory block corresponding to a kmemleak_object. A condition is -- cgit v1.2.3-55-g7522 From 04f5866e41fb70690e28397487d8bd8eea7d712a Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 18 Apr 2019 17:50:52 -0700 Subject: coredump: fix race condition between mmget_not_zero()/get_task_mm() and core dumping The core dumping code has always run without holding the mmap_sem for writing, despite that is the only way to ensure that the entire vma layout will not change from under it. Only using some signal serialization on the processes belonging to the mm is not nearly enough. This was pointed out earlier. For example in Hugh's post from Jul 2017: https://lkml.kernel.org/r/alpine.LSU.2.11.1707191716030.2055@eggly.anvils "Not strictly relevant here, but a related note: I was very surprised to discover, only quite recently, how handle_mm_fault() may be called without down_read(mmap_sem) - when core dumping. That seems a misguided optimization to me, which would also be nice to correct" In particular because the growsdown and growsup can move the vm_start/vm_end the various loops the core dump does around the vma will not be consistent if page faults can happen concurrently. Pretty much all users calling mmget_not_zero()/get_task_mm() and then taking the mmap_sem had the potential to introduce unexpected side effects in the core dumping code. Adding mmap_sem for writing around the ->core_dump invocation is a viable long term fix, but it requires removing all copy user and page faults and to replace them with get_dump_page() for all binary formats which is not suitable as a short term fix. For the time being this solution manually covers the places that can confuse the core dump either by altering the vma layout or the vma flags while it runs. Once ->core_dump runs under mmap_sem for writing the function mmget_still_valid() can be dropped. Allowing mmap_sem protected sections to run in parallel with the coredump provides some minor parallelism advantage to the swapoff code (which seems to be safe enough by never mangling any vma field and can keep doing swapins in parallel to the core dumping) and to some other corner case. In order to facilitate the backporting I added "Fixes: 86039bd3b4e6" however the side effect of this same race condition in /proc/pid/mem should be reproducible since before 2.6.12-rc2 so I couldn't add any other "Fixes:" because there's no hash beyond the git genesis commit. Because find_extend_vma() is the only location outside of the process context that could modify the "mm" structures under mmap_sem for reading, by adding the mmget_still_valid() check to it, all other cases that take the mmap_sem for reading don't need the new check after mmget_not_zero()/get_task_mm(). The expand_stack() in page fault context also doesn't need the new check, because all tasks under core dumping are frozen. Link: http://lkml.kernel.org/r/20190325224949.11068-1-aarcange@redhat.com Fixes: 86039bd3b4e6 ("userfaultfd: add new syscall to provide memory externalization") Signed-off-by: Andrea Arcangeli Reported-by: Jann Horn Suggested-by: Oleg Nesterov Acked-by: Peter Xu Reviewed-by: Mike Rapoport Reviewed-by: Oleg Nesterov Reviewed-by: Jann Horn Acked-by: Jason Gunthorpe Acked-by: Michal Hocko Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/infiniband/core/uverbs_main.c | 3 +++ fs/proc/task_mmu.c | 18 ++++++++++++++++++ fs/userfaultfd.c | 9 +++++++++ include/linux/sched/mm.h | 21 +++++++++++++++++++++ mm/mmap.c | 7 ++++++- 5 files changed, 57 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 70b7d80431a9..f2e7ffe6fc54 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -993,6 +993,8 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile) * will only be one mm, so no big deal. */ down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto skip_mm; mutex_lock(&ufile->umap_lock); list_for_each_entry_safe (priv, next_priv, &ufile->umaps, list) { @@ -1007,6 +1009,7 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile) vma->vm_flags &= ~(VM_SHARED | VM_MAYSHARE); } mutex_unlock(&ufile->umap_lock); + skip_mm: up_write(&mm->mmap_sem); mmput(mm); } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 92a91e7816d8..95ca1fe7283c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1143,6 +1143,24 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, count = -EINTR; goto out_mm; } + /* + * Avoid to modify vma->vm_flags + * without locked ops while the + * coredump reads the vm_flags. + */ + if (!mmget_still_valid(mm)) { + /* + * Silently return "count" + * like if get_task_mm() + * failed. FIXME: should this + * function have returned + * -ESRCH if get_task_mm() + * failed like if + * get_proc_task() fails? + */ + up_write(&mm->mmap_sem); + goto out_mm; + } for (vma = mm->mmap; vma; vma = vma->vm_next) { vma->vm_flags &= ~VM_SOFTDIRTY; vma_set_page_prot(vma); diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 89800fc7dc9d..f5de1e726356 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -629,6 +629,8 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, /* the various vma->vm_userfaultfd_ctx still points to it */ down_write(&mm->mmap_sem); + /* no task can run (and in turn coredump) yet */ + VM_WARN_ON(!mmget_still_valid(mm)); for (vma = mm->mmap; vma; vma = vma->vm_next) if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; @@ -883,6 +885,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file) * taking the mmap_sem for writing. */ down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto skip_mm; prev = NULL; for (vma = mm->mmap; vma; vma = vma->vm_next) { cond_resched(); @@ -905,6 +909,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) vma->vm_flags = new_flags; vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; } +skip_mm: up_write(&mm->mmap_sem); mmput(mm); wakeup: @@ -1333,6 +1338,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, goto out; down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; @@ -1520,6 +1527,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, goto out; down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 0cd9f10423fb..a3fda9f024c3 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -49,6 +49,27 @@ static inline void mmdrop(struct mm_struct *mm) __mmdrop(mm); } +/* + * This has to be called after a get_task_mm()/mmget_not_zero() + * followed by taking the mmap_sem for writing before modifying the + * vmas or anything the coredump pretends not to change from under it. + * + * NOTE: find_extend_vma() called from GUP context is the only place + * that can modify the "mm" (notably the vm_start/end) under mmap_sem + * for reading and outside the context of the process, so it is also + * the only case that holds the mmap_sem for reading that must call + * this function. Generally if the mmap_sem is hold for reading + * there's no need of this check after get_task_mm()/mmget_not_zero(). + * + * This function can be obsoleted and the check can be removed, after + * the coredump code will hold the mmap_sem for writing before + * invoking the ->core_dump methods. + */ +static inline bool mmget_still_valid(struct mm_struct *mm) +{ + return likely(!mm->core_state); +} + /** * mmget() - Pin the address space associated with a &struct mm_struct. * @mm: The address space to pin. diff --git a/mm/mmap.c b/mm/mmap.c index 41eb48d9b527..bd7b9f293b39 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -45,6 +45,7 @@ #include #include #include +#include #include #include @@ -2525,7 +2526,8 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr) vma = find_vma_prev(mm, addr, &prev); if (vma && (vma->vm_start <= addr)) return vma; - if (!prev || expand_stack(prev, addr)) + /* don't alter vm_end if the coredump is running */ + if (!prev || !mmget_still_valid(mm) || expand_stack(prev, addr)) return NULL; if (prev->vm_flags & VM_LOCKED) populate_vma_page_range(prev, addr, prev->vm_end, NULL); @@ -2551,6 +2553,9 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr) return vma; if (!(vma->vm_flags & VM_GROWSDOWN)) return NULL; + /* don't alter vm_start if the coredump is running */ + if (!mmget_still_valid(mm)) + return NULL; start = vma->vm_start; if (expand_stack(vma, addr)) return NULL; -- cgit v1.2.3-55-g7522 From 2ee27796f298b710992a677a7e4d35c8c588b17e Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sun, 30 Dec 2018 18:27:15 +0100 Subject: x86/cpu/intel: Lower the "ENERGY_PERF_BIAS: Set to normal" message's log priority The "ENERGY_PERF_BIAS: Set to 'normal', was 'performance'" message triggers on pretty much every Intel machine. The purpose of log messages with a warning level is to notify the user of something which potentially is a problem, or at least somewhat unexpected. This message clearly does not match those criteria, so lower its log priority from warning to info. Signed-off-by: Hans de Goede Cc: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20181230172715.17469-1-hdegoede@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/intel.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index fc3c07fe7df5..3142fd7a9b32 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -611,8 +611,8 @@ static void init_intel_energy_perf(struct cpuinfo_x86 *c) if ((epb & 0xF) != ENERGY_PERF_BIAS_PERFORMANCE) return; - pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n"); - pr_warn_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n"); + pr_info_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n"); + pr_info_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n"); epb = (epb & ~0xF) | ENERGY_PERF_BIAS_NORMAL; wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb); } -- cgit v1.2.3-55-g7522 From b40fabc05ea047f6af5933d26a5483873340b0d4 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 19 Apr 2019 10:31:27 +0800 Subject: block: kill all_q_node in request_queue all_q_node has not been used since commit 4b855ad37194 ("blk-mq: Create hctx for each present CPU"), so remove it. Reviewed-by: Chaitanya Kulkarni Reviewed-by: Ming Lei Signed-off-by: Hou Tao Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5c58a3b2bf00..317ab30d2904 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -548,7 +548,6 @@ struct request_queue { struct rcu_head rcu_head; wait_queue_head_t mq_freeze_wq; struct percpu_ref q_usage_counter; - struct list_head all_q_node; struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; -- cgit v1.2.3-55-g7522 From 6bedf00e55e5dd0a4ed1ad3f06131edd6fb56ec8 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 17 Apr 2019 09:11:26 +0800 Subject: block: make sure that bvec length can't be overflow bvec->bv_offset may be bigger than PAGE_SIZE sometimes, such as, when one bio is splitted in the middle of one bvec via bio_split(), and bi_iter.bi_bvec_done is used to build offset of the 1st bvec of remained bio. And the remained bio's bvec may be re-submitted to fs layer via ITER_IBVEC, such as loop and nvme-loop. So we have to make sure that every bvec's offset is less than PAGE_SIZE from bio_for_each_segment_all() because some drivers(loop, nvme-loop) passes the splitted bvec to fs layer via ITER_BVEC. This patch fixes this issue reported by Zhang Yi When running nvme/011. Cc: Christoph Hellwig Cc: Yi Zhang Reported-by: Yi Zhang Reviewed-by: Christoph Hellwig Fixes: 6dc4f100c175 ("block: allow bio_for_each_segment_all() to iterate over multi-page bvec") Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/bvec.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 3bc91879e1e2..ff13cbc1887d 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -160,8 +160,9 @@ static inline void bvec_advance(const struct bio_vec *bvec, bv->bv_page = nth_page(bv->bv_page, 1); bv->bv_offset = 0; } else { - bv->bv_page = bvec->bv_page; - bv->bv_offset = bvec->bv_offset; + bv->bv_page = bvec_nth_page(bvec->bv_page, bvec->bv_offset / + PAGE_SIZE); + bv->bv_offset = bvec->bv_offset & ~PAGE_MASK; } bv->bv_len = min_t(unsigned int, PAGE_SIZE - bv->bv_offset, bvec->bv_len - iter_all->done); -- cgit v1.2.3-55-g7522 From 36ad7022536e0c65f8baeeaa5efde11dec44808a Mon Sep 17 00:00:00 2001 From: Petr Štetiar Date: Wed, 17 Apr 2019 22:09:12 +0200 Subject: of_net: Fix residues after of_get_nvmem_mac_address removal I've discovered following discrepancy in the bindings/net/ethernet.txt documentation, where it states following: - nvmem-cells: phandle, reference to an nvmem node for the MAC address; - nvmem-cell-names: string, should be "mac-address" if nvmem is to be.. which is actually misleading and confusing. There are only two ethernet drivers in the tree, cadence/macb and davinci which supports this properties. This nvmem-cell* properties were introduced in commit 9217e566bdee ("of_net: Implement of_get_nvmem_mac_address helper"), but commit afa64a72b862 ("of: net: kill of_get_nvmem_mac_address()") forget to properly clean up this parts. So this patch fixes the documentation by moving the nvmem-cell* properties at the appropriate places. While at it, I've removed unused include as well. Cc: Bartosz Golaszewski Fixes: afa64a72b862 ("of: net: kill of_get_nvmem_mac_address()") Signed-off-by: Petr Štetiar Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/davinci_emac.txt | 2 ++ Documentation/devicetree/bindings/net/ethernet.txt | 2 -- Documentation/devicetree/bindings/net/macb.txt | 4 ++++ drivers/of/of_net.c | 1 - 4 files changed, 6 insertions(+), 3 deletions(-) diff --git a/Documentation/devicetree/bindings/net/davinci_emac.txt b/Documentation/devicetree/bindings/net/davinci_emac.txt index 24c5cdaba8d2..ca83dcc84fb8 100644 --- a/Documentation/devicetree/bindings/net/davinci_emac.txt +++ b/Documentation/devicetree/bindings/net/davinci_emac.txt @@ -20,6 +20,8 @@ Required properties: Optional properties: - phy-handle: See ethernet.txt file in the same directory. If absent, davinci_emac driver defaults to 100/FULL. +- nvmem-cells: phandle, reference to an nvmem node for the MAC address +- nvmem-cell-names: string, should be "mac-address" if nvmem is to be used - ti,davinci-rmii-en: 1 byte, 1 means use RMII - ti,davinci-no-bd-ram: boolean, does EMAC have BD RAM? diff --git a/Documentation/devicetree/bindings/net/ethernet.txt b/Documentation/devicetree/bindings/net/ethernet.txt index cfc376bc977a..2974e63ba311 100644 --- a/Documentation/devicetree/bindings/net/ethernet.txt +++ b/Documentation/devicetree/bindings/net/ethernet.txt @@ -10,8 +10,6 @@ Documentation/devicetree/bindings/phy/phy-bindings.txt. the boot program; should be used in cases where the MAC address assigned to the device by the boot program is different from the "local-mac-address" property; -- nvmem-cells: phandle, reference to an nvmem node for the MAC address; -- nvmem-cell-names: string, should be "mac-address" if nvmem is to be used; - max-speed: number, specifies maximum speed in Mbit/s supported by the device; - max-frame-size: number, maximum transfer unit (IEEE defined MTU), rather than the maximum frame size (there's contradiction in the Devicetree diff --git a/Documentation/devicetree/bindings/net/macb.txt b/Documentation/devicetree/bindings/net/macb.txt index 174f292d8a3e..8b80515729d7 100644 --- a/Documentation/devicetree/bindings/net/macb.txt +++ b/Documentation/devicetree/bindings/net/macb.txt @@ -26,6 +26,10 @@ Required properties: Optional elements: 'tsu_clk' - clocks: Phandles to input clocks. +Optional properties: +- nvmem-cells: phandle, reference to an nvmem node for the MAC address +- nvmem-cell-names: string, should be "mac-address" if nvmem is to be used + Optional properties for PHY child node: - reset-gpios : Should specify the gpio for phy reset - magic-packet : If present, indicates that the hardware supports waking diff --git a/drivers/of/of_net.c b/drivers/of/of_net.c index 810ab0fbcccb..d820f3edd431 100644 --- a/drivers/of/of_net.c +++ b/drivers/of/of_net.c @@ -7,7 +7,6 @@ */ #include #include -#include #include #include #include -- cgit v1.2.3-55-g7522 From 12fc512f5741443a03adde2ead20724da8ad550a Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Fri, 15 Mar 2019 16:41:43 +0200 Subject: net/mlx5e: Fix use-after-free after xdp_return_frame xdp_return_frame releases the frame. It leads to releasing the page, so it's not allowed to access xdpi.xdpf->len after that, because xdpi.xdpf is at xdp->data_hard_start after convert_to_xdp_frame. This patch moves the memory access to precede the return of the frame. Fixes: 58b99ee3e3ebe ("net/mlx5e: Add support for XDP_REDIRECT in device-out side") Signed-off-by: Maxim Mikityanskiy Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 03b2a9f9c589..10a99cd3e598 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -304,9 +304,9 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq) mlx5e_xdpi_fifo_pop(xdpi_fifo); if (is_redirect) { - xdp_return_frame(xdpi.xdpf); dma_unmap_single(sq->pdev, xdpi.dma_addr, xdpi.xdpf->len, DMA_TO_DEVICE); + xdp_return_frame(xdpi.xdpf); } else { /* Recycle RX page */ mlx5e_page_release(rq, &xdpi.di, true); @@ -345,9 +345,9 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq) mlx5e_xdpi_fifo_pop(xdpi_fifo); if (is_redirect) { - xdp_return_frame(xdpi.xdpf); dma_unmap_single(sq->pdev, xdpi.dma_addr, xdpi.xdpf->len, DMA_TO_DEVICE); + xdp_return_frame(xdpi.xdpf); } else { /* Recycle RX page */ mlx5e_page_release(rq, &xdpi.di, false); -- cgit v1.2.3-55-g7522 From d460c2718906252a2a69bc6f89b537071f792e6e Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Mon, 8 Apr 2019 15:12:45 +0300 Subject: net/mlx5e: Fix the max MTU check in case of XDP MLX5E_XDP_MAX_MTU was calculated incorrectly. It didn't account for NET_IP_ALIGN and MLX5E_HW2SW_MTU, and it also misused MLX5_SKB_FRAG_SZ. This commit fixes the calculations and adds a brief explanation for the formula used. Fixes: a26a5bdf3ee2d ("net/mlx5e: Restrict the combination of large MTU and XDP") Signed-off-by: Maxim Mikityanskiy Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 20 ++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h | 3 +-- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 5 +++-- 3 files changed, 24 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 10a99cd3e598..cad34d6f5f45 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -33,6 +33,26 @@ #include #include "en/xdp.h" +int mlx5e_xdp_max_mtu(struct mlx5e_params *params) +{ + int hr = NET_IP_ALIGN + XDP_PACKET_HEADROOM; + + /* Let S := SKB_DATA_ALIGN(sizeof(struct skb_shared_info)). + * The condition checked in mlx5e_rx_is_linear_skb is: + * SKB_DATA_ALIGN(sw_mtu + hard_mtu + hr) + S <= PAGE_SIZE (1) + * (Note that hw_mtu == sw_mtu + hard_mtu.) + * What is returned from this function is: + * max_mtu = PAGE_SIZE - S - hr - hard_mtu (2) + * After assigning sw_mtu := max_mtu, the left side of (1) turns to + * SKB_DATA_ALIGN(PAGE_SIZE - S) + S, which is equal to PAGE_SIZE, + * because both PAGE_SIZE and S are already aligned. Any number greater + * than max_mtu would make the left side of (1) greater than PAGE_SIZE, + * so max_mtu is the maximum MTU allowed. + */ + + return MLX5E_HW2SW_MTU(params, SKB_MAX_HEAD(hr)); +} + static inline bool mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_dma_info *di, struct xdp_buff *xdp) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h index ee27a7c8cd87..553956cadc8a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h @@ -34,13 +34,12 @@ #include "en.h" -#define MLX5E_XDP_MAX_MTU ((int)(PAGE_SIZE - \ - MLX5_SKB_FRAG_SZ(XDP_PACKET_HEADROOM))) #define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN) #define MLX5E_XDP_TX_EMPTY_DS_COUNT \ (sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) #define MLX5E_XDP_TX_DS_COUNT (MLX5E_XDP_TX_EMPTY_DS_COUNT + 1 /* SG DS */) +int mlx5e_xdp_max_mtu(struct mlx5e_params *params); bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, void *va, u16 *rx_headroom, u32 *len); bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index f7eb521db580..46157e2a1e5a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3777,7 +3777,7 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, if (params->xdp_prog && !mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) { netdev_err(netdev, "MTU(%d) > %d is not allowed while XDP enabled\n", - new_mtu, MLX5E_XDP_MAX_MTU); + new_mtu, mlx5e_xdp_max_mtu(params)); err = -EINVAL; goto out; } @@ -4212,7 +4212,8 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog) if (!mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) { netdev_warn(netdev, "XDP is not allowed with MTU(%d) > %d\n", - new_channels.params.sw_mtu, MLX5E_XDP_MAX_MTU); + new_channels.params.sw_mtu, + mlx5e_xdp_max_mtu(&new_channels.params)); return -EINVAL; } -- cgit v1.2.3-55-g7522 From ace329f4ab3ba434be2adf618073c752d083b524 Mon Sep 17 00:00:00 2001 From: Erez Alfasi Date: Thu, 11 Apr 2019 10:41:03 +0300 Subject: net/mlx5e: ethtool, Remove unsupported SFP EEPROM high pages query Querying EEPROM high pages data for SFP module is currently not supported by our driver and yet queried, resulting in invalid FW queries. Set the EEPROM ethtool data length to 256 for SFP module will limit the reading for page 0 only and prevent invalid FW queries. Fixes: bb64143eee8c ("net/mlx5e: Add ethtool support for dump module EEPROM") Signed-off-by: Erez Alfasi Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/port.c | 4 ---- 2 files changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 76a3d01a489e..78dc8fe2a83c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1586,7 +1586,7 @@ static int mlx5e_get_module_info(struct net_device *netdev, break; case MLX5_MODULE_ID_SFP: modinfo->type = ETH_MODULE_SFF_8472; - modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; + modinfo->eeprom_len = MLX5_EEPROM_PAGE_LENGTH; break; default: netdev_err(priv->netdev, "%s: cable type not recognized:0x%x\n", diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 21b7f05b16a5..361468e0435d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -317,10 +317,6 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev, size -= offset + size - MLX5_EEPROM_PAGE_LENGTH; i2c_addr = MLX5_I2C_ADDR_LOW; - if (offset >= MLX5_EEPROM_PAGE_LENGTH) { - i2c_addr = MLX5_I2C_ADDR_HIGH; - offset -= MLX5_EEPROM_PAGE_LENGTH; - } MLX5_SET(mcia_reg, in, l, 0); MLX5_SET(mcia_reg, in, module, module_num); -- cgit v1.2.3-55-g7522 From 30c04d796b693e22405c38e9b78e9a364e4c77e6 Mon Sep 17 00:00:00 2001 From: Po-Hsu Lin Date: Thu, 18 Apr 2019 19:57:25 +0800 Subject: selftests/net: correct the return value for run_netsocktests The run_netsocktests will be marked as passed regardless the actual test result from the ./socket: selftests: net: run_netsocktests ======================================== -------------------- running socket test -------------------- [FAIL] ok 1..6 selftests: net: run_netsocktests [PASS] This is because the test script itself has been successfully executed. Fix this by exit 1 when the test failed. Signed-off-by: Po-Hsu Lin Signed-off-by: David S. Miller --- tools/testing/selftests/net/run_netsocktests | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/run_netsocktests b/tools/testing/selftests/net/run_netsocktests index b093f39c298c..14e41faf2c57 100755 --- a/tools/testing/selftests/net/run_netsocktests +++ b/tools/testing/selftests/net/run_netsocktests @@ -7,7 +7,7 @@ echo "--------------------" ./socket if [ $? -ne 0 ]; then echo "[FAIL]" + exit 1 else echo "[PASS]" fi - -- cgit v1.2.3-55-g7522 From 925b0c841e066b488cc3a60272472b2c56300704 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Fri, 19 Apr 2019 14:31:00 +0800 Subject: team: fix possible recursive locking when add slaves If we add a bond device which is already the master of the team interface, we will hold the team->lock in team_add_slave() first and then request the lock in team_set_mac_address() again. The functions are called like: - team_add_slave() - team_port_add() - team_port_enter() - team_modeop_port_enter() - __set_port_dev_addr() - dev_set_mac_address() - bond_set_mac_address() - dev_set_mac_address() - team_set_mac_address Although team_upper_dev_link() would check the upper devices but it is called too late. Fix it by adding a checking before processing the slave. v2: Do not split the string in netdev_err() Fixes: 3d249d4ca7d0 ("net: introduce ethernet teaming device") Acked-by: Jiri Pirko Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- drivers/net/team/team.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 9ce61b019aad..16963f7a88f7 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1156,6 +1156,13 @@ static int team_port_add(struct team *team, struct net_device *port_dev, return -EINVAL; } + if (netdev_has_upper_dev(dev, port_dev)) { + NL_SET_ERR_MSG(extack, "Device is already an upper device of the team interface"); + netdev_err(dev, "Device %s is already an upper device of the team interface\n", + portname); + return -EBUSY; + } + if (port_dev->features & NETIF_F_VLAN_CHALLENGED && vlan_uses_dev(dev)) { NL_SET_ERR_MSG(extack, "Device is VLAN challenged and team device has VLAN set up"); -- cgit v1.2.3-55-g7522 From 8c03557c3f25271e62e39154af66ebdd1b59c9ca Mon Sep 17 00:00:00 2001 From: Po-Hsu Lin Date: Fri, 19 Apr 2019 19:01:13 +0800 Subject: selftests/net: correct the return value for run_afpackettests The run_afpackettests will be marked as passed regardless the return value of those sub-tests in the script: -------------------- running psock_tpacket test -------------------- [FAIL] selftests: run_afpackettests [PASS] Fix this by changing the return value for each tests. Signed-off-by: Po-Hsu Lin Signed-off-by: David S. Miller --- tools/testing/selftests/net/run_afpackettests | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tools/testing/selftests/net/run_afpackettests b/tools/testing/selftests/net/run_afpackettests index 2dc95fda7ef7..ea5938ec009a 100755 --- a/tools/testing/selftests/net/run_afpackettests +++ b/tools/testing/selftests/net/run_afpackettests @@ -6,12 +6,14 @@ if [ $(id -u) != 0 ]; then exit 0 fi +ret=0 echo "--------------------" echo "running psock_fanout test" echo "--------------------" ./in_netns.sh ./psock_fanout if [ $? -ne 0 ]; then echo "[FAIL]" + ret=1 else echo "[PASS]" fi @@ -22,6 +24,7 @@ echo "--------------------" ./in_netns.sh ./psock_tpacket if [ $? -ne 0 ]; then echo "[FAIL]" + ret=1 else echo "[PASS]" fi @@ -32,6 +35,8 @@ echo "--------------------" ./in_netns.sh ./txring_overwrite if [ $? -ne 0 ]; then echo "[FAIL]" + ret=1 else echo "[PASS]" fi +exit $ret -- cgit v1.2.3-55-g7522 From 62ef81d5632634d5e310ed25b9b940b2b6612b46 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 19 Apr 2019 16:51:38 -0700 Subject: net/tls: avoid potential deadlock in tls_set_device_offload_rx() If device supports offload, but offload fails tls_set_device_offload_rx() will call tls_sw_free_resources_rx() which (unhelpfully) releases and reacquires the socket lock. For a small fix release and reacquire the device_offload_lock. Fixes: 4799ac81e52a ("tls: Add rx inline crypto offload") Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: David S. Miller --- net/tls/tls_device.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 9f3bdbc1e593..1b5f55cac613 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -904,7 +904,9 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) goto release_netdev; free_sw_resources: + up_read(&device_offload_lock); tls_sw_free_resources_rx(sk); + down_read(&device_offload_lock); release_ctx: ctx->priv_ctx_rx = NULL; release_netdev: -- cgit v1.2.3-55-g7522 From 12c7686111326148b4b5db189130522a4ad1be4a Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 19 Apr 2019 16:52:19 -0700 Subject: net/tls: don't leak IV and record seq when offload fails When device refuses the offload in tls_set_device_offload_rx() it calls tls_sw_free_resources_rx() to clean up software context state. Unfortunately, tls_sw_free_resources_rx() does not free all the state tls_set_sw_offload() allocated - it leaks IV and sequence number buffers. All other code paths which lead to tls_sw_release_resources_rx() (which tls_sw_free_resources_rx() calls) free those right before the call. Avoid the leak by moving freeing of iv and rec_seq into tls_sw_release_resources_rx(). Fixes: 4799ac81e52a ("tls: Add rx inline crypto offload") Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: David S. Miller --- net/tls/tls_device.c | 2 -- net/tls/tls_main.c | 5 +---- net/tls/tls_sw.c | 3 +++ 3 files changed, 4 insertions(+), 6 deletions(-) diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 1b5f55cac613..cc0256939eb6 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -941,8 +941,6 @@ void tls_device_offload_cleanup_rx(struct sock *sk) } out: up_read(&device_offload_lock); - kfree(tls_ctx->rx.rec_seq); - kfree(tls_ctx->rx.iv); tls_sw_release_resources_rx(sk); } diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 9547cea0ce3b..478603f43964 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -293,11 +293,8 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) #endif } - if (ctx->rx_conf == TLS_SW) { - kfree(ctx->rx.rec_seq); - kfree(ctx->rx.iv); + if (ctx->rx_conf == TLS_SW) tls_sw_free_resources_rx(sk); - } #ifdef CONFIG_TLS_DEVICE if (ctx->rx_conf == TLS_HW) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index b50ced862f6f..29d6af43dd24 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2078,6 +2078,9 @@ void tls_sw_release_resources_rx(struct sock *sk) struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); + kfree(tls_ctx->rx.rec_seq); + kfree(tls_ctx->rx.iv); + if (ctx->aead_recv) { kfree_skb(ctx->recv_pkt); ctx->recv_pkt = NULL; -- cgit v1.2.3-55-g7522 From 085b7755808aa11f78ab9377257e1dad2e6fa4bb Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 21 Apr 2019 10:45:57 -0700 Subject: Linux 5.1-rc6 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 71fd5c2ce067..abe13538a8c0 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 1 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Shy Crocodile # *DOCUMENTATION* -- cgit v1.2.3-55-g7522 From 39420fe04f093c15e1674ef56dbae0df109738ec Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Sat, 20 Apr 2019 18:14:33 +0000 Subject: dt-bindings: add an explanation for internal phy-mode When working on the Allwinner internal PHY, the first work was to use the "internal" mode, but some answer was made my mail on what are really internal mean for PHY. This patch write that in the doc. Signed-off-by: Corentin Labbe Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/ethernet.txt | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/net/ethernet.txt b/Documentation/devicetree/bindings/net/ethernet.txt index 2974e63ba311..a68621580584 100644 --- a/Documentation/devicetree/bindings/net/ethernet.txt +++ b/Documentation/devicetree/bindings/net/ethernet.txt @@ -16,7 +16,8 @@ Documentation/devicetree/bindings/phy/phy-bindings.txt. Specification). - phy-mode: string, operation mode of the PHY interface. This is now a de-facto standard property; supported values are: - * "internal" + * "internal" (Internal means there is not a standard bus between the MAC and + the PHY, something proprietary is being used to embed the PHY in the MAC.) * "mii" * "gmii" * "sgmii" -- cgit v1.2.3-55-g7522 From 26d1b8586b4fe14814ff4fd471cfc56014359e59 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Sat, 20 Apr 2019 16:43:01 +0000 Subject: Documentation: decnet: remove reference to CONFIG_DECNET_ROUTE_FWMARK CONFIG_DECNET_ROUTE_FWMARK was removed in commit 47dcf0cb1005 ("[NET]: Rethink mark field in struct flowi") Since nothing replace it (and nothindg need to replace it, simply remove it from documentation. Signed-off-by: Corentin Labbe Signed-off-by: David S. Miller --- Documentation/networking/decnet.txt | 2 -- 1 file changed, 2 deletions(-) diff --git a/Documentation/networking/decnet.txt b/Documentation/networking/decnet.txt index e12a4900cf72..d192f8b9948b 100644 --- a/Documentation/networking/decnet.txt +++ b/Documentation/networking/decnet.txt @@ -22,8 +22,6 @@ you'll need the following options as well... CONFIG_DECNET_ROUTER (to be able to add/delete routes) CONFIG_NETFILTER (will be required for the DECnet routing daemon) - CONFIG_DECNET_ROUTE_FWMARK is optional - Don't turn on SIOCGIFCONF support for DECnet unless you are really sure that you need it, in general you won't and it can cause ifconfig to malfunction. -- cgit v1.2.3-55-g7522 From 7caa56f006e9d712b44f27b32520c66420d5cbc6 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 15 Apr 2019 00:43:00 +0200 Subject: netfilter: ebtables: CONFIG_COMPAT: drop a bogus WARN_ON It means userspace gave us a ruleset where there is some other data after the ebtables target but before the beginning of the next rule. Fixes: 81e675c227ec ("netfilter: ebtables: add CONFIG_COMPAT support") Reported-by: syzbot+659574e7bcc7f7eb4df7@syzkaller.appspotmail.com Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/bridge/netfilter/ebtables.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index eb15891f8b9f..3cad01ac64e4 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -2032,7 +2032,8 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, if (match_kern) match_kern->match_size = ret; - if (WARN_ON(type == EBT_COMPAT_TARGET && size_left)) + /* rule should have no remaining data after target */ + if (type == EBT_COMPAT_TARGET && size_left) return -EINVAL; match32 = (struct compat_ebt_entry_mwt *) buf; -- cgit v1.2.3-55-g7522 From 916f6efae62305796e012e7c3a7884a267cbacbf Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 17 Apr 2019 02:17:23 +0200 Subject: netfilter: never get/set skb->tstamp setting net.netfilter.nf_conntrack_timestamp=1 breaks xmit with fq scheduler. skb->tstamp might be "refreshed" using ktime_get_real(), but fq expects CLOCK_MONOTONIC. This patch removes all places in netfilter that check/set skb->tstamp: 1. To fix the bogus "start" time seen with conntrack timestamping for outgoing packets, never use skb->tstamp and always use current time. 2. In nfqueue and nflog, only use skb->tstamp for incoming packets, as determined by current hook (prerouting, input, forward). 3. xt_time has to use system clock as well rather than skb->tstamp. We could still use skb->tstamp for prerouting/input/foward, but I see no advantage to make this conditional. Fixes: fb420d5d91c1 ("tcp/fq: move back to CLOCK_MONOTONIC") Cc: Eric Dumazet Reported-by: Michal Soltys Signed-off-by: Florian Westphal Acked-by: Eric Dumazet Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_core.c | 7 ++----- net/netfilter/nfnetlink_log.c | 2 +- net/netfilter/nfnetlink_queue.c | 2 +- net/netfilter/xt_time.c | 23 ++++++++++++++--------- 4 files changed, 18 insertions(+), 16 deletions(-) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 3c48d44d6fff..2a714527cde1 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1017,12 +1017,9 @@ __nf_conntrack_confirm(struct sk_buff *skb) /* set conntrack timestamp, if enabled. */ tstamp = nf_conn_tstamp_find(ct); - if (tstamp) { - if (skb->tstamp == 0) - __net_timestamp(skb); + if (tstamp) + tstamp->start = ktime_get_real_ns(); - tstamp->start = ktime_to_ns(skb->tstamp); - } /* Since the lookup is lockless, hash insertion must be done after * starting the timer and setting the CONFIRMED bit. The RCU barriers * guarantee that no other CPU can find the conntrack before the above diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index b1f9c5303f02..0b3347570265 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -540,7 +540,7 @@ __build_packet_message(struct nfnl_log_net *log, goto nla_put_failure; } - if (skb->tstamp) { + if (hooknum <= NF_INET_FORWARD && skb->tstamp) { struct nfulnl_msg_packet_timestamp ts; struct timespec64 kts = ktime_to_timespec64(skb->tstamp); ts.sec = cpu_to_be64(kts.tv_sec); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 0dcc3592d053..e057b2961d31 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -582,7 +582,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, if (nfqnl_put_bridge(entry, skb) < 0) goto nla_put_failure; - if (entskb->tstamp) { + if (entry->state.hook <= NF_INET_FORWARD && entskb->tstamp) { struct nfqnl_msg_packet_timestamp ts; struct timespec64 kts = ktime_to_timespec64(entskb->tstamp); diff --git a/net/netfilter/xt_time.c b/net/netfilter/xt_time.c index c13bcd0ab491..8dbb4d48f2ed 100644 --- a/net/netfilter/xt_time.c +++ b/net/netfilter/xt_time.c @@ -163,19 +163,24 @@ time_mt(const struct sk_buff *skb, struct xt_action_param *par) s64 stamp; /* - * We cannot use get_seconds() instead of __net_timestamp() here. + * We need real time here, but we can neither use skb->tstamp + * nor __net_timestamp(). + * + * skb->tstamp and skb->skb_mstamp_ns overlap, however, they + * use different clock types (real vs monotonic). + * * Suppose you have two rules: - * 1. match before 13:00 - * 2. match after 13:00 + * 1. match before 13:00 + * 2. match after 13:00 + * * If you match against processing time (get_seconds) it * may happen that the same packet matches both rules if - * it arrived at the right moment before 13:00. + * it arrived at the right moment before 13:00, so it would be + * better to check skb->tstamp and set it via __net_timestamp() + * if needed. This however breaks outgoing packets tx timestamp, + * and causes them to get delayed forever by fq packet scheduler. */ - if (skb->tstamp == 0) - __net_timestamp((struct sk_buff *)skb); - - stamp = ktime_to_ns(skb->tstamp); - stamp = div_s64(stamp, NSEC_PER_SEC); + stamp = get_seconds(); if (info->flags & XT_TIME_LOCAL_TZ) /* Adjust for local timezone */ -- cgit v1.2.3-55-g7522 From d48668052b2603b6262459625c86108c493588dd Mon Sep 17 00:00:00 2001 From: Andrei Vagin Date: Wed, 17 Apr 2019 09:49:44 -0700 Subject: netfilter: fix nf_l4proto_log_invalid to log invalid packets It doesn't log a packet if sysctl_log_invalid isn't equal to protonum OR sysctl_log_invalid isn't equal to IPPROTO_RAW. This sentence is always true. I believe we need to replace OR to AND. Cc: Florian Westphal Fixes: c4f3db1595827 ("netfilter: conntrack: add and use nf_l4proto_log_invalid") Signed-off-by: Andrei Vagin Acked-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_proto.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index b9403a266a2e..37bb530d848f 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -55,7 +55,7 @@ void nf_l4proto_log_invalid(const struct sk_buff *skb, struct va_format vaf; va_list args; - if (net->ct.sysctl_log_invalid != protonum || + if (net->ct.sysctl_log_invalid != protonum && net->ct.sysctl_log_invalid != IPPROTO_RAW) return; -- cgit v1.2.3-55-g7522 From 6aaafc43a4ecc5bc8a3f6a2811d5eddc996a97f3 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 22 Apr 2019 12:34:23 -0400 Subject: nfsd: wake waiters blocked on file_lock before deleting it After a blocked nfsd file_lock request is deleted, knfsd will send a callback to the client and then free the request. Commit 16306a61d3b7 ("fs/locks: always delete_block after waiting.") changed it such that locks_delete_block is always called on a request after it is awoken, but that patch missed fixing up blocked nfsd request handling. Call locks_delete_block on the block to wake up any locks still blocked on the nfsd lock request before freeing it. Some of its callers already do this however, so just remove those calls. URL: https://bugzilla.kernel.org/show_bug.cgi?id=203363 Fixes: 16306a61d3b7 ("fs/locks: always delete_block after waiting.") Reported-by: Slawomir Pryczek Cc: Neil Brown Cc: stable@vger.kernel.org Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 6a45fb00c5fc..e87e15df2044 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -265,6 +265,7 @@ find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh, static void free_blocked_lock(struct nfsd4_blocked_lock *nbl) { + locks_delete_block(&nbl->nbl_lock); locks_release_private(&nbl->nbl_lock); kfree(nbl); } @@ -293,7 +294,6 @@ remove_blocked_locks(struct nfs4_lockowner *lo) nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock, nbl_lru); list_del_init(&nbl->nbl_lru); - locks_delete_block(&nbl->nbl_lock); free_blocked_lock(nbl); } } @@ -4863,7 +4863,6 @@ nfs4_laundromat(struct nfsd_net *nn) nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock, nbl_lru); list_del_init(&nbl->nbl_lru); - locks_delete_block(&nbl->nbl_lock); free_blocked_lock(nbl); } out: -- cgit v1.2.3-55-g7522 From f456458e4d25a8962d0946891617c76cc3ff5fb9 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 22 Apr 2019 12:34:24 -0400 Subject: nfsd: wake blocked file lock waiters before sending callback When a blocked NFS lock is "awoken" we send a callback to the server and then wake any hosts waiting on it. If a client attempts to get a lock and then drops off the net, we could end up waiting for a long time until we end up waking locks blocked on that request. So, wake any other waiting lock requests before sending the callback. Do this by calling locks_delete_block in a new "prepare" phase for CB_NOTIFY_LOCK callbacks. URL: https://bugzilla.kernel.org/show_bug.cgi?id=203363 Fixes: 16306a61d3b7 ("fs/locks: always delete_block after waiting.") Reported-by: Slawomir Pryczek Cc: Neil Brown Cc: stable@vger.kernel.org Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index e87e15df2044..f056b1d3fecd 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -298,6 +298,14 @@ remove_blocked_locks(struct nfs4_lockowner *lo) } } +static void +nfsd4_cb_notify_lock_prepare(struct nfsd4_callback *cb) +{ + struct nfsd4_blocked_lock *nbl = container_of(cb, + struct nfsd4_blocked_lock, nbl_cb); + locks_delete_block(&nbl->nbl_lock); +} + static int nfsd4_cb_notify_lock_done(struct nfsd4_callback *cb, struct rpc_task *task) { @@ -325,6 +333,7 @@ nfsd4_cb_notify_lock_release(struct nfsd4_callback *cb) } static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = { + .prepare = nfsd4_cb_notify_lock_prepare, .done = nfsd4_cb_notify_lock_done, .release = nfsd4_cb_notify_lock_release, }; -- cgit v1.2.3-55-g7522 From b561af36b1841088552464cdc3f6371d92f17710 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Mon, 22 Apr 2019 15:15:32 +0530 Subject: net: stmmac: move stmmac_check_ether_addr() to driver probe stmmac_check_ether_addr() checks the MAC address and assigns one in driver open(). In many cases when we create slave netdevice, the dev addr is inherited from master but the master dev addr maybe NULL at that time, so move this call to driver probe so that address is always valid. Signed-off-by: Xiaofei Shen Tested-by: Xiaofei Shen Signed-off-by: Sneh Shah Signed-off-by: Vinod Koul Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index a26e36dbb5df..48712437d0da 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2616,8 +2616,6 @@ static int stmmac_open(struct net_device *dev) u32 chan; int ret; - stmmac_check_ether_addr(priv); - if (priv->hw->pcs != STMMAC_PCS_RGMII && priv->hw->pcs != STMMAC_PCS_TBI && priv->hw->pcs != STMMAC_PCS_RTBI) { @@ -4303,6 +4301,8 @@ int stmmac_dvr_probe(struct device *device, if (ret) goto error_hw_init; + stmmac_check_ether_addr(priv); + /* Configure real RX and TX queues */ netif_set_real_num_rx_queues(ndev, priv->plat->rx_queues_to_use); netif_set_real_num_tx_queues(ndev, priv->plat->tx_queues_to_use); -- cgit v1.2.3-55-g7522 From 2f23a2a768bee7ad2ff1e9527c3f7e279e794a46 Mon Sep 17 00:00:00 2001 From: Daniel Gomez Date: Mon, 22 Apr 2019 21:08:03 +0200 Subject: spi: Micrel eth switch: declare missing of table Add missing table for SPI driver relying on SPI device match since compatible is in a DT binding or in a DTS. Before this patch: modinfo drivers/net/phy/spi_ks8995.ko | grep alias alias: spi:ksz8795 alias: spi:ksz8864 alias: spi:ks8995 After this patch: modinfo drivers/net/phy/spi_ks8995.ko | grep alias alias: spi:ksz8795 alias: spi:ksz8864 alias: spi:ks8995 alias: of:N*T*Cmicrel,ksz8795C* alias: of:N*T*Cmicrel,ksz8795 alias: of:N*T*Cmicrel,ksz8864C* alias: of:N*T*Cmicrel,ksz8864 alias: of:N*T*Cmicrel,ks8995C* alias: of:N*T*Cmicrel,ks8995 Reported-by: Javier Martinez Canillas Signed-off-by: Daniel Gomez Signed-off-by: David S. Miller --- drivers/net/phy/spi_ks8995.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/net/phy/spi_ks8995.c b/drivers/net/phy/spi_ks8995.c index 92b64e254b44..7475cef17cf7 100644 --- a/drivers/net/phy/spi_ks8995.c +++ b/drivers/net/phy/spi_ks8995.c @@ -159,6 +159,14 @@ static const struct spi_device_id ks8995_id[] = { }; MODULE_DEVICE_TABLE(spi, ks8995_id); +static const struct of_device_id ks8895_spi_of_match[] = { + { .compatible = "micrel,ks8995" }, + { .compatible = "micrel,ksz8864" }, + { .compatible = "micrel,ksz8795" }, + { }, + }; +MODULE_DEVICE_TABLE(of, ks8895_spi_of_match); + static inline u8 get_chip_id(u8 val) { return (val >> ID1_CHIPID_S) & ID1_CHIPID_M; @@ -526,6 +534,7 @@ static int ks8995_remove(struct spi_device *spi) static struct spi_driver ks8995_driver = { .driver = { .name = "spi-ks8995", + .of_match_table = of_match_ptr(ks8895_spi_of_match), }, .probe = ks8995_probe, .remove = ks8995_remove, -- cgit v1.2.3-55-g7522 From d04830531d0c4a99c897a44038e5da3d23331d2f Mon Sep 17 00:00:00 2001 From: Daniel Gomez Date: Mon, 22 Apr 2019 21:08:04 +0200 Subject: spi: ST ST95HF NFC: declare missing of table Add missing table for SPI driver relying on SPI device match since compatible is in a DT binding or in a DTS. Before this patch: modinfo drivers/nfc/st95hf/st95hf.ko | grep alias alias: spi:st95hf After this patch: modinfo drivers/nfc/st95hf/st95hf.ko | grep alias alias: spi:st95hf alias: of:N*T*Cst,st95hfC* alias: of:N*T*Cst,st95hf Reported-by: Javier Martinez Canillas Signed-off-by: Daniel Gomez Signed-off-by: David S. Miller --- drivers/nfc/st95hf/core.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/nfc/st95hf/core.c b/drivers/nfc/st95hf/core.c index 2b26f762fbc3..01acb6e53365 100644 --- a/drivers/nfc/st95hf/core.c +++ b/drivers/nfc/st95hf/core.c @@ -1074,6 +1074,12 @@ static const struct spi_device_id st95hf_id[] = { }; MODULE_DEVICE_TABLE(spi, st95hf_id); +static const struct of_device_id st95hf_spi_of_match[] = { + { .compatible = "st,st95hf" }, + { }, +}; +MODULE_DEVICE_TABLE(of, st95hf_spi_of_match); + static int st95hf_probe(struct spi_device *nfc_spi_dev) { int ret; @@ -1260,6 +1266,7 @@ static struct spi_driver st95hf_driver = { .driver = { .name = "st95hf", .owner = THIS_MODULE, + .of_match_table = of_match_ptr(st95hf_spi_of_match), }, .id_table = st95hf_id, .probe = st95hf_probe, -- cgit v1.2.3-55-g7522 From 9fa246256e09dc30820524401cdbeeaadee94025 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Wed, 24 Apr 2019 10:47:56 +1000 Subject: Revert "drm/i915/fbdev: Actually configure untiled displays" This reverts commit d179b88deb3bf6fed4991a31fd6f0f2cad21fab5. This commit is documented to break userspace X.org modesetting driver in certain configurations. The X.org modesetting userspace driver is broken. No fixes are available yet. In order for this patch to be applied it either needs a config option or a workaround developed. This has been reported a few times, saying it's a userspace problem is clearly against the regression rules. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=109806 Signed-off-by: Dave Airlie Cc: # v3.19+ --- drivers/gpu/drm/i915/intel_fbdev.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index e8f694b57b8a..376ffe842e26 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -338,8 +338,8 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper, bool *enabled, int width, int height) { struct drm_i915_private *dev_priv = to_i915(fb_helper->dev); + unsigned long conn_configured, conn_seq, mask; unsigned int count = min(fb_helper->connector_count, BITS_PER_LONG); - unsigned long conn_configured, conn_seq; int i, j; bool *save_enabled; bool fallback = true, ret = true; @@ -357,9 +357,10 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper, drm_modeset_backoff(&ctx); memcpy(save_enabled, enabled, count); - conn_seq = GENMASK(count - 1, 0); + mask = GENMASK(count - 1, 0); conn_configured = 0; retry: + conn_seq = conn_configured; for (i = 0; i < count; i++) { struct drm_fb_helper_connector *fb_conn; struct drm_connector *connector; @@ -372,8 +373,7 @@ retry: if (conn_configured & BIT(i)) continue; - /* First pass, only consider tiled connectors */ - if (conn_seq == GENMASK(count - 1, 0) && !connector->has_tile) + if (conn_seq == 0 && !connector->has_tile) continue; if (connector->status == connector_status_connected) @@ -477,10 +477,8 @@ retry: conn_configured |= BIT(i); } - if (conn_configured != conn_seq) { /* repeat until no more are found */ - conn_seq = conn_configured; + if ((conn_configured & mask) != mask && conn_configured != conn_seq) goto retry; - } /* * If the BIOS didn't enable everything it could, fall back to have the -- cgit v1.2.3-55-g7522 From a0cecc23cfcbf2626497a8c8770856dd56b67917 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Wed, 24 Apr 2019 10:52:20 +1000 Subject: Revert "drm/virtio: drop prime import/export callbacks" This patch does more harm than good, as it breaks both Xwayland and gnome-shell with X11. Xwayland requires DRI3 & DRI3 requires PRIME. X11 crash for obscure double-free reason which are hard to debug (starting X11 by hand doesn't trigger the crash). I don't see an apparent problem implementing those stub prime functions, they may return an error at run-time, and it seems to be handled fine by GNOME at least. This reverts commit b318e3ff7ca065d6b107e424c85a63d7a6798a69. [airlied: This broke userspace for virtio-gpus, and regressed things from DRI3 to DRI2. This brings back the original problem, but it's better than regressions.] Fixes: b318e3ff7ca065d6b107e424c85a63d7a6798a ("drm/virtio: drop prime import/export callbacks") Signed-off-by: Marc-André Lureau Signed-off-by: Dave Airlie --- drivers/gpu/drm/virtio/virtgpu_drv.c | 4 ++++ drivers/gpu/drm/virtio/virtgpu_drv.h | 4 ++++ drivers/gpu/drm/virtio/virtgpu_prime.c | 12 ++++++++++++ 3 files changed, 20 insertions(+) diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c index b996ac1d4fcc..af92964b6889 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.c +++ b/drivers/gpu/drm/virtio/virtgpu_drv.c @@ -205,10 +205,14 @@ static struct drm_driver driver = { #if defined(CONFIG_DEBUG_FS) .debugfs_init = virtio_gpu_debugfs_init, #endif + .prime_handle_to_fd = drm_gem_prime_handle_to_fd, + .prime_fd_to_handle = drm_gem_prime_fd_to_handle, .gem_prime_export = drm_gem_prime_export, .gem_prime_import = drm_gem_prime_import, .gem_prime_pin = virtgpu_gem_prime_pin, .gem_prime_unpin = virtgpu_gem_prime_unpin, + .gem_prime_get_sg_table = virtgpu_gem_prime_get_sg_table, + .gem_prime_import_sg_table = virtgpu_gem_prime_import_sg_table, .gem_prime_vmap = virtgpu_gem_prime_vmap, .gem_prime_vunmap = virtgpu_gem_prime_vunmap, .gem_prime_mmap = virtgpu_gem_prime_mmap, diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index 3238fdf58eb4..d577cb76f5ad 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -354,6 +354,10 @@ int virtio_gpu_object_wait(struct virtio_gpu_object *bo, bool no_wait); /* virtgpu_prime.c */ int virtgpu_gem_prime_pin(struct drm_gem_object *obj); void virtgpu_gem_prime_unpin(struct drm_gem_object *obj); +struct sg_table *virtgpu_gem_prime_get_sg_table(struct drm_gem_object *obj); +struct drm_gem_object *virtgpu_gem_prime_import_sg_table( + struct drm_device *dev, struct dma_buf_attachment *attach, + struct sg_table *sgt); void *virtgpu_gem_prime_vmap(struct drm_gem_object *obj); void virtgpu_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr); int virtgpu_gem_prime_mmap(struct drm_gem_object *obj, diff --git a/drivers/gpu/drm/virtio/virtgpu_prime.c b/drivers/gpu/drm/virtio/virtgpu_prime.c index c59ec34c80a5..eb51a78e1199 100644 --- a/drivers/gpu/drm/virtio/virtgpu_prime.c +++ b/drivers/gpu/drm/virtio/virtgpu_prime.c @@ -39,6 +39,18 @@ void virtgpu_gem_prime_unpin(struct drm_gem_object *obj) WARN_ONCE(1, "not implemented"); } +struct sg_table *virtgpu_gem_prime_get_sg_table(struct drm_gem_object *obj) +{ + return ERR_PTR(-ENODEV); +} + +struct drm_gem_object *virtgpu_gem_prime_import_sg_table( + struct drm_device *dev, struct dma_buf_attachment *attach, + struct sg_table *table) +{ + return ERR_PTR(-ENODEV); +} + void *virtgpu_gem_prime_vmap(struct drm_gem_object *obj) { struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(obj); -- cgit v1.2.3-55-g7522 From 66c031716bcd9647cd2304e4875163663b086405 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 23 Apr 2019 15:30:07 +0100 Subject: net: atheros: fix spelling mistake "underun" -> "underrun" There are spelling mistakes in structure elements, fix these. Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- drivers/net/ethernet/atheros/atlx/atl1.c | 4 ++-- drivers/net/ethernet/atheros/atlx/atl1.h | 2 +- drivers/net/ethernet/atheros/atlx/atl2.c | 2 +- drivers/net/ethernet/atheros/atlx/atl2.h | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c index 9e07b469066a..156fbc5601ca 100644 --- a/drivers/net/ethernet/atheros/atlx/atl1.c +++ b/drivers/net/ethernet/atheros/atlx/atl1.c @@ -1721,7 +1721,7 @@ static void atl1_inc_smb(struct atl1_adapter *adapter) adapter->soft_stats.scc += smb->tx_1_col; adapter->soft_stats.mcc += smb->tx_2_col; adapter->soft_stats.latecol += smb->tx_late_col; - adapter->soft_stats.tx_underun += smb->tx_underrun; + adapter->soft_stats.tx_underrun += smb->tx_underrun; adapter->soft_stats.tx_trunc += smb->tx_trunc; adapter->soft_stats.tx_pause += smb->tx_pause; @@ -3179,7 +3179,7 @@ static struct atl1_stats atl1_gstrings_stats[] = { {"tx_deferred_ok", ATL1_STAT(soft_stats.deffer)}, {"tx_single_coll_ok", ATL1_STAT(soft_stats.scc)}, {"tx_multi_coll_ok", ATL1_STAT(soft_stats.mcc)}, - {"tx_underun", ATL1_STAT(soft_stats.tx_underun)}, + {"tx_underrun", ATL1_STAT(soft_stats.tx_underrun)}, {"tx_trunc", ATL1_STAT(soft_stats.tx_trunc)}, {"tx_pause", ATL1_STAT(soft_stats.tx_pause)}, {"rx_pause", ATL1_STAT(soft_stats.rx_pause)}, diff --git a/drivers/net/ethernet/atheros/atlx/atl1.h b/drivers/net/ethernet/atheros/atlx/atl1.h index 34a58cd846a0..eacff19ea05b 100644 --- a/drivers/net/ethernet/atheros/atlx/atl1.h +++ b/drivers/net/ethernet/atheros/atlx/atl1.h @@ -681,7 +681,7 @@ struct atl1_sft_stats { u64 scc; /* packets TX after a single collision */ u64 mcc; /* packets TX after multiple collisions */ u64 latecol; /* TX packets w/ late collisions */ - u64 tx_underun; /* TX packets aborted due to TX FIFO underrun + u64 tx_underrun; /* TX packets aborted due to TX FIFO underrun * or TRD FIFO underrun */ u64 tx_trunc; /* TX packets truncated due to size > MTU */ u64 rx_pause; /* num Pause packets received. */ diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c index d99317b3d891..98da0fa27192 100644 --- a/drivers/net/ethernet/atheros/atlx/atl2.c +++ b/drivers/net/ethernet/atheros/atlx/atl2.c @@ -553,7 +553,7 @@ static void atl2_intr_tx(struct atl2_adapter *adapter) netdev->stats.tx_aborted_errors++; if (txs->late_col) netdev->stats.tx_window_errors++; - if (txs->underun) + if (txs->underrun) netdev->stats.tx_fifo_errors++; } while (1); diff --git a/drivers/net/ethernet/atheros/atlx/atl2.h b/drivers/net/ethernet/atheros/atlx/atl2.h index c64a6bdfa7ae..25ec84cb4853 100644 --- a/drivers/net/ethernet/atheros/atlx/atl2.h +++ b/drivers/net/ethernet/atheros/atlx/atl2.h @@ -260,7 +260,7 @@ struct tx_pkt_status { unsigned multi_col:1; unsigned late_col:1; unsigned abort_col:1; - unsigned underun:1; /* current packet is aborted + unsigned underrun:1; /* current packet is aborted * due to txram underrun */ unsigned:3; /* reserved */ unsigned update:1; /* always 1'b1 in tx_status_buf */ -- cgit v1.2.3-55-g7522 From ffbf9870dcf1342592a1a26f4cf70bda39046134 Mon Sep 17 00:00:00 2001 From: Ilias Apalodimas Date: Tue, 23 Apr 2019 09:01:41 +0300 Subject: net: socionext: replace napi_alloc_frag with the netdev variant on init The netdev variant is usable on any context since it disables interrupts. The napi variant of the call should only be used within softirq context. Replace napi_alloc_frag on driver init with the correct netdev_alloc_frag call Changes since v1: - Adjusted commit message Acked-by: Ard Biesheuvel Acked-by: Jassi Brar Fixes: 4acb20b46214 ("net: socionext: different approach on DMA") Signed-off-by: Ilias Apalodimas Signed-off-by: David S. Miller --- drivers/net/ethernet/socionext/netsec.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index a18149720aa2..cba5881b2746 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -673,7 +673,8 @@ static void netsec_process_tx(struct netsec_priv *priv) } static void *netsec_alloc_rx_data(struct netsec_priv *priv, - dma_addr_t *dma_handle, u16 *desc_len) + dma_addr_t *dma_handle, u16 *desc_len, + bool napi) { size_t total_len = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); size_t payload_len = NETSEC_RX_BUF_SZ; @@ -682,7 +683,7 @@ static void *netsec_alloc_rx_data(struct netsec_priv *priv, total_len += SKB_DATA_ALIGN(payload_len + NETSEC_SKB_PAD); - buf = napi_alloc_frag(total_len); + buf = napi ? napi_alloc_frag(total_len) : netdev_alloc_frag(total_len); if (!buf) return NULL; @@ -765,7 +766,8 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget) /* allocate a fresh buffer and map it to the hardware. * This will eventually replace the old buffer in the hardware */ - buf_addr = netsec_alloc_rx_data(priv, &dma_handle, &desc_len); + buf_addr = netsec_alloc_rx_data(priv, &dma_handle, &desc_len, + true); if (unlikely(!buf_addr)) break; @@ -1069,7 +1071,8 @@ static int netsec_setup_rx_dring(struct netsec_priv *priv) void *buf; u16 len; - buf = netsec_alloc_rx_data(priv, &dma_handle, &len); + buf = netsec_alloc_rx_data(priv, &dma_handle, &len, + false); if (!buf) { netsec_uninit_pkt_dring(priv, NETSEC_RING_RX); goto err_out; -- cgit v1.2.3-55-g7522 From 1c5c12ee308aacf635c8819cd4baa3bd58f8a8b7 Mon Sep 17 00:00:00 2001 From: Tao Ren Date: Wed, 24 Apr 2019 01:43:32 +0000 Subject: net/ncsi: handle overflow when incrementing mac address Previously BMC's MAC address is calculated by simply adding 1 to the last byte of network controller's MAC address, and it produces incorrect result when network controller's MAC address ends with 0xFF. The problem can be fixed by calling eth_addr_inc() function to increment MAC address; besides, the MAC address is also validated before assigning to BMC. Fixes: cb10c7c0dfd9 ("net/ncsi: Add NCSI Broadcom OEM command") Signed-off-by: Tao Ren Acked-by: Jakub Kicinski Acked-by: Samuel Mendoza-Jonas Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 12 ++++++++++++ net/ncsi/ncsi-rsp.c | 6 +++++- 2 files changed, 17 insertions(+), 1 deletion(-) diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index e2f3b21cd72a..aa8bfd6f738c 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -448,6 +448,18 @@ static inline void eth_addr_dec(u8 *addr) u64_to_ether_addr(u, addr); } +/** + * eth_addr_inc() - Increment the given MAC address. + * @addr: Pointer to a six-byte array containing Ethernet address to increment. + */ +static inline void eth_addr_inc(u8 *addr) +{ + u64 u = ether_addr_to_u64(addr); + + u++; + u64_to_ether_addr(u, addr); +} + /** * is_etherdev_addr - Tell if given Ethernet address belongs to the device. * @dev: Pointer to a device structure diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index dc07fcc7938e..802db01e3075 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -667,7 +668,10 @@ static int ncsi_rsp_handler_oem_bcm_gma(struct ncsi_request *nr) ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; memcpy(saddr.sa_data, &rsp->data[BCM_MAC_ADDR_OFFSET], ETH_ALEN); /* Increase mac address by 1 for BMC's address */ - saddr.sa_data[ETH_ALEN - 1]++; + eth_addr_inc((u8 *)saddr.sa_data); + if (!is_valid_ether_addr((const u8 *)saddr.sa_data)) + return -ENXIO; + ret = ops->ndo_set_mac_address(ndev, &saddr); if (ret < 0) netdev_warn(ndev, "NCSI: 'Writing mac address to device failed\n"); -- cgit v1.2.3-55-g7522 From 6819e3f6d83a24777813b0d031ebe0861694db5a Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Sat, 20 Apr 2019 12:09:39 +0800 Subject: net: vrf: Fix operation not supported when set vrf mac Vrf device is not able to change mac address now because lack of ndo_set_mac_address. Complete this in case some apps need to do this. Reported-by: Hui Wang Signed-off-by: Miaohe Lin Signed-off-by: David S. Miller --- drivers/net/vrf.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index cd15c32b2e43..9ee4d7402ca2 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -875,6 +875,7 @@ static const struct net_device_ops vrf_netdev_ops = { .ndo_init = vrf_dev_init, .ndo_uninit = vrf_dev_uninit, .ndo_start_xmit = vrf_xmit, + .ndo_set_mac_address = eth_mac_addr, .ndo_get_stats64 = vrf_get_stats64, .ndo_add_slave = vrf_add_slave, .ndo_del_slave = vrf_del_slave, @@ -1274,6 +1275,7 @@ static void vrf_setup(struct net_device *dev) /* default to no qdisc; user can add if desired */ dev->priv_flags |= IFF_NO_QUEUE; dev->priv_flags |= IFF_NO_RX_HANDLER; + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; /* VRF devices do not care about MTU, but if the MTU is set * too low then the ipv4 and ipv6 protocols are disabled -- cgit v1.2.3-55-g7522 From 4b9fc7146249a6e0e3175d0acc033fdcd2bfcb17 Mon Sep 17 00:00:00 2001 From: Zhu Yanjun Date: Wed, 24 Apr 2019 02:56:42 -0400 Subject: net: rds: exchange of 8K and 1M pool Before the commit 490ea5967b0d ("RDS: IB: move FMR code to its own file"), when the dirty_count is greater than 9/10 of max_items of 8K pool, 1M pool is used, Vice versa. After the commit 490ea5967b0d ("RDS: IB: move FMR code to its own file"), the above is removed. When we make the following tests. Server: rds-stress -r 1.1.1.16 -D 1M Client: rds-stress -r 1.1.1.14 -s 1.1.1.16 -D 1M The following will appear. " connecting to 1.1.1.16:4000 negotiated options, tasks will start in 2 seconds Starting up..header from 1.1.1.166:4001 to id 4001 bogus .. tsks tx/s rx/s tx+rx K/s mbi K/s mbo K/s tx us/c rtt us cpu % 1 0 0 0.00 0.00 0.00 0.00 0.00 -1.00 1 0 0 0.00 0.00 0.00 0.00 0.00 -1.00 1 0 0 0.00 0.00 0.00 0.00 0.00 -1.00 1 0 0 0.00 0.00 0.00 0.00 0.00 -1.00 1 0 0 0.00 0.00 0.00 0.00 0.00 -1.00 ... " So this exchange between 8K and 1M pool is added back. Fixes: commit 490ea5967b0d ("RDS: IB: move FMR code to its own file") Signed-off-by: Zhu Yanjun Acked-by: Santosh Shilimkar Signed-off-by: David S. Miller --- net/rds/ib_fmr.c | 11 +++++++++++ net/rds/ib_rdma.c | 3 --- 2 files changed, 11 insertions(+), 3 deletions(-) diff --git a/net/rds/ib_fmr.c b/net/rds/ib_fmr.c index 31cf37da4510..93c0437e6a5f 100644 --- a/net/rds/ib_fmr.c +++ b/net/rds/ib_fmr.c @@ -44,6 +44,17 @@ struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev, int npages) else pool = rds_ibdev->mr_1m_pool; + if (atomic_read(&pool->dirty_count) >= pool->max_items / 10) + queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10); + + /* Switch pools if one of the pool is reaching upper limit */ + if (atomic_read(&pool->dirty_count) >= pool->max_items * 9 / 10) { + if (pool->pool_type == RDS_IB_MR_8K_POOL) + pool = rds_ibdev->mr_1m_pool; + else + pool = rds_ibdev->mr_8k_pool; + } + ibmr = rds_ib_try_reuse_ibmr(pool); if (ibmr) return ibmr; diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index 63c8d107adcf..d664e9ade74d 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -454,9 +454,6 @@ struct rds_ib_mr *rds_ib_try_reuse_ibmr(struct rds_ib_mr_pool *pool) struct rds_ib_mr *ibmr = NULL; int iter = 0; - if (atomic_read(&pool->dirty_count) >= pool->max_items_soft / 10) - queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10); - while (1) { ibmr = rds_ib_reuse_mr(pool); if (ibmr) -- cgit v1.2.3-55-g7522 From 52fb56f7b5a9cc23a07b2c237bad91180263a492 Mon Sep 17 00:00:00 2001 From: Dan Murphy Date: Tue, 23 Apr 2019 15:00:24 -0500 Subject: MAINTAINERS: LEDs: Add designated reviewer for LED subsystem Add a designated reviewer for the LED subsystem as there are already two maintainers assigned. Signed-off-by: Dan Murphy Acked-by: Pavel Machek Signed-off-by: Jacek Anaszewski --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index e17ebf70b548..d11bc7a44294 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8698,6 +8698,7 @@ F: scripts/leaking_addresses.pl LED SUBSYSTEM M: Jacek Anaszewski M: Pavel Machek +R: Dan Murphy L: linux-leds@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/j.anaszewski/linux-leds.git S: Maintained -- cgit v1.2.3-55-g7522 From 032be5f19a94de51093851757089133dcc1e92aa Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 24 Apr 2019 09:44:11 -0700 Subject: rxrpc: fix race condition in rxrpc_input_packet() After commit 5271953cad31 ("rxrpc: Use the UDP encap_rcv hook"), rxrpc_input_packet() is directly called from lockless UDP receive path, under rcu_read_lock() protection. It must therefore use RCU rules : - udp_sk->sk_user_data can be cleared at any point in this function. rcu_dereference_sk_user_data() is what we need here. - Also, since sk_user_data might have been set in rxrpc_open_socket() we must observe a proper RCU grace period before kfree(local) in rxrpc_lookup_local() v4: @local can be NULL in xrpc_lookup_local() as reported by kbuild test robot and Julia Lawall , thanks ! v3,v2 : addressed David Howells feedback, thanks ! syzbot reported : kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] PREEMPT SMP KASAN CPU: 0 PID: 19236 Comm: syz-executor703 Not tainted 5.1.0-rc6 #79 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__lock_acquire+0xbef/0x3fb0 kernel/locking/lockdep.c:3573 Code: 00 0f 85 a5 1f 00 00 48 81 c4 10 01 00 00 5b 41 5c 41 5d 41 5e 41 5f 5d c3 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 <80> 3c 02 00 0f 85 4a 21 00 00 49 81 7d 00 20 54 9c 89 0f 84 cf f4 RSP: 0018:ffff88809d7aef58 EFLAGS: 00010002 RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000026 RSI: 0000000000000000 RDI: 0000000000000001 RBP: ffff88809d7af090 R08: 0000000000000001 R09: 0000000000000001 R10: ffffed1015d05bc7 R11: ffff888089428600 R12: 0000000000000000 R13: 0000000000000130 R14: 0000000000000001 R15: 0000000000000001 FS: 00007f059044d700(0000) GS:ffff8880ae800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000004b6040 CR3: 00000000955ca000 CR4: 00000000001406f0 Call Trace: lock_acquire+0x16f/0x3f0 kernel/locking/lockdep.c:4211 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline] _raw_spin_lock_irqsave+0x95/0xcd kernel/locking/spinlock.c:152 skb_queue_tail+0x26/0x150 net/core/skbuff.c:2972 rxrpc_reject_packet net/rxrpc/input.c:1126 [inline] rxrpc_input_packet+0x4a0/0x5536 net/rxrpc/input.c:1414 udp_queue_rcv_one_skb+0xaf2/0x1780 net/ipv4/udp.c:2011 udp_queue_rcv_skb+0x128/0x730 net/ipv4/udp.c:2085 udp_unicast_rcv_skb.isra.0+0xb9/0x360 net/ipv4/udp.c:2245 __udp4_lib_rcv+0x701/0x2ca0 net/ipv4/udp.c:2301 udp_rcv+0x22/0x30 net/ipv4/udp.c:2482 ip_protocol_deliver_rcu+0x60/0x8f0 net/ipv4/ip_input.c:208 ip_local_deliver_finish+0x23b/0x390 net/ipv4/ip_input.c:234 NF_HOOK include/linux/netfilter.h:289 [inline] NF_HOOK include/linux/netfilter.h:283 [inline] ip_local_deliver+0x1e9/0x520 net/ipv4/ip_input.c:255 dst_input include/net/dst.h:450 [inline] ip_rcv_finish+0x1e1/0x300 net/ipv4/ip_input.c:413 NF_HOOK include/linux/netfilter.h:289 [inline] NF_HOOK include/linux/netfilter.h:283 [inline] ip_rcv+0xe8/0x3f0 net/ipv4/ip_input.c:523 __netif_receive_skb_one_core+0x115/0x1a0 net/core/dev.c:4987 __netif_receive_skb+0x2c/0x1c0 net/core/dev.c:5099 netif_receive_skb_internal+0x117/0x660 net/core/dev.c:5202 napi_frags_finish net/core/dev.c:5769 [inline] napi_gro_frags+0xade/0xd10 net/core/dev.c:5843 tun_get_user+0x2f24/0x3fb0 drivers/net/tun.c:1981 tun_chr_write_iter+0xbd/0x156 drivers/net/tun.c:2027 call_write_iter include/linux/fs.h:1866 [inline] do_iter_readv_writev+0x5e1/0x8e0 fs/read_write.c:681 do_iter_write fs/read_write.c:957 [inline] do_iter_write+0x184/0x610 fs/read_write.c:938 vfs_writev+0x1b3/0x2f0 fs/read_write.c:1002 do_writev+0x15e/0x370 fs/read_write.c:1037 __do_sys_writev fs/read_write.c:1110 [inline] __se_sys_writev fs/read_write.c:1107 [inline] __x64_sys_writev+0x75/0xb0 fs/read_write.c:1107 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe Fixes: 5271953cad31 ("rxrpc: Use the UDP encap_rcv hook") Signed-off-by: Eric Dumazet Reported-by: syzbot Acked-by: David Howells Signed-off-by: David S. Miller --- net/rxrpc/input.c | 12 ++++++++---- net/rxrpc/local_object.c | 3 ++- 2 files changed, 10 insertions(+), 5 deletions(-) diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 4c6f9d0a00e7..c2c35cf4e308 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -1161,19 +1161,19 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb) * handle data received on the local endpoint * - may be called in interrupt context * - * The socket is locked by the caller and this prevents the socket from being - * shut down and the local endpoint from going away, thus sk_user_data will not - * be cleared until this function returns. + * [!] Note that as this is called from the encap_rcv hook, the socket is not + * held locked by the caller and nothing prevents sk_user_data on the UDP from + * being cleared in the middle of processing this function. * * Called with the RCU read lock held from the IP layer via UDP. */ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) { + struct rxrpc_local *local = rcu_dereference_sk_user_data(udp_sk); struct rxrpc_connection *conn; struct rxrpc_channel *chan; struct rxrpc_call *call = NULL; struct rxrpc_skb_priv *sp; - struct rxrpc_local *local = udp_sk->sk_user_data; struct rxrpc_peer *peer = NULL; struct rxrpc_sock *rx = NULL; unsigned int channel; @@ -1181,6 +1181,10 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) _enter("%p", udp_sk); + if (unlikely(!local)) { + kfree_skb(skb); + return 0; + } if (skb->tstamp == 0) skb->tstamp = ktime_get_real(); diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 15cf42d5b53a..01959db51445 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -304,7 +304,8 @@ nomem: ret = -ENOMEM; sock_error: mutex_unlock(&rxnet->local_mutex); - kfree(local); + if (local) + call_rcu(&local->rcu, rxrpc_local_rcu); _leave(" = %d", ret); return ERR_PTR(ret); -- cgit v1.2.3-55-g7522 From 0453c682459583910d611a96de928f4442205493 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 24 Apr 2019 05:35:00 -0700 Subject: net/rose: fix unbound loop in rose_loopback_timer() This patch adds a limit on the number of skbs that fuzzers can queue into loopback_queue. 1000 packets for rose loopback seems more than enough. Then, since we now have multiple cpus in most linux hosts, we also need to limit the number of skbs rose_loopback_timer() can dequeue at each round. rose_loopback_queue() can be drop-monitor friendly, calling consume_skb() or kfree_skb() appropriately. Finally, use mod_timer() instead of del_timer() + add_timer() syzbot report was : rcu: INFO: rcu_preempt self-detected stall on CPU rcu: 0-...!: (10499 ticks this GP) idle=536/1/0x4000000000000002 softirq=103291/103291 fqs=34 rcu: (t=10500 jiffies g=140321 q=323) rcu: rcu_preempt kthread starved for 10426 jiffies! g140321 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x402 ->cpu=1 rcu: RCU grace-period kthread stack dump: rcu_preempt I29168 10 2 0x80000000 Call Trace: context_switch kernel/sched/core.c:2877 [inline] __schedule+0x813/0x1cc0 kernel/sched/core.c:3518 schedule+0x92/0x180 kernel/sched/core.c:3562 schedule_timeout+0x4db/0xfd0 kernel/time/timer.c:1803 rcu_gp_fqs_loop kernel/rcu/tree.c:1971 [inline] rcu_gp_kthread+0x962/0x17b0 kernel/rcu/tree.c:2128 kthread+0x357/0x430 kernel/kthread.c:253 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:352 NMI backtrace for cpu 0 CPU: 0 PID: 7632 Comm: kworker/0:4 Not tainted 5.1.0-rc5+ #172 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: events iterate_cleanup_work Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 nmi_cpu_backtrace.cold+0x63/0xa4 lib/nmi_backtrace.c:101 nmi_trigger_cpumask_backtrace+0x1be/0x236 lib/nmi_backtrace.c:62 arch_trigger_cpumask_backtrace+0x14/0x20 arch/x86/kernel/apic/hw_nmi.c:38 trigger_single_cpu_backtrace include/linux/nmi.h:164 [inline] rcu_dump_cpu_stacks+0x183/0x1cf kernel/rcu/tree.c:1223 print_cpu_stall kernel/rcu/tree.c:1360 [inline] check_cpu_stall kernel/rcu/tree.c:1434 [inline] rcu_pending kernel/rcu/tree.c:3103 [inline] rcu_sched_clock_irq.cold+0x500/0xa4a kernel/rcu/tree.c:2544 update_process_times+0x32/0x80 kernel/time/timer.c:1635 tick_sched_handle+0xa2/0x190 kernel/time/tick-sched.c:161 tick_sched_timer+0x47/0x130 kernel/time/tick-sched.c:1271 __run_hrtimer kernel/time/hrtimer.c:1389 [inline] __hrtimer_run_queues+0x33e/0xde0 kernel/time/hrtimer.c:1451 hrtimer_interrupt+0x314/0x770 kernel/time/hrtimer.c:1509 local_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1035 [inline] smp_apic_timer_interrupt+0x120/0x570 arch/x86/kernel/apic/apic.c:1060 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:807 RIP: 0010:__sanitizer_cov_trace_pc+0x0/0x50 kernel/kcov.c:95 Code: 89 25 b4 6e ec 08 41 bc f4 ff ff ff e8 cd 5d ea ff 48 c7 05 9e 6e ec 08 00 00 00 00 e9 a4 e9 ff ff 90 90 90 90 90 90 90 90 90 <55> 48 89 e5 48 8b 75 08 65 48 8b 04 25 00 ee 01 00 65 8b 15 c8 60 RSP: 0018:ffff8880ae807ce0 EFLAGS: 00000286 ORIG_RAX: ffffffffffffff13 RAX: ffff88806fd40640 RBX: dffffc0000000000 RCX: ffffffff863fbc56 RDX: 0000000000000100 RSI: ffffffff863fbc1d RDI: ffff88808cf94228 RBP: ffff8880ae807d10 R08: ffff88806fd40640 R09: ffffed1015d00f8b R10: ffffed1015d00f8a R11: 0000000000000003 R12: ffff88808cf941c0 R13: 00000000fffff034 R14: ffff8882166cd840 R15: 0000000000000000 rose_loopback_timer+0x30d/0x3f0 net/rose/rose_loopback.c:91 call_timer_fn+0x190/0x720 kernel/time/timer.c:1325 expire_timers kernel/time/timer.c:1362 [inline] __run_timers kernel/time/timer.c:1681 [inline] __run_timers kernel/time/timer.c:1649 [inline] run_timer_softirq+0x652/0x1700 kernel/time/timer.c:1694 __do_softirq+0x266/0x95a kernel/softirq.c:293 do_softirq_own_stack+0x2a/0x40 arch/x86/entry/entry_64.S:1027 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- net/rose/rose_loopback.c | 27 ++++++++++++++++----------- 1 file changed, 16 insertions(+), 11 deletions(-) diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c index 7af4f99c4a93..094a6621f8e8 100644 --- a/net/rose/rose_loopback.c +++ b/net/rose/rose_loopback.c @@ -16,6 +16,7 @@ #include static struct sk_buff_head loopback_queue; +#define ROSE_LOOPBACK_LIMIT 1000 static struct timer_list loopback_timer; static void rose_set_loopback_timer(void); @@ -35,29 +36,27 @@ static int rose_loopback_running(void) int rose_loopback_queue(struct sk_buff *skb, struct rose_neigh *neigh) { - struct sk_buff *skbn; + struct sk_buff *skbn = NULL; - skbn = skb_clone(skb, GFP_ATOMIC); + if (skb_queue_len(&loopback_queue) < ROSE_LOOPBACK_LIMIT) + skbn = skb_clone(skb, GFP_ATOMIC); - kfree_skb(skb); - - if (skbn != NULL) { + if (skbn) { + consume_skb(skb); skb_queue_tail(&loopback_queue, skbn); if (!rose_loopback_running()) rose_set_loopback_timer(); + } else { + kfree_skb(skb); } return 1; } - static void rose_set_loopback_timer(void) { - del_timer(&loopback_timer); - - loopback_timer.expires = jiffies + 10; - add_timer(&loopback_timer); + mod_timer(&loopback_timer, jiffies + 10); } static void rose_loopback_timer(struct timer_list *unused) @@ -68,8 +67,12 @@ static void rose_loopback_timer(struct timer_list *unused) struct sock *sk; unsigned short frametype; unsigned int lci_i, lci_o; + int count; - while ((skb = skb_dequeue(&loopback_queue)) != NULL) { + for (count = 0; count < ROSE_LOOPBACK_LIMIT; count++) { + skb = skb_dequeue(&loopback_queue); + if (!skb) + return; if (skb->len < ROSE_MIN_LEN) { kfree_skb(skb); continue; @@ -106,6 +109,8 @@ static void rose_loopback_timer(struct timer_list *unused) kfree_skb(skb); } } + if (!skb_queue_empty(&loopback_queue)) + mod_timer(&loopback_timer, jiffies + 1); } void __exit rose_loopback_clear(void) -- cgit v1.2.3-55-g7522 From 20ff83f10f113c88d0bb74589389b05250994c16 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 24 Apr 2019 08:04:05 -0700 Subject: ipv4: add sanity checks in ipv4_link_failure() Before calling __ip_options_compile(), we need to ensure the network header is a an IPv4 one, and that it is already pulled in skb->head. RAW sockets going through a tunnel can end up calling ipv4_link_failure() with total garbage in the skb, or arbitrary lengthes. syzbot report : BUG: KASAN: stack-out-of-bounds in memcpy include/linux/string.h:355 [inline] BUG: KASAN: stack-out-of-bounds in __ip_options_echo+0x294/0x1120 net/ipv4/ip_options.c:123 Write of size 69 at addr ffff888096abf068 by task syz-executor.4/9204 CPU: 0 PID: 9204 Comm: syz-executor.4 Not tainted 5.1.0-rc5+ #77 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:187 kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317 check_memory_region_inline mm/kasan/generic.c:185 [inline] check_memory_region+0x123/0x190 mm/kasan/generic.c:191 memcpy+0x38/0x50 mm/kasan/common.c:133 memcpy include/linux/string.h:355 [inline] __ip_options_echo+0x294/0x1120 net/ipv4/ip_options.c:123 __icmp_send+0x725/0x1400 net/ipv4/icmp.c:695 ipv4_link_failure+0x29f/0x550 net/ipv4/route.c:1204 dst_link_failure include/net/dst.h:427 [inline] vti6_xmit net/ipv6/ip6_vti.c:514 [inline] vti6_tnl_xmit+0x10d4/0x1c0c net/ipv6/ip6_vti.c:553 __netdev_start_xmit include/linux/netdevice.h:4414 [inline] netdev_start_xmit include/linux/netdevice.h:4423 [inline] xmit_one net/core/dev.c:3292 [inline] dev_hard_start_xmit+0x1b2/0x980 net/core/dev.c:3308 __dev_queue_xmit+0x271d/0x3060 net/core/dev.c:3878 dev_queue_xmit+0x18/0x20 net/core/dev.c:3911 neigh_direct_output+0x16/0x20 net/core/neighbour.c:1527 neigh_output include/net/neighbour.h:508 [inline] ip_finish_output2+0x949/0x1740 net/ipv4/ip_output.c:229 ip_finish_output+0x73c/0xd50 net/ipv4/ip_output.c:317 NF_HOOK_COND include/linux/netfilter.h:278 [inline] ip_output+0x21f/0x670 net/ipv4/ip_output.c:405 dst_output include/net/dst.h:444 [inline] NF_HOOK include/linux/netfilter.h:289 [inline] raw_send_hdrinc net/ipv4/raw.c:432 [inline] raw_sendmsg+0x1d2b/0x2f20 net/ipv4/raw.c:663 inet_sendmsg+0x147/0x5d0 net/ipv4/af_inet.c:798 sock_sendmsg_nosec net/socket.c:651 [inline] sock_sendmsg+0xdd/0x130 net/socket.c:661 sock_write_iter+0x27c/0x3e0 net/socket.c:988 call_write_iter include/linux/fs.h:1866 [inline] new_sync_write+0x4c7/0x760 fs/read_write.c:474 __vfs_write+0xe4/0x110 fs/read_write.c:487 vfs_write+0x20c/0x580 fs/read_write.c:549 ksys_write+0x14f/0x2d0 fs/read_write.c:599 __do_sys_write fs/read_write.c:611 [inline] __se_sys_write fs/read_write.c:608 [inline] __x64_sys_write+0x73/0xb0 fs/read_write.c:608 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x458c29 Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f293b44bc78 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000458c29 RDX: 0000000000000014 RSI: 00000000200002c0 RDI: 0000000000000003 RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f293b44c6d4 R13: 00000000004c8623 R14: 00000000004ded68 R15: 00000000ffffffff The buggy address belongs to the page: page:ffffea00025aafc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 flags: 0x1fffc0000000000() raw: 01fffc0000000000 0000000000000000 ffffffff025a0101 0000000000000000 raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888096abef80: 00 00 00 f2 f2 f2 f2 f2 00 00 00 00 00 00 00 f2 ffff888096abf000: f2 f2 f2 f2 00 00 00 00 00 00 00 00 00 00 00 00 >ffff888096abf080: 00 00 f3 f3 f3 f3 00 00 00 00 00 00 00 00 00 00 ^ ffff888096abf100: 00 00 00 00 f1 f1 f1 f1 00 00 f3 f3 00 00 00 00 ffff888096abf180: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 Fixes: ed0de45a1008 ("ipv4: recompile ip options in ipv4_link_failure") Signed-off-by: Eric Dumazet Cc: Stephen Suryaputra Acked-by: Willem de Bruijn Signed-off-by: David S. Miller --- net/ipv4/route.c | 32 +++++++++++++++++++++++--------- 1 file changed, 23 insertions(+), 9 deletions(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 88ce038dd495..6fdf1c195d8e 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1183,25 +1183,39 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) return dst; } -static void ipv4_link_failure(struct sk_buff *skb) +static void ipv4_send_dest_unreach(struct sk_buff *skb) { struct ip_options opt; - struct rtable *rt; int res; /* Recompile ip options since IPCB may not be valid anymore. + * Also check we have a reasonable ipv4 header. */ - memset(&opt, 0, sizeof(opt)); - opt.optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr); + if (!pskb_network_may_pull(skb, sizeof(struct iphdr)) || + ip_hdr(skb)->version != 4 || ip_hdr(skb)->ihl < 5) + return; - rcu_read_lock(); - res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); - rcu_read_unlock(); + memset(&opt, 0, sizeof(opt)); + if (ip_hdr(skb)->ihl > 5) { + if (!pskb_network_may_pull(skb, ip_hdr(skb)->ihl * 4)) + return; + opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); - if (res) - return; + rcu_read_lock(); + res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); + rcu_read_unlock(); + if (res) + return; + } __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt); +} + +static void ipv4_link_failure(struct sk_buff *skb) +{ + struct rtable *rt; + + ipv4_send_dest_unreach(skb); rt = skb_rtable(skb); if (rt) -- cgit v1.2.3-55-g7522